Periodic Reporting for period 1 - ELO-X (Embedded learning and optimization for the next generation of smart industrial control systems)
Période du rapport: 2021-01-01 au 2022-12-31
Digital technologies are transforming all sectors of our economy and will increasingly do so in the years to come. Thanks to the increasing capabilities of digital technologies, the next generation of smart industrial control systems (SICS) are expected to learn from streams of data and to take optimal decisions in real-time on the process at hand, leading to increased performance, safety, energy efficiency, and ultimately value creation.
However, to develop this new control systems bottlenecks have to be overcome, the two most critical being: (1) the fact that the computation availability for industrial control systems is locally embedded in each system or subsystem, possibly with limited communication capabilities and distributed topologies; (2) the fact that industrial applications require reliable algorithms, with interpretable and verifiable behavior. Both these bottlenecks are related to safety aspects, which are crucial in applications where a single computation error can cause high economic and environmental cost or even damage to people.
Numerical optimization is at the very core of both learning and decision-making, since both the extraction of information from data and the choice of the most suitable action are naturally cast as optimization problems and solved numerically.
Therefore, the overall objectives of the project are to develop embedded learning- and optimization-based control methodologies for SICS, while training highly qualified and competent researchers.
Visit https://elo-x.eu/ for more information on the ELO-X network.
However, to develop this new control systems bottlenecks have to be overcome, the two most critical being: (1) the fact that the computation availability for industrial control systems is locally embedded in each system or subsystem, possibly with limited communication capabilities and distributed topologies; (2) the fact that industrial applications require reliable algorithms, with interpretable and verifiable behavior. Both these bottlenecks are related to safety aspects, which are crucial in applications where a single computation error can cause high economic and environmental cost or even damage to people.
Numerical optimization is at the very core of both learning and decision-making, since both the extraction of information from data and the choice of the most suitable action are naturally cast as optimization problems and solved numerically.
Therefore, the overall objectives of the project are to develop embedded learning- and optimization-based control methodologies for SICS, while training highly qualified and competent researchers.
Visit https://elo-x.eu/ for more information on the ELO-X network.
The project began in January 2021 with a focus on the setup of the consortium and in particular with recruitment of the early stage researchers (ESR) which was finalized in spring 2022. All 15 ESR candidates were selected before autumn 2021, and an online kick-off event has been organized on November 17, 2021 to present the whole Consortium and the ESR to each other. In the first months, the work of all ESR has been devoted to literature research and studying to reach the state of the art of their respective domain.
During March 2022, the first ELO-X seasonal school and workshop took place in Leuven (Belgium), organized by the academic partner KU Leuven and the industrial partner Siemens. It was the first event in person where all ESR and their supervisors could meet, strengthen the network and share new ideas.
Each ESR has already started to focus and work on particular topics or problems with the aim to find novel solutions. They start already to generate new contributions that are submitted to journals and proceeding of international conferences. The ESR are involved in laboratory activities and discussion groups in their respective host institutions, and some already started their first external research stays in the form of secondments. The ESRs hosted by the industrial partners have gained familiarity with the control systems and experimental setups. In addition to the 15 fully funded PhD students of ELO-X, the consortium decided to add a new status group of “associated PhD fellows”, which are financially decoupled from ELO-X but socially and scientifically fully integrated. Each ESR and his/her host institution of ELO-X can propose at maximum one associated fellow, and so far eight people were selected to join the consortium. A second seasonal school and workshop took place in October 2022, in Freiburg, Germany. In conjunction with this event, the first ELO-X Advisory Board meeting also took place, where the ESRs presented their work and interacted with the members of the Advisory Board.
At https://elo-x.eu/ it is possible to stay updated with the work of the fellows and the events of the network.
During March 2022, the first ELO-X seasonal school and workshop took place in Leuven (Belgium), organized by the academic partner KU Leuven and the industrial partner Siemens. It was the first event in person where all ESR and their supervisors could meet, strengthen the network and share new ideas.
Each ESR has already started to focus and work on particular topics or problems with the aim to find novel solutions. They start already to generate new contributions that are submitted to journals and proceeding of international conferences. The ESR are involved in laboratory activities and discussion groups in their respective host institutions, and some already started their first external research stays in the form of secondments. The ESRs hosted by the industrial partners have gained familiarity with the control systems and experimental setups. In addition to the 15 fully funded PhD students of ELO-X, the consortium decided to add a new status group of “associated PhD fellows”, which are financially decoupled from ELO-X but socially and scientifically fully integrated. Each ESR and his/her host institution of ELO-X can propose at maximum one associated fellow, and so far eight people were selected to join the consortium. A second seasonal school and workshop took place in October 2022, in Freiburg, Germany. In conjunction with this event, the first ELO-X Advisory Board meeting also took place, where the ESRs presented their work and interacted with the members of the Advisory Board.
At https://elo-x.eu/ it is possible to stay updated with the work of the fellows and the events of the network.
The papers published by the ESR have to be considered as progress beyond the state of the art, they are expanding the knowledge and the understanding of learning based control and embedded optimization. The common mission of the ELO-X project is to propose novel theoretical approaches to online learning and embedded optimization, to devise high performance algorithms, and to implement these on embedded systems in order to control prototypical real-world systems at the industrial and academic partners. These proof-of-concept implementations are expected to have a significant impact on industrial practice, by setting the stage for the deployment of the next generation of smart industrial control systems. These systems are expected to improve performance, safety and efficiency of industrial processes, prolong the life of industrial machinery, and to save energy and natural resources.