Shizhe Feng, Yicheng Guo, Weihua Li, Haiping Du, Grzegorz Krolczyk and Z Li
{"title":"An IGBT coupling structure with a smart service life reliability predictor using active learning","authors":"Shizhe Feng, Yicheng Guo, Weihua Li, Haiping Du, Grzegorz Krolczyk and Z Li","doi":"10.1088/1361-665x/ad7659","DOIUrl":null,"url":null,"abstract":"An effective approach is proposed to evaluate the service life reliability of a multi-physics coupling structure of an insulated gate bipolar transistor (IGBT) module. The node-based smoothed finite element method with stabilization terms is firstly employed to construct an electrical-thermal-mechanical (ETM) coupling structure of the IGBT module, based on which the multi-physics responses can be accurately calculated to predict the service life of the IGBT module. By using the high-quality sample data obtained through the ETM coupling model, a Monte Carlo based active learning Kriging metamodel (AK-MCS) is developed to assess the service life reliability of the IGBT module, which can greatly reduce the computational cost needed by the surrogate model construction and reliability analysis. Numerical results show that the proposed ETM coupling structure can produce high-quality sample data of the IGBT dynamics and the AK-MCS machine learning technique can accurately estimate the service life reliability of the IGBT module.","PeriodicalId":21656,"journal":{"name":"Smart Materials and Structures","volume":null,"pages":null},"PeriodicalIF":3.7000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Smart Materials and Structures","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.1088/1361-665x/ad7659","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"INSTRUMENTS & INSTRUMENTATION","Score":null,"Total":0}
引用次数: 0
Abstract
An effective approach is proposed to evaluate the service life reliability of a multi-physics coupling structure of an insulated gate bipolar transistor (IGBT) module. The node-based smoothed finite element method with stabilization terms is firstly employed to construct an electrical-thermal-mechanical (ETM) coupling structure of the IGBT module, based on which the multi-physics responses can be accurately calculated to predict the service life of the IGBT module. By using the high-quality sample data obtained through the ETM coupling model, a Monte Carlo based active learning Kriging metamodel (AK-MCS) is developed to assess the service life reliability of the IGBT module, which can greatly reduce the computational cost needed by the surrogate model construction and reliability analysis. Numerical results show that the proposed ETM coupling structure can produce high-quality sample data of the IGBT dynamics and the AK-MCS machine learning technique can accurately estimate the service life reliability of the IGBT module.
期刊介绍:
Smart Materials and Structures (SMS) is a multi-disciplinary engineering journal that explores the creation and utilization of novel forms of transduction. It is a leading journal in the area of smart materials and structures, publishing the most important results from different regions of the world, largely from Asia, Europe and North America. The results may be as disparate as the development of new materials and active composite systems, derived using theoretical predictions to complex structural systems, which generate new capabilities by incorporating enabling new smart material transducers. The theoretical predictions are usually accompanied with experimental verification, characterizing the performance of new structures and devices. These systems are examined from the nanoscale to the macroscopic. SMS has a Board of Associate Editors who are specialists in a multitude of areas, ensuring that reviews are fast, fair and performed by experts in all sub-disciplines of smart materials, systems and structures.
A smart material is defined as any material that is capable of being controlled such that its response and properties change under a stimulus. A smart structure or system is capable of reacting to stimuli or the environment in a prescribed manner. SMS is committed to understanding, expanding and dissemination of knowledge in this subject matter.