Sandra Bickelhaupt

2022

1. S. Kamm, S. Bickelhaupt, K. Sharma, N. Jazdi, I. Kallfass, und M. Weyrich, „Simulation-to-Reality based Transfer Learning for the Failure Analysis of SiC Power Transistors“, in 27th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Stuttgart, Germany, September 2022, 2022.
   • Zusammenfassung
   • BibTeX
   • Link

   Zusammenfassung

   Failure analysis is essential for improving the reliability and manufacturability of electronic devices. With the time-domain reflectometry method, failures can be analyzed non-destructively. The method enables the detection, location, and characterization of hard interconnection failures (open or shorts) as well as of soft interconnection failures, which can give an outlook on imminent hard failures. Generating measurement data from real failed devices is costly since failed devices need to be selected and the measurements need to be performed and prepared. In contrast, simulation models are often available where all possible kinds of failures can be created. Therefore, we propose simulation to real transfer learning for the failure analysis on time-domain reflectometry data. A deep learning model shall first be trained on time-domain reflectometry simulation data and then be transferred to measurement data of a power transistor. We investigate different possibilities of transfer and evaluate the performance of a SiC power transistor.

   BibTeX

   @conference{kamm2022simulationtoreality, abstract = {Failure analysis is essential for improving the reliability and manufacturability of electronic devices. With the time-domain reflectometry method, failures can be analyzed non-destructively. The method enables the detection, location, and characterization of hard interconnection failures (open or shorts) as well as of soft interconnection failures, which can give an outlook on imminent hard failures. Generating measurement data from real failed devices is costly since failed devices need to be selected and the measurements need to be performed and prepared. In contrast, simulation models are often available where all possible kinds of failures can be created. Therefore, we propose simulation to real transfer learning for the failure analysis on time-domain reflectometry data. A deep learning model shall first be trained on time-domain reflectometry simulation data and then be transferred to measurement data of a power transistor. We investigate different possibilities of transfer and evaluate the performance of a SiC power transistor.}, author = {Kamm, Simon and Bickelhaupt, Sandra and Sharma, Kanuj and Jazdi, Nasser and Kallfass, Ingmar and Weyrich, Michael}, booktitle = {27th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Stuttgart, Germany, September 2022}, title = {Simulation-to-Reality based Transfer Learning for the Failure Analysis of SiC Power Transistors}, url = {https://doi.org/10.1109/ETFA52439.2022.9921681}, year = 2022 }

   Link

   https://doi.org/10.1109/ETFA52439.2022.9921681