Predictive maintenance is a core concern in CEA-Leti’s laboratories, where highly sophisticated and sensitive systems underpin the work of research engineers. By extending machine lifespans, preventing unplanned downtime and improving maintenance planning in critical sectors, it has become a natural area for the Systems Department to combine established methods with artificial intelligence.

That approach is already drawing recognition. At the 2025 International Conference on Prognostics and Health Management in Seattle, Guillaume Prevost, a PhD student in signal processing and AI, presented the paper “Knowledge-Informed Symbolic Regression for New Features Discovery for Degradation Analysis of Rolling Bearings,” which received a Best Paper Award.

The work reflects the multidisciplinary nature of CEA-Leti projects. Predictive maintenance efforts bring together expertise in physical modeling, signal processing and data analysis. Team members include Youssof, who contributes physical modeling expertise, and Guillaume, who focuses on signal and data processing.

Another member, Leila Merzak, a PhD student in modeling and signal processing, said one of the team’s current applications is the development of digital twins for damage prediction and state-of-health estimation in mechanical structures. Her own PhD research applies this approach to knee prostheses.

Célestin Ott, a research engineer in multiphysics modeling at CEA-Leti, said combining digital twins with physics-informed AI makes predictive maintenance more accurate and more targeted by improving fault detection and degradation forecasting.

The collaboration is also marked by a lighter side. Célestin described the team’s exchanges as “very constructive and engaging,” and recalled a humorous episode when Guillaume ordered a milling machine for the lab to support experimental studies on state-of-health monitoring in rotating machinery, using ultrasonic sensing to anticipate degradation for predictive maintenance.

​​​​​​​​Ongoing predictive maintenance is critical in CEA-Leti labs, whose sophisticated and sensitive systems support the vital work of research engineers. Effective maintenance extends the lifespan of machines, prevents unplanned downtime, and optimizes mainten​​ance in key sectors. In CEA-Leti's Systems Department, researchers are incorporating artificial intelligence with established practices.​

It is no surprise that these enhanced tools are being incorporated in multiple industrial sectors and are receiving recognition.

At the 2025 International Conference on Prognostics and Health Management in Seattle,Guillaume Prevost, a PhD student in signal processing and AI,presented a papertitled, “Knowledge-Informed Symbolic Regression for New Features Discovery for Degradation Analysis of Rolling Bearings." It won a Best Paper Award.​

Like most CEA-Leti projects, predictive maintenance involves multidisciplinary teams, for example expertise in physical modeling, which Youssof brings, and Guillaume's signal-and-data processing.

Team member Leila Merzak, a PhD student in modeling and signal processing, said one of the team's current use cases is focused on developing digital twins for damage prediction and state of health estimation on mechanical structures. For example, in the framework of her PhD research, on knee prostheses.

Célestin Ott, a research engineer-multiphysics modeling at CEA-Leti, explained that integrating digital twins with physics-informed artificial intelligence enables more accurate and targeted predictive maintenance by improving the reliability of fault detection and degradation forecasting.

Like all well-matched research teams, the members recognize an opportunity to share a humorous moment along with their “very constructive and engaging exchanges", as Célestin describes them.

As when Guillaume ordered a milling machine for the lab to conduct experimental studies on tools' state-of-health (SoH) monitoring in rotating machinery, using ultrasonic sensing to anticipate degradation for predictive-maintenance purposes.