基于LSSVM的电子装备故障预测研究

Research of Fault Prognostic Based on Least Squares Support Vector Machine for Electronic Equipment

针对电子装备的故障信息不足,故障发生率高等特点,通过故障预测有效的监测设备故障状态以及发展趋势,实现对设备的事先维修,避免重大事故的发生,提高电子设备的安全性;对电子装备故障预测进行了分析,提出了一种基于最小二乘支持向量机(LSSVM)的故障预测方法;首先介绍了LSSVM故障预测算法的基本原理和预测流程;然后,对整个电子装备的故障预测研究可以从一个类似的模拟带通滤波器电路故障预测研究出发,将该元件容差设为不同范围来定义电路的不同故障状态,将LSSVM方法与最小二乘法、支持向量机法对电路的不同状态进行预测,可以得到不同状态的预测值,研究结果表明提出的方法能够实现模拟电路的缓变故障预测,且预测效果较好。

Because fault information of the electronic equipment is insufficient, high incidence of failure, through fault prediction and ef- fective monitoring equipment failure status and development trend, the realization of the equipment maintenance, to avoid the occurrence of major accidents, improve the safety of electronic equipment. Fault prediction of electronic equipment is analyzed, and a fault prediction meth- od based on least square support vector machine （LSSVM） is proposed. Firstly it introduces the basic principle and the fault prognostic algo- rithm of the LSSVM process. Then, fault prognostic research for the electronic equipment can be from a similar analog band--pass filter cir- cuit. Compared to the least square method and support vector machine method, LSSVM method is applied to the different fault condition of the circuit, which obtained the different results. It shows that the proposed method can achieve graded fault prognostic for the analog circuit, and has the better prediction effecting.