A Neural Network Method for Induction Machine Fault Detection with Vibration Signal

Author(s):  
Hua Su ◽  
Kil To Chong ◽  
A. G. Parlos
2008 ◽  
Vol 78 (7) ◽  
pp. 1247-1255 ◽  
Author(s):  
Khmais Bacha ◽  
Humberto Henao ◽  
Moncef Gossa ◽  
Gérard-André Capolino

2011 ◽  
Vol 311-313 ◽  
pp. 2277-2281 ◽  
Author(s):  
Xin Wang ◽  
Hong Liang Yu ◽  
Shu Lin Duan ◽  
Jin Yan

The characteristic vector of cylinder vibration signal is extracted by wavelet packet decomposition. The factor of selection is proposed to take adaptive integration on basis of improved super parent one dependence estimator Bayesian method and back propagation genetic algorithm neural network method. Experimental results on WD615 diesel engine showed that the method has high accuracy rate of detection.


Methods for evaluation the manufacturability of a vehicle in the field of production and operation based on an energy indicator, expert estimates and usage of a neural network are stated. By using the neural network method the manufacturability of a car in a complex and for individual units is considered. The preparation of the initial data at usage a neural network for predicting the manufacturability of a vehicle is shown; the training algorithm and the architecture for calculating the manufacturability of the main units are given. According to the calculation results, comparative data on the manufacturability vehicles of various brands are given.


Sign in / Sign up

Export Citation Format

Share Document