Real-Time Stratigraphic Framework Updating via Density Peak Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing geosteering-while-drilling technologies face challenges in accurately updating stratigraphic frameworks in real-time due to heterogeneity and differences in well logging and mud logging data, leading to poor control over well trajectories and recognition of depth and dipping angles, especially in complex reservoir structures.
Innovation Solution
An intelligent real-time updating method that involves obtaining well data, preprocessing it to eliminate abnormal values, conducting non-linear dimensionality reduction, clustering using the density peak clustering method, and employing a deep belief network for marker layer prediction to correct the stratigraphic framework model and adjust drilling trajectories.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional stratigraphic framework updating technology is used, then the process is simple and easy to operate, but the accuracy of stratum recognition and well trajectory control is poor
Solution Approach 1:
The patent segments the stratigraphic framework updating process into multiple modules: data acquisition module, data processing module (with preprocessing, dimensionality reduction, and clustering sub-modules), model construction module, and model updating module. Each module handles specific tasks independently, improving overall system accuracy while maintaining manageable complexity through modular design.
Solution Approach 2:
The patent applies non-linear dimensionality reduction technology to transform high-dimensional well logging data into lower-dimensional space while preserving essential stratigraphic information. This dimensional transformation enables more accurate stratum recognition by reducing data noise and redundancy, directly improving measurement precision without proportionally increasing system complexity.
2Adaptability or versatility
If multiple types of geological-geophysical data are merged, then the comprehensiveness of the stratigraphic framework model is improved, but the heterogeneity and parameter differences make data integration difficult
Solution Approach 1:
The patent introduces dimensionality reduction and clustering technologies as intermediary processing steps between raw data acquisition and model construction. These intermediaries standardize heterogeneous data from different sources (well logging, mud logging, seismic data) by transforming them into a unified feature space, enabling effective integration while managing complexity through standardized processing pipelines.
Solution Approach 2:
The patent transforms the parameters of heterogeneous geological-geophysical data through non-linear dimensionality reduction, changing the parameter space from high-dimensional raw measurements to lower-dimensional meaningful features. This parameter transformation preserves the essential characteristics of different data types while enabling their unified processing and integration.
3Reliability
If real-time data processing is performed during drilling, then the well trajectory control is improved, but the processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary data preprocessing and dimensionality reduction on well logging data as it is acquired during drilling, before the full stratigraphic framework model is constructed. This preliminary processing reduces the computational burden of subsequent model updating operations, enabling real-time or near-real-time trajectory control while minimizing processing time loss.
Solution Approach 2:
The patent implements continuous data processing during the drilling operation, where well logging data is continuously acquired, preprocessed, and used to incrementally update the stratigraphic framework model. This continuous processing approach maintains reliable well trajectory control without significant interruptions or batch processing delays, reducing overall processing time.
Data Source
AI summary
The present disclosure belongs to the field of geological prospecting and particularly relates to an intelligent real-time updating method and system for a stratigraphic framework with geosteering-while-drilling, aiming to solve the problems of insufficient precision in position and dipping angle of a stratigraphic framework due to differences in parameters measured by different instruments for well logging and mud logging while drilling. The method of the present disclosure comprises: obtaining existing well data, and acquiring well logging data and images imaged while-drilling in real time; constructing an initial stratigraphic framework model, eliminating abnormal values, and conducting dimensionality reduction; and based on dimensionality reduction well logging data, conducting non-linear clustering through a density peak clustering method, obtaining a marker layer primary prediction result through a marker layer prediction model of a depth belief network and conducting correction, to obtain a corrected stratigraphic framework model and to adjust a drilling trajectory.