Intelligent Industrial Setpoint Tracking Control Using Output Recurrent Elliptic Fuzzy Broad Learning System

ABSTRACT

This paper proposes an intelligent industrial setpoint tracking control approach using an output recurrent elliptic fuzzy broad learning system (Elliptic ORFBLS). This approach integrates the strengths of intelligent control, which effectively manages complex nonlinear systems with an adaptive identification mechanism that efficiently handles uncertain parameters in unknown systems. The adaptive mechanism notably enhances transient state responses, leading to faster rise times and reduced overshoot, while ensuring stable and precise setpoint tracking in the steady state. Three theorems are presented to guarantee system convergence, stability, and applicability. Additionally, a comprehensive study on time complexity and memory consumption is included to assist practitioners in controller selection. Through comparative simulations and experimental validations, this control strategy is shown to offer a robust and effective solution for challenging nonlinear systems.