Development of a High-Performance Regenerative Shock Absorber Utilizing Helical Gears for Efficient Energy Harvesting and Range Extension in Electric Vehicles

Electric vehicles rely on efficient energy management to extend driving range, and regenerative shock absorbers using helical gears can capture kinetic energy from suspension motion. Key challenges include mechanical complexity, vibration damping, and maximizing energy conversion without compromising ride comfort. This manuscript proposes a combined approach for an efficient regenerative absorber related to a twin helical-gear for range-extended electric vehicles (EVs). The proposed absorber converts suspension vibrations from road roughness into electricity using a suspension input module, helical gears, one-way clutches, and a generator module. The proposed approach combines the techniques of the Electric Eel Foraging Optimization (EEFO) Method and Generative Pre-Trained Physics-Informed Neural Networks (GPT-PINNs). Hence, it is called the EEFO-GPT-PINNs technique. The EEFO is utilized to optimize the motor driving system’s power consumption, while the GPT-PINNs method is utilized to forecast the EV Range based on current driving conditions. To increase the efficiency of energy transfer, the adaptive EEFO-GPT-PINNs optimize the one-way clutches and helical gears. The objective of this work is to develop the efficiency and power of the system. The proposed strategy is implemented and analyzed using MATLAB and its performance is compared with existing methods, including Proximal Policy Optimization (PPO), Multi-Objective Optimization (MOO), and Genetic Algorithm (GA) techniques. The proposed approach achieves significant improvements, yielding 21% higher energy harvesting at a damping ratio of 0.1 m/s, 46% mechanical efficiency at 6 Hz, and 94% recoverable power effectiveness at 3 Hz, thereby outperforming existing methods and validating its potential for enhanced power and efficiency optimization.