GEARBOX FAULT DIAGNOSIS MODEL TRAINING METHOD AND GEARBOX FAULT DIAGNOSIS METHOD

Title:

GEARBOX FAULT DIAGNOSIS MODEL TRAINING METHOD AND GEARBOX FAULT DIAGNOSIS METHOD

Document Type and Number:

WIPO Patent Application WO/2023/035869

Kind Code:

A1

Abstract:

Disclosed in the present invention are a gearbox fault diagnosis model training method and a gearbox fault diagnosis method. The training method comprises: obtaining a motor current signal in an electromechanical system where a gearbox is located; calculating feature values representing the complexity and the mutation degree of the current signal according to the current signal; screening the feature values according to a random forest algorithm to generate a sample data set; and training a deep reinforcement learning network model according to the data set to generate a fault diagnosis model. According to the gearbox fault diagnosis model training method provided by the present invention, only the current signal is obtained, no additional sensor is needed, and the defect in the prior art that hardware is added is overcome. Feature data related to the fault is extracted by calculating and screening the feature values representing the complexity and the mutation degree of the current signal. According to the method for inputting the current signal obtained during operation of the unit into the generated deep reinforcement learning network model to realize gearbox fault diagnosis, the diagnosis precision can be improved, and the defects of low reliability and low accuracy in the prior art are overcome.

More Like This:

WO/2023/184652	NON-ORTHOGONAL ELLIPTICAL TOROIDAL WORM GEAR PAIR
WO/2024/001719	PARAMETER OPTIMIZATION METHOD AND SYSTEM FOR VIBRATION COMPACTION OF HIGH-SPEED RAIL FILLER
WO/2021/245451	METHOD AND SYSTEM FOR TRIMMING INTERSECTING BODIES IN A COMPUTER-AIDED DESIGN ENVIRONMENT

Inventors:

WANG LUO (CN)
ZOU ZUBING (CN)
LI JUNQING (CN)
DENG YOUHAN (CN)
WANG ZUFAN (CN)
SU YING (CN)

Application Number:

PCT/CN2022/112476

Publication Date:

March 16, 2023

Filing Date:

August 15, 2022

Export Citation:

Click for automatic bibliography generation Help

Assignee:

CHINA THREE GORGES CORP (CN)

International Classes:

G06F30/17; G01M13/021; G01R31/00; G06F30/27; G06F111/08; G06F119/12; G06N3/04; G06N3/08

Foreign References:

CN114357663A	2022-04-15
US11220999B1	2022-01-11
CN113408068A	2021-09-17
CN111795819A	2020-10-20
CN112633245A	2021-04-09

Other References:

YANG MING, CHUANYANG DONG, DIANGUO XU: "Review of Gear Fault Diagnosis Methods Based on Motor Drive System", TRANSACTIONS OF CHINA ELECTROTECHNICAL SOCIETY, vol. 31, no. 4, 25 February 2016 (2016-02-25), XP093044033, ISSN: 1000-6753, DOI: 10.19595/j.cnki.1000-6753.tces.2016.04.009
JESUS ARELLANO-PADILLA ET AL.: "Condition Monitoring for Mechanical Faults in Fully Integrated Servo Drive Systems", 2008 13TH INTERNATIONAL POWER ELECTRONICS AND MOTION CONTROL CONFERENCE (EPE-PEMC 2008), 30 September 2008 (2008-09-30), pages 769 - 775, XP031328918

Attorney, Agent or Firm:

YICHANG THREE GORGES PATENT (CN)

Download PDF:

View/Download PDF PDF Help

Previous Patent: PHOTOGRAPHING METHOD AND ELECTRONIC DEVICE

Next Patent: METHOD AND APPARATUS FOR LABELING SPEECH DIALOGUE DURING HUMAN-COMPUTER INTERACTION, AND DEVICE AND ...