مقاومت غلتشی

In this research, field experiments were carried out in two types of soil (sandy clay loam and clay) to model the traction performance of the tractor considering drawbar power, rolling resistance, and traction efficiency, using deep learning and convolutional neural network while having some parameters such as soil type and conditions, tool parameters, and operation parameters. The tests were conducted within each soil texture in the form of factorial tests based on the randomized complete block design (RCBD) in triplicates. The tests were done in various moisture levels (8-17% for dry soils and 18-40% for moist soils), tractor forward speed (1.2, 1.6, 1.8, and 2.2 km h-1), working depth (30 and 50 cm), the number of pass (2 and 6 times), and tire inflation pressure (20 and 25 psi). The cone index, dynamic load, draft force, and moisture content were measured in each tests. The networks designed to model the drawbar power, rolling resistance, and traction efficiency were of convolutional neural network type. Various algorithms such as Sgdm, Adam, and Rmsprop were utilized to train the network. The results showed that the neural network developed by Sgdm algorithm outperformed the others. Therefore, this algorithm was utilized for the modeling process. Statistical criteria such as R2 and MSE were also employed to evaluate the performance of the network. For the drawbar power, the 8-499-499-1 architecture showed the best performance with R2=0.9953 and MSE=0.0016. Concerning the rolling resistance, the best performance was observed in 8-301-305-1 architecture with R2=0.9903 and MSE=0.0039. The best performance for the traction efficiency was obtained by 8-371-371-1 architecture with R2=0.9888 and MSE=0.003. The results showed that these networks can be used to model parameters by removing convolution layers and reducing dimensions.

Predicting the tire rolling resistance is an important issue in Agricultural Engineering, therefore, estimates it in different terms of vehicle performance is necessary. One of the rolling resistances predicting ways is to use models which are presented for pressure sinkage treatment of soil. In this study, the coefficient of each model has determined using MATLAB software, and then a comparison was made between them using two standards of correlation coefficient and root mean square error. The results showed that the Upadhyaya’s model with average Coefficient of determination of 0.9175 and average root mean square of 69.6211 has better accuracy in different moisture contents and bulk density. Also Gotteland and Benoit’s model with average Coefficient of determination of 0.7237 and average root mean square of 129.071 has less accuracy in predicting of sinkage value.

In this research, Wismer-luth model function was studied to estimate the rolling resistance of a wheel considering forward velocity and wheel number of passes parameters. Experimental tests were performed using a single wheel tester in controlled environment of a soil bin. Forward velocity and weight were considered at three levels and with wheel pass repeating in each path, it was also applied. Results suggest that Wismer model had a proper accuracy at prognosticating rolling resistance at all levels of weight and forward velocity, but with pass numbers up to 5, traffic parameter had more predicting accuracy compared with higher ones. A regression model was applied based on experimental data to predict the wheels rolling resistance with considering the effect of forward velocity and traffic. As a result Wismer model had a strong ability predicting the wheel rolling resistance while it did not encompass forward velocity and pass number.

Rolling resistance is one of the most substantial energy losses when the wheel moves on soft soil. Rolling resistance value optimization will help to improve energy efficiency. Accurate modeling of the interaction soil-tire is an important key to this optimization and has eliminated the need for costly field tests and has reduced the time required to test.
Rolling resistance will change because of the tire and wheel motion parameters and characteristics of the ground surface. Some tire design parameters are more important such as the tire diameter, width, tire aspect ratio, lugs form, inflation pressure and mechanical properties of tire structure. On the other hand, the soil or ground surface characteristics include soil type; moisture content and bulk density have an important role in this phenomenon. In addition, the vertical load and the wheel motion parameters such as velocity and tire slip are the other factors which impact on tire rolling resistance. According to same studies about the rolling resistance of the wheel, the wheel is significantly affected by the dynamic load.
Tire inflation pressure impacted on rolling resistance of tires that were moving on hard surfaces. Studies showed that the rolling resistance of tires with low inflation pressure (less than 100 kPa) was too high.
According to Zoz and Griss researches, increasing the tire pressure increases rolling resistance on soft soil but reduces the rolling resistance of on-road tires and tire-hard surface interaction. Based on these reports, the effect of velocity on tire rolling resistance for tractors and vehicles with low velocity (less than 5 meters per second) is usually insignificant.
According to Self and Summers studies, rolling resistance of the wheel is dramatically affected by dynamic load on the wheel.
Artificial Neural Network is one of the best computational methods capable of complex regression estimation which is an advantage of this method compared with the analytical and statistical methods.
It is expected that the neural network can more accurately predict the rolling resistance. In this study, the neural network for experimental data was trained and the relationship among some parameters of velocity, dynamic load and tire pressure and rolling resistance were evaluated.
The soil bin and single wheel tester of Biosystem Engineering Mechanics Department of Urmia University was used in this study. This soil bin has 24 m length, 2 m width and 1 m depth including a
single-wheel tester and the carrier.
Tester consists of four horizontal arms and a vertical arm to vertical load. The S-shaped load cells were employed in horizontal arms with a load capacity of 200 kg and another 500 kg in the vertical arm was embedded. The tire used in this study was a general pneumatic tire (Good year 9.5L-14, 6 ply)
In this study, artificial neural networks were used for optimizing the rolling resistance by 35 neurons, 6 inputs and 1 output choices. Comparison of neural network models according to the mean square error and correlation coefficient was used. In addition, 60% of the data on training, 20% on test and finally 20% of the credits was allocated to the validation and Output parameter of the neural network model has determined the tire rolling resistance. Finally, this study predicts the effects of changing parameters of tire pressure, vertical load and velocity on rolling resistance using a trained neural network.
Based on obtained error of Levenberg- Marquardt algorithm, neural network with 35 neurons in the hidden layer with sigmoid tangent function and one neuron in the output layer with linear actuator function were selected. The regression coefficient of tested network is 0.92 which seems acceptable, considering the complexity of the studied process. Some of the input parameters to the network are speed, pressure and vertical load which their relationship with the rolling resistance is discussed.
The results indicated that in general trend of changes, the velocity is not affected by rolling resistance. Rolling resistance increases when tire pressure decreases. This is due to energy consumption for creating deflection on the body of the tire at the lower levels of tire inflation pressure. Another variable parameter is the vertical load on the wheel and its logical relation with rolling resistance using neural network. The results showed that increasing the vertical load increases the rolling resistance.
The major purpose of this study was the feasibility of using learning algorithms for interaction between wheel and soil. The parameters of the wheel when clashes with soil are not stochastic and in spite of their complexity follow a specific model, certainly. Artificial neural network trained with a correlation coefficient of 0.92 relatively had a good performance in education, testing and validation parts. To validate the network results, the impact of some factors on the extraction process such as velocity, load and inflation pressure was simulated. The main objective of this article is comparing the network performance with basic principles and other scientific reports.
In this regard, the predictions by trained neural network indicated that rolling resistance is independent of the velocity of the wheel. On the other hand, rolling resistance decreases by increasing tire inflation pressure which is a general trend similar to other studies and reports in the same mechanical condition of the soil tested. Rolling resistance changes are directly proportional to load vertical variations on the wheel in terms of quantity and quality, similar to experimental models such as Wismer and Luth.

Monitoring and management of soil quality is crucial for sustaining soil function in ecosystem. Tillage is one of the management operations that drastically affect soil physical quality. Conservation tillage methods are one of the efficient solutions in agriculture to reduce the soil erosion, air pollution, energy consumption, and the costs, if there is a proper management on the crop residues. One of the serious problems in agriculture is soil erosion which is rapidly increased in the recent decades as the intensity of tillage increases. This phenomenon occurs more in sloping lands or in the fields which are lacking from crop residues and organic materials. The conservation tillage has an important role in minimizing soil erosion and developing the quality of soil. Hence, it has attracted the attention of more researchers and farmers in the recent years.
In this study, the effect of different tillage methods has been investigated on the crop residues, mechanical resistance of soil, and the stability of aggregates. This research was performed on the agricultural fields of Urmia University, located in Nazloo zone in 2012. Wheat and barley were planted in these fields, consecutively. The soil texture of these fields was loamy clay and the factorial experiments were done in a completely randomized block design. In this study, effect of three tillage systems including tillage with moldboard (conventional tillage), tillage with disk plow (reduced tillage), chisel plow (minimum tillage) and control treatment on some soil physical properties was investigated. Depth is second factor that was investigated in three levels including 0-60, 60-140, and 140-200 mm. Moreover, the effect of different percentages of crop residues on the rolling resistance of non-driving wheels was studied in a soil bin.
The contents of crop residues have been measured by using the linear transects and image processing methods. In the linear transects method, the experiments were replicated three times in each block due to increasing the accuracy and mean of datawas calculated. The tests were randomly performed in each block. Then, the number of nodes, which are located on crop residues of size 25 mm, longitudinally, was counted. So the percentage of crop residue in each block was calculated through the percentage of nodes. The experiments of rolling resistance were also performed in three levels, 10, 50, and 90% of crop residues, inside the soil bin.
Result showed that, in comparison with control treatment, tillage operation significantly decreased bulk density (p

Encountering soil from the viewpoint of management and product manufacturing has always been considered important, and an attempt is always made hat the tools and contrasting methods of soil be designed in such a way that itself prevents, as much as possible, the destructive consequences or energy waste that include economical or environmental limitations. Enhancing the soil encountering methods, quality reformation, and its related equipment, requires performing reliable tests in actual soil conditions. Considering the complexity and variety of variables in soil and machine contrast, this is a hard task. Hence, the numeral simulations are the key of all optimizations that illustrate efficient models by removing the costly farm tests and reducing research time. Tire is one of the main factors engaged with soil, and it is one of those tools that are discussable in both farms, and software environments. Despite the complexities in soil behavior, and tire geometry, modeling, tire movement on the soil has been the researchers’ objective from the past. A non-linear finite element (FE) model of the interaction of a non-driving tire with soil surface was developed to investigate the influence of the forward speed, tire inflation pressure and vertical load on rolling resistance using ABAQUS/Explicit code. In this research numerical and experimental tests were done under different conditions in order to estimate tire rolling resistance. In numerical tests, the soil part was simulated as a one-layer viscous-elastic material with a Drucker-Prager model by considering realistic soil properties. These properties included elastic and plastic properties which were obtained in the soil laboratory using relevant tests. The soil samples were prepared from the soil which was inside the soil bin. The same soil was utilized in experimental tests. Finite strain hyper elasticity model is developed to model nearly incompressible rubber materials for the tire. Tire model consisted of three components: tread, rubber and ring. Using a soil bin and one wheel tester with their related equipment, experimental tests were carried out in the workstation of mechanics of bio system engineering department of the Urmia University. This system includes various sections such as soil storage in dimensions of 22×2×1 meter, tools carrier or tracker, soil processing equipment, dynamic system, evaluation tools and controlling systems. In order to launch the collection and supply required power for wheel carrier, an industrial three phase electromotor with 22 kW (30 hp) was used. Both numerical and experimental tests were done at three levels of wheel dynamic load (1, 2, 3, 4 and 5) kN, tire inflation pressure (100, 200 and 300) kPa and four levels of speed (0.25, 0.45, 0.65, 0.9 and 1.15) m s-1 to obtain the rolling resistance of the tire. In order to evaluate the performance of final non driving tire-soil model to estimate the rolling resistance, numerical results were compared with preliminary experimental data obtained from the soil-bin tests. The comparison showed reasonably good agreement between the computed and measured general pattern of the rolling resistance at the tire-soil interface under different speeds, vertical loads and inflation pressures. In both tests, a specified relation was not seen between tire velocity and its rolling resistance, as it was not seen in empirical models such as Wismar and Luce. Correlation coefficient between experimental and numerical data, in the minimum and maximum value of tire inflation pressure was computed to be 0.06 and 0.016 percent, respectively. The amount of tire rolling resistance significantly increased with increase of tire vertical load. Correlation coefficient between experimental and numerical data, in the minimum and maximum vertical loads was computed to be 80 and 87 percent, respectively. Gent and Walter obtained the same results. The tire inflation pressure and rolling resistance variables had inverse relation to each other in both numerical and experimental tests. Correlation coefficient between experimental and numerical data was computed to be 97 and 73 percent in the minimum and maximum tire inflation pressure, respectively. The gradient of changes in tire inflation pressure - rolling resistance diagram was less in numerical tests. This was because of differences between real properties and the properties entered into the software. To conclude, in this investigation a new 3D tire-soil model was simulated which has specific features. The experimental results showed that the numerical data of estimation of non-driven tire rolling resistance were reliable. In both tests, the effect of changes in tire forward speed on rolling resistance was not significant.The amount of the tire rolling resistance significantly increased with increasing tire vertical load. Changes in tire inflation pressure and rolling resistance had an inverse relation with each other in both numerical and experimental tests. The slope of rolling resistance - inflation pressure diagram in numerical tests was less than the same diagram in the experimental tests.

Wheel numeric and different versions of mobility numbers are important models for predicting the rolling resistance. In this study, data related to the rolling resistance of cross ply and radial ply tires were compared with the resultant values from several models. Also, the preciseness of models in rolling resistance prediction was evaluated. For this purpose F test and 1-1 line method (p≥ 0.05) were used. According to the results of the evaluation, Cn and Bn models overestimated the rolling resistance for both cross ply and radial ply tires, but the slope of these models did not show any significant difference compared to 1-1 lines. Results indicated that these models had better prediction if an adjusting coefficient could be applied. The EMOB model showed better results compared to Cn and Bn models for cross ply tires, whereas it did not have acceptable predictions for radial tires. The N.I.A.E., FMOB and Dwyer models did not act well for any tire type, even though the best fit line of the Dwyer model did not show any significant difference with the 1-1 line for cross ply tires.