A Tensorflow Based Feature Learning Method Application in Fault Detecting of Tract Motor
作者单位：Lanzhou University of Technology
会议名称：《第30届中国控制与决策会议》
会议日期：2018年
学科分类：082304[工学-载运工具运用工程] 08[工学] 080204[工学-车辆工程] 0802[工学-机械工程] 0823[工学-交通运输工程]
基 金：supported by Natural Science Foundation of Gansu Province of China(1508RJZA090) Key Laboratory of Gansu Advanced Control for Industrial Processes(XJK201522)
关 键 词：Tensorflow Variational AutoEncoder Softmax Regression Feature Learning Fault Detection
摘 要：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 *** 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 is going ***,a Softmax Regression model is used for multi-faults *** final results showed that this method can be used fo finishing multi-faults detecting missions excellently,and for every metric,the results are betterthan 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 *** would be a good guidance of actual projects.