期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2013
卷号：49
期号：3
出版社：Journal of Theoretical and Applied
摘要：With the combination of particle swarm optimization and neural network, this paper presents a kind of analog circuit fault diagnosis method based on particle swarm neural network. In the training process, the linear decreasing inertia weight particle swarm algorithm optimized BP network�s initial weights and initial threshold, adaptive learning rate and additional momentum BP algorithm adjusted the weights and threshold of BP neural network, which makes the best of particle swarm algorithm and BP algorithm local search advantage to overcome the traditional BP algorithm converging slowly and falling into the limitations of local weights easily. Simulation results show that this diagnostic method can be used for tolerance analog circuit fault diagnosis, with a high convergence rate and diagnostic accuracy.
关键词：Fault diagnosis， Particle swarm neural network， Linear decreasing inertia weight， Analog circuits
