Journal of Researches in Mechanics of Agricultural Machinery

Abstract Nowadays, most of the planting machines that are used in Iran, do not have enough planting accuracy or because of having complex systems, require a lot of initial investment for farmers. These tools are offered at a high price and are not suitable for small farms that have low performance. In Iran, the method of planting chickpeas is mostly done manually, which requires spending a lot of time and money. Thus using such row crop planters will save costs and reduce the duration of planting. In this research, an automatic distribution system of a row crop chickpea planting machine was constructed and evaluated, and a new system was considered for the planter which automatically plant chickpea by relying on the uniform flow of seeds. For this purpose, the indicators including no planting, multiple planting, quality of nutrition and precision in planting distance were considered to investigate the uniformity and accuracy of chickpea planting. Tractor speed at three levels of 3, 5 and 7 km/hr and the distance between seeds at three levels of 5, 10 and 15 cm were used to evaluate the performance of the system. The results showed that the effect of speed on all indicators was significant at the level of 1%. Also, the effect of the distance between seeds on the indicators of multi-planting, nutrition quality and accuracy in planting distance was also significant at the level of 1%, however it had no significant effect on the no-planting index. In none of the indices, the mentioned variables had no mutual effect. Evolutionary polynomial regression was used to investigate the relationship between constant variables of speed and distance between seeds with distributed functional variables. This regression model was able to fit the relationship between variables with a high regression coefficient. According to the measured indices, the uniformity and precision in planting chickpeas with this automatic distributor was desirable.

Abstract Drying is one of the most effective methods to increase the shelf life of food products. Increasing efficiency and reducing energy consumption in drying is essential. Saving time and energy are the best advantages of the microwave drying method. So this work aims to investigates the influences of microwave power (P), mass of product (M) and time (T) on the absorbed energy and energy loss and also predict the efficiency during microwave dehydration of apple leaves. We perform the investigation at P=100, 300 and 600 W, M=20, 40, 60, 80 and 100 g; and T=60, 90, 120, 150 and 180 s. In this paper, three different machine learning methods are used to simulate the absorbed energy and energy loss of apple along with prediction of the microwave efficiency during dehydration process. These methods are: artificial neural networks (ANNs), adaptive neuro fuzzy inference system (ANFIS) and support vector machines (SVM) coupled with firefly algorithm (FFA) Our results indicates that the amount of absorbed energy by apple during microwave dehydration strongly depends on on the amount of the mass. The highest and lowest efficiency of the microwave was observed in the power of 600 W and mass of 100 g, and the lowest efficiency was observed in the time of 180 s and power of 100W. Also, absorbed energy at 600W was found to be almost four times higher than that at 100 W. ANFIS and SVM-FFA showed good results than ANN for predicting absorbed energy, energy loss and microwave efficiency.

Abstract An accurate, reliable, online, no-effect passing materials, continuous and non-invasive measurement of solids’ mass flow rate in conveying pipelines has been a technically challenging area, which becomes increasingly significant to achieve efficient utilization of energy raw materials and to reduce waste. In this study, a grain flow rate meter based on the centripetal force was designed, constructed, and evaluated. Initially, Discrete Element Method (DEM) analysis was performed to evaluate the easy passage of granular materials without obstructing the passage of materials in the device, as well as to determine the velocity of material passage on the measuring pan for three different rates of wheat 15.62, 32.90 and 66.75 kg/s. According to the results for three different fall rates, the velocity of the material on the measuring plate was 2.55±0.018 m/s. In the first stage of the evaluation, load cell calibration was done using standard weights from 100 to 1800 N with steps of 100 N and for validation from 5 to 500 N with steps of 5 N. Finally, the load cell calibration was confirmed with a coefficient of determination above 99% with RMSE=3.88 N. Then, the apparatus was evaluated for specific amounts of wheat in seven different amounts from 5 to 35 kg with 5 kg steps with a random shedding rate. The results showed that the device is able to measure the rate of granular material shedding with very high accuracy (determination coefficient above 99% and mean absolute percentage error 0.55%).

Abstract Leafy vegetable harvesting machines are made with the aim of improving the efficiency of harvesting, reducing the damage to the plant, reducing the need for manpower and also reducing contamination. In current research, a cutting system for leafy vegetable harvesting machine was designed and constructed. The system was tested on watercress, spinach and basil. The machine consists of a band saw blade that is placed on two pulleys. The pulleys are rotated by an electric motor powered by three-phase electricity. Driving pulley was connected to the motor by a shaft and a coupling. Two ball bearing were used to prevent angular deflection of the shaft. The driven pulley is also attached to the U-shaped frame by a shaft and ball bearing. The bearing connected to the movable pulley is responsible for adjusting the required tension of the saw blade. A screw and two nuts were used to provide the blade tension by screwing. The assembly is mounted on an inverted U-shaped metal frame, which is attached to the main chassis of the machine. The wheels are connected to the main chassis by a height adjustment mechanism. The constructed system was tested at blade linear velocities of 3.7T 5 and 6.3 m/s and forward speed levels of 1, 1.5 and 2 km/h. Experiments were designed by Minitab 2018 software and 13 experiments were designed for each of the three plants using the central composite design method. According to the results obtained in this study, the optimal blade linear velocity was 6.3 m/s and the forward speed in the range of 1.7 to 2 km/h. Also, the stems were cut by this machine without crushing and caused the least damage to the plants.

Abstract Identifying the growth stages of fruits in orchards is an important factor in improving the quantity and quality of the final product. Having such information helps the growers to apply the appropriate treatment for each growth stage and also to get a proper understanding of the fruit harvesting time, which may change due to changing weather conditions. Therefore, in the present study, color images of golden apples were used to estimate the weeks remaining to the harvest time. The EfficientNetB1 model was used to classify images taken from different weeks of apple fruit development using deep learning technology and convolutional neural networks. The data were divided into three categories: training (60%), validation (20%), and test (20%). Also, two pre-processing processes, i.e. data normalization and data augmentation, were used to obtain better results. Finally, Nadam optimizer and categorical_crossentropy cost function were considered in creating the model. The results showed that the developed model would have a good ability to classify input images. The value of the correlation coefficient (R) for training, validation, and test data was 0.86, 0.88, and 0.87 respectively. Also, the ability of the model to classify different classes was presented using precision, recall, and f1-score parameters for each class, according to which some classes achieved 100% accuracy. Consequently, the obtained results can be used as a platform for the development of harvesting robots, mobile apps, as well as aerial imagery systems using drones, etc. to fulfill various purposes in precision agriculture, and in particular, precision horticulture.

Abstract Producing powder from fruit pulp is a good way to prevent the loss of useful properties in the remaining meat from the skin, juice and core of fruits. The physicochemical properties of the powder play an important role in its storage time, customer friendliness and taste.This process was carried out using a vacuum dryer using the atmosphere control method and was checked in terms of drying time and browning index. The dryer is set on a laboratory scale for five temperature levels of 45, 55, 65, 75 and 85 °C and five vacuum pressure levels of 40, 50, 60, 70 and 80 kPa for a thickness of 6.5 mm.The statistical analysis of the obtained data and the optimization of the vacuum drying process were performed using the response surface method. The results showed that by increasing the temperature of the drying chamber, the drying rate of apple pulp sheets increased and the drying time decreased by 78.3%. The temperature values of the drying chamber were significant to the color indices of apple pulp powder. The lowest amount of browning index under the conditions of the temperature of the dryer chamber of 45 degrees Celsius and the vacuum pressure of 60 kPa for the vacuum dryer using the atmosphere control method was 100.26. The optimum point of the powder produced from the dried apple pulp sheets was proposed by the vacuum system using the atmosphere control method at the temperature of the drying chamber at 74.83 °Cand the vacuum pressure at 55.9 kPa. Under these conditions, the optimal value of the response variables, including drying time and browning time, were obtained in equal order.

Abstract The appropriate tree fertilization with essential nutrients is considered as one of the major factors in enhancing the quality and quantity of horticultural crops. Applying traditional tree fertilizing methods imposes high costs on the growers and has lower efficiency compared to mechanized methods. It shows the importance of applying and improving the mechanization of fertilizing operation in the horticultural sector. In the present study, multi-criteria decision-making (MCDM) methods including deterministic analytical hierarchy process (AHP) and fuzzy analytical hierarchy process (FAHP) and analytic network process (ANP) were used to score and select the appropriate fertilizing method for apple trees based on the growers and expert’s perspective. The criteria including fertilizing operation cost, crop yield, the percentage of tree damages, easiness of entering and moving fertilizing equipment in tree rows, field capacity (with or without machinery), the comfort and safety of fertilizing operation, after-sales service, access to the required machinery and implements, crop selling price, and crop quality were used in the above mentioned methods. The fertilizing methods considered in the present study were traditional fertilizing (Shovel), fertilizing with orchard Trencher, fertilizing drilling motor, fixed centerline tractor digger, and off-set digger. Based on the results obtained from AHP and FAHP, the priority of fertilizing methods was determined as tractor off-set digger, fixed centerline digger, drilling motor, and orchard Trencher, respectively. Based on the ANP method, off-set and fixed centerline diggers had the highest priority, which were followed by Trencher, drilling motor, and traditional method. Results showed that applying the orchard tractors equipped with tractor digger, especially off-set type, can play an important role in enhancing the quantity and quality of produced apple, as well as reducing the costs of fertilizing operation.

Abstract Medicinal plants are widely used in many fields around the world. Medicinal plants are an integral part of daily life and the increase in demand for these plants leads to fraud and reduced quality in the final product. Therefore, authentication is vitally important for consumers. Mint is valuable because of its medicinal properties and its essential oil, which is used in the food, pharmaceutical, cosmetic and health industries. In this research, the use of electronic nose to detect the age of mint plant by the odor emitted from its leaves was investigated. The main branches of mint plant with different ages of one to five years were taken from the distance of 4 to 5 cm from the ground. An electronic nose equipped with 8 metal oxide sensors was used to carry out experiments. To analyze the data, PCA, LDA and QDA analyzes were used. PCA results showed that 95% of the total variance of the data was explained by PC1 and 4% by PC2, and the two principal components expressed accounted for 99% of the variance of the normalized data. Also, the QDA method was 100% accurate in determining the age of the mint plant. The electronic nose has shown that it is a fast and effective tool to detect the quality parameters of plants and agricultural products.

Abstract Preparation and supply of ready and semi-ready food products for consumers is important due to time constraints in today's world. For this purpose and in order to create such a platform, it is necessary and essential to know the characteristics of agricultural products. The knowing information about the properties and mechanical behavior of agricultural products is necessary in order to design mechanized and automatic agricultural equipment. The properties that are effective in cutting cellular materials are: compression, stretching, bending and cutting. These characteristics depend on the species, variety, ripening, moisture content and cell structure. In this research, mass density modulus, crushing resistance coefficient and efficient cutting coefficient of faba bean have been obtained, by using cutting theory and existing relationships. A completely randomized design with factorial testing was used to investigate the effect of cutting angle and cutting speed on these traits. The results showed that the effect of the cutting angle on the values of the mass density modulus and the crushing resistance coefficient is significant at the level of 1%, and with the increase of the cutting angle, the values of the crushing resistance coefficient decreased and efficient cutting coefficient increased. It was also found that the increase in cutting speed caused a decrease in crushing resistance and an increase in efficient cutting coefficient, while the changes in the mass density modulus did not follow a regular trend.

Abstract Red meat, having all kinds of essential amino acids needed by humans and as one of the main sources of protein for human societies, has long been of great importance in the human diet, this special place has made the need to provide healthy and high-quality materials more urgent than ever. One of the most important and practical techniques for evaluating meat quality is studying its appearance and physical characteristics. This research designed and implemented a model based on convolutional neural networks based on three structures: Mobile Net, InceptionV3, and VGG16. In this research, the shear resistance value of each meat sample was measured by the Warner-Bratzler method, and input data for training and evaluation of the convolutional neural networks were digital images taken by the LG model smartphone (LG G4 H815) in uncontrolled conditions and independent of the environment and light.
In the end, the designed models were able to classify the prototypes based on the extracted features with acceptable accuracy. The performance of the designed models was evaluated with statistical indicators of accuracy, precision, sensitivity, and specificity, and the best classification model was the model designed based on the structure of the Mobile Net, which was able to classify image data with an accuracy of 92.61%.