Neuro-adaptive fast terminal sliding mode control of the continuous polymerization reactor in the presence of unknown disturbances

Abstract

This paper presents the design of fast terminal sliding mode control based on feed forward neural network (FTSMC $$+$$ NN) for a polymerization reactor in the presence of unknown disturbances. The FTSMC+NN offers robust trajectory tracking of the monomer concentration and the reactor temperature. The NN is employed to approximate the unknown complex dynamics and the external disturbances. Additionally, in order to avoid the chattering phenomenon, a continuous reaching law together with an adaptive gain estimator is adopted. The proposed controller showcases superior performances compared to the SMC and proportional-integral-derivative (PID) controller.