公开(公告)号：US11817809B2

公开(公告)日：2023-11-14

申请号：US17992946

申请日：2022-11-23

Applicant: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY

Inventor： Zicheng Liu ,  Lanlan Fang ,  She Yan ,  Dong Jiang

IPC: H02P29/028 ,  G01R31/34 ,  G05B23/02

CPC classification number: H02P29/028 ,  G01R31/343 ,  G05B23/0229 ,  G05B23/0254 ,  H02K2213/03

Abstract: The disclosure discloses a motor driving system converter fault diagnosis method based on adaptive sparse filtering, and belongs to the field of driving system fault diagnosis. The disclosure applies an unsupervised learning algorithm to an application scene of converter fault diagnosis. Effective features are automatically extracted from original data, and the problem of manual feature design based on expert knowledge is solved. Meanwhile, in consideration of current fundamental period change caused by different rotation speed working conditions, rotation speed feedback is introduced, secondary sampling is carried out on current sampled at a constant frequency, it is ensured that the length of a signal input into the deep sparse filtering network is one fundamental wave period, redundant information is better removed from original data, the calculation burden is relieved, and the accuracy and rapidity of the diagnosis algorithm are improved to a certain extent.

公开(公告)号：US20230163713A1

公开(公告)日：2023-05-25

申请号：US17992946

申请日：2022-11-23

Applicant: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY

Inventor： Zicheng Liu ,  Lanlan Fang ,  She Yan ,  Dong Jiang

IPC: H02P29/028 ,  G01R31/34 ,  G05B23/02

CPC classification number: H02P29/028 ,  G01R31/343 ,  G05B23/0229 ,  G05B23/0254 ,  H02K2213/03

Abstract: The disclosure discloses a motor driving system converter fault diagnosis method based on adaptive sparse filtering, and belongs to the field of driving system fault diagnosis. The disclosure applies an unsupervised learning algorithm to an application scene of converter fault diagnosis. Effective features are automatically extracted from original data, and the problem of manual feature design based on expert knowledge is solved. Meanwhile, in consideration of current fundamental period change caused by different rotation speed working conditions, rotation speed feedback is introduced, secondary sampling is carried out on current sampled at a constant frequency, it is ensured that the length of a signal input into the deep sparse filtering network is one fundamental wave period, redundant information is better removed from original data, the calculation burden is relieved, and the accuracy and rapidity of the diagnosis algorithm are improved to a certain extent.