| CPC G01V 20/00 (2024.01) | 7 Claims |
|
1. A method for assessing stability of roadway surrounding rock based on numerical simulation and deep learning, comprising the following steps:
step 1: determining a roadway to be assessed in an underground coal mine, collecting rocks from a roof of the underground coal mine as samples, and performing physical and mechanical property tests on the samples with laboratory equipment to obtain actual stratum rock parameters under an actual geological environment;
step 2: establishing a two-dimensional geological model through the numerical simulation based on a drill core columnar diagram corresponding to drilling holes near the roadway to be assessed and the actual stratum rock parameters obtained from the physical and mechanical property tests;
step 3: changing influencing factors in the two-dimensional geological model, and then recording amounts of deformation of sidewalls of the roadway in the two-dimensional geological model, acceleration values of the deformation of the sidewalls of the roadway and whether failure occurs in the roadway to thereby obtain dynamic response characteristics of the roadway surrounding rock, taking the changed influencing factors and the dynamic response characteristics of the roadway surrounding rock as labels, combining the changed influencing factors and the dynamic response characteristics of the roadway surrounding rock to obtain a dataset, obtaining a plurality of datasets comprising the dataset, and forming a database with the plurality of datasets, wherein the influencing factors comprise a dynamic load intensity, a dynamic load action distance, a dynamic load action time, a static load stress level, a support parameter, and a pressure-relief measure;
step 4: dividing the plurality of datasets into a training set and a validation set according to a set ratio, inputting the training set into a particle swarm optimization (PSO)-back propagation (BP) neural network and a genetic algorithm (GA)-support vector machine (SVM) deep learning model for the deep learning to obtain a preliminary roadway surrounding rock stability assessment model based on the numerical simulation and the deep learning, and adjusting and validating the preliminary roadway surrounding rock stability assessment model using the validation set to obtain an optimized roadway surrounding rock stability assessment model; and
step 5: using the optimized roadway surrounding rock stability assessment model to assess the stability of other mining stages of the roadway to be assessed, and determining whether the roadway surrounding rock to be assessed will become unstable or fail under a target geological condition, a target support method, and a target pressure-relief measure when subjected to dynamic loads.
|