IKERLAN’s Role in Advancing Battery Management Systems in BIG LEAP

IKERLAN is a key contributor to the BIG LEAP project, utilizing its expertise in energy storage technology to advance the development of battery management systems (BMS). The Energy Storage Research Centre at IKERLAN specializes in designing hardware units, testing and modeling lithium-ion batteries, and developing state-of-charge (SoC) and state-of-energy (SoE) algorithms using deep learning techniques. Learn more about their contributions here:

What is IKERLAN’s main contribution for the BIG LEAP project?  IKERLAN’s main contribution to BIG LEAP is divided into the following two key project research lines: – On the one hand, IKERLAN will lead the development of the battery algorithms required for the BMS interoperability. Indeed, providing battery SoX (State-of-X), RUL (Remaining Useful Lifetime) and self-diagnosis algorithms that can be easily adapted between 1st and 2nd life applications and between different battery chemistries is one of the core objectives of the project, as it will facilitate the interoperability of the BMS software layer. Besides leading and managing this task, IKERLAN will also develop the SOC, SOE and 1st life RUL algorithms. – On the other hand, IKERLAN will also contribute to the development of the BMS hardware. Specifically, IKERLAN will provide the master units of the low-level BMS layer, which will allow the interoperability aimed at BIG LEAP project. 

How will WP3 ensure effective BMS interoperability and adaptability through the development of SoX algorithms and self-diagnosis estimators?

As I mentioned before, IKERLAN leads WP3 of BIG LEAP project, which focuses on the development of SoX, RUL and self-diagnosis algorithms. Typically, these algorithms are developed and tunned ad-hoc for specific batteries, but lack of transversality to be used with different batteries, even if they share the same chemistry. Developing 100% transversal algorithms is not a feasible option, and therefore BIG LEAP project will provide a framework for the easy adaptation of algorithms between 1st life and 2nd life, or between different chemistries. The development of approaches based on transfer learning or other methodologies will allow this easy adaptation and interoperability. 3. How will the balance between low-level and cloud-based processing impact the system’s performance? Answer: To properly understand the importance of the balance between low-level and cloud-based processing, it is necessary first to understand the computational limitations of the low-level components. The low-level layer of the BMS cannot process large amount of data or execute very complex algorithms, and therefore, advanced approaches such as machine learning-based algorithms cannot be deployed locally. In order to overcome this issue, BIG LEAP project will enhance the computational capacity of the BMS by addressing data processing, data storage and algorithm execution also in the cloud. This allows balancing and dividing the computation effort between the low-level and the cloud-based layers, allocating the time-critical operations (such as cell balancing, state of charge computation, etc…) in the low-level layer, and the remainder operations in the cloud layer. Besides, the cloud layer allows also a centralized framework, in which data from different batteries is compilated together and allows its use in the fine-tunning of different SoX, RUL and self-diagnosis algorithms.