Temperature Prediction of Box-type Transformer High-Voltage Bushing Based on ELM

Aiming at the current situation of high temperature of transformer components and high accident rate of transformer bushing caused by closed environment and poor heat dissipation performance of box-type transformer, a prediction method of high-voltage bushing temperature of box-type transformer based on extreme learning machine (ELM) is proposed. Firstly, the sliding window method is used to construct the sample sets. Then, a transformer high-voltage bushing temperature prediction model based on ELM is established. ELM model has fast learning speed and good generalization performance. Finally, taking the relevant monitoring data of high-voltage bushing of a box-type transformer as an example, the field data are preprocessed. The effectiveness of the proposed method is verified through analysis, and the effects of the number of hidden layer neurons, activation function and sliding window width on the prediction effect are compared and analyzed.