A fault diagnosis method of wind turbine gearbox based on CNN-ISABO-SVM

Shengliang Yu; Lijie Zhang; Ze Xu

doi:10.1117/12.3052262

30 December 2024 A fault diagnosis method of wind turbine gearbox based on CNN-ISABO-SVM

Shengliang Yu, Lijie Zhang, Ze Xu

Author Affiliations +

Proceedings Volume 13394, International Workshop on Automation, Control, and Communication Engineering (IWACCE 2024); 133941P (2024) https://doi.org/10.1117/12.3052262
Event: International Workshop on Automation, Control, and Communication Engineering (IWACCE 2024), 2024, Hohhot, China

Abstract

Aiming at the problem that the early fault signal of wind turbine gearbox is weak and difficult to extract effective features, this paper proposes a fault diagnosis method based on convolutional neural network (CNN) and improved support vector machine (SVM). The S-transform is used to convert the one-dimensional gearbox vibration signal into a two-dimensional feature map containing time-frequency characteristics, and the CNN is constructed to extract features from the time-frequency map. The Latin hypercube and golden sine strategies are introduced to improve the Subtractive average Optimization Algorithm (SABO), and the improved SABO algorithm is used for parameter searching of the SVM, and an ISABO-SVM classifier is designed to classify the extracted fault features and derive the fault diagnosis results. The experimental results show that the CNN-ISABO-SVM wind turbine gearbox fault diagnosis model proposed in this paper has higher accuracy compared to the CNN-SVM and CNN-SABO-SVM fault diagnosis models.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Shengliang Yu, Lijie Zhang, and Ze Xu "A fault diagnosis method of wind turbine gearbox based on CNN-ISABO-SVM", Proc. SPIE 13394, International Workshop on Automation, Control, and Communication Engineering (IWACCE 2024), 133941P (30 December 2024); https://doi.org/10.1117/12.3052262

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE