S. F. Mousavi; M. H. Abbaspour-Fard; M. H. Aghkhani; E. Ebrahimi; A. Soheili Mehdizadeh
Abstract
Introduction
The diagnosis of agricultural machinery faults must be performed at an opportune time, in order to fulfill the agricultural operations in a timely manner and to optimize the accuracy and the integrity of a system, proper monitoring and fault diagnosis of the rotating parts is required. ...
Read More
Introduction
The diagnosis of agricultural machinery faults must be performed at an opportune time, in order to fulfill the agricultural operations in a timely manner and to optimize the accuracy and the integrity of a system, proper monitoring and fault diagnosis of the rotating parts is required. With development of fault diagnosis methods of rotating equipment, especially bearing failure, the security, performance and availability of machines has been increasing. In general, fault detection is conducted through a specific procedure which starts with data acquisition and continues with features extraction, and subsequently failure of the machine would be detected. Several practical methods have been introduced for fault detection in rotating parts of machineries. The review of the literature shows that both Artificial Neural Networks (ANN) and Support Vector Machines (SVM) have been used for this purpose. However, the results show that SVM is more effective than Artificial Neural Networks in fault detection of such machineries. In some smart detection systems, incorporating an optimized method such as Genetic Algorithm in the Neural Network model, could improve the fault detection procedure. Consequently, the fault detection performance of neural networks may also be improved by combining with the Genetic Algorithm and hence will be comparable with the performance of the Support Vector Machine. In this study, the so called Genetic Algorithm (GA) method was used to optimize the structure of the Artificial Neural Networks (ANN) for fault detection of the clutch retainer mechanism of Massey Ferguson 285 tractor.
Materials and Methods
The test rig consists of some electro mechanical parts including the clutch retainer mechanism of Massey Ferguson 285 tractor, a supporting shaft, a single-phase electric motor, a loading mechanism to model the load of the tractor clutch and the corresponding power train gears. The data acquisition section consists of a data analyzer (PCA-40), a personal computer, a piezoelectric accelerometer (VMI-102, DT-2234B), a tachometer and two rubber vibration absorbing elements are located between the rig’s components and the plate holder. An evaluation function was employed in order to achieve the optimal structure of neural network models by selecting the number of layers, number of cells in the layers, transfer function, training function, learning functions, performance function, and number of epochs, in such a way that the MSE of the calculated output error was minimal. The data were collected by means of the accelerometer sensor attached on the clutch mechanism, with three different working conditions (normal condition, with worn bearing, and with worn shaft), and three rotational speeds including: 1000 rpm, 1500 rpm and 2000 rpm. The Wavelet Packet Transform (WPT) was applied on the data-set for features vector extraction and the principle component analyses (PCA) was applied for dimension reduction of the features vector. The signal processing and the features extraction are the most important characteristics of the monitoring methodology, by which the working condition of the machine can be determined. These characteristics may be acquired by transforming the signals from the time domain to the frequency domain and MATLAB software is used for this purpose. This software receives the vibration data (time series of output voltage) which are in Excel files format. To remove the noise a suitable filtering procedure was used and finally the statistical parameters of time - frequency were calculated.
Results and Discussion
To verify the accuracy of the Genetic Algorithm model, the required data were collected from the training and testing steps of the Neural Network. For this purpose, the statistical parameters such as mean squared error (MSE), mean absolute error (MAE) and correlation coefficient (r) were used. The optimal parameters of the neural network obtained for the family of Db4. A trial and error procedure was used to minimize the mean square error of the network output and the desired amount of training step. During the training step, four neural networks including Db4, Db30, Db35 and Db40 achieved a gradient descent weight in the learning bias and four neural networks including Db9, Db15, Db20 and Db25 achieved a gradient descent with momentum weight in the learning bias. The two of the achieved neural networks including Db4, Db20 have circular logarithm function and the remaining networks have annular hyperbolic tangent transfer function. The most appropriate networks configuration was acquired when the network exhibited the minimal error with the training and testing data sets. The results show that the highest accuracy of the GA-ANN Artificial neural networks for all rotational speeds (1000, 1500 and 2000 rpm), and working conditions (intact gear and shaft, damaged bearing and worn shaft) observed for the network family of Db4. The highest error observed for the family of Db20 with MSE of 0.011.
Conclusions
Artificial neural networks can somewhat think and make decisions similar to an expert person. In this project in order to predict the occurrence of a failure of the clutch mechanism of MF 285 tractor, the experimental data were obtained using some sensors, and the data were transferred to a computer by means of a data analytical. By training of the neural networks, the errors were identified separately. The output data from the combined Neural Network and Genetic Algorithm shows that the performance of the prediction model is enhanced. Based on the experiments and calculations, the best data set belongs to the family of Db4 network with the least MSE equal to 4.09E-07 and r equal to 0.99999, indicating that the model could precisely detect the faulty bearings or shafts.
S. F. Mousavi; M. H. Abbaspour-Fard; M. Khojastehpour
Abstract
Introduction: Drying process of agricultural products, fruits and vegetables are highly energy demanding and hence are the most expensive postharvest operation. Nowadays, the application of control systems in different area of science and engineering plays a key role and is considered as the important ...
Read More
Introduction: Drying process of agricultural products, fruits and vegetables are highly energy demanding and hence are the most expensive postharvest operation. Nowadays, the application of control systems in different area of science and engineering plays a key role and is considered as the important and inseparable parts of any industrial process. The review of literature indicates that enormous efforts have been donefor the intelligent control of solar driers and in this regard some simulation models are used through computer programming. However, because of the effect of air velocity on the inlet air temperature in dryers, efforts have been made to control the fan speed based ont he temperature of the absorber plate in this study, and the behavior of this system was compared with an ordinary dryer without such a control system.
Materials and methods: In this study, acabinet type solar dryer with forced convection and 5kg capacity of fresh herbs was used. The dryer was equipped with a fan in the outlet chamber (the chimney) for creating air flow through the dryer. For the purpose of research methods and automatic control of fan speed and for adjusting the temperature of the drying inlet air, a control system consisting of a series of temperature and humidity sensors and a microcontroller was designed. To evaluatethe effect of the system with fan speed control on the uniformity of air temperature in the drying chamber and hence the trend of drying process in the solar dryer, the dryer has been used with two different modes: with and without the control of fan speed, each in twodays (to minimize the errors) of almost the same ambient temperature. The ambient air temperature during the four days of experiments was obtained from the regional Meteorological Office. Some fresh mint plants (Mentha longifolia) directly harvested from the farm in the morning of the experiment days were used as the drying materials. Each experimental run continued for 9 hours, startingat 8:00 am and terminating at 17:00. To determine the moisture content for the purpose of observing and recording the drying process, the drying materials were sampled with one hour time step. The moisture contentwas determinedin the laboratory using the well- known method of oven drying which is presented elsewhere.
Results and discussion: Since the ambient air temperature during the four days of experimental runs was almost the same, the effect of ambient air temperature on the drying process was ignored. Considering the dryer inlet air temperature charts obtained in this study (Fig. 2 and Fig. 3), it can be concluded that for those tests using the fan speed control system, the outlet air temperature of the collector during drying period associated with very little variations, is compared with the no control mode runs. At the beginning of the day and also during the hours at the end of the day, due to a decrease in the temperature of the absorber plate compared to the middle of theday, the fan speed is reduced as air passes slowly through the absorber plate and hence the temperature rises. But in the middle of the day, with increasing the temperature of absorber plate, the speed of the fan is increased to provide sufficient airflow and to prevent the absorber plate from warming up. Inexperiments without fan speed control, the fan works with no limitation, and the temperature of the inlet air was changed with the temperature change in the absorber plate. The fan speed control system in addition to lowering the temperature changes in the outlet air, also increased the average outlet temperature about 3C, compared to the dryer without such a control system. During the twodays of experiments, the average ambient air temperature was 28C and at the sametime the outlet air temperature was 40.6 and 40.8C, respectively. In twodays of no control system, the average temperature of the ambient air was 28.5 and 28C and at the sametime the outlet air temperature was 38 and 37.8C, respectively. The results showed that with fan speed control mode the variation of inlet air temperature of the drying chamber was more limited and remained within the range of 39 to 42 and 40 to 42°C during the two experimental days, respectively. However, without fan speed control, the system exhibited a wider variation of inlet drying air temperature and limited within the range of 33 to 44 and 32 to 43°C. Furthermore, with fan speed control in a solar dryer, along with more uniformity in moisture content, the drying rate may speed up and with further decrease in final moisture content up to 8%, when compared to a system with no fan speed control.
Conclusions: The average temperatures of the outlet air of collector in two days with fan speed control system, were 40.6 and 40.8°C while in the system without the fan speed control, were 38 and 37.8, respectively. This clearly indicates that the system control could increase the temperature of the collector outlet. The dryer was also able to control the fan speed during the 9hours of drying mint with initial moisture content of 85% (w.b) and to reduce it to about 24.5 and 25.5%, during the two experimental days, respectively. While the corresponding values without the use of a control system were 33.5 and 33.5%, respectively. In other words, in the experiments with the use of control system, the final moisture content was about 8% lower than the moisture content of materials dried without such a system. Furthermore, the control system reduces the volume of air required by the system and hence speeds up the drying process.