1009 results about "Rock mechanics" patented technology

The invention relates to the technical field of rock mechanics, and discloses a rock three-dimensional reconstruction method and system based on multi-source information fusion, and the method comprises the steps: obtaining and preprocessing data, carrying out the spatial feature learning of a fusion feature vector through a 3D-CNN network, and constructing a three-dimensional voxel model of rock microscopic damage; converting the fused image data into a point cloud model of the underground cavern surrounding rock structure by adopting a three-dimensional reconstruction algorithm based on point cloud, and constructing a digital twin framework of the underground cavern surrounding rock structure based on an implicit surface reconstruction algorithm; feature parameters output by the three-dimensional voxel model and the digital twinning framework are used as input, and the optimal supporting opportunity and supporting parameters are output through an LSTM-CNN fusion model; in the underground engineering construction process, surrounding rock deformation data are collected in real time, and a supporting scheme is adjusted in real time through a depth deterministic strategy gradient algorithm; according to the method, the scientificity and timeliness of support design under complex geological conditions can be improved.

A well location and well trajectory determination method, comprising: on the basis of a stratum pressure test, and a flow phase constraint of each stratum, establishing a full-stratum-series three-dimensional rock mechanical parameter field model, so as to obtain full-stratum-series rock mechanical parameters; on the basis of a geological structure, and a stratum pressure field of each stratum, establishing a three-dimensional full-stratum-series stress field prediction model, so as to acquire full-stratum-series three-dimensional stress field parameters; on the basis of the full-stratum-series rock mechanical parameters, the full-stratum-series three-dimensional stress field parameters and a three-dimensional natural fracture model, establishing a natural fracture activity prediction model, so as to evaluate fracture activity; and determining a well location and a well trajectory on the basis of a three-dimensional original field geostress model, a three-dimensional fracturability prediction model, the fracture activity and a three-dimensional collapse pressure prediction model. By means of the method, the effects of drilling speed increases and modification and production increases can be achieved in complex oil and gas field blocks. Further provided are a drilling speed increase method, a modification and production increase method, a well location and well trajectory determination apparatus, an electronic device, and a computer-readable storage medium.

The invention belongs to the technical field of tunnel safety monitoring, and particularly relates to a rock stratum stress-deformation coupled tunnel safety real-time dynamic modeling method, which comprises the following steps of: embedding a rock mass mechanical relationship into a neural network model as a hard constraint, and establishing explicit mapping of monitoring data and a physical field, a model parameter field is dynamically optimized by adopting ensemble Kalman filtering real-time general field detection data, and a data driving and physical mechanism collaborative deduction mechanism is designed, so that long-term prediction error accumulation is effectively inhibited; a stress field, a deformation field and other physical quantities deduced and output by the model are directly utilized to calculate disaster risk indexes with clear mechanical significance, and a physically interpretable early warning decision is realized by fusing fuzzy reasoning and multi-source risks; the technical problems of physical misalignment, weak long-term generalization and poor early warning interpretability of a data-driven model are solved.

The invention discloses a geological modeling, crack propagation and fluid-solid coupling production prediction integrated evaluation method, and relates to the field of multiple technologies, and the method comprises the steps: constructing a three-dimensional geological model of a deep shale gas reservoir; according to the construction model, the attribute model, the three-dimensional ground stress model and the rock mechanical parameter model, a hydraulic fracture model is constructed; based on the hydraulic fracture model and the three-dimensional geological model of the deep shale gas reservoir, establishing a fluid-solid coupling productivity simulation mathematical model of the deep shale gas reservoir; according to the fluid-solid coupling productivity simulation mathematical model of the deep shale gas reservoir, the fractured horizontal well yield of the shale gas reservoir is predicted, and a prediction result is comprehensively evaluated and optimized. According to the method, multiple links of geological modeling, fracture propagation simulation, fluid-solid coupling production prediction and the like are integrated, and the geological characteristics of the gas reservoir, the fracture propagation rule and the interaction between fluid flow and solid deformation are comprehensively considered, so that comprehensive evaluation and optimal development of the deep shale gas reservoir are realized.

The invention relates to the technical field of mine safety, and provides a cross-layer roadway multi-rock-stratum rigidity matching collaborative segmented supporting method which comprises the steps that plastic zone ranges of different rock stratum areas in a cross-layer roadway are determined, and rock stratum joint fissure zones and weak intercalated layers are identified; monitoring the elastic zone rigidity and the plastic zone weakening rate of the surrounding rock, constructing a surrounding rock mechanical model, obtaining the supporting structure rigidity for inhibiting the expansion of the plastic zone through the surrounding rock mechanical model, and constructing a supporting structure according to the supporting rigidity; and the reinforcing material is sprayed to the surface of the surrounding rock through high-pressure jet flow to form a protective layer. Through the cooperative control thought of weak layer control, rigidity adjustment and resistance transfer, breakthrough transformation of crossing roadway support from passive defense to active control is achieved, according to a scientific surrounding rock mechanical model, the rigidity of the support structure can effectively inhibit expansion of a plastic zone, the stability of a system is maintained, and the stability of the system is improved. And finally, an ultrahigh strength performance and gradient spraying layer structure technology is adopted, so that the compression strength and the shear strength of the surrounding rock are remarkably improved.

The embodiment of the invention relates to the technical field of rock mechanics, in particular to a rock micromechanical property determination method, device and equipment, and the method comprises the following steps: carrying out indentation test on a target area on the surface of a rock sample to obtain micromechanical response data of the rock sample; the micro-mechanical response data represents the change relationship between the micro-mechanical response of the rock sample and time; scanning a target area on the surface of the rock sample in the indentation test process to obtain microstructure evolution data corresponding to the micromechanical response data; the microstructure evolution data represents a change relationship between the microstructure of the rock sample and time; and determining the micromechanical properties of the rock sample according to the micromechanical response data of the rock sample and the corresponding microstructure evolution data. According to the embodiment of the invention, the heterogeneous micro-mechanical property of the rock can be accurately represented based on collaborative analysis of the micro-mechanical response and the microstructure of the rock sample at multiple time points, and dynamic, in-situ and quantitative representation of the micro-mechanical property of the rock is realized.

The invention discloses a rock crack evolution numerical simulation method based on data analysis, and relates to the technical field of rock mechanics engineering numerical simulation, and the method comprises the following steps: S1, obtaining microstructure data of a target rock, including a CT scanning image, an SEM image and mineral energy spectrum data; and S2, constructing a spatial distribution dynamic mechanical parameter field based on the microstructure data. According to the rock crack evolution numerical simulation method based on data analysis, a dynamic mechanical parameter field driven by a microstructure is constructed, so that the inherent defect that rock is simplified into a homogeneous material in a traditional method is overcome; microscopic characteristics such as mineral hardness gradient, grain boundary strength distribution and pore morphology are effectively quantified into an elastic modulus field, a tensile strength field and a fracture energy field which are spatially distributed, so that the numerical prediction of crack initiation and expansion truly reflects the inherent heterogeneity of the rock for the first time.

The invention relates to the technical field of underground cavern construction, and discloses a layered rock mass cavern excavation parameter dynamic optimization decision system and method, and the system comprises a rock stratum database building module, an excavation simulation module and an excavation model optimization module. The method comprises the following steps: collecting basic data such as engineering geological conditions, rock mechanical properties and ground stress distribution; establishing an initial rock stratum parameter database through a three-dimensional ground stress test and rock mass permeability characteristic analysis; establishing a stratified rock mass excavation simulation model, simulating a failure mode of a stratified rock stratum under excavation disturbance, and analyzing stress redistribution and a potential failure area; determining a cavern axis direction, an excavation sequence and support parameters according to a simulation result; acquiring surrounding rock deformation, loosening circle expansion and seepage characteristic change; and utilizing a damage proximity index to predict the distribution of the loose circles, and optimizing the stratified rock mass excavation simulation model. The method can adapt to various complex working conditions from a sand shale interbed to an ultra-deep fractured stratum and the like.

The invention relates to the technical field of rock mechanics and petroleum and natural gas engineering, and particularly discloses a hydraulic fracture fracturing monitoring system, method and device based on optical fiber monitoring, and the system comprises a hydraulic fracturing simulation platform which is used for applying three-dimensional stress to a hydraulic fracturing test piece so as to simulate a stratum stress environment; the fracturing fluid injection device is used for injecting pre-prepared fracturing fluid into the test piece, so that a crack in the test piece expands; a plurality of strain sensor groups embedded in the test piece in the preparation process of the test piece; the optical fiber sensing demodulation device is used for collecting strain data detected by the plurality of strain sensor groups; and the data processing device is in communication connection with the optical fiber sensing demodulation device and is used for acquiring the strain data and processing the strain data so as to determine real-time state data of crack expansion in the test piece. According to the scheme, the fracture strain can be monitored in real time, and the accuracy and controllability of the hydraulic fracturing process are improved.

The invention relates to the technical field of shale gas storage development and yield increase, in particular to a shale gas refracturing potential prediction method and system based on multi-modal data fusion. A data set is established according to the obtained shale gas well data, the data set comprises a multi-dimensional sequence data set and a single-valued data set, the multi-dimensional sequence data set comprises logging curve data and fracturing construction curve data, and the single-valued data set comprises geological data, reservoir physical property data, initial fracturing parameter data, production dynamic data and rock mechanics data; marking the refracturing potential of the well section through the production dynamic data; performing data cleaning and standardization processing, and dividing a data set into a training set, a test set and a verification set; and constructing a shale gas refracturing potential prediction model which meets a preset requirement and takes the multi-dimensional sequence data set and the single-valued data set as input and the refracturing effect type as output. According to the method, efficient prediction of the overall refracturing potential of the shale gas well can be realized.

The invention relates to the technical field of oil exploration, and discloses a rock mechanical parameter logging intelligent evaluation method considering continental facies shale fabric characteristics. The method comprises the following steps: 1, dividing shale lithofacies, identifying and determining the bedding development thickness of a sample through an optical microscope, determining a granularity experiment of the sample through granularity analysis, and forming mineral composition and bedding factor lithofacies division; 2, constructing a typical logging facies based on a rock electricity response relationship, and dividing the imaging logging facies of the research area according to natural gamma curves of conventional logging and imaging logging, core deposition structure characteristics and imaging logging image characteristics; 3, testing the longitudinal and transverse wave velocities and the porosity of different shale lithofacies, and calculating the dynamic elastic modulus and the Poisson's ratio. Through fine division and description, the method for accurately evaluating the bedding development condition, the particle size characteristics and the mineral components of the shale sample is provided, the testing time is short, the cost is low, and accurate evaluation of shale can be achieved.

The invention provides a reservoir in-situ key rock mechanical parameter space inversion prediction method and a reservoir in-situ key rock mechanical parameter space inversion prediction system, and belongs to the field of shale oil and gas geology, and the reservoir in-situ key rock mechanical parameter space inversion prediction method specifically comprises the following steps: carrying out a nanoindentation experiment to obtain an indentation experiment database, and simulating rock indentation experiments under different conditions to obtain a macroscopic indentation numerical model; using a Latin hypercube sampling method to obtain a simulation parameter combination database, carrying out batch numerical experiments, and constructing an inversion data set; according to the inversion data set, training the deep neural network model subjected to Bayesian optimization to obtain a single-point inversion prediction model; further establishing a spatial inversion prediction model according to a Kriging interpolation algorithm; and inputting real-time detection data of the deep rock stratum into the spatial inversion prediction model to obtain real-time underground rock mechanical parameter spatial distribution data of the deep rock mass. The deep reservoir space key rock mechanical parameters can be accurately inverted, and a basis is provided for well spacing, well trajectory design, fracturing scheme optimization and the like.

The invention discloses a method for analyzing the influence of a rock mass multi-scale structure on deep geothermal reservoir circular mining, and relates to the technical field of geothermal resource development and rock mechanics, and the method comprises the following steps: establishing a reservoir rock mass mechanical analysis model and a seepage heat transfer analysis model which simultaneously comprise a microscopic microcrack structure and a macroscopic crack structure; based on the reservoir seepage heat transfer analysis model, reservoir temperature field and seepage field analysis is carried out, and water pressure and temperature distribution results are transmitted to the mechanical analysis model; based on the reservoir mechanical analysis model, reservoir stress and deformation analysis under the heat-water-force coupling effect is carried out, and changes of microcosmic microcrack and macroscopic crack structures in the reservoir rock mass are obtained; the rock mass permeability evolution equation and the porosity evolution equation are adopted to calculate the reservoir rock mass permeability tensor and the porosity, and the reservoir rock mass permeability tensor and the porosity are transmitted to the seepage heat transfer analysis model; and solving the reservoir temperature field, the water pressure field and the mechanical response in the geothermal circulation exploitation process by adopting a seepage heat transfer analysis and mechanical analysis staggered iteration mode. By analyzing the reservoir temperature, the water pressure, the deformation evolution response and the reservoir permeability change in the geothermal exploitation process, geothermal exploitation design and protection can be reasonably carried out, and the application prospect is good.

The invention relates to the technical field of artificial intelligence, and discloses a complex stratum rock mechanics parameter prediction method, which comprises the following steps: collecting multi-source data of a complex stratum, and carrying out data preprocessing on the multi-source data; extracting physical features and statistical features related to the rock mechanical parameters based on the multi-source data, and aligning the physical features, the statistical features and the multi-source data after data preprocessing according to depth to obtain a high-dimensional feature matrix; an integrated machine learning model is constructed, the high-dimensional feature matrix is utilized to train the integrated machine learning model, the integrated machine learning model comprises a bottom layer model and a top layer model, and the bottom layer model comprises a time sequence modeling unit and a nonlinear regression unit; and optimizing model output of the integrated machine learning model based on dynamic weight adjustment and a physical constraint loss function to obtain a rock mechanical parameter prediction result. According to the method, the accuracy of complex stratum rock mechanical parameter prediction can be improved.

The invention relates to the technical field of rock mechanical tests and safety monitoring, and discloses a rock fracture prediction method based on acoustic emission and surface strain cooperative monitoring, and the method comprises the steps: building a monitoring system comprising acoustic emission and an industrial camera array, and building a unified timestamp of each subsystem through a GPS time service module; through load triggering logic, a synchronous trigger is utilized to synchronously acquire an acoustic emission signal and a sample surface image sequence, and evolution characteristics of three-dimensional coordinates of an acoustic emission source and surface full-field strain data are solved. And on the basis, calculating a main strain field variation coefficient, and performing cross-correlation analysis on the resampled energy rate and strain rate. And finally, according to multi-parameter coupling criteria of acoustic emission time sequence parameters, positioning events and surface strain, identifying rock fracture precursor types, and predicting fracture moments and areas by combining a Voight model inverse velocity method and a seismic source projection technology.

The invention relates to a strong mining roadway thick-layer transboundary supporting method, and belongs to the technical field of roadway supporting, and the method comprises the steps that geometric parameters, rock mass mechanical parameters and stress field parameters of a strong mining roadway are obtained; based on the geometric parameters, the rock mass mechanical parameters and the stress field parameters, the deformation process and the damage process of the strong mining roadway surrounding rock are simulated, and the incidence relation between each deformation stage of the strong mining roadway surrounding rock and the roof partition damage characteristic is obtained; determining a key stage of irreversible deformation of the strong mining roadway surrounding rock based on the association relationship; determining the critical time of transboundary anchoring of the thick layer based on the key stage; determining the support parameters of the anchor rod and the critical anchoring length of the thick layer transboundary; and supporting the top plate of the strong mining roadway based on the critical time, the supporting parameters and the thick-layer transboundary anchoring length. The method has the effect of improving the stability of the strong mining roadway surrounding rock.

The invention relates to the technical field of crustal stress measurement, in particular to a rock core three-dimensional crustal stress measurement system and method based on multi-source data. The method comprises the following steps: acquiring well wall damage information, and identifying a damage type in the well wall damage information; multiple sections of core samples are selected based on the well wall damage information, and overburden pressure parameters are determined based on the multiple sections of core samples; a rock mechanics experiment is conducted on the rock core sample, rock mechanics parameters are generated, and the rock mechanics parameters comprise the Poisson's ratio, the Young modulus, the uniaxial compressive strength value and the tensile strength value. According to the method, the difference value of the maximum stress and the minimum stress is combined with the multi-source coupling constraint principal stress interval, the intersection points are identified through the topological visualization graph, the numerical range of the maximum principal stress and the minimum principal stress can be accurately determined, and then the information of the three-dimensional crustal stress is obtained.

The invention relates to the technical field of geomechanical data research, in particular to a geomechanical data visualization method and system based on a mixed data model. According to the technical scheme, the method comprises the steps of data collection and arrangement, mixed data model construction, visual algorithm design and application and visual result display and interaction. The data collection and arrangement comprises the step of collecting geomechanical data including geologic structure data, rock mechanics parameter data and ground stress data. According to the method, geologists can be assisted to deeply understand the complex relationship between geologic structure evolution and rock mechanical behaviors, and powerful data visualization support is provided for development of geologic theories; geological risks can be predicted in advance, an engineering design scheme is optimized, and engineering safety and economic benefits are improved; through accurate visualization and deep analysis of geomechanical data, the possibility and the potential influence range of disaster occurrence can be evaluated more accurately, and key technical support is provided for disaster early warning and prevention and control measure formulation.

The invention discloses a coal rock mass creep disturbance test method, which belongs to the technical field of rock mechanics and engineering, and comprises the following steps: S1, carrying out a conventional compression test, and determining creep and disturbance test parameters; s2, carrying out a graded loading creep test; s3, carrying out a creep disturbance test; applying a disturbance load to the test piece according to creep and disturbance test parameters, and monitoring stress, strain, damage evolution and instability failure characteristics of the test piece under the action of dynamic load disturbance; judging the next test process according to the deformation evolution rule of the test piece after each disturbance; and S4, determining a strength limit neighborhood of the test piece under the action of creep and disturbance according to a test result. According to the method, key information such as the deformation rule, the instability failure characteristic and the strength limit of the coal rock mass can be disclosed, then the damage evolution rule, the strength limit and the instability mechanism of the coal rock mass under the creep action and the dynamic load disturbance action are researched, and scientific basis and technical support are provided for stability prediction and control of engineering rock mass in engineering practice.

The invention provides a numerical simulation method and system based on rock mass fracture extension and seepage coupling, and belongs to the field of rock mechanics. Rock is regarded as a set composed of particles and mechanical contact between the particles, and a triangulation network is constructed based on the circle center of each particle; according to the geometrical characteristics of the triangulation network, a seepage pipeline network containing the interior and the periphery is built, and network nodes and boundary nodes are determined; calculating the permeability coefficient according to the particle positions on the two sides of the pipeline, and forming a penetrating seepage channel and fracture network by taking the pipeline which is not 0 and penetrates through and is connected with boundary nodes as a passage pipeline; and constructing a flow conservation equation set based on network nodes, solving pore pressure by using a Jacobian iteration method, calculating fracture pressure, and applying the fracture pressure to the model to realize coupling of a stress field and a seepage field. According to the method, the advantages of particle discrete elements in calculation of rock mass fracture extension and the advantages of a pipeline network method in calculation of fracture seepage are fully exerted, and accurate simulation of rock mass fracture initiation extension, seepage channel recognition and seepage field calculation is achieved.

A rock breaking efficiency prediction method based on image recognition and machine learning comprises the following steps: acquiring a rock surface image, performing graying processing by applying an image processing technology, and then performing pixel classification and image segmentation so as to clearly divide different minerals into a plurality of independent structure diagrams; modeling a rock material according to mineral components, importing boundary information of the plurality of structure diagrams into a model, generating a plurality of large-particle filled rock blocks with the same size as the plurality of structure diagrams, and calibrating mesoscopic parameter values according to rock mechanical characteristics; establishing a hob rock breaking discrete element calculation model, and performing multiple intrusion rock breaking simulation tests on rock samples with different mineral contents; collecting simulation results to construct a rock breaking efficiency data set; a prediction model is established based on a PSO-BPNN algorithm, and a rock breaking efficiency prediction model is obtained after training; and carrying out real-time prediction on the rock breaking efficiency by utilizing the established model. According to the method, the influence of rock mineral components on the rock breaking effect of the hob is considered, and efficient and accurate prediction of the rock breaking efficiency of the hob is realized by utilizing a method of combining rock microscopic components and macroscopic rock breaking behaviors.

The invention belongs to the technical field of rock mechanics and oil and gas development, and particularly relates to a deep shale rock mechanics and fracture evolution characteristic collaborative testing system and method.The system comprises a full-diameter triaxial autoclave, a hydraulic fracturing experiment mechanism, a high-temperature fracture experiment mechanism, a strain monitoring mechanism and an acoustic emission signal monitoring mechanism; the method comprises the following steps: carrying out a mechanical property test, a thermal cracking characteristic experiment and a hydraulic fracturing experiment on the same shale, analyzing a thermal cracking process and a hydraulic fracturing process, analyzing and speculating generation positions, generation time and complexity of thermal cracking cracks and hydraulic fracturing cracks of the shale, and the like. According to the invention, the real occurrence environment of the deep shale reservoir is simulated, the shale mechanical property test is carried out, the generation of high-temperature shale thermal cracking micro-cracks and the crack extension or development state in the hydraulic fracturing process are monitored, a crack evaluation method is provided, and data support is provided for improving the high-temperature thermal cracking and hydraulic fracturing effects of the deep shale.

The invention relates to the field of geotechnical engineering and rock mechanics research, in particular to a bolt-grouting joint shear failure evolution monitoring method and system based on three-dimensional scanning, and the method comprises the steps: carrying out the multi-view three-dimensional scanning of a target rock mass at different load stages, and obtaining a time-sharing three-dimensional point cloud reflecting crack dislocation and surface deformation; and multi-modal data collected by a strain sensor, a vibration sensor and the like are input into a multi-scale feature extraction algorithm to generate automatic regulation and control parameters for the grouting pressure and the load mode. During application, a researcher can dynamically adjust a grouting scheme or a load strategy, and the whole crack propagation process is displayed by using a three-dimensional deformation diagram and a crack distribution diagram, so that the monitoring process is more visual and operable. According to the method, the key damage symptom of the rock mass in the loading process can be captured, the plugging effect of bolting and grouting can be effectively evaluated, and more visual and accurate data support is provided for rock mechanics research and engineering field reinforcement decision making.

The invention provides a hydraulic fracturing crack propagation simulation method and device and electronic equipment, and the method comprises the steps: obtaining the ground stress field distribution of each fracturing section through a geomechanical model according to the geological parameters, logging interpretation and rock mechanics experiment data of a target area fracturing section; utilizing an induced stress field model to simulate induced stress distribution of each fracturing section; obtaining comprehensive crustal stress field distribution according to the crustal stress field distribution and the induced stress distribution; the theoretical crack initiation pressure of each perforation cluster of each fracturing section is calculated according to the comprehensive crustal stress field distribution by means of a perforation cluster crack pressure model, perforation cluster crack initiation data of each fracturing section are determined according to the theoretical crack initiation pressure and the actual crack pressure, and the perforation cluster crack initiation data comprise the perforation cluster crack initiation state and the perforation cluster crack initiation number; and utilizing the multi-cluster crack propagation model to obtain a crack propagation trajectory simulation result according to perforation cluster crack initiation data and an actual pump injection program. According to the method and the device, hydraulic fracture expansion of segmented multi-cluster fracturing can be accurately simulated.

The invention relates to a nanoscale grouting method for illite-smectite mixed layer surrounding rock, which is characterized by comprising the following steps of: S1, combined detection of a borehole television and a ground penetrating radar or a geological radar: carrying out rock mass structure detection in a manner of combining the borehole television and the ground penetrating radar or the geological radar, and obtaining a deformation rule of a roadway and surrounding rock in an area; s2, arranging grouting pipes and an exhaust pipe: arranging two long and short grouting pipes and one exhaust pipe in the grouting hole according to the deformation rule of the roadway and the surrounding rock in combination with numerical simulation of rock mass mechanics and the result of the numerical simulation; s3, grouting is conducted, specifically, grouting is conducted in a deep and shallow hole matching grouting mode; s4, secondary splitting grouting reinforcement is conducted, specifically, the mine illite-smectite mixed layer surrounding rock is reinforced through a secondary splitting grouting technology, the unfilled part in the primary grouting process is made up, and it is ensured that all gaps are filled with grout; and the illite smectite mixed layer surrounding rock can be grouted well.

The invention provides a rock failure short-term and temporary early warning method and device based on acoustic emission clustering analysis, and relates to the technical field of rock mechanics and geotechnical engineering. The method comprises the following steps: acquiring acoustic emission characteristic parameters in a rock deformation and failure process; carrying out clustering analysis on the acoustic emission characteristic parameters by adopting a Kmeans + + algorithm to obtain clustering labels corresponding to the acoustic emission characteristic parameters; according to the clustering labels, a random forest algorithm is adopted, and importance scores of the acoustic emission characteristic parameters are calculated; constructing an early warning index set according to the acoustic emission characteristic parameters; an initial CNN-LSTM model is constructed; according to the early warning index set, establishing a sample data set of the rock failure conventional signal and the precursor signal; the initial CNN-LSTM model is trained according to the sample data set, and a trained CNN-LSTM model is obtained; acquiring a real-time acoustic emission signal; and inputting a real-time acoustic emission signal into the trained CNN-LSTM model, and carrying out early warning by identifying the category of the acoustic emission signal. According to the invention, early warning can be carried out in the rock complex damage process.

The invention discloses a deep tunnel surrounding rock mechanical parameter inversion method based on a three-dimensional brittle failure zone contour and sparrow optimization algorithm-information vector machine (SSA-IVM) combined optimization algorithm. The engineering technical problem that due to the fact that excavation instantaneous displacement is difficult to monitor, deep tunnel surrounding rock mechanical parameters are difficult to reasonably obtain through displacement back analysis is solved. The method comprises the following steps: firstly, constructing a tunnel FLAC3D numerical simulation model with the same ground stress condition at the occurrence position of a three-dimensional brittle failure zone; secondly, taking an absolute error between the total number of computational grid units in the actually measured brittle failure zone and the total number of computational grid units entering a plastic state in the range of the actually measured brittle failure zone after calculation of the FLAC3D numerical model as an optimization objective function; and then, by taking the tunnel surrounding rock mechanical parameters as optimization variables and taking a target function reaching a global minimum value as a target, performing global optimization by combining a tunnel FLAC3D numerical model and adopting an SSA-IVM joint optimization algorithm, thereby obtaining reasonable tunnel surrounding rock mechanical parameters.

The invention provides a fracture deformation-seepage cross-scale visualization experiment device and a test method, and relates to the technical field of hydraulic rock mechanics and measurement. Comprising a macroscopic observation assembly, a microscopic observation assembly, a microscopic seepage model, a temperature-stress-seepage loading system, a monochromatic coaxial light source and a data acquisition and analysis system, the microscopic seepage model is used for placing a fractured rock mass; the temperature-stress-seepage loading system is used for injecting fluid with fluorescent microspheres into the microcosmic seepage model, applying load, regulating and controlling temperature and collecting data; the data acquisition and analysis system is used for processing data and images. By arranging the macroscopic observation assembly and the microcosmic observation assembly, double-scale synchronous observation is achieved, the whole process of fracture internal fluid interface evolution and rock mass deformation can be obtained in real time under the multi-physics field coupling conditions of temperature, stress, seepage and the like, visual correlation of deformation, flow and stress is achieved, and the measurement accuracy is improved. And an experimental basis is provided for establishing a fracture multi-field coupling mechanism model.

A deep engineering hard rock true triaxial dynamic disturbance aging fracture testing device belongs to the technical field of rock mechanics tests and comprises a counter-force frame, a pressure chamber and six main stress linear disturbance actuators. The main stress linear disturbance actuator comprises a linear disturbance motor and a main stress hydraulic cylinder; the linear disturbance motor is coaxially and fixedly installed at the outer end of a cylinder barrel of the main stress hydraulic cylinder, a dowel bar is arranged in a central hole channel of a piston rod of the main stress hydraulic cylinder, and a power output shaft of the linear disturbance motor is coaxially and fixedly connected with the dowel bar. According to the utility model, the matching form of a traditional dynamic actuator and a hydraulic oil source is abandoned, the linear motor is introduced into the true triaxial test equipment as a power disturbance source, the long-time dynamic disturbance structure of the true triaxial test equipment is simplified, and the energy consumption of the equipment is greatly reduced after the linear motor is used as the power disturbance source; the maintenance process is simpler, the maintenance cost is greatly reduced, the installation and debugging processes of the linear motor are more time-saving and labor-saving, and no extra floor area is needed.

The invention discloses a numerical simulation method and device for seepage heat transfer of a three-dimensional rough fractured rock mass, and relates to the technical field of rock mechanics engineering.The dynamic opening degree of the fractured rock mass is obtained by combining the initial opening degree and the equivalent opening degree of the fractured rock mass, and in the process of obtaining the dynamic opening degree of the fractured rock mass, the dynamic opening degree of the fractured rock mass is obtained. According to the method, based on the initial opening and the equivalent opening, the coupling influence of the shear expansion effect and roughness degradation on the fracture opening under the action of shear stress is quantified, and then based on the dynamic opening of the fractured rock mass, the point cloud data of the upper and lower fracture surfaces of the fractured rock mass after shearing is updated; the dynamic updating of the three-dimensional geometrical morphology of the real fracture in the shearing process is realized, and the bidirectional coupling simulation of the seepage field and the temperature field is realized based on the three-dimensional geometrical morphology data of the real fracture, so that the precision of the seepage heat transfer numerical simulation of the fractured rock mass is improved.