Fuzzy logic-based learning system and estimation of state-of-charge of lead-acid battery

The objective of this work is to develop a state-of-charge (SOC) estimation system for the lead-acid battery, which is free from the time-dependent variation of the battery characteristics. In this system, the SOC is estimated by an improved Coulomb metric method, and the time-dependent variation is compensated by using a learning system. The learning system tunes the Coulomb metric method in such a way that the estimation process remains error free from the time-dependent variation. The proposed learning system uses the fuzzy logic, which is not used for estimation of SOC but perform as a component of learning system. The fuzzy logic is used as a soft computing device for a multi-variables function evolution. During learning process the system automatically generates a new fuzzy rule base, and replaces the old fuzzy rule base. Results of the simulations as well as the experiments on an 8-bit microcontroller are also included which indicate the effectiveness of the proposed method.