| Titles |
|
English :
|
Relative importance of Variables Affecting Chisel-Plow Performance Using Neural Networks
|
|
Arabic :
|
الأهمية النسبية للمتغيرات المؤثرة فى أداء المحراث الحفار مستخدما الشبكات العصبية
|
|
| Abstract |
Multilayer feedforward neural network with 8 input and 3 output neurons was trained using a backpropagation learning algorithm. It was used to predict and study the relative importance of variables affecting chisel plows performance under Egyptian conditions. Data needed to train and test the Artificial Neural Network (ANN) model was obtained from previous similar field experiments found in literatures. The obtained data set was 1191 points, where 801 and 390 of them were used for training and testing ANN model respectively. The input variables were soil texture index, plowing depth, rated width of plow, forward speed, initial soil moisture content, initial soil bulk density, rated tractor power and number of plow passes over soil. However, the performance parameters of chisel plow included draft (kN), specific draft (kN/m2) and energy requirements (kW.h/fed). After the ANN model is near its fully trained state, it is often useful to determine what inputs are important to an ANN output response. The results showed that the ANN model could predict the performance parameters of chisel plows with reasonable accuracy. However, coefficients of correlation are over 0.90. Also, percent of contribution of input variables for draft, specific draft and energy requirements were investigated. The major variable effect on draft requirements, specific draft and energy requirements was rated plow width.
|
| Publication year |
2003
|
| Pages |
407 - 395
|
| Organization Name |
Agricultural Engineering Research Institute (AENRI)
|
| Country |
Egypt
|
| serial title |
المؤتمر الحادى عشر للجمعية المصرية للهندسة الزراعية بالتعاون مع معهد بحوث الهندسة الزراعية والذى أقيم بمركز ميكنة الأرز بميت الديبة – كفر الشيخ والتابع للمعهد خلال الفترة من 15-16 أكتوبر 2003
|
| Department |
Agriculture Power and Energy
|
| Author(s) from ARC |
|
| External authors (outside ARC) |
|
| Agris Categories |
Agricultural engineering
|
AGROVOC
TERMS |
Neural networks.
|
| Publication Type |
Conference/Workshop
|