124 results about "Rock types" patented technology

The invention provides a rock image classification method based on edge enhancement and multi-scale feature fusion. By combining the edge enhancement and multi-scale feature fusion technology, the accuracy of mineral classification in the rock slice image is remarkably improved. According to the method, rock slice image interference is eliminated through filtering and denoising, and mineral particle edges are enhanced by fusing morphological top-hat transformation and a Laplace operator; and performing multi-scale pyramid decomposition on the enhanced image to extract high-frequency information, performing multi-direction response enhancement to generate a direction feature map, and performing channel-level fusion on the original image, the edge enhanced image and the direction feature map. And finally, inputting the fused image into a convolutional neural network to complete rock type classification. According to the method, mineral boundary expression is effectively enhanced, the classification accuracy is improved, and a reliable technical scheme is provided for geological analysis and lithology identification.

The invention provides a pore-scale underground natural hydrogen migration and accumulation behavior prediction method, and belongs to the field of underground natural hydrogen exploration and exploitation. Comprising the following steps: reconstructing an underground porous medium according to a real geological structure image; establishing an empirical formula of fluid attributes such as wettability, interfacial tension and viscosity of the hydrogen-water-rock system and temperature, pressure, salinity and rock type; establishing a flow equation of the hydrogen-water two-phase system in the porous medium; after initial conditions and boundary conditions are determined, the initial distribution, migration and aggregation process of natural hydrogen in the porous medium is simulated; and after the flow is stable, a migration and accumulation image of the hydrogen-water-rock system and a hydrogen recovery rate change curve are obtained. The hydrogen-water two-phase migration-accumulation model constructed by the method is suitable for the characteristics of high density ratio and high viscosity ratio of hydrogen and water, and is good at treating a porous medium complex structure and identifying a hydrogen-water interface; and the method is oriented to a real underground reservoir, and is suitable for predicting the hydrogen-water-rock migration and accumulation process under no environmental factors.

Systems and methods include obtaining well log data and core sample data of a subsurface formation; generating, based on the well log data and the core sample data, an unconfined compressive strength log for the subsurface formation; using an unsupervised machine learning model to form rock type clusters based on the unconfined compressive strength log and the well log data; forming a training dataset including the well log data, the training dataset labeled based on the rock type clusters; training a supervised machine learning model using the training dataset. While drilling a well in the subsurface formation, logging-while-drilling data is obtained from drilling equipment used to drill the well; and rock types in the subsurface formation are determined using the supervised machine learning model and the logging-while-drilling data.

The invention discloses an anchor rod or anchor cable mounting device and method for inhibiting failure of an anchoring interface, and relates to the technical field of roadway supporting. The device comprises an annular body, a conical protrusion structure, a pulse press-in device, a fluid flushing system and a guide stabilizer, and is suitable for various hole diameters and different surrounding rock types. The construction method using the device comprises the following steps: drilling a hole by a drilling machine to mount an anchor rod or an anchor cable, evaluating the drilling hole, determining a test environment and boundary conditions, performing a drilling hole compression test to simulate confining pressure to obtain a stress deformation response curve, and determining the bonding performance and the shear strength through a pull-out test. The size of the conical protrusion is determined by combining lithology and crustal stress characteristics, the device is installed to a drilling target section, the pulse pressing-in device is started, the conical protrusion structure is pressed into the hole wall of a drilling hole to form a continuous groove, and when a fluid washing system is started to remove dust and chippings, a guiding stabilizer is connected, so that the drilling target section is formed. It is ensured that the device retreats from a drill hole at a constant speed, cleaning operation in the hole is completed, and finally the prefabricated anchor rod is inserted to form a high-adhesion and high-shear-resistance complete anchoring structure.

The invention provides a blasting control construction method for a quarry based on rock mass lumpiness partition and prediction, and belongs to the technical field of blasting control construction. The method comprises the following steps: surveying and setting out, arranging steps and roads, partitioning blasting lumpiness, carrying out blasting design, predicting blasting grading, evaluating safety, drilling holes, cleaning and checking blast holes, loading explosives and detonators and blocking blast hole openings, connecting a detonating network, cleaning a site and warning all around, detonating and checking after blasting. Checking and eliminating unexploded shots; processing and analyzing muck pile images; clearing dangerous stones on the slope; clearing and transporting rock ballast and cleaning the bottom. Reasonable partitioning is carried out according to six indexes including rock types, rock hardness, average crack spacing, explosive unit consumption, blasting funnel volume and blasting lumpiness distribution indexes in a quarry, the qualified rate of specification stones is effectively increased, the resource utilization rate is increased, and a mathematical model Kuz-Ram model for quarry blasting lumpiness distribution forecasting has the advantages of being simple in structure and convenient to use. And predicting and forecasting the grading of the muck pile before blasting, and verifying the muck pile after blasting.

The invention belongs to the technical field of deep hole blasting parameter optimization, and discloses a hole site parameter optimization analysis method based on open-air deep hole blasting. According to the method, the rock type is judged through multi-index cooperation, and a dynamic threshold adjustment mechanism is combined, so that the rock classification accuracy is improved, and accurate matching of hole site parameters and geological conditions is ensured. According to the method, through geological parameter-rock type-mapping relation three-level correlation determination, limitation of an empirical formula is avoided, and the parameter range better fits actual geological features. And meanwhile, a historical blasting data set is introduced for similar case matching, a potential risk parameter set is removed through experience screening, the deviation between theoretical simulation and actual engineering is reduced, and the parameter reliability is improved. According to the method, the multi-objective optimization model is adopted, the crushing quality, the safety control and the economical efficiency are synchronously considered, the parameter set for balancing all the objectives is output through the Pareto optimal algorithm, and high-quality, low-risk and low-cost collaborative optimization is achieved.

The present invention discloses a method for in-situ collaborative development of coal-rock-sandstone type uranium deposits. Uranium resources in coal-rock and sandstone type uranium deposits are mined by combining underground coal gasification with in-situ neutral (CO2+O2) in-situ leaching. This method can achieve clean utilization of coal resources through gasification and collaborative development of sandstone and coal-rock type uranium resources. The method has the advantages of low energy consumption, high resource recovery rate, simple process, and low environmental impact. It conforms to the concept of green mining and is of great significance for addressing my country's demand for strategic key metallic uranium resources and protecting the environment.

A method for recognizing a dominant carbonate rock reservoir in a complex facies zone, comprising: determining a lithologic type and lithologic physical properties of a study section (S100); carving out a development pattern configuration of a special geologic body in the lithologic type (S200); on the basis of the development pattern configuration, using an iterative modeling method to construct an inversion low-frequency model under a phase controlled constraint (S300); using the inversion low-frequency model to perform multi-parameter pre-stack inversion of the study section to obtain an inversion parameter data volume of the study section (S400); and using a multi-parameter intersection method to predict a dominant reservoir distribution in the inversion parameter data volume (S500). Also provided are an apparatus for recognizing a dominant carbonate rock reservoir in a complex facies zone, and an electronic device. By means of the phase controlled constraint, a configuration attribute representing geomorphic facies and lithologic inversion representing lithologic facies are comprehensively considered, and the attribute lateral resolution and the inversion longitudinal resolution are combined, thereby achieving high-precision recognition of a dominant carbonate rock reservoir in a complex facies zone.

The invention belongs to the technical field of information, and discloses a cloud-English rock type ore body construction method and system based on drilling data, and the method comprises the steps: carrying out the boundary recognition processing according to the gradient change characteristics in an alteration intensity space distribution model, and if the alteration intensity gradient change rate of adjacent space points exceeds a preset boundary threshold value, carrying out the boundary recognition processing; if yes, determining that the position is an ore body boundary point, forming an ore body boundary surface by connecting all boundary points, and judging geometric morphology characteristics of the ore body; a three-dimensional reconstruction algorithm is adopted to carry out internal structure analysis on a space area inside the boundary surface of the ore body, mineral combination difference degrees of different positions inside are calculated through a heterogeneity analysis method, internal structure layers are divided according to difference degree distribution characteristics, and occurrence characteristics and spatial distribution rules inside the ore body are determined. According to the method, full-process automation from data preprocessing to three-dimensional space modeling is achieved, the depicting precision of the ore body space distribution characteristics is remarkably improved, and efficient and accurate technical support is provided for geological exploration and resource evaluation.

The invention provides an intelligent geological condition sensing system of a cantilever tunneling machine based on dual-band sound wave analysis, which can solve the problem that the geological condition encountered by the cantilever tunneling machine during construction is unclear, and realizes safe, efficient, intelligent and refined construction of the cantilever tunneling machine. The system is composed of a dual-band high-sensitivity sound pickup, a data wireless transmission antenna and an integrated industrial personal computer, and can collect sound wave data of a cutting head, a tunnel face and surrounding rock in the construction process of the cantilever tunneling machine in real time, and the sound wave data of the cutting head, the tunnel face and the surrounding rock can be obtained through processing methods such as wavelet denoising and Fourier transform on collected audio signals. The system can effectively remove noise signals, analyzes and identifies surrounding rock types in real time in combination with a machine learning algorithm, and can provide a scientific basis for selection of construction parameters of the cantilever tunneling machine, so that parameter setting in the construction process is optimized, the construction safety is improved, reliable support is provided for intelligent construction of tunnel engineering, and the construction efficiency is improved. And special requirements of construction of the cantilever heading machine are met.

A computer-implemented method for augmented inversion and uncertainty quantification for characterizing geophysical bodies is disclosed. The method includes machine-learning-augmented inversion that also facilitates the characterization of uncertainties in geophysical bodies. The method may further estimate wavelets without a well-log calibration, thereby enabling a pre-discovery exploration phase when well log data is unavailable. The machine learning component incorporates a priori knowledge about the subsurface and physics, such as distributions of expected rock types and rock properties, geological structures, and wavelets, through learning from examples. The methodology also allows for conditioning the characterization with the information extracted a priori about the geobodies, such as probabilities of rock types, using other analysis tools. Thus, the conditioning strategy may make the inversion more robust even when a priori distributions are not well balanced. Using the method, a scenario testing workflow may evaluate different candidate subsurface models, facilitating the management of uncertainty in decision-making processes.

The invention discloses a hot dry rock type geothermal resource prediction method and device, a medium and a program product, and the method comprises the steps: firstly carrying out the gravity inversion through the gravity measurement data of a to-be-researched region, and constructing a three-dimensional density model of a hot dry rock body; constructing a hot dry rock volume model according to the geothermal geological data; gridding the hot dry rock volume model to obtain a hot dry rock space grid model; performing geological attribute assignment on each cell in the hot dry rock space grid model according to the geological attribute of the to-be-studied area to obtain a hot dry rock attribute model; performing temperature numerical simulation on each thermal reservoir in the hot dry rock space grid model by using temperature data of the to-be-researched area to obtain a hot dry rock temperature model; and on the basis of the hot dry rock space grid model, the attribute model and the temperature model, the hot dry rock geothermal resource quantity is predicted, and a hot dry rock type geothermal resource quantity prediction result is obtained. According to the embodiment of the invention, the prediction accuracy of the hot dry rock type geothermal resources can be effectively improved.

The present application proposes a method and system for identifying anomalies in mine blasting monitoring images, wherein the method includes: obtaining the rock moisture distribution topology and rock temperature distribution topology of the mine, combining the rock type distribution topology to perform hardness zoning to obtain the rock hardness distribution topology; using the rock type distribution topology, rock fracture distribution topology, and rock hardness distribution topology as constraints, collecting blasting samples from the blasting location list and blasting series list to obtain a blasting sample set, performing high-frequency blast pile morphology mining, and obtaining a blast pile baseline morphology; when the blast pile monitoring morphology is inconsistent with the blast pile baseline morphology, the blast pile monitoring morphology is marked as uncontrollable and sent to the user end. The present application solves the technical problem in the prior art that it is difficult to accurately identify anomalies in mine blasting monitoring images, and achieves the technical effect of accurately identifying anomalies in mine blasting monitoring images and issuing timely warnings.

The invention discloses a comprehensive evaluation method for a deep coal bed gas reservoir, and the method comprises the following specific steps: S100, classifying gas wells according to the effects of produced wells in a research area, and dividing the gas wells into three types of gas wells I, II and III; s200, in combination with gas well classification standards, carrying out classification evaluation on three types of gas wells I, II and III, including coal rock type, coal rank, coal body structure, coal seam thickness, coal seam physical property, coal seam gas-bearing property, coal seam roof and floor research and the like; and S300, establishing a coal rock reservoir comprehensive evaluation classification standard table according to classification evaluation, evaluating the reservoir quality of the undeveloped target area of the research area, and guiding coal bed gas development. By establishing the comprehensive evaluation method for the deep coal-bed gas reservoir, the method has good guiding significance for efficient development of the deep coal-bed gas, the actual reservoir characteristics of the deep coal-bed gas can be reflected, the requirement for the quality of the geological comprehensive evaluation reservoir is met, a favorable area is preferably selected for comprehensive evaluation of the deep coal-bed gas reservoir, and efficient development is achieved.

The invention relates to a well pattern deployment method for improving the recovery degree of a fractured buried hill oil reservoir, and belongs to the technical field of oil exploitation. The method comprises the following specific steps: in combination with a rock core analysis result, formulating a logging curve combination to recognize a lithologic template, recognizing a rock type, and depicting a dominant rock distribution condition; carrying out fracture prediction by adopting an ant body analysis technology, and further predicting the distribution characteristics of the dominant reservoir; productivity evaluation, water injection evaluation, horizontal well development effect evaluation and adjustment potential evaluation are carried out according to the oil reservoir development effect, and a vertical well and horizontal well combined injection-production well network structure is established in combination with understanding of dominant lithology distribution and dominant reservoir prediction. An injection-production well pattern is perfected by establishing a fractured block buried hill oil reservoir well pattern structure, various types of enriched remaining oil are effectively used, the problems that the inner curtain of the fractured block buried hill oil reservoir is not clearly known, the remaining oil is difficult to dive, and gas-water combined three-dimensional energy complementing is feasible are solved, and the recovery degree of the oil reservoir is improved.

The invention discloses a multi-geophysical field joint inversion method based on physical subspace decoupling, and belongs to the field of geophysical exploration. According to the invention, the problem of poor inversion effect caused by difficult characterization of multivariate and nonlinear physical relations of different types of rocks under complex geological conditions in the existing structure coupling joint inversion method is solved; according to the method, K subspace clustering is utilized to dynamically divide underground model units into different low-rank subspaces according to physical property parameter characteristics in each inversion iteration, and then a low-rank constraint based on a Schatten-p norm is applied to a physical property parameter matrix in each subspace; the clustering-coupling process and the inversion iteration are alternately carried out, so that the division of the physical property subspace and the model updating in each subspace are mutually promoted, the self-adaptive optimization is realized, and the clustering-coupling process and the inversion iteration are carried out at the same time; and finally, high-precision and high-resolution reconstruction of multi-type rock physical property distribution in the complex underground structure is realized.

The invention relates to the technical field of oilfield development, in particular to a combined type oil well intelligent plug removal method which comprises the steps that the oil well rock type and the plug type are obtained; preparing an alkaline blocking remover and an acidic blocking remover; injecting an alkaline blocking remover, soaking the well, and performing pulse flowback; the alkaline blocking remover and the acid blocking remover are conveyed into the oil well according to the preset proportion; continuously detecting the temperature in the oil well, and adjusting the ratio of the acidic blocking remover to the alkaline blocking remover according to the reflux pH value and the measured temperature in the oil well; detecting the particle size of particles in the reflux liquid until the particle size is smaller than a preset particle size; and performing thermal flushing and pressure recovery testing, calculating a skin coefficient, and when the skin coefficient is reduced to a standard range, judging that blockage removal succeeds and completing blockage removal. Heat generated by the neutralization reaction can melt residual paraffin and asphalt, the viscosity of the paraffin and the asphalt is reduced, the paraffin and the asphalt can be dissolved and discharged by the blocking remover more easily, and therefore the blocking removal effect is improved.

A method for forecasting productivity in a subsurface formation includes receiving input data. The input data includes first input data and second input data. The method also includes determining a bulk density curve and a neutron porosity curve based upon the first input data and the second input data. The method also includes determining a permeability in the subsurface formation based at least partially upon the bulk density curve and the neutron porosity curve. The method also includes determining a rock type in the subsurface formation based upon the permeability.

The invention relates to the technical field of TBM equipment, and discloses a pumped storage power station underground cavity TBM applicability evaluation method, which comprises the following steps: S1, firstly carding an existing framework of pumped storage power station underground cavity TBM applicability evaluation, and defining core technical elements and a protection range of the framework; an evaluation framework of non-AHP driving, dynamic multi-source data fusion and machine learning enabling is provided. According to the method, an evaluation framework of non-AHP driving, dynamic multi-source data fusion and machine learning enabling is provided, an index system is constructed, the index system is divided into static indexes (in a design stage, cavern burial depth, surrounding rock category and turning radius) and dynamic indexes (in a construction stage, TBM attitude error, cutter wear rate, surrounding rock deformation rate and ventilation efficiency), a real-time monitoring system is integrated, and the dynamic index is divided into a dynamic index and a dynamic index; and data such as TBM attitude, cutter wear and surrounding rock deformation are input into the model in real time, and the applicability score is dynamically updated, so that the method has the advantages of high pertinence, comprehensive index system and the like.

The invention discloses a single well rock classification method and device and application, and the method comprises the steps: obtaining a single well saturation curve of a target well through the calculation of an Archie formula; constructing a saturation height function based on the core data; a height curve above a free water interface and a single well porosity curve of the target well are obtained; through the height curve above the free water interface, the single well porosity curve and the saturation height function, a single well saturation curve of different rock types is obtained through calculation; and determining the rock type of the target well based on the different rock type saturation curves of the single well and the single well saturation curve. By applying the method to a core well and comparing with core well rock classification, the coincidence rate of the rock type of the method reaches 85%, and the coincidence rate of the original method is improved by 12% while the coincidence rate of the original method is 73%. According to the method, the accuracy rate of single well rock classification is improved, a foundation is laid for subsequent rock type three-dimensional modeling, and the method can be continuously used for other similar oil reservoirs in the Middle East.

The present application belongs to the technical field of deep hole blasting parameter optimization, and discloses a hole site parameter optimization analysis method based on open pit deep hole blasting. The present application determines rock types through multi-index coordination, improves the accuracy of rock classification by combining a dynamic threshold adjustment mechanism, and ensures the accurate matching of hole site parameters and geological conditions. The present application determines through three-level correlation of geological parameters-rock types-mapping relationship, avoids the limitations of empirical formulas, and makes the parameter range more in line with actual geological characteristics. At the same time, historical blasting data sets are introduced for similar case matching, potential risk parameter sets are removed through experience screening, the deviation between theoretical simulation and actual engineering is reduced, and the parameter reliability is improved. The present application adopts a multi-objective optimization model, simultaneously considers fragmentation quality, safety control and economy, outputs a parameter set balancing each target through a Pareto optimal algorithm, and realizes the coordinated optimization of high quality, low risk and low cost.

Deep azimuthal electromagnetic ("DAEM") data, is combined with seismic data and resistivity data from an offset well to generate a saturation model solution of a reservoir in hydrocarbon bearing subterranean formation. The DAEM data is inverted to create a stratigraphic framework, which is updated with rock types to form an updated framework. The updated framework is combined with the DAEM data to obtain the saturation solution model. Hydrocarbons in the reservoir are identified and produced based on the model.

The present invention belongs to the technical field of efficient fragmentation of hard rocks. Provided are a vehicle-mounted system and method for controlling high-energy laser-induced rock fracturing, the method comprising: by means of a second image acquisition and analysis unit, acquiring surrounding environment information of an electric flat car during movement; on the basis of a stored motion path of the electric flat car and the surrounding environment information, an electric flat car control unit generating a first control instruction; the electric flat car controlling the electric flat car to move to a designated position for rock fragmentation; by means of a first image acquisition and analysis unit, acquiring the type of a rock to be fragmented, and after a laser emission unit is started, acquiring real-time condition information of laser-induced rock fracturing; a laser control unit acquiring a laser emission parameter corresponding to the type of the current rock to be fragmented, and upon receiving the real-time condition information of laser-induced rock fracturing that is acquired by the first image acquisition and analysis unit, adjusting the laser emission parameter, and generating a second control instruction on the basis of the laser emission parameter; and the laser emission unit controlling the laser emission unit to start emitting a laser for rock fragmentation.

Disclosed are methods, systems, and computer programs for generating petrophysical analysis data. The methods include: accessing first porosity data and first well log data associated with an NMR well; randomly selecting data elements comprised in the first porosity data and the first well log data; developing, based on the randomly selected first porosity data and first well log data, a learning data structure; generating, based on the learning data structure, a machine learning model; receiving second well log data using sensor(s) deployed about a non-NMR well; adapting, based on the second well log data, variable input parameters of the machine learning model to generate second porosity data; and formatting the second porosity data to generate petrophysical analysis data. The petrophysical analysis data indicates one or more of: a petrophysical characterization of a rock type; flow dynamic data of a carbonate reservoir; well test or perforation zone data; and pore data.

The present application relates to a kind of carbonate lithology identification method based on well logging parameter, device and storage medium, belong to rock type identification technical field, the method includes: the multiple carbonate thin section of target formation is calibrated, obtains the well logging parameter and type of corresponding depth of carbonate thin section;Carbonate thin section includes dolomite thin section and limestone thin section;Based on the well logging parameter of corresponding depth of carbonate thin section plot crossplot, and determine target parameter according to crossplot and type;Target parameter includes uranium value, thorium value, acoustic time difference and compensation neutron;Based on target parameter, the lithology of dolomite and limestone in non-coring section is identified.The present application provides the carbonate lithology identification method based on well logging parameter, is analyzed with multiple parameters such as uranium, thorium, acoustic time difference and compensation neutron, realizes accurate identification to carbonate lithology.

The invention discloses an altered rock type gold ore rich ore section prospecting method, and belongs to the field of geological data processing, mineral resource evaluation and investment decision support, and the method comprises the steps: obtaining and fusing multi-source geological data to construct a three-dimensional seepage physical model; performing numerical simulation based on the physical model to obtain flow field parameters; calculating and generating a fluid focusing index according to the flow field parameters; performing regression calibration on the focusing index by using the drilling data to establish a grade thickness prediction model; and delineating and generating a three-dimensional rich ore exploration target area by using the prediction model according to a grade threshold value. According to the method, a technical path of combining physical process simulation and machine learning regression is adopted, and a closed-loop feedback correction mechanism connecting theoretical prediction and calibration results is constructed, so that end-to-end quantitative prediction of the hidden ore body from geological causes to commercial values can be realized, the success rate of deep prospecting is remarkably improved, and the exploration investment risk is reduced.

The invention provides a characterization method and device for carbonate rock micro-nano apertures and a medium, and relates to the technical field of carbonate rock microcosmic reservoir space characterization, reservoir multi-scale evaluation and reservoir transformation. The method comprises the steps that the target rock type and aperture type of carbonate rock are determined; under the condition that the target rock type and the aperture type are determined to be the millimeter-micron aperture type, performing qualitative analysis on the micro-nano aperture of the carbonate rock to obtain the characteristic type of the micro-nano aperture; carrying out quantitative analysis on the micro-nano aperture to obtain the structural characteristics and heterogeneity of the micro-nano aperture; and performing characterization description on the micro-nano aperture according to the feature type, the structural feature and the heterogeneity. Therefore, micro-nano-scale reservoir space fine characterization of deep ancient carbonate rocks and compact carbonate rocks is realized, so that a technical system suitable for micro reservoir space fine characterization of carbonate rocks is established.

The application provides a kind of geotechnical engineering investigation three-dimensional geological model automatic construction method and system based on machine learning and BIM, it is related to geotechnical engineering investigation technical field, wherein, the method comprises: after obtaining borehole investigation data, color correction is carried out on original core image based on color chart image, corrected core image is input into convolutional neural network model to identify rock type and demarcate first rock layer boundary line;Key area of resistivity gradient change is used to replace fuzzy area to obtain second rock layer boundary line;According to the inclination correction space position and fill the wave velocity value to generate target borehole columnar section;According to the degree of stratigraphic relief, the calculation weight of spatial interpolation algorithm is adaptively adjusted, and three-dimensional stratum data is generated;Three-dimensional stratum data is imported into BIM software interface to automatically assemble three-dimensional geological model.The application improves the degree of automation and spatial accuracy of geological model construction.

The present invention discloses a device and method for inverting lunar rock types through annihilation radiation, belonging to the technical field of lunar geological structure detection. The method uses a proton accelerator to obtain high-current proton bombardment of typical lunar rock composition samples, and simultaneously uses a detector to measure the induced gamma energy spectrum information generated by the samples. The proton stream bombards the samples to be tested, obtains the annihilation radiation count rate in the 511keV energy window and the count rate in the 969-1133keV characteristic peak area of ​​different samples to be tested, and calculates the ratio of the two. Different lunar rock types are accurately distinguished based on different ratios. The present invention achieves accurate distinction of lunar rock types by successfully stimulating the annihilation radiation of typical rocks using a direct ground calibration method.

This invention relates to an intelligent prediction method for the safety risks of surrounding rock in underground powerhouses of pumped storage power stations, comprising the following steps: S1, firstly, multiple monitoring devices are installed in the surrounding rock of the underground powerhouse to monitor and collect data on surrounding rock displacement, stress change, fissure opening, and environmental parameters; S2, then, the collected data on surrounding rock displacement, stress change, fissure opening, and environmental parameters are preprocessed using a terminal to complete time synchronization, abnormal data removal, and data standardization, forming a time-series dataset required for surrounding rock safety analysis. This invention realizes real-time monitoring, intelligent prediction, automatic support, and feedback of safety risks in the surrounding rock of underground powerhouses, improves the efficiency of surrounding rock safety management, reduces the risks of manual inspection and emergency operations, and can adapt to the temporary support needs of different surrounding rock types and construction stages.