Wastewater neutralisation control using a neural network based model predictive controller

The purpose of neutralization is to adjust the pH value to meet the requirements of the different processing units in the wastewater treatment system. However, there are many control problems in the industrial wastewater neutralization because of the nonlinearity of the titration curve, variable buffering, and changes in loading. In order to solve these problems, many authors have proposed different solutions. One of the alternative control schemes for the pH control of chemical process is the use of model predictive control (MPC). A neural network based MPC (NNMPC) is developed in this paper. In order to study the effectiveness of NNMPC, a simulation of wastewater neutralisation process was chosen as a test case.