A method for evaluating the aging degree of an IGBT module

A technology of aging degree and implementation method, which is applied in the field of power electronic devices, can solve the problem that the prediction performance of extreme learning machines is overly dependent on the initial weight and threshold setting, etc., so as to improve the prediction regression ability, overcome the lack of search ability, and evaluate the results full effect

Active Publication Date: 2018-12-28
HEBEI UNIV OF TECH
View PDF4 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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 learn

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method for evaluating the aging degree of an IGBT module
  • A method for evaluating the aging degree of an IGBT module
  • A method for evaluating the aging degree of an IGBT module

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0056] The embodiments of the present invention are described in further detail below with reference to the accompanying drawings.

[0057] The present invention is implemented based on the following design principles:

[0058] 1. Extreme learning machine

[0059] The Extreme Learning Machine (ELM) is a fast single hidden layer feedforward neural network learning algorithm. The algorithm only needs to set the number of neurons in the hidden layer and the type of activation function. ELM can calculate the output weights according to the input weights and thresholds randomly generated before training, and finally obtain the optimal solution. Compared with the traditional neural network algorithm, ELM has the advantages of fast learning speed and good method performance.

[0060] For a single hidden layer neural network, the input layer has n neurons, the hidden layer has L neurons, and the output layer has m neurons. Suppose there are training data with Q samples {(x i ,y i )}, where t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

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...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F17/50G06N3/08G06N3/00
CPCG06N3/006G06N3/08G06F2119/04G06F30/39
Inventor 李玲玲孙进冯一博彭桦冯欢刘伯颖
Owner HEBEI UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap