Descrizione del progetto
Un nuovo modello per batterie migliori per veicoli elettrici
I veicoli elettrici sono il futuro. Cosa riserva il domani per le loro batterie? Per renderle meno complesse e più facili da ricaricare è importante migliorare il sistema di gestione (BMS, Battery Management System) che monitora, controlla e protegge i pacchi di batterie agli ioni di litio. Dal momento che le batterie per veicoli elettrici sono soggette a cicli operativi intensi e a condizioni ambientali variabili, che originano interazioni molto complesse, il progetto DeepBMS, finanziato dall’UE, svilupperà un nuovo modello per migliorare la funzionalità del loro sistema di gestione. Attraverso algoritmi efficienti basati sull’apprendimento di rinforzo profondo, verrà registrato il complesso comportamento variabile nel tempo che contraddistingue le batterie. Grazie alla fornitura di stime più precise in un intervallo di temperatura ampio e per l’intera durata del ciclo di vita delle batterie, DeepBMS le renderà anche più affidabili e durevoli.
Obiettivo
Battery Management System (BMS) plays a pivotal role in monitoring, control, and protecting the Electric Vehicle (EV) Lithium-ion battery packs. In vehicular applications, batteries are usually subjected to harsh operating cycles and varying environmental conditions leading to very complicated interactions of different aging factors and unforeseeable modeling uncertainties. Therefore, the classical model-based techniques cannot completely handle the foregoing factors, which always leave an unwanted state estimation error in the BMS. This project intends to apply a multidisciplinary approach by combining the advantages of deep reinforcement learning and classical model-based techniques to improve the BMS functionality in EVs. Specifically, DeepBMS aims to: 1-Develop efficient deep reinforcement learning-based algorithms which are able to capture the convoluted time-varying behavior of battery and can gradually improve themselves by learning in real-time 2- Combine the beneficial features of model-based and data-driven techniques to improve the state estimation accuracy in a wide temperature range and over the full life span of the batteries, thereby increasing the reliability and extending the battery lifetime. The interdisciplinary nature of DeepBMS is very strong, involving a combination of control and state estimation theory, power electronics, battery storage systems, and machine learning. The supervisor and candidate have excellent complemental research experiences in these fields providing the necessary competencies to bring the project to successful completion. The project ensures two-way transfer of knowledge including training of the candidate in cutting-edge advanced techniques in a state-of-the-art laboratory, which improves his future career prospects. Likewise, DeepBMS is in line with the EU strategic action plan on batteries and its results have a great potential to be further developed at the fundamental and applied levels through follow-up research.
Campo scientifico
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectrical engineeringelectric energy
- natural scienceschemical scienceselectrochemistryelectric batteries
- social sciencessocial geographytransportelectric vehicles
- natural sciencescomputer and information sciencesartificial intelligencemachine learningreinforcement learning
Programma(i)
- HORIZON.1.2 - Marie Skłodowska-Curie Actions (MSCA) Main Programme
Meccanismo di finanziamento
HORIZON-AG-UN - HORIZON Unit GrantCoordinatore
9220 Aalborg
Danimarca