Transformer fault diagnosis based on IWOA optimized XGBoost

Sidan Lu; Xianwen Zeng

doi:10.1117/12.3008720

27 October 2023 Transformer fault diagnosis based on IWOA optimized XGBoost

Sidan Lu, Xianwen Zeng

Proceedings Volume 12922, Third International Conference on Electronics, Electrical and Information Engineering (ICEEIE 2023); 129221S (2023) https://doi.org/10.1117/12.3008720
Event: The Third International Conference on Electronics, Electrical and Information Engineering (ICEEIE 2023), 2023, Xiamen, China

Abstract

In order to address the low accuracy of existing transformer fault diagnosis techniques, this research suggests an unique transformer fault diagnostic model based on an improved whale algorithm optimized extreme gradient boosting (IWOA-XGBoost). First, based on Dissolved Gas Analysis (DGA) of oil, nine gas ratios were created utilizing the no coding ratio approach; Then use the hybrid strategy to improve the traditional WOA; Finally, IWOA is constructed to optimize XGBoost for transformer fault diagnosis. As compared to other algorithms, the accuracy rates of the experimental findings show that the model put forward in this study is superior, increasing by 16.89%, 11.69%, 6.5%, 3.9%, and 1.3%, respectively.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Sidan Lu and Xianwen Zeng "Transformer fault diagnosis based on IWOA optimized XGBoost", Proc. SPIE 12922, Third International Conference on Electronics, Electrical and Information Engineering (ICEEIE 2023), 129221S (27 October 2023); https://doi.org/10.1117/12.3008720

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

Includes PDF, HTML & Video, when available