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

doi:10.1109/CCDC.2018.8407684

	A tensorflow based feature learning method application in fault detecting of tract motor
	Huizhong, Wang; Linhan, Qiao; Keke, He
	2018-07-06
会议日期	June 9, 2018 - June 11, 2018
会议地点	Shenyang, China
DOI	10.1109/CCDC.2018.8407684
页码	3248-3252
英文摘要	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 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. © 2018 IEEE.
会议录	Proceedings of the 30th Chinese Control and Decision Conference, CCDC 2018
会议录出版者	Institute of Electrical and Electronics Engineers Inc.
语种	英语
内容类型	会议论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/118019]
专题	电气工程与信息工程学院
作者单位	Lanzhou University of Technology, Lanzhou; 730050, China
推荐引用方式 GB/T 7714	Huizhong, Wang,Linhan, Qiao,Keke, He. A tensorflow based feature learning method application in fault detecting of tract motor[C]. 见:. Shenyang, China. June 9, 2018 - June 11, 2018.