A hybrid evolutionary approach for electric vehicle controller tuning: Integration of WOA, QAA, and RMSProp

• Hybrid WOA integrates BE, QAA, and RMSprop for enhanced EV controller tuning. • Balloon Effect improves adaptation to real-time disturbances and parameter drift. • WOA+QAA+BE offers superior overshoot reduction and convergence speed. • Experimental results validate performance under noise and load variations. • Proposed method outperforms PSO and GA in stability and ISE metrics. This research presents a novel hybrid intelligent control strategy aimed at improving the adaptive position regulation of electric vehicle (EV) motion systems, with an emphasis on real-time accuracy, resilience, and energy-conscious operation. The proposed method combines the Whale Optimization Algorithm (WOA) with two advanced enhancements: RMSProp and the Quantum Approximation Algorithm (QAA), while utilizing the Balloon Effect (BE) as a dynamic feedback mechanism to assess performance. The hybrid control framework is tested on a DC motor-based platform under various conditions, including step responses, parameter fluctuations, external noise disturbances, and multi-level trajectory tracking. Both simulation and experimental outcomes reveal that the WOA+BE+QAA configuration delivers superior performance, achieving reduced overshoot, quicker rise times, and lower steady-state errors compared to other controller variants. In addition, the study assesses the environmental benefit of the proposed control improvements by estimating energy savings and the associated decrease in CO₂ emissions, based on the social cost of carbon methodology. These results underscore the dual advantage of control-level optimization (enhancing system dynamics while supporting eco-friendly transportation initiatives).