Main Converter Fault Diagnosis for Power Locomotive Based on PSO-BP Neural Networks

Hong Sheng Su

doi:10.4028/www.scientific.net/AMR.267.271

Paper Titles

Application of Community Discovery in SNS Scientific Paper Management Platform
p.247

Comparative Analysis of the Major Ontology Library
p.253

Interactive Technology Application Program of Experience Learning for Children with Developmental Disabilities
p.259

The Study on the Quality Management of Supply Chain Production in Operations
p.265

Main Converter Fault Diagnosis for Power Locomotive Based on PSO-BP Neural Networks
p.271

Research on Software Trustworthiness Level Evaluating Model Based on Layered Idea and its Application
p.277

Research on Face Recognition Based on Pulse Coupled Neural Network
p.283

Study on Coordinate Information Generation Method of Interested Area in IMRT Inverse Planning System
p.289

Topology Optimization in the Conceptual Design: Take the Frame of a Bender as Example
p.297

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 267Main Converter Fault Diagnosis for Power...

Main Converter Fault Diagnosis for Power Locomotive Based on PSO-BP Neural Networks

Abstract:

To aim at conventional BP learning algorithm of its flaws, say, low convergence speed and easy falling into local extremum, and etc, during main converter fault diagnosis system for power locomotive, this paper proposed a novel learning algorithm called PSO-BP neural networks based on particle swarm optimization (PSO) and BP neural networks. The algorithm generated the two phases: one is that PSO was applied to optimize the weight values of neural networks based on training samples, the other is that BP algorithm was applied to farther optimize based on verifying samples till the best weight values are achieved. Eventually, a practical example indicates that the proposed algorithm has quick convergence speed and high accuracy, and is ideal patter classifier.