Research on the Equipment Fault Diagnosis Based on GN-BP Neural Network

DOI

10.2991/amcce-17.2017.140How to use a DOI?

Keywords

Fault diagnosis; GA-BP; Network training; Data analyses

Abstract

Neural network provides a new research method for equipment fault diagnosis with its inherent memory ability, self-learning ability and strong fault tolerance. In the basis of equipment fault diagnosis characterized mathematical, the research established the model of fault diagnosis for equipment based on GA-BP, and the diagnosis model has been applied in the theoretical analyses and test for fault diagnosis of gear box. Experimental results show that equipment fault diagnosis technology based on GA-BP neural network, it can optimize the tactics with genetic algorithm when the network trained model, and adjust precision using BP network, the model can accurately diagnosis the types of fault for equipment. The model of GA-BP neural network has higher prediction accuracy and adaptability than the traditional BP neural network and has important application in the field of fault diagnosis.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Jian Du
AU  - Yu-cai Dong
AU  - Jing Xia
AU  - HuiZhen Li
PY  - 2017/03
DA  - 2017/03
TI  - Research on the Equipment Fault Diagnosis Based on GN-BP Neural Network
BT  - Proceedings of the 2017 2nd International Conference on Automation, Mechanical Control and Computational Engineering (AMCCE 2017)
PB  - Atlantis Press
SP  - 791
EP  - 796
SN  - 2352-5401
UR  - https://doi.org/10.2991/amcce-17.2017.140
DO  - 10.2991/amcce-17.2017.140
ID  - Du2017/03
ER  -