A method for evaluating the aging degree of an IGBT module

Abstract

The invention relates to a method for evaluating the aging degree of an IGBT module, comprising the following steps: the electrothermal characteristic data of the IGBT module under different aging degrees are measured and the aging degree calibration is completed; the network structure of the limit learning machine is initialized; the optimal input weights and hidden layer thresholds are obtained, and the optimal output weights of the limit learning machine are obtained. The IGBT module aging degree evaluation model of the extreme learning machine is obtained by training the extreme learningmachine. The electrothermal characteristic data of the IGBT module to be tested are measured and input into the aging degree evaluation model of the trained IGBT module so as to obtain the aging degree evaluation results. The invention adopts the limit learning machine optimized by the hybrid improved whale optimization algorithm to optimize the input weight value and the hidden layer threshold value, solves the problem that the prediction precision of the limit learning machine excessively depends on the input weight value and the hidden layer threshold value, and effectively improves the prediction regression ability of the limit learning machine.

Description

technical field [0001] The invention belongs to the technical field of power electronic devices, in particular to a method for evaluating the aging degree of an IGBT module. Background technique [0002] Insulated gate bipolar transistor (Insulated Gate Bipolar Transistor, IGBT) is the core device of electric energy transmission and conversion, and has a wide range of applications in the fields of smart grid, rail transit and renewable energy distributed power generation. These application areas have high requirements on the reliability of IGBTs. Once the IGBTs fail, it will cause serious economic losses and even cause major safety accidents. Therefore, to ensure the reliability of the IGBT module in the working process, it is very important to effectively evaluate the health status of the module. [0003] At present, the packaging of the IGBT module is usually a multi-layer structure, and the IGBT chip is fixed on the bottom plate through a copper layer, a ceramic layer an...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the deficiencies of the prior art, propose a method for evaluating the aging degree of IGBT modules, and solve the problem that the prediction performance of extreme learning machines is excessively dependent on the setting of initial weights and thresholds, resulting in the need for a large number of hidden layer nodes , to improve the predictive regression ability of the extreme learning machine

Images