Support Vector Machine Applying in the Prediction of Effluent Quality of Sewage Treatment Plant with Cyclic Activated Sludge System Process

Sewage treatment system is a complicated nonlinear system with multi-variables, chemical reaction, biological process and altered loads, hard to describe mathematically. Thus prediction of the effluent quality of sewage treatment plant through a mathematical model has being a challenge. In this paper we adopts regression support vector machine (SVM) to set up a prediction model of a sewage treatment plant with a popular process cyclic activated sludge system (CASS). Kernel function of the prediction model is radial basic function, and parameters of the kernel function are optimally determined by cross-validation. Then the prediction model is used to predict effluent quality of the sewage treatment plant with CASS process. Test result of the case study shows that the prediction model works well and the regression SVM is powerful in predicting effluent quality of CASS process sewage treatment plant with small sample learning ability and good generalization.