摘要详情

ID / 提交时间

48 / 2023-10-01 17:43:45

标题

Deep Learning -Based Remaining Life Prediction for DC-Link Capacitor in High Speed Train

关键字

Residual life prediction, support capacitors, long short-term memory neural networks, macro-micro attention mechanism, particle swarm optimization.

主题及专题

6.AI-driven technology > (4)、Fault prognosis and life prediction

状态

终稿

作者

Zhang Kunpeng / East China Jiaotong University

摘要

The accurate prediction of the remaining useful life of DC-link capacitors is crucial in high-speed railway traction drive operating conditions. This prediction takes into account environmental factors, physical structure, and strict safety operation requirements. In this paper, we propose a method for predicting remaining life using deep learning optimized by the particle swarm algorithm. Firstly, the upper and lower voltage of the capacitor are selected as the characteristic values. By denoising the voltage with wavelet transform, we calculate failure thresholds for both ends of the support capacitor. Then, we amplify the input weights in real-time using the Long Short-Term Memory (LSTM) neural network with a macro-micro attention mechanism. Finally, we utilize the particle swarm optimization algorithm to optimize the number of input units and the learning rate of the neural network for the purpose of predicting lifetime. The effectiveness of this method is verified through model evaluation indices in a case study of high speed train traction system.