An Advanced Energy Consumption Predictive Method for Artificial Intelligence-Based Hybrid Electric Vehicle to Improve Vehicle Battery Efficiency for Sustainable Development

In recent decades, Hybrid Electric Vehicle (HEV) battery management is a vital role in the world. So, improving the battery economy and its environmental implications have been key social goals. To enhance system performance for battery vehicle efficiency, an HEV was proposed for use in the Artificial Intelligence Predictive Method (AIPM). In this method, the HEV predicts reduced carbon emissions with the help of Machine Learning Techniques (MLT). The novelty of the proposed method is to improve the State of Charge (SoC) charging/discharging time interval between the full cycles. The internal combustion engine is described accordingly; one of the primary elements of the combustion engine is incorporated with electric motors by translating the battery power into the proposed HEV. This HEV equivalent battery minimizes the total battery consumption using the proposed algorithm. To boost the battery effectiveness, an AIPM-based Hybrid Particle Swarm Optimization–Equivalent Consumption Minimization Strategy (HPSO–ECMS) system controller was described with an advanced Indian Driving Cycle (IDC) driving cycle system. The proposed system should concentrate on mechanical design, combustion engine power and utilization power. These factors are assessed, and the finding results are reported. The electrical design includes the controller and electrical subsystem to improve battery economy with combined battery management. The main objective of this paper is AIPM mechanism-based HPSO to predict automobile battery/fuel Compressed Natural Gas (CNG) consumption (g/s) — 250 with 1200 driving cycles. This method is known as ECMS, where the minimized internal vehicle displacement is 240[Formula: see text]km, speed (km/h) 100–120 and acceleration 0.3[Formula: see text]m/s 2 .