Productivity prediction method and system for perforated well based on machine learning

The invention provides a productivity prediction method and system for a perforated well based on machine learning. The method comprises the following steps: obtaining perforation well productivity influence parameter data; preprocessing the perforation well productivity influence parameter data; inputting the preprocessed perforation well productivity influence parameter data into the trained radial basis function network, and outputting a perforation well productivity prediction result. According to the method, a machine learning and neural network model is adopted, the method is applied to data prediction of the productivity of the perforation well, the prediction accuracy is high, the response is rapid, and the working efficiency of an enterprise is improved. Different from an existing perforation well productivity prediction method, the method does not need a large amount of calculation, and the efficiency of perforation well productivity prediction is greatly improved. 本公开提出了基于机器学习的射孔井产能预测方法及系统，包括如下步骤：获