中文摘要：

从电梯机械、安全保护、电力和调速控制4个系统出发采集特征样本数据作为BP神经网络的输入,利用遗传算法优化神经网络的权值和阈值。实验证明遗传算法优化后的神经网络减少了运算量,缩短了训练时间,提高网络的稳定性,同时有效地提高了故障诊断的精确度。

英文摘要：

Based on the elevator machinery, safe protection, electricity, and speed regulation control, the characteristic sample data are collected as the input of BP neural network to optimize the weight and threshold of the neural network using genetic algorithm. The test shows that the neural network optimized by the genetic algorithm can reduce the calculating amount, shorten training time, improve the network stability, and effectively raise accuracy of fault diagnosis.