THE INTELLIGENT SYSTEM DESIGN OF REMOTE FAULT DIAGNOSIS OF REDUCER BASED ON GA AND NN

摘要：

In this paper, reducer failure was analyzed and by use of BP neural network, model of failure diagnosis was established. Using genetic algorithms, the value of neural networks, the threshold, and the network structure were optimized. Genetic neural network model was applied to the system design of remote reducer fault diagnosis. To compare training error curve of BP neural network with genetic neural network, it was shown that genetic neural network in the training of speed and accuracy higher than the neural network training model.

关键词： component NN GA weights threshold error curve

作者: Jun Su

作者单位: Nantong university，Department of Mechanical Engineering， Nantong Jiangsu China 226007

会议类型: 国际会议

会议名称: The Fifth International Conference on VETOMAC-V(第五届振动工程及机械技术国际会议)

会议地点: 武汉

会议语种:英文

页码: 225-230

在线出版日期: 2009-08-27（万方平台首次上网日期，不代表论文的发表时间）