A tensorflow based feature learning method application in fault detecting of tract motor

In purpose of detecting the inner and outer ring faults of tractor motor, one Feature Learning method, Variationa AutoEncoder, which based on Tensorflow, was cited to process the motor vibration signal. This method firstly normalized all data sets Next, these data sets were input into the built Vari...

Full description

Saved in:
Bibliographic Details
Published in2018 Chinese Control And Decision Conference (CCDC) pp. 3248 - 3252
Main Authors Huizhong, Wang, Linhan, Qiao, Keke, He
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Fault Detection
Feature Learning
Softmax Regression
Tensorflow
Variational AutoEncoder
Online AccessGet full text

Cover

More Information
Summary:In purpose of detecting the inner and outer ring faults of tractor motor, one Feature Learning method, Variationa AutoEncoder, which based on Tensorflow, was cited to process the motor vibration signal. This method firstly normalized all data sets Next, these data sets were input into the built Variational AutoEncoder model to train the weights and biases as the feature learning i¡ going on. Then, a Softmax Regression model is used for multi-faults diagnosis. The final results showed that this method can be used fo: finishing multi-faults detecting missions excellently, and for every metric, the results are better than traditional Back Propagation Neura Network, from 87.51% to 93.61%. Hence, this unsupervised feature learning method decreased lots of Machine learning model's dependency on feature engineering. It would be a good guidance of actual projects.
ISSN:1948-9447
DOI:10.1109/CCDC.2018.8407684