A case study on the MPC for ozone dosing process based on SVM

Ozone is an important disinfectant in drinking water treatment. The ideal ozone dosage should be a good trade-off between the requirement of disinfection and the restriction of bromate formation. Additionally, the ozone dosing process should cope with the changes of raw water quality and maintain the treated water stable. However, ozone dosing process is very difficult to be controlled because of its complicated nonlinear behaviour. In this paper, model predictive control (MPC) scheme based on support vector machine (SVM) model is designed for the ozone dosing process. With the proposed control scheme, a SVM model is established which could be used for MPC. The control strategy of maintaining a constant ozone exposure is attempted for the requirement of more effective disinfection. The plant-scale experimental studies demonstrate the efficiency and effectiveness of proposed control scheme.