摘要
为克服 BP算法中存在的网络学习收敛速度慢 ,以及容易陷入局部极小的问题 ,本文在神经网络训练过程中 ,加入一个局部极小判别式 ,以确定网络是否陷入局部极小点 ,若陷入局部极小点 ,则利用遗传优化算法进行权值的修正。以机械设备故障诊断为例 ,应用此算法对其进行了故障诊断研究 ,从而证明了该算法的有效性。
In order to overcome the problems of slow rate of convergence and falling easily into local minimum in BP algorithm, a new improved genetic BP algorithm was put forward. To determine whether the network fall into local minimum point, a discriminant of local minimum was put forth in the training process of neural network. Genetic algorithm was used to revise the weights of the neural network if the BP algorithm fell into local minimum. The structure damages and mechanical faults were diagnosed using the algorithm put forward in this paper, which testified the validity of this improved genetic BP algorithm.
出处
《机械科学与技术》
CSCD
北大核心
2002年第4期625-627,共3页
Mechanical Science and Technology for Aerospace Engineering
关键词
机械
故障诊断
遗传神经网络
BP算法
Genetic neural network
BP algorithm
Mechanical failure
Diagnosis
