基于AFSA-WNN的Sallen-Key滤波器电路软故障诊断  

Soft Fault Diagnosis for Sallen-Key Filter Circuit Based on AFSA-WNN

作　　者：王春兰[1] 郭峰[1] WANG Chun-lan;GUO Feng(Xijing University,Xi’an 710123,China)

机构地区：[1]西京学院

出　　处：《火力与指挥控制》2019年第10期173-177,共5页Fire Control & Command Control

摘　　要：为提高对Sallen-Key滤波器的软故障诊断能力,提出一种基于多分辨率变换与小波神经网络(WNN)的软故障诊断方法。该方法先引入多分辨率变换提取Sallen-Key滤波器电路的软故障特征,在此基础上,采用人工鱼群算法优化的WNN构建电路软故障诊断模型。仿真结果表明,与单纯的WNN相比,所提出方法对电路软故障的诊断性能更好,总正确率达到94.1%。从而证明该方法用于Sallen-Key滤波器软故障诊断是可行的,也是有效的。In order to improve the capability of soft fault diagnosis for Sallen-Key filter,a soft fault diagnosis method based on multi-resolution transform and wavelet neural network (WNN )is proposed. Firstly, the soft fault feature of Sallen-Key filter circuit is extracted by multi-resolution transform, and then, on the basis of this, WNN optimized by artificial fish swarm algorithm is used to establish the soft fault diagnosis model of the circuit. The simulation results show that, compared with the simple WNN, the proposed method has better diagnosis performance for circuit soft fault, the total correct rate is 94.1 %. So it is proved that the method is feasible and effective in soft fault diagnosis for Sallen-Key filter.

关 键 词：Sallen-Key滤波器 多分辨率变换 小波神经网络 人工鱼群算法 软故障诊断 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TM930[自动化与计算机技术—控制科学与工程]