Adaptive Nonlinear PID Control Using Output Recurrent Broad Learning System for Discrete-Time Nonlinear Dynamic Systems

This paper presents a new learning control structure using output recurrent broad learning system (ORBLS) for adaptive nonlinear PID control of unknown digital nonlinear dynamic systems with time delays. The proposed control method, abbreviated as ORBLS-ANPID, is novel in combining ORBLS and model predictive control to develop a new Nonlinear PID control law for high-performance setpoint tracking control and disturbance rejection. Comparative simulations on two renowned nonlinear digital time-delay systems are well used to show the effectiveness and superiority of the proposed method by comparing to six existing methods.