Julian M. Angel F., J. A. G. Higuera, A. Bernal, Carlos E. Villarraga Pinzon
{"title":"神经网络在微机电系统故障检测中的比较","authors":"Julian M. Angel F., J. A. G. Higuera, A. Bernal, Carlos E. Villarraga Pinzon","doi":"10.1109/CERMA.2010.32","DOIUrl":null,"url":null,"abstract":"The development of microelectronic industry has been related with the development of methodologies for detection of faults, either in production lines or in the field of action of devices. This has not happened in the industry of micro electromechanical systems (MEMS), which have made great progress in developing device but the fault detection techniques have been inherited the microelectronic. This presents a major problem since the nature of failures in MEMS is radically different from microelectronic failure. Given the complexity of fault modeling MEMS multi physics propose the use of neural networks as classifier system failures that could be implemented in systems self-test or verification in production line for these devices. Defective Comb Drive is detected by neural networks using as an input the resonance frequency and the gain.","PeriodicalId":119218,"journal":{"name":"2010 IEEE Electronics, Robotics and Automotive Mechanics Conference","volume":"64 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Comparison of Neural Networks to Detect Failures in Micro-electro-mechanical Systems\",\"authors\":\"Julian M. Angel F., J. A. G. Higuera, A. Bernal, Carlos E. Villarraga Pinzon\",\"doi\":\"10.1109/CERMA.2010.32\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The development of microelectronic industry has been related with the development of methodologies for detection of faults, either in production lines or in the field of action of devices. This has not happened in the industry of micro electromechanical systems (MEMS), which have made great progress in developing device but the fault detection techniques have been inherited the microelectronic. This presents a major problem since the nature of failures in MEMS is radically different from microelectronic failure. Given the complexity of fault modeling MEMS multi physics propose the use of neural networks as classifier system failures that could be implemented in systems self-test or verification in production line for these devices. Defective Comb Drive is detected by neural networks using as an input the resonance frequency and the gain.\",\"PeriodicalId\":119218,\"journal\":{\"name\":\"2010 IEEE Electronics, Robotics and Automotive Mechanics Conference\",\"volume\":\"64 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2010-09-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2010 IEEE Electronics, Robotics and Automotive Mechanics Conference\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CERMA.2010.32\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 IEEE Electronics, Robotics and Automotive Mechanics Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CERMA.2010.32","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A Comparison of Neural Networks to Detect Failures in Micro-electro-mechanical Systems
The development of microelectronic industry has been related with the development of methodologies for detection of faults, either in production lines or in the field of action of devices. This has not happened in the industry of micro electromechanical systems (MEMS), which have made great progress in developing device but the fault detection techniques have been inherited the microelectronic. This presents a major problem since the nature of failures in MEMS is radically different from microelectronic failure. Given the complexity of fault modeling MEMS multi physics propose the use of neural networks as classifier system failures that could be implemented in systems self-test or verification in production line for these devices. Defective Comb Drive is detected by neural networks using as an input the resonance frequency and the gain.