An evaluation model of water quality based on Learning Vector Quantization neural network

Abstract

Real time evaluation of rivers water quality has great significance for maintenances and protection of water resources. In the case of Huaihe River, we took advantages of LVQ (Learning Vector Quantization, LVQ) to classify the water qualities. Comparing with BP neural network and RBF neural network. LVQ neural network has the advantages of simple structure, self-learning, self-organization, and nonlinear classification processing capacity. The accuracy rate of water quality classification in Xuyi Huaihe River Bridge monitoring section and Zhoukou Shenqiu monitoring section could reach 88%, and it is as high as 92% in Fuyang Zhang Bridge monitoring section. The testing result shows that the suggested method has shorter convergence time, stronger practicability and higher generalization performance. It can effectively fulfill water quality assessment with high precision.