Executive Summary : | The greenhouse effect can be controlled by renewable energy resources and Lithium-Ion batteries (LIBs) are the most prominent devices of scientific achievement to tackle energy supply and storage challenges, specifically for Electric Vehicles (EVs). In particular, the long-run and long-life cycle performance of EV batteries are essential for today's transportation. To achieve these, an efficient battery management system (BMS) is essential; which completely relays on the state-of-charge (SoC) and state-of-health (SoH) estimation. Many SoC and SoH techniques are available; howbeit more efficient, accurate and reliable SoC and SoH models will be developed using the electrical equivalent circuit model (EECM) governed by a new state-space mathematical model (SSMM) for LIBs with the hybrid AI/ML/DL in this project. The state-space mathematical model includes integer and fractional-order dynamical systems, neural networks, and memristor neural networks. The newly developed model is then analyzed and optimized using the Lyapunov stability theory and Linear Matrix Inequality (LMI) technique. The novel battery will be designed based on the proposed EECM governed SSMM, then it will be tested using SEMCO BMS testing equipment with various battery parameter conditions. The acquired data from the data acquisition device will then be used to train the AI/ML/DL for the battery parameter optimization. The optimized battery design will meet the challenges in the day-to-day lives of EVs, and the same can be commercialized and patented. |