Temperature and Fault Prediction of Transformer in Distribution Station Based on Digital Twin Model

Abstract

This article presents an innovative method for predicting transformer temperature and faults in distribution substations using a digital twin model combined with deep learning techniques. By constructing a digital model of the transformer, real-time monitoring and precise simulation of its operating status are achieved. In the prediction process, convolutional neural networks (CNN) and long short-term memory networks (LSTM) are fused to mine data features deeply and predict the future state of the transformer. The results show that this method demonstrates significant advantages in transformer temperature and fault prediction, with an accuracy rate as high as 96.55%. Moreover, the error rate of this method has been significantly reduced through comparative experimental verification. In addition to ensuring high accuracy, this method achieves a false alarm rate of less than 0.12% and an average detection time of only 1.35 seconds, further highlighting its effectiveness in practical applications. Therefore, the transformer temperature and fault prediction system developed in this article for distribution substations can effectively improve the stability and safety of the electrical power system (EPS) and provide new and powerful support for the intelligent management and maintenance of transformers.

Keywords

• digital twin model
• radio distribution area
• transformer
• temperature
• fault detection
• 68t27