Adaptive Predictive PID Control Using Recurrent Fuzzy Broad Learning System for Accurate Setpoint Tracking of Digital Nonlinear Time-Delay Dynamic Systems

Abstract

This paper presents a novel adaptive predictive proportional-integral-derivative (PID) control using a new recurrent fuzzy broad learning system (RFBLS) for setpoint tracking control and disturbance rejection of a class of nonlinear discrete-time dynamic systems with time delay. The proposed controller, abbreviated as RFBLS-APPID, is formed from an online RFBLS identifier for online parameter tuning and identification, and an adaptive predictive RFBLS-PID control for accurate setpoint tracking and disturbance rejection. The three-term PID controller gain parameters are automatically tuned by the RFBLS identifier. The setpoint tracking of the proposed RFBLS-APPID control method is well exemplified by conducting simulations employing two well-known nonlinear digital discrete-time time-delay dynamic systems, thus showing its effectiveness and superiority.