Application of the dynamic self-adaptive nearest neighbor clustering algorithm in an industrial waste water treatment system

In order to establish a positive model of pH value control, the process with severe non-linearity and serious lag of neutralization action was studied by adding medicine in an industrial waster water neutralization control system. A novel kind of Dynamic Adaptive Nearest Neighbor Clustering (DANNC) algorithm was adopted, and a strategy by adjusting the parameter in the entire neural network to finish the task of learning and training of the neural network (NN) was applied. The NN internal model control system for pH value of neutralization, which serves as a controller of the converse model was designed, and different kinds of simulation experiments were carried. The results showed that the accuracy of the pH control system is △pH≤0.2, which satisfied the requirement of the real time adding medicine track and anti-jamming abilities in industrial application.