Type-2 fuzzy broad learning controller for wastewater treatment process

Abstract

Affected by multiple operation conditions, wastewater treatment process (WWTP) is a complex industrial process with strong nonlinearity and disturbance. How to enhance the rapid tracking response-ability and robustness of the controller is still a challenge when the operation conditions change. To solve this problem, a type-2 fuzzy broad learning controller (T2FBLC) is proposed in this paper. First, a type-2 fuzzy broad learning system (T2FBLS) is constructed in T2FBLC by replacing nodes in feature window with a group of interval type-2 fuzzy submodules. Then, the proposed T2FBLC can take tracking error as inputs while its outputs acting on WWTP to directly obtain a control law, and the controller makes a quick tracking response in different operation conditions. Second, the weight parameters of T2FBLC are adjusted by using the gradient descent method to ensure the control performance. In this way, the developed T2FBLC can realize online learning to reduce tracking errors. Third, according to the Lyapunov function theory, the stability of control strategy is proved. Finally, benchmark simulation model 1 (BSM1) is adopted to verify the effectiveness of T2FBLC. The experimental results prove the applicability and superior tracking performance of the proposed method.