Fédération dirigée par les modèles des systèmes de modélisation

The engineering of complex systems and systems of systems often leads to complex concurrent modelling activities (MA). Some problems exhibited by these MA are: understanding the context where they are carried out and their impacts on the lifecycles of models they produce, and ultimately providing a support for mastering them. How to address these problems with a formal approach is the central challenge of this thesis. In this thesis, we start by discussing the related works from systems engineering in general and the co-engineering of the product (system to be made) and the project (system for make) systems. The main challenges that emerge from this discussion for the mastering of MA are: the explicit and adequate abstractions of MA (and generally the product-and-process) – henceforth considered as the System-Of-Interest; the modelling framework to study this system; explicit algorithms for models (of the SOI) analysis against some formal requirements; the tooling of approaches. Following this discussion, we position a devised and developed methodology named MODEF, which addresses the aforementioned challenges and aims to master the operation of MA. MODEF consists in: (1) characterizing MA as a system (and more globally as a federation of systems) in its own right; (2) iteratively architecting this system through: the modelling of the conceptual content of the models produced by MA and their life cycles, the tasks carried out within MA and their effects on these life cycles; (3) specifying the expectations over these life cycles and; (4) analysing models of MA against expectations (and possibly tasks constraints) – to check how far expectations are achievable – via the synthesis of the acceptable behaviours. On a practical perspective, the exploitation of the results of the analysis allows of figuring out what could happen with the modelling tasks and their impacts on the whole state of models they handle. We show on two case studies how this exploitation provides insightful data on how the system (i.e. MA) is end-to-end operated and how it can behave. Based on this information, it is possible to take some preventive or corrective actions on how the MA are carried out. On the foundational perspective, the formal semantics of three kinds of involved models and the expectations formalism are first presented. Then the analysis and exploitation algorithms are presented. The latter are roughly compared with model checking and systems synthesis approaches. Last but not least, two enablers whose first objectives are to ease the implementation of MODEF are presented. The first one is a modular implementation of MODEF's building blocks. The second one is a federated architecture (FA) of models which aims to ease reuse models in practice and independently of a specific modelling tool. Despite the fact that FA is formalized within the abstract framework of category theory, an attempt to bridge the gap between abstraction and implementation is sketched via some basic data structures and base algorithms. Finally, several perspectives (on resources allocation, analysis algorithms, model architecture, and expectations) related to the different components of MODEF conclude this work.Keywords: systems engineering, product (system to be engineered) /project (system for engineering), model-based system engineering, architecture, assumption/preference formalism, model semantics, modelling-analysis, co-exploration, tooling issues, model reuse, multicategories, algorithmic