Adaptive fuzzy control for dynamic process optimisation of precision robotic arms in industrial automation

The growing demand for high-precision, cost-effective manufacturing has pushed the use of robotic arms in industrial automation, particularly for welding, painting, and material handling tasks. Traditional PID and standalone fuzzy controllers often struggle to handle nonlinear dynamics, multi-joint interactions, delayed transient responses, and steady-state errors. To address these limitations, this research provides an adaptive Fuzzy PID control system that incorporates a hybrid Scalable Glow worm Swarm-tuned Elephant Clan Optimisation (SGWS-ECO) method for dynamic parameter optimisation. The fuzzy DC linear servo actuator allows for fine-grained motion control, while SGWS-ECO combines luciferin-based local exploration with clan-based global exploitation to provide rapid convergence and robust performance. MATLAB/Simulink simulations of multi-joint robotic manipulators show significant gains, with a rise time of 0.045 s, maximum overshoot of 0.02%, and steady-state inaccuracy of 0.016. The suggested technology outperforms traditional fuzzy and fuzzy-PSO controllers, providing faster, more precise, and resilient solutions for next-generation smart manufacturing environments.