Prediction of gas well productivity in eastern South China Sea based on GA-BP neural network
Considering the high proportion of subsea wellhead gas wells in the eastern South China Sea,as well as the high cost,difficulty,and low accuracy of gas productivity testing,this paper establishes a productivity prediction model using BP neural network method opti-mized by genetic algorithm(GA)based on actual data of 33 gas wells in the eastern South China Sea,and the prediction results are compared with that of BP neural network model and measured data.The research results show that the average relative error of the BP neural network model for gas well productivity prediction is 36.8%,and the average relative error of the GA-BP neural network model is 4.7%.The predicted values of GA-BP neural network model are closer to the actual test values,and the relative error of prediction is smaller,pro-viding an efficient and feasible method for predicting the productivity of gas wells in the eastern South China Sea.The research results have guiding significance for gas well produc-tion allocation and management.
offshore gas wellproductivity predictiongenetic algorithmneural network
NETL
NSTL
万方数据
