基于遗传神经网络的大型机械故障诊断

Fault diagnosis of large mechanism based on genetic-neural network

大型机械应用极为广泛,分析和解决其常见故障,并对其进行及时处理是关键。将遗传优化的神经网络用于大型机械的故障诊断,利用遗传算法的全局搜索能力来克服BP神经网络的收敛速度慢,容易陷入局部极小的缺陷,优化神经网络的权值和阈值。实验结果表明,遗传优化的神经网络具有更高的稳定性,训练时间明显缩短。

Now the giant machinery is in a wide range of application：Analyzing and solving their common faults and processing them timely are the key. Through the way to apply Neural Network which has been optimized by Genetic Algorithm to fault diagnosis of giant machinery, Using the global searching ability of genetic algorithm to overcome the defects of slow convergence speed and easily falling into local minimum of BP Neural Network,the weights and threshold of neural network can be optimal. The results show that Neural Network which has been optimized by Genetic Algorithm has the higher stability and the training time is shorten significantly.