Fault diagnosis method, system and device, and storage medium

The invention discloses a fault diagnosis method, system and device, and a storage medium. The method comprises the steps of obtaining feature data sets corresponding to initial feature sets during normal running and fault running of a target device, thereby obtaining training data comprising the no...

Full description

Saved in:
Bibliographic Details
Main Authors WANG BANGJUN, LING XINGHONG, ZHANG ZHAO, XUE YANGTAO, ZHANG LI, LI FANCHANG
Format Patent
LanguageChinese
English
Published 18.05.2018
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:The invention discloses a fault diagnosis method, system and device, and a storage medium. The method comprises the steps of obtaining feature data sets corresponding to initial feature sets during normal running and fault running of a target device, thereby obtaining training data comprising the normal feature data set and the fault feature data set; calculating a corresponding KL distance between each piece of feature data in the normal feature data set and corresponding feature data in the fault feature data set, thereby obtaining a KL distance set; performing cross validation on the training data by adopting support vector machine classification; according to a validation result and the values of the KL distances in the KL distance set, determining features related to fault running inthe initial feature sets, and obtaining optimal feature sets; and when to-be-diagnosed data of the target device is obtained, determining the feature data corresponding to the optimal feature sets inthe to-be-diagnosed data,
Bibliography:Application Number: CN201711320019