Active Design Aided Deep Learning for Reliability of DC-Link Capacitor in Traction Drive System

In order to solve the reliability problem of DC-link capacitor, a capacitor active design method based on deep learning is proposed. Staring from the introduction of two test case, the electrical parameters of film capacitor are collected and the lifetime expectancy of the capacitors is solved. A deep learning network model is established through the Deep Neural Network. The model can quickly and accurately map the performance parameters of capacitors to the volume, cost and lifetime expectancy of the selected dc-link capacitors, and realize the selection and design of the DC-link film capacitor in the traction drive system.