A new fault diagnosis method for power transformers

Xiaoxiao Zhao; Yuxin Yun; Xi Wang; Aijing Li; Xin Lin

doi:10.1117/12.3024487

13 May 2024 A new fault diagnosis method for power transformers

Xiaoxiao Zhao, Yuxin Yun, Xi Wang, Aijing Li, Xin Lin

Proceedings Volume 13159, Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023); 131595F (2024) https://doi.org/10.1117/12.3024487
Event: Eighth International Conference on Energy System, Electricity and Power (ESEP 2023), 2023, Wuhan, China

Abstract

Dissolved gas analysis can be abbreviated as DGA, which is a powerful and good method we used earlier to detect the initial fault operation of power transformers. In order to improve the accuracy of fault diagnosis based on DGA, this paper proposes a new fault diagnosis method that combines fuzzy logic with Cerebellar Model Articulation Controller (CMAC) neural network. Fuzzy CMAC Neural Network (FCMAC NN) utilizes each method to extract fuzzy logic diagnostic rules from a large number of fault samples, and trains CMAC based on the extracted rules to optimize its network. The combination of fuzzy logic and CMAC has an optimization mechanism to ensure high diagnostic accuracy for all general fault types. The proposed FCMAC neural network has been tested on many actual fault samples and its results have been compared with those of IEC ratio codes and CMAC networks, indicating that the method has significant diagnostic accuracy.

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

Citation Download Citation

Xiaoxiao Zhao, Yuxin Yun, Xi Wang, Aijing Li, and Xin Lin "A new fault diagnosis method for power transformers", Proc. SPIE 13159, Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023), 131595F (13 May 2024); https://doi.org/10.1117/12.3024487

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