مجله پژوهش های مکانیک ماشین های کشاورزی
سال ششم شماره 2 (پاییز و زمستان 1396)

Transmission of mechanical energy from vibration source to human body has different effects, such as reduced efficiency, skeletal lesions, disorder in the comfort, physiological and psychological problems. The lack of suspension systems on agricultural machines has causedthat the operators of agricultural machinery to be exposed to a wide range of vibrations indirectly. Use of suitable seat foam is one solution to reduce the vibrations. In this study, the vibration transmission of Polyurethane foam or sponge and effect of various factors for reducing vibrations is investigated. Therefore, different types of foam and sponge with a thickness of 6, 8, 10 and 12 cm, and densities of 12.5, 20, 30 and 50 kg/m3 were exposed to the vibration. Also the passenger mass and stimulation acceleration in three different levels were applied to the samples. Acceleration Data were records and the experimantal analyses were then performed with SPSS and MATLAB software. The results showed that vibration transmissibility of the cold foam was less than that of hot foam (about 10%). Considering the Anthropometrics data and the range of tractor operators mass in Iran (72-90 kg), and also due to the principles of ergonomics, the use of cold foam with a density of 50 kg/m3 (transferability of 26%), the thickness of 8-10 cm in acceleration of 3-4 m/s2 (transferability of 17%) is the most appropriate choice for the machines with high vibration seat.

These years, the use of tractors and self-propelled agricultural machines has been caused to increase the human death numbers due to accidents with them. Hence, having an alarm system on agricultural vehicles for humans and obstacles detection can be beneficial to reduce the accidents. This study was aimed to develop a machine vision system for human detection to use in agricultural tractors. A camera was installed in front of the tractor, and an algorithm was then designed in MATLAB for image processing. After trimming the input image, the human was identified using watershed and gradient magnitude techniques, and also subtracting human from the background. According to the results of the algorithm evaluation in various image acquisitions, the proposed algorithm had high accuracy at distances of 4 to 20 meters compared with two common human detection methods (Histogram of oriented gradient and Cascade). Average accuracy of the proposed algorithm in these distances was within 85 - 94 %. The results of variance analysis for accuracy of human detection showed that the effect of identification method and distance on the accuracy of human detection were significant as well as the interaction effects between different parameters were significant at the 1% level.

The main fraud way in olive oil adulteration is mixing with other vegetable oils such as maize, canola, sunflower and soy oil. Therefore, the aim of this study was to evaluate a portable system to detect adulteration in olive oil using combination of machine vision and capacitive methods. To identify adulteration in olive oil by using frequency and color features, Principal Component Analysis (PCA) and Linear discriminant analysis (LDA) were thus applied. The best neural network model with 36-6-1 structure had R2 of 0.944 and mean square error of 0.006, for prediction of adulterated olive oil with sunflower oil. Also, the best model of neural network for olive-canola mixture had the structure of 36-10-1, R2 and mean square error of 0.946 and 0.003, respectively. Finally, a combination of frequency and color properties was used to develop the models. The R2 and mean square error of mixed samples of olive-sunflower were obtained as 0.962 and 0.008 for 38-2-1 network. For mixed samples olive-canola, the R2 and mean square error were obtained 0.961 and 0.0013 for the structure of 38-16-1 neural network.

Due to the possibility of mixing hard, semi soft and soft almonds with different market value after harvesting, using an effective separation system for supplying uniform products to the market is essential. In this research, in order to classify almond varieties, an intelligent impact-acoustic system was used. The system operation was done by dropping almond nuts onto a steel impact plate through a pipe. Then some features such as amplitude, phase and power spectral density (PSD) of almond nuts were extracted from the analysis of sound signal gained by a microphone in both time and frequency domains by means of Fast Fourier Transform (FFT). Principal component analysis method was used for reduction of the features. Two types of artificial intelligence techniques including Artificial Neural Networks (ANNs) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were used to classify almond nuts and their performances were then compared. The ANN model used the multi-layer perceptron network with back propagation algorithm and Levenberg–Marquardt algorithm (LM) learning function. In ANFIS model, due to the limitation of inputs number, three principal components of PSD feature that had higher priority were selected as inputs and the almond classes as outputs. Also, hybrid optimization techniques were used for classification. By comparing the artificial intelligence techniques used here, ANN model with about 96.2% accuracy had better performance to classify almond nuts than that of the ANFIS model with 81% accuracy.

Recently, optical GreenSeeker sensor, because of its accuracy and user friendly, has attracted the attention of many farmers to use it for measuring Normalized Difference Vegetation Index (NDVI). The main objective of this study was to measure the total leaf area of plants using this optical sensor and investigate the possibility of using this sensor instead of conventional methods. The images of all plots were recorded using camera and the G-R (Green-Red) was determined as a best function to distinguish soil from the leaf. Based on the Results, an appropriate relationship between total leaf area and NDVI was obtained (R2=0.84). Results of comparing Greenseeker and chlorophyll meter SPAD-502 indicated a promising accuracy of the Greenseeker sensor (R2=0.82) in measuring the plant chlorophyll. The root mean square error resulted from the effect of organic matter on sensor output was found to be 0.048. It must be noted that every product has a specific reflection in the red and infrared bandwidth, so the model obtained in this study just can be used for corn. For the other crops it is necessary to develop specific models. Finally, it is concluded that the GreenSekeer sensor can be used to determine the total top area of canopy and it provides the possibility of comparing the total leaf area of canopy between fields.

One of the major limitations in farmlands is soil compaction caused by trafficking of agricultural machinery. Machinery trafficking management on farmland in terms of how and why is depended on the parameters of each section, soil and crop operations. This study was aimed at investigating the effects of wheel forward velocity, load and multi-pass on clay loam soil compaction. Experimental tests were conducted in the soil bin facility equipped with single wheel tester. Input parameters were velocity at three levels (i.e. 0.5, 1 and 1.5 m/s) and wheel load at three levels (i.e. 2, 3, 4 kN). Rut depths and cone index as research target variables were measured in different combinations of treatment and repetition of wheel passes in each direction. The effect of wheel load on the increase of rut depth was only significant up to sixth levels. Moreover, wheel load and number of passes over the same path had a significant effect on the increase of cone index. In contrary, the effect of forward velocity on this parameter is ignorable based on the statistical analysis performed. Furthermore, the effect of wheel pass number on rut depth and cone index was extracted as regression models.

This study was aimed to determine human and machine causes including musculoskeletal disorders for 399MF tractor drivers in Iran, Kohgiluyeh and Boyer Ahmad province (city of Yasouj, Dena, Dehdasht and Gachsaran). The data was collected by using musculoskeletal and aided Nordic questionnaire and analyzed by SPSS 21 software as well as independent T-test and (Chi-Square) X 2. The mean age of the study population, was noted to be 36.33, mean weight and mean height were 85.35 kg and 172.82 cm, respectively. it was found that 91.9% of studied drivers suffered at least once in one part of the body during 12 months. The most frequent injuries and disorders proved to be neck (83.54 %) and back (75.33%), respectively and the lowest was the feet and ankles (17.36 %). The results obtained from Rapid Entire Body Assesment (REBA) technique proved that in 20 investigated work condition, 13 cases were in a high dangerous status and 7 ones were in mid dangerous status which need special attention. Main ergonomic problems were the force exerted on the knee, bending and torsion force on the waist and neck. This study indicated that the prevalence of work-related musculoskeletal disorders of MF399 tractor drivers needs to be urgently modified.