机械故障诊断的遗传BP算法应用研究

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。

On the Application of Genetic BP Algorithm to Diagnosis of Mechanical Failure

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.