Special Session 4

SPECIAL SESSION #4

Automotive Fault Mitigation in the R-PODID European Project

Marco Crescentini

University of Bologna, Italy

• m.crescentini@unibo.it

Pier Andrea Traverso

University of Bologna, Italy

• pierandrea.traverso@unibo.it

Fault mitigation in automotive applications refers to the architectures, strategies and techniques employed to predict, detect, manage, and recover from faults (failures or malfunctions) in-vehicle systems, particularly in critical functions such as braking, steering, and powertrain. As modern vehicles increasingly rely on complex, interconnected systems (like Advanced Driver Assistance Systems (ADAS), Electric Vehicle (EV) drivetrains, and autonomous driving features), ensuring system reliability and safety is a growing challenge. This increase in complexity and required performance is valid for the systems embedded in the vehicle and the testbeds used to characterize and qualify automotive components. Those challenges can be faced by the development of advanced and innovative sensors and methodologies for fault detection and diagnostics, fault prediction models and algorithms, predictive maintenance approaches, self-testing, and self-repairing, to cite a few.

R-PODID is a European Project started in September 2023 that aims at the general goal of developing an automated, cloudless, short-term fault-prediction approach for electric drives, power modules, and electronic devices that can be integrated into power converters without losing performance by the exploitation of AI methodologies. The project defines four different applicative use cases, two of which are oriented to the automotive sector, tackling the challenges related to fault mitigation either embedded into an electrical powertrain or applied to a high-duty testbed.

In this workshop, we will examine the solutions developed by the Partners of the R-PODID consortium at the component, algorithmic, methodology, and system levels. These include sensor technologies for fault detection, experimental characterization of components, modeling of faults in complex systems, exploitation of AI models for fault detection, hybrid physical-AI reliability models, and techniques for embedding AI into resources-sparce devices used in automotive. Participants will have the opportunity to learn from experts in the field and participate in interactive discussions on the challenges and opportunities of implementing these technologies in the automotive industry.

Prospective authors can provide original contributions that can include, but are not limited to, the following aspects:

• Sensors and sensing systems for automotive real-time monitoring and fault detection (e.g., current/voltage sensors, vibration sensors, electromagnetic sensors, temperature sensors etc.);
• Advanced characterization techniques for active/passive devices, components, and systems used in automotive applications (e.g., power transistors, bearings, machines, gearboxes, inverters, etc.);
• AI-based fault and reliability models for automotive applications;
• Testing and measurement procedures for automotive devices, modules, and systems;
• Embedding techniques for AI deployment on resource-scarce devices.

Marco Crescentini (Member, IEEE) received the Ph.D. degree from the University of Bologna, Bologna, Italy, in 2012. He is currently an Associate Professor with the Department of Electrical, Electronic, and Information Engineering “Guglielmo Marconi,” University of Bologna, Cesena Campus. He authored or coauthored more than xxxx papers in technical journals or proceedings of international conferences. He is the coordinator of the CHIPS-JU European Project R-PODID. His current research interests include the design of high-accuracy, low-noise, and broadband instrumentation for either biomedical or energy applications.

Pier Andrea Traverso received the M.S. degree (cum laude) in Electronic Engineering and the Ph.D. degree in Electronic and Computer Science Engineering from the University of Bologna, Italy, in 1996 and 2000, respectively.
Since 2002, he is with the Department of Electrical, Electronic and Information Engineering "Guglielmo Marconi" - DEI, University of Bologna, where he is currently Associate Professor of Electrical and Electronic Measurement and teaches for the Courses in the ICT area.
Pier Andrea Traverso is the Coordinator of the I&M research activity of the Group of Electronic Design and Measurement for RF and Industrial Applications (EDM-Lab) of University of Bologna. His main research interests are in the areas of nonlinear dynamic system characterization and empirical modeling, micro- and millimeter-wave semiconductor device characterization and modeling, smart sensor nodes and advanced sampling instrumentation & techniques. He is the co-author of more than 130 international journal/conference technical papers.
Pier Andrea Traverso is a member of the TC-10 Committee (Waveform Generation, Measurement and Analysis) - Subcommittees on Jitter, Digital-to-Analog Converters, Analog-to-Digital Converters and Transitions, Pulses, and Related Waveforms - of the IEEE Instrumentation and Measurement Society. He is a member of the Italian Association of Electrical and Electronic Measurement (GMEE).