100 results about "Rock failure" patented technology

The present invention relates to the technical field of tunnel rockburst microseismic monitoring, and provides a strain-structural plane slip-type rockburst failure mechanism analysis method for a drill-and-blast method tunnel. The present invention collects strain-structural plane slip-type rockburst microseismic data during tunnel construction; in light of engineering geological survey data, performs microseismic monitoring and data analysis on strain-structural plane slip-type rockburst that has occurred in a tunnel, divides a strain-structural plane slip-type rockburst risk area, and determines a microseismic rockburst early warning area; and, by means of these data, deeply understands a microseismic activity law of strain-structural plane slip-type rockburst of deep-buried drill-and-blast method tunnels, discriminates respective functions of tensioning and shearing in rock failure processes, comprehensively analyzes the failure mechanism of strain-structural plane slip-type rockburst, and further obtains the failure mechanism of strain-structural plane slip-type rockburst of the deep-buried drill-and-blast method tunnels, providing an important theoretical basis for predicting and preventing rockburst disasters.

The invention discloses a deep well rock mass instability failure time accurate forecasting and early warning system, and relates to the technical field of deep well rock mass failure early warning, and the deep well rock mass instability failure time accurate forecasting and early warning system comprises the following steps: collecting a plurality of deep well rock samples to carry out a uniaxial compression experiment, and collecting acoustic emission signals in real time based on an acoustic emission sensor to obtain original acoustic emission signal data; carrying out self-adaptive preprocessing, and carrying out data classification and integration to obtain rock sample acoustic emission parameter data; constructing an original damage forecasting model, and performing model training and verification optimization based on the rock sample acoustic emission parameter data to obtain a rock damage forecasting model; collecting an acoustic emission signal of the deep well rock mass, and predicting the instability failure time of the deep well rock mass in real time based on the rock failure forecasting model; the method is used for solving the problems that when an existing deep well rock mass damage early warning technology carries out early warning on rock mass instability damage through acoustic emission monitoring, single or few characteristic parameters are manually processed and analyzed, and the early warning reliability and timeliness are not high.

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 relates to the technical field of computers, and discloses a rock creep model construction method and device and a rock failure mode determination method. The method comprises the steps of obtaining a data set; samples in the data set comprise input data and output data, the input data comprise creep load holding time, sample rock stress data, initial macroscopic damage data, initial microscopic damage data, long-term strength and a creep starting threshold value, and the output data is a strain true value; fitting the initial rock creep model by using the data set to obtain a final rock creep model; wherein the initial rock creep model comprises at least one of a damaged elastomer strain item, a damaged viscoelastomer strain item and a damaged viscoplastic body strain item; each strain item comprises a macro-micro nonlinear coupling damage item, and the macro-micro nonlinear coupling damage item is generated based on the initial micro damage data and the initial macro damage data. The model constructed by the method can truly reflect the nonlinear mechanical response of the rock mass under the combined action of the multi-scale initial defects.

The invention discloses a method and a system for distinguishing water-endowed surrounding rock failure of underground engineering, and the method comprises the steps: obtaining water pressure change data of water-endowed surrounding rock, calculating a stress field change trend in combination with a preset stress distribution model, and simulating a micro-fracture extension process by adopting a fracture extension model; based on the fracture extension simulation result and the physical properties of the surrounding rock, the nonlinear characteristics of fracture extension are judged; analyzing the influence of water pressure fluctuation on surrounding rock permeability characteristics, correcting fracture extension model parameters according to the influence, and recalculating a dynamic process; a multi-dimensional discrimination model of surrounding rock failure is constructed by adopting multi-field coupling analysis, a critical state is dynamically captured in combination with time evolution data, and a failure development trend is predicted by applying a nonlinear dynamics algorithm. According to the method, through multi-dimensional data analysis and model iterative optimization, accurate simulation and prediction of the surrounding rock failure process under complex geological conditions are realized, and important technical support is provided for engineering safety.

The invention provides a reservoir mechanical integrity evaluation method under high-frequency injection and production. The evaluation method comprises the steps that S1, rock sample compressive strength and mechanical property parameters of a reservoir under multiple confining pressures are determined; s2, determining the upper limit and the lower limit of the reservoir pressure of the energy storage reservoir in the injection-production process; s3, obtaining the critical fatigue strength of the reservoir rock sample under a plurality of confining pressures within the designed age limit; s4, determining a deviating stress-average stress plane according to the compressive strength and the critical fatigue strength of the rock sample under the plurality of confining pressures, and dividing rock failure zones on the deviating stress-average stress plane; and S5, establishing a geomechanical model to predict the stress level of the reservoir, and judging the safety of the reservoir during the cyclic injection-production period from the perspective of mechanical integrity. Safe, efficient, economical and lasting operation of the energy storage warehouse is guaranteed, and a feasible method is provided for expanding the application range of compressed air energy storage.

The invention provides a fractured rock damage prediction method and system, and belongs to the field of rock mechanics and engineering monitoring. The problem that a prediction result obtained by an existing fractured rock damage prediction method is not accurate is solved. According to the technical scheme, the method comprises the following steps: synchronously obtaining a DIC image sequence and an acoustic emission signal in a loading process of a to-be-measured fractured rock, carrying out data processing to generate a gray variance evolution curve and an acoustic emission b value evolution curve, and extracting a gray variance surge point on the gray variance evolution curve and a b value surge point on the acoustic emission b value evolution curve; performing time sequence comparison on the gray variance sharp increase point and the b value sudden drop point on a time axis, and when the gray variance sharp increase point and the b value sudden drop point meet a preset consistency condition on the time axis, judging the corresponding gray variance sharp increase point or b value sudden drop point as a damage critical point of the fractured rock; the method is applied to rock failure prediction.

The invention discloses a test method for overlying strata joint fault instability induced by supercritical CO2 injection, and aims to solve the technical problems that the overlying strata instability process caused by supercritical CO2 injection cannot be effectively simulated under true triaxial stress at present, and CO2 geological storage and development of oil and gas reservoirs are severely hindered. A true triaxial device is used for applying three-way unequal stress, supercritical CO2 is injected by a high-precision high-pressure pump according to a constant rate or flow until the rock is damaged, and the unstability mechanism of the joint fault of the cover layer under different conditions is systematically explored. According to the test method for inducing the unstability of the joint fault of the cover layer by the supercritical CO2 injection, the evolution law of the joint fault of the cover layer by the CO2 injection can be intuitively and accurately observed, the unstability mechanism of the cover layer under a real reservoir condition is comprehensively simulated, scientific and reliable theoretical support and technical guidance are provided for related engineering practice, and the test method has important application value.

The invention relates to the technical field of thermocycling damage treatment, in particular to a granular rock thermocycling damage prediction method, which comprises the following steps: establishing a particle-based numerical model by using discrete element software; setting initial temperature and confining pressure of the rock sample, and constructing a heating, balancing and cooling experiment process; setting different preset temperature values and temperature rising and cooling step lengths; elastic modulus damage and crack number development are obtained; thermal damage is calculated through elastic modulus damage and crack number development, the relation between rock volume thermal strain and rock heating-cooling damage under different confining pressures is obtained, and a damage prediction model of rocks under different confining pressures under the cold and heat cycle condition is constructed. Aiming at the rock damage problem caused by rock heating expansion and cooling shrinkage, the thermal damage and volume thermal strain model considering heating and cooling is constructed, and the universality of the model is high.

This invention provides a method and device for short-term early warning of rock failure based on acoustic emission clustering analysis, relating to the fields of rock mechanics and geotechnical engineering. The method includes: acquiring acoustic emission characteristic parameters during rock deformation and failure; performing clustering analysis on the acoustic emission characteristic parameters using the K-means++ algorithm to obtain cluster labels corresponding to the acoustic emission characteristic parameters; calculating the importance scores of the acoustic emission characteristic parameters based on the cluster labels using the random forest algorithm; constructing an early warning index set based on the acoustic emission characteristic parameters; constructing an initial CNN-LSTM model; establishing a sample dataset of conventional and precursor signals of rock failure based on the early warning index set; training the initial CNN-LSTM model using the sample dataset to obtain a trained CNN-LSTM model; acquiring real-time acoustic emission signals; and inputting the real-time acoustic emission signals into the trained CNN-LSTM model to provide early warning by identifying the acoustic emission signal category. This invention can provide early warning for complex rock failure processes.

The invention relates to a rock mechanics testing method and system based on artificial intelligence, and the method comprises the steps: carrying out the three-dimensional scanning of a rock sample, and obtaining three-dimensional model data; sending into a convolutional neural network to analyze the surface characteristics of the rock sample, and obtaining the initial state parameters of the rock sample; according to the initial state parameters, a rock mechanics test loading scheme is formulated through an adaptive optimization algorithm, and a test execution instruction is obtained; applying a preset load to the rock sample according to the test execution instruction, and synchronously acquiring mechanical response data and a deformation image sequence; according to the deformation image sequence, constructing a full displacement field and a strain field of the rock sample, and obtaining global deformation characteristics; and based on the global deformation characteristics and the mechanical response data, identifying damage behavior parameters of the rock sample through a time sequence characteristic extraction algorithm, and obtaining a damage type. Intellectualization, data closed loop and self-evolution of the whole rock mechanics test process are achieved, and the test precision and the reliability of rock damage prediction are improved.

This invention belongs to the fields of rock mechanics, signal processing, and deep learning. It provides an intelligent method, device, equipment, and medium for identifying rock fracture types. The method includes: acquiring acoustic emission signal data, loading stress-strain data, and rock image / video of the rock sample; extracting multimodal features from the acoustic emission signal data and loading stress-strain data; performing principal component analysis on the multimodal features to obtain a dimensionality-reduced feature matrix; labeling training data using a rock failure event time-series correlation method to obtain crack type labels; training and detecting using a gated recurrent unit network based on the dimensionality-reduced feature matrix and crack type labels to obtain a shear crack probability sequence, and then calculating the tension-shear ratio within a time step; and generating time stamps in the rock image / video based on the tension-shear ratio. This invention achieves accurate and rapid identification of rock fracture types and real-time monitoring of the dynamic evolution of fractures.

The invention discloses a rock material tension-shear failure simulation method and equipment based on a dynamic dual-phase field model. The method comprises the following steps: establishing a stress tensor physical model corresponding to a rock material constitutive relationship; respectively introducing a tension phase field and a shear phase field, and establishing a dynamic double-phase field model corresponding to the rock tension-shear failure physical process; deducing an energy functional of the dynamic double-phase field model; establishing a crack surface local coordinate system, and judging a crack contact state according to a frictional contact phase field theory; switching a stress tensor decomposition mode according to the contact state, and calculating a phase field evolution driving force; rock material tension-shear failure simulation based on the dynamic two-phase field model is achieved, and rock fracture form evolution data are output and used for evaluating rock slope stability.

The application discloses a rock residual strength determination method based on an energy drop ratio parameter and belongs to the technical field of geological engineering. According to a rock stress-strain curve obtained through a rock triaxial test, the energy of each component in a failure process is calculated according to the rock stress-strain curve characteristics, and based on the energy evolution law in the rock failure process, an energy drop ratio parameter is proposed to quantitatively represent the strength drop. A residual strength determination method considering the whole rock failure process is proposed through the energy drop ratio parameter. The application comprehensively considers the influence of the pre-peak stage and the post-peak stage on the residual strength, proposes a rock residual strength determination method suitable for different post-peak drop trends, and calculates the stability of the broken rock mass through the residual strength, which has an important guiding role for the excavation, design and stability evaluation of the rock mass engineering.

The present invention discloses a uniaxial compression damage model of rock considering the mechanical behavior of microcracks, which reflects that rock failure is caused by the slip and propagation of microcracks. According to the microcrack slip model and the principle of energy balance, the uniaxial compression stress-strain relationship of rock is established, and it is considered that microcracks obey the Weibull distribution model. Furthermore, taking the strain energy density criterion as the microcrack propagation criterion, the iterative method is used to solve the propagation length of the wing crack in the mixed-mode fracture, and the evolution equation of the rock damage variable expressed by the propagation length of the wing crack is obtained. Thus, a uniaxial compression damage model of rock is proposed and its rationality is verified. The influence of microcrack length, friction coefficient and rock fracture toughness on the mechanical properties of rock is studied by parameter sensitivity analysis. The research results show that the macroscopic mechanical properties of rock are the macroscopic manifestation of its mesoscopic mechanical parameters. Therefore, the rock damage constitutive model established from the mesoscopic perspective can better reveal its deformation and failure mechanism and has good application prospects.

The embodiment of the present invention discloses a quantitative evaluation method of the rock-breaking effect of explosion stress wave and blasting gas, and a rock blasting method, wherein the evaluation method includes: setting a plurality of relative position relationships between explosives and blastholes, wherein the explosives are located in the blastholes and there is a cavity between the explosives and the blasthole wall, and the volume of the cavity between the explosives and the blasthole wall in the direction of the measured position of the rock under different relative position relationships is different; for each relative position relationship: placing the explosives at the corresponding position in the blasthole, using the explosion effect of the explosives in the blasthole to apply a load to the rock to destroy the rock; based on the stress conditions and / or damage conditions of the measured position of the rock during the rock destruction process under various relative position relationships, the rock-breaking effect of the explosion stress wave and the blasting gas is quantitatively evaluated. The embodiment of the present invention can be applied to the experimental scene of the study of the action mechanism of the explosion stress wave and the blasting gas, and realizes the accurate identification and quantification of the rock-breaking effect of the coupling of the explosion stress wave and the blasting gas.

The invention provides a geophysical prospecting-drilling combined inversion method and system for a roadway surrounding rock loosening circle, and aims to solve the problem that the existing roadway surrounding rock loosening circle range detection is not accurate and comprehensive enough, improve the detection precision and efficiency, and provide a basis for roadway support design and safety maintenance. The method comprises the following steps: geophysical prospecting is carried out on top and bottom plates and two sides of a roadway by using a geological radar, data processing and preliminary detection are completed, and an approximate range of a loose circle is determined; selecting a representative position for drilling, analyzing the surrounding rock damage and crack conditions by means of a drilling peeping instrument, and judging the surrounding rock damage depth. And comparing the borehole peeping data with a geological radar preliminary detection result, constructing a target function through a least square method, and solving and correcting geological radar parameters. And scanning the roadway again by using the corrected parameters, importing secondary scanning data and drilling peeping data into professional software, constructing and visualizing a three-dimensional model of the roadway surrounding rock loose circle, and visually displaying information such as the shape, the size and the depth of the loose circle. The advantages of geophysical prospecting and drilling are integrated, the detection precision is effectively improved, roadway detection is comprehensively covered, a reliable basis is provided for roadway support design and safety maintenance, and meanwhile cost and time are saved.

The invention discloses a coal rock failure characteristic quantification method and device, equipment, a medium and a crack visualization tool, and relates to the technical field of coal rock detection.The method comprises the steps that graying processing is conducted on a coal rock image, and a gray image is obtained; carrying out binarization processing on the grayscale image to obtain a binarized image; and calculating the opening degree of each crack and the average characteristic size of the cracks of the coal rock image according to the pixel-level pores in the binarized image, thereby realizing accurate quantification of coal rock damage.

The invention discloses a three-dimensional failure criterion construction method considering bedding and three-dimensional stress and intermediate principal stress effect degradation, and the method comprises the steps: S1, obtaining rock strength data through true triaxial static tests under different bedding dip angles, direction angles and intermediate principal stress; s2, constructing a transverse isotropic strength characteristic function based on the spatial relationship between the bedding structure and the loading direction; s3, introducing an intermediate principal stress degradation parameter, and establishing a rock failure criterion considering three-dimensional stress and intermediate principal stress effect degradation; s4, constructing a three-dimensional failure criterion considering bedding space and three-dimensional stress and intermediate principal stress effect degradation; s5, determining model parameters by fitting static test data, and drawing a strength evolution curve; and S6, based on the three-dimensional failure criterion parameters, drawing a stratified rock strength prediction curve. According to the method, quantitative characterization of true three-dimensional stress, middle principal stress degradation and bedding three-dimensional space effect coupling of the strength of the layered rock is achieved for the first time.

The invention discloses a test method and system of an indoor model for ultra-large-span cavern excavation support and a medium, and relates to the technical field of geotechnical engineering physical model tests. Through the counter-force frame and the three-dimensional gradient active loading system, a real non-uniform three-dimensional crustal stress field is precisely restored. By means of a numerical control mechanical arm carrying a head-replaceable end effector, a finish-milling cutting head and a negative pressure suction system, extra disturbance of excavation to surrounding rock is reduced. Excavation and support triggering conditions are preset to control actuator tool switching, and excavation-support time sequence linkage is achieved. Through cooperative acquisition and analysis of a pre-embedded sensor, monitoring equipment around a model box and a multi-source data acquisition cabinet, full-dimensional data is obtained, and the finally constructed four-dimensional surrounding rock failure evolution comprehensive map completely presents the whole process from microscopic crack initiation to macroscopic instability. And a high-fidelity test basis is provided for risk pre-judgment and design optimization of a super-large-span cavern project.

The present invention belongs to the technical field of deep formation drilling and completion, and discloses a method for quantitatively analyzing the probability of mixed multi-criterion collapse pressure based on GMM, which includes collecting samples of geomechanical parameters and performing standardization processing; conducting cluster analysis on the standardized data of the geomechanical parameter samples; constructing a parameter uncertainty quantification model in combination with the geomechanical parameter samples; constructing a wellbore stability evaluation model based on the wellbore stress distribution and different rock failure criteria, and setting the probability weight coefficients of different criterion models; randomly generating N groups of sampling data based on the parameter uncertainty quantification model and calculating the wellbore collapse pressure; and quantifying the probability result of the collapse pressure in combination with the Monte Carlo method. The present invention can use the geomechanical parameter samples to realize the quantification of the high-dimensional joint probability distribution of the parameters, and further combine multiple failure criteria to construct a multi-criterion collapse pressure probability model for the wellbore, thereby effectively improving the efficiency of the uncertainty quantification work of the wellbore collapse pressure.

The invention discloses a chamber excavation surrounding rock failure area simulation method and related equipment, and relates to the field of geotechnical engineering stability evaluation.The method comprises the steps that an underground chamber excavation process is simulated through an underground chamber initial model without setting support measures, a plastic zone range is obtained, and principal stress information of a corresponding unit of a failure area is extracted; calculating the damage degree of the surrounding rock based on the surrounding rock stress state; performing zoning operation on the damage area according to the surrounding rock damage degree to obtain refined zoning information; on the basis of a triaxial compression test, rock mechanical parameters related to the residual strength of the surrounding rock under different damage degrees are obtained; assigning values to different partitions with different damage degrees according to the rock mechanical parameters related to the residual strength; and excavation numerical simulation is conducted again to obtain a new plastic zone range and main stress distribution, and final partition assignment and refined simulation are completed. According to the method, the authenticity, engineering adaptability and reliability of numerical simulation are improved, and the method has clear technical progress and engineering practical value.

The invention provides a surrounding rock staged failure semi-analytical solution method and system suitable for tunnel water gushing, and belongs to the technical field of tunnel engineering. The method comprises the steps that according to test data under different water contents, all surrounding rock mechanical parameters are fitted, and a surrounding rock mechanical parameter fitting equation considering the water contents is obtained; the three-dimensional arch effect in the tunnel excavation process is considered, and the surrounding rock damage process caused by tunnel excavation is divided into two stages, namely the first stage and the second stage; in the first stage, the surrounding rock failure mode is that the first stress of the excavation effect is redistributed; in the second stage, the surrounding rock failure mode is that stress is redistributed again under the combined action of the excavation effect and the water weakening effect; and for the second stage, establishing a circular tunnel calculation model considering the water weakening effect, and performing mechanical calculation on the surrounding rock failure process by adopting a semi-analytical method. Through two-stage division, the excavation effect and the water weakening effect are considered, and the progressive failure characteristics of the surrounding rock under the water gushing condition are described more accurately.

The embodiment of the present application provides a kind of unconventional oil and gas reservoir brittleness evaluation method, device, equipment, medium and product, it is related to unconventional oil and gas reservoir exploration and development technical field.Aiming at the problem that the brittleness evaluation of current unconventional oil and gas reservoir is not well matched with reservoir reconstruction effect, a brittleness evaluation method according to reservoir rock failure energy and deformation behavior is proposed to realize the quick and accurate evaluation of reservoir rock brittleness, and provide theoretical guidance for the selection of fracturing target reservoir and fracturing scheme design.The present application uses the basic principle that the greater the rock brittleness, the smaller the energy consumed by the rock under uniaxial / triaxial compression and the smaller the rock deformation, combines the uniaxial / triaxial compression failure energy of rock with the deformation of rock at the time of failure, obtains the compression failure energy and deformation parameters of rock using the stress-strain curve of rock, and evaluates the brittleness of reservoir rock by the deformation size under unit energy when rock fails.

The invention discloses a rock residual strength determination method based on energy drop ratio parameters, and belongs to the technical field of geological engineering. According to a rock stress-strain curve obtained by a rock triaxial test, energy of each component in the damage process is calculated according to characteristics of the rock stress-strain curve, and based on an energy evolution rule in the rock damage process, an energy drop ratio parameter is proposed to quantitatively characterize strength drop; a residual strength determination method considering the whole rock damage process is provided through an energy drop ratio parameter; according to the method, the influence of the pre-peak stage and the post-peak stage on the residual strength is comprehensively considered, the rock residual strength determination method suitable for different post-peak descending trends is provided, the stability of the fractured rock mass is calculated through the residual strength, and the method has an important guiding effect on excavation, design and stability evaluation of rock mass engineering.

The utility model belongs to the technical field of stone sample Poisson's ratio measurement, and discloses an auxiliary device for measuring the Poisson's ratio of a stone sample, so as to solve the problems that the measurement precision is influenced and the number of measurement points is small in the prior art, the device comprises an installation ring, six installation plates are uniformly distributed on the installation ring along the circumferential direction, the six installation plates are divided into three groups, each group of mounting plates are arranged oppositely, sliding sleeve frames with adjustable height positions are arranged on the mounting plates, dial gauge mounting ports are formed in the upper ends of the sliding sleeve frames, and limiting clamping caps for fixing dial gauges are movably arranged at the tops of the sliding sleeve frames. According to the rock Poisson's ratio measuring device, the multi-point precision measurement can be realized, a plurality of groups of dial indicators are arranged, a plurality of test point positions are formed by contact points of the dial indicators and a rock sample, and stress-deformation data of a plurality of different positions can be recorded and analyzed before the rock is damaged, so that the measurement precision of the rock Poisson's ratio is improved. And errors caused by measurement by using a magnetic gauge stand are avoided.

The present invention provides an intelligent method for distinguishing rock failure modes based on unique microseismic signals, which includes collecting the original microseismic waveforms of known rock failure modes, extracting the characteristic parameters in the time domain and frequency domain of the microseismic waveforms by using Fourier transform, performing deviation standardization on the extracted characteristic parameters and then flattening the characteristic parameters into a one-dimensional microseismic parameter feature map, constructing a rock failure mode discrimination network with a convolutional neural network as the basic framework, training and learning the mapping relationship between the one-dimensional microseismic parameter feature map and the rock failure mode discrimination to construct an intelligent rock failure mode discrimination model, verifying the intelligent rock failure mode discrimination model, and inputting the processed microseismic waveforms of unknown failure modes into the trained intelligent rock failure mode discrimination model for failure mode discrimination. This application can complete the discrimination of rock failure modes only by using a single microseismic signal, without using the variation law of microseismic signals within a continuous time, reducing the subjective and objective errors in the monitoring and early warning of dynamic disasters.

The application relates to the technical field of geotechnical engineering, and in particular to a rock failure precursor identification method and device, a storage medium and computer equipment. The method comprises the following steps: acquiring a multimodal acoustic signal of a rock under the superposition of different types of loads; dividing the multimodal acoustic signal according to a preset time window to obtain a multimodal acoustic signal segment; performing time-frequency analysis on the multimodal acoustic signal segment to construct a time-frequency matrix of the multimodal acoustic signal segment; performing singular value decomposition on the time-frequency matrix to obtain a singular value sequence of the time-frequency matrix; calculating the information entropy of the singular value sequence to obtain the time-frequency singular entropy of the multimodal acoustic signal segment corresponding to the singular value sequence; constructing a time-frequency singular entropy sequence of the multimodal acoustic signal according to the time-frequency singular entropy of the multimodal acoustic signal segment; and identifying a rock failure precursor based on the time-frequency singular entropy sequence of the multimodal acoustic signal. The application avoids false positives and false negatives in rock failure precursor identification, and makes early warning more reliable.

The application discloses a kind of shallow-buried tunnel surrounding rock failure simulation device, belong to tunnel construction technical field, including transparent and top opening test box, detachably connected with tunnel model between the front and rear sidewall of the test box, surrounding rock for covering tunnel model is arranged in the test box, base is fixed in the tunnel model, a plurality of support rods connected with the inner wall of tunnel model are arranged on the base, monitoring instrument is arranged at the end of the support rod, vibration generator is further arranged in the tunnel model;Building model is arranged above the surrounding rock, and pile foundation model is arranged in the surrounding rock in the lower end of building model;Sensor for detecting the settlement of building model is arranged on the test box;The purpose of the application is to solve the problem that the existing shallow-buried tunnel surrounding rock failure simulation device does not consider the influence of tunnel surrounding rock failure on building (structure).

The invention relates to a rock failure stage identification method based on multi-channel acoustic emission feature fusion. The method comprises the following steps: collecting acoustic emission signals of a plurality of acoustic emission sensors arranged on a rock to be detected; counting the acoustic emission signals according to time windows with preset duration, and extracting acoustic emission characteristic parameters corresponding to each time window; and inputting the acoustic emission characteristic parameters corresponding to the acoustic emission sensors in the same time window into the trained rock failure stage identification model to obtain the failure stage of the rock to be detected in the current time window. Real-time and high-precision identification of a rock damage stage is realized through multi-channel acoustic emission signal fusion and a deep learning model; multiple sensors are used for collecting signals, the model automatically extracts high-dimensional features and enhances key information by means of an attention mechanism, and the recognition accuracy and robustness are remarkably improved; compared with a traditional method, the method can output judgment in real time, and provides effective support for engineering safety monitoring and early warning.