LWD Azimuthal Resistivity Data Amplification for Lithology Evaluation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The accuracy of logging-while-drilling (LWD) azimuthal resistivity in sand shale formations is insufficient due to equipment or technology deficiencies, leading to inadequate lithology evaluation, especially in deep oil and gas navigation where real-time and precise data are crucial.
Innovation Solution
A method involving data amplification using the Akima interpolation method to enhance density, gamma, and resistivity distribution data from 8-sector to 32-sector data, followed by clustering, dimensionality reduction, and the use of a trained missing curve prediction model to generate a photoelectric data prediction curve for improved lithology evaluation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If acoustic LWD data is used to estimate mechanical properties of rocks, then the accuracy of geological interpretation is improved, but the cost and equipment complexity increase
Solution Approach 1:
The patent creates a virtual copy of the missing photoelectric curve data through mathematical modeling and prediction algorithms. By using measured logging data (density, gamma, resistivity) as input features, the system generates predicted photoelectric curve values that replicate what the actual measurement would have provided, eliminating the need for specialized photoelectric logging equipment in certain scenarios
Solution Approach 2:
The patent introduces an intermediary prediction model that bridges the gap between available measured logging data and the required photoelectric curve information. This intermediary system processes multiple logging parameters through a trained prediction algorithm to generate the missing photoelectric data, serving as a mediator between existing measurements and the needed geological interpretation information
2Measurement precision
If photoelectric logging is performed to achieve real-time lithology evaluation, then the accuracy of lithology evaluation is improved, but the equipment reliability and data acquisition success rate decrease due to instrument deficiencies
Solution Approach 1:
The patent performs preliminary actions by collecting and training the prediction model using comprehensive photoelectric logging data from wells where such measurements are available. This pre-trained model stores the relationships between various logging parameters and photoelectric responses, enabling the system to predict photoelectric curves in wells where direct measurement fails or is unavailable, thus ensuring continuous data acquisition success
Solution Approach 2:
The patent prepares backup prediction models and multiple algorithmic approaches in advance to compensate for potential instrument failures. By having pre-trained alternative prediction systems ready, the method ensures that if one prediction approach fails or the actual photoelectric instrument malfunctions, alternative models can provide the necessary photoelectric curve data, cushioning against data acquisition failures
3Loss of information
If missing logging data is predicted through mathematical methods based on local analysis, then the completeness of logging data is improved, but the accuracy of prediction is limited
Solution Approach 1:
The patent transitions from local one-dimensional analysis to a multi-dimensional approach by incorporating multiple logging parameters (density, gamma, resistivity) as input features and using well-wide contextual information from both measured and predicted data. This dimensional expansion allows the prediction model to capture complex relationships between different logging parameters and improve prediction accuracy beyond simple local correlations
Solution Approach 2:
The patent merges multiple sources of information including measured logging data, predicted logging data, seismic data, and well log data from adjacent wells into a unified prediction framework. By combining these diverse data sources, the system creates a more robust prediction model that leverages complementary information from each source, thereby improving overall prediction accuracy while maintaining data completeness
Data Source
AI summary
A sand shale formation lithology evaluation method and system for precise deep oil and gas navigation aims to solve the problem in the prior art, that is, the accuracy of the logging-while-drilling (LWD) azimuthal resistivity is insufficient due to an equipment or technology deficiency. The method includes: acquiring density distribution data, gamma distribution data, and resistivity distribution data of a target location; amplifying the data to acquire amplified logging distribution data; clustering the data to acquire clustered logging data; adding stratigraphic information to the clustered data; performing dimensionality reduction by a principal component analysis (PCA) method, and taking dimensionality-reduced data as a weight of azimuthal logging data to acquire an LWD feature dataset; predicting missing LWD photoelectric data through the LWD feature dataset; and acquiring a formation lithology evaluation result based on an LWD photoelectric data prediction curve. The method and system improves the accuracy of LWD lithology evaluation.