•   Home
  • Proceedings
  • Power and Energy Engineering Conference (PEEC 2010 E-BOOK)

Power and Energy Engineering Conference (PEEC 2010 E-BOOK)

Wuhan,China,9.11-9.13，2010

ISBN: 978-1-935068-17-4 Scientific Research Publishing, USA

E-Book 846pp Pub. Date: October 2010

Category: Engineering

Price: $80

Title: Turbo-Generator Vibration Fault Diagnosis Based on QPSO-BP Neural Networks
Source: Power and Energy Engineering Conference (PEEC 2010 E-BOOK) (pp 600-603)
Author(s): Hongsheng Su, Dept. of electrical engineering, Lanzhou Jiaotong University, Lanzhou 730070, China
Abstract: To improve the diagnosic properties of BP neural networks during turbo-generator vibration faults diagnosis, a novel learning algorithm called QPSO-BP is proposed for artificial neural network (ANN) training based on quantum-behaved particle swarm optimization(QPSO) in this paper. The algorithm firstly applies QPSO to optimize the weight values of the networks, and then the well-trained ANN is applied to diagnose the turbo-generator vibration faults. Compared with the diagnostic results of BP neural networks with PSO based, the simulation results show that the method possesses higher speed and accuracy, and is an ideal pattern classifier.
Proceedings by Subjects
Resources
Products
Contact us
book@scirp.org
WhatsApp +86 18163351462(WhatsApp)
Click here to send a message to me 1243940697
Book Publishing WeChat
Follow SCIRP
Free SCIRP Newsletters
Copyright © 2006-2024 Scientific Research Publishing Inc. All Rights Reserved.
Top