Analytical Study of Dominating Features of Intelligent Controller over Conventional Controller
Ankita Maheshwari, Vishal Goyal, A. K. Agrawal · 2025
The escalating demand for sophisticated control systems in diverse industries necessitates highly efficient controllers capable of precise trajectory tracking while robustly rejecting environmental disturbances and uncertainties. In response to this, our study aims to develop adaptive controllers using artificial intelligence and machine learning techniques. We focus on combatting external factors and non-linear effects, recognizing that controller efficacy is determined mainly by optimal parameter tuning. To this end, we explore and compare various evolutionary and swarm intelligence-based optimization algorithms to enhance overall system performance. Our comprehensive study introduces four controllers, including those based on conventional PID-type and intelligent fuzzy-neural techniques. We utilize the well-established Genetic Algorithm and a novel metaheuristic approach, Spider Monkey Optimization (SMO), which is a unique contribution to our research. Through extensive numerical simulations and comparative analysis, we rigorously evaluate the performance of these controllers across multiple criteria including settling time, overshoot, and steady-state error. Our results demonstrate that the SMO-based intelligent controller consistently outperforms its counterparts in all assessed performance metrics. This superior behaviour not only highlights the potential of combining advanced bio-inspired optimization techniques with intelligent control strategies, but also underscores the practical benefits of our research. The SMO-based controller is particularly effective in addressing complex, multi-objective control challenges in dynamic environments, offering a promising solution for real-world applications.