基于BP神经网络的军用电源智能故障诊断

Intelligent Fault Diagnosis of Military Power Based on BP Neural Networks

电源设备的可靠运行关系到地空导弹武器系统的性能,对电源系统进行准确的故障诊断是十分重要的。为对地空导弹武器系统中电源设备故障进行准确诊断,介绍了BP神经网络和某型地空导弹静变电源的相关知识,建立了三相DC/AC逆变器的故障模型,并对几种常见的故障进行了简要的分析。最后,将BP神经网络模型应用于某型地空导弹静变电源的故障诊断,利用神经网络较好的模式分类能力,解决了以往地空导弹部队进行静变电源故障诊断的不足。仿真结果表明,该方法能够准确诊断电源设备的故障,验证了该方法的准确性和实用性。

The reliable operation power equipment is related to the performance of surface-to-air missile weapon systems, accurate fault diagnosis is very important for power system. In order to accurately diagnose the power supply equipment of the surface-to-air missile weapon systems, the BP neural networks and the related knowledge of a certain type missile static variable power supply are introduced. The fault model of the three phase DC/AC inverter is established, and several common faults are analyzed briefly. The BP neural model is applied to the fault diagnosis of a certain type of surface-to-air missile static variable power, better pattern clas- sification capability of the neural network is used to solve the previous static inverter fault diagnosis problem of surface-to-air missile troops. The simulation results show that the method can diagnose the fault of power equip- ment accurately, and the accuracy and practicability of the method are verified.