Convolutional Discriminative Feature Learning for Induction Motor Fault Diagnosis

A convolutional discriminative feature learning method is presented for induction motor fault diagnosis. The approach firstly utilizes back-propagation (BP)-based neural network to learn local filters capturing discriminative information. Then, a feed-forward convolutional pooling architecture is bu...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on industrial informatics 2017-06, Vol.13 (3), p.1350-1359
Main Authors: Sun, Wenjun, Zhao, Rui, Yan, Ruqiang, Shao, Siyu, Chen, Xuefeng
Format: Article
Language:English
Subjects:
Architecture
Automation
Back propagation networks
Computer simulation
Construction
Convolution
Convolutional pooling architecture
discriminative learning
Fault diagnosis
Feature extraction
Induction motors
Learning
Motors
Neural networks
Representations
Robustness
State of the art
support vector machine (SVM)
Support vector machines
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A convolutional discriminative feature learning method is presented for induction motor fault diagnosis. The approach firstly utilizes back-propagation (BP)-based neural network to learn local filters capturing discriminative information. Then, a feed-forward convolutional pooling architecture is built to extract final features through these local filters. Due to the discriminative learning of BP-based neural network, the learned local filters can discover potential discriminative patterns. Also, the convolutional pooling architecture is able to derive invariant and robust features. Therefore, the proposed method can learn robust and discriminative representation from the raw sensory data of induction motors in an efficient and automatic way. Finally, the learned representations are fed into support vector machine classifier to identify six different fault conditions. Experiments performed on a machine fault simulator indicate that compared with the current state-of-the-art methods, the proposed method shows significant performance gains, and it is effective and efficient for induction motor fault diagnosis.
ISSN:1551-3203
1941-0050
DOI:10.1109/TII.2017.2672988