Performance detection method and device for polyurethane material

Abstract

The invention relates to the technical field of detection, and discloses a polyurethane material performance detection method, which comprises the following steps: clamping a material to be detected on a loading platform, cooperatively controlling and simulating the stress effect of a target application scene, and capturing a time sequence image of the microstructure of the surface of the material by adopting a visual unit; synchronously acquiring internal strain distribution data through a distributed strain sensing array, acquiring a dynamic stress response spectrum in combination with a piezoelectric mechanical sensor, and generating a multi-modal deformation characteristic data set; performing crack density and texture orientation analysis on the time sequence image, extracting a crack growth rate and a direction consistency coefficient, and marking a strain concentration area; calculating an apparent elastic modulus attenuation rate based on the dynamic stress response spectrum, establishing a material performance degradation model, generating a dynamic flexible performance index through a weighted fusion algorithm, and performing graded evaluation on the material; material detection is upgraded from a single mechanical test to a multi-physics coupling intelligent evaluation system, and accurate and reliable detection support is provided for multiple application scenes.

Description

Technical Field

[0001] The present invention relates to the field of detection technology, and in particular to a method and device for detecting the performance of a polyurethane material. Background Art

[0002] Polyurethane materials are widely used in precision fields such as hinges of foldable electronic devices and dynamic seals of automobiles due to their excellent flexibility, wear resistance and environmental adaptability. As flexible electronic devices develop towards ultra-thinness and high-frequency bending, and as lightweight automobiles increase the dynamic durability requirements of sealing systems, traditional static mechanical performance indicators (such as tensile strength and hardness) can no longer meet the performance evaluation requirements of materials under complex alternating stresses. Especially under extreme working conditions such as hinges being bent thousands of times a day and seals being subjected to long-term vibration and compression, the correlation mechanism between the accumulation of microscopic damage in materials and the degradation of macroscopic performance has become a key bottleneck restricting product reliability.

[0003] In the prior art, the performance testing of polyurethane materials mostly adopts a static observation scheme combining a uniaxial tensile testing machine with a digital microscope. For example, the flexible performance is evaluated by measuring parameters such as elongation at break and elastic recovery rate. This type of method has the core defect of insufficient adaptability to dynamic scenarios: its uniaxial loading mode cannot simulate the multi-directional composite stress in real applications, resulting in a deviation of up to 30%-50% between the test results and the actual working conditions; at the same time, static parameters cannot characterize the performance attenuation law of the material under cyclic load, and it is difficult to predict the crack initiation location and the end of life. This defect makes the traditional detection method have a serious design guidance blind spot in scenarios such as the selection of foldable mobile phone shaft materials and the verification of flexible seals of new energy vehicle battery packs. It is urgent to develop multi-dimensional detection technology that can reproduce dynamic working conditions.

[0004] In view of this, it is necessary to improve the performance testing technology of polyurethane materials in the prior art to solve the technical problems of single testing dimension and low accuracy. Summary of the invention

[0005] The purpose of the present invention is to provide a method and device for detecting the performance of a polyurethane material to solve the above technical problems.

[0006] To achieve this object, the present invention adopts the following technical solutions: A method for detecting the performance of a polyurethane material, comprising: In the preset testing environment, the strip of polyurethane material to be tested is clamped on the multi-axis deformation loading platform, the force effect of the target application scenario is simulated through collaborative control, and the real-time temperature changes during the deformation process are recorded; The visual unit is used to capture the time-series images of the microscopic morphology of the material surface, and the internal strain distribution data is collected synchronously through the distributed strain sensor array. The dynamic stress response spectrum is obtained by combining with the piezoelectric mechanical sensor to generate a multi-modal deformation feature data set. Perform crack density and texture orientation analysis on the time series images, extract crack growth rate and directional consistency coefficient, and reconstruct the three-dimensional deformation field of the internal strain data to mark the coordinates of the strain concentration area and the strain gradient change; Based on the dynamic stress response spectrum, the apparent elastic modulus attenuation rate is calculated, and the material performance degradation model is established by combining the crack growth rate and the strain gradient change, and the cycle life prediction equation of the target application scenario is associated; According to the crack density, directional consistency coefficient and apparent elastic modulus attenuation rate, a dynamic flexibility performance index is generated through a weighted fusion algorithm, and the material is graded and evaluated according to the preset scene adaptability threshold.

[0007] Optionally, in the preset testing environment, the strip of polyurethane material to be tested is clamped on a multi-axis deformation loading platform, the force effect of the target application scenario is simulated by collaborative control, and the real-time temperature change during the deformation process is recorded, specifically including: A multi-axis deformation loading platform is built in a constant temperature environment box, and the two ends of the strip polyurethane material to be tested are clamped in a pneumatic clamp, the surface of the pneumatic clamp is coated with a polytetrafluoroethylene anti-slip layer, and the spatial angle deviation between the material clamping axis and the platform reference plane is calibrated by a laser alignment instrument; Set the loading mode based on the working condition parameters of the target application scenario; The axial stretching unit is driven by a servo motor to apply linear tensile stress at a preset stretching rate, while the multi-directional bending module is controlled by a pneumatic drive device to generate dynamic bending deformation in the middle section of the material; A closed-loop feedback control system is used to synchronously adjust the phase relationship of stretching, bending and pressing actions, and a protection mechanism is triggered according to the phase relationship. The protection mechanism includes: when the material yield point is detected, the stretching rate is automatically reduced to 50% of the set value, and when the bending angle reaches the threshold, the pressure head withdrawal protection mechanism is triggered; A temperature sensor array is mounted on the surface of the material to record the temperature fluctuation data during deformation detection at a preset sampling frequency to generate a temperature-deformation time series correlation curve.

[0008] Optionally, the temperature sensing array is composed of 16 thin film sensors, and the 16 thin film sensors are arranged in a serpentine routing to cover the stretching area, the bending area and the pressing point; wherein the thin film sensor is a PT100 thin film sensor.

[0009] Optionally, the method uses a visual unit to capture a time-series image of the microscopic morphology of the material surface, synchronously collects internal strain distribution data through a distributed strain sensor array, and combines a piezoelectric mechanical sensor to obtain a dynamic stress response spectrum to generate a multimodal deformation feature data set, specifically including: Deploy an imaging system on the surface of the material, use a polarized light source to illuminate the area to be tested at a preset incident angle, adjust the polarization direction to form a preset angle with the material stretching axis, and capture a time-series image of the surface microscopic morphology; A distributed grating array is embedded inside the material, and the strain value of each grating node is monitored in real time through a demodulator to generate a three-dimensional strain distribution data set in the axial, radial and tangential directions; Piezoelectric mechanical sensors are installed at the clamping end and bending area of ​​the material, and the dynamic stress spectrum is collected through an anti-aliasing filter, and the timestamp is recorded synchronously.

[0010] Optionally, the step of collecting the dynamic stress spectrum through an anti-aliasing filter and synchronously recording a timestamp further includes: Establish a multi-source data synchronization fusion mechanism: when the loading platform triggers the deformation action, send hardware synchronization pulse signals to the visual unit, fiber demodulator and piezoelectric sensor to make the time deviation of the time series image, strain data and stress spectrum within the allowable range; Preprocess the collected data: perform non-uniform illumination correction and motion blur compensation on the time series images, use median filtering to eliminate the instantaneous noise of the three-dimensional strain distribution data set, and perform baseline drift correction and dimension normalization on the dynamic stress spectrum; The preprocessed surface image, three-dimensional strain distribution data set and dynamic stress spectrum are aligned along the time axis to construct a multimodal deformation feature database containing spatial coordinates, strain gradient, stress amplitude and texture feature vector.

[0011] Optionally, performing crack density and texture orientation analysis on the time series image, extracting crack growth rate and directional consistency coefficient, and reconstructing the three-dimensional deformation field of the internal strain data, marking the coordinates of the strain concentration area and the strain gradient change, specifically includes: Perform dynamic noise reduction on the time series images to separate the background texture and crack pixels, and compensate for the image displacement artifacts caused by material deformation based on the optical flow method to generate a denoised and enhanced image set; The U-Net network is used to perform crack semantic segmentation on the denoised and enhanced image set. The crack length threshold is set to 50 μm, the crack skeleton line of each frame is extracted and the fractal dimension is calculated. The total length of cracks per unit area is counted to generate a crack density heat map. The crack skeleton line direction is analyzed by directional gradient histogram, the main crack extension direction is detected by weighted transformation, and the anisotropy coefficient η=1-secondary dominant direction energy / main direction energy is calculated; Perform spatial interpolation on the three-dimensional strain distribution data set, reconstruct the three-dimensional deformation field including axial, radial and tangential strain components, calculate the strain gradient change, and identify the local area where the strain gradient change rate exceeds 0.5% / mm² as the strain concentration area; The coordinates of the strain concentration area are mapped to the three-dimensional solid model of the material, the strain energy density W = 0.5σ·ε of each hot spot area is calculated, and the strain energy density cloud map is generated and spatially registered with the crack density thermogram; A crack-strain coupling analysis matrix was established, and the coordinates of the dangerous areas that simultaneously satisfied the crack density ≥ 0.8 mm / mm² and the strain energy density ≥ 15 kJ / m³ were marked, and their spatial distribution patterns and strain gradient changes were recorded.

[0012] Optionally, the apparent elastic modulus attenuation rate is calculated based on the dynamic stress response spectrum, and the material performance degradation model is established by combining the crack growth rate and the strain gradient change, and the cycle life prediction equation of the target application scenario is associated, specifically including: The dynamic stress response spectrum is processed in time domain segmentation, and the stress relaxation stage, steady-state maintenance stage and elastic rebound stage are divided based on the deformation loading characteristics. The stress attenuation slope and creep recovery rate of each stage are calculated to generate the modulus attenuation characteristic vector. The apparent elastic modulus attenuation curve was fitted by piecewise exponential function, the peak stress ratio of adjacent deformation cycles was used as the attenuation factor, and the time-varying weight coefficient of the elastic modulus attenuation rate was solved by nonlinear least square method. Extract the spatial distribution heat map of the crack growth rate, calculate the cosine value of the angle between the main direction of the crack and the strain gradient vector, and mark the three-dimensional coordinate point set where the strain gradient change exceeds the preset change threshold; A performance degradation differential equation including modulus attenuation rate, crack-strain coupling factor and local gradient mutation is constructed, and the material damage accumulation rate is solved by adaptive iteration method. The accelerated aging test parameters are reconstructed based on the typical load spectrum of the target scenario, and the damage accumulation rate is substituted into the Paris-Erdogan equation to establish a cycle life prediction model considering multi-axial stress state. By sampling and simulating the material performance degradation path, the confidence interval of the life prediction value is calculated. When the interval width exceeds the preset threshold, the dynamic calibration mechanism of the model parameters is triggered.

[0013] Optionally, a dynamic flexibility performance index is generated by a weighted fusion algorithm based on the crack density, directional consistency coefficient and apparent elastic modulus attenuation rate, and the material is graded and evaluated based on a preset scene adaptability threshold, specifically including: The crack density, directional consistency coefficient and apparent elastic modulus attenuation rate are normalized, the crack density is converted into a relative damage degree in the range of 0-1, the directional consistency coefficient is calibrated to match the index according to the cosine similarity, and the modulus attenuation rate is mapped to the preset degradation level; Based on the failure mode library of the target application scenario, the weight coefficients are assigned using the analytic hierarchy process; Construct a dynamic flexibility performance index calculation model: perform linear weighted summation of normalized parameters and weight coefficients, superimpose nonlinear correction terms of strain energy density gradient, and generate a comprehensive performance score; Set the adaptability threshold based on historical test data and scenario operating condition limits; Compare the comprehensive score with the preset threshold and make a graded evaluation decision based on the comparison result; A graded evaluation map is generated based on the graded evaluation decision, and the material surface is divided into several grid units. Red, yellow and green warning signs are assigned according to the performance scores in the grid units, and the spatial coordinates and weight rankings of the priority improvement areas are marked.

[0014] Optionally, the material is graded and evaluated according to a preset scene adaptability threshold, and then the method further includes: The graded evaluation results are integrated with the deformation field distribution and life prediction data to generate a visual inspection document containing a three-dimensional damage evolution map, process optimization suggestions and scenario adaptation report, which is then transmitted to the terminal interactive interface through an encrypted channel.

[0015] The present invention also provides a performance detection device for a polyurethane material, which is used in the performance detection method for the polyurethane material as described above, and the performance detection device comprises: A constant temperature environment box, wherein a laser alignment instrument is arranged in the constant temperature environment box; A multi-axis deformation loading platform is provided with a pneumatic clamp, an axial stretching unit, a multi-directional bending module and a servo motor; Multimodal sensing module, including vision unit, temperature sensing array, piezoelectric force sensor and distributed grating array; A data processing unit, used to process the acquired temperature data, time series images, strain distribution data and dynamic stress response spectrum to generate a multi-modal deformation feature data set; The decision-making system is used to carry data processing models and grade and evaluate materials.

[0016] Compared with the prior art, the present invention has the following beneficial effects: first, the composite stress effect of the target scene is simulated by a multi-axis deformation loading platform to trigger the evolution of material microscopic damage; the surface crack extension, internal strain distribution and dynamic mechanical response are synchronously captured by a visual unit, a strain sensing array and a piezoelectric sensor to construct a multimodal feature data set; the density and orientation of surface cracks are analyzed, and the material damage hotspots are identified in combination with three-dimensional strain field reconstruction; the elastic modulus decay rate is calculated based on the dynamic stress response spectrum, a performance degradation model is established and the cycle life is predicted; a dynamic flexibility performance index is generated by weighted fusion of crack density, directional consistency and modulus decay parameters to achieve quantitative evaluation of material scene adaptability; this method upgrades material detection from a single mechanical test to an intelligent evaluation system coupled with multiple physical fields, which solves the technical problem that traditional methods cannot characterize the mismatch between dynamic flexibility performance and real scenes, and provides accurate and reliable detection support for a variety of application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0018] The structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with this technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantive technical significance. Any structural modification, change in proportion or adjustment of size, without affecting the effects and purposes that can be achieved by the present invention, should still fall within the scope of the technical contents disclosed by the present invention.

[0019] Figure 1 This is one of the flow diagrams of the method for detecting the performance of the polyurethane material of the first embodiment; Figure 2 This is a second flow chart of the method for detecting the performance of the polyurethane material of the first embodiment; Figure 3 It is a schematic diagram of the performance detection device of the polyurethane material of the second embodiment. DETAILED DESCRIPTION

[0020] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] In the description of the present invention, it should be understood that the terms "upper", "lower", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. It should be noted that when a component is considered to be "connected" to another component, it may be directly connected to the other component or there may be a centrally arranged component at the same time.

[0022] The technical solution of the present invention is further described below with reference to the accompanying drawings and through specific implementation methods.

[0023] Embodiment 1: Please combine Figure 1 and Figure 2 As shown, an embodiment of the present invention provides a method for detecting the performance of a polyurethane material, comprising: S1, in a preset testing environment, clamp the strip of polyurethane material to be tested on a multi-axis deformation loading platform, simulate the force of the target application scenario through collaborative control, and record the real-time temperature changes during the deformation process; In a constant temperature and humidity chamber, a multi-axis deformation loading platform is used to apply composite stress (stretching, bending, and pressing) to the strip polyurethane material to simulate real working conditions. The servo motor controls the axial stretching rate, the pneumatic bending module dynamically adjusts the bending radius, and the piezoelectric actuator array applies local periodic pressure.

[0024] S2, using a visual unit to capture time-series images of the material surface micro-morphology, synchronously collects internal strain distribution data through a distributed strain sensing array, combines with a piezoelectric mechanical sensor to obtain a dynamic stress response spectrum, and generates a multi-modal deformation feature data set; The visual unit is preferably a polarization microscope system that captures the surface crack initiation process at 120fps, and the light intensity difference enhances the microcrack contrast. The embedded fiber Bragg grating array (2mm spacing) solves the three-dimensional strain (axial / radial / tangential) through the wavelength offset, and the piezoelectric sensor collects the dynamic stress signal and converts it into a voltage spectrum through the charge amplifier. The hardware synchronization trigger module sends TTL pulses to align the optical, mechanical, and thermal data timestamps.

[0025] S3, performs crack density and texture orientation analysis on the time series images, extracts the crack growth rate and directional consistency coefficient, and reconstructs the three-dimensional deformation field of the internal strain data, marking the coordinates of the strain concentration area and the strain gradient change.

[0026] S4, calculate the apparent elastic modulus attenuation rate based on the dynamic stress response spectrum, combine the crack growth rate and strain gradient change, establish a material performance degradation model, and associate it with the cycle life prediction equation for the target application scenario; Wavelet packet energy characteristics: The expansion of microcracks inside the material will excite stress waves in a specific frequency band (2-4kHz), and the energy accumulation is positively correlated with the degree of damage.

[0027] Gradient-corrected Paris model: The traditional Paris law only considers the stress intensity factor ΔK, and introduces the strain gradient term α∇ε to reflect the influence of multi-axial loads and improve the prediction accuracy.

[0028] S5, based on the crack density, directional consistency coefficient and apparent elastic modulus attenuation rate, a dynamic flexibility performance index is generated through a weighted fusion algorithm, and the material is graded and evaluated according to the preset scene adaptability threshold.

[0029] The working principle of the present invention is as follows: first, the composite stress of the target scene is simulated by a multi-axis deformation loading platform to trigger the evolution of microscopic damage of the material; the surface crack extension, internal strain distribution and dynamic mechanical response are synchronously captured by visual units, strain sensing arrays and piezoelectric sensors to construct a multimodal feature data set; the surface cracks are subjected to density and orientation analysis, combined with three-dimensional strain field reconstruction, to identify material damage hotspots; the elastic modulus decay rate is calculated based on the dynamic stress response spectrum, a performance degradation model is established and the cycle life is predicted; a dynamic flexibility performance index is generated by weighted fusion of crack density, directional consistency and modulus decay parameters to achieve quantitative evaluation of material scene adaptability; this method upgrades material detection from a single mechanical test to an intelligent evaluation system coupled with multiple physical fields, solving the technical problem that traditional methods cannot characterize the mismatch between dynamic flexibility performance and real scenes, and providing accurate and reliable detection support for a variety of application scenarios. In this embodiment, it is specifically stated that step S1 specifically includes: S11, build a multi-axis deformation loading platform in a constant temperature environment box, clamp the two ends of the strip polyurethane material to be tested in a pneumatic clamp, the surface of the pneumatic clamp is coated with a polytetrafluoroethylene anti-slip layer, and use a laser alignment instrument to calibrate the spatial angle deviation between the material clamping axis and the platform reference plane.

[0030] S12, set the loading mode based on the working condition parameters of the target application scenario; for example: for the hinge scenario of foldable equipment, input the parameter set of daily bending times 500±50 times, bending radius 0.5-2mm, and stretching amplitude 120%-150%; for the dynamic sealing scenario of automobiles, input the parameter set of vibration frequency 20-100Hz and compression deformation rate 15%-30%.

[0031] S13, driving the axial stretching unit by a servo motor to apply linear tensile stress at a preset stretching rate, and at the same time controlling the multi-directional bending module by a pneumatic drive device to generate dynamic bending deformation in the middle section of the material; The servo motor drives the ball screw to achieve axial stretching, and the speed is controlled in stages: 0.5mm / s (elastic zone) in the initial stage, and the speed is reduced to 0.25mm / s (plastic zone) after the yield point. The pneumatic bending module applies dynamic bending to the middle section of the material through the profiling die, and the bending radius is switched in real time through the die curvature radius. The piezoelectric actuator is triggered synchronously to apply a 0.1-5N point pressure load in the bending zone to simulate the repeated pressing of the touch screen.

[0032] S14, adopts a closed-loop feedback control system to synchronously adjust the phase relationship of stretching, bending and pressing actions, and triggers a protection mechanism based on the phase relationship. The protection mechanism includes: when the material yield point is detected, the stretching rate is automatically reduced to 50% of the set value, and the pressure head withdrawal protection mechanism is triggered when the bending angle reaches the threshold; The closed-loop feedback system is controlled by three signal linkages: Yield point detection: Real-time calculation of the second-order derivative of the stress-strain curve. When d²σ / dε²<-10MPa, it is judged to have entered the plastic stage and the speed reduction command is triggered; Bending protection: A high-precision rotary encoder monitors the bending angle. When the preset threshold (such as 90°) is exceeded, the solenoid valve will exhaust air urgently to reset the cylinder. Phase synchronization: The phase difference of stretching, bending and pressing actions is controlled synchronously through the EtherCAT bus, which is less than 0.2ms to prevent multi-directional stress interference.

[0033] S15, mounting a temperature sensor array on the surface of the material, recording temperature fluctuation data during deformation detection at a preset sampling frequency, and generating a temperature-deformation time series correlation curve.

[0034] A flexible temperature sensor array is mounted on the surface of the material, using a serpentine layout (covering the stretching area (5 sensors at each end), the bending area (4), and the pressing point (2). The PT100 thin film sensor is attached by polyimide tape, with a sampling rate of 10Hz, and the data is converted into temperature values ​​by the RTD module. The temperature-deformation timing curve shows that the temperature rise rate in the stretching stage is about 0.2℃ / s, and the temperature difference of the local hot spot in the bending area is 3℃.

[0035] In this embodiment, the temperature sensing array is composed of 16 thin film sensors, and the 16 thin film sensors are arranged in a serpentine routing to cover the stretching area, the bending area and the pressing point; wherein the thin film sensor is a PT100 thin film sensor.

[0036] It should be noted that the 16-point layout (10 points in the stretching area, 4 points in the bending area, and 2 points in the pressing area) achieves full coverage of the deformation thermal effect with a spatial resolution of 5mm; the serpentine routing avoids stress concentration caused by wire concentration, while ensuring uniform sensor spacing.

[0037] The timing curve can identify the viscous thermal hysteresis effect (for example, the temperature peak in the bending zone lags behind the stress peak by 1-2s); the thermal gradient distribution reflects the difference in energy dissipation caused by frictional heat generation inside the material.

[0038] In this embodiment, it is specifically described that step S2 specifically includes: S21, deploying an imaging system on the surface of the material, using a polarized light source to illuminate the area to be measured at a preset incident angle, adjusting the polarization direction to form a preset angle with the material stretching axis, and capturing a time-series image of the surface microscopic morphology; A high-resolution polarization microscopy system was deployed on the surface of the material. A 532nm polarized light source was used to illuminate the area to be tested at an incident angle of 30°. The polarization direction was adjusted to form a 45° angle with the material tensile axis to enhance the contrast of the crack edge.

[0039] S22, a distributed grating array is embedded inside the material, and the strain value of each grating node is monitored in real time by a demodulator to generate a three-dimensional strain distribution data set in the axial, radial and tangential directions; A distributed fiber Bragg grating array is embedded inside the material with a grating spacing of 2 mm. The strain value of each grating node is monitored in real time by a wavelength demodulator (resolution 1 pm, sampling rate 1 kHz). Based on the linear relationship between the wavelength offset Δλ_B and the strain ε (Δλ_B=k·ε, k≈1.2pm / με), the axial, radial and tangential strain components are calculated to generate a three-dimensional strain distribution data set.

[0040] S23, install piezoelectric mechanical sensors at the material clamping end and the bending area, collect dynamic stress spectra through anti-aliasing filters, and synchronously record timestamps; set the sensor range to ±10N and the resolution to 0.01N.

[0041] The anti-aliasing filter removes high-frequency noise (such as motor vibration interference), and the dynamic stress spectrum is recorded at a sampling rate of 1 kHz, and the synchronized time stamp is used for multi-source data alignment.

[0042] S24, establish a multi-source data synchronization fusion mechanism: when the loading platform triggers the deformation action, send a hardware synchronization pulse signal to the visual unit, the optical fiber demodulator and the piezoelectric sensor, so that the time deviation of the time series image, the strain data and the stress spectrum is within the allowable range; Establish a hardware-level multi-source data synchronization fusion mechanism: When the main controller of the loading platform triggers the deformation action, it sends a TTL synchronization pulse signal to the visual unit, fiber demodulator and piezoelectric sensor. Each acquisition module aligns the data time axis based on the synchronization pulse to ensure that the time deviation of the time series image, strain data and stress spectrum is ≤0.1ms. The synchronization error is corrected in real time through the time domain cross-correlation algorithm to eliminate the phase mismatch caused by transmission delay.

[0043] S25, preprocessing the collected data: performing non-uniform illumination correction and motion blur compensation on the time series images, using median filtering to eliminate instantaneous noise of the three-dimensional strain distribution data set, and performing baseline drift correction and dimension normalization on the dynamic stress spectrum; Median filtering is applied to eliminate instantaneous noise and retain effective strain gradient information; baseline drift is corrected by polynomial fitting and normalized to stress value according to sensor sensitivity coefficient. The preprocessed data is stored in the cache area (DDR4, bandwidth 3200MHz) for subsequent analysis.

[0044] S26, aligning the preprocessed surface image, three-dimensional strain distribution data set and dynamic stress spectrum along the time axis to construct a multimodal deformation feature database including spatial coordinates, strain gradients, stress amplitudes and texture feature vectors.

[0045] The preprocessed surface image, three-dimensional strain distribution data set and dynamic stress spectrum are aligned along the time axis to construct a multi-modal deformation feature database. The database adopts a hierarchical storage structure: Spatial coordinates: record the crack position and strain concentration area coordinates (XYZ); Strain gradient: store axial, radial and tangential strain gradient values; Stress amplitude: record the peak stress (σ_max) and valley stress (σ_min) of the dynamic stress spectrum; Texture features: Extract parameters such as crack direction angle (θ) and fractal dimension (D_f).

[0046] In this embodiment, it is specifically described that step S3 specifically includes: S31, performing dynamic noise reduction processing on the time series image, separating the background texture and the crack pixels, and compensating the image displacement artifacts caused by material deformation based on the optical flow method to generate a denoised enhanced image set; Dynamic denoising is performed on the time series images, and an adaptive Gaussian mixture model is used to separate background textures (such as grain boundaries on the material surface and filler particles) from crack pixels. The pixel displacement field between adjacent frames is calculated based on the optical flow method to compensate for image displacement artifacts caused by material deformation. The denoised images are contrast-enhanced by histogram equalization to generate a denoised enhanced image set. During the denoising process, the separation threshold of the background texture is dynamically adjusted according to the local grayscale variance to avoid excessive smoothing that causes loss of crack details.

[0047] S32, using the U-Net network to perform crack semantic segmentation on the denoised and enhanced image set, setting the crack length threshold to 50 μm, extracting the crack skeleton line of each frame and calculating the fractal dimension, and statistically calculating the total length of cracks per unit area to generate a crack density heat map; The U-Net network is used to perform crack semantic segmentation on the denoised and enhanced image set. The network adds an attention mechanism module to improve the recognition rate of small cracks. The segmentation results are processed by morphology to extract the crack skeleton line, and the box counting method is used to calculate the fractal dimension D_f to quantify the complexity of the crack morphology. The total length of cracks per unit area is counted to generate a crack density heat map to improve the spatial resolution.

[0048] S33, analyze the crack skeleton line direction through the directional gradient histogram, use weighted transformation to detect the main crack extension direction, and calculate the anisotropy coefficient η=1-(secondary dominant direction energy / main direction energy); The crack skeleton line direction is analyzed by directional gradient histogram, and the local gradient direction (0°~180°, interval 10°) is extracted and the energy distribution is statistically analyzed. The weighted Hough transform is used to detect the main crack propagation direction, and the long crack segment is given a higher weight to avoid interference from short cracks. The anisotropy coefficient η=1-(secondary dominant direction energy / main direction energy) is calculated. η<0.3 is determined as a uniform damage mode, and η≥0.6 is a directional propagation mode. The angle θ between the main direction and the tensile axis of the material is used to evaluate the correlation between the crack propagation path and the load direction.

[0049] S34, spatially interpolate the three-dimensional strain distribution data set, reconstruct the three-dimensional deformation field including axial, radial and tangential strain components, calculate the strain gradient change, and identify the local area where the strain gradient change rate exceeds 0.5% / mm² as the strain concentration area; Specifically, the three-dimensional strain distribution data set is interpolated by Kriging space, and the spatial correlation is fitted based on the semivariogram function γ(h)=C0+C1(1-e^(-h / a)), and the three-dimensional deformation field containing axial, radial and tangential strain components is reconstructed. The strain gradient change ∇ε=√(∂ε_x / ∂x)²+(∂ε_y / ∂y)²+(∂ε_z / ∂z)² is calculated, and the local area with a gradient change rate exceeding 0.5% / mm² is identified as the strain concentration area. The three-dimensional coordinates (x, y, z) and gradient values ​​of the strain concentration area are marked to generate a strain gradient thermal map for subsequent energy density calculation and damage risk assessment.

[0050] S35, mapping the coordinates of the strain concentration area to the three-dimensional solid model of the material, calculating the strain energy density W = 0.5σ·ε of each hot spot area, generating a strain energy density cloud map and performing spatial registration with the crack density thermogram; The strain ε and stress σ in the strain concentration area are combined to calculate the strain energy density and quantify the degree of local energy accumulation; 3D solid mapping: Map the strain energy density value to the 3D solid model of the material (such as CAD model or point cloud model) to generate an energy density cloud map; Then, the energy density cloud map and the crack density heat map are aligned to locate the overlapping areas of high energy density and high crack density.

[0051] Simple strain gradient marking (S34) only reflects geometric deformation, while energy density calculation (S35) reveals the internal energy distribution of the material and is more directly related to the damage mechanism; spatial registration establishes the physical relationship between cracks (surface damage) and strain energy (internal energy), breaking through the limitations of traditional single data analysis.

[0052] S36, establish a crack-strain coupling analysis matrix, mark the coordinates of the dangerous areas that meet both the crack density ≥ 0.8 mm / mm² and the strain energy density ≥ 15 kJ / m³, and record their spatial distribution patterns and strain gradient changes.

[0053] Use crack density (≥0.8 mm / mm²) and strain energy density (≥15 kJ / m³) as joint criteria to screen high-risk areas; mark the coordinates of the areas that meet both thresholds, and record their spatial distribution patterns (such as band distribution along the bending axis); track the gradient change trend of the dangerous area (such as the increasing rate of strain energy density over time) to predict the direction of damage expansion.

[0054] A single indicator (crack only or strain only) may miss potential risks such as: Areas with high crack density but low energy: likely surface scratches with no risk of deep damage; Areas with high energy density but no cracks: may be potential damage initiation points; The combination of dual thresholds can accurately identify truly dangerous areas (i.e., areas where high energy drives crack propagation) and avoid misjudgment.

[0055] In this embodiment, it is specifically described that step S4 specifically includes: S41, performing time-domain segmentation processing on the dynamic stress response spectrum, dividing the stress relaxation stage, steady-state maintenance stage and elastic rebound stage based on the deformation loading characteristics, calculating the stress attenuation slope and creep recovery rate of each stage, and generating the modulus attenuation characteristic vector; The dynamic stress response spectrum is processed in time domain and divided into three stages based on deformation loading characteristics: Stress relaxation stage: from the peak stress σ_max down to 90% σ_max, calculate the attenuation slope k1 = (σ_max-σ_90%) / Δt1; Steady-state holding stage: stress fluctuation range ±5%σ_max, calculated creep recovery rate η=(σ_end-σ_min) / σ_max; Elastic rebound stage: the stress recovers from 90%σ_max to the initial value, and the rebound slope k2=(σ_90%-σ_0) / Δt2 is calculated.

[0056] Generate the modulus decay eigenvector V=[k1, η, k2] to characterize the viscoelastic behavior of the material.

[0057] S42, using a piecewise exponential function to fit the apparent elastic modulus attenuation curve, taking the peak stress ratio of adjacent deformation cycles as the attenuation factor, and solving the time-varying weight coefficient of the elastic modulus attenuation rate by the nonlinear least squares method; The piecewise exponential function is used to fit the apparent elastic modulus attenuation curve: Function form: E(t)=E0·[A·exp(-α1t)+(1-A)·exp(-α2t)], where A is the weight coefficient, α1 and α2 are the decay rates; Attenuation factor: The ratio of the peak stresses of adjacent cycles r=σ_max,i / σ_max,i+1 is used as the attenuation factor. When r<0.95, the attenuation rate adjustment is triggered. Parameter solution: α1, α2, and A are fitted using the Levenberg-Marquardt algorithm (maximum iterations 200 times, tolerance 0.1%) to generate a time-varying weight coefficient matrix.

[0058] This model can accurately describe the nonlinear modulus decay behavior of materials under cyclic loading.

[0059] S43, extracting the spatial distribution heat map of the crack growth rate, calculating the cosine value of the angle between the main direction of the crack and the strain gradient vector, marking the three-dimensional coordinate point set whose strain gradient change exceeds the preset change threshold; this step reveals the correlation between the crack growth path and the strain field distribution.

[0060] Rate calculation: Based on the time series image segmentation results, the crack length increment da / dt per unit time is calculated; Direction analysis: The main crack direction θ_c is extracted by the histogram of oriented gradients (HOG), and the cosine value of the angle between the main crack direction θ_c and the strain gradient vector θ_s is calculated, i.e., cos(θ_c-θ_s); Threshold marking: When the strain gradient change Δ(∇ε) / Δt>0.2% / mm² / s, the corresponding three-dimensional coordinate point set (x, y, z) is marked.

[0061] S44, constructs a performance degradation differential equation including modulus attenuation rate, crack-strain coupling factor and local gradient mutation, and uses an adaptive iterative method to solve the material damage accumulation rate; comprehensively considers the multi-field coupling effects of modulus attenuation, crack extension and strain gradient mutation.

[0062] Equation form: dD / dt=k1·ΔE+k2·(da / dN)+k3·∇ε, where D is the damage degree, k1, k2, k3 are weight coefficients; Coupling factor: Crack-strain coupling factor k2 = cos (θ_c-θ_s)· (da / dN), reflecting the dependence of crack propagation on local strain; Iterative solution: The adaptive step-size Runge-Kutta method (initial step size 1s, error limit 0.001%) is used to solve the damage accumulation rate dD / dt.

[0063] S45, based on the typical load spectrum of the target scenario, the accelerated aging test parameters are reconstructed, the damage accumulation rate is substituted into the Paris-Erdogan equation, and a cycle life prediction model considering the multi-axial stress state is established.

[0064] S46, by sampling and simulating the degradation path of material performance, the confidence interval of the life prediction value is calculated, and when the interval width exceeds the preset threshold, the dynamic calibration mechanism of the model parameters is triggered. This step ensures the reliability of the life prediction results and avoids misjudgment caused by parameter uncertainty.

[0065] Parameter distribution: set the statistical distribution of crack growth rate C, n and strain gradient correction coefficient α (normal distribution, coefficient of variation 10%); Life prediction: Generate 10,000 sets of random parameter combinations and calculate the mean μ and standard deviation σ of the life distribution; Confidence interval: When the interval width (2σ / μ) is greater than 20%, the dynamic calibration mechanism of the model parameters is triggered to refit C, n, and α.

[0066] In this embodiment, it is specifically described that step S5 specifically includes: S51, normalize the crack density, directional consistency coefficient and apparent elastic modulus attenuation rate, convert the crack density into a relative damage degree in the range of 0-1, calibrate the matching index of the directional consistency coefficient according to the cosine similarity, and map the modulus attenuation rate to a preset degradation level.

[0067] S52, based on the failure mode library of the target application scenario, uses the hierarchical analysis method to assign weight coefficients; for example: the foldable scenario assigns a crack density weight of 0.5, directional consistency 0.3, and modulus attenuation 0.2; the automotive sealing scenario assigns a modulus attenuation weight of 0.6, crack density 0.25, and directional consistency 0.15.

[0068] S53, constructing a dynamic flexibility performance index calculation model: performing linear weighted summation of normalized parameters and weight coefficients, superimposing a nonlinear correction term of the strain energy density gradient, and generating a comprehensive performance score; Linear weighted summation: DFI_base=w1·RDI+w2·DCI+w3·(1-ΔE / E0), where w1, w2, w3 are weight coefficients; Nonlinear correction term: Introduce the exponential correction term of strain energy density gradient ∇W, DFI = DFI_base + λ·exp (∇W), correction coefficient λ = 0.05, to suppress misjudgment caused by local energy concentration; Comprehensive performance score: DFI values ​​range from 0 to 1, DFI ≥ 0.85 indicates excellent performance, and DFI < 0.6 indicates a high risk of failure.

[0069] The model takes into account both global performance and local damage characteristics by combining linear and nonlinear terms.

[0070] S54, sets the adaptability threshold according to historical test data and scenario operating condition limit values; for example: the foldable scenario threshold is set to 0.85 (corresponding to 5000 cycles without breakage), and the automotive sealing scenario threshold is set to 0.75 (corresponding to 10^7 vibration fatigue life).

[0071] S55, comparing the comprehensive score with a preset threshold, and executing a graded evaluation decision according to the comparison result; For example: when the comprehensive score is ≥ the threshold, it is marked as "scenario adaptation", when the score is between the threshold and 20%, it is marked as "critical monitoring", and when the score is less than the threshold and 20%, it is marked as "failure risk".

[0072] S56, generates a graded evaluation map based on the graded evaluation decision, divides the material surface into a number of grid units, assigns red-yellow-green warning signs based on the performance scores within the grid units, and marks the spatial coordinates and weight rankings of the priority improvement areas.

[0073] In this embodiment, it is specifically described that after step S5, the following steps are further included: S6 integrates the graded evaluation results with the deformation field distribution and life prediction data to generate a visual inspection document containing a three-dimensional damage evolution map, process optimization suggestions and scenario adaptation report, and transmits it to the terminal interactive interface through an encrypted channel.

[0074] Embodiment 2: Combination Figure 3 As shown, the present invention also provides a performance detection device for a polyurethane material, which is used in the performance detection method for a polyurethane material as in Example 1, and the performance detection device comprises: The constant temperature environment box 10 is provided with a laser alignment instrument.

[0075] The multi-axis deformation loading platform 20 is provided with a pneumatic clamp 21 , an axial stretching unit 22 , a multi-directional bending module 23 and a servo motor 24 .

[0076] The multimodal sensing module 30 includes a visual unit, a temperature sensing array, a piezoelectric mechanical sensor and a distributed grating array.

[0077] The host module 40 is provided with a data processing unit for processing the acquired temperature data, time series images, strain distribution data and dynamic stress response spectrum to generate a multi-modal deformation feature data set.

[0078] The decision-making system is used to carry data processing models and grade and evaluate materials.

[0079] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting the performance of a polyurethane material, characterized in that: include: In the preset testing environment, the strip of polyurethane material to be tested is clamped on the multi-axis deformation loading platform, the force effect of the target application scenario is simulated through collaborative control, and the real-time temperature changes during the deformation process are recorded; The visual unit is used to capture the time-series images of the microscopic morphology of the material surface, and the internal strain distribution data is collected synchronously through the distributed strain sensor array. The dynamic stress response spectrum is obtained by combining with the piezoelectric mechanical sensor to generate a multi-modal deformation feature data set. Perform crack density and texture orientation analysis on the time series images, extract crack growth rate and directional consistency coefficient, and reconstruct the three-dimensional deformation field of the internal strain data to mark the coordinates of the strain concentration area and the strain gradient change; Based on the dynamic stress response spectrum, the apparent elastic modulus attenuation rate is calculated, and the material performance degradation model is established by combining the crack growth rate and the strain gradient change, and the cycle life prediction equation of the target application scenario is associated; According to the crack density, directional consistency coefficient and apparent elastic modulus attenuation rate, a dynamic flexibility performance index is generated through a weighted fusion algorithm, and the material is graded and evaluated according to the preset scene adaptability threshold.

2. The method for detecting the performance of polyurethane materials according to claim 1, characterized in that: In the preset testing environment, the strip of polyurethane material to be tested is clamped on the multi-axis deformation loading platform, the force effect of the target application scenario is simulated by collaborative control, and the real-time temperature change during the deformation process is recorded, which specifically includes: A multi-axis deformation loading platform is built in a constant temperature environment box, and the two ends of the strip polyurethane material to be tested are clamped in a pneumatic clamp, the surface of the pneumatic clamp is coated with a polytetrafluoroethylene anti-slip layer, and the spatial angle deviation between the material clamping axis and the platform reference plane is calibrated by a laser alignment instrument; Set the loading mode based on the working condition parameters of the target application scenario; The axial stretching unit is driven by a servo motor to apply linear tensile stress at a preset stretching rate, while the multi-directional bending module is controlled by a pneumatic drive device to generate dynamic bending deformation in the middle section of the material; A closed-loop feedback control system is used to synchronously adjust the phase relationship of stretching, bending and pressing actions, and a protection mechanism is triggered according to the phase relationship. The protection mechanism includes: when the material yield point is detected, the stretching rate is automatically reduced to 50% of the set value, and when the bending angle reaches the threshold, the pressure head withdrawal protection mechanism is triggered; A temperature sensor array is mounted on the surface of the material to record the temperature fluctuation data during deformation detection at a preset sampling frequency to generate a temperature-deformation time series correlation curve.

3. The method for detecting the performance of the polyurethane material according to claim 2, characterized in that: The temperature sensing array is composed of 16 thin film sensors, and the 16 thin film sensors are arranged in a serpentine pattern to cover the stretching area, the bending area and the pressing point; wherein the thin film sensor is a PT100 thin film sensor.

4. The method for detecting the performance of the polyurethane material according to claim 1, characterized in that: The method uses a visual unit to capture the time-series image of the microscopic morphology of the material surface, synchronously collects the internal strain distribution data through a distributed strain sensor array, and combines the piezoelectric mechanical sensor to obtain the dynamic stress response spectrum to generate a multi-modal deformation feature data set, which specifically includes: Deploy an imaging system on the surface of the material, use a polarized light source to illuminate the area to be tested at a preset incident angle, adjust the polarization direction to form a preset angle with the material stretching axis, and capture a time-series image of the surface microscopic morphology; A distributed grating array is embedded inside the material, and the strain value of each grating node is monitored in real time through a demodulator to generate a three-dimensional strain distribution data set in the axial, radial and tangential directions; Piezoelectric mechanical sensors are installed at the clamping end and bending area of ​​the material, and the dynamic stress spectrum is collected through an anti-aliasing filter, and the timestamp is recorded synchronously.

5. The method for detecting the performance of the polyurethane material according to claim 4, characterized in that: The method further includes collecting the dynamic stress spectrum through an anti-aliasing filter and synchronously recording the timestamp, and then: Establish a multi-source data synchronization fusion mechanism: when the loading platform triggers the deformation action, send hardware synchronization pulse signals to the visual unit, fiber demodulator and piezoelectric sensor to make the time deviation of the time series image, strain data and stress spectrum within the allowable range; Preprocess the collected data: perform non-uniform illumination correction and motion blur compensation on the time series images, use median filtering to eliminate the instantaneous noise of the three-dimensional strain distribution data set, and perform baseline drift correction and dimension normalization on the dynamic stress spectrum; The preprocessed surface image, three-dimensional strain distribution data set and dynamic stress spectrum are aligned along the time axis to construct a multimodal deformation feature database containing spatial coordinates, strain gradient, stress amplitude and texture feature vector.

6. The method for detecting the performance of the polyurethane material according to claim 5, characterized in that: The crack density and texture orientation analysis is performed on the time series image to extract the crack growth rate and direction consistency coefficient, and the three-dimensional deformation field is reconstructed for the internal strain data to mark the coordinates of the strain concentration area and the strain gradient change, specifically including: Perform dynamic noise reduction on the time series images to separate the background texture and crack pixels, and compensate for the image displacement artifacts caused by material deformation based on the optical flow method to generate a denoised and enhanced image set; The U-Net network is used to perform crack semantic segmentation on the denoised and enhanced image set. The crack length threshold is set to 50 μm, the crack skeleton line of each frame is extracted and the fractal dimension is calculated. The total length of cracks per unit area is counted to generate a crack density heat map. The crack skeleton line direction is analyzed by directional gradient histogram, the main crack extension direction is detected by weighted transformation, and the anisotropy coefficient η=1-secondary dominant direction energy / main direction energy is calculated; Perform spatial interpolation on the three-dimensional strain distribution data set, reconstruct the three-dimensional deformation field including axial, radial and tangential strain components, calculate the strain gradient change, and identify the local area where the strain gradient change rate exceeds 0.5% / mm² as the strain concentration area; The coordinates of the strain concentration area are mapped to the three-dimensional solid model of the material, the strain energy density W = 0.5σ·ε of each hot spot area is calculated, and the strain energy density cloud map is generated and spatially registered with the crack density thermogram; A crack-strain coupling analysis matrix was established, and the coordinates of the dangerous areas that simultaneously satisfied the crack density ≥ 0.8 mm / mm² and the strain energy density ≥ 15 kJ / m³ were marked, and their spatial distribution patterns and strain gradient changes were recorded.

7. The method for detecting the performance of a polyurethane material according to claim 1, characterized in that: The method calculates the apparent elastic modulus attenuation rate based on the dynamic stress response spectrum, combines the crack growth rate and the strain gradient change, establishes a material performance degradation model, and associates the cycle life prediction equation of the target application scenario, specifically including: The dynamic stress response spectrum is processed in time domain segmentation, and the stress relaxation stage, steady-state maintenance stage and elastic rebound stage are divided based on the deformation loading characteristics. The stress attenuation slope and creep recovery rate of each stage are calculated to generate the modulus attenuation characteristic vector. The apparent elastic modulus attenuation curve was fitted by piecewise exponential function, the peak stress ratio of adjacent deformation cycles was used as the attenuation factor, and the time-varying weight coefficient of the elastic modulus attenuation rate was solved by nonlinear least square method. Extract the spatial distribution heat map of the crack growth rate, calculate the cosine value of the angle between the main direction of the crack and the strain gradient vector, and mark the three-dimensional coordinate point set where the strain gradient change exceeds the preset change threshold; A performance degradation differential equation including modulus attenuation rate, crack-strain coupling factor and local gradient mutation is constructed, and the material damage accumulation rate is solved by adaptive iteration method. The accelerated aging test parameters are reconstructed based on the typical load spectrum of the target scenario, and the damage accumulation rate is substituted into the Paris-Erdogan equation to establish a cycle life prediction model considering multi-axial stress state. By sampling and simulating the material performance degradation path, the confidence interval of the life prediction value is calculated. When the interval width exceeds the preset threshold, the dynamic calibration mechanism of the model parameters is triggered.

8. The method for detecting the performance of a polyurethane material according to claim 1, characterized in that: According to the crack density, directional consistency coefficient and apparent elastic modulus attenuation rate, a dynamic flexibility performance index is generated through a weighted fusion algorithm, and the material is graded and evaluated according to the preset scene adaptability threshold, including: The crack density, directional consistency coefficient and apparent elastic modulus attenuation rate are normalized, the crack density is converted into a relative damage degree in the range of 0-1, the directional consistency coefficient is calibrated to match the index according to the cosine similarity, and the modulus attenuation rate is mapped to the preset degradation level; Based on the failure mode library of the target application scenario, the weight coefficients are assigned using the analytic hierarchy process; Construct a dynamic flexibility performance index calculation model: perform linear weighted summation of normalized parameters and weight coefficients, superimpose nonlinear correction terms of strain energy density gradient, and generate a comprehensive performance score; Set the adaptability threshold based on historical test data and scenario operating condition limits; Compare the comprehensive score with the preset threshold and make a graded evaluation decision based on the comparison result; A graded evaluation map is generated based on the graded evaluation decision, and the material surface is divided into several grid units. Red, yellow and green warning signs are assigned according to the performance scores in the grid units, and the spatial coordinates and weight rankings of the priority improvement areas are marked.

9. The method for detecting the performance of a polyurethane material according to claim 1, characterized in that: The method further includes: performing graded evaluation on the materials according to a preset scene suitability threshold; and then: The graded evaluation results are integrated with the deformation field distribution and life prediction data to generate a visual inspection document containing a three-dimensional damage evolution map, process optimization suggestions and scenario adaptation report, which is then transmitted to the terminal interactive interface through an encrypted channel.

10. A performance testing device for polyurethane material, characterized in that: The performance testing method for the polyurethane material according to any one of claims 1 to 9, wherein the performance testing device comprises: A constant temperature environment box, wherein a laser alignment instrument is arranged in the constant temperature environment box; A multi-axis deformation loading platform is provided with a pneumatic clamp, an axial stretching unit, a multi-directional bending module and a servo motor; Multimodal sensing module, including vision unit, temperature sensing array, piezoelectric force sensor and distributed grating array; A data processing unit, used to process the acquired temperature data, time series images, strain distribution data and dynamic stress response spectrum to generate a multi-modal deformation feature data set; The decision-making system is used to carry data processing models and grade and evaluate materials.

Images