Abstract:

Recent advancements in automotive technologies, most notably autonomous driving, demand electronic systems much more complex than those realized in the past. The automotive industry has been forced to adopt advanced consumer electronics to satisfy the demand, and thus it becomes more challenging to assess system reliability while adopting the new technologies. The system-level reliability can be enforced by implementing a process called condition monitoring. In this paper, a piezoresistive silicon-based stress sensor is implemented to recognize in situ failure in outer molded electronic control units subjected to reliability testing conditions. The test vehicle consists of six double decawatt package power packages and three stress sensors mounted on a printed circuit board. A unique algorithm is proposed and implemented to handle the data obtained from the piezoresistive stress-sensing cells. The accuracy of measured data is examined by finite-element method, and the physical changes are validated with scanning acoustic microscope. Oneclass support vector machines are used to autonomously classify data based on a training set of measurements from healthy state, and the reported results confirm that robust classification is possible based on data from the silicon stress sensor

© IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.