26. Juli 2021, 11:34 Uhr | WEKA FACHMEDIEN, Newsdesk
The 1st prize of the IEEE Council on Electronic Design Automation (CEDA) is awarded to a team of eight researchers from the TU Ilmenau and the IMMS Institute for Microelectronic and Mechatronic Systems for their contribution to the ML-based plugin for KiCad »AnoPCB«.
The IEEE Council on Electronic Design Automation (CEDA) has awarded the EDA Competition Award and a prize money of 1000 US dollars to the contribution about a ML-based anomaly detection for PCB layout data, developed by TU Ilmenau and IMMS.
A team of eight undergraduate, graduate and research students from Ilmenau University of Technology and IMMS Institut für Mikroelektronik- und Mechatronik-Systeme gemeinnützige GmbH (IMMS) won the EDA Competition Award on July 22, 2021. The competition, sponsored by the IEEE Council on Electronic Design Automation (CEDA) for young scientists with 1000 US dollars, on the occasion of the international conferences on methods for integrated circuit design SMACD 2021 and PRIME 2021, called for demonstrating solutions that help improve design automation for integrated circuits and systems.
Julian Kuners, student of engineering informatics at TU Ilmenau and student assistant at IMMS, presented the paper »Trash or Treasure? Machine-learning based PCB layout anomaly detection with AnoPCB« to the jury consisting of representatives from Cadence Design Systems Germany, Dialog Semiconductor Germany, Infineon Technologies Germany, Gebze Technical University Turkey and Reutlingen University.
The Plugin »AnoPCB« for KiCad, developed by the TU Ilmenau and the IMMS Institute for Microelectronic and Mechatronic Systems, uses machine learning to detect anomalies in layout data and thus better account for coupling effects, for example.
The software project »AnoPCB« was supervised at the TU Ilmenau by Dr. Marco Seeland and Prof. Dr.-Ing. Patrick Mäder from the Chair of Data-Intensive Systems and Visualization and at the IMMS. The work builds on solutions developed in the Thuringian research group IntelligEnt for the layout of microelectronic chips. »In the layout of analog/mixed-signal circuits, one designs the blueprint for the chip manufacturer. However, formally correct layouts can contain inconsistencies, such as substrate coupling and mismatch«, explains Georg Gläser of IMMS, a specialist in integrating AI methods into design automation and head of the research group. Design experience of engineers plays a major role especially in the geometric design of circuits, and these last steps on the way to manufacturing require knowledge about which lines carry particularly sensitive or highly interfering signals and how they have to be handled, Gläser adds. »We have therefore developed an AI-based anomaly detection method in the research group that can detect non-proven and potentially faulty locations in layouts.« The solutions for flexible data representation are important here, he said, because they can be used to process layout data for both chips and printed circuit boards - and the latter is what the award-winning contribution is all about. »Julian Kuners, Henning Franke and Paul Kucera then further developed the software project as student employees at IMMS. They put the finishing touches on our learning anomaly detection method as a plugin for the free PCB design tool KiCad. This allows our approaches to be applied much more broadly«, is Gläser's assessment.
The »AnoPCB« plugin allows KiCad signals to be categorized and transferred to the training or evaluation process. The system was designed so that the design data is prepared at the user for the process and then transmitted to a central server for processing. Thus, on the one hand, a graphics processor that may be required is only needed in the server and, on the other hand, the designs of several users can be combined.
The jury evaluated the candidates' solutions on the basis of complexity, degree of automation, designer interface, applicability, degree of integration with available design tools, and robustness, among other factors: »The presented tool convinced the jury by the complexity of the posed problem, which in our estimation was solved well. The tool is user-friendly and we see it not only as an academic solution, but also as a solution that can be used in practical applications by PCB designers. The tool has significant potential and we are interested to see how it progresses«, said jury member Anton Klotz of Cadence Design Systems.
»For the first training, we used open-source designs such as Crazyflie and HackRF, and then added error locations there. With our anomaly detection plugin, we were able to locate these spots quickly and correctly«, explains Julian Kuners. »Of course, this spurs us on - and the prize anyway. We would like to use the occasion and call on developers to work with the plugin. The more training data there is, the more we can expand and improve it.« The plugin will be made available for this purpose in the near future.