Lithium-ion battery dataset for data driven models' development

This paper provides a novel dataset derived from lithium batteries' charge-discharge tests performed at laboratory scale. The primary goal is to enhance available data resources for the scientific community in the field of batteries reliability assessment, focusing our research on a thorough examination of lithium battery behavior. The dataset prioritizes the evaluation of critical parameters such as State-Of-Health (SOH), Remaining-Useful-Life (RUL) and State-Of-Charge (SOC), pivotal parameters for optimizing battery performance across various industrial applications allowing the development of data driven approaches such as Artificial Intelligence based techniques Moreover, the authors tried to replicate the phenomenon of the capacity regeneration due to the long relaxation times of the battery. By offering this expanded dataset, compatible with the well-known and well-established NASA and CALCE datasets, our aim is to facilitate deeper insights into battery behavior, thereby promoting advancements in Battery Management Systems (BMS). This work is part of a wider research mainly focused on studying the battery RUL using AI methodologies.