Journal of Researches in Mechanics of Agricultural Machinery

Abstract Disease management in grapevine has become one of the basic issues that farmers have to face. Diseases can greatly affect the performance and life of this plant. With increasing environmental pressures and climate changes, the need for new and smart methods in managing diseases and pests has become inevitable. In this research, in order to diagnose and classify grape plant leaf diseases with the names Black Rot, Black Measles and Leaf Blight, after removing the background from the images of the leaves and extracting the features of texture, color and shape from the images, A combination of support vector machine classifier and butterfly optimization algorithm was used to select the most important features in the diagnosis of grape plant leaf disease. The results of the precision for black rot, Black Measles, and Leaf Blight diseases and healthy leaves were 100, 100, 100 and 95% respectively, and the classification accuracy for the diagnosis of the diseases and healthy group was 98.75%. Also, 15 characteristics of texture, color and shape were introduced to the researchers of plant pathology and data science with the help of butterfly optimization feature selection algorithm. The classification results showed that the use of image processing and machine learning has a high ability to diagnose and classify plant diseases.

Abstract Agricultural mechanization is considered as a basic approach in the production of agricultural products, and the goals such as carrying out agricultural operations on time, reducing production costs, reducing labor intensity, managing the consumption of agricultural inputs, creating attractiveness in agricultural activities, improving the quality and quantity of production, and basically making it economical It provides mass production of agricultural products. A requirement for correct planning regarding rice farming in Guilan province is sufficient knowledge of the current state of its mechanization. For this purpose, defined and meaningful indexes and standards are needed. Knowing and evaluating these indexes can be used in the correct estimation and optimal use of agricultural machines and timely and quality agricultural operations. In this study, by collecting information and data by completing the questionnaire and by referring to the available statistical sources, the indexes that determine the status of rice mechanization in the province (including the degree, level and capacity of mechanization, actual and potential executive power), working days and farm productivity Calculated. The number of agricultural machines needed to perform mechanized operations in different stages of rice production was estimated using the time opportunity method. The results of this study have been showed that the degree of mechanization of tillage, planting with transplanter, spraying, weeding and harvesting (reaper and combine) is 100%, 72.55%, 23.57%, 4.62% and 84.83% respectively, the level of mechanization was 3.55 horsepower per hectare, and the average mechanization capacity was 404.48 horsepower per hectare. There is also a tractor for every 27 hectares, a tiller for 4 hectares, a transplanter for 30 hectares, a weeder for 563 hectares, and a rice combine harvester for every 60 hectares. In addition, there are 2 tractors and 2 transplanters for every 100 users. According to the results, the number of machines available in the province in tillage (Primary tillage, Secondary tillage, Puddling, Leveling), Plant Protection (spraying and weeding) and harvesting (Rice reaper, rice combine harvester, baler) are 19.85, 33.23 and 55.69% more and in planting 61.2% less than the estimated number.The comparison of the current conditions with the estimated shows that there is no proper planning in the supply and distribution of agricultural machines.

Abstract One of the most important agricultural operations in wood fields, row crop fields, gardens, and traditional greenhouses is breaking up, churning, aerating the topsoil, and removing weeds. In this research, a light-weight (65 kg) plow-harrow machine with a 5-hp engine and a walk-behind cultivator unit was designed, manufactured, and evaluated. A single-speed planetary gearbox was used to transmit the engine power through a power transmission shaft and a 90-degree final reducer to the blades installed in front of the machine. Using a planetary gearbox, in addition to providing the required torque for tillage operations, caused a significant weight reduction in the device compared to conventional rototillers. The working width of the cultivator unit can be changed from 15 to 60 cm with 6 C-shaped blade flanges. The tests were carried out with 3 revolutions of the tiller unit (200, 250, and 300 rpm) and in vegetation conditions as a completely random basic design experiment. The results of the field evaluation show that the machine has a higher operating speed and more satisfactory performance compared to conventional agricultural tillers for performing shallow plowing, breaking up, churning, aerating the topsoil, and removing weeds. Because the tiller unit is mounted in the front, it has better maneuverability especially when it works between the rows. However the increase in the blade's axis rotation increases the speed of traveling, the results of the statistical analysis show that the increase in the blade's axis rotation causes the particles of tilled soil to become finer. Also, by increasing the rotation of the blade’s axis, the intensity of the device's operation is more suitable in the conditions of maximum vegetation and prevents the locking of the tiller axis.

Abstract Rice is the staple food of about 2.5 billion people in the world. The quality of this product is influenced by various factors. As a result, quality control and fraud detection are important issues in the rice industry. The purpose of this research was to investigate and detect mixing in white rice cultivars using Vis/NIR spectroscopy, chemometrics and machine learning. In order to conduct experiments, 13 classes were prepared based on the amount of mixing of the main variety of rice (Hashmi variety) with non-main varieties of Fajr, Gilaneh, Khazar and Shiroudi, so that the gross classes resulting from mixing 90, 80 and 70% of Hashmi variety rice respectively with 10, 20 and 30% of other figures mentioned. Multilayer perceptron (MLP), decision tree (DT) and support vector machines (SVM) algorithms were used to classify rice samples. To evaluate the performance of the studied classifiers, statistical indices including sensitivity (Se), specificity (Sp), accuracy (Ac) and root mean square error (RMSE) were used in the form of developing asymmetry matrices of the classifiers. The results of the study showed that J48 DT, MLP and SVM with RBF kernel function with accuracy and RMSE values of 100% and zero, 96.92% and 0.0951, 92.31%, and 0.2483% respectively, were able to classify different samples of white rice.

Abstract Physiological disorder of citrus granulation is one of the qualitative issues and problems in consumer markets and the phenomenon of granulation in agricultural products is not visually detectable, so the detection of this disorder on a large scale requires the use of precise and rapid techniques. One of the applicable methods for non-destructive examination of internal tissue of agricultural products is visible and near-infrared spectroscopy technique, which was used in this research with Vis-NIR method and artificial intelligence for the detection of granulation in oranges. In this research, 200 samples of Valencia oranges were prepared, Then, VIS/NIR signals in the wavelength range of 200-1100 nanometers were recorded for each sample. Spectroscopy was performed on the samples With contact Then, the amount of reflectance was calculated in the interaction mode, and absorption spectra were normalized using the Min-Max method. Subsequently, the recorded spectra were smoothed by the moving average (MA) method, and the Stavisky-Golay algorithm was applied to each spectrum, and finally, 7 statistical features were extracted from each spectrum. In this research, five levels of granulation phenomenon, including levels A, B, C, D, and E were examined. The degree of granulation of each sample was defined based on the dryness and appearance of the dried area using a destructive method. Support vector regression (SVR) and support vector machine (SVM) were used to estimate the moisture content of oranges and to detect the levels of granulation in oranges, respectively. With the change in the levels of granulation, the changes in weight and moisture content of oranges were significant, so that with an increase in the level of granulation in oranges, the weight of samples and their moisture content decreased. Also, the examination of ViS-NIR spectra showed that with the development of granulation in oranges, the absorption in the 400-950 nanometer range significantly decreased, and the difference in absorption intensity for different levels of granulation was maximum in the 570-850 nanometer range. The results of granulation level detection showed that the highest accuracy was observed for SVM with polynomial kernels, with a sensitivity of 98%, 91%, 97%, 96%, and 95% for levels A, B, C, D, and E of granulation, respectively.

Abstract Onion is one of the most important crops in the world and also in Iran. In spite of its high quantity produced in Iran, it sent to the domestic and foreign markets in inappropriate conditions, and at a low price due to the lack of sorting process and appropriate packaging. The aim of this study was to test and evaluate the onion sorting machine, study the effect of performance characteristics of the machine on the sorting quality indexes and determine the probable mechanical damage to the product during the sorting in order to achieve the optimum performance characteristics of the machine. This machine was designed and constructed with two reciprocating sieves with a length and width of 2*1 m, using a wobble shaft. Onion was sorted at 3 degrees based on their diameter according to the international standards code (D<50 mm, 50mm70mm). The sorting performance indexes consist of the degree of pollution and the degree of purity were measured and calculated during sorting of 200 kg of onion. Also, based on the obtained indexes in all test conditions, the amount of optimum performance characteristics of the machine was determined such as effective capacity, slope and frequency of sieves and their effect on the onion mechanical damage during the sorting process. The highest degree of purity equal to 95.60% was obtained at a frequency of 3.33 s-1 and a slope of 10 degrees for the sieves at a capacity of 1 to 1.2 t/h. Also, the overall sorting efficiency of the machine was 92.34% and no mechanical damage was observed to the onion.

Abstract Potatoes tubers harvesters cause mechanical damage due to the presence of metal parts. According to the construct, the number of moving parts, and the way the harvesting machine works, the amount of these damages is different. Also, the increase in the sensitivity of potato tubers to mechanical damage during harvesting has caused it to increase, while these damages during storage also cause more spoilage of potato tubers and increase the resulting damage. Therefore, in this research, based on the results and recommendations of the research done inside the country, in order to reduce the amount of mechanical damage to potatoes and its role in increasing production, in the form of a systematic review and the meta-analysis method was used. Articles published in scientific journals, final reports of research projects, papers presented at scientific conferences, and student theses were reviewed using standard keywords. Then, those who met the criteria to enter the research, entered the meta-analysis process after quality control using a random model. The results showed that the Sabzdasht harvesting machine without a shaker, with the least mechanical damage, was the most suitable machine for harvesting potato tubers, and the Sabzdasht harvesting machine with a shaker, Russian design, Grimme, Zaka design and American design respectively with 2.14, 4.09, 12.27, 23.52 and 24.07 percentages of their mechanical damages are more than the control treatment (Sabzdasht harvesting machine without shaker).

Abstract Economic benefit, improving energy efficiency and compatibility with environment are crucial in order to make sustainable wheat production and provide secure food. This study was carried out in the form of randomized complete block design with three treatments (raised bed planter, and conventional planter and planter without furrower) and four replications, in Pars Abad Moghan Agro industrial Company, Ardabil province of Iran. Results showed that raised bed wheat cultivation has significantly increased energy use efficiency up to 95, while reduced greenhouse gas emission up to 220 kg CO2 per hectare. Among the Calculated values of impact sections in all three planting methods, the largest share was related to open fresh water aquatic ecotoxicity, human ecotoxicity, and Marine aquatic ecotoxicity, which is caused by the consumption of fertilizer and poison inputs. In general, conventional tillage and planting methods, in addition to lower yield, due to high inputs and water consumption, increase the emission of environmental pollutants. As a summary, the comparison of sustainability indicators (environmental impacts, energy efficiency, net profit, harvest index and water consumption efficiency) showed that the priority of sustainable planter belongs to the rised bed planter, conventional planter and planter without furrower respectively. In future researches, new concepts of sustainability in raised bed planters including effect of reducing chemicals and fertilizers, using organic fertilizers, placing legumes in the crop rotation and correct management of irrigation water based on experimentally tested studies suggested to study in long-term cultivation periods.