Multi-dimensional neural network and its application in fault diagnosis of analog circuits

DOI

10.2991/icmemtc-16.2016.38How to use a DOI?

Keywords

Analog circuits fault diagnosis; dimensional neural network; wavelet transform ;principal component analysis

Abstract

when a man classifies an object, he makes a comprehensive judgment after a plurality of feature extraction and classification. Based on the phenomenon and in accordance with the theory of one-dimensional neural network, the concept and theory of multi-dimensional neural network is put forward , which is applied in the field of analog circuit fault diagnosis .Firstly wavelet is used for feature extraction and principal component analysis is applied for dimension reduction. Then multi-dimensional neural network is added as a classifier to classify. Finally, decider is used for final judging categories. Experimental results show that the proposed network architecture used for fault diagnosis of analog circuits can effectively improve the accuracy of diagnosis.

Copyright

© 2016, 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  - Dezan Zhao
AU  - Jun Xing
AU  - Zhisen Wang
PY  - 2016/04
DA  - 2016/04
TI  - Multi-dimensional neural network and its application in fault diagnosis of analog circuits
BT  - Proceedings of the 2016 3rd International Conference on Materials Engineering, Manufacturing Technology and Control
PB  - Atlantis Press
SP  - 200
EP  - 204
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmemtc-16.2016.38
DO  - 10.2991/icmemtc-16.2016.38
ID  - Zhao2016/04
ER  -