Search

Two geological steering models, the particle swarm support vector machine (PSO-SVM) and the gray wolf support vector machine (GWO–SVM), were analyzed to determine the models' optimal global parameters. The fitness function was used to compare and analyze the models, while the original data and feature reconstruction data were used to simulate and analyze the models. The most suitable model for shale gas geosteering identification was selected; the multi-source information fusion for the shale gas geosteering design was completed; and a complete geosteering discrimination model was established. Research on the shale gas geosteering identification system with multi-source information fusion was conducted, and we completed the technical scheme design of shale gas geosteering discrimination system with multi-source information fusion, supported the ground real-time data acquisition system, processed the geosteering discrimination, and completed the demand analysis of the shale gas geosteering discrimination system with multi-source information fusion. In the process of drilling, the relationship between the trajectory and the formation position was analyzed, and the drilling trajectory was monitored. The system mainly included the software main interface, data, and geosteering identification module. [ABSTRACT FROM AUTHOR]

To solve the problem in traditional technology of the time lag in determining formation information based on drilling time and rock physical characteristics, which leads to the failure of the guided drilling tool, a Levy flight optimized gray wolf support vector machine (LGWO-SVM) shale gas geosteering identification method based on gamma spectrum dataset was proposed. First, the gamma spectrum dataset was processed using mapminmax normalization to eliminate the feature confusion caused by data modeling. Second, principal component analysis (PCA) feature reconstruction was carried out on the gamma spectrum dataset to provide an excellent data basis for the subsequent establishment of a multiclassification support vector machine (SVM) model. Then, the Levy distribution was adopted into gray wolf optimization for the multiclassification SVM model to obtain the LGWO-SVM model for geosteering discriminant prediction. Finally, the experimental results corresponding to the particle swarm optimization support vector machine (PSO-SVM) and the gray wolf optimizer support vector machine (GWO-SVM) models were summarized and compared. The experimental results show that after the data processing and feature extraction of the gamma spectrum dataset, the established LGWO-SVM model can accurately distinguish the formation information and effectively improve the reservoir drilling rate. [ABSTRACT FROM AUTHOR]

The rapid and accurate identification of the formation lithology encountered during the drilling of oil and gas fields is an important step to control the trajectory of the drilling tool borehole and improve the optimal reservoir encounter rate. At present, the main way to distinguish the lithology of the formation encountered by drilling is to use artificial detection elements, which does not form a set of intelligent formation identification system. In view of the above problems, this paper proposes a method to identify the lithology of drilled formation by using element and gamma spectrum measurement and establishes a reasoning model of intelligent identification of formation lithology by using improved fuzzy clustering algorithm-SVM (IFCM-SVM) method. Field application shows that the accuracy of IFCM-SVM intelligent formation identification method proposed in this paper can reach 90.9%, and verifies the feasibility of using element and gamma spectrum measurement to realize the intelligent identification of formation lithology in drilling. [ABSTRACT FROM AUTHOR]