Title :
Improved genetic algorithm and neural network method and the application in fault diagnosis of valve diesel engine
Author :
Xin, Wang ; Hongliang, Yu ; Lin, Zhang
Author_Institution :
Coll. of Marine Eng., Dalian Maritime Univ., Dalian, China
Abstract :
As the shortcomings of BP neural network slow convergence rate, falling into local minimum easily and difficult to determine the number of hidden nodes accurately, the number of hidden nodes, weights and threshold of BP neural network were optimized, using binary and real number hybrid coding based on genetic algorithms with global searching ability. Finally, the method tested with WD615 diesel engine valve fault diagnosis data. Experimental results showed that this algorithm has obvious advantages, it is able to overcome the deficiencies of BP neural network, and improves the network´s learning ability.
Keywords :
backpropagation; diesel engines; encoding; fault diagnosis; genetic algorithms; mechanical engineering computing; neural nets; valves; BP neural network; WD615 diesel engine valve; convergence rate; fault diagnosis; genetic algorithm; global searching ability; hidden nodes; hybrid coding; local minimum; Artificial neural networks; Biological cells; Diesel engines; Encoding; Fault diagnosis; Gallium; Valves; BP neural network; diesel engine; fault diagnosis; genetic algorithms; hybrid coding;
Conference_Titel :
Information Computing and Telecommunications (YC-ICT), 2010 IEEE Youth Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-8883-4
DOI :
10.1109/YCICT.2010.5713124