NNDOB-based composite control for binary distillation column under disturbances

This paper presents a composite disturbance rejection control strategy for high purity binary distillation column with complex characteristics, such as couplings, non-minimum phase, model mismatches and external disturbances. Main goal of the controller is to get the desired top and bottom compositions in presence of both model mismatches and external disturbances. The composite controller includes neural network inverse controller (NNIC) and neural network disturbance observer (NNDOB) both using radial basis function network (RBFN). The inverse model of the system is identified by RBFN, whose stability is proved via the Lyapunov function analysis. And a rigorous analysis is also given to show why the NNDOB can effectively suppress the disturbances. Performance of the proposed scheme is compared with PID and NNIC schemes in two cases. The feasibility, effectiveness and disturbance rejection property of the proposed method are demonstrated by the simulation studies.