In the context of the increased digitalization of production organizations and the emergence of Industry 5.0, which is more human-centered, the ability of companies to make the most of their digital capital (data, information, experience feedback, knowledge) is becoming increasingly important. Data and information processing is now a widely addressed subject (both in research laboratories and at the application level), but the management of experience feedback and knowledge often remains delicate for SMEs. Few works, and even fewer solutions, are available and we propose to work on the implementation of an innovative solution so that SMEs, the engines of the European economy, can have practical and ergonomic knowledge management tools, adapted to their specificities. The "REMIND 4.0" Joint Laboratory, involving the ENIT/LGP Laboratory and the AXSENS-bte company, thus aims to create an integrated and collaborative feedback and knowledge management platform for SMEs. This platform will be structured around two complementary and synergistic elements: an experience base resulting from problem-solving and a knowledge base. To achieve this objective, the research and innovation roadmap of the REMIND 4.0 Joint Laboratory is structured along 3 complementary axes contributing to the targeted platform: Axis 1. Capitalization, sharing and reuse of feedback in problem-solving Experience feedback from problem-solving is an important source of learning and continuous improvement for companies. In order to learn on a company-wide scale, it is important to capitalize on experience feedback and facilitate its sharing and reuse in an «Enterprise Experience Management System» (OEMS). The level of maturity of the partners on this subject has enabled the development of the "ProWhy" problem-solving and feedback software used daily by SMEs in various industrial sectors. As an extension of this work, we have identified a very promising research topic concerning exploratory processes (such as problem-solving processes) which constitutes a major scientific issue that we wish to remove in this area. Axis 2. New method of knowledge capitalisation and reuse for SMEs In this area, we propose to develop an original method and an appropriate support for the capitalization, sharing and reuse of knowledge for SMEs. To do this, we will take inspiration from the "Personal Knowledge Management" (PKM) approaches, which allow knowledge to be capitalized in a structured (graph of knowledge blocks) but not very formalized form. In recent years, several PKM tools have emerged (Roam research, Obsidian and more recently Logseq for example) to instrument this approach. In this section, we will study the extension of these PKM approaches to the scale of an enterprise (development of an "Enterprise Knowledge Management System" (OKMS)). In addition, we propose to define an acquisition process inspired by agile methods as well as a search and reuse mechanism based on a recommendation system. Axis 3: Hybridization and synergy between experience and knowledge bases The transition from a set of experiences (knowledge fragments) resulting from problem-solving to a more general and structured knowledge is a major challenge for organizational learning. However, it is particularly difficult to implement in a systematic and operational way. In this axis, we propose to explore the possible interactions and synergies between the experience base and the knowledge base resulting from the results of axes 1 and 2.

This project deals with the exploration of the possibility to use control theory tools for the design of vibrational piezoelectric energy harvesters (vPEH) devoted to supply tracking devices in migratory birds. The proposed explored techniques, radically different and scientifically novel relative to existing design methods of vPEH, will provide four major advantages: i) giving methodological designs, ii) pushing the actual limitation on power density, iii) introducing robustness for the harvested energy over a frequency variation of the ambient vibrations, iv) and permitting the substantial increase of their autonomy. The impact of the resulting vPEH to birds tracking are evident: volume and weight radically small allowing to equip more species of birds while than the actual possibility, devices autonomy extremely high (calculated for the bird entire life), and safety and harmlessness for the equipped animal thanks to the reduced sizes and weights.

According to the practical requirements of the factory of the future, this project combines the recent advancements in different domains to develop an explainable intelligent maintenance system (X-IMS) that enables both self-monitoring and decision-making support functionalities for connected manufacturing systems. The developed solution should allow automated construction of effective and interpretable health indicators for system continuous self-monitoring. They also integrate explainable intelligent algorithms for fault detection, diagnostic, and/or prognostics at the system level. Furthermore, embedded maintenance decision optimization algorithms, that can handle prediction uncertainties, component dependencies, and impacts of multiple maintenance activities will be developed. The optimal decision process obtained by the proposed intelligent algorithms should be explicitly conveyed to managers and therefore enable them to understand, trust, and effectively deploy the developed solution in practice. The performance of the algorithms developed in this project will be verified and highlighted by real industrial applications.