مجله پژوهش های مکانیک ماشین های کشاورزی
سال هفتم شماره 1 (بهار و تابستان 1397)

In present study, image processing technology and ANNs were used to identify the pistachio leaf pests include Ocneria terebinthina stgr and agonoscena pistaciae. The color images were captured from leaves of Ohadi pistachio variety and, color, texture, morphological and texture-color features were extracted from images in order to detection and classification of pests. To achieve the best models of ANNs, different types of ANNs and extracted features were evaluated and the following choices were selected according to the performance of different developed ANNs as the bests; A:The two-layer back propagation ANNs with two hidden layers with SigmoidAxon transfer function and TanhAxon as transfer function in output layer, by using the six color features (variance, mean, standard deviation, skewness, kurtosis and smoothness) with an accuracy of 93.3%, B: The two-layer back propagation ANNs with two hidden layers with SigmoidAxon transfer function and Linear transfer function in output layer, by using the five texture features (entropy, contrast, correlation, energy, homogeneity) with an accuracy of 95%, C: The two-layer back propagation ANNs with two hidden layers, with TanhAxon transfer function and Linear transfer function in output layer, by using the five morphological features (Area, perimeter, convex hull area, extent and solidity) and also, 11 texture-color features with accuracy of 86.7% and 98.3% respectively. The results showed the image processing technology and ANNs, had excellent ability to identify and classification of pistachio leaf pests.

Farm tractors are an unavoidable part of agricultural activity and it is desired that when failures accoured, the tractors get prepared at a minimum time and back to the farms. With an effective maintenance program, the costs of maintenance and machine downtime reduce at an acceptable value. In the current study, the life and maintenance distribution functions of a mechanized system including two MF285, two MF399 and two NewHolland 155 tractors were assessed. The maintainability of tractors and system reliability were analyzed in the next steps. Finally, a suitable maintenance system was proposed based on the queuing theory. Indeed, in the current study by combination of life and maintenance distribution functions and queuing theory, the capacity of a suitable maintenance system was estimated such that tractors with minimum downtime work continuously. The results showed Poisson function suitable for life and Exponential function suitable for maintenance. The two NewHolland 155 tractors consume around 180 hour more time for emergency maintenances compared to two MF285 tractors in around 6700 hour life duration. The reliability of the system was 80% during 30 working hours with three available tractors. The suitable maintenance capacity was proposed around 0.4 maintenance per working shift.

The Iran's share of global production of date palm was 1,157,000 tons. It could be estimated that 11000 tons of date pit oil can be extracted annually. The aim of this study was to investigate the effect of particle size, moisture content and the type of solvent parameters on oil extraction from Mazafati date pit and biodiesel production from that. The effect of particle size in two levels, the solvent type and moisture content parameters on three levels were investigated on oil extraction from Mazafati date pit. The extracted date pit oil converted to biodiesel by transesterification reaction. Ultrasound waves used in order to produce biodiesel. The ultrasound parameters were vibration pulse on three levels, ultrasound duration on two levels and fixed vibration amplitude at 60%. Some of the properties of produced biodiesel from date pit oil were determined. The results showed that the effects of moisture content, particle size, type of solvent and interaction effect of moisture content by solvent type were significant (P

Due to the problems of body weight measurement methods directly (e.g. being stressful for both farmers and animals), a method based on digital images for determination of growth rate and body size of various animals have been proposed. However, determination of animal's physical characteristics along with head conveyed significant errors in body dimensions due to frequent changes of its position. Therefore, the aim of this study was to reduce prediction error of chicken weight with removing its head using active shape model. After removing chickens’ head between area and perimeter of chickens’ body with actual weight, regression models were developed and its results was compared with Otsu segmentation method. The correlation coefficients obtained from active shape model between actual weight with area and perimeter were 97% and 93% respectively; and these coefficients are higher then Otsu method (93% and 92%, respectively, for actual weight with the area and perimeter), therefore, removing head using active shape model increased prediction precision of live body weight.

Today, mechanized farming systems, on time performance of operations requires correct machine programming. For proper planning, it is necessary to know the exact downtime of machines. In this regard, the study was conducted to accurate predicting of MF399 tractor failure rate for the both of corrective and preventive maintenance policies in Khuzestan province. For this purpose, Models applied to forecast are Exponential and ARIMA. Results of Durbin-Watson tests, failure rate of corrective and preventive maintenance policies series were found non stochastic and predictable. Based on the lowest forecasting error criterion, ARIMA is the best model for forecast failure rate of CM and PM policies series. Hence, using the forecast method can affect on different policy about failure rate via forecasting the fluctuation variables. According to results of failure rate forecasting, it was found that there is not significant difference between statistical descriptive measures of forecasting and actual tractor failure rate that it represents high accuracy of forecasting via ARIMA model.

In many countries, diesel fuel is the most important for use in diesel engines. The use of diesel fuel in this engine would be harmful emissions and cause irreparable damage to the environment.Although various measures is taken to curb pollution such as vehicle inspection programs or control systems installed in vehicle exhaust emissions in developed countries .But these programs is not reduced enough in large cities to the problem of air pollution.In this regard, biofuels have inherent physical and chemical properties that make them in practice, seems cleaner than other fuels. One of the main topics of nanotechnology is materials with new properties and its positive effects, raising the efficiency of current internal combustion engines. In this study,an experimental investigation is carried out to establish the emission characteristics of a compression ignition engine while using cerium oxide nanoparticles as additive in neat diesel and diesel-biodiesel blends. The diesel engine emissions were measured at four engine speed levels (1500, 2000, 2400 and 2600 rpm) for the different fuel blends. The results showed that in most blends, the hydrocarbons and carbon monoxide has fallen than diesel fuel.But the amount of nitrogen oxides and carbon dioxide produced by the blend of fuel increased than diesel fuel.

High energy consumption and worker costs caused to fish growers don’t have highly motivated to buy aerators. Dissolved Oxygen (DO) is one of the importance parameters which can be applied for time of starting and finishing activity of aerators however its sensor is expensive and should be estimated by other parameters. The aim of this research was to create a suitable model to estimate DO rate at growing pools. Input parameters were pH and temperatures of water, moisture and temperature of air and wind speed. Along growing period total of parameters were measured and with three models were estimated. The first one was Artificial Neural Network (ANN). The results showed that the maximum R2 was achieved by logsig-purelin transfer function with 17 neuron at hidden layer with 0.70. Second one was an aggregated ANN-AG model and its result showed that the maximum of R2 was 0.41 and finally, Third one was Adaptive Nero Fuzzy Inference System (ANFIS) model and the results showed that at condition of 3 Membership function per layer with gaussian type and constant output could estimate DO with R=0.87 accuracy. Therefore ANN was the best method for evaluation of DO at growing pools for the region under study.