A propos du centre ou de la direction fonctionnelle

The Inria centre at Université Côte d'Azur includes 42 research teams and 9 support services. The centre's staff (about 500 people) is made up of scientists of different nationalities, engineers, technicians and administrative staff. The teams are mainly located on the university campuses of Sophia Antipolis and Nice as well as Montpellier, in close collaboration with research and higher education laboratories and establishments (Université Côte d'Azur, CNRS, INRAE, INSERM ...), but also with the regiona economic players.

With a presence in the fields of computational neuroscience and biology, data science and modeling, software engineering and certification, as well as collaborative robotics, the Inria Centre at Université Côte d'Azur is a major player in terms of scientific excellence through its results and collaborations at both European and international levels.

Contexte et atouts du poste

Model Hybridization in Digital Twins for Mechanical Engineering
Context

Complex cyber-physical systems are evolving at an accelerating pace, operating in increasingly dynamic environments and contending with ever-increasing uncertainty. This requires a high level of adaptability, through a continuous engineering of complex cyber-physical, socio-technical, ecosystems. Digital twins are key enablers, and leverage on both model simulation and data science. Modeling & Simulation is a time-honored activity consisting in building complex analytical models to be simulated to evaluate natural or engineered phenomena. Conversely, data science relies on the availability of data to build complex predictive AI-based learning models. While both could be confused or even opposed, we argue they better complement each other to enhance the ability to best engineer complex systems continuously.

The sound hybridization of model simulation and data science enables a coordinated use of both techniques in complex scenarios (e.g., analytical models for explanation, and data model for recurrent pattern retrieval). Moreover, the hybridization also opens the door to adaptive modeling, where one model is inferred or refined by the others, and vice-versa (e.g., inferring or refining an analytical model from a learning model, and better tuning and explaining a learning model thanks to an analytical model).

Challenges are related to the identification of relevant patterns, and their proper implementations with well-defined interfaces for each model and the required protocols and operators to support the proposed scenarios. We aim to establish the first unifying theory for both model simulation and learning models, and demonstrate its applicability in practice within digital twins for mechanical engineering.

References

• R. Eramo, F. Bordeleau, B. Combemale, M. v. d. Brand, M. Wimmer and A. Wortmann, "Conceptualizing Digital Twins," in IEEE Software, vol. 39, no. 2, pp. 39-46, March-April 2022,
• R. Verdecchia, L. Cruz, J. Sallou, M. Lin, J. Wickenden and E. Hotellier, "Data-Centric Green AI An Exploratory Empirical Study," 2022 International Conference on ICT for Sustainability (ICT4S), Plovdiv, Bulgaria, 2022, pp. 35-45
• Narciso, Diogo AC, and F. G. Martins. "Application of machine learning tools for energy efficiency in industry: A review." Energy Reports 6 (2020): 1181-1199.
• Ahmad, Muhammad Waseem, Monjur Mourshed, and Yacine Rezgui. "Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption." Energy and buildings 147 (2017): 77-89.
• Zendehboudi S, Rezaei N, Lohi A. Applications of hybrid models in chemical, petroleum, and energy systems: A systematic review. Applied Energy. 2018;228:2539-2566. doi:10.1016/j.apenergy.2018.06.051.
• Slater L, Arnal L, Boucher MA, Chang AYY, Moulds S, Murphy C, et al. Hybrid forecasting: using statistics and machine learning to integrate predictions from dynamical models. Hydrology and Earth System Sciences Discussions. 2022;2022:1-35.
• Syauqi A, Pavian Eldi G, Andika R, Lim H. Reducing data requirement for accurate photovoltaic power prediction using hybrid machine learning-physical model on diverse dataset. Solar Energy. 2024;279:112814. doi: https://doi.org/10.1016/j.solener.2024.112814 .
• Mayer MJ. Benefits of physical and machine learning hybridization for photovoltaic power forecasting. Renewable and Sustainable Energy Reviews. 2022;168:112772. doi: https://doi.org/10.1016/j.rser.2022.112772 .
• Rudolph M, Kurz S, Rakitsch B. Hybrid modeling design patterns. Journal of Mathematics in Industry. 2024;14(1):3.
• von Rueden L, Mayer S, Sifa R, Bauckhage C, Garcke J. Combining machine learning and simulation to a hybrid modelling approach: Current and future directions. In: Advances in Intelligent Data Analysis XVIII: 18th International Symposium on Intelligent Data Analysis. Springer; 2020. p. 548-560.
• von Rueden L, Mayer S, Beckh K, Georgiev B, Giesselbach S, Heese R, et al. Informed machine learning-a taxonomy and survey of integrating prior knowledge into learning systems. IEEE Transactions on Knowledge and Data Engineering. 2021;35(1):614-633.
• Thummerer T, Mikelsons L. Learnable & Interpretable Model Combination in Dynamical Systems Modeling; 2025. Available from: https://arxiv.org/abs/2406.08093 .
• Hajirahimi Z, Khashei M. Hybridization of hybrid structures for time series forecasting: a review. Artificial Intelligence Review. 2022;56(2):1201-1261.
• Schweidtmann AM, Zhang D, von Stosch M. A review and perspective on hybrid modeling methodologies. Digital Chemical Engineering. 2024;10:100136.
• Yang S, Navarathna P, Ghosh S, Bequette BW. Hybrid modeling in the era of smart manufacturing. Computers & Chemical Engineering. 2020;140:106874.
• Wang J, Li Y, Gao RX, Zhang F. Hybrid physics-based and data-driven models for smart manufacturing: Modelling, simulation, and explainability. Journal of Manufacturing Systems. 2022;63:381-391.

Mission confiée

Objectives

Unifying theory for inductive and deductive reasoning
Hybrid modeling: coordinated use of heterogeneous predictive models.

This objective focuses on the definition of well-defined concepts to specify complex hybrid modeling scenarios through the coordinated use of different techniques involved in digital twins, e.g., Modeling & Simulation, Machine Learning, Data Mining, etc. These concepts will provide the semantic foundations to enact hybrid models in digital twin services such as recommenders, linters and decision-making tools.
Adaptive modeling: model adaptation (inference/refinement/configuration).

This objective focuses on the definition of well-defined concepts to specify complex adaptive modeling scenarios through a retro-action in between the different models involved in the different techniques (e.g., Modeling & Simulation, Machine Learning, Data Mining, etc.) These concepts will provide the semantic foundations to enact adaptive modeling scenarios in digital twin services such as modeling environment, and decision-making tools.
Model interfaces and protocols.

This objective aims at formalizing the required model interfaces and protocols to leverage on the two aforementioned objectives. The outcome if a unifying predictive platform, supporting both the orchestration of service requests on the different available predictive models, but also possibly the adaptation of them from others.

Principales activités

Application domain

The application domain of this work involves Mechanical equipments or systems made of several mechanical equipments. Several potential industrial applications in the field of Process equipment (fluid systems, specific components as valves,...), Mobile (off-road) working machines (as forklift or parts of it) and Production machines (welding robot, machining,...) are targeted. Therefore the developped pattern should be generic enough to encompass the aforementioned applications. Nevertheless, the existing thermal-hydraulic loop (JNEM) available at the Cetim facility may be use as a support for the involved developpment.

The JNEM loop is representative of an industrial process loop. It's a closed, instrumented hydraulic loop. It is equipped with a pump, a heat exchanger, a tank, a regulation valve and three piping sections. Its function is simply to provide the flow, pressure and/or temperature requested by the operator. Several control devices have been added to generate some defects artificially in the future.

This digital twin is designed to serve several purposes: predictive maintenance, optimization of process loop settings and decision support. The main objectives are to:

• Detect, localize, and estimate variations in process parameters (pipe clogging, heat exchanger performance degradation, valve dynamic behavior changes, etc.) through comparison with process parameters measurements (flow, pressure, temperature) at several locations of the physical system
• Optimization of the process loop settings (pump speed, valve opening) to reach target process parameters (flow, pressure, temperature) according to operator requirements (minimization of the time to reach the target, minimization of the energy consumption...) thanks to the simulation of different scenario using the digital twin. The "best" scenario is then automatically applied on the physical system through the driving of the involved actuators or through operator validation.
• Provide monitoring and prediction capabilities: use of virtual sensor to estimate and predict process parameters, such as flow rate (in the event of a flow meter failure), allowing for real-time monitoring and control of the physical system

Environment

This PhD is funded by the CETIM (the French Technical Center for Mechanical Industries) in the context of a collaboration with Inria (the national center for research in computer science). The main advisors of the PhD thesis will be Prof. Benoit Combemale (Inria, DiverSE team), Prof. Julien Deantoni (Université Cote d'Azur, I3S/Inria Kairos team), and Dr. Yoann JUS / Hubert LEJEUNE (CETIM).

The candidate will be involved either in the Inria DiverSE team (Rennes) or in the Inria Kairos team (Sophia-Antipolis), and will register either to the doctoral school in computer science of the University of Rennes or to the one from the University Côte d'Azur accordingly.

The DiverSE team is located in Rennes, France. DiverSE's research is in the area of software engineering. The team is actively involved in European, French and industrial projects and is composed of 13 faculty members, 25 PhD students, 4 post-docs and 8 engineers.

The Kairos team is located in Sophia Antipolis, France. Kairos's research focuses on continuous engineering, promoting synergies between heterogeneous artifacts throughout the whole development lifecycle. The team is actively involved in several projects at the regional, national, and European levels. It is composed of 6 lecturer-researchers, 4 PhD students, and 2 postdocs.

Compétences

Prerequisites

• A degree (and strong background) in data science and computer science (esp. software engineering)
• skills on numerical analysis, scientific computing and simulation
• interests in programming and modeling languages, and supporting envirionments
• interests in machine learning
• interests in mechanics
• professional proficiency in english
• skills for presenting and writting
• autonomly, rigor and hard worker

Avantages

• Subsidized meals
• Partial reimbursement of public transport costs
• Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
• Possibility of teleworking and flexible organization of working hours
• Professional equipment available (videoconferencing, loan of computer equipment, etc.)
• Social, cultural and sports events and activities
• Access to vocational training
• Contribution to mutual insurance (subject to conditions)

Rémunération

Duration: 36 months
Location: Sophia Antipolis, France
Gross Salary: 2 300€ per month