yousef abbaspour-gilandeh

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.

In recent decades, the deployment of technologies such as robotics, unmanned aerial vehicles, and satellite operations has become increasingly evident in all farming activities. The revolution known as smart agriculture, employed to enhance the efficiency of agricultural products, allows farmers to achieve higher yields while minimizing the use of fertilizers and other chemicals, thereby contributing to a reduction in greenhouse gas emissions and mitigating climate change. This paper investigates and analyzes the challenges and constraints of eco-friendly innovative technologies in the field of smart agriculture globally and in Iran. It also proposes indigenous solutions for the localization of eco-friendly innovative technologies within the country. The localized management of nutrients in domestic farms, despite their small size, is expected to provide relatively positive outcomes. Agriculture presents an excellent opportunity for the introduction of various types of robots. Countries such as China, Japan, and Australia have made significant strides in the development of automated tractors capable of performing various tasks on the farm. The use of drones in domestic farms has demonstrated an increase of approximately 30% in pesticide consumption efficiency. A national type of drone developed within the country has significant advantages over its foreign counterparts in terms of electronic engines, operational types and services, cameras and sensors, flight types, and monitoring functions. It is anticipated that the mentioned technologies, as part of smart agriculture, will significantly reduce the human labor intensity in farms to a much lower level than before.

Maize (Zea mays. L) is one of the most important crops acrossthe world that ranks third in terms of acreage behind wheat and rice. As this crop can adapt to different climatic conditions, it is of great importance and has a large area under cultivation.Therefore, maize is one of the major products of temperate, warm-temperate, subtropical, and humid regions. After wheat, rice, and barley, this plant is the main crop in Iran with the largest cultivated area.There are different types of maizeseeds, so their classification is essential to ensure quality. A key component of sustainable agriculture is quality assurance. On the one hand, techniques such as drying, cooling, and edible coating must be used to maintain the quality of agricultural products. On the other hand, effective and efficient methods should be developed to evaluate and classify their quality, which is used in seed and seedling processing centers, silos, and mechanized warehouses.The detection of various varieties of crop seeds using instrumental methods has been the subject of extensive research. As a non-destructive and rapid inspection method for the recognition and classification of cereal seed varieties, the visual machine is available. Machine vision-based automated methods can have a positive impact on food processing. In other words, this tool is the process of preparing and analyzing images of a real scene using a computer to obtain information or control a process. The features of images can be extracted using this machine to recognize and identify the quality of different types of products. To identify the types of plants, their growth patterns, and the effects of the environment on them to obtain more and superior products, machine vision occupies a special place and is one of the most important research areas. Inspection and quality control of factory output products is an important application of machine vision.Advances in image processing technology have opened up a wide range of machine vision applications in agriculture. The development of powerful microcomputers and specialized software has led to the use of image processing for the inspection of fruits and agricultural products, especially for quality control and sorting. Many agricultural products sorting systems used to separate fruits or crops based on color, shape, size, the extent of damage, crushing, bursting, spotting, etc., now rely on visual machines and image processing functions.Images of products moving on the conveyor system are taken by a CCD camera, transmitted to a computer for processing, and in these systems, the necessary data are extracted from them. Depending on the information obtained, commands are then issued to activate or deactivate a mechanical part so that the product can be removed from or allowed to cross the main path. Sorting is a common practice in many industries. Compared to mechanical systems, machine vision technology offers the highest accuracy and quality at the lowest cost and with the lowest error rate, so it can be considered the most effective solution to this problem. The agricultural industry is one of the areas where sorting and grading systems based on machine vision are urgently needed.The core elements of machine vision are image processing and analysis used together with new methods and classifiers such as neural networks, backup vector machines, fuzzy logic, etc. to perform classifications and required measurements. This study aimed to identify seeds of three maize varieties using macroscopic imaging techniques, evaluate the morphological and chromatic features in maize grains, and discriminate varieties using a stepwise method and remove some variables using LDA and ANN.

Three seed varieties of single cross 703,single cross 704, and single cross 705 were provided by the Agricultural and Natural Resources Research Centre of Ardabil Province in Pars Abad Moghan. The seeds were then taken to the Biophysical Properties Laboratory of the Department of Biosystems and Mechanical Engineering, MohagheghArdabili University.Three samples (20 g) of each variety were stored in a laboratory oven at 105 °C for 24 h to determine the initial moisture content of maize grains. According to the dry weight of grains, the initial moisture content of them was calculated by 10.50%. To distinguish 3 maize varieties, 180 samples were analyzed as single seeds (30 replicates in the anterior direction and 30 replicates in the posterior direction) for each variety with 60 replicates. In addition, 9 more samples were used in bulk with 3 replicates for each variety.Thus, we imaged a total of 189 samples. In addition, a digital scale with an accuracy of 0.001 g was used to measure the weight of the grains. Computer vision systems consist of five main components: lighting chamber, camera, analogue-digital card (for digitization), computer, and computer software. Images were taken using a Canon IXY DIGITAL 510 IS digital camera. A dome-shaped chamber was used to reduce noise and control ambient light. The system was illuminated with four fluorescent lamps and two rows of LED lamps, one white and one yellow. While the camera was pointed perpendicular to the imaging surface, it provided images with a resolution of 12.1 megapixels.In this case, the images were processed using MATLAB software. First, 10 maize seeds were randomly sampled from the first variety (single cross 703) and weighed using a digital balance. Then, parameters such as the large and small diameters and thickness of each grain were measured using a caliper of 0.02 mm. Then, these grains were placed at appropriate distances from each other on a plate of red cardboard in the opposite direction to be imaged. Finally, 30 maizeseeds were imaged in both directions and 60 images were taken as single seed. In total, we obtained 180 images of all three varieties as single seeds. To prepare the mass, first, some seeds of the first variety were placed in a cylindrical container (1.5 cm high, 4.2 cm in basal diameter, and 70.62174 cm2 in volume) so that the container was filled. After weighing, the mass of grains with a certain volume was poured onto the red plate in a circular pattern. In the end, the camera was placed on the bulk sample and the image was taken, just like the single grain image.The same procedure was repeated twice more on two more bulk samples of the first variety. Similarly, three bulk samples of two more varieties were imaged. In this way, a total of nine images were obtained. After each imaging, we measured and recorded the dimensions and weight of 10 randomly selected seeds from the imaged bulk. In the end, 189 images were obtained, including 180 single-grain and 9 bulk images.In the single sample feature extraction step using the bwlabel function, all samples were labeled and the grain morphological features were extracted. Then, the set of Regionprop functions was used to determine eight parameters, including area, perimeter, major principal axis, minor principal axis, integrity, irregularity, convex area, and equivalent diameter. An artificial neural network (NAA) and a statistical linear discriminant analysis (LDA) method were used to identify maize varieties based on their morphological and color characteristics. The data were normalized before analysis. LDA is a statistical method for classifying objects based on independent variables. The analysis was carried out using SPSS software. The diagnostic analysis includes stepwise analysis, principal component analysis, and elimination of recursive features. In this study, the stepwise method was used. In the usual method, all variables are included in the analysis. However, in the stepwise method, some variables were removed and only the variables with the greatest influence on the model were included. To classify the maize varieties, a network consisting of three layers: input, output, and hidden layers was used.

We performed image processing to classify three maize varieties based on the results obtained. A linear diagnostic analysis method was used in this study. A total of 16 predictor variables were used with an accuracy of 70.6%. Some variables were eliminated by a stepwise method. In addition, eight other predictor variables were analyzed with the same accuracy of 70.6%. Thus, although the number of predictor variables was reduced, the detection accuracy remained constant. Moreover, the highest accuracy of diagnosis (80%) was associated with the first variety (single cross 703). Additionally, the accuracy of the methods of ANN with 16 and 8 predictor variables was 75.6% and 72.2%, respectively. These values were higher than that of LDA.Predictive variables included areas, perimeter, major principal diameters, minor principal diameters, irregularities, concave areas, equivalent diameters, color indices (red, green, and blue) resulting from maize grain sample processing, weight, and grain size. The following factors were the most important predictors of varietal discrimination: thickness, major principal axis, minor principal axis, irregularity, equivalent diameter, integrity, red color index, and green color index. According to the results, the length and width of individual grains had no significant effect on variety classification.Our finding demonstrated thatmachine vision technology can be used in seed and seedling processing centers, silos, mechanized warehouses, and other places where maize seed crops need to be identified and separated in a non-destructive manner.

Drying is a common technology that provides a long post-harvest storage period for products such as cantaloupe. Hot air drying is a method that, if the conditions are optimized, gives the product better appearance and improved textural properties. In this study, drying time, specific energy consumption, energy efficiency, shrinkage, rehydration ratio, changes in total color, phenol and antioxidant content were modeled to optimize drying factors (air temperature and air velocity) using the response surface method. The drying processes of the samples were investigated at three temperature levels of 50, 60 and 70 °C and three velocity levels 0.5, 1 and 1.5 m/s. For optimization of the drying conditions (drying time, SEC, energy efficiency, shrinkage, RR, color changes, TPC and AC), the influences of two levels of independent variables including air temperature and air velocity were assessed by response surface method through a face-centered central composite design. The results showed that in the drying of cantaloupe using the hot air method by increasing the inlet air temperature and decreasing the air velocity, energy efficiency, rehydration ratio, total phenol content and antioxidant were increased, while drying time, specific energy consumption, shrinkage and color changes were reduced. The optimum point for drying cantaloupe samples was obtained at an air temperature of 70 °C and air velocity of 0.5 m/s. The results showed that drying at higher temperatures increases the desirability index of the model obtained from the response surface method. The authors believe the outcomes of the present study can be used as a framework for choosing efficient drying parameters for drying cantaloupe or similar fruits in HAD systems

This study is aimed to investigate the effect of a Hybrid Hot air-Microwave- Rotary Drum (HMRD)  dryer on the thermal properties, quality, and nutritional characteristics of green pea under different operational conditions. The experiments were conducted under different air temperatures (40, 55, and 70 °C), microwave power (90, 270, 450, and 630 W), and drum rotation speeds (5, 10, and 15 rpm). The thermal properties (e.g. drying time, effective moisture diffusion coefficient, activation energy, and specific energy consumption), quality features (color, shrinkage, and rehydration ratio), and nutritional properties (antioxidant activity and total phenol content) were determined. The results indicated that by increasing the microwave power, air temperature, and drum rotation speed, the drying time will decline. The highest diffusion coefficient and energy consumption were determined as 5.0410-11 m2/s and 109.91 MJ/kg, respectively. The lowest changes in color, shrinkage, and rehydration were calculated as 41.34, 24.08%, and 1.57. The highest total phenol (14.02 mg GAE/g d.w) and antioxidant (85.86%) were obtained. Thus the newly designed dryer can be employed for drying granular products and lead to satisfactory results.

Pepper (Capsicum annuum L.) is one of the most consumed vegetables in the world, containing a large amount of vitamins C and A, as well as minerals. Therefore, the consumption of about 60 to 80 g of pepper per day can provide 100 and 25% of the recommended daily amount of vitamin C and A, respectively. In addition, this horticultural product contains considerable levels of other health-promoting substances with antioxidant activity, including carotenoids, flavonoids, and other polyphenols.The quality of fresh pepper depends primarily on consumer acceptance, which is determined primarily by color, pungency, and aroma. Aroma plays an essential role in determining the sensory characteristics of these products. Volatile organic compounds (VOCs) are generally associated with the taste and aroma of foods and are important factors in assessing consumer acceptance or rejection. Consequently, food quality, originality, purity, and origin can be evaluated by determining VOC.Because it is important to distinguish hot peppers from sweet ones, we used an electronic nose to determine food quality in this study. Research has shown that the electronic nose is able to discriminate between products.

The variety used in this study was Padrón, a very popular species in Spain. The peppers can be harvested when they reach a length of 2.5 to 4 cm. One fruit out of 20 has a spicy flavor, while the rest has a mild taste. The green fruits showed no signs of ripening or discoloration and remained completely green.The peppers weighed an average of 12 ± 2 g when fresh. The weights for the sweet and spicy varieties were determined by weighing 30 fruits each. The fruits to be examined were evaluated by electronic nose.In this research, an electronic nose made in the Department of Biosystem Engineering of Mohaghegh Ardabili University was used. This device uses 9 low-power metal oxide (MOS) semiconductor sensors.The sample chamber was connected to the electronic nose and data collection was performed. The data collection was done by first passing clean air through the sensor chamber for 100 seconds to clear the sensors of odors and other gases. The sample odor was then sucked out of the sample chamber by the pump for 100 seconds and directed to the sensors, and finally fresh air was injected into the sensor chamber for 100 seconds to prepare the device for repetition and subsequent tests. 30 replicates were considered for each sample.The study began with the chemometrics method with principal component analysis (PCA) to detect the output response of the sensors and reduce the data dimension. In the next step, Quadratic detection analysis and Mahalanobis detection analysis (QDA and MDA) were used to classify 2 group of pepper. Principal component analysis (PCA) is one of the simplest multivariate methods and is known as an unsupervised technique for clustering data by groups. It is usually used to reduce the size of the data and the best results are obtained when the data are positively or negatively correlated with each other.Quadratic detection analysis and Mahalanobis detection analysis (QDA and MDA) are the most common monitored technique for separating samples into predetermined categories. This technique selects independent data variables to differentiate the sample that is to follow the normal distribution. The QDA and MDA are based on linear classification functions in which intergroup variance is maximized and intragroup variance is minimized.

Principal component analysis diagram shows the total variance of the data equal to PC-1 (90%) and PC-2 (6%), respectively, and the first two principal components constitute 96% of the total variance of the normalized data. When the total variance is above 90%, it means that the first two PCs are sufficient to explain the total variance of the data set. two group of pepper are well differentiated by PCA method. Therefore, it can be concluded that e-Nose has a good response to the smell of 2 group of pepper and they can be distinguished from each other, which shows the high accuracy of the electronic nose in detecting the smell of different products.The correlation loadings plot diagram can show the relationships between all variables. The loading diagram shows the relative role of the sensors for each principal component. The inner ellipse shows 50% and the outer ellipse shows 100% of the total variance of the data. The higher the loading coefficient of a sensor, the greater the role of that sensor in identifying and classifying. Therefore, the sensors located on the outer circle have a greater role in data classification and it is clear that the three sensors MQ4, MQ9 and TGS822 have played an important role in identifying 2 group of pepper.The correlation loadings plot diagram can show the relationships between all variables. The loading diagram shows the relative role of the sensors for each principal component. The inner ellipse shows 50% and the outer ellipse shows 100% of the total variance of the data. The higher the loading coefficient of a sensor, the greater the role of that sensor in identifying and classifying. Therefore, the sensors located on the outer circle have a greater role in data classification and it is clear that the three sensors MQ4, MQ9 and TGS822 have played an important role in identifying 2 group of pepper. Unlike the PCA method, the LDA method can extract multi-sensor information to optimize resolution between classes. Therefore, this method was used to detect 2 group of pepper based on the output response of sensors. The results of detection of cultivars were equal to 100%.The electronic nose has the ability to be used and exploited as a fast and non-destructive method to distinguish sweet and hot pepper from leaf odor. Using this method in identifying sweet and hot pepper will be very useful for consumers, especially processing units and food industries in order to select appropriate cultivars. Since the detection of pepper using an electronic nose has not yet been researched, the promising results of this study can be widely applied in the sorting industry.

Wheat is one of the most important grains in the human food basket, which is known as a major source of energy, protein and fiber due to its valuable nutrients. The post-harvest stage of the wheat crop is explained in two ways: either it is sent to food processing factories or it is stored in silos for sale at regular intervals. Various parameters represent the quality of wheat grain that the percentage of purity of the mass is one of the main factors affecting the purchase price of the product. Several types of non-wheat grains, including germinated grains, broken grains, legumes, weed seeds, insect-damaged grains, foreign matter (pebbles, straw), etc. are the main sources of impurities in wheat. Researchers have always tried to develop computer-based solutions for impurities in wheat grain to be able to develop automated wheat grain separators. Image processing based on morphology, color and texture characteristics of grains has been used for various applications in the grain industry, including grain quality assessment and wheat classification. Various grading systems based on image processing have been studied. The presence of various impurities at the time of wheat harvest is one of the important factors in reducing the quality of wheat, so it seems necessary to detect impurities in wheat grain. The quality of wheat has a significant effect on its marketability. In addition, if wheat is used as a crop seed, the impurities in the mass will be a determining factor in the yield of the future crop.

In statistical analysis of data, situations are sometimes encountered in which the relationship between problem variables is very complex. This makes it difficult to analyze and process the data, so that sometimes no definite relationship can be found between the variables. In these cases, instead of purely theoretical research, applied research is done. Artificial neural networks are one of the solutions that, by processing experimental data, discover the knowledge or law behind the data, and transfer it to the network structure. In this study, the possibility of identifying wheat in wheat grain mass and estimating the amount of impurities in the mass, based on video processing using two types of artificial neural network (ANN) algorithms and hybrid genetic algorithm (GA) has been investigated. For this study, the code related to the artificial neural network with two hidden layers and the number of different neurons in each layer was written in MATLAB software. This code was used to identify and classify each component in the wheat grain mass. The main task of ANN is to learn the structure of the model data set. To achieve this, the network is trained with examples of related outcomes to generalize the capability. Multilayer artificial neural networks (MLPs) are the most common ANN models. In the present study, to reduce the computational load and increase the accuracy of the results, as well as to save time, some parameters that can be changed in the genetic algorithm were extracted as a fixed number using trial and error method. Among these parameters is the number of layers in the main structure of the neural network.

A hidden layer with a number of neurons 2 to 12 was used as an even number. It should be noted that the number of neurons above this amount of computational time increased dramatically and did not have much effect on classification accuracy. Another parameter in this field is the Max Reproduction factor (Max Generation) which according to the results of trial and error for this factor, the results showed that increasing this value more than 30 has little effect on classification accuracy and decreases the mean squared error. And only increases the computation time, so a constant value of 30 was considered for this parameter. 4 values of 50, 100, 150 and 200 were used for the Pop Size parameter. Values above 200 dramatically increased computational volume and processing time, so values over 200 were omitted. Values less than 50 also reduced classification accuracy, and values less than 50 were excluded from the analysis process. After preparing the video of mass movement on the conveyor belt, using MATLAB software and image processing toolbox, 17 shape features, 12 color features and 6 texture features were extracted from each grain sample in the image. The data obtained from the image processing section were classified into five categories: wheat, barley, oats, straw and weed seeds. Two types of artificial neural network (ANN) algorithms, feeder (newff) and feeder (newcf), and hybrid genetic algorithm (GA) were used to achieve the highest classification accuracy and minimum error.

Techniques related to image segmentation were used to separate objects within the image. In this stage of image processing, an attempt is made to separate interconnected objects using a variety of morphological and color methods in the image. In fact, the purpose of separating interconnected objects in the image is to make it possible to examine the individual objects in the image separately and extract the different characteristics of each of them. The results showed that from 36 different artificial neural network (ANN) structures, the 5-4-10-35 structure for the newff algorithm with 100 and 89.74% accuracy for training and testing conditions, respectively, with a processing time of 10.39 seconds and the structure 5-8-10-35 for newcf algorithm was obtained with 100% accuracy for training conditions and 87.17% for test conditions with a processing time of 44.94 seconds. On the other hand, the results of the hybrid GA algorithm showed the highest classification accuracy with 95.55% and 86.66% for training and testing, respectively, in a structure in which 8 neurons in the hidden layer with a population size of 200 were used. Was obtained. According to the obtained results, the use of video processing using ANN artificial neural network and newff algorithm due to high accuracy and lower computation time is a powerful tool for detecting impurities in wheat grain mass. Therefore, the use of artificial neural network with the help of video processing has the ability to classify wheat grains and can be used in a practical way. Given the importance of grain mass velocity in the discussion of industrial application, it is suggested that higher grain mass velocities be investigated in a similar way.

The four-wheel drive and rear-wheel drive tractors are commonly used in agricultural operations. In order to investigate the effect of a type of driving system a series of tests were performed usin the three driving systems of foour wheel drive, rear wheel drive and front wheel drive in different axle loads of 0, 150 and 300 kg, tire inflation pressures of 170, 200 and 230 kPa and travel speeds of 1.26, 3.96 and 6.78 km/h. Bulk density was measured as an indicator of soil compaction at different depths of 10, 20, 30 and 40 cm. Also, under the different conditions, the drive wheel slip was measured. To carry out the tests, the four-wheel tractor of Goldoni 240 was used which has the ability to work with mentioned driving systems. The experiments were carried out under controlled conditions in a soil channel  with the length of 3 m and a width and depth of 1 and 0.6 m, respectively. Test were conducted in completely randomised block design with three repetations and results were analysied using SPSS 22 software. The results showed that by changing the driving system from 4WD to RWD and FWD, there was a significant increase in soil density, with the lowest density associated with 4WD system and the highest density related to FWD. The reason for increasing the density by changing the driving system can be attributed to different slip levels in each of these systems due to the lower slip percentage of the 4WD system than the other two systems.  Increasing axial load increased soil boulk density. Of note that with increasing the axial load, the stress was transferred from the surface soil to the subsoil layers. As the axial load on tire increases, the subsoil density was closer to the surface layer. Increased axial load on tire and decreasing tire pressure reduced wheel slip. Stepwise regression model with determination coefficient of 0.92 and according to calculated standard coefficients showed that axial load, soil depth, type of driving system, tractor speed, and finally tire pressure, have the greatest effect on soil bulk density, respectively.

In this research, horizontal, vertical and side forces on a single bentleg plow (SBLP) and a double bentleg plow (DBLP) at four forward speeds of 1.8, 2.3, 2.9 and 3.5 kmh-1 and at the constant depth of 40 cm was evaluated. The experiment was arranged in the randomized complete block design with four replications. In each experiment, three perpendicular soil forces were measured and recorded. Results showed that increasing forward speed from 1.8 to 3.5 kmh-1 resulted in increasing horizontal, vertical and side forces by 14, 3.5 and 1% for SBLP and 13, 1.2 and 11.5% for DBLP, respectively. Other results indicated that horizontal force for DBLP was more than twice of that for SBLP. The vertical force was lower for SBLP but it was not more than half that of DBLP and the side force for DBLP was very less than that for SBLP. Generally, using the DBLP increases tine penetration and decreases side force which leads to balanced operation of the subsoiler and tractor and therefore recommended.

Wild oat (Avena fatua) is the most common weed of wheat fields. Given that the presence of even small amounts of wild oat in the wheat grain mass may lead to a sharp drop in the quality of flour produced, separation of wild oat from wheat will increase the purity of the seed and enhance the economic value of the crop. In present study, some physical properties of wheat and wild oat, including geometric properties, gravity properties, frictional properties and initial moisture content were determened. A gravity separator - equipped with some tools to adjust  five parameters: air flow rate, frequency of oscillation, amplitude of oscillation, longitudinal slope and latitudinal slope of the table - was used to separate wild oats from wheat grain mass. The effects of these parameters were studied to achieve maximum separation of wild oat from wheat mass. Statistical analyses were performed in two factorial experiments in a completely randomized design. Also, using dimensional analysis, a dimensionless dimensional parameter V/aω was obtained (where v is air speed, a is oscillation and ω is oscillation frequency), which was effective in evaluating the effect and reducing the number of parameters. The results showed significant differences (1%) in moisture content, mass and particle density, boundary velocity and interaction between grain type and friction surface between two grain types. Also, the results indicated that the maximum separation of wild oats from wheat (70.47%) was obtained when the air flow rate was 6 m/s, the oscillation was 5 mm, the oscillation frequency was 395 cycl/min,, and the longitudinal slope and latitudinal slope were 2.5° and 1.5°, respectively.

In this research, the adaptive neuro-fuzzy inference system was used for predicting the parameters related to traction of tractor included of drawbar power (DP), drive wheels slippage (S), traction efficiency (TE) and overall energy efficiency (OEE) in tractor- implement combination under the effect of independent variables included of tine type (subsoiler and paraplow), depth (30, 40 and 50 cm) and forward speed (1.8, 2.3, 2.9 and 3.5 km/h) during subsoiling operation. The field data were used to create the regression and ANFIS models for predicting the studied parameters and the results of them were compared together. The field results showed that all independent variables were effective on the studied parameters except TE. The increment of forward speed and depth resulted in increase of S, DP, OEE and decrease of TE. Moreover, with considering the studied parameters, the paraplow tine was more commodious than subsoiler tine. The results of ANFIS part showed that about S, DP, TE and OEE, the membership functions of Trimf, dsigmf, Primf and Gaussmf with the mean square error of 0.0159, 0.0231, 0.0212 and 0.0224 also correlation coefficient of 0.9996, 0.9999, 0.9985 and 0.9997 caused the best models to predict, respectively. ANFIS models had higher accuracy than regression models and it could be calculated the model outlet for a special inlet using ANFIS outlet surfaces.

In this research, the adaptive neuro-fuzzy inference system was used for predicting the imposed forces on the tines and tractor fuel consumption during subsoiling operation. The draft and vertical forces imposed on subsoiling tines and tractor fuel consumption were measured under the effect of tine type (subsoiler and paraplow), tillage depth (30, 40 and 50 cm) and forward speed (1.8, 2.3, 2.9 and 3.5 km/h). The field data were used to create the regression and ANFIS models for predicting the studied parameters; the results obtained from applying two models were compared with each other. The field results showed that all independent variables were effective on the studied parameters. Increase in forward speed and tillage depth resulted increase in draft force, vertical forces, and also fuel consumption. Moreover, from the point of consumption of fuel, the paraplow tine was more profitable than subsoiler tine. The results of ANFIS part showed that draft force, vertical force, and fuel consumption, the membership functions of Gaussmf, Trimf and dsigmf, with the mean square error of 0.0156, 0.0231 and 0.0212 also correlation coefficient of 0.999, 0.989 and 0.991, respectively, were the best models for prediction. ANFIS models were found more accurate than regression models, and it could be possible to calculate the model outlet for a special inlet using ANFIS outlet surfaces.

Presence of foreign materials with the product is one of the important problems of wheat production. The economic value of the produced wheat and the degree of purity of the produced seeds increases with the separation of wheat mass impurities. Hence, in this research, a gravity separator table was used to remove impurities from wheat bulk. The machine has adjusting five parameters of air velocity, frequency of oscillation, amplitude of oscillation, longitudinal slope and latitudinal slope of the table. The effect of these parameters was studied to achieve maximum impurity separation from wheat bulk. Statistical analysis was performed in two factorial experiments based on completely randomized design. In the first experiment, the effects of three parameters of longitudinal slope, latitudinal slope and frequency of oscillation of the table were investigated and in the second experiment the effect of two other parameters was investigated. Also, using dimensional analysis, a dimensionless number parameter was obtained which was effective in evaluating the effect and reducing the number of parameters. The results showed that the maximum separation of impurities from wheat bulk was 87.03% at longitudinal slope of 2.5 °, latitudinal slope of 1.5 °, frequency of oscillation of 395 cycles per minute, amplitude of oscillation of 5 mm and air velocity of 6.75 m/s,. Also, with increasing longitudinal slope from 2.5 ° to 4.5 °, latitudinal slope from 0.75 °  to 2.5 ° (in most cases) and the amplitude of oscillation of the table from 5 to 7 mm, the separation of impurities was reduced and with increasing the air velocity from 5.25 to 6.75 m/s the separation of impurities was increased.

The acquisition of basic knowledge in quality control of wheat seed using machine vision technology is important. The objective of this research was to develop hardware and appropriate software to determine seven-grain groups in wheat seed samples. Ninety-one features were extracted through 21000 single seed images and the shape, texture and color features were ranked. Five classification models were investigated. The highest classification accuracy was obtained by artificial neural network with two hidden layers and the first 35 superior features. In the test run of this model with independent data, classifying accuracy for big white wheat, small white wheat, broken white wheat, wrinkled white wheat, red wheat, barley and rye were 100, 96.7, 99.3, 90.3, 99, 99.7, and 98 percent respectively with the average of 97.6 %. Shape features were more prominent and textural and color characteristics followed it respectively. Average classification accuracy in models of linear discriminant analysis, quadratic discriminant analysis, K- nearest neighbor and artificial neural network with a hidden layer were 95, 96.7, 91.6 and 97.3 % respectively. In the context of this study, the machine vision system comprising an industrial digital camera and artificial neural network with two hidden layers was identified as a valuable system in the investigation of the visual qualities of wheat seeds.

Optimal design for sourcing, grading and other post-harvest operations requires the availability of appropriate information about their physical properties. Also, achieving a high quality product requires the fight against weeds and impurities in the product. Therefore, in this research, some physical properties of wheat and barley were measured. A gravity separator was also used to separate the barley in the wheat mass. This machine has five customizable parameters includes air velocity, frequency of oscillation, amplitude of oscillation, longitudinal slope and latitudinal slope of the table. The effect of these parameters was investigated in the form of two factorial experiments in a completely randomized design to achieve maximum separation of barley from wheat mass. The results of experiments showed that in the conditions of air velocity of 6.75 m / s, the oscillation amplitudes of 5 mm, the longitudinal slope of 2.5 degree, the latitudinal slope 0.75 degree and the frequency of oscillation of 395 cycl / min, the maximum separation of barley from wheat mass to 20.6 % was achieved. In most cases, with increasing latitudinal slope from 0.75 degree to 2.52 degree , the longitudinal slope of the table from 2.5 degree to 4.5 degree and with the increase of the frequency up to 435 cycl / min, the separation of barley from the mass of wheat decreases. Also, the minimum amount of barley separation from wheat mass in condition of oscillation frequency of 455 cycl / min, l o n g i t u d i n a l slope of 4.5 degree, latitud in a l lope of 1.5 degree, oscillation a mplitude of 5 mm and air velocity of 6 m/s was obtained 9.417 %.

Traction efficiency and fuel consumption hgave close affinity and are considered to be important unit operations, especially during primary tillage operations. Therefore, analyzing factors that affect the amount of Traction efficiency and fuel consumption is considered important. Amongst these factors, forward speed of tractor and tillage depth are of prime importance. Experiments were conducted for comparison of draft force and fuel consumption using, three types of cultivator blades (flat Duckfoot, Duckfoot with curve shank and Chisel plow), under sandy loam soil condition by using a factorial experiment based on randomized complete block design (RCBD). The effect of forward speed (3, 6.5 and 9 km/h) and tillage depth (10 and 20 cm) was the experimental conditions. Within each experimental plot, draft force of cultivators, fuel consumption, soil cone index, soil dispersion and percent of soil moisture content were measured.Analysis of variance showed that the effects of the blade type, forward speed and depth on the draft force and fuel consumption was significant at 1%. Comparing the draft force and fuel consumption of blades in different forward speeds and also considering the relatively light texture of the soil, it was found that duckfoot blade with curve shank with forward speed of 3 km/h was more appropriate.

Suitable soil structure is important for crop growth. One of the main characteristics of soil structure is the size of soil aggregates. There are several ways of showing the stability of soil aggregates، among which the determination of the median weight diameter of soil aggregates is the most common method. In this paper، a method based on adaptive neuro fuzzy inference system (ANFIS) was used to describe the soil fragmentation for seedbed preparation with combination of primary and secondary tillage implements including subsoiler، moldboard plow and disk harrow. Adaptive neuro fuzzy inference system (ANFIS) is a suitable approach to solving non-linear problems. ANFIS is a combination of fuzzy inference system (FIS) and an artificial neural network (ANN) method and it uses the ability of both models. In this study، the model inputs included “soil moisture content”، “tractor forward speed” and “working depth”. The performance of the model was evaluated using the statistical parameters of root mean square error (RMSE)، percentage of relative error (ε)، mean absolute error (MAE) and the coefficient of determination (R2). These parameters were determined as 0. 135، 3. 6%، 0. 122 and 0. 981، respectively. For the evaluation of the ANFIS model، the predicted data using this model were compared to the data of artificial neural network model. The simulation results by ANFIS model showed to be closer to the actual data compared with those made by the artificial neural network model.

Draft of different tillage tools is an important parameter for performance measurement, evaluation of tillage tools and also for determining the amount of required energy. Prediction of this parameter could be beneficial in many farm management practices, prediction of energy requirements and selecting appropriate tractor. In this study, field experiments were carried out at two soil types, namely, clay loam and loam clay, for predicting draft of a vertical narrow tillage tool, using artificial neural network and also, for comparison of developed model accuracy with that of regression models. Some parameters such as soil types, soil conditions, tools parameters and operational parameters were selected as inputs to artificial neural network. Within each type of soil, experiments were conducted in the form of factorial experiment based on randomized complete block design (RCDB) with three replications. Different levels of soil moisture content (factor A) 5-16 percent for dry soil and 17-38 percent for wet soil, tractor speed (factor B) at four levels of 1, 1.5, 1.8 and 3 km/hr, working depth (factor C) at four levels of 10, 20, 30 and 40cm and blade width (factor D) in four levels of 2.5, 3, 3.5 and 4cm were selected. Back propagation neural networks with three different training algorithms (gradient descending algorithm with momentum, descending scaled gradient and Levenberg-Marquardt) were adopted to predict the draft. Back propagation neural networks with Levenberg-Marquardt training algorithm presented better accuracy in simulation (95.05%) and correlation coefficient (R2 ) of 0.9935 as compared to others. The obtained data from neural network model were compared to ASAE and Ashrafizadeh (2006) models; the result showed that the predicted data by artificial neural network were very close to real data obtained from field experiments and the regression models did not have much proficiency for predicting draft at the studied area.