A Convolutional Neural Network Based on Attention Mechanism for Designing Vibration Similarity Models of Converter Transformers

Abstract

A vibration scale training model for converter transformers is proposed by combining attention modules with convolutional neural networks to solve the nonlinear problem of converter transformers in similar processes. Firstly, according to the structure and operating parameters of the converter transformer, a reliable three-dimensional multi-field coupled finite element model was established considering the influence of the winding and iron core component structure on the overall vibration characteristics. By changing different input parameters such as the size and voltage of the finite element model, corresponding output parameters are obtained, and a dataset is established through data expansion for training and verifying the attention convolution model. By analyzing the prediction processes and results of five prediction models on different operating conditions datasets, it is shown that attention convolution has higher accuracy, faster convergence speed, more stable training process, and better generalization performance in the prediction process of converter transformer recognition. Based on the predictive model, a prototype of the proportional vibration model for the converter transformer with scale factor of 0.2 was designed and manufactured. By analyzing the basic experimental items and vibration characteristics of the prototype, the stability of the prototype and the reliability of the prediction model were verified.