Wellbore Dip Merging for Inclined and Horizontal Wells
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining the apparent dip of formation structures in wellbore images are limited to vertical or near-vertical wellbores and generate numerous partial dip orientations, failing to effectively handle inclined and horizontal wellbores.
Innovation Solution
A method involving lamination analysis, classification using a neural network, and DBSCAN clustering to identify and merge dip orientations, enabling accurate determination of a single dip orientation for geological layers in wellbores of any orientation, including vertical, inclined, and horizontal configurations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If existing methods are used to determine apparent dip in vertical wellbores, then dip orientation can be computed for sinusoidal structures, but the methods fail to handle inclined and horizontal wellbores effectively
Solution Approach 1:
The patent develops a unified dip determination method that works across all wellbore orientations (vertical, inclined, and horizontal) by using a consistent mathematical framework based on the relationship between apparent dip angle, true dip angle, and wellbore inclination angle. This universal approach eliminates the need for separate methods for different well orientations.
Solution Approach 2:
The patent transforms the dip determination problem by introducing the wellbore inclination angle as a key parameter and deriving relationships that account for variations in this parameter. By expressing apparent dip as a function of true dip and wellbore inclination, the method adapts to different well orientations through parameter variation rather than requiring different algorithms.
2Quantity of substance
If existing methods compute apparent dip for depth intervals, then dip information is obtained, but a large number of partial dip orientations are generated for a single geological surface
Solution Approach 1:
The patent merges multiple partial dip orientation measurements into a single representative dip orientation for each geological surface by using statistical aggregation methods. This combining process reduces data redundancy while preserving the essential geological information, transforming numerous fragmented measurements into coherent dip estimates.
Solution Approach 2:
The patent extracts the essential dip orientation information from the large set of partial measurements by identifying and removing redundant data. Through filtering and selection processes, the method isolates the most reliable dip orientations and discards duplicate or conflicting measurements, resulting in a streamlined set of meaningful results.
3Quantity of substance
If more dip orientations are computed from wellbore images, then more data is available for analysis, but the complexity of processing and merging these orientations increases
Solution Approach 1:
The patent applies preliminary filtering and validation steps to dip orientation measurements before merging them. By pre-processing the data to remove obvious errors and outliers, and by establishing quality criteria in advance, the method reduces the complexity of subsequent merging operations while maintaining data integrity.
Solution Approach 2:
The patent replaces complex manual or iterative merging processes with automated computational algorithms based on mathematical relationships. By using formula-based approaches to combine dip orientations rather than manual analysis, the system handles large quantities of data efficiently without proportionally increasing processing complexity.
Data Source
AI summary
A method for computing a dip orientation of a subterranean structure from a wellbore image includes conducting a lamination analysis on a received wellbore image to identify a structure therein and to compute a plurality of dip orientations of the identified structure at a corresponding plurality of the depths. The received image is further evaluating with a classification algorithm to generate a labeled image including an image label for each of a plurality of depth zones in the received image. The plurality of computed dip orientations and the image label are evaluated for at least one of the plurality of depth zones to generate a substructure therein, wherein the substructure includes a subset of the computed dip orientations. The subset of computed dip orientations in the substructure is merged to compute at least one dip orientation for the geological layer.


