Generative AI for the Design of Next-Generation Power Converters, End-of-Life Guaranteed: Accelerated Topology Discovery and Multi-Criteria Optimization Integrating Ageing and Eco-Design

Next-generation wide-bandgap (SiC/GaN) power converters are at the heart of the electrification of our economy, yet their ageing and environmental impact are only assessed a posteriori, on a frozen design: this leads either to costly oversizing margins or, conversely, to nominally optimal designs that no longer meet their specifications at end of life. This thesis aims to remove this obstacle by establishing a closed-loop, generative-AI-based design loop in which end-of-life specification compliance and environmental impact per kWh converted become first-rank objectives, on a par with efficiency, volume, mass, EMC and consumption. The method couples a topology generation constrained by a versioned electrotechnical ontology, frontier LLM models, a propagation of multi-component drift (R_DS(on) and V_th of GaNs, ESR and capacitance of capacitors) up to system-level performance, recalibrated on accelerated tests, a multi-fidelity evaluation (physics-informed surrogates, simulation tools), and a multi-objective Bayesian optimization under probabilistic constraints, integrating LCA impact through a functional unit that depends on the predicted lifetime. The work will be validated experimentally on a converter prototype measured both new and aged, with explainability of the trade-offs. It capitalizes on the CEA's local generative-AI infrastructure (AITIANA Studio), aiming for measurable gains in reliability and environmental footprint, a reusable method, and open data.

New High-Temperature Heat Pump (> 250°C) upgrading industrial waste heat < 90°C by hybridizing thermodynamic cycles

Decarbonizing industry is crucial to mitigate the impacts of human activities on the environment. Particularly, high-temperature heat (> 250°C) needs are substantial and difficult to decarbonize because of the high amount of energy required. Thermodynamic cycles of Heat Pump (HP), such as Reversed Brayton (RB) cycle, allow for upgrading industrial waste heat to higher temperature usable by processes. However, the energy efficiency of HP to produce heat > 250°C from 100°C from 80°C waste heat with low energy consumption was developed in our laboratory.
This doctoral thesis offers to study an innovative high-temperature HP combining an AHT with a RB cycle. The concept consists of using the AHT to elevate the temperature level of waste heat to temperature > 100°C and provide it to the RB cycle to generate high-temperature heat > 250°C at a low energy cost. Thus, this hybrid system offers a solution to meet industrial needs in decarbonized high-temperature heat. The main challenges laying ahead are the selection of relevant coupling architectures, as well as the study and development of efficient thermal transfer interfaces.
This research work will require mastering modelling tools of thermodynamic cycles and heat exchangers. The thesis will also involve an experimental aspect, since validation of the numerical results on a laboratory test bench are expected.

Tuning the Electronic Structure of Tungsten Oxide Thin Films by Combinatorial Deposition: Impact of Intrinsic and Extrinsic Defects on Electrochemical Properties (DETOX Project)

We are offering a fully funded PhD position within the DETOX project, a collaborative research project involving CEA-TECH, CEA-INSTN, the Bordeaux Institute of Condensed Matter Chemistry (ICMCB), and FCSEL-LaRFIS at Polytechnique Montréal.
The DETOX project is dedicated to accelerated materials discovery, with a particular emphasis on electrochemical materials for electrochromic and photoelectrocatalytic applications. These two functionalities share a common redox origin: electrochromic materials reversibly modulate their optical properties under an applied voltage, while photoelectrocatalytic materials promote hydrogen production through solar-driven water splitting. Hence, understanding and controlling the relationship between defects, electronic structure, and electrochemical performance is a key scientific challenge.
The PhD project will focus on the synthesis of tungsten oxide (WO3)-based thin films using combinatorial magnetron sputtering. Tuning deposition parameters—including target composition, working pressure, and reactive atmosphere—the candidate will investigate how intrinsic and extrinsic defects influence the structural, morphological, electronic, and electrochemical properties of the deposited materials.
Combinatorial thin-film deposition provides a powerful high-throughput approach for rapid exploration of complex materials parameter spaces. Coupled with artificial intelligence and machine learning tools for data analysis and materials prediction, this strategy offers a significant acceleration in the discovery and optimization of functional materials.
The successful candidate will join a multidisciplinary consortium having complementary expertise in thin-film deposition, electrochemistry, materials characterization, and data-driven materials science. Throughout the project, the student will work closely with researchers from the four partner institutions, benefiting from their active supervision and scientific support.
The PhD will be carried out within the DIADEM Priority Research Programme and Equipment (PEPR), a national initiative coordinated by CNRS and CEA which aims to accelerate the discovery of innovative materials through artificial intelligence.
The research will be held primarily in Bordeaux, France at two partners laboratories:
- CEA Tech Materials Screening Platform (PRTT Nouvelle-Aquitaine)
- Bordeaux Institute of Condensed Matter Chemistry (ICMCB)
The project will also include regular research visits to CEA-INSTN in Saclay and an international research stay of 9 to 12 months at Polytechnique Montréal (Canada), providing the candidate a valuable international research experience.

Top