A method, apparatus, device, and storage medium for predicting the remaining lifetime of an IGBT module.

By collecting operating data and health parameters of IGBT modules, combining rainflow counting and cycle feature extraction, and using LESIT and Norris-Landzberg models to calculate the theoretical lifespan, and performing health parameter correction and time series prediction, the problem of lifespan prediction of IGBT modules under complex operating conditions is solved, and more accurate lifespan assessment is achieved.

CN122307288APending Publication Date: 2026-06-30CRRC CHANGCHUN RAILWAY VEHICLES CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CRRC CHANGCHUN RAILWAY VEHICLES CO LTD
Filing Date
2026-04-14
Publication Date
2026-06-30

AI Technical Summary

Technical Problem

Existing technologies are insufficient to accurately describe the thermal stress distribution characteristics and life prediction of IGBT modules under complex and non-stationary operating conditions, resulting in life assessment results that do not match actual operation.

Method used

By collecting operating data and health parameters of IGBT modules, rainflow counting and cycle feature extraction are performed. The theoretical lifetime is calculated by combining LESIT and Norris-Landzberg models. Health parameter correction and time series prediction are used, and finally weighted fusion is performed to improve prediction accuracy.

Benefits of technology

It enables accurate lifetime prediction of IGBT modules under complex stress conditions, improves the reliability and accuracy of lifetime assessment, and can better reflect the actual degradation law of the device.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122307288A_ABST
    Figure CN122307288A_ABST
Patent Text Reader

Abstract

This application discloses a method, apparatus, device, and storage medium for predicting the remaining life of an IGBT module. When the train meets the target operating conditions, multiple sets of operating data from the traction auxiliary converter and multiple sets of health measurement parameters from the target IGBT module are simultaneously collected within a preset time period, ensuring that the two types of data are time-aligned and time-period-corresponding. The chip junction temperature is calculated based on the operating data, and cycle characteristic parameters are extracted through rainflow counting to calculate the physical predicted remaining life. The physical life is then corrected using health parameters such as junction-to-shell thermal resistance increment and on-state voltage drop drift to obtain the corrected remaining life. Simultaneously, prediction is performed based on the time-series characteristics of the health parameters to obtain the data-fitted remaining life. Finally, the corrected remaining life and the data-fitted remaining life are weighted and fused to output the final remaining life. This application can effectively improve the accuracy of remaining life prediction for IGBT modules under complex stress conditions.
Need to check novelty before this filing date? Find Prior Art