نشریه ماشین های کشاورزی
سال دهم شماره 2 (پیاپی 20، نیمسال دوم 1399)

The annually production of cattle manure is estimated around six million tons in Iran. Manure transportation with high moisture and low density recognized as crucial issue. The densification of dry or wet manure is the profound method for decreasing the manure volume which reduces the cost of handling and storage. Besides, the particle size is one of the important factors in the pellet production. Ball mills, vibratory mills, hammer mills, knife mills, two roll mills, colloid mills, attrition mills, or extruders can be used for size reduction of biomass. Specific energy consumption for size reduction of biomass highly depends on moisture content, bulk and particle densities, feed rate of the material, particle size distribution (initial/final particle size) and machine variables. The present study is conducted for wet cattle manure size reduction machine. Furthermore, the relationship between moisture content (35, 40 and 45 %w.b) and drum of special size reduction machine in rotational speed (150, 200 and 250 rpm) considering geometric mean diameter of particle and size distribution of wet cattle manure were investigated. A factorial experiment under randomized complete design method was employed with three replications.

The main parts of machine include drum, concave, spring and adjusting screw. The main function of this thresher machine is to combine crushing and cutting in order to conduct the size reduction methods, i.e., to apply compressive and shear forces to the cattle manure particles. The drum is also equipped with several rows of sharp-edged milling segments. The spring constants were determined by evaluating the slope of the force vs. deflection curves. The rotational speed of drum was changed in the range of 100-700 rpm during these experiments. In the test of the machine physical properties of grinds such as geometric mean diameter of grind particles and particle size distribution were determined. One kg of cattle manure was grinded in each test and the particle size distribution of grinded cattle manure was determined according to ASAE standard S319.3. The moisture content of cattle manure was obtained according to ASAE standard S358.3.

The initial and final particle size of the materials are 20 millimeters and less than 5 millimeters, respectively and the angle of nip is 30 degrees (according to the installation space limitations), the diameter of the drum is 310 millimeters. The spring constant was equal to 24.371 N / mm and on the basis of the experiments a drum speed in the range of 150–250 rpm is considered to be optimal settings for the milling for cattle manure disintegration. The results of Table 4 show that for wet cattle manure with 35% (w.b) moisture content at 250 rpm rotational speed of drum (P > 0.05; Skewness = -0.056; Kurtosis = -2.15), 40% (w.b) moisture content at 250 rpm rotational speed of drum (P > 0.05; Skewness = 0.076; Kurtosis = -1.77), 45% (w.b) moisture content at 200 rpm rotational speed of drum (P > 0.05; Skewness = 0.095; Kurtosis = -1.72), in grinds that would potentially produce better compacts. The geometric mean particle size and standard deviation for each test are shown in Table 2. According to Table (2), the lowest geometric mean of particle size is related to rotational speed of 200 rpm and a moisture content of 45% (w.b), and the highest at rotational speed of 250 rpm and a moisture content of 45% (w.b) can be observed.

The use of cattle manure of thresher machine reduces the specific energy consumption of cattle manure by 92% compared to the conventional method (using drying and hammer mill) in the pellet production.The lowest geometric mean diameter of wet cattle manure was 1.02 millimeter for drum rotational speed of 200 rpm at 45% (w.b) moisture content and the highest was 1.38 at rotational speed of 250 rpm and a moisture content of 45% (w.b%).The best particle size distribution was observed for milling of wet cattle manure with 35% (w.b) moisture content at 250 rpm rotational speed of drum (P> 0.05; Skewness = -0.056; Kurtosis = -2.15), 40% (w.b) moisture content at 250 rpm rotational speed of drum (P> 0.05; Skewness = 0.076; Kurtosis = -1.77), 45% (w.b) moisture content at 200 rpm rotational speed of drum (P> 0.05; Skewness = 0.095; Kurtosis = -1.72)

An olfactory machine system based on eight MOS sensors was designed to detect pure cow ghee from the adulterated with various proportions of vegetable oil and animal fat. Designed system includes data acquisition system, sensors, sensors chamber, sample box, power supply, connections, electric valves, air pump and air filter. The sensor array was consisted of the 8 MOS sensors that each of them react to specific volatile compounds. These sensors are widely used in olfactory machines because of their high chemical stability, high durability, low response to moisture and affordable prices. These are the most commonly used sensors in electronic nose system. To prepare samples with different percentages of adulteration, animal body fat and refined vegetable oils were added to pure cow ghee. In order to carry out the experiments, the sample was placed in sample box and in the baseline correction step (200 seconds), clean air was passed through the sensors to transmit the response of sensor array to steady state. At the injection step (180 seconds), the sample headspace was transmitted and passed through sensors chamber.  Output voltage of each sensor depends on the type of sensor and its sensitivity. At the cleaning step (120 seconds) the clean air was passed through sensors to get the sensor array responsive to a stable state. Also, at this step the pump removed the odor remaining inside the sample container and system was prepared for the next test. The signals obtained from the sensors were recorded and then pre-processed.

An eight-sensory olfactory machine system (MOS) was designed to detect pure cow ghee from the presence of vegetable oil and animal fat oil. In PCA analysis, the variance between samples was 97% and 98%, respectively. According to the results the radar graph of PCA analysis, it can be concluded that the sensors No 2 (TGS822), 3(MQ136), 4(MQ9) and 8(TGS2620) have the highest and sensor 6 (MQ135) has the lowest ability in classification. The MQ135 sensor reacts to the detection of ammonia, benzene, and sulfide. In other words these gases did not play important role in separating of cow ghee from other mixed oils.

Increasing the production efficiency is an important goal in precision farming. The use of precision farming requires a lot of labor work. Also, due to the risk of agricultural operations, it is not recommended to do it directly by humans. Therefore, it is necessary for agricultural operations to be carried out automatically. For this reason, the application of robotics in agricultural environments, especially in the greenhouse, is increasing. The first step in automatic farming is autonomous navigation. For autonomous navigation, a robot must be the ability to understand its environment and recognize its position. In other words, a robot must be able to create a map of an unknown environment, locate itself on this map and finally plane for the path. This problem is solvable by Simultaneous Localization and Mapping (SLAM). The SLAM problem is a recursive estimation process. In the other words, when a robot moves in an unknown environment, mapping and localization errors increase incrementally. To reduce these two errors, a recursive estimation process is used to solve the SLAM problem.

In this research, two webcams, made by Microsoft Corporation with the resolution of 960×544, are connected to the computer via USB2 in order to produce a stereo parallel camera. For this study, we used a greenhouse that was located the Arak, Iran. Before taking stereo images, a camera path was designed in the greenhouse. This path may be either straight or curved. The designed path was implemented in the greenhouse. The entire path traversed by a stereo camera was 32.7 m and 150 stereo images were taken. Graph-SLAM algorithm was used for Simultaneous Localization and Mapping in the greenhouse. Using the ROS framework, the SLAM algorithm was designed with nodes and network for connecting the nodes.

For evaluation, the stereo camera locations, every step was measured manually and compared with the stereo camera locations that were estimated in the graph-SLAM algorithm. The position error was calculated through the Euclidean distance (DE) between the estimated points and the actual points. The results of this study showed that, the proposed algorithm has an average of error 0.0679412, standard deviation of 0.0456431 and root mean square error (RMSE) of 0.0075569 for camera localization.In this research, only a stereo camera was used to prepare a map of the environment, but other researches have used multiple sensor combinations. Another advantage of this research related to others was created a 3D map (point cloud) of the environment and loop closer detection. In the 3D map, in addition to determining the exact location of the plant, the height of the plant can also be estimated. Plant height estimate is important in some agricultural operations such as spot spray, harvesting and pruning.

Due to the risk of agricultural activities, the use of robotics is essential. Autonomous navigation is one of the branches of the robotics. For autonomous navigation, a map of environment and localization in this map is need. The purpose of our research was to provide simultaneous localization and mapping (SLAM) in agricultural environments. ROS is a strong framework for solving the SLAM problem. So that, this problem can be solved by combining different nodes in ROS. The method depended only on the information from the stereo camera because stereo camera provided exact distance information. We believe that this study will contribute to the field of autonomous robot applications in agriculture. In future studies, it is possible to use an actual robot in the greenhouse with various sensors for SLAM and path planning.

Stereo vision is an approach to 3D information from multiple 2D views of a scene. The 3D information can be extracted from a pair image, as known stereo pair by estimating the relative depth of points in the scene.Soil aggregate size distribution is one of the most important issues in the agriculture sector which highly affects energy consumed for preparing the field before planting. Mean weight diameter of clods is a standard metric for determining clod (big aggregates) size. Conventional methods are based on sieving soil samples to calculate the MWD. However, they are faced with several challenges in larger scales and practical applications. Furthermore, due to inherent limitations of soil environment and also being a tedious work, traditional methods would beuse to estimate the metric higher or lower than actual value.As new methods, researchers are using computer vision techniques as virtual sieve so that the size of clods can be determined via processing digital images which have been taken from soil surface. Although, image-based methods have solved many of previous problems, their accuracy is not so high due to the complexity of soil environment and overlapping colds, and needs to be improved. In order to overcome the mentioned challenges, in the current study stereo vision method was developed so that it is possible to extract the third dimension information as height of clods which helps us to categorize clods into their own class.

In this study, the W3-Fujifilm stereo camera equipped with two 10-megapixel CCD sensors for both left and right lenses, and baseline spacing of 7.5 cm was used. The distance between the camera lens and the ground was also set to 60 cm.In order to get three components of soil clods including (x, y, z), point cloud was investigated. For this, local features were extracted using a SIFT feature detector. The SIFT algorithm is robust against scale, rotation and illumination changes, so that these specifications have made it as a strong tool in the field of stereo vision. Then, the extracted features (keypoints) were matched between two stereo pair images by means of Brute Force algorithm and the location of all corresponding points were determined and point cloud was obtained.At the final stage, three features including length, width and height of all six classes of soil clods were entered into a linear classifier entitled discriminant analysis. This classifier as a linear separator classified these six classes based on appropriate functions in a 5 dimensional space.

Results of classification model showed that the height (thickness) of clods have more distinguishing different soil clods. The reason for this refers to the event of overlapping, because most of clods were touched each other after sieving. Consequently, the length and width of clods had not significant effect in soil aggregates classification.In order to analysis the result of soil aggregate classification, confusion matrix was calculated and the overall classification accuracy was achieved 83.7%. The lowest and highest accuracy were obtained for class 1 (the littlest class) and class 6 (the biggest class), respectively due to their low and high height from the soil surface.

In this research, the basic geometrical features including length, width and height were extracted from stereo pair digital images via stereo vision techniques to classify six classes of soil clods. This aim was reached by 3-D reconstruction of image data, so that the height of each image as the third component of (x,y,z) was obtained as well as the length and width. The results of classification indicated that the stereo vision technique had the satisfactory performance in determining the aggregate size distribution which is one of the most important indices for tilled soil quality.

Tillage is a very important operation that influences the growth and productivity of agricultural products. It is necessary to introduce some conditions to improve soil physical properties, aeration, permeability and root development in tillage operations. However, in primary tillage, especially when moldboard ploughs are used, this may be time consuming and costly for researchers to use it in their research. Some researchers use physical experiments to perform the work, which the accuracy of the results is dependent on the measuring instruments precision. However, some other researchers use simulation and mathematical modeling to reduce the time and costs and increase the relative accuracy of the research results. Many studies have also shown that modeling the forces involved in tillage is a good way to estimate the performance of different tillage tools and improve their geometry. However, the key to success in numerical simulation of tillage operations is to simulate the exact instrumentation, based on the correct assumptions as well as the proper methods. The prediction of the forces involved in tillage tools has an important role in their design. Collecting data on the forces involved in tillage tool under different farm conditions is a time consuming and costly task. Therefore, the prediction of a tillage tool forces is very important for the designer and the user in order to achieve better performance of the tool.

In this study, a cylindrical moldboard made by Alpler Company in Turkey was used to simulate the moldboard. A measuring device was designed and constructed to measure the various points of the desired moldboard. Then, the spatial points obtained by the measuring device were presented to the SolidWorks 2016 software and the desired moldboard was modeled. The finite element method by Abacus 2016 was then used to simulate the interaction between soil and moldboard. Treatments used in simulated tillage operations included tillage depths (5, 10, 15, 20 and 25 cm) and forward speed (1, 1.5, 2, 2.5 and 3 millimeters per second). The independent variables were considered as tensile, vertical and lateral forces (Kilo newton). After simulating the tillage operations, tensile, vertical and lateral forces were obtained. These forces were modeled using response surface and artificial neural networks techniques. Then, the obtained models were compared using R2, RMSE and MRDM statistical indices and the best model was selected.

When using the response surface method, the quadratic model was selected by using the maximum value of the statistical indices R2, R2a and R2p, among the linear, two-factor and quadratic models. Then, the significance of model variables was evaluated by using variance analysis. The forces were also modeled by using the neural network method. According to the fitting curves and statistical indices of R2, RMSE and MRDM for the tensile, vertical and lateral forces, it is revealed that both methods could well predict the forces but artificial neural network was more suitable than the response surface method. Moreover, by investigating the interactions of tillage treatments and forward speed on the forces in this research, it was observed that by increasing the depth of tillage and velocity, tensile, vertical and lateral forces were increased nonlinearly by 66.55%, 68.47%, and 64.76%, respectively.

Regarding all the results obtained from this study, it can be concluded that the developed models using the artificial neural network in this research was a good and powerful tool for predicting the forces involved in moldboard ploughs both in the field operations and in related studies. It is also recommended that the developed models in this study can be used to manage the tillage operations, such as selecting the proper tractor. However, it is also suggested that other affecting factors, such as moldboard angles, should be included in future models to increase the ability of the model to predict the forces involved in moldboard plows.

The most costly part of poultry breeding is feeding. Due to the noticeable developments in animal husbandry and agricultural sectors, it is necessary to use the mechanized methods to reduce the casualties, increase the productivity as well as reduce the time and cost in each of these sectors. Reducing the particle size is one of the ways to process cereals which improves the mixing and also the nutritional value of the feed and the quality of the pellet feed. Optimizing the performance of hammer mill with the aim of reducing the size of different materials for poultry feed, would be very beneficial for obtaining the minimum cost of food, maximum quality and capacity. The main objective of this research was to optimize the operational variables, including sieve size, grain moisture content, feed rate and the number of hammers, each of them at three levels, on a hammer mill during the process of poultry food production from wheat, corn, barley and soybean grains.

The seeds used in experiments were wheat (Azar2 variety), corn (Brazilian variety), soybean (Danpars variety) and barley (Aras variety). A laboratory hammer mill was used to perform experiments. The treatments including sieve diameter (2, 2.3and 4.4 mm), grain moisture content (10, 14 and 18%), seed input rate to milling compartments (one-third, two-thirds and fully openness of tank gate) and the number of hammer (12, 18 and 24) were investigated. In order to measure the working capacity of the hammer mill, the required time for milling was recorded. The amount of final milled crop in each experiment was weighed and divided into the needed time for milling. Sieve analysis was used to determine the distribution and dispersion of the milled material which works according to the standard of ASTM E-11-70 Part 41 (Anonymous, 2004). In this study, the effects of input variables were investigated using the response surface method focusing on the central composite design approach to optimize the fineness degree and working capacity of the mill. The Design Expert 8.0.6 software was applied for statistical analysis, modeling and optimization.

The results indicated that sieve size and the number of hammers have been affected by the fineness degree of wheat grains, significantly. In addition, all four factors and interaction effects between sieve size and moisture content and also moisture content and number of hammers influential working capacity at the significant level of 1%. In the case of corn, the influence of moisture content and its interaction with sieve size on grain fineness, and the effect of sieve size, moisture content, feed rate and interactions between sieve size and moisture content and moisture content and feed rate of working capacity were significant at the level of 1%. For barley, moisture content at the level of 1% and interaction between sieve size and moisture content at the probability level of 5% were effective on barley fineness degree. Meanwhile, the moisture content at the level of 1% and sieve size and its interaction with moisture content at the level of 5% influenced working capacity, significantly. Soybeans were not able to respond the required moisture level for the experiments due to their soft and brittle texture, whereas unreliable results were obtained by changing its moisture levels. The best size of sieve holes, grain moisture content, feed rate and the number of hammers were determined to minimize the fineness degree and maximize the working capacity of the hammer mill.

In this research, the response surface method considering a central composite design was used to optimize the operational variables of a hammer mill, including sieve hole size, grain moisture, feed rate and the number of hammer to produce poultry feed with the aim of achieving a minimum fineness degree (more grain crushing) and maximum milling capacity. The results of variance analysis were presented for wheat, corn, barley and soybean. Regression models could represent the relationship between the independent variables and the outputs with high confidence coefficient, and the best values of input variables were determined to optimize grinding operation.

Dracocephalum moldavica L. is an annual plant with blue or white flowers and fragrant leaves which belongs to the family of Lamiaceae with the height of up to 80 cm. This plant is native to Central Asia and is accepted in Central and Eastern Europe. In Iran, it is mainly grown in the province of West Azarbaijan and the Alborz Mountains. The essential oils and extracts derived from the secondary metabolisms which are mainly used in the pharmaceutical industry, dietary, cosmetic, flavoring and also as tea and beverage with sugar or honey. The liquid extract of the herb contains a high percentage of water, which should evaporate to increase shelf-life, easy transport, handling and storage, the ease of standardization and preservation of the product quality. On the other hand, the active compounds of the extracts are affected by temperature, oxygen, light and enzymes. Therefore, because of the uses and benefits of herbal extracts, they need to be dried by a practical and effective method like spray drying. In literature still there are no studies taking into account to the comparisons between RSM and TOPSIS as two important optimization methods. So, as the main objective of the present work, the effects of moisture content, drying performance, total phenol content, total flavonoid content and antioxidant activity have been surveyed. Finally, the optimal point of each process variable was presented by two optimization methods.

Aerial parts of Moldavian balm plant were cleaned and drying of plant was carried out under shade and thin layer conditions. The extraction of Moldavian balm was obtained by maceration method using ethanol 50 % (v/v), plant to solvent ratio of 1/10 (w/v). After 48h, the extract was concentrated in a rotary evaporator (Buchi Rotavapor R-205, Switzerland) to obtain a solid concentration of 6%. The used carrier was: Maltodextrin and apple pectin. Different ratios of carrier were prepared, then the ratio was added to distilled water and stirred by a magnetic stirrer. Finally, the solution was mixed with extract. The drying of Moldavian Balm plant extract was performed using a spray-dryer (Büchi B-191, Switzerland) with co-current flow regime. The powders provided by the spray drying were stored in refrigerator until they were needed for the experiment.

The results of variance analysis showed that the Box-Behnken design with the second-order model has led to the meaningfulness of the model, insignificant of the Lack of Fit and the appropriate correlation coefficient for each of the responses. A total number of 15 experiments were conducted to investigate the effect of process variables such as inlet air temperature, compressed air flow rate and concentration of carriers on moisture content, drying performance, total phenolic content, total flavonoid content and antioxidant activity of  Moldavian balm powder. Inlet air temperature and compressed air flow rate had the most significant effect on moisture content and drying performance, while Chemical properties of the powder affected by changing the concentration of carriers.
Optimization parameters of the spray drying process was performed using surface response and TOPSIS methods. The optimum predicted conditions in the response surface method and TOPSIS method were obtained at inlet air temperature, compressed air flow rate and concentration of carrier (152.5-150°C), (8.046-7.5 lit min-1) and 20%, respectively.

By comparing two methods, it can be concluded that although they could provide the same optimum points, the RSM is more efficient. Because RSM offers a mathematical model that can be used at any desired point of variables to predict the output quantities as well as describing the process trend, while TOPSIS method is unable to predict the process trend and only provides the ranking of alternatives.

Introduction:

 Controlling greenhouse microclimate not only influences the growth of plants, but is also critical in the spread of diseases inside the greenhouse. The microclimate parameters are inside air, roof, crop and soil temperature, relative humidity, light intensity, and carbon dioxide concentration. Predicting the microclimate conditions inside a greenhouse and enabling the use of automatic control systems are the two main objectives of greenhouse climate model. The microclimate inside a greenhouse can be predicted by conducting experiments or by using simulation. Static and dynamic models and also artificial neural networks (ANNs) are used for this purpose as a function of the metrological conditions and the parameters of the greenhouse components. Usually thermal simulation has a lot of problems to predict the inside climate of greenhouse and the error of simulation is higher in literature. So the main objective of this paper is comparison between two types of artificial neural networks (MLP and RBF) for prediction 4 inside variables in an even-span glass greenhouse and help the development of simulation science in estimating the inside variables of intelligent greenhouses. 

Materials and Methods:

 In this research, different sensors were used for collecting the temperature, radiation, humidity and wind data. These sensors were used in different positions inside the greenhouse. After collecting the data, two types of ANNs were used with LM and Br training algorithms for predicting the inside variables in an even-span glass greenhouse in Mollasani, Ahvaz. MLP is a feed-forward layered network with one input layer, one output layer, and some hidden layers. Every node computes a weighted sum of its inputs and passes the sum through a soft nonlinearity. The soft nonlinearity or activity function of neurons should be non-decreasing and differentiable. One type of ANN is the radial basis function (RBF) neural network which uses radial basis functions as activation functions. An RBF has a single hidden layer. Each node of the hidden layer has a parameter vector called center. This center is used to compare with the network input vector to produce a radially symmetrical response. Responses of the hidden layer are scaled by the connection weights of the output layer and then combined to produce the network output. There are many types of cross-validation, such as repeated random sub-sampling validation, K-fold cross-validation, K×2 cross-validation, leave-one-out cross-validation and so on. In this study, we pick up K-fold cross- validation for selecting parameters of model. The K-fold cross-validation is a technique of dividing the original sample randomly into K sub-samples. Different performance criteria have been used in the literature to assess model’s predictive ability. The mean absolute percentage error (MAPE), root means square error (RMSE) and coefficient of determination (R2 ) are selected to evaluate the forecast accuracy of the models in this study.

Results and Discussion:

 The results of neural network optimization models with different networks, dependent on the initial random values of the synaptic weights. Thus, the results in general will not be the same in two different trials, even if the same training data have been used. Therefore, in this research K-fold cross validation was used and different data samples were made for train and test of ANN models. The results showed that Trainlm for both of MLP and RBF models has the lower error than Trainbr. Also MLP and RBF were trained with 40 and 80% of total data and results indicated that RBF has the lowest sensitivity to the size data. Comparison between RBF and MLP model showed that, RBF has the lowest error for prediction all the inside variables in the greenhouse (Ta, Tp, Tri, Rha). In this paper, we tried to indicate the fact that innovative methods are simpler and more accurate than physical heat and mass transfer method to predict the environment changes. Moreover, this method can use to predict other changes in greenhouse such as final yield, evapotranspiration, humidity, cracking on the fruit, CO2 emission and so on. So the future research will focus on the other soft computing models such as ANFIS, GPR, Time Series and select the best one for modeling and finally online control of greenhouse in all climate and different environment.

Conclusions:

 This research presents a comparison between two models of Artificial Neural Network (RBF-MLP) to predict 4 inside variables (Ta, Tp, Tri, Rha) in an even-span glass greenhouse. Comparison of the models indicated that RBF has lower error. The range of RMSE and MAPE factors for RBF model to predict all inside variables were between 0.25-0.55 and 0.60-1.10, respectively. Besides the results showed that RBF model can estimate all the inside variables with small size of data for training. Such forecasts can be used by farmers as an appropriate advanced notice for changes in temperatures. Thus, they can apply preventative measures to avoid damage caused by extreme temperatures. More specifically, predicting a greenhouse temperature can not only provide a basis for greenhouse environmental management decisions that can reduce the planting risks, but also could be as a basic research for the feedback-feed-forward type of climate control strategy.

Corn harvest losses are imposed by several factors, the most important of which is harvesting-time. Since the harvesting-time is coincident with the rainy season, it is necessary to appropriately estimate the corn harvest time to avoid harvesting losses and losing the next cultivation. Accordingly, in the current research, the effect of harvesting-time on corn losses during the month and the day has been into consideration. An expert fuzzy system was designed to predict the best harvest time as it operates based on the losses amounts which are measured in processing and collection units into the combine, and losses due to the humidity percentage.

In this paper, corn harvest losses in a John Deere Combine, Model 1165, was studied in a different climatic circumstance in Moghan region. Moreover, a split plot experiment in a completely randomized block design was conducted with three replications. The losses data were collected from the processing and collection units of the combine harvester on the November 5th, 8th and 11th, 2017, in three different daily times of 8-10, 11-13 and 14-16 with three replications. The Mamdani fuzzy inference system with singleton fuzzifire and center average defuzzifire‎ was used to develop a fuzzy expert system.  In the designed expert system, the losses percentage in the processing and collection units and ‎the humidity percentage were considered as system inputs and optimal harvesting time was used as the system output. "Low, Very low, high and very ‎high" and "‏Best, Suitable, Unfit, and Worst" were four groups of linguistic variables for input and output parameters, respectively. These variables follow the triangular and trapezoidal membership functions. The number of 64 fuzzy rules were considered and introduced into the fuzzy system by experts, experienced farmers, and combiners. Furthermore, the same field data (measured data) were applied to evaluate the designed system, so that the predicted value was accounted as the system output.

Analysis of variance showed that there was a significant difference between the harvesting dates at the 0.05 probability level and significant difference between the harvesting times of a day at the 0.01 probability level. It can be concluded that the harvest dates and harvest times of a day were very effective in the number of corn losses, but the interaction effects were not significant. The results appeared that the lowest losses were 10.05% on November 8th, 2017, at 14-16 p.m., and the highest losses were 12.88% on November 11th, 2017, at 8-10 a.m.‎ The amount of losses was increased due to the higher air humidity and lower temperature. In the fuzzy simulation model, the suitable harvesting-time can be predicted based on the losses quantities in the processing and collection units and the humidity percentage. The results showed that the predicted values for harvesting-times, by a designed fuzzy system, were completely matched with measured values in this study. The coefficient of determination (R2) was 0.980 between measured and predicted harvesting times. This coefficient demonstrated that the developed fuzzy logic system was suitable for prediction of harvesting time in the studied area.

The experimental observations in the field and data analysis showed that in the corn harvesting in the Moghan region, the humidity level, date, and harvesting-time were the most effective factors in the harvesting losses. In this paper, based on measured data from a small farm and implementation of the expert fuzzy system, the most suitable harvest date was set on November 8th  at 14-16 p.m, at 21-24°C and relative humidity of 44%-53% to have 10.5% losses which has been confirmed by the lowest losses observed in the corn plan (10%). Moreover, the high value of the determination coefficient demonstrates a high correlation between measured and predicted data.

Large industrial factories often discharge significant quantities of low-pressure steam (dead steam) into the atmosphere, which causes energy losses. Retaining low-pressure steam content reduces boiler load, resulting in energy savings and lower costs for the fuel consumption (for example, gas consumption bill in a factory). The boosted-pressure steam is used in processes such as distillation, hot water production, space heating or vacuum generation. If the vapor pressure for the intended application is low, a thermo-compressor is able to increase the pressure and temperature to the required level. Thermo-compressors are a special type of gas compressor that uses an actuator to compress secondary fluid and does not have any blades or moving parts. The accurate prediction of the thermo-compressor performance improves the reliability of this process and increases its efficiency.

Two important characteristics for the current thermo-compressors are entrainment ratio (ER) and compression ratio (CR). The first is the dimensionless mass flow rate, and the second is the dimensionless pressure. The wet steam theory as a classic theory is used by Wolmer-Frankel-Zeldovich to calculate the amount of liquid particles. In order to select the best geometry for the thermo-compressor among all possible geometries, the performance of each model must be compared with other models. In following, the case that includes characteristic parameters associated with the target values has been selected.The commercial Ansys Fluent Versions 15, based on the finite volume method (FVM) was used to simulate and monitoring the flow behavior inside the thermo-compressor. The governing partial differential equations (PDE) were solved implicitly using a density-based solution. The convective heat transfer terms were discriminated based on the second-order upwind scheme. The non-linear governing equations were solved using the implicit coupling solver and the standard wall function was used near the wall. Given the three-dimensional flow for steam, the equations of mass conservation, momentum, and energy were written. The Realizable  model was used to simulate turbulences in the flow.

A summary of the results is presented in terms of the results of pressure, velocity magnitude, Mach number and temperature. A general understanding of this characteristic for a thermo-compressor is extremely important for recognizing the fluid flow inside it, and it is very useful for practical use. Pressure is the most important factor in the recharge section of a thermo-compressor. Increasing the recharge vapor pressure in a thermos-compressor revival the dead steam and increases the steam efficiency. The revival steam can be used in other parts because of their high thermal content. Another important factor in the study of flow behavior inside the thermocouple is velocity magnitude. This quantity, which is closely related to the concept of momentum inside the thermocouple, had high influences from high pressure inputs as well as the thermo-compressor geometry. The highest amount of velocity occurs after the initial nozzle and had a very high magnitude (1000 ms-1), which was also remarkably high in Monnet's terms. Another important characteristic of a flow is the temperature of the stream. The high input temperature associated with motive vapor at the outlet of the primary nozzle was sharply reduced, even in some section reached to 110 °Kelvin. Due to the very high flow momentum in this section, the fluid phase remained gas and it can be justified from the point of view of the fluid dynamics.

Considering the importance of thermodynamic properties of steam in conversion and industries, it would be extremely beneficial to fully understand the interactions inside the thermocouple compressor. The importance of the discussed characteristics is more specific when there is a close relationship between each of these factors and energy consumption in a factory or in any industrial production unit. It was observed that the designed thermos-compressor was able to increase the velocity and temperature in a desirable range for the conversion of non-consumable vapor to the pressure and temperature. It was concluded that the Realizable  model due to the prediction of the jet characteristics appearing in the flow regimes for axial symmetry had a high ability to simulate fluid flows inside the thermos-compressor.

The issue of noise pollution is one of the concerns of most societies and industries because of their relationship to the environmental comfort of life or work of people are paying attention. The Aero-acoustics not only because of government regulations on the noise pollution, but also due to the increasing demand of the people's living standards and create a safe environment for farm animals is considered important. At the same time, products with high aero-acoustic performance will attract a lot of customers, which is in the interest of the global economy. Reducing current noise is often accompanied by a reduction in energy costs, resulting in durability of structures and improved product quality.

Sound measurements were carried out at the wind tunnel in Tabriz Tractor Engineers Company. Using the measurements performed by the instrument, the sound levels were measured at different periods of the fan. In many practical applications that include turbulent flow, no noise has any specific tone and the sound energy is continuously distributed over a wide range of frequencies. In cases where broadband noise is present, statistical disturbance values easily calculated from the RANS equations can be used in conjunction with semi-experimental correlations and audio coordination to reveal some broadband noise sources.
Based on the problem, the boundary condition is the type of "input velocity" for the input and "output pressure" for the output. It was also used to move the mesh to apply the rotary motion of the fan. The thermodynamic conditions at these boundaries should be considered.

The accuracy of the simulation results data was verified with the measured data. In the laboratory results, the audio level is accompanied by an audio environment and an inverter and a belt that is about 15 db. With this in mind, the simulation results had a good agreement with experimental results.The velocity is a critical parameter in fan-related discussions. In the upper part of the fan, the speed of the air increases as the fan sucks, and this speed will increase as the fan approaches. In the second part, which includes the fan, for speeding objects, the speed will increase as the radius increases (due to the constant rotational speed), so the maximum speed will be at the tip of the blades. In the lower part of the fan, the speed will decrease as the fan impact decreases on the air molecules as well as the boundary layer behavior near the walls.As the speed and intensity of the turbulence are higher at the tip of the blades, hence the kinetic energy of these regions must also be higher. The kinetic energy of the turbulence in these areas is the highest. At the bottom of the fan, it is also observed that the kinetic energy of the turbulence has been relatively high, due to the existence of flow vortices that emerge from the fan period and the presence of positive and negative pressure (negative pressure due to suction of the fan center). The high pressure difference on both sides of the fluid particles causes a rotating flow in the particles, which affects the adjacent particles and causes vortex formation.

The results showed that the numerical acoustic evaluation simulates the performance of the broadband band with good results and has good agreement with the effects of the current on the noise. Increasing the recognition of the factors and their effects on the fan noise level can help to reduce the noise effects of turbo-machines. Using numerical simulations in predicting and reducing noise, in addition to time saving, dramatically reduces costs by using direct methods and mechanical design physically. With regard to all aspects and calculations, it can be concluded that acoustic numerical simulation and broadband noise model have a good ability to analyze noise in fans and rotary machines.

Immature birds, like humans and many animals, pass through the puberty period to sexual maturity that is accompanied by sound changes and after the sexual maturity, the sound structure evolves. The puberty period is one of the most important periods in the breeder chicken farms. Because the feeding of roosters at this age can delay or accelerate the time of sexual maturity. On the other hand, the diagnosis of mature roosters to mating with chickens increases egg production in early adulthood. Sexual maturity is a summary of the morphological and physiological changes its peak in the roosters from the age of 16 to 24 weeks. In female birds, the beginning of the first laying is considered to be sexual maturity, while the exact timing of sexual maturity in a male bird cannot be determined. The puberty term means the age at which reproduction is possible for the first time, but reproductive processes have not yet evolved. Therefore, the chance of pregnancy at this age is very low and fertility will not be optimal. Puberty can be likened to teenage years in humans. Bird sounds are generated mainly by the syrinx and humans speak with the stimulation of the vocal cords. The sound produced by the bird is similar to how human speech is produced. Therefore, techniques used to recognize human speech are also likely to be useful for classifying bird sounds.

Variation in an animal’s vocalizations can provide clues about how the animal uses sound, as well as qualities of the individual that is vocalizing. Bioacoustics research depends heavily on the ability to characterize these variations. The main goal of this study is to diagnosis puberty and the sexual maturity in bred roosters based on sound signals. To do this, the number of roosters with the first ejaculation for puberty and sperm concentration criterion for sexual maturity was divided into three groups of immature males, roosters during the puberty period and adult roosters and the rooster's acoustic signals were recorded by a microphone in a double-sided glass box (50x50x60 cm). The main purpose of using the box is to prevent the effects of noise in the environment on acoustic signals because otherwise, the sound signal of the rooster is unreliable due to the characteristics of the normal sound. Linear predictive coding (LPC) coefficients from the frequency domain were extracted as sound features. The sound features were used to classify k- nearest neighbors (K-NN) inputs for network training.

The results of accuracy, recall and precision values are, respectively, 97.7%, 98.3%, and 98.8% for the classification of roosters. Immature roosters had similar sound structures that with start the puberty and Leakage testosterone hormone, the rooster's syrinx, which is part of the secondary sexual feature, also begins to change. After sexual maturity, the syrinx has grown and this evolution also makes the sound structure of the mature rooster very similar. Therefore, according to the similarity of the sound of the mature rooster and immature one, as well as the syrinx continuous changes during the puberty period, the K-NN classifier with the LPC coefficients can show a high degree of accuracy in the classification of roosters. Because a feature of the k-NN algorithm is that it is sensitive to the data local structure.

The main objective of the present study is to detect sexual and puberty of roosters using acoustic signals. The LPC coefficients as K-NN classification inputs show accuracy, recall, and precision values of 98.7%, 98.3%, and 98.8%, respectively. These results indicate high accuracy of K-NN classification to identify and categorize immature roosters, rooster during puberty period, and mature roosters.

Due to problems such as water resources constraints, poor soil and soil organic matter, and the problems related conventional tillage, the attention paid to protective tillage equipment should be taken into consideration by farmers. Today, agricultural machinery designers and manufacturers are looking for ways to resolve the problems due to the lack of water and soil resources and the reduction in fuel resources. One of these solutions is the optimization of agricultural machinery. The blade is one of the most important consumed components of tillage tools, which is very important for how it is adjusted and its effect on soil. According to research conducted on the importance of optimizing tillage implements, this study was carried out with the aim of optimizing the operating conditions for combined tillage with a new narrow blade.

The tests were taken place in the 10th section of farms in Agriculture school (Bajgah zone) of Shiraz University. Those tests were arranged as the split-split plot based on a completely randomized design. The treatments included the tillage depth, tilt angle and forward speed. The levels for the tillage depth, tilt angle and forward speed were 15, 20 cm and 0, 10, 15, 20, 25 degree and 3, 4, 5 km h-1 respectively. The experiments were performed in three replications. The test variables were draft, soil upheaving and disturbance areas, specific draft, fuel consumption and tractor wheel slippage. The CK 45 steel was used to make blades. The blades were made of the same dimensions and the difference between the blades was only at their tilt angle. Before starting the field tests, some properties of soil such as soil moisture content, soil texture and soil bulk density were measured. The RNAM test code was then used for measuring the draft force. The encoder and the fifth wheel were also employed to measure the slippage. For measuring the fuel consumption, two flow meters were used in the round way. The profilometer was applied for measuring the soil upheaving and disturbance areas. The specific draft was also computed. The data analysis was performed by SAS software (9.4 edition). Multiple regression method was used for modeling the desired treatments.

The results of multivariate regression method for optimizing forward speed, tillage depth and tilt angle for the blades including winged were 3.3 km h-1, 20 cm and 25°, respectively, and for the non-winged, 3.5 km h-1, 20 cm and 24.8°. Providing the tilt angle on the blade surface is considered as an innovation in this research, therefore, it can be seen from the results that with increasing this angle, the draft of the tillage was decreased. This could be due to the increased surface of the blade in the face of the soil on the diagonal surface. This increase was proportional to the cosine tilt angle at the initial surface of the blade. Therefore, the shear strength of the soil was decreased with increasing of this surface and ultimately decreased the amount of draft of the tillage. This variable had a significant difference with the depth of tillage and the forward speed of tractor and fuel consumption for the winged new narrow blade. Although the interactions of the above mentioned variables on the fuel consumption for the new blade condition were not significantly different, the minimum fuel consumption for the non-winged blade condition was also obtained at the same tilt angle as the winged new blade. In general, considering all of factors, the 25 degree inclination angle was proposed for both conditions. The interaction of this factor (tilt angle) on the wheel slip rate was also significant. The effect of the angle of inclination for both blades was significant on the slip of the wheel drive, so that the increase in the tilt angle reduced the amount of wheel slip. However, if the amount of slip of the tractor's wheel for an optimum angle of 25° was considered, according to the graph which representing the relationship between tractive efficiency vs. wheel slip and for Cn = 50, the tractive efficiency will be determined by calculation. It should be noted that the tractor's tractive efficiency was equivalent to 82%. This value reflects the effect of the tilt angle on the amount of tractor output power according to the definition of the tractive efficiency of the tractor.

Considering the increasing growth of using combined tillage tools in dry soil and its low moisture content, and considering the necessity of replacing the custom chisel blades with new blades which resistance to the soil reaction forces upon them, the non- winged blades with the tilt angle about 25° for working depth of 20 cm and forward speed of 3.5 km h-1 can increase the tractive efficiency of tractors to 82% and also decrease the fuel consumption by 34% compared to conventional tillage blades.

Cereals as one of the most important sources of food plants could provide more than 70% of the food for the human population. Passing of water from the magnetic field is among approachable methods in order to reduce the total amount of water used for irrigation. Moreover, magnetized water is a new concept for increasing the water efficiency. Therefore, this study was aimed to investigate the effects of the magnetized water on some of features containing dry weight, germination velocity and percentage, length and weight vigor indices of five common wheat cultivars including Roshan, Sardari, Shiraz, Falat and Yavarus, to introduce the best cultivar considering the growth and germination indices as well as water and energy efficiency.

To perform this experiment, a device with a magnetic field of 500 millitesla was constructed to accommodate both the water path and the placement of seeds in the magnetic field. To perform the experiments, 10 seeds in 4-kg vases and 25 seeds in each Petri dish were cultivated in the greenhouse and laboratory, respectively. The experiments were carried out in the form of completely randomized factorial design. The factors are considered as the duration time of keeping the water in the magnetic field (three levels of 30, 60 and 120 minutes), the intensity of the magnetic field (three levels of 100, 150, and 200 millitesla), and five wheat cultivars (Roshan, Sardari, Shiraz, Falat and Yavarus) in three replications.
Experiments related to the both of rate and percent of germination and for dry weight were performed at room temperature in the laboratory and greenhouse under controlled conditions, respectively. The measured data were analyzed using SAS software. The F test was used to determine the significant level of treatments. The comparison of the means was evaluated using LSD test.

The obtained results, showed that the effect of magnetic water on all growth and germination indices compared to control samples was significant. Under the 150 millitesla and 120 minutes treatment, the Yavarus, Roshan and Sardari cultivar had maximum dry weight, respectively. The Roshan cultivar had the maximum germination velocity at 100 and 150 millitesla and duration time of 30 minutes. Moreover, the maximum germination percentage was found in the Roshan cultivar, which did not have a significant difference with Yavarus cultivar. The Roshan cultivar in 200 millitesla field and duration time of 60 minutes, had the maximum percentage of length vigor index, which showed a significant difference with other averages.In general, Roshan and Sardari cultivars had more length vigor index than other cultivars. Sardari cultivar had maximum percentage of weight vigor index under 200 millitesla and 120 minutes duration time, which had no significant difference with the percentage of weight vigor index at the same field level and with duration time of 60 minutes.

According to the obtained results to achieve the maximum value of dry weight, it is better to use the Yavarus cultivar. It is recommended to use the Roshan cultivar with the lower level of magnetic field and duration time to attain the maximum value of the germination velocity and percentage. To get the maximum value of the length vigor index and the weight vigor index the Roshan and Sardari cultivars, and the Sardari cultivar with field of 200 milli Tesla and lower duration time are preferred.

One of the main factors affecting plant growth is soil compaction. More attention should be paid to soil compaction than the past. Soil compaction not only destroys the soil structure, but also leads to a heavier soil structure with natural cavities. The rolling resistance reduces energy and occurs when the tire moves on a soft soil and rolling resistance of the tire is brought about by two processes of soil deformation and wheel change. This force is influenced by the design of the tire, the parameters of the tire, and the characteristics of the soil. The apparent electrical conductivity (ECa) indicates the direct conductivity of direct current in the soil. The electrical conductivity is effective on chemical and physical properties, including the amount of soluble salts in the soil, salinity, cation exchange capacity, soil texture, organic matter content, moisture content and water holding capacity, and compression. The purpose of this study was to investigate the effect of soil compaction and soil moisture on the soil electrical conductivity and rolling resistance of the Messy Ferguson 285 tractor rear tire. This study showed the density and soil moisture were associated with soil electrical conductivity and rolling resistance.

This test had independent and dependent variables. The dependent variables including rolling resistance and electrical conductivity, whose values were measured by a torque meter and a portable EC meter. Independent variable comprised of soil compaction and soil moisture measured by Penetrologger and soil moisture measurement tools including soil harvesting cylinder, scale and oven device. Experiments were carried out in the soil bin Laboratory with a 1.7 m wide, 24 m long and 1 m deep with soil texture of clay loamy in Agricultural Engineering Research Institute (Karaj). The soil was prepared layer by layer and up to a depth of 20 cm by the soil preparation unit. In all experiments, the vertical load was fixed at 4000 N and the tire pressure of 6899 N.m-2. On each layer, the water was evenly sprayed to reach the desired moisture. To do this research, factorial experiment with soil compaction levels at 3 levels of 2, 4 and 6 roller passes, respectively, with the bulk density of 1.47, 1.54 and 1.69 g.cm-3 and soil moisture at 3 levels of 10%, 12% and 14% were used in 3 replications. Data were analyzed using SPSS software. The tools used included the tire test rig, the rear tire of a Massy Ferguson 285 tractor, the soil preparation unit, and the measuring instrument, including the torque meter, the penetrologger and the portable EC meter.

In this experiment, it was found that as the amount of moisture increased, the compaction was also increased. The test indicated that the soil rolling resistance was increased by decreasing the soil moisture content. Moreover, increasing in the soil compaction ration led to decreasing the soil rolling resistance. The CI was used at a depth of 20 cm to 0 cm. In these experiments, we concluded that the higher density of compaction resulted in increasing the soil cone index (CI). This index was directly related to the compaction, but it had an adverse relation with the moisture. It means the lower amount of moisture led to the higher amount of CI. The amount of electrical conductivity of soil was measured at a depth of 0-25 cm. In this experiment, we concluded that the higher compaction ratio resulted in the higher electrical conductivity. It means that electrical conductivity had a direct relation with the compaction and the moisture content. The lower moisture content led to the lower electrical conductivity of the soil.

In general, considering all the tests and comparison between rolling resistance, soil cone index and apparent electrical conductivity before and after roller passing, it can be concluded that as the amount of moisture content increased, the soil cone index (CI) decreased. The soil cone index (CI) had a relationship with the moisture. The lower moisture content led to the lower soil moisture resistance, as well as the higher moisture content resulted in the higher soil resistance. The lower amount of soil compaction showed the greater soil rolling resistance, and the greater amount of soil compaction caused to the less soil moisture resistance. The electrical conductivity before and after the roller pass was different in the case of roller pass, and the higher amount of moisture led to the greater electrical conductivity, because the electrical conductivity was directly related to the moisture and the compaction affects all parameters.

Soil compaction reduces soil porosity and thus, increases the resistance and bulk density of the soil. These changes limit water and air movement and root penetration in the soil and ultimately, they may reduce the seed germination and the crop yield. For planting sugar beets, tractors and equipment need to move several times on the ground, which is a factor in soil re-compaction and the loss of the effects of previous tillage. Therefore, if, after planting, inter-row tillage was done, it can have a positive effect on reducing the bulk density of the soil and it may even increase yield.

An experiment was conducted to determine the effect of inter-row tillage on the sugar beet yield and its quality and water use efficiency during two years cropping period (2016-2017) in Ekbatan Research Station, Hamadan with loam texture soil. A strip plot experiment with eight treatments and three replications was used. Irrigation regimes consist of 100% of sugar beet water requirement (I1) and 75% of sugar beet water requirement (I2) were considered as main plots. Inter-row tillage operations consist of  combined cultivator equipped with chisel and crescent blades to 20-25 cm soil depth (T1), a simple cultivator equipped with crescent blades (T2), crescent cultivator + inter-row subsoiling to 30-35 cm soil depth (T3), combined cultivator equipped with rotary and sweep blades to 20-25 cm soil depth were considered (T4 ) as sub-plots. During the experiment, some physical properties of soil including bulk density and soil cone index were measured. At the end of the growth season, the root yield and yield of white sugar were measured and analyzed statistically.

The results showed that the effect of inter-row tillage methods on the soil bulk density and soil cone index was significant. The T3 treatment (crescent cultivator + inter-row subsoiling to 30-35 cm soil depth) had the highest effect on reducing the cone index and bulk density of soil, but the lowest root yield was obtained.  Due to the low spacing of rows (50 cm) in the sugar beet cultivation, as well as the structure of the subsoiler and its depth, it is possible that the subsoiling caused the moving of the roots and minor damage to it. The effects of irrigation and inter-row tillage and their interactions on quantitative and qualitative yield of sugar beet were not significant. The results of analysis of variance of treatment effect on the water use efficiency showed that the effect of inter-row tillage on the water use efficiency was not significant. The effect of water requirement on the water use efficiency on the basis of sugar and white sugar performance was significant at 5% probability level. The treatment of 75% of water requirement increased the efficiency of water use based on the root yield, sugar yield and white sugar yield by 4%, 14% and 7%, respectively. Therefore, with the goal of reducing water consumption and not significantly reducing the yield, after plant establishment, it can reduce water use by about 25%.

The effect of inter-row tillage on the cone index and bulk density of soil was significant and subsoiling treatment caused a further reduction of these two indices compared to the other inter-row tillage methods. The effect of inter-row tillage and water requirement on root and sugar yields was not significant. According to the results, after planting completely establishment, the water use can be reduced by about 25% (this decrease in the total length of sugar beet growing was about 15%).

In recent years, with increasing population growth and improving livelihoods, the consumption of vegetable oils has been increasing and has led to an increase in the level of oilseed cultivation. Sesame (Sesamum indicum L.) is an economically important crop which is widely cultivated all over the world. Sesame has been considered as an oil plant for cultivation in Iran's climatic conditions recently. Sesame contains about 58-44% oil, 18-25% protein and 13.5% carbohydrate. Sesame is grown mainly in the developing tropical and subtropical areas of Asia, Africa. The three countries of China, India and Myanmar are accounted as the largest producers of this product in the world. Screw pressing is the most reliable method for extracting oil from oilseed grains. This method is simpler than others and is more efficient in terms of cost and food security. The general objective of this research was to investigate the effects of rotational speed, temperature, type of screwing and die diameter on the amount of oil extraction from sesame oil and prediction of oil extraction using artificial neural network and compare to regression models.

In this research, a sesame oil extractor machine was designed and manufactured. Various experiments were carried out to determine the amount of oil extracted based on variable parameters such as the shape of the press screw, the rotational speed, the temperature and the diameter of the die. The experiment was performed at three levels of press screw type (constant pitch, variable pitch and conical), temperature (30, 60, 90), three levels of rotational speed (20, 50, 80 rpm) and three level of die diameter (6, 8, 10mm). The experimental design was factorial based on completely randomized design with three replications. The mathematical software (Matlab, 2012b) was used to determine the optimal neural network. The type of network was Multi-Layer Perceptron (MLP). In order to design this network, there were 3 neurons in the first layer (input), which was equal to the number of studied variable parameters (type of screw, rotational speed and temperature), the second layer was hidden layer, and the last layer (the output) had a neuron for the extracted oil) was equal to the number of outputs examined in this network. The Levenberg-Marquardt algorithm (LM) was used to train it, which is one of the fastest neural network training methods. The Second-order polynomial regressions were performed based on the step-by-step method and non-meaningful sentences were eliminated from the model. The accuracy of the models was determined by calculating the correlation coefficient and root mean square error (RMSE) indices.

The results of the experiments showed that the effect of type of press screw, rotational speed, extraction temperature and die diameter on the amount of oil extraction was significant (p≤0.01). The highest amount of extracted oil was obtained at conical press screw , rotational speed of 50 rpm, temperature of 60 °C and die diamter of 6 mm. An artificial neural network of three-layer perceptron and regression models were used to predict the amount of sesame oil extracted. The results showed that the artificial neural network model (1-8-3) with a correlation coefficient of 97.47% and a RMSE of 0.65 compared to linear regression and quadratic regression models had the higher efficiency in predicting the amount of extracted oil.

In this study, the effect of temperature, rotational speed, press screw type and die diameter on the amount of extracted oil were investigated. The results of this study showed that the change in the type of screw, rotational speed, diameter of die and temperature on the amount of extracted oil was significant at 1% level. Results also showed that the artificial neural network method was more efficient than linear and second order regression methods.

Considering the high consumption of diesel fuel in the agricultural sector, it is necessary to find solutions to reduce its consumption, and it will be feasible to have a convenient mathematical model more easily and transparently.Fuel and lubrication costs range from at least 16% to more than 45% of total machine costs, depending on the type of fuel and the amount of time that the tractor or the machine carries out for agricultural operations. Therefore, the fuel consumption index has a significant role in the selection and management of tractors and agricultural equipment. Most budgeting models also use a simple method to estimate the consumption of diesel fuel, but it is needed a model that describes the real conditions of agronomic operations used to compare agricultural machinery management policies.

This case study was conducted in Parsabad city of Moghan, the northernmost province of Ardabil province. The main agricultural products in Pars-Abad Moghan include wheat, maize, maize, canola and sugar beet. The product of this study was irrigated wheat with a crop area of 18042 hectares.In this study, in order to create homogeneous conditions in the study of diesel fuel consumption and the ineffectiveness of the type and model of tractor in it, only diesel fuel consumption was considered by the tractor MF-399. Selection of sample farmers was also carried out among owners of this type of tractor. Selection of owners of tractor MF-399 in Pars-Abad Moghan city was done by random sampling method. For this purpose, Cochran formula was used. Two-way flexible and non-flexible models have been used to predict the diesel fuel consumption. The model used includes the Cobb-Douglas function and transcendental function. Statistical calculations in this study were performed using Excel software and SPSS16 software.

For comparing the best form of the fuel function, the test formulas for the comparison of the form of functions such as bounded least squared F, LR test, White test, Breusch-Godfrey test and Rigorous test were used. Diagnostic statisticians (well-fitting coefficient), the normal distribution of distorted sentences, and the heterogeneity of variance showed that both forms were acceptable. Based on the LR statistic, zero statistics did not rule out the discrepancy between the two coherent models (Cobb-Douglas) and non-dominant (transcendent), but the coherent model was preferable to be the transcendental model because of its simplicity and power of explanation.According to the estimated model, the duration of soil tillage operations had a positive stretch in diesel fuel consumption and, among other variables, had the highest elongation. It should be noted that the average time required for tillage operations was 387.6 min ha-1, which will save 0.31 L ha-1, if one percent of this time (3.9 minutes) is reduced. Thus, the value of the amount of gasoline saved will be about 990 Rials per hectare and equal to 7.7 percent of the value of one kilogram of wheat. Therefore, if the operating time is reduced at the macro level of the country, a significant amount of cost will be saved. Therefore, it is imperative that farm managers take time management in serious soil tillage operations and try to reduce this time.So that, in exchange for an increase of 1% over the duration of the tillage, a fuel consumption of 0.6% would be increased. It is also clear that an increase of 0.6% in fuel consumption for tillage operations is significant, indicating the fact that farm managers have made the need for time management, especially in the tillage operations, to reduce this time. According to the estimated model, the duration of the planting operation also had a positive stretch in the consumption of diesel fuel. So that, in exchange for an increase of 1% over the duration of the planting operation, a fuel consumption of 0.04% would be increased.

Use of the Cobb-Douglas model with five sentences and four independent variables including cropping area, soil tillage operation time, planting time and weeding operation time in order to predict the amount of diesel fuel used to produce wheat, had acceptable results and as a predictive model with low complexity but with high precision, can be easily used in annual budgeting for the production of wheat.

Optimal operation and maintenance of engineering systems heavily relies on the accurate prediction of their failures. Repairable engineering systems are well known in industries. A repairable engineering system indicates that the performance of this system after each failure can be restored through suitable maintenance. It is normally a complex system composed of a number of components. Failure prediction of a repairable system and its subsystems is an important topic in the reliability engineering. One of the most important repairable systems in agro-industrial companies is the sugarcane harvester. This machine has a key role in harvesting operations of sugarcane plant. The failures of this machine causes delay in operations and reduce products yield and quality. Currently, preventive maintenance is conducted on these harvesters to improve the overall reliability of these systems. Therefore, in this study, the long-term effect of preventive maintenance strategy on the efficiency and failure rate of the sugarcane harvester was investigated.

This research was carried out on 30 sugarcane harvesters used by sugarcane and by Products Development Company of Khuzestan during 6 years period. The goal of this study was to introduce a methodology aimed to acquire the information to predict the effect of preventive maintenance strategy on the failure rate and efficiency of sugarcane harvester by time series. Time series forecasting is the use of a model to predict future values based on previously observed values. The expected shape is a forecast from a combination of an ARIMA models (AR, MA, ARMA and ARIMA). The first step in analyzing the time series is plotting the data and obtaining the sample records. The next step is consideration of a trend and periodic components and remove them from the time series and fitting the static model on the time series. The next stage is implementation of the data normalization using skewness coefficient method and their normalization through logarithm differentiation of data. The arithmetic mean of data was applied to obtain zero average of the time series. Sample ACF (Auto Correlation Function) and PACF (Partial Auto Correlation Function) was drawn and then the model rank "a" was recognized and selected by comparison of ACF and PACF for AR, MA, ARMA, and ARIMA models.

According to the results of failure rate related to the sugarcane harvester, it can be found that the mean failure rate of this machine for the 6-years period was equal to 0.147 per hour. The minimum and maximum value of the failure rate were 0 and 0.517 per hour, respectively. The mean annual use hours of these harvesters was 189.8 h. Although the accumulated used hours increased, the mean time between failures (MTBF) was increased. According to Jacobs et al. (1983), the machines may breakdown due to a design defect, physical damage, or normal wear and tear, but many times machines fail because of a neglect and the lack of properly scheduled maintenance. In this study, implemented preventive maintenance resulted in decreasing of failure rate and increasing of machine efficiency as well. In 2016, the failure rate of sugarcane harvester was decreased by 73.23% and the machine efficiency was increased by 14.9%  compared to 2011, because timely preventative maintenance and inspection will not only help to reduce major problems and downtime, but it will also help to identify problems when they can be corrected with relatively minor repairs. Among the 12 studied subsystems, topper, electric and motor subsystems were more affected by preventive maintenance by 94.75%, 80.46% and 58.74% decreasing in the failure rate, respectively. With regard to the evaluation criteria such as AIC, MAPE and RMSE, the ARIMA (1, 3, 2) model was determined as a suitable model for predicting the failure rate of sugarcane harvester. Furthermore, there is no significant difference between statistical descriptive measures of forecasting and actual tractor failure rate that it represents high accuracy of forecasting via ARIMA model.

This study was adapted to the preventive maintenance as a useful strategy that could increase availability and operational efficiency of the sugarcane harvester. Furthermore, it focused on time series modeling method to analyze and forecast the reliability characteristics such as the expected number of failures per interval (failure rate). It is found that time series model is a viable alternative that gives satisfactory results for interval failure predictions in terms of its predictive performance for the sugarcane harvester reliability.

According to the importance of energy and the impact of this input on the final price of a product, selection of materials and components of poultry saloons is very important.  Poultry saloons are divided into two types: open saloons and closed saloons. In closed saloons, the choice of materials and components of the saloon (door, window, etc.) are more sensitive than the open type. Due to the climatic conditions of Khuzestan province, all of the used saloons in this province are almost closed. Poultry farms in Khuzestan province have a lot of cooling load in the warm seasons. If the materials and components of the saloons are not chosen properly, energy losses increase, and as a result, the price of meat increases. Therefore, investigating of heating and cooling loads of saloons and use of suitable components to prevent energy losses is necessary. Energy modeling of saloons and buildings is done by various software (Plast Energy, Design Builder, Trnsys, etc.). One of the most efficient and precise of this software is Carrier.

This study was conducted to calculate heating and cooling loads in different climates of Khuzestan province. In this research, the cities of Izeh, Shoosh, Abadan and Andimeshk were selected as corresponding to different climates in the province.Required data  for software was collected in three categories: (a) Weather data (geographic information, location of the saloon, local time zone and local soil specifications), (b) Data  about the physical properties of the building (general specifications of the space, internal sources of heat production (personslabors, poultry, equipment), (c) Specifications of walls, floor, windows and doors, ceiling and lighters, (d) Infiltration of air, (e) Systems, and (f) Information on power and fuel consumption.In this research, a rectangular saloon with dimensions of 85×16 meter was considered for all three types of conventional saloons in the province (block, brick and panel), which are the common dimensions and the capacity of these saloons is 20,000 broiler chickens. In this study, Carrier software was used to calculate heating and cooling loads. The results of software were verified by the amount of fuel and power consumption.

The sand and soil floors had the highest cooling load by 48828 and 53012 kJ h-1, respectively, while concrete and mosaic floors had lower cooling load than them. The heating load of these two floors (3906 kJ h-1) was less than that in the sand and soil floors. Concrete floor had better conditions to choose because of the less cost than the mosaic floor.Comparison of heating and cooling loads in different types of walls made of various materials showed that the block wall had the highest heating load of 429356 kJ h-1 and the highest cooling load by 658356 kJ h-1, while the sandwich panel wall had the lowest heating load by 116873 kJ h-1 and the lowest cooling load by 123618 kJ h-1.Three types of doors are commonly used in poultry houses: iron, fiberglass and aluminum. The results showed that the iron and fiberglass doors had the highest and lowest heating and cooling loads, respectively. The investigation of the effect of different types of windows on heating and cooling loads showed that iron and plastic windows had the highest and lowest heating and cooling loads, respectively. The results showed that Irannait ceiling had the highest heating and cooling loads by 371416 kJ h-1 and 787535 kJ h-1, respectively, while the ceiling made of sandwich panel had the lowest heating and cooling loads by 72756 kJ h-1 and 72429 kJ h-1, respectively, because of low heat transfer coefficient.Comparison of heating load of the saloons showed that the block saloon had the highest heating load by 891525 kJ h-1 and the suggested saloon in this study had the lowest heating load by 309068 kJ h-1. The block and suggested saloons also had the highest and lowest cooling loads by 1604828 kJ h-1 and 330795 kJ h-1, respectively.

The amount of heating and cooling loads for suggested saloon were 29.6% and 18.24% lower than that of brick and block saloons, respectively. The difference in the cost of constructing suggested and brick (the most common saloon in the province) saloons was 28.9 million tomans. By considering the difference in the cost of energy consumption of them (11.726 million tomans), this amount will be compensated after 2 years and 5 months and then will be returned on investment.