{"title":"Towards a new health prognostics method for inverters: Power SiC-GTO failures and its precursors","authors":"Lifang Liu, An Xiang, Shun Li, Yijia Du, Gang Dai","doi":"10.1109/ICPHM.2017.7998330","DOIUrl":"https://doi.org/10.1109/ICPHM.2017.7998330","url":null,"abstract":"A device-based health conditions monitoring and diagnosis method for inverters is present. In the inverter, SiCGTO (Gate-Turn-Off Thyristor) is considered as the key device to achieve pulse-width modulation. So the performance degradation of SiC-GTO device induced by interface-states is critical for the health conditions of inverters. In the research, key electrical parameters, including the forward blocking voltage and the dynamic switch characteristics, are evaluated for SiC-GTO device with elevated interface-states density. Results indicate that the forward blocking voltage, turn-on/off speed and gate drive current can be used as precursors for the failure. Based on further study, a test structure and an indirect precursor are developed for feasibly application on health prognostics algorithms (data-driven or physics-based) of failure with interface-states accumulation as a mechanism.","PeriodicalId":124147,"journal":{"name":"2017 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126383018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Deovrat Kakde, A. Chaudhuri, Seunghyun Kong, M. Jahja, Hansi Jiang, Jorge Silva
{"title":"Peak criterion for choosing Gaussian kernel bandwidth in Support Vector Data Description","authors":"Deovrat Kakde, A. Chaudhuri, Seunghyun Kong, M. Jahja, Hansi Jiang, Jorge Silva","doi":"10.1109/ICPHM.2017.7998302","DOIUrl":"https://doi.org/10.1109/ICPHM.2017.7998302","url":null,"abstract":"Support Vector Data Description (SVDD) is a machine learning technique used for single class classification and outlier detection. SVDD formulation with kernel function provides a flexible boundary around data. The value of kernel function parameters affects the nature of data boundary. For example, it is observed that with Gaussian kernel, as the value of kernel bandwidth is lowered, the data boundary changes from spherical to wiggly. The spherical data boundary leads to underfitting and extremely wiggly data boundary leads to overfitting. In this paper we propose an empirical criteria to obtain a good value of Gaussian kernel bandwidth which provides a smooth boundary capturing the essential visual features of the data.","PeriodicalId":124147,"journal":{"name":"2017 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127851787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}