Mehdi Ghrabli

Mehdi Ghrabli

PhD in applied mathematics

Publications

You can also find my articles on my Google Scholar profile.

Theses & Dissertations

Data-Efficient Reliability Assessment Using Machine Learning : Application to Lifetime Estimation of Power Electronic Modules

Published in theses.fr, 2026

This thesis introduces data-efficient machine learning methodologies for the lifetime estimation of power electronic modules. Key technical contributions include high-fidelity surrogate models for accelerated damage estimation, a probabilistic Physics-Informed Markov Chain framework, and BEDTime, a few-shot time series forecasting model utilizing Dynamic Time Warping to extrapolate long-term degradation from sparse data.

Download Paper

Journal Articles

AI surrogate models for lifetime prediction in power electronic modules

Published in Microelectronics Reliability, 2026

This work presents an accessible blueprint for applying AI to power electronics, utilizing machine learning metamodels to replace computationally expensive finite element simulations for lifetime prediction. We expand upon this framework by introducing a novel active learning data selection technique to further minimize simulation time, alongside rigorous residual and learning behavior analyses to ensure robust model evaluation.

Download Paper

Conference Papers

Data-driven Metamodels for Failure Analysis of Power Electronic Modules

Published in 36th European Symposium on Reliability of Electron Devices, Failure Physics and Analysis (ESREF 2025), 2025

We present the results of using machine learning surrogate models to replace computationally expensive finite element simulations for estimating the remaining useful life of power electronic modules. This approach drastically accelerates the pipeline, achieving a 10⁶ computational speed-up while maintaining high precision with an R² score of 0.962.

Download Paper

Hybrid modeling for remaining useful life prediction in power module prognosis

Published in 2024 25th International Conference on Thermal, Mechanical and Multi-Physics Simulation and Experiments in Microelectronics and Microsystems (EuroSimE), 2024

This paper presents a hybrid approach to estimate the remaining useful life of power electronic modules. It uses Paris law alongside an adaptive polynomial interpolation method to predict the evolution of the module s health indicator

Download Paper