Indentation Stress Measurement for Nonlinear Soft Rock Formations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current in-situ stress measurement technologies struggle to accurately measure stress in deep and shallow soft rocks due to their nonlinear characteristics, and existing methods based on elastic theory are inadequate for complex geological conditions.
Innovation Solution
An in-situ stress measurement method combining indentation technology with machine learning, specifically using a Bayesian neural network, to derive nonlinear mechanical models for deep Earth rocks, involving drilling, processing rock cores, conducting indentation tests, and utilizing machine learning to calculate principal stresses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If elastic theory-based methods are used for in-situ stress measurement, then measurement simplicity is maintained, but measurement precision deteriorates for deep and shallow soft rocks with nonlinear characteristics
Solution Approach 1:
The patent introduces an indentation device as an intermediary tool that bridges the gap between simple measurement procedures and accurate stress determination in nonlinear rock materials. The device applies controlled indentation loads and measures deformation responses, providing intermediate data that feeds into the machine learning model for accurate stress inference without requiring complex direct measurement equipment.
Solution Approach 2:
The patent replaces traditional mechanical stress measurement systems based on elastic theory with a data-driven machine learning system. Instead of using complex mechanical models and assumptions about rock behavior, the system uses indentation test data combined with neural network algorithms to directly predict in-situ stress values, substituting mechanical theory with computational intelligence.
2Adaptability or versatility
If indentation technology combined with machine learning is used, then measurement precision improves for nonlinear rocks, but device complexity increases
Solution Approach 1:
The patent creates a universal measurement system that can handle various rock types and geological conditions through the combination of indentation technology and machine learning. The indentation device serves multiple functions: applying load, measuring deformation, and providing input data for the machine learning model, which in turn adapts to different rock mechanics characteristics, making the system versatile across diverse geological scenarios.
Solution Approach 2:
The patent changes the fundamental parameters used for stress measurement from traditional elastic mechanical parameters to indentation-specific parameters such as load-depth curves and deformation characteristics. By measuring and analyzing these alternative parameters through the indentation device and processing them via machine learning, the system achieves adaptability to nonlinear rock behavior without requiring the rock to conform to elastic theory assumptions.
3Reliability
If traditional elastic theory methods are used, then ease of operation is maintained, but reliability deteriorates for rocks with plastic deformation and rheology
Solution Approach 1:
The patent implements a self-service measurement system where the machine learning model automatically learns the relationship between indentation test results and in-situ stress conditions from training data. The system performs self-calibration and adaptation by processing indentation data through the neural network, eliminating the need for operators to manually apply complex elastic theory calculations or make subjective judgments about rock behavior, thereby improving reliability while maintaining operational simplicity.
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
The method provides accurate in-situ stress measurement by depicting both elastic and plastic deformation behaviors of deep Earth rocks, expanding the range of stress measurement and overcoming limitations of existing elastic theory-based methods.
Implementation Method 1
an equivalent elastic model of rock core is derived... depicting both elastic and plastic deformation behaviors
Implementation Method 2
depicting both elastic and plastic deformation behaviors of deep Earth rocks
Data Source
AI summary
An in-situ stress measurement method based on indentation technology and machine learning includes steps as follows. A rock core is obtained to be processed into a sample. A shallow indentation test is conduct on the sample to obtain the indentation load-depth curve and the equivalent elastic model is derived. A deep indentation test is performed and the test data is used as actual training samples for machine learning. The actual training sample set is input into the neural network for network training to obtain an inverse problem model of in-situ stress. An in-situ indentation test is performed on the sample and, based on the equivalent elastic model, the minimum and maximum horizontal principal stresses are calculated. A direction of main crack of an indentation at a bottom of a borehole as a direction of the maximum horizontal principal stress is measured by an imaging logging tool.