Periodic Reporting for period 1 - ENERGETIC (NEXT GENERATION BATTERY MANAGEMENT SYSTEM BASED ON DATA RICH DIGITAL TWIN)
Reporting period: 2023-06-01 to 2024-11-30
Current battery management systems (BMS) typically rely on semi-empirical battery models (such as equivalent-circuit models) and on a limited amount of measured data. In fact, a battery’s first life lasts between 10-15 years and is likely to retain more than two-thirds of its usable energy storage. Depending on their condition, used EV batteries can be repurposed for up to additional years in “second-life cases” such as stationary energy storage, also known as the battery’s “second life”.
Therefore, ENERGETIC project aims to develop the next generation BMS for optimizing batteries’ systems utilisation in the first (transport) and the second life (stationary) in a path towards more reliable, powerful and safer operations.
The on-board BMS cannot store or process large amounts of data during the operation of a vehicle, with poor real-time capability and data utilization rate. For efficient battery management, it is necessary to in-depth study mechanisms, such as battery ageing and thermal runaway. ENERGETIC project contributes to the field of translational enhanced sensing technologies, exploiting multiple Artificial Intelligence models, supported by Edge and Cloud computing. ENERGETIC’s vision not only encompasses monitoring and prognosis the remaining useful life of a Li-ion battery with a digital twin, but also encompasses diagnosis by scrutinising the reasons for degradation through investigating the explainable AI models. This involves development of new technologies of sensing, combination and validation of multiphysics and data driven models, information fusion through Artificial Intelligence, Real time testing and smart Digital Twin development. There are huge challenges in the research of accurate state estimation including smart charging, fast charging, thermal management, and extending useful life.
Based on a solid and interdisciplinary consortium of partners, the ENERGETIC R&D project develops innovative physics and data-based approaches both at the software and hardware levels to ensure an optimised and safe utilisation of the battery system during all modes of operation.
Therefore, ENERGETIC project aims to develop the next generation BMS for optimizing batteries’ systems utilisation in the first (transport) and the second life (stationary) in a path towards more reliable, powerful and safer operations.
The on-board BMS cannot store or process large amounts of data during the operation of a vehicle, with poor real-time capability and data utilization rate. For efficient battery management, it is necessary to in-depth study mechanisms, such as battery ageing and thermal runaway. ENERGETIC project contributes to the field of translational enhanced sensing technologies, exploiting multiple Artificial Intelligence models, supported by Edge and Cloud computing. ENERGETIC’s vision not only encompasses monitoring and prognosis the remaining useful life of a Li-ion battery with a digital twin, but also encompasses diagnosis by scrutinising the reasons for degradation through investigating the explainable AI models. This involves development of new technologies of sensing, combination and validation of multiphysics and data driven models, information fusion through Artificial Intelligence, Real time testing and smart Digital Twin development. There are huge challenges in the research of accurate state estimation including smart charging, fast charging, thermal management, and extending useful life.
Based on a solid and interdisciplinary consortium of partners, the ENERGETIC R&D project develops innovative physics and data-based approaches both at the software and hardware levels to ensure an optimised and safe utilisation of the battery system during all modes of operation.
The ENERGETIC project, now at its halfway mark, is driving transformative advancements in battery management technology to enhance the safety, efficiency, and longevity of lithium-ion batteries. By integrating low-cost sensors, advanced modeling, artificial intelligence (AI), and cloud-connected digital twins, the project is pioneering a predictive, intelligent approach to battery monitoring and maintenance.
Key Innovations and Progress:
Central to the project’s success are novel, cost-effective sensors that provide real-time insights into battery health. Ultrasonic sensors, validated on commercial cells, enable precise tracking of aging and performance metrics like State of Charge (SoC) and State of Health (SoH). Flexible distributed temperature sensors offer detailed thermal mapping to prevent overheating, while AI-driven thermal imaging systems detect anomalies with minimal computational effort. These sensors are unified through a scalable hardware platform based on ESP32 microcontrollers, ensuring seamless integration with existing Battery Management Systems (BMS).
To process this data, a robust Hardware Abstraction Layer (HAL) standardizes and synchronizes sensor inputs, enabling real-time communication with cloud platforms. Advanced multiphysics models simulate electrical, thermal, and chemical behaviors, while AI frameworks—including Transformer-based algorithms and hybrid LSTM architectures—achieve exceptional accuracy in predicting battery lifespan (errors below 1.5%) and detecting faults. A cloud-connected Digital Twin (DT), validated in virtual environments mirroring real-world conditions, integrates predictive maintenance tools powered by Google Cloud’s scalable infrastructure.
Current Focus and Future Goals:
With 20 months remaining, the team is refining prototypes for real-world reliability. Lab-tested ultrasonic and thermal sensors will undergo rigorous field trials under extreme conditions (temperature fluctuations, vibrations) to ensure robustness. AI algorithms, already demonstrating over 98% accuracy in predicting battery wear, are being optimized for diverse applications, from electric vehicles to renewable energy storage. A critical challenge remains the seamless integration of these technologies into a unified, cloud-based platform. Collaborative testing with industry partners, including Forsee Power and EDF, will validate system performance by late 2025.
Ultimately, ENERGETIC aims to extend battery lifespans through predictive maintenance, reducing waste and supporting the global energy transition. By bridging cutting-edge sensor technology, AI, and digital innovation, the project empowers a sustainable future where batteries operate smarter, last longer, and reliably power an electrified world.
Key Innovations and Progress:
Central to the project’s success are novel, cost-effective sensors that provide real-time insights into battery health. Ultrasonic sensors, validated on commercial cells, enable precise tracking of aging and performance metrics like State of Charge (SoC) and State of Health (SoH). Flexible distributed temperature sensors offer detailed thermal mapping to prevent overheating, while AI-driven thermal imaging systems detect anomalies with minimal computational effort. These sensors are unified through a scalable hardware platform based on ESP32 microcontrollers, ensuring seamless integration with existing Battery Management Systems (BMS).
To process this data, a robust Hardware Abstraction Layer (HAL) standardizes and synchronizes sensor inputs, enabling real-time communication with cloud platforms. Advanced multiphysics models simulate electrical, thermal, and chemical behaviors, while AI frameworks—including Transformer-based algorithms and hybrid LSTM architectures—achieve exceptional accuracy in predicting battery lifespan (errors below 1.5%) and detecting faults. A cloud-connected Digital Twin (DT), validated in virtual environments mirroring real-world conditions, integrates predictive maintenance tools powered by Google Cloud’s scalable infrastructure.
Current Focus and Future Goals:
With 20 months remaining, the team is refining prototypes for real-world reliability. Lab-tested ultrasonic and thermal sensors will undergo rigorous field trials under extreme conditions (temperature fluctuations, vibrations) to ensure robustness. AI algorithms, already demonstrating over 98% accuracy in predicting battery wear, are being optimized for diverse applications, from electric vehicles to renewable energy storage. A critical challenge remains the seamless integration of these technologies into a unified, cloud-based platform. Collaborative testing with industry partners, including Forsee Power and EDF, will validate system performance by late 2025.
Ultimately, ENERGETIC aims to extend battery lifespans through predictive maintenance, reducing waste and supporting the global energy transition. By bridging cutting-edge sensor technology, AI, and digital innovation, the project empowers a sustainable future where batteries operate smarter, last longer, and reliably power an electrified world.
The tests were carried out on a variety of battery types, not just the one used at the start of the project, enabling a wider range of results to be obtained.”