Roadway Rock Stability Assessment via Numerical Simulation and Deep Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current stability assessment methods for roadway surrounding rock in mines are inadequate, often relying on empirical formulas and theoretical calculations that fail to consider the complexity and variability of geological factors, leading to inaccurate assessments and insufficient support measures for rockburst-prone environments.
Innovation Solution
A method combining numerical simulation and deep learning to assess roadway stability, using physical and mechanical property tests, two-dimensional geological modeling, and a PSO-BP neural network and GA-SVM deep learning model to create an optimized stability assessment model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If empirical formulas and theoretical calculations are used for stability assessment, then the assessment process is simple and quick, but the accuracy and comprehensiveness of the assessment deteriorates due to inability to consider complex geological factors
Solution Approach 1:
The patent creates a virtual copy of the complex geological system through numerical simulation models. Instead of directly measuring all geological factors in the field, the system copies the geological conditions into a computational model where complex interactions can be analyzed efficiently, thus maintaining assessment speed while improving accuracy.
Solution Approach 2:
The patent replaces traditional mechanical/empirical assessment methods with computational intelligence systems (neural networks, support vector machines). These intelligent systems substitute for complex mechanical analysis, enabling the system to process multiple geological factors simultaneously and provide accurate predictions without manual complexity.
2Ease of manufacture
If theoretical models are simplified for ease of calculation, then the model is easy to apply in practice, but the model fails to reflect complex actual engineering situations
Solution Approach 1:
The patent transforms the assessment problem by changing parameters from direct physical measurements to processed indicators that capture complex relationships. The system calculates composite parameters like stress concentration coefficients and deformation rates that encapsulate multiple underlying factors, making the model both simple to apply and accurate in reflecting real conditions.
Solution Approach 2:
The patent introduces intermediary computational layers between raw geological data and final assessment results. Neural networks and support vector machines act as intermediaries that process complex geological inputs and translate them into reliable stability predictions, bridging the gap between complex reality and simplified application.
3Measurement precision
If comprehensive geological factors are included in the assessment, then the assessment accuracy improves, but the complexity of data collection and processing increases
Solution Approach 1:
The patent segments the complex assessment system into distinct functional modules: data collection modules for different geological factors, numerical simulation modules for specific physical processes, and prediction modules using different intelligent algorithms. This segmentation allows each module to handle specific tasks efficiently, reducing overall system complexity while maintaining comprehensive assessment capability.
Solution Approach 2:
The patent creates a universal assessment platform that can handle multiple types of geological factors and assessment scenarios through a single integrated system. The numerical simulation and intelligent prediction framework is designed to be multi-functional, accommodating various rock types, stress conditions, and geological structures without requiring separate specialized systems for each case.
Data Source
AI summary
A stability assessment method of roadway surrounding rock includes: obtaining actual stratum rock parameters; establishing a two-dimensional geological model through numerical simulation based on a drill core columnar diagram and the actual stratum rock parameters; changing influencing factors, and recording amounts and acceleration values of deformation of roadway sidewalls, and whether failure occurs to obtain dynamic response characteristics of roadway surrounding rock, combining the changed influencing factors and the dynamic response characteristics as labels to obtain a dataset, and obtaining multiple datasets including the dataset; dividing the multiple datasets into a training set and a validation set, inputting the training set into a PSO-BP neural network and a GA-SVM deep learning model to obtain a preliminary stability assessment model, and adjusting and validating the preliminary stability assessment model by the validation set to obtain an optimized stability assessment model; and using the optimized stability assessment model to assess roadway stability.