391 results about "Experimental testing" patented technology

The invention discloses a multi-field coupled microwave deicing intelligent system and an energy efficiency dynamic regulation and control method, and relates to the field of material surface ice layer desorption behavior research and deicing technology experimental testing. In order to solve the technical defects in the prior art that the existing microwave deicing technology still has obvious defects in the aspects of power adjustability, field distribution uniformity, interface depth temperature measurement, real-time mechanical test and the like, the technical scheme provided by the invention is as follows: the microwave deicing device comprises a microwave box body which is a metal closed cavity and is provided with a waveguide interface; a stirrer is arranged inside; the refrigerating system is connected with the back surface of the bearing plate of the microwave box body; a pressure head at the tail end of the mechanical loading module applies thrust to the ice layer; the device and the method are used for realizing construction, microwave heating and real-time mechanical testing of a low-temperature icing environment on the same platform. The method can be applied to dynamic monitoring and research work in multi-physics coupling deicing scenes such as aviation, traffic and new energy.

The invention belongs to the technical field of simulation calculation, and particularly relates to a metal grounding body underground water corrosion characteristic simulation calculation method, which comprises the following steps: preparing a metal grounding body sample, and preparing an electrolyte; carrying out a polarization curve and electrochemical impedance spectroscopy test, and carrying out data fitting and corrosion kinetic parameter extraction on a test result; establishing a three-dimensional finite element model of the metal grounding body under an actual environment condition based on a polarization fitting curve obtained by data fitting and the extracted corrosion kinetic parameters; and performing grid division, performing simulation calculation on corrosion rates of the metal grounding body under different environmental conditions, and further calculating corrosion rate distribution, thereby realizing corrosion rate prediction of the metal grounding body under the actual environmental condition. According to the method, electrochemical experiment testing and finite element simulation modeling are fused, and the method is suitable for conducting quantitative prediction and material comparison evaluation on the corrosion rate of the metal grounding body in the groundwater environment where different pH values and multiple corrosive anions coexist.

The invention discloses a pressure reconstruction method and system based on error correction and an adaptive grid, and a storage medium. The system comprises a PIV experiment test subsystem, a processing module (comprising a PIV post-processing unit and a pressure reconstruction unit) and the like. The method comprises the following steps: firstly, controlling a laser emitting sheet to irradiate tracer particles in a water tank through a synchronizer, and simultaneously triggering a high-speed camera to capture a particle image sequence at a microsecond-to-millisecond-level time interval; the PIV post-processing unit performs cross-correlation analysis on the image to generate a gridding velocity field; a pressure reconstruction unit solves a pressure Poisson equation based on the velocity field to obtain a preliminary pressure field, then iteratively corrects an error through an error correction mechanism and gradient correlation optimization, and triggers self-adaptive mesh refinement / coarsening according to a pressure / velocity gradient amplitude; and finally, outputting a high-precision pressure field on the optimized grid. The method can be applied to flow field tests and hydrodynamic performance analysis in ship and ocean engineering, especially pressure field reconstruction in a complex flow field, and has a wide application prospect.

The invention provides a method for recovering free hydrocarbon contents of different lithologic shale. The method comprises the following steps: carrying out closed freezing heat release, freezing pyrolysis and freezing multi-temperature-order pyrolysis experiment test analysis on a closed coring well core; performing freezing pyrolysis experiment test analysis on the core of the non-closed coring well; carrying out pyrolysis experiment test analysis on the multi-courtyard core; determining the lithology type of the shale; and recovering the free hydrocarbon content of the shale according to an experimental test analysis result and the lithology type. According to the method, light hydrocarbon loss can be reduced to the greatest extent, the content of free hydrocarbons in different lithology non-closed coring well samples and placed samples is recovered, and the accuracy of shale oiliness evaluation is improved.

The invention belongs to the technical field of pressure sore treatment, and discloses an experimental test method for treating stress injury based on danshen emodin, which comprises the following specific steps: step 1, preparing experimental materials, selecting a healthy SD (Sprague Dawley) rat, and preparing a clean and sterile magnet and a shaver; the traditional Chinese medicine composition is prepared from the following raw materials in parts by weight: 1 part of isoflurane, 1 part of iodophor, 1 part of Vaseline, 1 part of Rhapontigenin and 1 part of resveratrol. The method comprises the following steps: modeling a stress injury model for an SD (Sprague Dawley) rat so as to simulate a stress injury disease, then respectively smearing three medicines, i.e., Danjie emodin, resveratrol and vaseline, tracking the healing condition of a stress injury wound, and finally performing ELISA (Enzyme-Linked Immunosorbent Assay) and Hamp; according to the present invention, the detection analysis is performed through the dyeing E, and the results show that the rheum emodin has good treatment effect on the stress injury, can reduce the expression of the proinflammatory factor, can promote the wound healing, has characteristics of environmental protection and low cost, and provides the new research direction for the treatment of the stress injury.

The present invention discloses a device and method for testing the flow corrosiveness and thermal stability of molten salt, which belongs to the field of thermal property testing of energy storage high-temperature molten salt. The device includes: an experimental test subsystem, a heating constant temperature subsystem, and an information acquisition and control subsystem; the experimental test subsystem includes a W-shaped quartz tube, an air pump, and a molten salt tank; the W-shaped quartz tube includes a vertical first quartz tube, a second quartz tube, and a third quartz tube, and the lower ends of the three vertical quartz tubes are connected to accommodate the high-temperature molten salt to be tested. The present invention detects the dynamic and static thermal stability of the molten salt by detecting the penetration rate of infrared rays through the capillary tube, and can also detect the corrosiveness of the molten salt in two states of long-term immersion and scouring. The detection of molten salt by the present invention is more in line with the working state of the molten salt, with high accuracy, and is intelligent and convenient.

The invention provides a multi-objective structure optimization method and system suitable for a wheel excavator. Comprising the steps that a three-dimensional model which has the same actual size as an experimental test prototype of the wheel excavator and comprises a cab, an upper frame and other related parts is established; and comparing frequency domain response curve results obtained by experimental tests and verifying the accuracy of vibration performance prediction of the finite element model. Sensitivity analysis is carried out, and parts finally used for follow-up multi-target optimization are screened out according to the influence degree on the performance of the multiple targets; and performing test design according to the screened parts to obtain sample points, and importing the sample points into a finite element model for simulation to obtain a sample response data set. And fitting the agent model according to the sample data, optimizing by using a genetic algorithm to obtain an optimal solution, and sorting according to the magnitude of an acceleration root mean square value to select an optimal scheme. And importing the optimal scheme obtained according to the steps into a finite element model, and comparing the optimal scheme with an original scheme to verify the rationality of a new optimization scheme.

The invention provides a multi-physics field transformer noise reduction method and a related device, relates to the technical field of transformers, and aims to solve the problems of complex multi-physics field modeling, low simulation efficiency and low response surface model precision in the prior art. The method comprises the following steps: constructing a transformer multi-physical field coupling simulation model covering a circuit field, a magnetic field, a solid mechanical field and an acoustic field; obtaining noise response data under different structure parameters through simulation; verifying the reliability of a simulation result based on an experimental test; key structure parameters are selected, and a response surface model between the iron core structure parameters and modal response is constructed; and with noise reduction as a target, an optimal structure combination is obtained through optimization by using an optimization algorithm, so that the electromagnetic noise in the operation process of the transformer is suppressed. The method has the advantages of being high in modeling precision, high in analysis efficiency and capable of effectively optimizing the structure, and theoretical basis and support can be provided for design of the low-noise transformer.

The invention provides a bearing outer ring fault diagnosis test parameter setting optimization method, which comprises the following steps of: firstly, accurately acquiring structural parameters of a bearing by utilizing a measuring tool; secondly, testing and calculating the inherent frequency and the damping ratio of the bearing in the installed state through a modal experiment; selecting test working condition parameters according to the actual operation environment of the bearing, and calculating the fault characteristic frequency of the bearing; bearing fault simulation signal band-pass filtering processing is constructed; meanwhile, constructing a fault signal equivalent model; carrying out resonance demodulation analysis on the equivalent model, extracting an envelope spectrum and evaluating a fault diagnosis effect; and finally, circularly adjusting working condition parameters, iteratively optimizing the test working conditions, and selecting the working condition with the maximum fault characteristic frequency amplitude and the minimum noise interference as the optimal test condition. According to the invention, the accuracy and reliability of bearing outer ring fault detection are effectively improved, and powerful support is provided for fault diagnosis of mechanical equipment.

A carbonate rock rough slit acid liquid mass transfer coefficient calculation method comprises the following steps: 1) setting conditions based on carbonate rock rough morphology, and constructing a diffusion boundary layer thickness equation under the rough morphology conditions; and 2) solving to obtain the thickness of the diffusion boundary layer, and calculating the mass transfer coefficient according to the relational expression between the thickness of the diffusion boundary layer and the mass transfer coefficient. The carbonate rock rough slit acid liquid mass transfer coefficient calculation method is provided by considering rough morphology influence, no slippage of the acid liquid and filtration loss, and compared with a plane assumption condition in the prior art, the method is more consistent with a real condition, and the coincidence degree with an experimental test result is higher.

The invention discloses a multi-parameter dynamic coupling hydrothermal activity deterministic calculation and quantitative evaluation method which is used for quantitatively evaluating hydrothermal activity in marine shale. The method comprises the following steps: firstly, collecting a typical marine shale sample, and carrying out systematic experimental test analysis, including TOC determination and element content (ICP-MS, XRF) and mineral composition (XRD, FEM-EDS) analysis, to obtain geochemical and mineralogical data of the sample; thirdly, constructing a hydrothermal influence index (HII), and based on the influence of organic matter development on nonlinear enrichment of metal elements, introducing TOC data to perform dynamic threshold adjustment on HII to form an HIIc model; and the existence of hydrothermal activity is further verified by combining the rare earth element Eu abnormity. The method comprises the following steps: constructing a hydrothermal mineral combination index (HMI) through mineral phase equilibrium constraint, and establishing a hydrothermal contribution rate (HCR) model in combination with multivariate parameters; and finally, according to the HCR value and mineral development characteristics, performing quantitative evaluation on the activity intensity of the hydrothermal solution.

The invention relates to the technical field of aircraft aerodynamic analysis, and discloses an aircraft full envelope aerodynamic database intelligent generation method and system, and the method comprises the steps: obtaining the aerodynamic coefficients of an aircraft under different combination conditions through simulation, constructing an aerodynamic coefficient control derivative matrix of the aircraft under the corresponding combination conditions, a continuous derivative matrix is generated through three-dimensional grid interpolation, and aircraft full envelope control derivative matrix coverage is achieved; and performing global correction on the continuous derivative matrix through a method of combining experimental testing and simulation analysis. According to the method, CFD simulation and deep fusion of test data can be realized, and the prediction accuracy and reliability of the pneumatic database are improved; the method can ensure that the generated aircraft full envelope pneumatic database can reflect the pneumatic characteristics of the aircraft more truly, has the characteristics of high efficiency and accuracy, and can greatly improve the efficiency and accuracy of aircraft control law design.

The invention provides an ice and snow pavement simulation experiment test method and system, and relates to the technical field of intelligent construction of road engineering, and the method comprises the steps: obtaining test pavement data; acquiring molten accumulated water data; acquiring simulation test data; determining a test environment severe coefficient according to the pavement ice and snow density and the simulation test data; determining a comprehensive melting effect coefficient according to the pavement friction coefficient, the pavement ice and snow thickness and the melting accumulated water data; determining a snow-melting agent effect coefficient according to the test environment severe coefficient and the comprehensive melting effect coefficient; obtaining a second pavement ice and snow thickness; determining an anti-re-freezing effect coefficient according to the second pavement ice and snow thickness; and determining a test report according to the snow-melting agent effect coefficient and the anti-re-freezing effect coefficient. According to the invention, a low-cost repeated road ice and snow melting experiment under a controllable ice and snow environment condition can be realized, and the data stability is relatively good.

The invention provides a financial news topic modeling method based on multi-level comparative learning, which applies a comparative learning fine tuning task to the financial news topic modeling method, adopts a multi-level comparative learning method, and adjusts vector representation generated by a pre-training language model to obtain a multi-level comparative learning model. According to the method, the generated text vector representation is more suitable for the topic modeling task, and the topic modeling is carried out through the community discovery algorithm, so that the number of topics does not need to be appointed in advance, various hyper-parameters do not need to be set in advance, the application is more convenient, and the influence of the setting of the hyper-parameters on the topic modeling result is also avoided. Through experimental tests of the inventor, compared with an existing topic modeling method, when the method provided by the invention is applied to a financial news text data set, the two indexes of topic consistency and topic diversity of the topic obtained through modeling are improved to a great extent.

The present invention provides a method and system for manufacturing a spherical pressure-resistant structure suitable for implosion protection in deep-sea submersibles. This method relates to the field of deep-sea submersibles and includes: a method for manufacturing the spherical pressure-resistant structure through compression molding, and a testing method for testing its performance based on both the structural performance indicators and its protective effectiveness in simulated deep-sea environments. This method overcomes the difficulty of traditional methods in meeting manufacturing requirements. This method enables the manufacture of a pressure-resistant structure suitable for implosion protection in deep-sea submersibles, meeting requirements for roundness, smoothness, fit, and structural performance. Furthermore, through experimental testing, the improved implosion protection provided by the pressure-resistant structure is visually verified, laying the foundation for its practical application in submersibles. This invention is of great significance to the design and manufacture of deep-sea submersibles.

The invention discloses a shafting vibration characteristic analysis method and system based on elastohydrodynamic lubrication, and relates to the technical field of mechanical engineering.The method comprises the steps that the entrainment speed, the time-varying curvature radius and the contact load at a contact point in a gas distribution-oil supply cam pair are determined; respectively inputting the entrainment speed, the time-varying curvature radius and the contact load at the contact point into a friction analysis model in an elastohydrodynamic lubrication state, and calculating a time-varying curve of the total interfacial friction force of the gas distribution-oil supply cam pair in the whole working cycle; based on time-varying friction excitation corresponding to any moment in the change curve, determining a system excitation vector of the gas distribution-oil supply cam pair by using interface friction as a key connection quantity through experimental testing and simulation modeling technologies; according to the system excitation vector and the structure parameters of the camshaft system, establishing a camshaft system torsional vibration characteristic coupling analysis model considering the interface elastohydrodynamic state; and solving the shaft system torsional vibration differential equation set to obtain the influence rule of the time-varying friction on the instantaneous vibration characteristics of the camshaft system.

The invention relates to a combined loading test device, system and method for a non-adhesive flexible pipeline, and the device comprises a stretching mechanism which comprises a matrix frame, a first driving source disposed at one side of the matrix frame, a moving module disposed in the matrix frame and slidably connected with the matrix frame, and a fixed module fixedly disposed in the matrix frame; the acting end of the first driving source is in transmission connection with the moving module to apply a load in a first direction; the bending mechanism comprises a second driving source and at least one bending action module connected with the action end of the second driving source; the second driving source applies a load in a second direction, and the second direction is perpendicular to the first direction; the test sample tube is axially arranged in the base body frame, the two ends of the test sample tube are hinged to the movable module and the fixed module respectively, and the test sample tube is clamped by the bending action module. The integrated experiment test system can simulate the complex combined load working condition and is closer to the actual working condition.

The invention provides a method for designing components of a multi-component alloy based on component extrapolation of symbolic regression, relates to the technical field of material calculation, and can efficiently test the feasibility of new element introduction for low-component alloys in the material field so as to design high-performance multi-component alloys. The method comprises the following steps: S1, establishing a low-component alloy data set; s2, key element feature screening is carried out through Spearman correlation screening, feature importance analysis and recursive elimination; s3, constructing a relation equation of key element characteristics and material performance by using a symbol regression method based on a multi-population evolutionary algorithm; s4, new elements are imported based on domain knowledge, and a multi-component alloy system is determined; and S5, a multi-component alloy component space is uniformly sampled through Latin hypercube sampling, and sampling points are selected for experimental testing. And S6, performing performance forecasting on the sampling points of the multi-component alloy by using the relation equation, and evaluating the effectiveness of the relation equation. And S7, the symbolic regression model is optimized according to the evaluation result and the experimental data, the steps S3-S6 are iterated to improve the alloy design, and finally the multi-component alloy with high performance is prepared. The technical scheme provided by the invention is suitable for the process of extrapolating the multi-component alloy from the low-component alloy in the material field.

The invention discloses an unmanned ship track tracking precision calculation and evaluation method, and relates to the technical field of water surface unmanned equipment test. The method comprises the following steps: acquiring position information and timestamp information of an unmanned ship, and performing time synchronization processing; and when the unmanned ship autonomously sails towards a preset straight line leg or a broken line leg, the shore-based processing center respectively judges whether the track points are located in an effective judgment range of the corresponding leg, calculates track offsets, and counts an arithmetic mean value or a root-mean-square value of all the track offsets to serve as a tracking precision evaluation result of the straight line track or the broken line track. The method for evaluating the track tracking precision of the unmanned surface vehicle is formed, the algorithm is scientific and feasible, the method has the advantages of high evaluation accuracy and high evaluation efficiency, and beneficial reference is provided for test verification of related technical indexes of the unmanned surface vehicle.

The invention belongs to the technical field of oil well pipe column experimental testing, and discloses an oil well pipe column anti-extrusion strength experimental device and an oil well pipe column anti-extrusion strength experimental method. The oil well tubular column anti-extrusion strength experimental device comprises an extrusion testing mechanism, an external pressure loading mechanism, an internal pressure loading mechanism, a sensing assembly, a heating mechanism and a cooling mechanism. The sleeve sample is arranged in the extrusion testing mechanism in a penetrating manner, and the external pressure loading mechanism provides an external pressure substance for the extrusion testing mechanism. The internal pressure loading mechanism is connected to the interior of the casing sample and can circulate internal pressure substances in the casing sample. The sensing assembly comprises a plurality of sensors which are arranged at intervals in the circumferential direction and the axial direction of the casing pipe sample and can detect strain and pressure of the corresponding position of the casing pipe sample. The heating mechanism is arranged in the extrusion testing mechanism and is used for heating the sleeve sample; and the cooling mechanism is positioned at the downstream of the sleeve sample and can cool the internal pressure substance flowing out of the sleeve sample. The oil well pipe column anti-extrusion strength experimental device can simulate the actual stratum environment, and the accuracy and comprehensiveness of experimental data acquisition are improved.

The invention discloses a functional gradient coating cone-cylindrical shell high-temperature vibration dynamics modeling and analysis method. The method comprises the following steps: establishing a linear vibration analysis model and a nonlinear vibration model considering temperature and amplitude dependence; identifying material parameters of the functional gradient coating-composite material combined shell and determining a corresponding fitting coefficient; preparing a functional gradient coating, coating the conical-cylindrical shell matrix structure with the functional gradient coating, and measuring geometric and material parameters of the matrix and the coating; building a high-temperature vibration test system, and measuring the dynamic response characteristics of the test piece under normal-temperature and multi-temperature working conditions; the theoretical model is verified based on an experimental test result, and a mechanism of influence of key parameters on the dynamic performance of the functionally gradient coating cone-cylindrical shell structure in a high-temperature vibration environment is further researched. The method has the advantages that calculation is easy and convenient, precision is high, a reliable theoretical tool is provided for thermal shock resistance design and life prediction of the structure in the extreme environment, and service safety and reliability are remarkably improved.

The invention provides a forecasting system and method for forecasting underwater radiation noise after ship equipment replacement. The system comprises a data acquisition module, a data processing module and a noise forecasting module, and the data acquisition module acquires various related data before and after equipment replacement to provide comprehensive support for subsequent calculation; the data processing module performs a series of calculation processing on the acquired data to ensure that the data is accurate and available; the ship underwater radiation noise prediction system is compact and reasonable in structure, and the existing technical problems can be effectively solved. According to the method, through the steps of experimental testing before equipment replacement, transfer function construction, acceleration admittance matrix acquisition and the like, the influence of various factors on noise after equipment replacement is comprehensively considered, and specific operations of each step, such as construction of a base-underwater noise transfer function, construction of an equipment-base transfer function and the like, are explained in details, so that the noise level can be accurately forecasted, and the noise level can be accurately predicted. And powerful support is provided for making a ship equipment replacement scheme.

The utility model relates to the technical field of integrated circuit testing, and particularly discloses an integrated circuit experiment testing device which comprises a shell. A microcontroller, and a digital oscilloscope, a function generator, a digital logic analyzer, a pattern generator, a virtual digital I / O interface, a front PCB panel and a plurality of test interfaces which are electrically connected with the microcontroller are arranged in the shell; the front end of the shell is provided with a voltage acquisition interface, a current acquisition interface, a display screen and a plurality of voltage output ports which are electrically connected with the front PCB panel, the bottom of the shell is provided with an air inlet, a cooling fan is arranged above the air inlet, and the middle part of the shell is provided with a middle air outlet. According to the utility model, a plurality of instruments and meters are integrated to carry out experimental testing, so that the device is convenient to operate and overhaul, smaller in size and small in occupied space, meets the requirement of carrying out rapid testing in a limited space, and is suitable for design, simulation, manufacturing and testing of integrated circuits and related experimental teaching and scientific research activities.

The invention aims to provide a gas turbine blade unstable flow visualization testing method, and belongs to the technical field of gas turbine experimental testing. Comprising the following steps: inputting boundary conditions and geometric conditions of a calculation model; numerical simulation flow field data under the condition are obtained through CFD calculation; if yes, the next step is carried out, and if not, a higher-quality grid is generated and returned to the encrypted grid, and CFD numerical simulation calculation is carried out again; selecting a proper resolution ratio based on an actual demand; generating a data source quantity and obtaining CFD calculation data according to the data source quantity; and outputting the three-dimensional transient visual flow field at the moment obtained by the checked high-precision CFD numerical simulation. The actual working condition of the gas turbine blade can be simulated, the test error of an actual instrument under the severe working condition is avoided, and the test difficulty is reduced. The precision of CFD numerical simulation is optimized, and the error is reduced, so that the credibility of the three-dimensional visualization cloud picture is improved.

The invention provides an FC network switch simplified test method, which relates to the technical field of aviation systems, and comprises the following steps: S1, constructing a test environment, inserting a first FC switch and a second FC switch into a test tool, and interconnecting a plurality of ports of the first FC switch and the second FC switch; s2, controlling the first FC switch and the second FC switch to start and operate in a ground working mode through an external discrete magnitude, and setting domain IDs of the two switches to be 1; and S3, controlling the CPUs of the first FC switch and the second FC switch to inject an FC excitation source through software, so that the first FC switch and the second FC switch mutually send and receive FC test messages through interconnected ports to execute an automatic test. According to the method, the problem of test environment conflict frequently existing in actual scientific research test and experimental test is solved, the progress of production delivery, scientific research and troubleshooting is accelerated, and a reference basis is provided for development and test of similar products.

The invention relates to a quick design method for a floating body system of an oscillating water column type wave energy device, which comprises the following steps of: selecting a proper turbine system type according to wave characteristics of a target sea area, and determining the size, blade shape and rotating speed of the turbine system; performance parameters of the turbine system are obtained through numerical simulation and experimental testing, and the performance parameters of the turbine system are simplified; according to the performance parameters of the simplified turbine system, a correlation model of the turbine system and a floating body system is established, and wave boundary conditions are set; carrying out grid division on a flow field around the floating body system, selecting a proper turbulence model and a solver, and carrying out steady-state or transient-state simulation; and calculating the primary energy conversion efficiency of the floating body system and optimizing the floating body system. According to the method, the design period and the repeated modification frequency are reduced, parameter matching between the turbine system and the floating body system is more reasonable through the whole design method, the energy conversion efficiency of the whole device is improved, and the performance of the whole system is optimized.

The invention provides a multi-physics-field coupled core particle microchannel boiling heat exchange experiment testing device and testing method, and belongs to the field of boiling heat exchange experiment testing devices. According to the invention, a laser thermal control module, a reflection temperature measurement module, a particle velocity measurement module, a three-dimensional micro-control module, a stress test module, a sound field test module and an electric field test module are creatively integrated, and flexible combination and active control of each physical field are realized through standardized interfaces. Local point heating is achieved through pulse laser, non-contact transient surface temperature analysis is achieved through a heat reflection method, a micro-nano scale phase change flow field is analyzed through a PIV system, local thermal stress is measured through an embedded film strain gauge set, and automatic alignment and cooperative measurement of all modules are achieved in combination with a high-precision piezoelectric displacement table. Through modular design and system integration, accurate coupling and cooperative measurement of multiple physical fields of light, sound, heat, force and flow on the core particle scale are realized.

The application discloses a kind of methods for evaluating the delamination fracture performance of wind power blade sandwich structure, it is related to blade sandwich structure experiment and simulation field, S1: prefabricated crack sample preparation;S2: sample processing;S3: experimental test;S4: theoretical analysis;S5: simulation modeling;S6: simulation model verification;S7: interface delamination backtracking analysis;The application can accurately obtain the delamination fracture material parameters of wind power blade sandwich structure, analyze the delamination failure load of sandwich structure by simulation model, obtain interface damage, crack propagation and other information of sandwich structure, and quantitatively evaluate the resistance of blade sandwich structure to delamination crack propagation.

The invention belongs to the crossing field of computational mechanics and deep learning, and particularly discloses a heterogeneous composite material equivalent elastic modulus prediction method based on cross-scale differential-integral coupling, and the method comprises the steps: building a multi-scale elastic modulus prediction equation; constructing a cross-scale coupling differential equation set; performing data sampling on the multi-scale elastic modulus prediction equation to generate a training sample; designing a multi-channel neural network architecture; calculating an elastic modulus predicted value and an integral operator original function of each order of the defect field function through neural network forward propagation; through an automatic differential technology, a high-order derivative is accurately calculated, and a differential operator is obtained; driving the neural network to perform back propagation through a composite loss function to update network parameters; when the convergence condition is met, the output of the neural network is the solution of the multi-scale elastic modulus prediction equation. By constructing a macroscopic-microscopic dual-scale differential constraint system and a defect field integral error suppression framework, the bottleneck of traditional experimental test and numerical simulation in cross-scale mechanical analysis is effectively broken through.