Iterative design of Socio-technical system Digital TWINs by AI-Augmented process mining
Context
Digital twins are virtual representations of real-world products, systems, or processes, enabling simulation, integration, testing, monitoring, and maintenance. They play a pivotal role in optimizing complex systems across a wide range of domains, from industrial manufacturing and energy to environmental monitoring and healthcare.
The Engineering Digital Twin EDT program, funded by the France 2030 investment plan, is a national initiative aimed at advancing the foundations of digital twin engineering in France and Europe. By bringing together leading academic and industrial partners, EDT seeks to strengthen the bases for the design, use, and deployment of digital twins, addressing key open challenges in model hybridization, composability, development methodologies, digital coupling, and human–twin interaction.
Organizational systems — hospitals, logistics networks, industrial plants — are governed by hundreds of decision rules that their operators rarely write down. People know how things work, but that knowledge is tacit: it lives in experience, not in documentation. This makes building accurate predictive models of these systems genuinely hard. Our objective is to build digital twins that learn those rules iteratively, by observing the gap between what the model predicts and what actually happens, then asking the right questions to the right people at the right time. The scientific challenge lies in formalizing that loop: how to detect meaningful divergences, how to classify them, how to structure the elicitation, how to integrate practitioners’ knowledge into a consistent model, and how to know when you are done. The implementation of this loop requires online and efficient methods, leveraging AI techniques such as incremental learning, streaming anomaly detection, and lightweight predictive models to ensure continuous adaptation to operational reality in real time. Two real healthcare pathway use cases will provide the validation ground throughout the thesis.
Thesis Objectives
Key scientific challenges include:
- Modeling organizational processes as Discrete Event Systems
- Designing divergence metrics between simulated and observed behavior
- Developing structured knowledge elicitation protocols with practitioners
- Implementing efficient methods, leveraging AI techniques to integrate elicited rules into digital twins.
- Validating the full methodology on live healthcare environments
Work Environment
The PhD candidate will be co-supervised by [Olivier CARDIN, Université de Nantes, LS2N], [Hind BRIL-EL HAOUZI, Université de Lorraine, CRAN], and [Abir ISMAILI ALAOUI, Université de Lorraine,CRAN]. The candidate will benefit from a stimulating scientific and industrial environment of the highest level, with access to a national network of leading research institutions and industry partners, regular interactions with the broader EDT community through workshops, seminars, and joint demonstrators, and the opportunity to contribute to Artemis, the program’s open software platform.
Three years of doctoral contract of Nantes University on a problem that is both scientifically open and operationally relevant. You will be part of the PEPR EDT national program, with access to a network of PhD students, academic and industrial partners, and a contribution to the Artemis open-source platform. Publication targets are international conferences and journals in simulation and systems engineering.
What You Will Gain from This PhD
This PhD offers the opportunity to:
- Develop highly sought-after skills in system modeling, real-time data processing, and collaborative innovation.
- Collaborate with leading partners (Inria, CRAN, CEA, CNRS, etc.) and validate your research on real-world industrial use cases.
- Join a network of PhD candidates within the EDT program, fostering collaboration, peer support, and interdisciplinary exchanges.
- Contribute to an open-source platform (Artemis) and publish in international conferences and journals.
- Gain recognition in a rapidly growing field, with career prospects in academic research, industrial R&D, or entrepreneurship.
Upon completion, you will be positioned as a recognized expert in a key domain for industry and research, with diverse professional opportunities in France and internationally.
Profile
A candidate with a Master’s degree in industrial engineering or computer science, with solid modeling skills and genuine curiosity for human-centered, real-world problems. Experience with simulation or process mining is a plus
Contacts
“” “”, “”