基于小波变换与BP神经网络的模拟电路故障诊断

Abstract

Abstract:

This paper presents a systematic fault diagnosis method for analogue circuits based on the combination of wavelet transform and modified BP neural network (BPNN).With the wavelet decomposition as a preprocessor,the feature information is extracted by wavelet de-noising and normalization and applied to the BPNN.The method reduces the number of inputs to the neural network and improves the convergence speed and the ability to detect faults.Simulation results show that the scheme locates faults exactly with improved network structure and fault diagnosis precision and speed.

Key words: wavelet transform;BP networks;analogue circuits;fault diagnosis

CLC Number:

TN710.4

HUANG Ruke,LIANG Tiansheng,YU Hanhua. Analog Circuit Fault Diagnosis Based on Wavelet Transform and BP Neural Network[J]., 2014, 27(8): 46-.

[1]	SUN Bo,GUO Weisheng. The Method of Analog Quantity Measure and Calibrate of Mobile Frequency Convertor [J]. , 2017, 30(9): 82-.
[2]	XI Da-Li. Voltage Series Negative Feedback Amplifier Simulation Based on Multisim8 [J]. , 2013, 26(4): 140-.
[3]	WANG Hanzhuo,CHEN Haihua. Analysis of the Sinusoidal State Circuit Based on Multisim10 and Matlab7.0 [J]. , 2013, 26(1): 146-.
[4]	WANG Jie. Application of Pspice to Circuit Software Design [J]. , 12, 25(9): 112-.
[5]	PU Jian-Kai, HU Zhi-Zhong, ZHU Qiong, SHAO Yuan-Chao. Method for Catastrophic Faults Location in Analog Circuits Based on Wavelet Transform and Mahalanobis Distance [J]. , 2012, 25(5): 10-.
[6]	LI Yong-Feng, HUANG Juan, WANG Dan, WANG Long-Ye. Design and Simulation of a Bandgap Reference Circuit [J]. , 2011, 24(7): 3-.

Analog Circuit Fault Diagnosis Based on Wavelet Transform and BP Neural Network

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 6

Metrics

Comments

Recommended 0