Near-Bit Lithology Detection with Intelligent Rock Voiceprints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing acoustic logging while drilling and seismic while drilling methods are complex, have limited resolution, generate large data volumes, and are not conducive to accurate and real-time analysis of near-bit strata information, leading to potential drilling deviations from oil and gas reservoirs.
Innovation Solution
A method and device for identifying near-bit lithology using intelligent voiceprint identification, involving rock sound data acquisition, pre-processing, feature extraction, database establishment, and intelligent algorithm training to predict lithology based on rock voiceprint features, reducing data transmission volume and simplifying acoustic instrument structure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If acoustic logging while drilling or seismic while drilling methods are used to detect near-bit strata, then stratum features can be obtained, but the instrument structure becomes complex and data volume increases significantly
Solution Approach 1:
The patent extracts only the essential acoustic reception function from the complex acoustic logging instrument, using a single acoustic receiver instead of multiple receivers and insulators. This simplifies the instrument structure while maintaining the ability to detect near-bit stratum acoustic signals for lithology identification.
Solution Approach 2:
The acoustic receiver performs multiple functions: detecting both longitudinal waves and transverse waves, serving as both the sensor and the primary signal processing element. This multi-functionality reduces the need for separate components, simplifying the overall instrument structure.
2Measurement precision
If acoustic logging while drilling method is used to measure stratum, then longitudinal and transverse waves can be detected, but the instrument structure becomes complex with multiple receivers and insulators
Solution Approach 1:
The patent removes the acoustic insulator and multiple receivers from the traditional acoustic logging instrument, retaining only a single acoustic receiver. This extraction of unnecessary components simplifies the instrument while preserving the core wave detection capability through intelligent signal processing.
Solution Approach 2:
The patent replaces the mechanical solution of using multiple receivers and insulators with an intelligent software-based signal processing system. The single receiver's output is processed using wave separation algorithms and machine learning models to extract both longitudinal and transverse wave information, substituting mechanical complexity with computational intelligence.
3Measurement precision
If seismic while drilling method is used to obtain geological information, then underground structure can be imaged, but signal intensity becomes insufficient in deep wells and data processing is challenging
Solution Approach 1:
The patent replaces the traditional seismic imaging method with an intelligent recognition system based on machine learning. Instead of relying on weak seismic signals that travel long distances, the system uses acoustic signals detected near the drill bit and processes them through trained models to identify lithology, improving signal reliability in deep wells.
Solution Approach 2:
The patent applies preliminary action by pre-training the intelligent recognition model with extensive rock acoustic signal data before field deployment. This pre-processing and model training enable the system to accurately identify lithology from acoustic signals even in deep well conditions where signal intensity is reduced, without requiring complex real-time processing adjustments.
4Measurement precision
If traditional acoustic logging or seismic methods are used, then stratum information can be obtained, but real-time analysis is difficult due to large data volumes
Solution Approach 1:
The patent extracts only the essential acoustic signal data near the drill bit and processes it through an intelligent recognition model to extract key lithology features. This extraction of essential information from raw acoustic signals dramatically reduces data volume while maintaining measurement precision, enabling real-time analysis.
Solution Approach 2:
The patent replaces the mechanical data processing approach (transmitting and processing large volumes of raw acoustic data) with an intelligent system that performs feature extraction and lithology identification through machine learning models. This substitution reduces computational burden and enables real-time processing of stratum information.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach significantly reduces data volume by 2 to 3 orders of magnitude, enabling real-time and accurate near-bit stratum lithology identification, optimizing drilling processes, and reducing manufacturing costs, thus enhancing drilling precision and safety.
Implementation Method 1
acoustic detection methods, such as acoustic logging while drilling and seismic while drilling, have been proposed to measure near the drill bit
Implementation Method 2
obtaining the corresponding sound data of hitting and drilling by hitting or drilling a cubic rock, and acquiring same by a miniature piezoelectric transducer and an oscilloscope
Data Source
AI summary
The present disclosure relates to the technical field of acoustic detection while drilling, in particular to a method and a device for identifying near-bit lithology based on intelligent voiceprint identification, including acquiring rock sound data; pre-processing the acquired rock sound data; extracting voiceprint features of pretreated rock sounds; establishing a rock voiceprint feature database; training the intelligent voiceprint identification algorithms according to the lithology labels and voiceprint feature data in the rock voiceprint feature database; intelligently identifying or predicting the rock voiceprint features using the intelligent voiceprint identification algorithms and outputting the lithology identification results. The present disclosure can greatly enhance the real-time availability and accuracy of obtaining near-bit stratum lithology data in-site, which can effectively improve the reservoir drilling rate and timely avoid drilling risks.