236results about How to "Effective simulation" patented technology

The invention discloses a probe card simulation method and system based on counter-acting force analysis, which are used in the field of wafer simulation test, and the probe card simulation method comprises the following steps: integrating multiple physical field working conditions to construct a probe card geometric model, and importing the probe card geometric model into finite element simulation analysis software; carrying out grid division on the geometric model of the probe card by utilizing the hybrid voxel tree model, adjusting the grid density according to the distribution requirement of the multi-physical field, and setting a simulation boundary condition by utilizing a preset boundary condition template according to the actual simulation requirement; starting a simulation calculation process based on the adjusted grid density and simulated boundary conditions; and providing a visual interface of physical field distribution and a structural stress state in the simulation calculation process, and performing iterative optimization on the performance of the probe card in the simulation process according to a reactive force distribution result. According to the method, the grid density is automatically adjusted to adapt to changes of a physical field, and it is ensured that higher simulation precision is obtained in a key area.

The invention discloses a bridge beam plate load testing device for road and bridge construction, and belongs to the technical field of bridge beam plate detection. The device comprises the following modules: an intelligent multi-point collaborative loading module for realizing multi-point synchronous dynamic loading of a beam plate so as to simulate various traffic load conditions; the multi-modal sensing and data acquisition module is used for acquiring dynamic response data of the beam slab in an omnibearing manner; the central control module is used for coordinating and managing the work of each module, processing dynamic response data in real time and dynamically optimizing a test strategy; the self-adaptive safety protection module monitors the health state of the beam slab in real time, predicts potential risks and takes active prevention measures; the environmental simulation and compensation module simulates the influence of various environmental conditions on the beam slab and compensates the interference of environmental factors on a test result in real time; the artificial intelligence data analysis module evaluates the performance of the beam slab and predicts the service life of the beam slab; and the augmented reality interaction and visualization module provides a visual user interface and visualizes the test process and result in real time.

The invention discloses an environment adaptive meta-universe scene perception system and method, and belongs to the technical field of data transmission, and the method specifically comprises the steps: collecting and preprocessing multi-dimensional environment and sensory data in a meta-universe scene in real time through a sensor array, and constructing a full sensory environment data set; radar scanning and depth camera technologies are utilized to accurately obtain three-dimensional information of a physical environment, and a super-reality three-dimensional model is established to simulate a complex ecological system and environment characteristics of the physical world; in combination with real-time full-sensory environment data, an intelligent algorithm is adopted to dynamically adjust meta-universe scene elements, a user behavior prediction technology is introduced, scene layout and an interaction mode are intelligently adjusted according to user history and current states, and user experience is improved; user feedback is collected through VR immersive interaction, a scene perception method is evaluated, and iterative optimization is implemented according to an evaluation result so as to continuously improve the sense of reality and interactivity of the meta-universe scene; and efficient construction and intelligent management of the meta universe scene are realized.

The invention provides a greenhouse climate prediction control method and device, electronic equipment and a storage medium, and relates to the technical field of agriculture, and the method comprises the steps: obtaining climate data and crop data in a greenhouse, and carrying out the multi-source data fusion, and obtaining multi-source fusion data; according to the multi-source fusion data, taking a crop growth state as output, training and verifying a deep neural network, and obtaining a nonlinear dynamic model of the greenhouse climate system; through a Bayesian inference technology, taking parameters of the nonlinear dynamic model as random variables, taking climate data inside and outside a greenhouse as observation data, and establishing posterior distribution of parameter uncertainty, so as to obtain a posterior distribution model of output uncertainty; establishing an optimization problem of a multi-target random opportunity constraint MPC according to a nonlinear dynamic model of a greenhouse climate system, a posterior distribution model of parameter uncertainty and targets of a greenhouse production system; and solving to obtain control input and a control strategy of the greenhouse.

The invention discloses a slope stability test device and test method, and relates to the technical field of slope test.The slope stability test device comprises a test frame and further comprises a test adjusting device.A shielding frame is slidably installed on the inner wall of the test frame, a displacement sensor is fixedly installed on the front side of the shielding frame, and a slope model is arranged at the bottom of the inner wall of the test frame; a placing plate is fixedly installed on the inner wall of the test frame, the test adjusting device comprises hydraulic equipment, an L-shaped frame, an adjusting rod, a pressing plate, an adjusting gear, a U-shaped rod, a limiting frame and an elastic telescopic rod, and the pressing plate moves to make contact with the slope model and conducts a stability test on the slope model; meanwhile, the displacement sensor works to detect and record the displacement condition of the slope model in real time, external force mistaken touch is prevented through the elastic telescopic rod, it can be ensured that the angle of the pressing plate is kept stable in the test process, and therefore the real stability of the slope model is correctly reflected.

The invention relates to the technical field of computers, and provides a back pressure verification method for chip design, computer equipment and a medium, which are used for solving the problem of high development difficulty of back pressure verification. The back pressure verification method comprises the following steps: carrying out initialization operation on a chip simulation verification platform, and then instantiating a top layer, a to-be-tested design and an interface module; a corresponding back pressure signal is determined based on at least one back pressure type associated with a to-be-tested design through a back pressure test module, and then back pressure overshoot check and continuity check after back pressure release are executed by monitoring the back pressure signal according to a pre-configured response mode. Therefore, various conditions which may cause back pressure can be efficiently simulated, the reusability of the back pressure test is good, the system can be conveniently transplanted to various verification environments, the chip verification period can be shortened, and the chip development efficiency can be improved.

The invention provides a microfluidic chip, system and method for osteochondral organs, and relates to the technical field of organoid microfluidic chips, the chip comprises a bone microvascular endothelial cell channel, a bone compartment, a cartilage compartment and a synovial fluid channel which are arranged in parallel and in sequence, and permeation areas between the channel and the compartments and between the compartments. According to the scheme, the complex structure and function of a human osteochondral system are effectively simulated, the physiological and pathological processes of human bone joints can be simulated more truly in an in-vitro environment, and a method for establishing a highly-simulated femoral head necrosis model and osteoarthritis model based on the chip is provided. The problems that a traditional model is insufficient in physiological environment simulation, lack of control over dynamic culture conditions, tedious and time-consuming in the construction process, difficult to support high-throughput experiments and the like are solved.

The invention relates to the technical field of water and soil monitoring, in particular to a water and soil loss intelligent monitoring system based on the Internet of Things, which comprises an earth surface remote sensing image data acquisition module for acquiring remote sensing image data covering a monitoring area through a remote sensing satellite; the perturbation perception compensation module is used for repairing data by adopting a compensation mechanism aiming at abnormal fluctuation of the remote sensing image caused by landslide geological disturbance, and specifically comprises a disturbance detection unit and a disturbance area compensation unit; and the disaster tracing module is used for reconstructing a loss path based on the remote sensing image data restored by the perturbation perception compensation module, simulating a diffusion path of water and soil loss and tracing the loss based on the diffusion path. According to the method, water and soil loss prevention and control guidance of the key area is provided, the accuracy and efficiency of water and soil loss tracing are improved, and powerful technical support is provided for source identification and prevention and control decision of water and soil loss.

The invention provides a neuromuscular multi-element coupled organoid micro-fluidic chip, a device and a method. Relates to the technical field of organoid micro-fluidic chips. A first culture chamber, a second culture chamber and a third culture chamber are arranged in a culture layer of the chip; the first culture room is used for culturing nerve cells; the second culture room is used for culturing muscle cells; a microfluidic channel for communicating the first culture chamber with the second culture chamber is arranged between the first culture chamber and the second culture chamber; the third culture room is arranged on the micro-fluidic channel and is used for culturing a neuromuscular joint formed by convergence of axons of nerve cells and muscle cells; a microelectrode array plate is arranged in the circuit layer and is used for performing electrical stimulation and electrophysiological function detection on neuromuscular cells. Through the chip, co-culture of in-vitro nerves and muscle organs can be realized, a complex interaction relationship in a neuromuscular system can be accurately simulated, and the chip can also be used for constructing various neuromuscular related disease models.

The invention discloses an electrocardio identity authentication method based on feature fusion. An electrocardio identity recognition model constructed by the method comprises a local feature self-learning module, a global feature self-learning module, a feature fusion module and a classifier. A local feature self-learning module and a global feature self-learning module are adopted to extract local features and global features of electrocardiosignals, individual features are captured through the local sensing ability of the local feature self-learning module, and overall fluctuation of ECG is analyzed through the global association ability of the global feature self-learning module. The precision and robustness of identity authentication are improved; meanwhile, the electrocardiosignals are preprocessed through filtering, cardiac beat segmentation and data amplification, the processing capacity for unknown data is enhanced, the robustness and generalization capacity of the model are improved, the signal quality is improved, the diversification condition in reality is effectively simulated, and follow-up analysis is more accurate.

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 invention discloses a method for simulating and predicting a corrosion fatigue evolution process of a steel structure, which comprises the following steps of: establishing an integral finite element stress simulation model of the steel structure, and reserving a local finite element corrosion fatigue simulation model insertion gap of the steel structure on the integral finite element stress simulation model of the steel structure; establishing a local finite element corrosion fatigue simulation model of the steel structure, wherein the local finite element corrosion fatigue simulation model of the steel structure comprises a steel structure finite element corrosion simulation unit and a steel structure finite element fatigue simulation unit which are coupled and associated; inserting and binding the steel structure local finite element corrosion fatigue simulation model into the steel structure local finite element corrosion fatigue simulation model insertion gap to form a steel structure overall finite element corrosion fatigue simulation model; and obtaining simulation and prediction results of the corrosion fatigue evolution process of the steel structure through operation of the integral finite element corrosion fatigue simulation model of the steel structure. And multi-scale and coupling simulation of the whole process of corrosion pit formation and crack propagation is realized.

The invention discloses a drying chamber characteristic and heat pump drying system dynamic modeling method based on Modelica. The method comprises the steps that connectors of different physical domains in a heat pump drying system are designed; splitting the system into component model libraries according to different functions, and performing physical modeling respectively; adding a defined connector in the component model, and constructing a drying loop and a heat pump loop according to a system structure; the unstable drying characteristic of the drying chamber in the drying loop is explored, and a safe operation boundary is provided for the heat pump loop; designing parameters of key components of a heat pump loop and designing a PID controller; and carrying out simulation research to obtain dynamic response of the key parameters. According to the method, a physical model library of each component of the heat pump drying system is established, and a dynamic simulation model of the heat pump drying system is established on the basis; and the unstable drying characteristic of the drying chamber is disclosed, heat pump loop parameter design and PID control design are carried out, and the dynamic response performance of the system under closed-loop response is obtained through a step response experiment.

The invention discloses a fishway inlet flow velocity adjusting system and method based on fish induction flow velocity, and relates to the technical field of data processing. Firstly, environment and fish information comprehensive data of a fishway subordinate area are collected and analyzed, then target flow velocity adjustment parameters of the fishway subordinate area are obtained through matching, first fishway inlet flow velocity adjustment is carried out, a fish migration rule can be better understood, and therefore a more accurate flow velocity adjustment strategy is achieved; then analyzing the fishway operation parameters of the fishway membership area after the first adjustment and performing the second adjustment, continuously optimizing the flow velocity adjustment parameters, improving the fish luring effect of the fishway, and finally collecting the environment and fish information comprehensive data of the fishway membership area after the second adjustment and the fishway operation parameters of the fishway membership area so as to improve the fish luring effect of the fishway. The environment change can be quickly responded, the fish safety passing rate is improved, and therefore the fish passing effect of the fishway affiliated area is improved.

The invention discloses a multi-channel arbitrary regulation and control full-connection space photon Isin machine, and belongs to the field of photoelectric intelligent calculation. The photon Isin machine comprises a laser light source module, a modulation multiplexing module and a detection electric control module. The photon Isin machine provided by the invention realizes multichannel multiplexing of a spatial spin matrix based on a diffraction beam splitting element and polarization multiplexing, realizes arbitrary full-connection coupling weight loading through a matrix decomposition approach, and finally realizes the full-connection space photon Isin machine with arbitrary regulation and control. According to the spatial multiplexing working mode, on one hand, calculation acceleration of the Isin model in any coupling connection can be achieved in a matrix decomposition mode, on the other hand, the modulation rate of the modulator is not sacrificed, and the defect that the calculation speed is low due to time division multiplexing is overcome. Therefore, the full-connection space photon Isin machine with multi-channel arbitrary regulation and control has important practical value in the fields of traffic planning, resource allocation, financial prediction, circuit design and the like.

The invention belongs to the technical field of coupling algorithms, and discloses a smoothed particle dynamics-based warhead shell expansion fracture simulation method, which comprises the following steps of dispersing an explosive and a metal shell into SPH particles carrying physical information; calculating a correction matrix of a smooth function derivative of the SPH particle # imgabs 1 # according to the dispersed particle space position # imgabs 0 #; calculating the stress of the SPH particle # imgabs3 # at the spatial position # imgabs2 #; reconstructing the stress of an SPH particle # imgabs4 # and a neighborhood particle # imgabs5 # of the SPH particle # imgabs4 #; updating the density and the internal energy of the SPH particles at the spatial position # imgabs6 #; and the speed and the spatial position # imgabs8 # of the SPH particle # imgabs7 # are updated. According to the warhead shell expansion fracture simulation method based on smoothed particle dynamics, the reconstructed stress is introduced into the conservation equation, the continuity equation is corrected, on the premise that the speed continuity condition is guaranteed, the complex fracture problems such as warhead shell expansion fracture can be effectively solved, and the working efficiency of the warhead shell is improved. And the method has higher precision and robustness.

The invention discloses an agricultural multi-source knowledge migration method based on a graph model, and belongs to the technical field of agricultural information, and the method comprises the steps: carrying out the reduction, feature selection and feature fusion of agricultural literature data; the data processing efficiency and accuracy are improved by utilizing agricultural data reduction based on self-organizing mapping and feature selection and fusion based on spatial mapping; constructing a knowledge migration network based on a graph model, and performing knowledge semantic extraction and knowledge migration relationship mining; agricultural multi-carrier meta-knowledge acquisition and information feedback are adjusted, and meta-knowledge acquisition and network weight adjustment are optimized. According to the method, large-scale and heterogeneous agricultural data can be effectively processed, effective migration of knowledge is realized, the performance of agricultural learning tasks is greatly improved, and the method is of great significance to improvement of agricultural production efficiency.

The invention provides a grassland grass yield inversion method based on multi-source data fusion and a machine learning algorithm, and aims to improve the estimation precision and efficiency of grassland biomass. According to the method, satellite remote sensing data, unmanned aerial vehicle high-resolution images, climate data acquired by a meteorological station and a digital elevation model are integrated, key features are extracted by using a feature selection technology, and model training and optimization are performed by using machine learning algorithms such as random forest, a support vector machine and extreme gradient lifting. Through model optimization strategies such as cross validation and grid search, the generalization ability and stability of the model are ensured. According to the method, real-time inversion prediction of the grassland grass yield can be realized, a scientific basis is provided for grassland ecological protection, grass and livestock balance management and animal husbandry production, and the method has important practical application value and wide market prospect.

The invention discloses an infrared small target detection model construction method and an infrared small target detection method, belongs to the technical field of computer vision, and particularly relates to infrared image small target detection. The problems that in an existing infrared image small target detection technology, detection is difficult, light weight is not enough, and real-time performance is insufficient are solved. The method comprises the following steps: the trained infrared small target detection model is used for obtaining a finally detected small target according to an input original infrared image. The construction method of the infrared small target detection model and the infrared small target detection method are used for detecting an infrared image small target.

The invention discloses a Gaussian sputtering general rendering enhancement method based on space fusion. The method comprises the following steps: obtaining a real image to be processed; constructing a degradation simulator of a Gaussian sputtering style, adding a gating mechanism into the degradation simulator, selecting a degradation type in an image degradation process, and generating a training data set; inputting a real image to be processed into the degradation simulator to generate a training image; and a Gaussian intensifier is constructed, the Gaussian intensifier utilizes a spatial information fusion network to carry out feature fusion and enhancement rendering processing on the training image through a view fusion module and a depth modulation module, and a final enhancement result is generated. According to the method, highly-correlated and high-quality training images can be mixed, and details are rendered by using the depth information of the target image, so that the output rendering quality of the image is improved.

The invention relates to a method, device and equipment for determining the safety coefficient range of a karst cave slope and a medium. The method comprises the steps that the maximum value and the minimum value of the slope in the X direction and the Y direction are obtained; based on the maximum value and the minimum value of the slope in the X direction, the slope is divided in the X direction according to the vertical division interval, and a plurality of vertical units are obtained; based on the maximum value and the minimum value of the slope in the Y direction, unit bodies with random heights are generated in all the vertical units; according to the unit bodies, determining the distribution condition of the rock-soil body and the karst cave in each vertical unit, and constructing a slope karst cave simulation model; performing assignment calculation on the slope karst cave simulation model to obtain a slope safety coefficient; and a plurality of groups of slope safety coefficients are obtained through iterative calculation, and the range of the slope safety coefficients is determined based on each group of slope safety coefficients. Reliable data support can be provided for engineering design of the karst cave slope, and safety and engineering economy are both considered.

The invention discloses a tunnel fire detection and simulation method and system driven by video data, belongs to the technical field of computer vision and machine learning, and solves the problem that the current tunnel fire target detection algorithm is easy to cause insufficient distinguishing capability of vehicles and flames in a complex multi-target scene environment. The method comprises the following steps: preprocessing an obtained original data set to obtain a target data set to train an improved YOLOv8 neural network model, and carrying out target detection on a to-be-detected tunnel fire scene disaster image to obtain a central coordinate of each preliminary disaster object target for correction; after correction, a monocular vision positioning method is adopted to carry out position calibration and distinguishing on the corrected disaster situation object target, and then real-time scene twinborn modeling is carried out, so that a tunnel fire scene twinborn model is obtained and dynamically updated; and performing flame spread analysis on the tunnel fire scene based on the tunnel fire scene twinborn model, and realizing dynamic updating in un ity. The method is used for tunnel fire detection and simulation driven by video data.

The invention provides an earth surface deformation evolution numerical simulation method based on near-field dynamics, which comprises the following steps: dispersing a geologic body model and a virtual boundary layer which need to be calculated into a plurality of material points to obtain an initial geologic body model; acquiring a neighborhood of each substance point in the initial geologic body model; based on the pore water pressure change of the substance point at the current time step, acquiring the internal force of the substance point at the current time step as the stress of the substance point at the current time step; based on the stress of the substance point at the current time step, obtaining the displacement of the substance point at the current time step by using an adaptive dynamic relaxation method; based on the displacement of the substance point in the current time step, obtaining the stress of the substance point in the current time step; and based on the stress of the substance point at the current time step, judging the fracture condition of the virtual key by utilizing a Mohr-Coulomb failure criterion, and obtaining a local damage value of the substance point at the current time step. The invention provides another scheme capable of revealing a physical mechanism that ground subsidence disasters into ground fissures.

The invention relates to the technical field of turbine blade detection, in particular to an ultrahigh pressure turbine blade precision detection device which comprises a workbench, a mounting mechanism, a water impact mechanism and a precision detection mechanism, one side of the workbench is provided with a control terminal with a built-in PLC, and one side of the workbench is further provided with a water tank capable of using water circularly. Two fixing frames are installed between the side walls of the workbench, a cross beam is installed between the fixing frames on the two sides, the installation mechanism is arranged on the workbench, a horizontally-arranged blade is clamped in the middle of the installation mechanism, and the installation mechanism can drive the blade to rotate and adjust so as to control the simulation position and the detection position of the blade. The water impact mechanism is arranged between the two cross beams on the upper portion, the water impact mechanism is connected with the water tank, and a collecting groove is formed in the workbench. Compared with the prior art, the simulation test process of the blade under the action of water flow impact can be effectively simulated, and the radian change of the blade can be better fitted.

The invention discloses a compaction water release simulator, relates to the technical field of monitoring and prediction, and mainly aims to accurately simulate the compaction water release process of an aquitard and the accumulative effect of long-term land subsidence. According to the main technical scheme, the compaction water release simulator comprises a mold cylinder used for containing a soil body sample, a drainage assembly is arranged on one side of the mold cylinder in the axial direction, and a pressing rod is arranged on the other side of the mold cylinder in the axial direction; the first driving assembly is connected with the pressing rod, and the first driving assembly is used for driving the pressing rod to ascend and descend; the control assembly comprises a pressure sensor and an analysis module, the pressure sensor is connected with the first driving assembly and used for monitoring the pressure value of the first driving assembly acting on the soil body sample through the pressing rod, and the analysis module is connected with the pressure sensor and the first driving assembly and used for obtaining the pressure value; and comparing with a preset interval, and controlling the first driving assembly to move based on a comparison result.

The invention discloses a zero-day malicious code detection model and method and a model construction device and method, and belongs to the technical field of malicious code detection. According to the model construction method, TransXNet serves as a basic model, training optimization is conducted on the basic model through a training set, then the zero-day malicious code detection model is obtained, diffusion operation is conducted on a visual malicious code image through a diffusion model DDIM, a new malicious code image is generated, and therefore the zero-day malicious code detection model is obtained. And combining the new malicious code image with the original malicious code image to jointly form training set data. By the adoption of the construction method, the detection accuracy and robustness of the model for the zero-day malicious code are improved, the problem of data set imbalance is solved, and therefore an effective technical scheme is provided for solving the problems existing in existing zero-day malicious code detection.

The invention discloses a target object description method, device and equipment based on multi-source data fusion, and relates to the technical field of social simulation.The method comprises the steps that a target community needing object description is selected and determined based on an electronic map, an API interface function is called to obtain description data of a target object of the target community in the mobile internet, and the description data are stored in the mobile internet; probability distribution of the target object in each dimension is obtained; obtaining description data of a target object of the target community based on an active investigation mode, and performing conversion processing to obtain probability distribution of the target object in each dimension; and fusing the probability distribution of the target object on each dimension obtained from the mobile internet with the probability distribution of the target object on each dimension obtained in the active investigation mode to obtain a multi-dimensional description of the target object of the target community. According to the method, the community description data is obtained through two modes of mobile internet big data and questionnaire survey, effective complementation is formed, complete crowd portraying of the community can be realized, and community social simulation is effectively supported.

The invention provides a cluster dynamic scheduling method and system for FPGA channel simulation and a medium, and belongs to the technical field of information communication. The method comprises the following steps: acquiring a to-be-scheduled data stream in a cluster; taking the real-time information age as a timeliness index of the data stream, and calculating a priority weight between the data stream and the scheduling node by using the real-time load of the scheduling node to be distributed; performing priority division on a pre-constructed directed acyclic graph to obtain task priorities; according to the task priority and the priority weight, distributing the data flow to a scheduling node to obtain the data flow on the scheduling node; updating the load of the scheduling node, and updating the information age; and according to the timeliness index of the data stream and a preset timeliness threshold, optimizing data resources of the scheduling node to obtain a scheduled data stream.

The invention discloses an aircraft skin-tail flame full flow field coupled infrared radiation characteristic simulation method, which comprises the following steps of: drawing a fuselage and an external flow field area, and establishing an aircraft skin-tail flame full flow field model; aircraft flight parameters and engine parameters are obtained, flow field boundary conditions are set according to the aircraft flight parameters and the engine parameters, flow field simulation is carried out, and aircraft skin surface heat flux density and tail flame gas temperature distribution are calculated; performing solid heat conduction simulation by taking the heat flux density on the surface of the aircraft skin as a second type of boundary condition, and calculating temperature distribution on the surface of the aircraft skin; respectively establishing infrared emissivity models of the skin surface and the tail flame of the aircraft; and combining the obtained tail flame gas temperature distribution, the aircraft skin surface temperature distribution and the infrared emissivity model to calculate the infrared radiation characteristics of the aircraft skin surface and the tail flame. By utilizing the method, the simulation accuracy and precision of the infrared radiation characteristics of the airplane can be improved.

The invention provides a preparation device of a nondestructive testing stress corrosion crack calibration test block, which comprises a base, a corrosion mechanism, a test block, a pressing mechanism, at least two limiting mechanisms and a crack propagation monitoring mechanism, the corrosion mechanism is arranged on the base, and corrosive liquid flows in the corrosion mechanism; the test block abuts against the end face of the corrosion mechanism, a prefabricated crack is formed in the test block, the corrosion mechanism provides a corrosion environment for the prefabricated crack side of the test block, and stress corrosion crack initiation and expansion are accelerated; the pressing mechanism is arranged opposite to the corrosion mechanism and can linearly move towards one side of the corrosion mechanism to apply a load to the position of the prefabricated crack; the at least two limiting mechanisms are arranged on the base and are used for limiting the test block to move along the horizontal direction; the crack propagation monitoring mechanism is arranged on one side of the base and used for monitoring the propagation depth of the stress corrosion crack of the test block applying the load, the device can effectively simulate the crack propagation process of metal in the stress corrosion environment, the accuracy of the position and the size of the stress corrosion crack in a practical engineering welding structure can be ensured, and the working efficiency is improved. Therefore, the detection reliability is improved.