Design and application of data-driven LESN-DHP controller

Wastewater treatment processes (WWTP) involve a large number of physical, chemical and biological reactions. The concentration of Dissolved oxygen (DO) is an important water quality parameter in WWTP, so it is necessary to control it. To solve this difficult problem, a dual heuristic programming (DHP) controller based on leakage Echo State Network (LESN) is proposed, which is called LESN-DHP controller for short. Firstly, a neural network (NN) identifier based on LESN (LESN-Identifier) is designed to obtain the dynamic characteristics of the system. Then the stability analysis and convergence analysis are carried out. Finally, the feasibility of LESN-DHP controller is verified by simulation experiment. The simulation experiment proves that LESN-DHP controller has better control effect and better performance index than other controllers in WWTP.

I. Introduction

Due to the shortage of water resources and the increase in industrial consumption, the WWTP has become a social issue of concern. Meanwhile, the discharge standards of effluent water quality for WWTP in China are becoming increasingly strict. The concentration of DO is an important indicator. It is the focus of research on how to achieve better results with less consumption [1]–[3].