1370 results about "Model test" patented technology

The present disclosure relates to the technical field of landslide hazard model tests, and in particular to a landslide model test method and device for realizing multi-variable synchronous monitoring. In the test device, a soil slope simulation unit is configured to pile up a soil slope and simulate different inclinations of the slope. A rainfall simulation unit is configured to simulate rainfall of different intensities and induce a landslide. A runoff-seepage separation unit is configured to realize separation of runoff from seepage of the slope under the effect of rainfall. A monitoring module is configured to monitor runoff and seepage flow rates of the slope, changes in water content and pore water pressure within the slope, and a morphological change of the slope under the effect of rainfall, to obtain a mechanism of rainfall-induced landslide deformation and damage based on changes in the flow rate.

The invention relates to the technical field of dredge pump performance analysis, and discloses a numerical simulation and model test-based dredge pump performance analysis method, which comprises the following steps of: planning an analysis process, and determining numerical simulation (dredge pump internal flow field simulation) and model test contents (actually measured performance data under different working conditions); determining working condition types according to design parameters and working conditions; generating a performance analysis process set and determining an execution sequence; generating a simulation parameter setting list and a test scheme list of each working condition; and associating the data to generate an overall scheme. The method further relates to working condition analysis boundary determination, working condition type subdivision, dynamic adjustment of the process, test rule optimization, database construction and the like. According to the method, comprehensive and accurate analysis of the dredge pump performance is achieved through multi-dimensional data integration and a dynamic mechanism, the analysis efficiency and reliability are improved, and the method is suitable for evaluation and optimization of the dredge pump performance.

The utility model relates to the technical field of model tests, and discloses a landslide damage simulation test device which comprises a model test box, a rainfall frame, a hydraulic assembly, a plurality of spraying assemblies, a water tank assembly and a constant temperature system. The angle of the landslide model box can be adjusted through the hydraulic machine so as to change the slope of a model test landslide soil body; the multiple spraying assemblies are arranged at the top of the rainfall frame and located over the model test box, the output ends of the spraying assemblies aim at a test soil body in the model test box, the influence of rainfall on landslide slippage is simulated by adjusting the spraying size, and the constant temperature system is arranged at the top of the model test box and used for regulating and controlling the temperature of the test soil body. The constant temperature system is used for measuring the influence of the dry-wet cycle effect on the landslide soil body.

The invention discloses a transformer current rising test data analysis method based on deep learning, and relates to the technical field of power transformation equipment, and the method comprises the following steps: S1, data collection and preprocessing; s2, performing feature engineering; s3, dividing a data set; s4, model selection and architecture design; s5, model training; s6, performing model verification and hyper-parameter tuning; s7, testing and evaluating the model; s8, performing anomaly detection and adaptive learning; s9, result interpretation and model interpretability; and S10, continuously monitoring and updating the model. According to the transformer current rising test data analysis method based on deep learning, based on deep learning, in combination with technologies of feature engineering, model selection and architecture design, anomaly detection and adaptive learning and the like, the accuracy and robustness of a transformer current rising test are improved through comprehensive data analysis; the generalization ability of the model for unseen data can be improved, and the model can adapt to environmental changes in real time.

The invention relates to the technical field of geological disaster model tests, in particular to a cold region soil engineering collapse monitoring device, system and method.The cold region soil engineering collapse monitoring device comprises an outer box, an inner box and a side slope model, the side slope model is arranged in the inner box, and the outer box is used for containing the inner box; the rainfall assembly is movably mounted on the inner box and is used for controllably and quantitatively spraying water or mist towards the inner box so as to simulate a rainfall or plum rain state; the vibration assembly is arranged at the bottom of the side slope model, the side slope model is adjustably installed on the vibration assembly, and the vibration assembly is used for enabling the side slope model to generate vibration so as to simulate the vibration state; the device further comprises an electromagnetic force loading assembly, and the electromagnetic force loading assembly is arranged on the outer side of the side slope model and used for applying loads in at least one direction to the side slope model. The device is used for simulating the slope stability of the cold region soil engineering under the multi-factor coupling effect.

The invention provides a circular through karst cave physical model test device and method, belongs to the field of physical property test analysis, and is used for preparing a karst foundation model test block and carrying out a simulation experiment. The circular through karst cave physical model test device comprises a model frame with an opening in the top and a reinforcing structure arranged on the periphery of the model frame. The device further comprises a cylindrical cavity reserved part, the cavity reserved part is located in the model frame, the two ends of the cavity reserved part penetrate through the model frame, rock mass similar materials are poured into the model frame to form a karst foundation model test block, and after pouring is completed, the reserved part forms a penetrating cylindrical cavity in the karst foundation model test block. The device is combined with the method, so that the simulation precision of the model test block on the karst foundation is improved, the influence of the karst cave on the stability of the foundation is conveniently and intuitively analyzed, and a powerful experimental basis is provided for design and treatment of the karst foundation.

The invention relates to the technical field of underground engineering groove wall stability physical simulation, and discloses a model test device and method for stratum excavation and grouting reinforcement, and the model test device comprises a grooving construction module, a grouting support module and a dynamic monitoring module. The device adopts a pressing plate method to simulate a grooving excavation process, so that the device conforms to an actual excavation working condition from top to bottom; a servo motor drives a power lead screw to drive a model groove to move downwards, so that a free face is formed in a sand layer, and the actual excavation working condition is simulated; a water tank for storing fresh slurry is pressurized by using an air compressor, so that the slurry overflows from the hollow model groove section, and the permeation and invasion process of the slurry is simulated; and a water and soil pressure gauge and a matched acquisition device are arranged in the sand layer, and a soil displacement field is obtained by utilizing a particle image velocity measurement system, so that the visualization of the whole process of excavation-grouting-invasion is realized. It is ensured that simulation results are highly matched with actual working conditions, and accuracy and reliability are improved.

The invention discloses a method and a system for predicting the lumpiness of open-air throwing blasting, and relates to the technical field of rock blasting engineering. The invention discloses a new calculation relation about a lumpiness similarity proportion, relates to the technical field of open-air loose blasting mining, and can predict blasting lumpiness of projects such as mines, tunnels and the like by scaling a lumpiness distribution proportion. The method comprises the following steps: firstly, acquiring a rock sample from a blasting site, measuring parameters such as rock density and fracture toughness, and acquiring blasting parameter information of a to-be-blasted area; and then, a numerical simulation model under an open-air throwing blasting similar material is constructed by using a numerical simulation method, the change rule of blasting fragmentation lumpiness along with explosive unit consumption in a scale model test is studied, and the blasting lumpiness in a field blasting area is predicted according to the blasting lumpiness similarity ratio. According to the method, the change rule along with the unit consumption of the explosive is analyzed, the utilization rate of crushing energy of the explosive in surface blasting engineering is improved, reference is provided for blasting lumpiness control, and prediction of field blasting lumpiness before blasting is achieved.

The invention discloses a railway tunnel full-life-cycle model test system and test method considering train vibration, and relates to the technical field of railway tunnel engineering. The model test system adopts modular design and comprises a box frame module, a constant-pressure loading module, an excitation system module, a seepage system module and a monitoring system module. The test method comprises the steps of physical similar model laying, constant-pressure loading control, tunnel excavation and supporting, vibration loading and data monitoring analysis. By accurately simulating an initial stress field and train vibration loads in the construction and operation stages of the tunnel, dynamic monitoring of stress strain, deformation and damage processes of the tunnel surrounding rock and the lining structure in the whole life cycle is achieved. The device has the advantages of compact structure, modular design, high loading precision and stability, real simulation and the like, and a scientific basis can be provided for the fields of performance evaluation, structure optimization, reinforcement design and the like in the whole life cycle of the railway tunnel.

A large-scale underground shield docking model test platform and a test method using the same are provided. The test platform includes a test soil tank, a partition wall, a shield docking model, and a freezing system. The test soil tank is of an underground foundation pit structure, the partition wall is disposed in the test soil tank to separate the test soil tank into a filling area and a non-filling area. The shield docking model is disposed in the filling area and is a reduced-scale test model. The shield docking model is provided with the freezing system, including a refrigeration system, a coolant circulation system, and freezing pipes. The freezing pipes are arranged on the shield docking model and are connected to the refrigeration system through the coolant circulation system. The refrigeration system is placed on a laminate in the non-filling area of the test soil tank.

The invention relates to the technical field of fishways, in particular to a fishway overall model test method which comprises the following steps: S1, establishing a fishway overall model design scheme based on a preliminary design scheme; s2, a fishway overall model is manufactured based on the fishway overall model design scheme, the fishway overall model is designed to be a normal model, the fishway overall model is designed according to a gravity similarity criterion, and geometric similarity, water flow motion similarity and dynamic similarity checking is conducted on the fishway overall model design scheme; and S3, performing a fishway overall model test on the basis of the fishway overall model, and optimizing the fishway overall arrangement structure scheme so as to obtain a final fishway overall structure scheme. According to the fishway overall model test method, the fishway overall arrangement structure scheme is optimized, so that the final fishway overall structure scheme is obtained, and a theoretical basis is provided for fishway overall optimization.

The invention discloses a multivariate monitoring data fusion method and system for a slope tunnel model test, particularly relates to the technical field of geotechnical engineering physical model test, and aims to solve the problem that dynamic stress waves in an existing model test integrating static and dynamic measurement cause static monitoring signal distortion and further influence the model state evaluation accuracy. Coupling interference in static signals is identified by synchronously collecting dynamic excitation and static response signals; obtaining signal samples before and after a model state sudden change event to perform frequency domain comparative analysis, identifying characteristic frequency components related to sudden change, and evaluating a coupling interference dominant frequency band; separating an effective static response component from the original static signal based on the frequency band; and finally, fusing the effective component with a soil dynamic parameter derived from dynamic excitation to generate comprehensive stability evaluation data. Dynamic interference is effectively suppressed, the authenticity of static signals is improved, and the reliability of model stability state evaluation is improved.

A compressed air energy storage underground cavern model test system designed according to a preset joint disclosed by the present invention comprises a simulation cavern, a loading system, a measurement system and a protection device, the measurement system comprises a plurality of temperature sensors, a plurality of pressure sensors, a plurality of crack meters and a plurality of optical fiber gas sensors, and the simulation cavern comprises a steel cylinder sealed by a sealing door. A deformation simulation layer, a lining layer, a leveling layer, a geotechnical cloth layer and a flexible sealing layer are arranged on the inner wall of the steel cylinder, a plurality of longitudinal exhaust pipelines are embedded in the joint of the deformation simulation layer and the lining layer, a plurality of exhaust pipes are inserted into the cylinder wall of the steel cylinder, each exhaust pipe is communicated with one longitudinal exhaust pipeline, a plurality of longitudinal prefabricated cracks are distributed in the lining layer, and the longitudinal prefabricated cracks are communicated with the geotechnical cloth layer. A crack meter is embedded in the middle of each longitudinal prefabricated crack, and the simulation cavern is communicated with the loading system through an air inlet in the sealing door. The test system is low in cost, convenient to operate, large in scale, comprehensive in test item, high in test precision and high in reference value for actual engineering.

The invention provides a tunnel surrounding rock time sequence deformation monitoring data anomaly detection method and device combined with an LSTM and an auto-encoder, and a medium. The tunnel surrounding rock time sequence deformation monitoring data anomaly detection method combining the LSTM and the auto-encoder comprises the following steps: step 1, cleaning original monitoring data; 2, constructing a data set; step 3, constructing a self-encoding LSTM neural network model; 4, model training; 5, performing model testing and performance evaluation; and 6, deploying the model. According to the tunnel surrounding rock time sequence deformation monitoring data anomaly detection method and device combined with the LSTM and the auto-encoder and the medium, the problem that in existing tunnel automatic monitoring, due to the fact that the data quality is poor and noise is large, traditional threshold value early warning is low in reliability can be solved, the efficient deep learning model is constructed, and the reliability of the tunnel surrounding rock time sequence deformation monitoring data anomaly detection is improved. And automatic and accurate anomaly detection of tunnel surrounding rock monitoring data is realized, so that reliable guarantee is provided for tunnel construction safety.

The invention discloses a construction method of a TiH binary system machine learning potential. The construction method comprises the following steps: constructing a reference electronic structure data set by adopting first principle calculation software VASP; training and testing an artificial neural network potential-ANN potential model on the reference data set by using the artificial neural network model; vASP and ANN potential obtained through training are used for calculating and comparing a Dimer curve, a lattice constant, an elastic modulus and the like for performance testing; and performing targeted improvement on data with large comparison error between the ANN model and the DFT result in model test and performance test results by increasing related configuration weights until an ANN potential model conforming to the precision is obtained. The machine learning potential model constructed by the invention can better fit the interatomic interaction potential energy surface of the TiH binary system, solves the problems of small time-space scale and low precision of the traditional empirical potential in the calculation of the first principle, and provides a technical basis for the high-precision and large-size simulation and research of the TiH binary system.

The embodiment of the invention discloses a model training method and device applied to direct current arc discharge detection. The method comprises the steps of performing at least two times of data processing on first time sequence data and second time sequence data and forming a sample set; selecting an initial neural network model obtained by training the initial sample set as a current detection model, taking the initial sample set as a current test set, and testing the current detection model by using the current test set to obtain a current test output result; and determining a next sample set based on the current test output result, taking a next neural network model obtained by training the next sample set as a current detection model, and taking the next sample set as a current test set for model test until the current test output result meets a preset requirement. According to the technical scheme, the precision and the accuracy of the output model can be improved, so that the accurate detection of the direct current arc discharge of the photovoltaic system is realized, and the safe and stable operation of the photovoltaic power generation system is ensured.

The invention provides a karst foundation model test block preparation device and a test method, belongs to the technical field of physical property test analysis, and is used for solving the problem that a karst model with a cavity structure is difficult to cast inside by a traditional model test block preparation technology in the prior art. Specifically, the device comprises a model frame with an opening in the top and a reinforcing structure arranged on the periphery of the model frame; the device further comprises a cavity reserving device, the cavity reserving device is located in the model frame and does not make contact with the wall face of the model frame, rock mass similar materials are poured into the model frame to form a karst foundation model test block, and after pouring is completed, the reserving device forms a cavity with an arc-shaped top face in the karst foundation model test block. A cavity space for simulating a karst hole is constructed in the model test block, the problem that a hole structure is difficult to form in the model test block through a traditional preparation technology is effectively solved, and powerful support is provided for deeply researching a karst foundation instability mode and a karst foundation instability process.

The invention relates to a hydraulic pump motor degradation evaluation method and system based on an LSTM neural network and similarity calculation. The hydraulic pump motor degradation evaluation method comprises the steps that key indexes representing hydraulic pump motor degradation and input parameters influencing hydraulic pump motor working conditions are extracted from test data in different working conditions; selecting and dividing the obtained original test data into a training data set and a test data set; performing normalization and data screening on samples in the training data set to obtain data enhancement samples for model training; samples in the test data set are only subjected to normalization processing and are used for model testing; setting model parameters based on data features, obtaining a volumetric efficiency calculation result, and calculating a root-mean-square error; determining operation conditions of the hydraulic pump motor in the test data, and analyzing change trends of degradation index parameters of the hydraulic pump motor in different time periods; the similarity of the degradation index parameters of the hydraulic pump motor in different time periods is calculated, and the degradation degree is obtained; and respectively multiplying a prediction result of the neural network and a similarity calculation result by a weight coefficient of 0.5 to realize degradation evaluation of the hydraulic pump motor.

The invention discloses an active anti-floating drainage model test device and test method considering saturation change, and belongs to the technical field of active anti-floating of buildings. The test device comprises a boundary model box, a building model box, a plurality of pore pressure sensors, a plurality of dielectric constant sensors, a pressure limiting drainage pipe for simulating active anti-floating equipment in an actual building, a water head control device and a rainfall simulation device, and can simulate a seepage field of an underground space under the condition of active anti-floating measures during rainfall. The drainage condition of the underground space under the condition is reproduced; the pore pressure sensor and the dielectric constant sensor monitor the saturation change of the soil body in real time, the vacancy of the existing test device in the saturation change factor of the soil body is filled up, the drainage condition of the active anti-floating measure and the seepage law of the soil body in the unsaturated-saturated transition process of the soil body under different rainfall and different stratum conditions can be demonstrated, and the test device has a wide application prospect. Scientific basis and data support are provided for optimization application of active anti-floating measures under different saturation working conditions.

The invention relates to a hydraulic tunnel model test device, and belongs to the technical field of pressure test devices in hydroelectric and hydraulic engineering. Multi-directional ground stress is applied through external oil cylinders, wherein the external oil cylinder on the upper portion applies vertical stress to a rock mass similar material layer; horizontal stress is applied through external oil cylinders on the left side and the right side; a clay layer is laid at the bottom, plastic deformation is generated under the action of vertical stress to form bottom ground stress from bottom to top, and full stress field simulation is achieved. The loading process is divided into two stages: firstly, ground stress loading is carried out, vertical stress and horizontal stress are sequentially applied, and a clay layer deforms to ensure bottom stress; and then internal and external water pressure loading is carried out, the external pressure controller simulates surrounding rock water pressure through the external loading membrane bag, and the internal pressure controller simulates water pressure in the tunnel through the internal loading membrane bag. According to the device, the complex stress environment of the deep-buried tunnel is truly simulated by accurately controlling the multidirectional ground stress and the internal and external water pressure, and a reliable test platform is provided for studying the stability of a lining structure.

The invention relates to the technical field of lightning current measurement, in particular to a wireless measurement method for a high tower wave impedance real-model test. According to the technical scheme, the method comprises the steps that a three-dimensional model with the size proportion of 1: 1 to an actual tower is established in simulation software based on structural parameters of the actual tower, and the model is segmented; and applying a standard lightning current signal to the tower top of the three-dimensional model in simulation to obtain a simulation voltage value of each section of tower. A traditional potential line is replaced by the wireless measurement module, coupling interference is eliminated, and the wave impedance measurement precision is remarkably improved; the trigger voltage is pre-judged by adopting sectional type wireless networking and simulation, so that field wiring is simplified, and the test period is shortened; the system is suitable for high-rise towers of different heights and structures, stable data transmission in a complex environment is ensured in combination with a wireless transmission system deployed in a layered mode, meanwhile, the electrical characteristics of the towers under transient lightning current are accurately captured, and a reliable basis is provided for lightning protection design and electromagnetic compatibility optimization.

The invention provides a method and device for an intelligent computing center cloud platform to adjust model training parameters according to computing power operation states, and relates to the technical field of intelligent computing centers, intelligent computing centers and computing power infrastructures. The first working component is a component deployed in a node in the intelligent computing center cloud platform, the target link comprises a data preparation link, a model training link, a model evaluation link and / or a model test link in the first working component, and the target link performs data processing or model training based on preset hyper-parameters; s2, calculating target correction parameters corresponding to the operation related parameters in a preset period based on a preset regulation and control model; and S3, adjusting the preset hyper-parameter based on the target correction parameter to obtain a target hyper-parameter. The computing power utilization rate of the intelligent computing center cloud platform can be greatly improved, and then the model training efficiency is greatly improved.

The invention relates to a rainfall nowcasting method fusing three-dimensional radar reflectivity and an environmental element field. The rainfall nowcasting method comprises the following steps: 1) collecting radar reflectivity data, rainfall live data and environmental field element data; 2) converting the radar reflectivity data into three-dimensional data, converting rainfall live data into a two-dimensional rainfall grid point field, converting environmental field element data into a three-dimensional equidistant grid point field, and making a sample set by taking the radar reflectivity three-dimensional data and the environmental field element data as input and the two-dimensional rainfall grid point field as a label; 3) building a rainfall nowcasting model; 4) dividing a training set, a verification set and a test set, training the model on the training set, performing hyper-parameter tuning on the verification set, and performing model test on the test set; and 5) taking the radar reflectivity data and the environmental field data as model input, wherein the model output is a rainfall nowcasting field. The influence of distribution and evolution of water vapor particles in the environment field and the vertical direction on rainfall is fully considered, and the rainfall nowcasting precision is improved.

The invention relates to a salient scene graph generation method and device based on fuzzy logic reasoning relation importance, a scene graph generation model test method and device and computer equipment. The method comprises the following steps: step S100, calculating an importance score of a real relationship of each image sample in a target data set; step S200, constructing a target detector; step S300, constructing a semantic extractor and an instance feature refining module; step S400, constructing a bounding box modeling module and a feature splicing module; step S500, constructing a feature fusion module and a relation representation modeling module; step S600, constructing a relation loss weighting module; step S700, returning to the step S200 when the number of the training image samples reaches the batch processing size; and under the condition that all the image samples in the training set are read, entering the step S800 to output the scene graph generation model. According to the method, the importance of the relationship can be flexibly and comprehensively evaluated on the basis of not reducing the number of the relationship samples.

The invention relates to the technical field of data analysis, in particular to a non-limit active soil pressure numerical calculation method in a mode of rotating around a wall top, and derives a function relationship between soil body strength parameters and wall body displacement in the mode of rotating around the wall top. It is assumed that a soil body behind a wall forms an arc-shaped soil arch and a slip crack surface is a logarithmic spiral curved surface, the soil body behind the wall is horizontally layered according to a small step length, a numerical iteration format of the non-limit active soil pressure in a mode of rotating around the wall top is constructed, and a numerical calculation method of the non-limit active soil pressure in the mode is given. A numerical solution is compared with a model test result, and it is found that a calculation result of the solution basically conforms to the model test result. The method provides a more accurate solution to the non-limit active soil pressure when the rigid retaining wall rotates around the top, and has a practical guidance value for the design of the retaining wall.

The invention relates to the technical field of coast and offshore engineering model tests, in particular to a water tank PIV particle sowing device. Wherein a flow channel is arranged in the water tank, the support is arranged in the water tank in a sliding mode, the first baffles are evenly arranged at intervals, one ends of the first baffles are rotationally connected to the support, the other ends of the first baffles abut against the bottom of the water tank, and the throwing pipes correspond to the first baffles one to one. A plurality of outlets are formed in the first baffle at intervals in the vertical direction, the throwing pipe communicates with the outlets and is used for throwing tracer particles, and the flow velocity measuring mechanism is arranged on the downstream of the rectifying mechanism. By arranging the first baffles and adjusting the angles of the first baffles, water flow can be smooth, and the stability of the water flow is improved; the throwing pipe is communicated with the vertically distributed outlets, so that the particles can be uniformly diffused in the water body along the vertical direction, and the uniformity and the concentration stability of the particles after throwing are improved.

The method comprises the following steps: obtaining training data of a voice data construction model, preprocessing the obtained training data to obtain original waveform features and multi-scale fundamental frequency features, inputting the features into the model to carry out model training, and obtaining an attention enhancement model; in the training process of the detection model, hyper-parameters of the detection model are set, a loss function is continuously reduced, the trained detection model is obtained when the set training frequency is reached, test data of the voice data construction model are obtained, and preprocessing is carried out to obtain original waveform features and multi-scale fundamental frequency features; the original waveform features and the multi-scale fundamental frequency features are input into a trained model for model testing, in the testing process, a voice authenticity classification result is obtained, the performance of the model is evaluated, and the performance of the detection model can be effectively improved.

The invention discloses an offshore sand dam construction protection measure physical model test method and device. The method comprises the steps that marine hydrological information of an engineering area and parameter information of a sand dam are obtained; designing a model scale according to the parameter information; according to the parameter information of the sand dam, a sand adding device is designed and calibrated, and an antifouling curtain model is designed; based on marine hydrological information, constructing a seabed model and calibrating dynamic conditions of a physical model test; and arranging a sand adding device and an anti-fouling curtain, operating power conditions, and obtaining topographic data of the sand dam model. According to the technical scheme provided by the invention, the parameter information of the to-be-added sand dam and the corresponding required sand adding device and antifouling curtain are calculated by obtaining the marine hydrological information of the engineering area, the sand dam model meeting the similarity criterion is constructed, and the sand loss rate in the sand dam construction process is simulated through the physical model test, so that the sand dam construction efficiency is improved. The defects that the construction precision is low and the cost of manpower and material resources is additionally increased due to the fact that the silt loss rate is high in the actual sand dam hydraulic reclamation process can be overcome.

The utility model relates to the field of soil body model test saturation, in particular to a rubber mixed soil model test saturation device. The device comprises a model box, a vacuumizing assembly, a saturated liquid permeation assembly and a saturated liquid chamber, wherein rubber mixed soil is placed in the model box; the vacuumizing assembly is used for conducting vacuumizing operation on the interior of the model box from the top of the model box. The saturated liquid permeation assembly comprises a plurality of longitudinal permeation pipelines and a plurality of transverse permeation pipelines, the longitudinal permeation pipelines and the transverse permeation pipelines are laid at the inner bottom of the model box and jointly form a grid shape, and the longitudinal permeation pipelines and the transverse permeation pipelines are each provided with a plurality of holes used for discharging water and wrapped with geotechnical filter cloth; the saturated liquid chamber is communicated with the saturated liquid permeation assembly and used for supplying saturated liquid to the saturated liquid permeation assembly. The device is suitable for rapid and high-quality saturation of rubber light mixed geotechnical materials, and the saturated liquid permeation assembly is high in flexibility, detachable, easy to clean and free of hole blocking risks.

The invention discloses a roadbed model test device and method for simulating bidirectional subway reciprocating load, and belongs to the technical field of geotechnical engineering foundation tests, the device comprises a reaction frame, a model system, a loading assembly, a moving assembly and a control and acquisition system; the model system is used for simulating a subway track roadbed and is arranged at the bottom of the reaction frame; the loading assembly is mounted on the reaction frame and is used for applying a dynamic load to the model system; the moving assembly is installed on the side, close to the loading assembly, of the counter-force frame and used for moving the loading assembly. And the control and acquisition system is used for controlling the loading component to load, controlling the moving component to move and acquiring monitoring data. The problems that a model test cannot simulate the influence of principal stress shaft rotation on foundation deformation caused when a subway moves and roadbed deformation caused by bidirectional subway reciprocating motion are solved, and meanwhile simulation of roadbed model tests under different stress rotation fixed angles can be achieved.