Hot spot temperature prediction method for oil-immersed transformers based on ACO-SVM model

Feng Liang; Xin Yang; Pengfei Jia

doi:10.1117/12.2679560

18 July 2023 Hot spot temperature prediction method for oil-immersed transformers based on ACO-SVM model

Feng Liang, Xin Yang, Pengfei Jia

Proceedings Volume 12722, Third International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2023); 127220T (2023) https://doi.org/10.1117/12.2679560
Event: International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2023), 2023, Hangzhou, China

Abstract

At present, when artificial intelligence algorithm is used to predict the hot spot temperature of oil-immersed air-cooled transformer, the selection of the input characteristic quantity of the prediction model is not accurate enough and the prediction accuracy is insufficient. Based on the analysis of the internal temperature rise and heat dissipation process of the transformer, the tank wall temperature of oil-immersed air-cooled transformer is taken as one of the input characteristic quantities in the prediction model, an ant colony algorithm optimized support vector machine (ACO-SVM) model for predicting transformer winding hot spot temperature is established. Taking the measured data as a sample, the prediction performance of the model in this paper is compared with the PSO-SVM model and the SVM model, indicating that the proposed method has higher prediction accuracy and better applicability for predicting the hot spot temperature of oil-natural air-forced transformers.

Citation Download Citation

Feng Liang, Xin Yang, and Pengfei Jia "Hot spot temperature prediction method for oil-immersed transformers based on ACO-SVM model", Proc. SPIE 12722, Third International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2023), 127220T (18 July 2023); https://doi.org/10.1117/12.2679560

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