Based on the massive static and dynamic data of 137 fractured wells in WY shale gas block in Sichuan, China, this paper carried out the analysis of shale gas fracturing production influencing factors, production prediction model, and fracturing parameter optimization model research. Taking geological, engineering, fracturing operation, and production data of fractured wells in WY block as data set, the main control analysis method is used to construct the shale gas fracturing production influencing factors as the sample set. A production prediction model based on six machine learning (ML) algorithms including random forest (RF), back propagation (BP) neural network, support vector regression (SVR), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and multivariable linear regression (LR) has been established; the evaluation results show that the XGBoost model has the best performance on this sample set. The selection method of shale gas well fracturing operation scheme set is studied; the production rate and the ratio of cost and profit (ROCP) are comprehensively considered to select the final fracturing operation scheme. Research result shows that the data-driven production prediction model and fracturing parameter optimization model can not only be used to predict the production of shale gas fracturing and optimize operation parameters but also realize the sensitivity analysis of fracturing parameters and the effect comparison of fracturing operation schemes, which has good field application value.

Aiming at the popularization and application of a real-time monitoring parameter acquisition system of the electric submersible pump (ESP) well, this paper proposes a fault diagnosis method of ESP well operation based on the SPC rule and prior knowledge fusion. Based on the study of parameter variation rules of ESP well, the SPC expansion rule model is established; by analyzing the variation of some typical characteristic parameters of ESP well, combined with SPC expansion rules and expert experience, a priori knowledge of fault diagnosis of ESP well is formed, that is, multiparameter fault analysis table and weight factor; the SPC extended rule model and prior knowledge are fused to establish the fault probability model of ESP well, form the fault diagnosis method of ESP well, develop the online fault diagnosis software of ESP well, and deploy it in 425 ESP wells in a block. Taking five types of tubing leakage, pump wear, shaft breakage, gas influence, and pump plugging as examples, the application process of fault diagnosis method is analyzed. The research and application show that compared with other fault diagnosis methods, this method needs a smaller time window and higher diagnosis accuracy. By setting multiple time windows, this diagnosis method is applied to calculate the fault probability of ESP well in real time, solve the real time and accurate identification of 14 sudden faults and gradual faults, and significantly improve the intelligent diagnosis level of production faults of ESP well.

Reservoir permeability, generally determined by experimental or well testing methods, is an essential parameter in the oil and gas field development. In this paper, we present a novel analogy and machine learning method to predict reservoir permeability. Firstly, the core test and production data of other 24 blocks (analog blocks) are counted according to the DLG block (target block) of Jing’an Oilfield, and the permeability analogy parameters including porosity, shale content, reservoir thickness, oil saturation, liquid production, and production pressure difference are optimized by Pearson and principal component analysis. Then, the fuzzy matter element method is used to calculate the similarity between the target block and analog blocks. According to the similarity calculation results, reservoir permeability of DLG block is predicted by reservoir engineering method (the relationship between core permeability and porosity of QK-D7 in similar blocks) and machine learning method (random forest, gradient boosting decision tree, light gradient boosting machine, and categorical boosting). By comparing the prediction accuracy of the two methods through the evaluation index determination coefficient (⁠ $R2$⁠) and root mean square error (RMSE), the CatBoost model has higher accuracy in predicting reservoir permeability, with $R2$ of 0.951 and RMSE of 0.139. Finally, the CatBoost model is selected to predict reservoir permeability of 121 oil wells in the DLG block. This work uses simple logging and production data to quickly and accurately predict reservoir permeability without coring and testing. At the same time, the prediction results are well applied to the formulation of DLG block development technology strategy, which provides a new idea for the application of machine learning to predict oilfield parameters.