As the demand for electric automobiles continues to rise, more advanced hybrid energy storage systems will be required to meet peak power demands while preserving battery life. Investigations on the effects of battery degradation provide helpful direction for improving energy management in hybrid systems using both batteries and ultracapacitors. An artificial neural network-based controller dynamically manages the power transfer between the battery and ultracapacitor based on signals related to age, state-of-charge, and load need. The architecture of ultracapacitors allows them to withstand high-frequency power fluctuations, which reduces pressure on the battery current and depth-ofdischarge variations. Capability fading may be accurately predicted using an ageing model that accounts for degradation and incorporates several Crate profiles obtained from driving cycles. This energy management system outperforms conventional ones in terms of efficiency, battery current ripple, and runtime under real-world EV driving conditions, according to the simulation results. Consequently, it is more suited for use in real-time electric vehicle applications.
Keywords : Power quality, electric vehicle management systems (EMS), driving cycles, power distribution, capacity fading, energy efficiency, artificial neural networks (ANN), hybrid energy storage systems (HESS), and electric cars (EVs).
Author : Dr. K. Srinivas1 , Gajjagouni Madhav Goud2
Title : ARTIFICIAL NEURAL NETWORK-BASED ENERGY MANAGEMENT FOR BATTERY–ULTRACAPACITOR HYBRID ENERGY STORAGE SYSTEM CONSIDERING BATTERY DEGRADATION IN ELECTRIC VEHICLES
Volume/Issue : 2026;03(08)
Page No : 7-19