Machine State Identification based on Information Fusion

DOI

10.2991/asei-15.2015.362How to use a DOI?

Keywords

DS evidence theory; SVDD; BP neural network; Machine state identification

Abstract

Aiming at the uncertainty of the results obtained by using single sensor and single algorithm in the process of machine state identification, the DS evidence theory is introduced. Firstly, the basic probability assignment (BPA) is constructed according to the classification results of the support vector data description (SVDD) and BP neural network. Then the BPA of the two algorithms are fused according to the evidence rule, and the output result of the single sensor is obtained. Finally, the decision conclusion is obtained according to the fusion of multi sensor classification results. It can be seen from the bearing experiment that the uncertainty of decision is greatly reduced after information fusion, which can make full use of the complementary information of each signal sensor to improve the accuracy and credibility of the decision.

Copyright

© 2015, 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  - Zhiyuan Sun
AU  - Jian Zheng
AU  - Chao Xiong
AU  - Junhui Yin
PY  - 2015/05
DA  - 2015/05
TI  - Machine State Identification based on Information Fusion
BT  - Proceedings of the 2015 International conference on Applied Science and Engineering Innovation
PB  - Atlantis Press
SP  - 1819
EP  - 1822
SN  - 2352-5401
UR  - https://doi.org/10.2991/asei-15.2015.362
DO  - 10.2991/asei-15.2015.362
ID  - Sun2015/05
ER  -