Quantitative characterization method and device for physical phase of productivity rocks

Abstract

The invention discloses a quantitative characterization method and device for physical phases of productivity rocks, and belongs to the technical field of oil-gas field development. The method comprises the steps: firstly, extracting production test data to establish a production data big table by taking a vertical well perforation or a horizontal well section cluster as a data unit, carrying out space grid conversion on productivity parameter characteristics by utilizing a grid technology, and calculating an overlapping degree coefficient between different geological and engineering characteristic parameters; and establishing a hierarchical structure between different geological and engineering characteristics by using a hierarchical clustering algorithm by taking a grid density overlapping degree as a key attribute, mining master control geological and engineering factors of productivity difference, and finally determining a productivity rock physical facies type according to a threshold value output result. Innovative research results solve the problem of quantitative characterization of the relationship between the geologic features and the engineering features and the oil and gas productivity, play an important supporting role in oil and gas reservoir productivity evaluation service development, and are beneficial to improving the oil and gas reservoir development effect, improving the oil and gas well yield and reducing the production cost.

Description

technical field [0001] The invention relates to the technical field of oil and gas field development, and relates to a quantitative characterization method of productivity petrophysical facies, in particular to a method and device for quantitative characterization of productive petrophysical facies based on a grid density-based overlapping degree hierarchical clustering algorithm. Background technique [0002] Affected by sedimentation, diagenesis, fluids and engineering, the productivity of oil and gas wells has strong heterogeneity. Excavating the main controlling factors of oil and gas well productivity is the technical key to increase the production of oil wells and improve the development effect of oil and gas reservoirs. However, the current analysis of the main control factors of horizontal wells is mainly based on qualitative and semi-quantitative methods, and there is no effective technical method to quantitatively characterize the productivity differences between di...

AI Technical Summary

Problems solved by technology

However, the current analysis of the main controlling factors of horizontal wells is mainly based on qualitative and semi-quantitative methods, and there is a lack of effective technical methods to quantitatively characterize the productivity differences between different geological and engineering characteristics.

At present, with the rapid development of big data and artificial intelligence technology, the use of data-driven technology to solve the analysis of the main controlling factors of oil and gas reservoirs has become a hot spot in industry research. However, conventional supervised classification algorithms, regression algorithms and unsupervised clustering algorithms cannot effectively solve this problem. Therefore, The present invention proposes a supervised hierarchical clustering algorithm based on label data to solve the problem of quantitative characterization of the relationship between geological features and engineering features and oil and gas productivity

Images