UAV DC Motor behaviors control using new hybrid PSO-fuzzy logic with a dynamic error based optimization

This study introduces a novel and comprehensive control architecture for DC motor speed regulation in unmanned aerial vehicles (UAVs), leveraging a hybrid Particle Swarm Optimization-Fuzzy Logic (PSO-FL) strategy. UAV platforms inherently exhibit highly nonlinear, time-varying, and uncertain dynamics, which often challenge the efficacy of traditional control techniques such as Proportional-Integral-Derivative (PID) controllers and conventional fuzzy logic systems. To overcome these limitations, a dual-layer PSO-FL controller is proposed, wherein the PSO algorithm is utilized to optimize both fuzzification and defuzzification parameters, thereby enhancing controller adaptability and precision. Moreover, a Centralized Agent Optimization (CAO) framework is integrated to accelerate convergence and improve overall computational efficiency. The proposed controller dynamically adjusts membership functions and rule weights in real time, enabling robust, stable, and rapid system responses even under sudden aerodynamic perturbations and variable payload conditions. Extensive simulation and experimental validations confirm the superior performance of the proposed method over classical PID, PSO-tuned PID, and conventional fuzzy logic controllers, demonstrating faster rise times, reduced overshoot, and minimized steady-state error. These findings significantly advance the development of intelligent UAV control systems by effectively combining swarm intelligence with human-like reasoning methodologies.