132 results about "Geohazard" patented technology

The invention relates to the cross technical field of artificial intelligence and geological disaster monitoring and early warning, in particular to a landslide recognition method and system based on staged feature adaptive transfer learning, and the method comprises the steps: constructing an initial landslide recognition model F1 with an encoder-decoder; a universal visual pre-training weight is migrated, and encoder parameters of the model F1 are finely adjusted by using a remote sensing image data set DS of a source domain, so that a landslide identification optimization model F2 adaptive to the field is obtained; inputting the remote sensing image data set DS of the source domain and the unmanned aerial vehicle image data set DT of the target domain into the model F2, and processing based on a covariance alignment mechanism to obtain a domain adaptive model F3; inputting a small amount of labeled target domain small sample data D 'T into the model F3, and finely adjusting specified parameters in the model F3 through a supervised learning mechanism to obtain a target domain adaptive model F4; and based on the target domain adaptation model F4, executing a landslide identification task on an input to-be-detected unmanned aerial vehicle image.

The invention relates to the technical field of slope reinforcement, and particularly discloses a slope reinforcement system and method for building municipal administration, slope rock mass strain time sequence data is collected through a distributed optical fiber sensing system, slope deformation monitoring data is obtained through a spaceborne interferometric synthetic aperture radar, and a three-dimensional deformation monitoring data set is constructed; an LSTM-rock constitutive model fusing a DFOS strain field and an InSAR deformation field is established, strain time sequence data and deformation data are input into the model for three-dimensional stress field inversion, and shear modulus degradation rate parameters, creep coefficient parameters and displacement increment prediction data are output; shear modulus degradation rate parameters, creep coefficient parameters and displacement increment prediction data are processed, regulation and control strategy codes of anchor rod tensioning force gradients and grouting pressure intervals are generated and uploaded to a control terminal, the precision and timeliness of slope stability analysis are remarkably improved, accurate intervention can be conducted in time according to potential risks of a slope, and the stability of the slope is improved. The probability of geological disasters such as landslide is reduced, and life and property safety of people is protected.

The invention provides a deep learning landslide identification method and system fusing optical and SAR remote sensing data, and relates to the field of geological disaster monitoring and identification, and the method comprises the steps: obtaining an optical image and an SAR image of a target region, carrying out the registration, generating an optical-SAR image pair, and generating a corresponding binary label map for the optical-SAR image pair; constructing a to-be-trained landslide recognition model, constructing a data set by the optical-SAR image pair and the corresponding binary label graph, and training the to-be-trained landslide recognition model by using the data set to obtain a trained landslide recognition model; and inputting an optical-SAR image pair of a to-be-identified area into the trained landslide identification model, and outputting a landslide identification result graph of the to-be-identified area. According to the invention, the limitation of a single remote sensing data source in landslide identification in the prior art is overcome, and the landslide identification precision in a complex environment is improved.

The invention discloses an air-space-ground landslide monitoring method and system based on deep learning, and relates to the technical field of landslide monitoring of mines. The system divides a mine area into a plurality of monitoring sub-areas by establishing a visual man-machine interaction platform and combining a digital geological disaster model; the multi-source data collection covers various sensing data of air-based, space-based and ground-based data, and the consistency and reliability of the data are ensured through standardization, time synchronization and space registration processing; a dynamic landslide monitoring model is constructed by adopting a convolutional neural network, multi-scale spatial-temporal characteristics of a landslide mass are extracted in real time, and accurate identification of landslide physical effect risks is realized; in combination with a geomechanical strain response index, a micro-seismic excitation response coefficient and a fluctuation disturbance abnormal index, a landslide risk is evaluated in multiple dimensions through a threshold judgment mechanism, a risk state and an early warning level are dynamically output, an early warning strategy is generated, mine safety management and emergency response are assisted, and life safety of mining personnel and environmental stability are guaranteed.

The invention provides a method for determining the spontaneous combustion evolution process of end slope coal of a strip mine, and belongs to the field of geotechnical engineering geological disaster prevention and control and the field of mine safety and environmental protection. Updating the porosity, the permeability and the range of the combustion space area in the pre-established three-dimensional geologic model by adopting the three-dimensional distribution of the porosity of the bending subsidence zone, the permeability of the fissure zone, the permeability of the caving zone and the porosity of the caving zone in the combustion space area; performing coal fire evolution simulation again according to the updated pre-established three-dimensional geologic model to obtain a coal fire development range, an updated real-time temperature field range and a gas concentration field; and if the combustion cannot be continued, outputting a final coal fire development range and an updated real-time temperature field range. According to the method, the efficiency and accuracy of open-pit mine end slope coal fire treatment are effectively improved.

The invention relates to a spoil field three-dimensional form change analysis method, which comprises the following steps: constructing an air-space-ground collaborative multi-scale three-dimensional monitoring network by adopting an unmanned aerial vehicle carrying a laser radar system; dynamic construction of a multi-period digital elevation model and a digital terrain model is realized through a weighted fusion algorithm based on point cloud density difference and an improved progressive triangulation network encryption algorithm; performing time sequence alignment on the digital terrain models in different periods, and constructing a digital elevation difference model; and through a digital elevation difference model and a self-adaptive threshold change detection technology, the space-time differentiation characteristics and evolution rules of a slope curvature sudden change area, a surface roughness abnormal zone and a deformation rate of the spoil site are disclosed. According to the scheme provided by the invention, high-precision three-dimensional form dynamic modeling and deformation process precise monitoring of the spoil ground can be realized, and reliable technical support is provided for ecological safety situation assessment and geological disaster advanced early warning of the spoil ground.

The invention provides a soil body-structure interaction boundary damage quantitative testing device and method, and relates to the technical field of geotechnical engineering test.The soil body-structure interaction boundary damage quantitative testing device comprises a stress conduction boundary shear strength and rigidity combined testing structure and a testing system integrating a shaft confining pressure-temperature collaborative loading system and a monitoring collection and process control system; through an improved slurry sample preparation method, tight connection and constant contact area between the hollow columnar soil sample and the friction pile body are ensured, and the test sealing performance is enhanced through the elastic sealing design; the real-time measurement of the rigidity of different positions in the whole shearing process is realized by virtue of the excitation damage detection element capable of synchronously moving; according to the method, the constitutive model of the marine rock-soil stress conduction boundary domain is perfected, a reliable experimental basis is provided for foundation design of deep-sea engineering such as submarine pipelines and anchoring structures, and the method has important theoretical value and engineering significance for improving design scientificity and safety of deep-sea infrastructures and preventing and controlling submarine geological disasters.

The invention provides an anchoring slope landslide instability risk evaluation method under a rainfall condition, and belongs to the technical field of geotechnical engineering and geological disaster prevention and control, and the method comprises the steps: constructing a theoretical calculation formula of a multilayer rock-soil body anchoring slope stability coefficient under a rainfall infiltration effect based on a segmented slip plane method; based on a Monte Carlo probability analysis framework, introducing a reliability index, and establishing a slope reliability integrated evaluation model; acquiring soil body, rainfall, support and geometric parameter data of the side slope; defining various parameters as random variables, and performing large-scale sampling calculation based on the theoretical formula; counting probability distribution of the stability coefficient, and solving a reliability index and a failure probability; establishing a risk monitoring criterion, and judging whether each index exceeds a permissible value or not; and implementing risk dynamic early warning based on a judgment result. According to the method, an integrated evaluation technology system for the reliability of the anchored side slope under rainfall suitable for the multi-layer rock-soil body is constructed, and efficient quantification of the reliability of the side slope under the multi-parameter coupling effect is achieved.

The invention relates to the technical field of geological disaster monitoring, in particular to a rock collapse accumulation body debris flow tendency intelligent evaluation system and method based on multi-parameter coupling. The method comprises the following steps: acquiring geological structure data of a rock collapse accumulation body; performing potential unconsolidated formation analysis according to the geological structure data to obtain potential unconsolidated formation data; performing rainfall infiltration analysis according to the potential unconsolidated formation data to obtain infiltration rate data; determining the water content state of the accumulation body according to the infiltration rate data; performing stability analysis according to the water-containing state of the accumulation body to obtain accumulation body stability data; identifying a potential sliding section based on the accumulation body stability data; detecting flow energy according to the potential sliding section to obtain sliding power data; and performing hydrological confluence analysis according to the geological structure data to obtain hydrological confluence data. According to the method, the accuracy of identifying and evaluating the debris flow tendency of the rock collapse accumulation body is improved based on a geological disaster monitoring technology.

The invention provides a drainage channel structure of a geological disaster control project and a construction method of the drainage channel structure, and relates to the technical field of drainage channels. The drainage channel structure of the geological disaster control project comprises an excavated U-shaped drainage channel body, a channel body supporting structure is arranged in the drainage channel body, and the channel body supporting structure comprises a first supporting layer and a second supporting layer arranged on the inner side of the first supporting layer; the first supporting layer comprises U-shaped supporting walls and a U-shaped concrete platform which are matched with the U-shaped drainage channel body, the U-shaped supporting walls are embedded in supporting wall setting cavities so as to form the first supporting layer with the U-shaped concrete platform, and the U-shaped supporting walls are formed by filling stone cages with broken stones; the second supporting layer is a concrete layer, and waterproof geotechnical cloth is arranged between the second supporting layer and the first supporting layer. The concrete layer of the second layer is not prone to cracking or damage, the canal body supporting structure is more stable, and the service life is longer.

The invention discloses a red clay excavation side slope collapse emergency disposal and treatment construction method, and belongs to the technical field of geological disaster prevention and side slope engineering. According to the method, through six-step integrated construction of monitoring, closing, reinforcing, back pressing, structure and slope protection, rapid emergency rescue and long-acting treatment of red clay slope collapse are achieved. The method has the advantages of being rapid in construction, small in traffic influence, low in cost, lasting in treatment effect and the like, and is suitable for comprehensive treatment of red clay slope slump in projects such as highways and railways.

The present application relates to geotechnical engineering and geological disaster prevention technical field, specifically disclose a kind of combined bedrock reconstruction and slope modification multi-cladding layer slope and its construction method, the present application is strengthened by constructing cemented rock-embedded groove the binding force of slope and bedrock, form anti-sliding "structure pile" effect, control bedrock seepage passage, significantly improve the overall collaborative stability of slope-bedrock;In the process of layered filling, embedded cemented soil and rock interlayer body, constitute continuous, multi-level interlayer structure, enhance the integrity of structure, overcome the problem of localization of traditional supporting structure;By being arranged between cemented soil and rock interlayer body and conventional soil and rock mixture embedded cemented layer gravel drainage groove, realize multi-channel grading drainage and anti-seepage function in slope, effectively reduce pore pressure;Through conventional drainage facilities and the drainage structure inside slope cooperation, form "upper cut, surface guide, lower discharge, buffer" four-in-one composite drainage system, improve the anti-sliding performance and seepage control ability of slope.

This application discloses a method and apparatus for identifying and imaging landslide geological bodies, comprising the following steps: constructing an initial model of the landslide geological body based on landslide disaster data of the target area; performing geophysical simulation based on the initial model to extract field data acquisition parameters of the target area; conducting natural and / or artificial electric field detection based on the field data acquisition parameters to obtain electric field observation data; inverting the electric field observation data to extract imaging data; and performing inversion imaging based on the imaging data to obtain a two-dimensional profile and a three-dimensional slice of the target area. The technical solution of this application can perform detailed identification and imaging of landslide geological disaster structures, providing crucial data information for subsequent landslide geological disaster early warning and engineering management. Its advantages of low cost, speed, high precision, and non-destructive green exploration are significant.

1. The name of this design product: Deformation detection radar. 2. Application of this product design: It is used for deformation monitoring in areas such as high and steep slopes, road / railway slopes, geological disaster risk points, tailings ponds (dams), open-pit mining areas, water conservancy projects, and geological disaster emergency rescue. It is especially suitable for field geological disaster emergency rescue monitoring and fixed monitoring equipment for slope construction. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: three-dimensional picture.

The invention relates to the technical field of ecological restoration monitoring, and discloses a landslide monitoring device and method for mine ecological restoration, and the device comprises a shell which comprises a cylindrical part shell and a moving part longitudinally connected to the part shell in a sliding manner, and a signal transmitting module is arranged at the top of the moving part; the inclination measuring piece is arranged at the bottom of the component shell; the conical head is arranged at the bottom of the inclination measuring piece; the spring rods are horizontally arrayed in the circumferential direction of the component shell, the protection plates are arranged at the ends of movable rods of the spring rods, and clamping rings are arranged on the spring rods; the installation ring is arranged on the inclination measuring piece in a sleeving mode, the arc-shaped plates and the connecting plates are arranged above the installation ring, sliding blocks are hinged to the tops of the arc-shaped plates, the connecting plates are connected with the sliding blocks in a sliding mode respectively, and connectors are arranged at the ends of the connecting plates; the device can be quickly and accurately arranged on a steep slope in a large scale, is damage-resistant, and improves the geological disaster monitoring capability and the safety guarantee level of a mine ecological restoration area.

The invention discloses a multi-mode intelligent interpretation method and system for collapse remote sensing monitoring. The method comprises the following steps: firstly, acquiring and preprocessing multi-source remote sensing data; the multi-source remote sensing data comprises a true color image RGB (Red-Green-Blue), a near infrared wave band NIR (Near-Infra) and a digital elevation model DEM (Digital Elevation Model), and the method comprises the following steps of: acquiring the multi-source remote sensing data; inputting the multi-source remote sensing data into a collapse remote sensing monitoring network, and outputting five types of collapse erosion bodies with preset scales; according to the method, the landform information represented by the high-resolution remote sensing image and the digital elevation model is comprehensively utilized, and various interactive prompts such as text description, voice instructions and geometric elements are combined, so that the precise, efficient and interactive intelligent recognition and boundary interpretation of the collapse hill are realized under the driving of the domain knowledge graph. The system is especially suitable for professional application scenes which require high precision, high flexibility and support natural interaction, such as natural resource investigation, geological disaster monitoring and the like.

The application discloses a kind of prediction methods of damming dam geometric form parameters, comprising: obtaining physical parameters and topography and geomorphology parameters to establish the calculation model of damming dam formation process;Analysis landslide volume, sliding surface inclination, landslide body natural repose angle and landslide speed influence on damming dam geometric form parameters obtain the fitting formula.Distribution position and volume of potential landslide body entering valley are obtained, based on the distribution position and the volume of potential landslide body entering valley, the volume of potential landslide body entering valley per unit time is obtained;Compare the volume of potential landslide body entering valley and river flow, to determine whether damming dam can be formed;Obtain the state parameters of potential landslide body and potential damming dam;Based on the geometric formula, the state parameters of potential landslide body and potential damming dam, the geometric form parameters of damming dam are predicted.The application can predict the geometric form of potential damming dam in advance, and provide a new method for the prediction and early warning of mountain damming dam geological disasters.

This invention relates to the field of mine geological disaster control and geotechnical engineering testing technology, and particularly to a device and method for simulating and testing the seepage and particle migration of glacial till under rainfall conditions. The device includes a rainfall simulation mechanism, a glacial till seepage simulation mechanism, a seepage monitoring system, and a migration and seepage monitoring system. The glacial till seepage simulation mechanism includes a cylinder, and the monitoring end of the seepage monitoring system is located inside the cylinder. By setting up a rainfall simulation mechanism and a cylinder, and placing the monitoring end of the seepage monitoring system inside the cylinder, this invention allows the seepage monitoring system to monitor the seepage and moisture content changes of glacial till samples at different depths in real time. The migration and seepage monitoring system collects infiltrated water and migrating fine particles, enabling researchers to determine the rainwater infiltration situation of this type of glacial till sample and the migration pattern of fine particles under infiltration conditions based on the amount of water and fine particles collected by the migration and seepage monitoring system.

The application provides a kind of fusion optical and SAR remote sensing data deep learning landslide identification method and system, it is related to geological disaster monitoring and identification field, including obtaining the optical image and SAR image of target area are registered, generate optical-SAR image pair, and generate corresponding binary label graph for the optical-SAR image pair;Constitute to be trained landslide identification model, by the optical-SAR image pair and corresponding binary label graph, construct data set, utilize the data set to the training of the to-be-trained landslide identification model, obtain the training completed landslide identification model;The optical-SAR image pair of area to be identified is input into the training completed landslide identification model, and the landslide identification result graph of the area to be identified is output.The application overcomes the limitation of single remote sensing data source in landslide identification in the prior art, and improves the landslide identification accuracy in complex environment.

The invention relates to the technical field of geotechnical engineering and geological disaster prevention and control, and discloses a loess slope stability calculation method considering a stress state, and the method comprises the steps: building a slope three-dimensional model according to the landform, geologic structure and rock-soil body physical and mechanical parameters of a slope; applying a load in the side slope three-dimensional model and setting boundary conditions to obtain a stressed side slope three-dimensional model; carrying out stress field solving on the three-dimensional model of the stressed side slope to obtain a global stress field of the side slope; for each collected soil sample, extracting a corresponding stress tensor from the stressed slope three-dimensional model, and determining a confining pressure condition corresponding to an indoor shear strength test; according to the confining pressure condition, an indoor shear strength test is carried out, and a soil shear strength index under the actual stress field condition is obtained; a soil sample representative horizon method is adopted, the stratigraphic position corresponding to each soil sample is analyzed, the slope stability is calculated, and the slope safety coefficient and the potential sliding surface position are obtained. Therefore, the accuracy of slope stability analysis is improved.

The application discloses a landslide susceptibility prediction method combining terrain combined features and partition explainable analysis, and relates to the technical field of geological disaster evaluation. Slope, plane curvature and profile curvature factors are extracted from a digital elevation model of a research area, and after standardization, Gaussian mixture model is used for unsupervised clustering. The class labels obtained by clustering are taken as terrain combined features and are coded, and are combined with landslide influence factors to form an input feature set. The input feature set is input into an XGBoost model for training and the hyperparameters are optimized through grid search. Based on the trained model, the SHAP method is used to calculate the global feature contribution degree, and the contribution degrees of various factors are calculated according to terrain combination types, and the spatial differences of the factors under different terrain units are analyzed. The terrain types obtained by clustering are used as explicit features to participate in model training, and the spatial heterogeneity of the factors is revealed through grouped contribution degree analysis, which provides a new technical means for landslide susceptibility evaluation.

The application discloses a karst evaluation unit construction and feature factor extraction method, relates to the technical field of karst geological disaster prediction and evaluation, and is based on topography, geology, hydrology, geophysical prospecting, drilling and human activities and the like to perform spatial dispersion on a research area based on multi-source data, so that initial spatial units for bearing karst action and underground cavity information are formed. The initial units are divided into multiple types of karst evaluation units by identifying karst structure features, underground cavity distribution, roof-soil combination relationship and hydrological connectivity. Further, attributes such as karst development intensity, cavity geometric features, roof stability, hydrological disturbance and surface load change are extracted, and a unified feature factor system is constructed. The method can provide a standardized spatial unit basis for karst collapse susceptibility or risk analysis.

The invention provides a rock-soil crack intelligent identification method based on unmanned aerial vehicle multi-source remote sensing data, and relates to the technical field of geotechnical engineering safety monitoring and geological disaster identification. An unmanned aerial vehicle is used for synchronously collecting earth surface images and laser point cloud data, a YOLO crack detection network is adopted for recognition, the network integrates a terrain texture prior attention module, a point cloud constraint fusion layer and a self-adaptive confidence degree re-estimation module, and deep coupling of image texture and point cloud geometric features is achieved. Density clustering segmentation is further carried out on the point cloud to extract space abnormal features, image recognition results and point cloud features are registered and fused through principal direction and depth consistency constraints, and a crack space positioning model is constructed. And finally, according to a positioning result, guiding the unmanned aerial vehicle to fly close to the ground to obtain a high-precision image of a potential rock-soil fracture development area, and completing fracture boundary accurate segmentation and morphological parameter extraction. According to the method, the accuracy, robustness and whole-process intelligent level of crack identification are remarkably improved.

The application discloses a submarine landslide multi-source data simulation data preprocessing method, belongs to the technical field of marine geological disaster data processing, and comprises multi-source simulation data aggregation and format normalization. Different types and formats of submarine landslide simulation data are integrated into the same data set and converted into a unified data format. According to the application, multi-source data is subjected to space-time registration in a unified geographic reference framework and time reference. Through topographic data re-projection, time series data interpolation synchronization, and accurate matching of strata and sediment parameters to corresponding land elements, strict alignment of multi-dimensional simulation data in spatial position and time node is realized, different physical processes are ensured to be comparable, fusable and superimposable in the same space-time scale, and the collaborative expression capability of multi-source information in landslide evolution mechanism analysis is significantly enhanced.

The invention discloses a semi-supervised S3VM soft label-based landslide susceptibility mapping method, and belongs to the technical field of geological disaster risk assessment and remote sensing, and the method comprises the steps of S1, multi-dimensional data acquisition and collaborative preprocessing; s2, constructing a feature stack and training a semi-supervised support vector machine (S3VM) model; and S3, selecting a negative sample and endowing a soft label. According to the landslide susceptibility mapping method based on the semi-supervised S3VM soft label, the accuracy and the reliability of landslide susceptibility identification are remarkably improved by introducing a multi-dimensional factor and a semi-supervised learning mechanism.

The application relates to the technical field of remote sensing information processing and geological disaster monitoring, and discloses a mountainous area landslide intelligent identification method and system fusing multiple remote sensing sources, which comprises the following steps: inputting an optical image and a digital elevation model into an experience mapping function to generate a static coherence expectation value; extracting a soil moisture stress adjustment factor based on a precipitation sequence, and generating a dynamic coherence background matrix through a nonlinear modulation model; performing interference coherence estimation on polarized radar complex data to extract a coherence residual matrix; screening first-level abnormal image elements with continuously increasing residuals, calling a polarized target decomposition algorithm to extract polarized scattering power components, and determining second-level abnormal image elements based on a physical mechanism partial differential equation set; generating a catchment network based on an elevation model, and performing micro-geomorphology spatial topological filtering on abnormal image element aggregation patches. The application excludes environmental and hydro-meteorological interference, and effectively reduces the false alarm rate of landslide identification in complex mountainous areas.

The invention relates to the technical field of geotechnical engineering safety monitoring, in particular to a waste slag field safety monitoring method. According to the method, aiming at the problems of multiple monitoring blind areas, weak data integration capability, early warning lag and the like in the prior art, a set of multi-level monitoring system is constructed by systematically arranging a displacement, stress-strain and osmotic pressure sensor network at key positions such as the surface, the interior and the side slope of the waste slag field. A wired and wireless mixed transmission mode is adopted, a redundant communication link and encryption measures are configured, monitoring data are efficiently, stably and safely transmitted to a cloud server, the server side carries out fusion processing and trend analysis on multi-source real-time data based on an intelligent algorithm, and graded early warning is automatically triggered through a multi-stage threshold comparison mechanism. According to the invention, the sensing precision, the monitoring efficiency and the early warning timeliness of the safety state of the waste slag field are effectively improved, and a reliable technical means is provided for geological disaster prevention and control.

A mine geological disaster early warning device with a damping effect disclosed by the present invention comprises a monitoring part, the monitoring part comprises a support frame, a monitoring camera, a controller, a master control system and an alarm device, the upper part of the support frame is fixedly provided with the monitoring camera and the controller, and the bottom of the support frame is provided with an inner support cylinder which cannot rotate; the inner supporting cylinder wraps the periphery of the bottom of the supporting frame and is coaxially and rotatably connected with an outer supporting cylinder, and a hollow air bag is fixed outside the outer supporting cylinder. When rolling stones, debris flow or landslides continue to move downwards under the action of gravitational potential energy to collide with the air bags in the using process, due to the fact that the air bags are eccentrically arranged relative to the outer supporting barrel, the trend of enabling the air bags to rotate is known through stress analysis, and therefore the moving direction of the collided rolling stones, debris flow and landslides can be changed; discharging is convenient, accumulation is not prone to occurring, and then damage and vibration caused by front impact are reduced; and on the other hand, after the air bag is impacted, the impacted part shrinks.