IEEE Transactions on Industrial Electronics, pp. 1-1, 2021. DOI: 10.1109/tie.2021.3068681

Degradation Estimation and Prediction of Electronic Packages using Data Driven Approach

Alexandru Prisacaru1, Przemyslaw Jakub Gromala2, Bongtae Han3, G.Q. Zhang4

1 Reliability Modeling and System Optimization, Robert Bosch GmbH, 39259 Gerlingen-Schillerhohe, Germany, 70839
2 AE/ECU3, Robert Bosch GmbH, 39259 Gerlingen-Schillerhohe, Baden-Wrttemberg, Germany
3 University of Maryland at College Park College of Computer Mathematical and Natural Sciences, 123981 College Park, Maryland, United States
4 Delft University of Technology, Netherlands


Recent trends in automotive electronics such as automated driving will increase the number and complexity of electronics used in safety relevant applications. Applications in logistics or ridesharing will require a specific year of service. Reliable operations of the electronic systems must be assured at all times, regardless of the usage condition.A more dynamic and on-demand way of assuring the system availability will have to be developed. This paper proposes a thermo-mechanical stress-based prognostics method as a potential solution.The goal is achieved by several novel advancements.On the experimental front, a key microelectronics package is developed to directly apply the prognostics and health management(PHM) concept using a piezoresistive silicon-based stress sensor.On the data-management front, proper data-driven approaches have to be identified to handle the unique data set from the stress sensor employed in the study.The approaches effectively handle the massive amount of data that reveals the important information and automation of the prognostic process and thus to be able to detect, classify, locate and predict the failure.The statistical techniques for diagnostics and the machine learning(ML) algorithms for health assessment and prognostics are also determined to implement the approaches in a simple, fast but accurate way within the capacity of limited computing power.

This article is available online here and to CALCE Consortium Members for personal review.

[Home Page] [Articles Page]
Copyright © 2021 by CALCE and the University of Maryland, All Rights Reserved