In petroleum engineering,real-time lithology identification is very important for reservoir evaluation,drilling decisions and petroleum geological exploration.A lithology identification method while drilling based on ...In petroleum engineering,real-time lithology identification is very important for reservoir evaluation,drilling decisions and petroleum geological exploration.A lithology identification method while drilling based on machine learning and mud logging data is studied in this paper.This method can effectively utilize downhole parameters collected in real-time during drilling,to identify lithology in real-time and provide a reference for optimization of drilling parameters.Given the imbalance of lithology samples,the synthetic minority over-sampling technique(SMOTE)and Tomek link were used to balance the sample number of five lithologies.Meanwhile,this paper introduces Tent map,random opposition-based learning and dynamic perceived probability to the original crow search algorithm(CSA),and establishes an improved crow search algorithm(ICSA).In this paper,ICSA is used to optimize the hyperparameter combination of random forest(RF),extremely random trees(ET),extreme gradient boosting(XGB),and light gradient boosting machine(LGBM)models.In addition,this study combines the recognition advantages of the four models.The accuracy of lithology identification by the weighted average probability model reaches 0.877.The study of this paper realizes high-precision real-time lithology identification method,which can provide lithology reference for the drilling process.展开更多
Located in the middle of the Tarim Basin, Tazhong is a typical area of compound reservoirs rich in oil and gas found in the Carboniferous, Silurian and Ordovician strata. The proved, probable and possible reserves （3...Located in the middle of the Tarim Basin, Tazhong is a typical area of compound reservoirs rich in oil and gas found in the Carboniferous, Silurian and Ordovician strata. The proved, probable and possible reserves （3P reserves） in the area amount to 5×108 tons, so it is of great significance to study the advances and problems in hydrocarbon exploration in the Tazhong area. On the basis of exploration history and analysis of scientific problems, we outline eight achievements： distribution characteristics of reservoirs, stages of reservoir formation, different sources of oil and gas and their respective contributions, the effective regional caprock and reservoir-caprock combinations dominating the vertical distribution of hydrocarbon reservoirs, the control of the Tazhong Palaeo-uplift on reservoir formation and establishing geologic models, structure balance belts influencing the reconstruction and residual potential of reservoirs after accumulation, the rules and mechanisms of fractures controlling oil and gas, and the types of favorable reservoirs and their characteristics of controlling oil and gas distribution. We further point out the main problems about the oil and gas exploration in the Tazhong area and put forward some relevant proposals.展开更多
基金supported by CNPC-CZU Innovation Alliancesupported by the Program of Polar Drilling Environmental Protection and Waste Treatment Technology (2022YFC2806403)。
文摘In petroleum engineering,real-time lithology identification is very important for reservoir evaluation,drilling decisions and petroleum geological exploration.A lithology identification method while drilling based on machine learning and mud logging data is studied in this paper.This method can effectively utilize downhole parameters collected in real-time during drilling,to identify lithology in real-time and provide a reference for optimization of drilling parameters.Given the imbalance of lithology samples,the synthetic minority over-sampling technique(SMOTE)and Tomek link were used to balance the sample number of five lithologies.Meanwhile,this paper introduces Tent map,random opposition-based learning and dynamic perceived probability to the original crow search algorithm(CSA),and establishes an improved crow search algorithm(ICSA).In this paper,ICSA is used to optimize the hyperparameter combination of random forest(RF),extremely random trees(ET),extreme gradient boosting(XGB),and light gradient boosting machine(LGBM)models.In addition,this study combines the recognition advantages of the four models.The accuracy of lithology identification by the weighted average probability model reaches 0.877.The study of this paper realizes high-precision real-time lithology identification method,which can provide lithology reference for the drilling process.
基金supported by the National Basic Research Program of China (973 Program, Grant No. 2006CB202308)
文摘Located in the middle of the Tarim Basin, Tazhong is a typical area of compound reservoirs rich in oil and gas found in the Carboniferous, Silurian and Ordovician strata. The proved, probable and possible reserves （3P reserves） in the area amount to 5×108 tons, so it is of great significance to study the advances and problems in hydrocarbon exploration in the Tazhong area. On the basis of exploration history and analysis of scientific problems, we outline eight achievements： distribution characteristics of reservoirs, stages of reservoir formation, different sources of oil and gas and their respective contributions, the effective regional caprock and reservoir-caprock combinations dominating the vertical distribution of hydrocarbon reservoirs, the control of the Tazhong Palaeo-uplift on reservoir formation and establishing geologic models, structure balance belts influencing the reconstruction and residual potential of reservoirs after accumulation, the rules and mechanisms of fractures controlling oil and gas, and the types of favorable reservoirs and their characteristics of controlling oil and gas distribution. We further point out the main problems about the oil and gas exploration in the Tazhong area and put forward some relevant proposals.
