Research on Prediction Model of Contamination Viscosity Based on the BP Neural Network
The prediction model of contamination viscosity is set up respectively to three different contaminations based on analysis of the basic principle of forward back propagation (BP) neural network. The structure of model is 1-7-1 three-layer BP network. The non-linear relationship between contamination viscosity and contamination concentration was gotten continuously. The distribution in the network connect right was stored and the contamination concentration and the contamination viscosity was recorded finally in the form of the objective function of the complex non-linear relationship knowledge to connect the matrix. The mapping from input to output patterns of arbitrary non-linear model was established. The results show that the error ratios of three different contaminations are all less than 2.5％. It also indicates that the present method has higher accuracy and wider applicability than Kerndal-Munnloe formula and Zdanowski formula proposed by Pre-Soviet scholar and it can well meet the needs of engineering.
pipeline BP neural network contamination viscosity forecasting model
Zhao Huijun Zhang Guozhong Zhang Qingsong Wang Shuli Zhou Shidong
China University of Petroleum East China, Dongying 257061, China;Jiangsu Polytechnic University, Cha China University of Petroleum East China, Dongying 257061, China Jiangsu Polytechnic University, Changzhou, 213016, China
国际会议
北京
英文
2007-08-05（万方平台首次上网日期，不代表论文的发表时间）