An adaptive sliding mode controller based on online support vector regression for nonlinear systems

In this paper, a novel adaptive sliding mode controller (SMC) based on support vector regression (SVR) is introduced for nonlinear systems. The closed-loop margin notion introduced for self-tuning regulators is rearranged in order to optimize the parameters of SMC. The proposed adjustment mechanism consists of an online SVR to identify the forward dynamics of the controlled system and SMC parameter estimators realized by separate online SVRs to approximate each tunable controller parameter. The performance of the proposed control architecture has been evaluated by simulations performed on a nonlinear continuously stirred tank reactor system, and the obtained results indicate that the SMC based on SVR provides robust and stable closed-loop performance.