Analog circuit fault diagnosis with echo state networks based on corresponding clusters

Authors:
Xiyuan Peng;Jia Guo;Miao Lei;Yu Peng
Affiliations:
Automatic Test and Control Institute, Harbin Institute of Technology, Harbin, China;Automatic Test and Control Institute, Harbin Institute of Technology, Harbin, China;Automatic Test and Control Institute, Harbin Institute of Technology, Harbin, China;Automatic Test and Control Institute, Harbin Institute of Technology, Harbin, China
Venue:
ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part I
Year:
2011

Citing 3
Cited 0

Development of multi-cluster cortical networks by time windows for spatial growth

Neurocomputing
2007 Special Issue: Automatic speech recognition using a predictive echo state network classifier

Neural Networks
Effects of connectivity structure of complex echo state network on its prediction performance for nonlinear time series

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Analog circuit fault diagnosis can be modeled as a pattern recognition problem. Fault patterns are complicated which has high demands for classification accuracy and efficiency. Therefore a new analog circuit fault diagnosis method using Echo State Networks (ESNs) is proposed. We adopt the time windows function to construct reservoir with corresponding clusters of ESNs inspired by complex network topologies imitating cortical networks of the mammalian brain. Multiple-cluster reservoir is generated instead of nonclustering reservoir of the original ESNs with random sparse connections. We use the number of classes to determine the number of clusters to improve performances in specific analog circuit fault diagnosis problems. Simulation results show the effectiveness of the proposed method.