Neural Network Well Log Depth Matching for Gamma-Ray Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The synchronization of gamma-ray logs from multiple logging passes is challenging due to environmental perturbations, tool sticking, and irregular borehole shapes, leading to inaccurate depth measurements and sub-optimal interpretation, particularly in thinly-laminated formations.
Innovation Solution
A machine learning-based approach using a neural network for automated depth matching of well logs, employing data structuring, data augmentation, and Generative Adversarial Networks (GANs) to align gamma-ray logs, with training on real and synthetic data to achieve nearly perfect synchronization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If multiple logging passes are carried out to measure formation characteristics, then comprehensive formation data is obtained, but depth misalignment between logs occurs due to tool sticking and environmental perturbations
Solution Approach 1:
The patent introduces an intermediary alignment algorithm that uses gamma ray logs as a reference framework to mediate between multiple logging passes. The algorithm identifies correlation peaks between gamma ray logs from different passes and applies depth shifts to align them, effectively using the gamma ray log as an intermediary mediator to synchronize other measurement logs across multiple passes despite tool sticking and environmental perturbations
Solution Approach 2:
The patent implements feedback by iteratively refining depth alignment through correlation analysis. The alignment algorithm continuously compares gamma ray logs, identifies misalignments through correlation peak detection, applies corrective depth shifts, and re-evaluates the alignment until optimal synchronization is achieved, creating a closed-loop feedback system that progressively improves depth matching accuracy
2Ease of operation
If GR logs are used to synchronize multiple logging passes, then depth matching is attempted, but synchronization accuracy deteriorates due to signal distortion from tool sticking and environmental effects
Solution Approach 1:
The patent applies segmentation by dividing the logging data into distinct segments: gamma ray logs are separated from other measurement logs, and further segmented into individual passes. This allows the alignment algorithm to process gamma ray data independently, identify correlation peaks within each segment, and apply targeted depth corrections without the interference of distorted signals from other log types affected by tool sticking
Solution Approach 2:
The patent employs parameter changes by transforming the gamma ray log data through normalization and filtering operations before correlation analysis. The algorithm adjusts parameters such as sampling rates, applies smoothing filters to reduce noise from environmental effects, and modifies the correlation window parameters to optimize peak detection accuracy despite signal distortion from tool sticking and borehole irregularities
3Device complexity
If conventional alignment methods are used assuming logs are aligned, then processing is simplified, but interpretation quality deteriorates particularly in thinly-laminated formations
Solution Approach 1:
The patent applies preliminary action by performing depth alignment of gamma ray logs before conducting formation interpretation. The alignment algorithm pre-processes the logs by identifying and correcting depth misalignments through correlation analysis, ensuring that subsequent interpretation workflows receive pre-aligned data. This preliminary alignment step prevents propagation of alignment errors through the interpretation process, particularly protecting against misinterpretation of thin laminations that would occur with conventional assume-aligned methods
Data Source
AI summary
A method and computing system device for receiving a plurality of well logs. A depth shift between at least one well log of the plurality of well logs and at least one other well log may be determined based upon, at least in part, processing the plurality of well logs with a neural network. The plurality of well logs may be matched with one another based upon, at least in part, the depth shift between the at least one well log and the at least one other well log.