612 results about "Soil horizon" patented technology

The invention provides a geological data driving path optimization and settlement prediction method for pipe jacking construction, and relates to the technical field of artificial intelligence. The method comprises the following steps: firstly, acquiring sparse drilling point location geological data, constructing a geological data set including soil layer types, forming continuous geological feature tensors through multi-dimensional interpolation, and generating a path vector sequence by combining starting and ending points and building distribution to represent crossing tracks of different paths under geological conditions; and constructing a path graph topological structure through a graph coding neural network, performing feature propagation, obtaining a path comprehensive score vector, and screening an optimal path meeting structural integrity and settlement response constraints. Further identifying settlement trend sensitive points by utilizing the settlement risk prediction values and the accessibility scores of the nodes, constructing a settlement trend map and calculating settlement transaction coefficients. And the transaction coefficient is fed back to a path generation link and is used for iteratively optimizing path sampling density and node distribution so as to realize dynamic correction and stable convergence of a path scheme.

The invention belongs to the field of soil rock engineering, and provides a three-surface integrated geologic structure modeling method for a deep and large foundation pit in a river-adjacent region, which comprises the following steps: acquiring physical and mechanical parameters and hydrogeological information of the deep and large foundation pit in the river-adjacent region; dividing spatial distribution of different soil layers and rock stratums; describing the influence of water level time variation on the pore water pressure and subsurface erosion of the surrounding rock of the foundation pit through an unstable seepage equation; dividing a finite element or finite difference grid, and applying a dynamic water level and ground load boundary condition; gradually unloading and analyzing the evolution of an underground water flow field and a soil-rock deformation field in each excavation step, and enabling the water surface-ground-soil-rock surface coupling effect to penetrate through the whole excavation process; and numbering the support members, sequentially simulating local failures of the support members, recording the maximum horizontal displacement, the maximum vertical displacement or the change curve of the safety coefficient along with the number of the failure members after each failure of the foundation pit, quantifying the redundancy of the support system, and identifying key members. According to the scheme, the accuracy of the model is improved.

The invention discloses a standard soil layer sequence division method for foundation soil. The method comprises the following steps: generating a unified engineering geologic feature data set; forming a multi-dimensional engineering geologic feature sample set; obtaining parameters of the trained improved ultra-dense connection neural network model; obtaining an initial drilling sequence prediction result; encoding the initial drilling sequence prediction result into a drilling sequence embedding vector according to a drilling sequence, and generating a cross-drilling sequence alignment matrix; and generating a standard soil layer code and corresponding confidence information to obtain a standard sequence division result. According to the invention, full-process automatic integration of design, modeling and construction is supported, and consistency, rechecking performance and digital management capability in engineering application are improved.

The utility model relates to the technical field of geological survey marking, and discloses a geological survey marking device convenient to install, which comprises a main body structure and an auxiliary structure, the outer wall of the main body structure is fixedly connected with the auxiliary structure, the main body structure comprises a shell, and a storage box is slidably connected in the shell. A strong spring is fixedly connected to the inner wall of the storage box, one end of the strong spring is fixedly connected with a push plate, a plurality of sets of marking rods are vertically placed in the storage box, the auxiliary box is placed on the ground needing to be marked, a control motor is started to work, the output end of the motor drives a drill rod and a ground breaking drill bit to rotate, and the marking rods are arranged on the ground. Then the lifting air cylinder is controlled to work, the output end shrinks to drive the carrying plate to move downwards, meanwhile, the ground breaking drill bit continuously moves downwards when drilling the ground, the ground breaking drill bit can conveniently go deep into the deeper position of the ground and crush a hard soil layer, in this way, workers can conveniently insert the marking rod, and the marking rod can go deep into the soil layer and is not prone to falling down.

The invention discloses an AI and algorithm fused intelligent geological layering system and method for geotechnical engineering investigation, and the method comprises the steps: data importing and preprocessing, data verification and gross error elimination, automatic classification of related / non-related variables, cleaning and iterative updating of layer mean values and boundaries, and hierarchical division. According to the method, the data is automatically cleaned, the layer group is verified, the main layer / sub-layer / sub-layer / interbed is divided, the layering accuracy and efficiency are improved, the artificial intelligence technology is applied, and the layering efficiency is improved. Technicians are replaced to complete the heavy work flow of drawing grass sections, manually layering, inputting soil layer information into a computer, manually judging the rationality of in-situ test, geotechnical and rock test data and layering, modifying sketches, secondarily proofreading the rationality of results and completing division, and the exploration efficiency is improved.

The invention discloses a slope soil layer drilling device, and relates to the field of soil layer drilling, the slope soil layer drilling device comprises a drilling guide sleeve for a drill rod to rotatably and movably pass through, and the outer wall of the drilling guide sleeve is connected with a limiting mechanism for limiting and supporting the drilling guide sleeve in a drill hole; a fine adjustment deviation rectifying mechanism is movably arranged below the limiting mechanism; the limiting mechanism is used for being supported in a drill hole, and the fine adjustment deviation rectifying mechanism is used for conducting fine adjustment deviation rectifying and reducing the risk of hole inclining and the like. When the drilling device is used, a certain supporting effect can be achieved on the side wall of a drilled hole, disturbance of a drill bit on the periphery of the soil body of the drilled hole in the drilling process is reduced, the risk of hole collapse is reduced, deviation correction adjustment is conducted in the drilling process, unqualified holes such as inclined holes are avoided, and the construction quality is guaranteed; and the drilling device is convenient to mount and dismount, and can further guarantee the construction period and quality and save the construction cost in the construction of soil bodies with uneven geology such as slopes.

The invention belongs to the technical field of foundation settlement monitoring, and discloses a layered monitoring device and method for deep foundation settlement, a combined system of springs and steel strings is innovatively adopted, the measuring range and the application range of a vibrating wire type monitoring structure are expanded, and checking calculation results show that the vibrating wire type monitoring structure can meet the requirement for foundation deformation monitoring; a hard plastic anchoring plate is adopted, traditional point contact anchoring is converted into a surface bearing mode, it is ensured that the device and a soil layer are integrally solidified and synchronously settled through backfill soil pressure, mechanical transmission errors caused by indirect measurement are effectively eliminated, and the physical authenticity and precision of monitoring data are remarkably improved; the vibration excitation and vibration pick-up integrated module is used for converting tiny deformation into high-stability frequency signals with high anti-interference capacity, dependence on manual on-site reading is eliminated, and all-weather and unattended automatic real-time monitoring of foundation settlement is achieved.

The invention provides a physical information long-short-term memory network site seismic response prediction method based on kinematics derivative constraint and data folding. The method comprises the following steps: collecting and preprocessing bedrock and ground surface seismic oscillation data; displacement, speed and acceleration supervision labels are constructed through surface acceleration integration; constructing a long-short-term memory network containing a data folding and unfolding module; physical constraint loss is constructed by utilizing kinematics derivative relations between displacement and speed and between speed and acceleration, and a network is trained by combining an adaptive weight strategy; and outputting earth surface displacement, speed and acceleration time history by adopting the trained network. According to the method, under the condition that constitutive parameters of a soil layer are not explicitly given, physical consistency constraint can be applied to the field seismic response prediction process, the long-time program train training burden is reduced through sequence folding processing, and the method is suitable for field seismic response prediction.

The invention relates to the technical field of soil profile recognition, in particular to a soil profile recognition method and system based on multi-source information fusion and artificial intelligence. Synchronously acquiring image data, physicochemical property sequence data and mechanical resistance sequence data of a field soil profile through a data acquisition assembly; performing data preprocessing and spatial registration on the data; extracting visual features of the image and sequence features of the sensor data, and then performing feature level fusion to form a multi-source fusion feature vector; inputting into a pre-trained soil layer identification model to obtain soil profile layering result information; according to the scheme, the reference image data, the physicochemical property sequence data and the mechanical resistance sequence data are fused, unified decision making is carried out through the soil layer recognition model, the problems that a traditional method is high in subjectivity and low in efficiency are solved, objective, efficient and accurate layered recognition of the soil profile is achieved, and the accuracy of layered recognition of the soil profile is improved. And the digitization and standardization process of soil investigation is powerfully promoted.

The invention provides a coastal area foundation pit dewatering system and method, and belongs to the technical field of foundation pit dewatering, the coastal area foundation pit dewatering system comprises a foundation pit, a plurality of light well points, a deep tube well and an electroosmosis auxiliary module, and the light well points are annularly arranged in a shallow layer area on the periphery of the foundation pit; the deep tube well extends to a deep area from the ground; and a plurality of electro-osmosis auxiliary modules are arranged in the peripheral clay layer area of the foundation pit. The annularly-arranged light well points evenly intercept shallow underground water around the foundation pit, the deep pipe wells can rapidly reduce the deep underground water level, and the drainage problem of a low-permeability clay layer area is effectively solved through the synergistic effect of the arranged electro-osmosis auxiliary modules and the well points / pipe wells; the synchronous precipitation uniformity of the complex soil layer is improved, layered targeted precipitation design is adopted in a shallow area, a deep area and a clay layer area, and the overall precipitation efficiency is improved. According to the foundation pit dewatering system in the coastal area, the problem that in the prior art, in the environment with complex hydrogeological conditions, the dewatering efficiency of a single dewatering measure is low is solved.

The invention relates to the technical field of foundation settlement monitoring, and discloses a BIM-based foundation settlement dynamic monitoring system and a use method, and the BIM-based foundation settlement dynamic monitoring system comprises a BIM parametric modeling module, a dynamic monitoring module and a settlement compensation regulation and control module. The BIM parametric modeling module generates a three-dimensional model containing rock-soil mechanical parameters, underground water level data and soil layer distribution information, and receives real-time data to update a settlement state; the dynamic monitoring module collects foundation key node vertical displacement, bearing structure internal stress and edge horizontal inclination angle data and transmits the data to the BIM module and the settlement compensation regulation and control module. The settlement compensation regulation and control module comprises a compensation decision unit, an execution mechanism unit and a feedback control unit, and a'monitoring-decision-execution-feedback 'closed-loop control link is formed. According to the invention, the three modules are integrated to realize full-flow dynamic linkage of foundation settlement, so that the problems that a traditional geologic model is disjointed with monitoring data and settlement is difficult to compensate in real time are solved, and the construction precision and the structural stability are improved.

The invention discloses a response test method and device for soil layer deformation and tunnel stress in foundation pit excavation, and relates to the technical field of underground engineering tests. The method comprises the following steps: acquiring engineering geology and tunnel structure parameters, and constructing a geological tunnel coupling similarity model embedded with a layered sensing array; step-by-step excavation is adopted to simulate foundation pit construction, and soil layer displacement strain, tunnel stress contact pressure and excavation disturbance parameters are synchronously collected through multiple channels; constructing a deformation stress coupling prediction model and an excavation disturbance quantification model; and constructing a dynamic coupling response model based on the two, and outputting a dynamic coupling curve of soil layer deformation and tunnel stress. The device comprises a model box body, a data processing host and a display terminal, a layered sensing array, a dynamic loading device, a servo excavation mechanism and a multi-channel data acquisition instrument are arranged in the box body, and the whole test process integrated operation can be realized. According to the method, the dynamic coupling rule can be accurately captured, and technical support is provided for safety assessment and parameter optimization of underground engineering construction.

The invention discloses a rock and soil medium parameter testing and reinforcing method which comprises the following steps: step 1, arranging a plurality of in-situ testing holes and object detection lines on a side slope, a foundation or a filling site, and performing in-situ tests and geophysical prospecting tests, including in-situ drilling shear tests, penetration tests and pore pressure observation, the mechanical property, the permeability characteristic and the pore water pressure parameter of the soil layer are obtained; 2, according to the obtained soil layer parameters, the needed initial grouting pressure, flow and slurry concentration are calculated; 3, grouting equipment is used for injecting grout into the soil layer, and the deformation amount, the pressure change and the permeability change of the soil layer are monitored in the grouting process; 4, according to data monitored in real time, the grouting pressure and flow are adjusted so as to ensure the grouting uniformity and the reinforcing effect, compared with a traditional empirical grouting method, the method has the advantages that the reinforcing uniformity and the anti-seepage effect can be remarkably improved, energy consumption and risks are reduced, and good universality and engineering application value are achieved.

This application discloses a method, apparatus, and storage medium for calculating earthwork volume in site leveling. The method includes: dividing the site leveling area into cells and obtaining earthwork data for each cell, including information on the soil within the area of ​​each cell from the top elevation of different soil layers to the site leveling design elevation; constructing a three-dimensional geological model and correcting the excavation and filling volumes of each cell in the earthwork data based on the three-dimensional geological model; calculating the excavation and filling volumes of each soil layer based on the corrected excavation and filling volumes, and for each soil layer, accumulating the excavation volumes of all cells to obtain the total excavation volume of that soil layer; modifying the site leveling design elevation in the site leveling design data, recalculating, and obtaining multiple sets of earthwork volume data; calculating the project cost based on the multiple sets of earthwork volume data, and selecting the optimal earthwork volume data based on the project cost. This application improves the accuracy of earthwork volume calculation by interpolating existing layer points to construct a refined three-dimensional geological model and correcting the designed excavation and filling volumes.

The invention discloses a static sounding intelligent monitoring and risk early warning system based on the Internet of Things, which is characterized in that when static sounding equipment executes investigation operation, data is collected in real time through an Internet of Things module, and a probe is maintained to penetrate according to a design track based on regulation and control parameters, and specifically, a three-dimensional coordinate system is established in a space where an investigation site is located; data are collected based on the three-dimensional coordinate system and the Internet of Things, and the track boundary and the penetration speed of the static sounding probe are calculated; and obtaining a design depth reference point of the exploration area. Relates to the technical field of geotechnical engineering investigation. Second-level acquisition and transmission of probe tracks, soil layer parameters and attitude angles are achieved through the Internet of Things module, the problem of data lag of traditional exploration is solved, and soil layer sudden change and probe offset can be captured in real time. The trajectory boundary is modeled based on the three-dimensional coordinate system, and the soil layer layering mutation degree and the probe attitude are cooperatively regulated and controlled, so that data distortion caused by probe offset and parameter abnormality is reduced, and the exploration precision is improved.

The invention discloses a subway tunnel response model test method and device under underground water level variation, and the method comprises the steps: obtaining the stratum investigation parameters of a target area, determining a similar scale according to the size of a model box, determining the proportion of similar materials of a soil layer and a tunnel segment through an orthogonal test method, and carrying out the test optimization, and laying monitoring equipment for the model box. And collecting tunnel structure mechanical response parameters by taking water level changes as variables. The model box comprises a main body, a water supply tank and a water pumping device and can simulate geological environment and underground water level variation and monitor equipment coverage strain, pressure, pore water pressure and the like. The method truly simulates stratum and hydrological conditions through similar materials and water level regulation and control, systematically studies the dynamic influence of underground water level change on the tunnel structure, meets the complexity of the actual operation environment, and provides a scientific basis for subway tunnel design and risk assessment.

A method for seismic fragility analysis of a shield tunnel considering surface surcharge effects includes the steps of: determining mechanical property parameters of tunnel materials and physical-mechanical parameters of soil layers; investigating case studies of surface surcharge to define surface surcharge scenarios; selecting seismic waves and performing one-dimensional equivalent linear site response analysis on soil conditions; establishing a dynamic finite element numerical model of a soil-tunnel system considering surface surcharge; defining ground motion intensity measures (IM), tunnel damage measures (DM), and damage states (DS); and establishing probabilistic seismic demand models for the tunnel under various surface surcharge effects. Based on key parameters, seismic fragility curves for tunnel structures under surface surcharge effects are established. Through a nonlinear incremental dynamic analysis method, this method establishes the finite element numerical model of the soil-tunnel system, allowing for quantitative assessment of tunnel seismic fragility and seismic performance under various surface surcharge effects.

The invention relates to the technical field of data processing, and discloses a method for accurately predicting the concrete dosage of a cast-in-place pile in foundation pit engineering. The method comprises the following steps: collecting the pore-forming arrival time of each depth section of an initial calibration pile group, the soil layer type, the slurry density and the actual concrete dosage to establish a database, calculating the exposure duration of a hole wall, and establishing a pore diameter expansion coefficient time sequence evolution relationship of soil layer classification through power function fitting; and obtaining the soil layer type of each depth section of the to-be-predicted pile and the estimated exposure duration, substituting into the evolution relationship, and accumulating to obtain the total predicted concrete dosage. According to the method, the soil layer classification time sequence evolution relation of the hole diameter expansion coefficient along with the hole wall exposure duration is established, and the mud density correction term and the dynamic parameter updating mechanism are introduced; the technical problems that an existing cast-in-place pile concrete dosage prediction method cannot accurately reflect the hole wall state time-varying characteristic, ignores the soil layer differential response rule and lacks the construction process self-adaptive calibration capacity are solved.

The invention discloses a pile-soil coupling loss prediction method based on soil layer quantification and a neural network. The method comprises the following steps: firstly, through parameterized finite element-infinite element coupling numerical simulation, extracting a pile-soil coupling loss quantitative index-transfer function amplitude ratio; converting the multi-layer soil body distribution information into standardized soil layer distribution characteristic parameters through a normalized coordinate system; then, a neural network model is constructed, pile body parameters, load parameters, characteristic frequency points and soil layer distribution characteristic parameters serve as input, and a transfer function amplitude ratio serves as an output target for training; and finally, rapid and accurate prediction of the pile-soil coupling loss is realized through the trained model. According to the method, effective quantification of complex soil layer space distribution is innovatively realized, and the problems of insufficient precision and low efficiency of a traditional method in pile-soil dynamic coupling loss prediction are solved.

Disclosed is a method for assessing nitrogen leaching risk based on farmland soil pressure, including the following steps: acquiring soil drilling pressure data from a plurality of soil layers of different depths on soil to be tested using a soil drilling device, to obtain raw soil drilling pressure data; comparing a calibration curve with a raw soil drilling pressure curve; setting an interquartile range (IQR) coefficient based on a first fluctuation factor and a second fluctuation factor, and constructing a box plot of the raw soil drilling pressure data based on the IQR coefficient; and determining a peak soil drilling pressure according to the box plot of the raw soil drilling pressure data, and determining nitrogen leaching risk according to a depth interval of soil layer. The box plot is utilized to filter out abnormal values, ensuring the accuracy of assessing the nitrogen leaching risk in soil.

The application provides a local surge-induced adjacent reef seabed topography evolution model test device and test method, and the device comprises a soil box, a soil layer, a runner, a handle, a support, a fixing ring, a hose, an adjusting pipe, a pore pressure gauge, a displacement gauge and a partition plate. A constant pressure water head is set at one end to simulate a far-field water pressure, a hose fixed on the runner periodically rises and falls at the other end, a periodic surge pressure is formed in the soil layer on the right side of the partition plate, and the local scouring and far-field pressure seepage migration effects of the local surge on the adjacent reef seabed are simulated. The pore pressure gauge is used to determine the pore pressure change of the stratum to analyze the local scouring force and the far-field stratum seepage force change of the adjacent reef seabed, and the displacement gauge is used to determine the stratum displacement to analyze the local scouring deformation and the far-field pressure seepage migration law of the adjacent reef seabed. The influence of the local surge cycle, amplitude and pressure sudden increase point position on the surface morphology of the adjacent reef seabed is researched, and analysis basis is provided for the adjacent reef seabed topography evolution, far-sea island reef construction and erosion protection.

This invention provides an indoor testing device and method for the surface impermeability and erosion resistance of ecological slope protection. It includes a slope simulation device with a rainfall simulation device mounted above it. The slope simulation device comprises an inclined soil-rock bearing device and a slope soil-rock layer, on which a vegetation layer is arranged. The slope simulation device is supported by a slope adjustment device. The erosion material collection device includes a mud-water collection tank, a collection trough, and a collection container. The mud-water collection tank collects surface runoff and erosion material from the vegetation layer; the collection trough collects seepage water between the vegetation layer and the slope soil-rock layer; and the collection container collects mud-water that has infiltrated below the slope soil-rock layer. This invention considers the runoff at the interface between the substrate and the slope, comprehensively analyzes the infiltration patterns of rainfall on the slope, and provides data and basis for numerical simulation and analysis processes. It provides a more accurate quantitative evaluation of the impermeability and erosion resistance of vegetation, and is more rigorous than existing testing methods.

The invention discloses a site characteristic and displacement loading-based on-bridge ballastless track seamless track response simulation method under an earthquake. The method comprises the following steps: S1, constructing a site soil layer model containing a non-uniform soil layer; s2, inputting transverse and vertical seismic waves at the boundary of the field soil layer model at the same time, and simulating dual-path seismic oscillation transmission; s3, extracting a three-way displacement time history of surface nodes of the field soil layer model; and S4, inputting the three-way displacement time history into a bridge-track coupling model, and obtaining the dynamic response and damage state of the track structure. According to the method, the amplification and attenuation effects of a real site on seismic oscillation can be simulated, and the simulation precision of a real seismic situation is improved, so that the prediction capability of local failure and residual deformation of the ballastless track under a strong earthquake is improved.

The invention relates to a depth operator digital intelligent model-based soft foundation consolidation degree rapid deduction method, which comprises the following steps of: obtaining soil layer thickness, layered structure, consolidation coefficient of each layer and drainage boundary condition of a soft soil foundation, and carrying out dimensionless processing on physical depth and physical time; generating a dimensionless consolidation coefficient field sample which changes along with the dimensionless depth, and dispersing the dimensionless consolidation coefficient field sample at a plurality of fixed depth positions; inputting the dimensionless time-depth coordinate into a backbone network of the physical information-depth operator network, inputting the consolidation coefficient discrete vector and the soil layer distribution parameter into a branch network of the physical information-depth operator network, and fusing the output of the backbone network and the output of the branch network to obtain an estimated value of the dimensionless hyperstatic pore water pressure; and training the physical information-depth operator network based on the physical information loss function to obtain a soft soil foundation consolidation prediction model. According to the method, rapid and accurate deduction of the consolidation process can be realized.

The invention relates to the technical field of black land protection, and discloses a cultivated land quality monitoring system based on black land protection. The system comprises a data acquisition module which is used for obtaining the position and time of a sampling point, the organic matter content and the soil layer thickness, and calculating quality evaluation indexes to generate an evaluation set; the feature extraction module is used for extracting quality evaluation indexes and positions, sorting adjacent point pairs according to spatial distances, and marking consistent and difference sections to obtain a feature consistency partition marking set; the state evaluation module is used for acquiring a pH value and water content time sequence of the sampling points in the section with consistent characteristics, and evaluating the degradation influence degree by combining the farming intensity to generate a comprehensive analysis result; the risk early warning module is used for identifying abnormal points with degradation response values greater than a reference value and located in a difference section to form an abnormal point set; and the result output module is used for acquiring abnormal points and information, marking deterioration risk point locations and generating monitoring and early warning results. The system can comprehensively monitor the quality of black land cultivated land and perform early warning in time.

The invention discloses a membrane bag sand levee slope settlement prediction method and system based on a neural network, and belongs to the technical field of prediction systems.The method comprises the steps that construction parameters, foundation monitoring data and geological exploration data of a membrane bag sand levee slope are obtained; performing feature fusion by analyzing correlation between the construction parameters and the compression amount of each foundation soil layer in the time dimension and between the foundation monitoring data and the compression amount of each foundation soil layer to obtain fusion time sequence features; and on the basis of the geological exploration data, using a settlement prediction model and fusion time sequence characteristics, predicting each compression amount by analyzing the pore drainage rate of each foundation soil layer, outputting a settlement prediction result of the membrane bag sand bank slope, identifying the settlement abnormal risk of the membrane bag sand bank slope, and outputting the settlement risk grade of a preset construction point. Therefore, by implementing the method and the device, the problem that the predicted total settlement amount of the film bag sand bank slope is not accurate enough due to the fact that the influence of the bank slope foundation structure on the settlement amount in the construction process is not completely considered in the prior art can be solved.

This application relates to the field of dredging equipment technology and discloses a dredger cutter head device for dredging underwater sediment-laden hard soil layers. The device includes a linkage sleeve, with a cutter head fixedly mounted at one end of the linkage sleeve. A mud inlet pipe is also mounted on the cutter head, located below the linkage sleeve. Four cutter motors are installed inside the linkage sleeve to drive the cutter head rotation. A gear transmission mechanism is also fixedly installed inside the linkage sleeve. This design with four cutter motors significantly increases the total driving power of the cutter head compared to existing equipment with only one motor, thereby improving cutting efficiency and effectively reducing and preventing phenomena such as "cutter rolling," "cutter running," and "cutter slippage" during the cutting process, achieving effective cutting capability for slab sand.

The invention discloses a test device and a test method for researching seepage settlement of a water-rich tunnel, belongs to the technical field of geotechnical engineering tests, and aims to disclose a disaster-causing mechanism of the water-rich tunnel and a difference between the disaster-causing mechanism and a settlement disaster-causing process of a typical engineering area. Comprising a model box, a tunnel model, a water injection-seepage system and a settlement-deformation monitoring system, the model box is filled with a soil layer, and the tunnel model is buried at the designed depth of the soil layer; the water injection-seepage system is buried in a soil layer, is used for injecting water into the soil layer to simulate a seepage process, and comprises a seepage pipe and a water injection pipe; the settlement-deformation monitoring system comprises settlement measuring rods for monitoring stratum settlement, and the settlement measuring rods have various specifications; the dial indicator is used for monitoring ground surface settlement; the soil pressure gauge is used for monitoring soil pressure; the pore water pressure gauge is used for monitoring pore water pressure; a moisture meter for monitoring moisture migration; and the reflective monitoring target spot is used for monitoring tunnel convergence.

The invention belongs to the field of engineering geology, particularly relates to an engineering geology soil layer name judgment system, method and equipment carried on a static sounding instrument, and aims to solve the problem that real-time dynamic soil layer name presumption cannot be carried out in an existing geotechnical engineering investigation technology. The system comprises a spectrum acquisition module which comprises a spontaneous light source and a multispectral sensor and is integrated between static sounding probe rods; the data processing module is used for analyzing the spectral data through a neural network and processing end resistance / side resistance / friction resistance ratio data of static sounding through a regression algorithm; and the data output module compares the two types of judgment results: outputting a single soil layer name when the two types of judgment results are consistent, and outputting double results and converting the double results into standard results for display when the two types of judgment results are inconsistent. According to the method, the soil layer name is presumed by adopting a real-time dynamic method, the detected sample does not need to be remodeled, the recognition accuracy and efficiency are improved, the model is fed back and optimized according to a new test set, the prediction precision is kept, and the detection speed is improved.

The application relates to the technical field of composite foundation bearing capacity, and discloses a multilayer composite foundation bearing capacity detection device and a detection method thereof. The device comprises a sensor array module, a data processing module, a bearing capacity analysis module, a calibration output module, a communication module and a user interface module. Static force parameters of the foundation are collected through a static sounding sensor, dynamic parameters of the foundation are collected through a dynamic sounding sensor, and deformation parameters of the foundation are collected through a fiber grating sensor, so that integrated collection of multi-source static and dynamic parameter data is realized. Meanwhile, a wavelet transform algorithm is used for noise filtering, and a K nearest neighbor interpolation algorithm is used for data filling, so that standardized foundation parameter data is generated, the consistency and accuracy of data preprocessing are ensured, and the soil layer is intelligently identified and hierarchically divided through K-means clustering algorithm-based foundation hierarchical division processing of the standardized foundation parameter data.