基于神经网络的复杂电子装备故障诊断系统

The Complex Electric Equipment Fault Diagnosis Based on Neural Network

文章针对复杂电子装备故障诊断难的特点，以一种典型设备的几种主要故障为例，设计了一种新型神经网络模型，并对系统进行了诊断，讨论了以此模型为基础进行诊断的可能性和正确性。实践表明了该模型的有效性和合理性，与传统方法相比，提高了故障诊断的准确度，而且充分运用了工作经验、专家知识，具有很大的工程应用价值。

This paper designs a new type of neural network model based on the characteristic of a complex electric equipment fault diagnosis system according to a few fault of a typical equipment, discusses the probability and correctness of the model while using the model to diagnose. The results indicate the validity and rationality of the model. It improves the accuracy of fault diagnosis comparing to traditional methods. Work experience and expert knowledge are used sufficiently, which has great engineering application value.