Shale Gas Well Classification Using Fuzzy Geological-Production Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing shale gas well type evaluation methods fail to accurately and meticulously assess shale gas wells, leading to deviations in classification due to isolation of static geological and dynamic production evaluations, ignoring geological-engineering integration, and being inflexible in adjusting classifications based on actual production needs.
Innovation Solution
A shale gas well type classification method that integrates geological and production parameters, using multi-parameter standardization, distance coefficient matrix construction, and dynamic fuzzy clustering to classify wells into flexible classes, followed by proximity matching for precise evaluation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If static geological parameters or dynamic production parameters are used in isolation for classification, then the classification process is simple, but the classification accuracy deteriorates due to ignoring geological-engineering integration
Solution Approach 1:
The patent merges static geological parameters (effective thickness, gas saturation, formation pressure) with dynamic production parameters (open flow rate, gas production per unit casing pressure drop, peak daily gas production) into a unified evaluation system. This combination allows comprehensive assessment of shale gas wells by integrating both geological characteristics and production performance, thereby improving classification accuracy while accounting for the complexity of multiple parameters.
2Adaptability or versatility
If traditional three-category classification is used, then the classification scheme is simple, but the adaptability deteriorates because it cannot adjust or refine gas well types according to actual production needs
Solution Approach 1:
The patent implements dynamic classification by calculating distance coefficients between wells and using fuzzy membership functions that allow wells to belong to multiple categories with different degrees of membership. The classification scheme can be adjusted by modifying the distance threshold coefficient k, enabling flexible refinement of gas well types according to actual production needs while maintaining a systematic framework.
3Reliability
If hard classification with clear boundaries is used, then the classification is straightforward, but the reliability deteriorates when data points have overlapping features or unclear category boundaries
Solution Approach 1:
The patent transforms the classification approach from hard boundaries to soft boundaries by introducing fuzzy membership degrees. Instead of assigning wells to discrete categories, the system calculates membership degrees for each category based on distance coefficients, allowing wells with overlapping features to be reliably classified with quantitative uncertainty measurement. The reliability is further enhanced by calculating a comprehensive evaluation index that synthesizes multiple parameters.
4Measurement precision
If comprehensive multi-parameter evaluation is implemented, then the evaluation thoroughness is improved, but the calculation complexity increases due to dimensionality issues
Solution Approach 1:
The patent standardizes six evaluation parameters with different units and ranges into a unified dimensionless scale using the formula (x - min) / (max - min), where x is the parameter value, min is the minimum value, and max is the maximum value. This standardization eliminates dimensionality issues and allows direct comparison and integration of geological and production parameters, improving evaluation thoroughness while managing calculation complexity through systematic normalization.
Data Source
AI summary
A shale gas well type classification method includes: S1, acquiring raw data of evaluation parameters for stable production wells and trial production wells; S2, performing standardization on the raw data; S3, calculating distance coefficients; S4, classifying the stable production wells; S5, after determining a class number of the stable production wells, calculating comprehensive evaluation parameters S of the stable production wells based on standardized data; S6, for each class of the stable production wells, calculating average values of standardized data of the evaluation parameters for the stable production wells to construct a standard fuzzy set A, and constructing a to-be-identified fuzzy set B for each of the trial production wells, S7, calculating a closeness degree between each to-be-identified fuzzy set and each standard fuzzy set, and classifying a trial production well corresponding to the to-be-identified fuzzy set into a class of the stable production wells with a highest closeness degree.