A method for on-line detection of sealing performance of a seal

Abstract

The application discloses a kind of sealing performance online detection methods of sealing element, specifically related to industrial sealing element quality detection technical field, for solving the benchmark deviation and misjudgment problem caused by ignoring installation stress influence in existing detection method;Method constructs sealing contact interface phase field model by real-time acquisition installation stress data, analyzes crack network permeability to predict leakage diffusion path;According to the spatial correlation of stress gradient and leakage density, high / low stress sensitive area is divided, and differential signal acquisition is implemented;By topological data analysis, extract barcode entropy value and generate compensation priority sequence, dynamically correct detection benchmark;Finally, based on the regional weight fusion compensation signal, output high-precision pressure distribution and leakage flow trend result;Installation stress and leakage signal cross-field coupling analysis are realized, and the accuracy and reliability of sealing performance detection under complex working conditions are improved.

Description

Technical Field

[0001] This invention relates to the field of industrial sealing component quality testing technology, and more specifically, to an online testing method for the sealing performance of sealing components. Background Technology

[0002] In the field of industrial equipment sealing performance testing, online testing technology for seals has been widely used in the quality control of production lines. Existing technologies typically determine whether a seal meets design requirements by monitoring pressure, flow rate, or media leakage parameters during the operation of the sealing system. These methods rely on preset testing benchmarks, such as initial pressure thresholds or leakage rate standards, as the basis for judging whether the sealing performance is qualified. However, external mechanical forces (such as bolt tightening, flange assembly, etc.) experienced by the seal during installation may cause uneven internal stress distribution. This stress state may continue to exist after the sealing system starts working and affect the actual contact state of the sealing interface.

[0003] The current limitations of online sealing performance testing methods lie in the fact that the setting of the testing benchmark value does not fully consider the potential impact of the installation process on the initial state of the seal. Due to the microscopic deformation of the sealing interface or the residual local stress caused by the installation stress, the initial parameters obtained by the online testing system may deviate from the actual working state of the seal, thus causing a systematic deviation between the testing benchmark value and the actual sealing performance. This deviation will reduce the accuracy of leakage detection, especially in scenarios where online testing is performed immediately after the seal is installed, which may lead to misjudgment or missed detection, affecting the reliability of quality control. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide an online testing method for the sealing performance of a sealing component to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A method for online testing of the sealing performance of a sealing component includes the following steps:

[0007] S1. During the installation of the seal, obtain real-time installation stress data between the seal and the mounting structure;

[0008] S2. Construct a phase-field model of the sealing contact interface based on real-time installation stress data, and determine the diffusion path of the leaking medium along the sealing contact interface through crack network permeability analysis.

[0009] S3. Based on the phase field model and diffusion path, the sealed contact interface is divided into a high-stress sensitive region and a low-stress sensitive region.

[0010] S4. High-frequency signal acquisition is performed in high-stress sensitive areas, and low-frequency signal acquisition is performed in low-stress sensitive areas to obtain the pressure signal and flow signal of the leaking medium at the sealing contact interface.

[0011] S5. Map the pressure signal and flow signal into high-dimensional point cloud data, calculate the continuous coherence barcode of the high-dimensional point cloud data and extract the barcode entropy value, allocate regional weights according to the spatiotemporal distribution correlation of the barcode entropy value in the high stress sensitive area and the low stress sensitive area, and generate a compensation priority sequence.

[0012] S6. Dynamically compensate for high-weight regions based on the compensation priority sequence and output the corrected sealing performance test results.

[0013] In a preferred embodiment, during the seal installation process, real-time installation stress data between the seal and the mounting structure is acquired, including:

[0014] Multiple strain gauges are arranged on the contact surface between the seal and the mounting structure to form a stress sensing network;

[0015] Dynamic strain data during the installation of the seal is collected in real time using distributed fiber optic sensors.

[0016] Based on the preset stress-strain relationship curve, dynamic strain data is dynamically calibrated to generate real-time installation stress data.

[0017] In a preferred embodiment, a phase-field model of the sealing contact interface is constructed based on real-time installation stress data, and the diffusion path of the leaking medium along the sealing contact interface is determined through crack network permeability analysis, including:

[0018] The three-dimensional stress field components of the real-time installation stress data are used as the stress driving term input of the phase field model. The governing equations of the phase field model include the coupled stress balance equation and the phase field sequence parameter evolution equation. The crack surface energy density function in the phase field sequence parameter evolution equation is defined based on the fracture toughness parameter of the sealed contact interface material.

[0019] An explicit time integration algorithm is used to iteratively solve the phase field model, generating crack propagation paths and crack network topology at the sealed contact interface. The crack network topology includes geometric characteristic parameters such as crack branch angle and radius of curvature.

[0020] Based on the geometric characteristic parameters of crack branch angle and radius of curvature, the equivalent permeability tensor of the crack network is calculated. The calculation of the equivalent permeability tensor includes a weighted statistical average of crack branch angle and radius of curvature.

[0021] The diffusion path of the leaking medium along the sealing contact interface is determined based on the matching degree between the direction of the maximum principal value of the equivalent permeability tensor and the direction of the main branches in the crack network topology.

[0022] In a preferred embodiment, based on the phase-field model and diffusion path, the sealed contact interface is divided into a high-stress-sensitive region and a low-stress-sensitive region, including:

[0023] The stress gradient distribution at the sealed contact interface is calculated based on the phase field model. The stress gradient distribution includes the normal stress gradient and shear stress gradient components.

[0024] Extract the spatial density distribution of the diffusion path and mark the overlapping area of ​​the stress gradient distribution and the diffusion path density distribution as a candidate area of ​​high stress sensitive region;

[0025] Based on the geometric relationship between the stress gradient components and diffusion path density within the candidate region, boundary delineation rules for high-stress-sensitive regions and low-stress-sensitive regions are generated.

[0026] Based on the boundary division rules, the coordinate sets of high-stress sensitive areas and low-stress sensitive areas are output. The coordinate sets are generated by using a spatial clustering algorithm to aggregate areas that meet the conditions.

[0027] In a preferred embodiment, the boundary delineation rule is that regions where the stress gradient component exceeds a preset gradient threshold and the diffusion path density exceeds a preset density threshold are defined as high stress-sensitive regions.

[0028] In a preferred embodiment, high-frequency signal acquisition is performed on high-stress sensitive areas, and low-frequency signal acquisition is performed on low-stress sensitive areas to obtain pressure signals and flow signals of the leaking medium at the sealing contact interface, including:

[0029] Based on the coordinate sets of high-stress sensitive areas and low-stress sensitive areas, configure the deployment locations of pressure sensor arrays and flow sensors;

[0030] The high-frequency signal acquisition frequency is allocated according to the risk level of the high-stress sensitive area, and the risk level is quantified by the product of the stress gradient component and the diffusion path density.

[0031] Low-frequency signal acquisition frequencies are allocated to low-stress sensitive areas;

[0032] The pressure sensor array and flow sensor are synchronized to acquire the data timestamps, thereby obtaining the pressure signal and flow signal of the leaking medium at the sealing contact interface in real time.

[0033] In a preferred embodiment, pressure signals and flow signals are mapped to high-dimensional point cloud data. A continuous coherence barcode of the high-dimensional point cloud data is calculated, and the barcode entropy value is extracted. Regional weights are assigned based on the spatiotemporal distribution correlation of the barcode entropy values ​​in high-stress-sensitive and low-stress-sensitive regions, generating a compensation priority sequence, including:

[0034] Pressure and flow signals are sliced ​​into time windows, and the signal sequence within each time window is mapped into high-dimensional point cloud data through time delay embedding.

[0035] Continuous cohomology analysis is performed on high-dimensional point cloud data to generate continuous cohomology barcodes. The generation of continuous cohomology barcodes adopts the Vietoris-Rips complex construction method.

[0036] The barcode entropy value is calculated based on the length distribution of the continuous homology barcode. The barcode entropy value is the Shannon entropy. A regional sensitivity weighting coefficient is introduced in the calculation. The regional sensitivity weighting coefficient is the ratio of the average lifespan of the barcode in the high-stress sensitive area to that in the low-stress sensitive area.

[0037] Regional weights are assigned based on the spatiotemporal distribution correlation of barcode entropy values ​​in high-stress-sensitive and low-stress-sensitive regions.

[0038] The compensation priority sequence is generated by sorting the regions in descending order of their weights. The rule for generating the compensation priority sequence is to prioritize regions with the same weights when selecting high-frequency signal acquisition regions.

[0039] In a preferred embodiment, the embedding dimension and delay parameter of the time-delay embedding method are adaptively adjusted according to the dynamic ratio of the high-frequency signal acquisition frequency of the high-stress sensitive region to the low-frequency signal acquisition frequency of the low-stress sensitive region.

[0040] In a preferred embodiment, the spatiotemporal distribution correlation is calculated by spatial gridding and time window sliding correlation. The division of the spatial grid is aligned with the cluster boundaries of the high stress-sensitive region, and the length of the time window is inversely proportional to the signal acquisition frequency.

[0041] In a preferred embodiment, dynamic compensation is performed on high-weight regions based on a compensation priority sequence, and the corrected sealing performance test results are output, including:

[0042] Extract the high-weight regions that are ranked first from the compensation priority sequence. The number of high-weight regions is determined according to a preset ratio range based on the total number of regions in the compensation priority sequence.

[0043] Dynamic compensation is performed on the pressure signal in the high-weight region. The dynamic compensation method is to adjust the compensation coefficient based on the pressure signal deviation value.

[0044] Dynamic compensation is performed on the flow signal in high-weight areas. The dynamic compensation method is to adjust the compensation coefficient based on the flow signal deviation value.

[0045] The compensated pressure and flow signals are then weighted and fused with the original signals from the uncompensated area by multiplying the area weight by the compensation coefficient.

[0046] The output includes the weighted and fused corrected sealing performance test results, including pressure distribution cloud map and leakage flow trend curve.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. By acquiring installation stress data in real time and constructing a phase-field model, it is possible to accurately quantify the microscopic deformation and crack propagation path of the sealing interface under installation stress. Based on the differentiated signal acquisition strategy of stress-sensitive area division, combined with the dynamic adaptation mechanism of high-frequency and low-frequency monitoring, it effectively solves the problem of detection benchmark distortion caused by residual installation stress, significantly improves the real-time performance and spatial resolution of leak detection, and is especially suitable for scenarios where detection is performed immediately after installation, avoiding misjudgment or missed detection caused by local stress concentration.

[0049] 2. By generating a compensation priority sequence through topological data analysis, the spatiotemporal distribution characteristics of leakage signals are dynamically correlated with regional weights, realizing adaptive correction of the detection benchmark. Through multi-physics coupling modeling and dynamic signal fusion, strong consistency between the detection results and the actual working conditions of the seal is ensured, providing highly reliable support for the evaluation of sealing performance in complex installation environments, while reducing redundant data processing and optimizing detection efficiency. Attached Figure Description

[0050] Figure 1 This is a flowchart of an online testing method for the sealing performance of a sealing component according to the present invention. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0052] Example: Figure 1 This invention provides an online testing method for the sealing performance of a sealing component, comprising the following steps:

[0053] S1. During the installation of the seal, obtain real-time installation stress data between the seal and the mounting structure;

[0054] S2. Construct a phase-field model of the sealing contact interface based on real-time installation stress data, and determine the diffusion path of the leaking medium along the sealing contact interface through crack network permeability analysis.

[0055] S3. Based on the phase field model and diffusion path, the sealed contact interface is divided into a high-stress sensitive region and a low-stress sensitive region.

[0056] S4. High-frequency signal acquisition is performed in high-stress sensitive areas, and low-frequency signal acquisition is performed in low-stress sensitive areas to obtain the pressure signal and flow signal of the leaking medium at the sealing contact interface.

[0057] S5. Map the pressure signal and flow signal into high-dimensional point cloud data, calculate the continuous coherence barcode of the high-dimensional point cloud data and extract the barcode entropy value, allocate regional weights according to the spatiotemporal distribution correlation of the barcode entropy value in the high stress sensitive area and the low stress sensitive area, and generate a compensation priority sequence.

[0058] S6. Dynamically compensate for high-weight regions based on the compensation priority sequence and output the corrected sealing performance test results.

[0059] The specific implementation method for obtaining real-time installation stress data between the seal and the mounting structure during the installation process is as follows: Multiple resistance strain gauges are arranged on the contact surface between the seal and the mounting structure to form a stress sensing network. The resistance strain gauges cover the key areas of the sealing contact interface in an equally spaced grid layout. The key areas include the area around the bolt holes, the flange edge contact area, and the geometric abrupt change area of ​​the seal. The area around the bolt holes is defined as an annular area with a radius of 10 mm centered on the center of the bolt holes. The flange edge contact area is defined as a strip-shaped area with a width of 5 mm where the flange and the seal actually contact. The geometric abrupt change area includes the grooves and bosses of the seal. The arrangement density of the resistance strain gauges is dynamically adjusted according to the stress concentration degree of the sealing contact interface. The stress concentration degree is determined by finite element analysis. The finite element analysis uses ANSYS software to build a three-dimensional model of the sealing contact interface and apply bolt preload load, outputting a stress distribution cloud map to guide the strain gauge layout.

[0060] Dynamic strain data during the sealing process is acquired in real time using distributed fiber optic sensors. These sensors are fiber Bragg grating-based sensor arrays, laid out in a crisscross pattern along the circumferential and radial directions of the sealing interface. The circumferential path involves placing one fiber every 30 degrees, while the radial path involves placing one fiber every 5 millimeters along the radius of the sealing component. This fiber Bragg grating sensor array layout complements the gridded layout of the resistive strain gauges, enabling spatial redundancy verification of the strain data. The acquisition frequency of the dynamic strain data is synchronized with the loading rate of the sealing process, including the application rate of bolt tightening torque and the pressing speed of flange assembly. The acquisition frequency is set to 1000 to 5000 times per second, with the specific value adaptively matched to the real-time adjustments of the installation process. For example, when the bolt tightening torque application rate exceeds 5 N·m per second, the acquisition frequency is increased to 5000 times per second.

[0061] Based on the preset stress-strain relationship curve, dynamic strain data is dynamically calibrated to generate real-time installation stress data. The stress-strain relationship curve is obtained through a combination of uniaxial tensile and shear tests on the sealing material. In the uniaxial tensile test, an axial tensile force is applied to the sealing material specimen on a universal testing machine, with the tensile force ranging from 0 to 120% of the material's yield strength. In the shear test, an in-plane shear load is applied using a double shear clamp at a loading rate of 0.5 mm per second. The test environment temperature covers the sealing material's operating temperature range (-40℃ to 150℃), and the humidity range is 30% to 90% relative humidity.

[0062] The stress-strain relationship curve is stored in the non-volatile memory of the signal processing terminal in the form of a two-dimensional interpolation table. The dynamic calibration process includes the following steps: converting the original wavelength offset acquired by the distributed optical fiber sensor into strain value. The conversion formula between wavelength offset and strain value is Δλ / λ=K·ε, where Δλ is the wavelength offset, λ is the initial center wavelength of the fiber Bragg grating, K is the strain sensitivity coefficient of the fiber Bragg grating, and ε is the strain value.

[0063] The validity of strain values ​​is verified by measuring the resistance change rate of a resistance strain gauge. The relationship between the resistance change rate ΔR / R and the strain value is ΔR / R = G·ε, where G is the strain gauge sensitivity coefficient. If the strain values ​​calculated by the two sensors deviate by more than 5%, they are identified as abnormal data points. Abnormal data points that exceed the preset strain threshold range are removed. The preset strain threshold range is 50% to 80% of the yield strain of the sealing material. The rule for removing abnormal data points is that the strain value exceeds the threshold within three consecutive sampling periods and the spatial correlation with the data of adjacent sensors is lower than the preset correlation coefficient. The preset correlation coefficient is 0.7 to 0.9. The spatial correlation is determined by calculating the Pearson correlation coefficient between the abnormal data point and the data of the eight adjacent sensors.

[0064] The verified strain data is matched with the stress-strain relationship curve by an interpolation algorithm to generate real-time installation stress data of the sealing contact interface. The interpolation algorithm is a bilinear interpolation algorithm. The input of the bilinear interpolation algorithm is the spatial coordinates and timestamp of the strain value, and the output is the stress component of the corresponding coordinate point. The stress component includes normal stress and shear stress.

[0065] The specific steps of the bilinear interpolation algorithm are as follows: For a coordinate point (x, y), select the strain values ​​ε1, ε2, ε3, and ε4 of its four nearest neighbor resistive strain gauges, and calculate the interpolated strain by weighting by distance: ε(x, y) = (w1ε1 + w2ε2 + w3ε3 + w4ε4) / (w1 + w2 + w3 + w4); ε(x, y) represents the interpolated strain; the weight is: wi = 1 / di 2 ; wi represents the weight of the i-th resistive strain gauge, and di is the Euclidean distance between the coordinate point and the i-th resistive strain gauge.

[0066] Real-time installation stress data is stored in the form of a three-dimensional stress field with a spatial resolution of 1 mm to 5 mm and a temporal resolution of 1 ms to 10 ms. The coordinate system of the three-dimensional stress field is aligned with the local coordinate system of the sealing contact interface. The origin of the local coordinate system is located at the geometric center of the sealing contact interface, and its axis coincides with the axis of symmetry of the seal.

[0067] The specific implementation method for constructing a phase-field model of the sealing contact interface based on real-time installation stress data and determining the diffusion path of the leaking medium along the sealing contact interface through crack network permeability analysis is as follows: The three-dimensional stress field components of the real-time installation stress data are used as the stress driving terms input to the phase-field model. The governing equations of the phase-field model include coupled stress equilibrium equations and phase-field sequence parameter evolution equations. The stress equilibrium equation is a linear elastic mechanical equilibrium equation used to calculate the displacement field and stress field distribution of the sealing contact interface under installation stress. The phase-field sequence parameter evolution equation is a diffusion-type equation based on Ginzburg-Landau theory, used to describe the crack initiation and propagation process. The crack surface energy density function in the phase-field sequence parameter evolution equation is defined based on the fracture toughness parameter of the sealing contact interface material. The fracture toughness parameter is measured by a standard three-point bending test. The specimen dimensions for the three-point bending test were 50 mm long, 10 mm wide, and 10 mm high, with a span of 40 mm. The loading rate was 0.5 mm per minute. The surface energy density function of the crack was a quadratic polynomial function, with the coefficient of the quadratic term proportional to the fracture toughness parameter. The stress-driven term was calculated using the three-dimensional stress field components from real-time installed stress data. The three-dimensional stress field components included normal stress and shear stress. The calculation formula for the stress-driven term was a linear combination of the stress field components. The weighting coefficient of the linear combination was adjusted according to the anisotropic properties of the sealing interface material. The anisotropic properties were determined by the difference between the stress-strain curves of the uniaxial tensile test and the shear test of the sealing material. The loading rate for the uniaxial tensile test was 1 mm per minute, and the shear test used a double shear clamp to apply an in-plane shear load at a loading rate of 0.5 mm per minute.

[0068] An explicit time integration algorithm is used to iteratively solve the phase-field model. The explicit time integration algorithm is the central difference method. The time step is adaptively adjusted according to the stability condition of the phase-field sequence parameter evolution equation. The stability condition is that the time step is less than or equal to the ratio of the square of the grid size to the material diffusion coefficient. The grid size is 1 mm to 5 mm. The material diffusion coefficient is obtained by experimental calibration of the thermal diffusion coefficient of the sealing material. The crack propagation path and crack network topology of the sealing contact interface are generated. The crack network topology includes geometric feature parameters such as crack branch angle and radius of curvature. The crack branch angle is defined as the angle between the two branches at the crack bifurcation point. The radius of curvature is defined as the radius of the fitted arc of the curved section of the crack path. The geometric feature parameters of crack branch angle and radius of curvature are extracted from the crack propagation path by an image processing algorithm. The image processing algorithm is a skeletonization algorithm based on Canny edge detection. After the skeletonization algorithm extracts the crack centerline, the crack branch angle and radius of curvature are fitted by the least squares method. The residual threshold of the least squares fitting is set to 0.1 mm. The fitting results exceeding the threshold are judged as invalid and recalculated.

[0069] Based on the geometric characteristic parameters of crack branching angle and radius of curvature, the equivalent permeability tensor of the crack network is calculated. The calculation of the equivalent permeability tensor involves a weighted statistical average of the crack branching angle and radius of curvature. The weighting coefficients are allocated according to the contribution ratio of the crack branching angle and radius of curvature to fluid flow resistance. The contribution ratio is determined through fluid dynamics simulation. Specifically, crack element models with different branching angles and radii of curvature are established. The dimensions of the crack element models are 5 mm long and 0.1 mm wide. A constant pressure difference of 1 MPa is applied, and the flow rate is calculated. The flow rate is related to the branching angle and radius of curvature. The reciprocal of the linear relationship is the contribution ratio. For example, when the branch angle is 90 degrees, the contribution ratio coefficient is 1.0. For every 10-degree decrease in the branch angle, the coefficient increases by 0.1. When the radius of curvature is 1 mm, the contribution ratio coefficient is 1.0. For every 0.5 mm increase in the radius of curvature, the coefficient decreases by 0.2. The formula for calculating the weighted statistical average is to multiply the permeability component of each crack element by its contribution ratio coefficient, sum them up, and then divide by the sum of the total contribution ratio coefficients. The unit of the permeability component is Darcy. The sum of the total contribution ratio coefficients is obtained by accumulating the contribution ratio coefficients of all crack elements.

[0070] The diffusion path of the leaking medium along the sealing interface is determined based on the matching degree between the direction of the maximum principal value of the equivalent permeability tensor and the direction of the main branches in the crack network topology. The matching degree is quantified by the cosine value of the direction angle, which is the cosine of the angle between the direction of the maximum principal value of the permeability tensor and the direction of the main branch of the crack. When the cosine value of the direction angle is greater than or equal to 0.9, it is considered a match, and the diffusion path extends along this direction. The direction of the main branch is the extension direction of the branch path with the highest connectivity in the crack network. The connectivity is calculated by multiplying the crack branch length by the number of adjacent crack elements. For example, if a branch path is 5 mm long and connects 3 adjacent crack elements, the connectivity is 15. The branch path with the highest connectivity is selected as the main branch direction. The direction of the main branch direction is obtained by fitting the extension trend line of the branch path using the least squares method. The fitting residual threshold of the trend line is set to 0.2 mm.

[0071] Step S2 constructs a phase-field model using real-time installation stress data and predicts leakage paths based on crack network permeability analysis. Its rationale lies in the fact that the phase-field model can couple stress distribution and crack evolution. Compared with existing technologies, this step dynamically corrects permeability calculations by leveraging the correlation between stress-driven terms and crack geometric parameters (branching angle, radius of curvature), thus solving the problem of leakage path prediction deviation caused by neglecting installation stress. The parameter linkage mechanism across mechanics and seepage field improves prediction accuracy.

[0072] Based on the phase-field model and diffusion path, the specific implementation method for dividing the sealing contact interface into high-stress sensitive regions and low-stress sensitive regions is as follows: The stress gradient distribution of the sealing contact interface is calculated based on the phase-field model. The stress gradient distribution includes normal stress gradient and shear stress gradient components. The normal stress gradient is the rate of change of the normal stress of the sealing contact interface with spatial coordinates, and the shear stress gradient is the rate of change of the shear stress with spatial coordinates. The stress gradient distribution is calculated by performing spatial partial derivative calculations on the three-dimensional stress field output by the phase-field model. The spatial partial derivative calculation adopts the central difference method, with a grid size of 1 mm to 5 mm. The step size of the central difference method is consistent with the grid size. For example, when the grid size is 2 mm, the step size is set to 2 mm. The spatial density distribution of diffusion paths is extracted. The spatial density distribution of diffusion paths is defined as the proportion of the length of the diffusion path within a unit area of ​​the sealed contact interface. The diffusion path length is measured from the diffusion path map using an image processing algorithm. The diffusion path map is generated by crack network permeability analysis. The image processing algorithm is a skeletonization and length statistics method based on the OpenCV library. The unit area is 1 square millimeter to 5 square millimeters. For example, when the unit area is set to 3 square millimeters, the diffusion path density is the total path length divided by 3 square millimeters.

[0073] The overlapping region of the stress gradient distribution and the diffusion path density distribution is marked as a candidate region for high stress-sensitive areas. The criteria for determining the overlapping region are that the absolute value of the stress gradient component is greater than or equal to a preset gradient threshold and the diffusion path density is greater than or equal to a preset density threshold. The preset gradient threshold is obtained through yield stress gradient experiments on the sealed contact interface material. The specimen size for the yield stress gradient experiment is 50 mm long, 10 mm wide, and 10 mm high, with a span of 40 mm and a loading rate of 1 mm per minute. The preset gradient threshold is determined based on the stress gradient value at specimen fracture. For example, if the stress gradient value at specimen fracture is 100 MPa per millimeter, then the preset gradient threshold is set to 80 MPa per millimeter. The preset density threshold is determined through diffusion path density simulation of the leaking medium at a standard leakage rate of 1 cubic centimeter per minute. The simulation uses the finite volume method to calculate the diffusion path length distribution. For example, if the median diffusion path density obtained from the simulation at the standard leakage rate is 0.5 mm per square millimeter, then the preset density threshold is set to 0.4 mm per square millimeter.

[0074] Based on the geometric relationship between the stress gradient components and diffusion path density within the candidate region, boundary delineation rules for high-stress-sensitive and low-stress-sensitive regions are generated. The boundary delineation rules define regions where the stress gradient components exceed a preset gradient threshold and the diffusion path density exceeds a preset density threshold as high-stress-sensitive regions, while the remaining regions are defined as low-stress-sensitive regions. The threshold determination adopts a pixel-by-pixel comparison method with a pixel resolution of 0.1 mm. For example, when the normal stress gradient of a certain pixel is 90 MPa per millimeter and the diffusion path density is 0.6 mm per square millimeter, it is determined to be a high-stress-sensitive region. Based on boundary partitioning rules, coordinate sets of high-stress sensitive regions and low-stress sensitive regions are output. The coordinate sets are generated by a spatial clustering algorithm that aggregates regions that meet the conditions. The spatial clustering algorithm is the density-based DBSCAN algorithm, with a neighborhood radius of 2 mm and a minimum number of neighboring points of 5. Isolated noise points are excluded during the clustering process. The criteria for identifying isolated noise points are that the number of pixels in the cluster is less than 10 and the distance from the nearest neighbor cluster is greater than 5 mm. For example, if a region contains 8 pixels and is 6 mm away from the nearest neighbor cluster, it is identified as a noise point and removed. The coordinate sets are stored in the form of a polygon vertex sequence in the local coordinate system of the sealed contact interface. The polygon vertex sequence is extracted from the boundary of the cluster region using the Alpha Shape algorithm, with a radius parameter of 1 mm. For example, the boundary point cloud of a certain cluster region is generated into a polygon with 20 vertices using the Alpha Shape algorithm.

[0075] Step S3 divides high / low stress sensitive areas based on the dual thresholds of stress gradient and diffusion path density, while also considering the spatial superposition effect of mechanical load and leakage medium diffusion. Compared with the single stress threshold division method in the existing technology, this step accurately locates high-risk leakage areas through spatial clustering algorithm and geometric relationship determination, solving the detection blind spot problem caused by misjudgment of local stress concentration in traditional methods. The multi-parameter collaborative area division logic reduces the false detection rate.

[0076] The specific implementation method for acquiring pressure signals and flow signals of the leaking medium at the sealed contact interface by acquiring high-frequency signals in high-stress sensitive areas and low-stress sensitive areas by acquiring low-frequency signals is as follows: Based on the coordinate sets of the high-stress sensitive areas and low-stress sensitive areas, the deployment positions of the pressure sensor array and flow sensor are configured. The pressure sensor array consists of multiple piezoelectric pressure sensors. The deployment positions of the piezoelectric pressure sensors are determined according to the polygon vertex sequence in the coordinate set of the high-stress sensitive areas. One piezoelectric pressure sensor is deployed at each polygon vertex, with a spacing of 1 mm to 5 mm between adjacent vertices. The deployment spacing of the piezoelectric pressure sensors in the low-stress sensitive areas is twice that in the high-stress sensitive areas. For example, when the vertex spacing in the high-stress sensitive areas is 2 mm, the deployment spacing in the low-stress sensitive areas is 4 mm. The flow sensor is a vortex flow meter. The deployment position of the vortex flow meter is determined according to the direction of the main branch of the diffusion path. The direction of the main branch is parallel to the boundary of the clustered region of the high-stress sensitive area, 1 mm to 3 mm away from the boundary line. For example, when the boundary of the clustered region is a straight line of 10 mm in length, the vortex flow meters are deployed at 1 mm intervals along the direction parallel to this straight line.

[0077] The high-frequency signal acquisition frequency is allocated according to the risk level of the high-stress sensitive area. The risk level is quantified by the product of the stress gradient component and the diffusion path density. The stress gradient component is the vector sum of the normal stress gradient and the shear stress gradient, which are extracted from the stress gradient distribution of the sealing contact interface. The diffusion path density is extracted from the diffusion path density distribution. The product quantification formula is: Risk Level = Stress Gradient Component × Diffusion Path Density. For example, if the stress gradient component is 120 MPa per millimeter and the diffusion path density is 0.6 mm per square millimeter, then the risk level is 72. The high-frequency signal acquisition frequency is linearly mapped to 1000 to 5000 times per second according to the risk level. The linear mapping relationship is: Frequency = 1000 + (Risk Level / Maximum Risk Level) × 4000. The maximum risk level is determined by statistical analysis of historical leakage accident data, which includes records of the leakage rate of the seal under different combinations of stress gradient and diffusion path density. For example, when the historical maximum risk level is 100, the frequency corresponding to risk level 72 is 1000 + (72 / 100) × 4000 = 3880 times per second.

[0078] A low-frequency signal acquisition frequency is allocated to the low-stress sensitive area. The low-frequency signal acquisition frequency is fixed at 100 to 500 times per second. The specific value is adjusted according to the area ratio of the low-stress sensitive area to the high-stress sensitive area. The area ratio is calculated by the ratio of the polygon area of ​​the low-stress sensitive area coordinate set to the total area of ​​the sealing contact interface. When the area ratio is less than 10%, 500 times per second is used; when the area ratio is greater than or equal to 10% and less than 30%, 300 times per second is used; and when the area ratio is greater than or equal to 30%, 100 times per second is used. For example, if the area of ​​the low-stress sensitive area is 15% of the total area, then the acquisition frequency is 300 times per second. The pressure sensor array and flow sensor are synchronized to acquire the pressure signal and flow signal of the leaking medium at the sealing contact interface in real time. The timestamp synchronization adopts a combination of GPS timing module and internal clock calibration. The synchronization accuracy of the GPS timing module is 1 microsecond, and the internal clock calibration cycle is once per minute. The calibration method is to compare the internal clock with the GPS timestamp and correct the deviation. The timestamp deviation between the pressure signal and the flow signal is less than or equal to 1 millisecond. The pressure signal and the flow signal are transmitted to the signal processing terminal via Modbus protocol. The data buffer capacity of the signal processing terminal is 10,000 data points per second. The data buffer adopts a circular queue structure to store real-time signals.

[0079] The pressure and flow signals are mapped to high-dimensional point cloud data. The continuous coherence barcode of the high-dimensional point cloud data is calculated and the barcode entropy value is extracted. The regional weights are assigned according to the spatiotemporal distribution correlation of the barcode entropy value in high-stress sensitive areas and low-stress sensitive areas. The specific implementation method for generating a compensation priority sequence is as follows: The pressure and flow signals are sliced ​​according to time windows. The length of each time window is 1 to 5 seconds. The sliding step of the time window is 10% to 50% of the window length. For example, when the time window length is 3 seconds, the sliding step is 0.3 seconds to 1.5 seconds. The signal sequence within the time window is mapped to high-dimensional point cloud data using a time-delay embedding method. The embedding dimension and delay parameter of the time-delay embedding method are adaptively adjusted based on the dynamic ratio of the high-frequency signal acquisition frequency in the high-stress sensitive area to the low-frequency signal acquisition frequency in the low-stress sensitive area. The dynamic ratio is the quotient of the high-frequency signal acquisition frequency divided by the low-frequency signal acquisition frequency. The embedding dimension is the integer part of the dynamic ratio, and the delay parameter is the decimal part of the dynamic ratio rounded to two decimal places. For example, if the high-frequency signal acquisition frequency is 5000 times per second and the low-frequency signal acquisition frequency is 500 times per second, the dynamic ratio is 10.0. In this case, the embedding dimension is set to 10, the delay parameter is 0.00, the mapping dimension of the time-delay embedding method is 10-dimensional, and the delay time is 0 milliseconds.

[0080] Continuous cohomology analysis is performed on high-dimensional point cloud data to generate continuous cohomology barcodes. The generation of continuous cohomology barcodes adopts the Vietoris-Rips complex construction method. The range of filtering parameters of the Vietoris-Rips complex construction method is dynamically set according to the statistical distribution of pressure signal amplitude. The statistical distribution of pressure signal amplitude includes mean and variance. The mean is the average value of pressure signal within each time window, and the variance is the square of the standard deviation of pressure signal amplitude. The standard deviation is calculated using an unbiased estimation formula. The lower limit of the filtering parameter is the mean minus three times the variance, and the upper limit is the mean plus three times the variance. For example, if the mean of the pressure signal is 10 MPa and the variance is 4 (standard deviation is 2 MPa), then the lower limit of the filtering parameter is 10 - 3 × 2 = 4 MPa, and the upper limit is 10 + 3 × 2 = 16 MPa. The range of the filtering parameter is 4 MPa to 16 MPa. The filtering step size is adjusted according to the dynamic range of pressure signal amplitude. The dynamic range is the difference between the upper and lower limits. For example, when the dynamic range is 12 MPa, the filtering step size is set to 0.3 MPa.

[0081] The barcode entropy value is calculated based on the length distribution of continuously homogeneous barcodes. The barcode entropy value is the Shannon entropy, calculated by taking the negative logarithm of the probability distribution of barcode lengths as a weighted sum. The probability distribution represents the proportion of each barcode length to the total length. A regional sensitivity weighting coefficient is introduced during the calculation. This coefficient is the ratio of the average lifespan of barcodes in high-stress sensitive areas to those in low-stress sensitive areas. The average lifespan of a barcode is the arithmetic mean of the lengths of all barcodes within the same area. For example, if the average lifespan of barcodes in a high-stress sensitive area is 10 seconds and in a low-stress sensitive area it is 5 seconds, then the regional sensitivity weighting coefficient is 2.0. The threshold for judging short-lifespan barcodes is dynamically adjusted based on the regional sensitivity weighting coefficient. The threshold for judging short-lifespan barcodes is the reciprocal of the regional sensitivity weighting coefficient multiplied by a baseline threshold, which is 1 second. For example, if the regional sensitivity weighting coefficient is 2.0, then the short-lifespan judgment threshold is 0.5 seconds. Barcodes shorter than 0.5 seconds are ignored in the entropy calculation, and the proportion of ignored barcodes in the total number of barcodes does not exceed 10%.

[0082] Regional weights are assigned based on the spatiotemporal distribution correlation of barcode entropy values ​​in high-stress-sensitive and low-stress-sensitive regions. The spatiotemporal distribution correlation is calculated using spatial gridding and a sliding time window. The spatial grid is aligned with the cluster boundaries of the high-stress-sensitive regions, with a grid size ranging from 1 mm to 5 mm, consistent with the vertex spacing of the polygons in the coordinate set of the high-stress-sensitive regions. For example, when the vertex spacing is 2 mm, the grid size is set to 2 mm. The time window length is inversely proportional to the signal acquisition frequency. For signal acquisition frequencies of 1000 to 5000 times per second, the time window length is 1 to 5 seconds. For example, when the signal acquisition frequency is 5000 times per second, the time window length is 1 second; when the signal acquisition frequency is 1000 times per second, the time window length is 5 seconds. The spatiotemporal sliding correlation is calculated using the Pearson correlation coefficient. Regions with a correlation coefficient greater than or equal to 0.7 are considered to have high correlation. The regional weight is the square of the correlation coefficient multiplied by the regional sensitivity weight coefficient. For example, if the correlation coefficient is 0.8 and the regional sensitivity weight coefficient is 2.0, then the regional weight is 0.8. 2 ×2.0=1.28.

[0083] The compensation priority sequence is generated by sorting regions in descending order of weight. The generation rule for the compensation priority sequence is to prioritize regions with the same weight, and the criteria for determining the high-frequency signal acquisition region is that the signal acquisition frequency is greater than or equal to 3000 times per second. The compensation priority sequence is stored in the format of a list of region numbers in the local coordinate system of the sealed contact interface. The region number corresponds one-to-one with the coordinate set index of the high-stress sensitive region and the low-stress sensitive region. For example, the compensation priority sequence is [region A1, region B3, region C2], which means that region A1 has the highest compensation priority. The list of region numbers is stored in JSON format, and each entry contains the region number, weight value and coordinate range.

[0084] Step S5 calculates the barcode entropy value by dynamically adjusting the time delay embedding parameters and regional sensitivity weights. Combining the characteristics of high-frequency / low-frequency signals with regional risk differences, it solves the limitation that traditional fixed topology parameters cannot adapt to dynamic leakage signals. Compared with existing technologies, this step introduces regional sensitivity weight coefficients (barcode lifetime ratio in high / low stress areas) and statistical distribution-driven filtering rules. By dynamically suppressing noise interference and strengthening the characteristics of high-risk areas, the sensitivity of leakage signal identification is improved. The dynamic adaptation mechanism of signal characteristics and regional weights directly addresses the complexity of local leakage paths caused by installation stress, ensuring strong consistency between the detection benchmark correction accuracy and the spatial distribution of leakage risk.

[0085] The specific implementation method for dynamically compensating high-weight regions based on the compensation priority sequence and outputting the corrected sealing performance test results is as follows: Extract the high-weight regions ranked first from the compensation priority sequence. The number of high-weight regions is determined according to a preset proportion range based on the total number of regions in the compensation priority sequence. The preset proportion range is 10% to 30% of the total number of regions. For example, when the compensation priority sequence contains 100 regions, the first 10 to 30 regions are extracted as high-weight regions. The extraction rule is to select continuously starting from the head of the sequence. If there are regions with the same weight in the sequence, the region corresponding to the high-frequency signal acquisition frequency is selected first. The condition for determining the high-frequency signal acquisition frequency is that the signal acquisition frequency is greater than or equal to 3000 times per second.

[0086] Dynamic compensation is applied to the pressure signal in high-weight areas. The dynamic compensation method involves adjusting the compensation coefficient based on the pressure signal deviation. The pressure signal deviation is the difference between the current pressure signal and the reference pressure signal. The reference pressure signal is the moving average of the historical pressure signal mean. The window length of the moving average is adaptively adjusted according to the time span of the historical data. The time span is the total duration of the historical data, and the window length is 10% to 20% of the time span. For example, if the historical data duration is 100 seconds, the window length is 10 to 20 seconds. The moving average is calculated by taking the arithmetic mean of the historical pressure signals within the window. The current pressure signal deviation is the difference between the current pressure signal value and the moving average. The compensation coefficient is 1 plus the ratio of the deviation to the moving average. For example, if the moving average is 10 MPa and the current pressure signal is 12 MPa, the deviation is 2 MPa, and the compensation coefficient is 1 + 2 / 10 = 1.2.

[0087] Dynamic compensation is applied to the flow signals in high-weight areas. The dynamic compensation method involves adjusting the compensation coefficient based on the flow signal deviation. The flow signal deviation is the difference between the current flow signal and the reference flow signal. The reference flow signal is the exponentially smoothed value of the historical flow signal average. The smoothing coefficient of the exponential smoothing value is dynamically set according to the flow signal change rate, which is the absolute change of the flow signal per unit time. The smoothing coefficient is the reciprocal of the change rate multiplied by the reference coefficient, which is between 0.1 and 0.3. For example, if the flow signal change rate is 0.5 liters per second, the smoothing coefficient is 0.2. The formula for calculating the exponential smoothing value is the current flow signal value multiplied by the smoothing coefficient plus the previous exponential smoothing value multiplied by (1 - smoothing coefficient). The current flow signal deviation is the difference between the current flow signal value and the exponential smoothing value. The compensation coefficient is 1 minus the ratio of the deviation value to the exponential smoothing value. For example, if the exponential smoothing value is 5 liters per minute and the current flow signal is 6 liters per minute, the deviation value is 1 liter per minute, and the compensation coefficient is 1 - 1 / 5 = 0.8.

[0088] The compensated pressure and flow signals are weighted and fused with the original signal from the uncompensated area by multiplying the area weight by the compensation coefficient. The area weight is the weight value defined in the compensation priority sequence, and the compensation coefficient is the dynamic compensation coefficient of the pressure or flow signal. The weighted fusion formula is the product of the compensated signal value and the area weight and the compensation coefficient, plus the product of the original signal value from the uncompensated area and (1 - the product of the area weight and the compensation coefficient). For example, if the area weight is 1.2, the compensation coefficient is 0.8, the product is 0.96, the compensated pressure signal is 12 MPa, and the original pressure signal from the uncompensated area is 10 MPa, then the fused pressure signal value is 12 × 0.96 + 10 × (1 - 0.96) = 11.52 + 0.4 = 11.92 MPa.

[0089] The output is the fused corrected sealing performance test result, which includes a pressure distribution cloud map and a leakage flow trend curve. The pressure distribution cloud map is generated by mapping the fused pressure signal to the local coordinate system of the sealing contact interface through an interpolation algorithm. The interpolation algorithm is bilinear interpolation. The leakage flow trend curve is generated by smoothing the fused flow signal according to a time window through a time series analysis method. The time series analysis method is the moving average method, and the moving average window length is 1 second to 5 seconds, which is consistent with the time window length in step S5. The corrected result is stored in the form of a two-dimensional image and a curve. The image resolution is 10 to 20 pixels per millimeter. The horizontal axis of the curve is the time axis, and the vertical axis is the flow value. The time axis scale is aligned with the signal acquisition timestamp in step S4.

[0090] All calculations involved in the embodiments are dimensionless numerical calculations, and the preset parameters and thresholds in the calculations are set by those skilled in the art according to the actual situation.

[0091] It should be noted that this invention can be deployed on the device itself to realize embedded applications, or it can run on a PC or other terminal with a user interface, thereby meeting various hardware environments and usage requirements.

[0092] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0093] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0094] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0095] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0096] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0097] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0098] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0099] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for online testing of the sealing performance of a sealing component, characterized in that, Includes the following steps: S1. During the installation of the seal, obtain real-time installation stress data between the seal and the mounting structure; S2. Construct a phase-field model of the sealing contact interface based on real-time installation stress data, and determine the diffusion path of the leaking medium along the sealing contact interface through crack network permeability analysis. S3. Based on the phase field model and diffusion path, the sealed contact interface is divided into a high-stress sensitive region and a low-stress sensitive region. S4. High-frequency signal acquisition is performed in high-stress sensitive areas, and low-frequency signal acquisition is performed in low-stress sensitive areas to obtain the pressure signal and flow signal of the leaking medium at the sealing contact interface. S5. Map the pressure signal and flow signal into high-dimensional point cloud data, calculate the continuous coherence barcode of the high-dimensional point cloud data and extract the barcode entropy value, allocate regional weights according to the spatiotemporal distribution correlation of the barcode entropy value in the high stress sensitive area and the low stress sensitive area, and generate a compensation priority sequence. S6. Dynamically compensate for high-weight regions based on the compensation priority sequence and output the corrected sealing performance test results.

2. The method for online testing of the sealing performance of a sealing component according to claim 1, characterized in that, During the installation of the seal, real-time installation stress data between the seal and the mounting structure is acquired, including: Multiple strain gauges are arranged on the contact surface between the seal and the mounting structure to form a stress sensing network; Dynamic strain data during the installation of the seal is collected in real time using distributed fiber optic sensors. Based on the preset stress-strain relationship curve, dynamic strain data is dynamically calibrated to generate real-time installation stress data.

3. The method for online testing of the sealing performance of a sealing component according to claim 1, characterized in that, A phase-field model of the sealing contact interface is constructed based on real-time installation stress data. The diffusion path of the leaking medium along the sealing contact interface is determined through crack network permeability analysis, including: The three-dimensional stress field components of the real-time installation stress data are used as the stress driving term input of the phase field model. The governing equations of the phase field model include the coupled stress balance equation and the phase field sequence parameter evolution equation. The crack surface energy density function in the phase field sequence parameter evolution equation is defined based on the fracture toughness parameter of the sealed contact interface material. An explicit time integration algorithm is used to iteratively solve the phase field model, generating crack propagation paths and crack network topology at the sealed contact interface. The crack network topology includes geometric characteristic parameters such as crack branch angle and radius of curvature. Based on the geometric characteristic parameters of crack branch angle and radius of curvature, the equivalent permeability tensor of the crack network is calculated. The calculation of the equivalent permeability tensor includes a weighted statistical average of crack branch angle and radius of curvature. The diffusion path of the leaking medium along the sealing contact interface is determined based on the matching degree between the direction of the maximum principal value of the equivalent permeability tensor and the direction of the main branches in the crack network topology.

4. The method for online testing of the sealing performance of a sealing component according to claim 1, characterized in that, Based on the phase-field model and diffusion path, the sealed contact interface is divided into high-stress-sensitive regions and low-stress-sensitive regions, including: The stress gradient distribution at the sealed contact interface is calculated based on the phase field model. The stress gradient distribution includes the normal stress gradient and shear stress gradient components. Extract the spatial density distribution of the diffusion path and mark the overlapping area of ​​the stress gradient distribution and the diffusion path density distribution as a candidate area of ​​high stress sensitive region; Based on the geometric relationship between the stress gradient components and diffusion path density within the candidate region, boundary delineation rules for high-stress-sensitive regions and low-stress-sensitive regions are generated. Based on the boundary division rules, the coordinate sets of high-stress sensitive areas and low-stress sensitive areas are output. The coordinate sets are generated by using a spatial clustering algorithm to aggregate areas that meet the conditions.

5. The method for online testing of the sealing performance of a sealing component according to claim 4, characterized in that, The boundary delineation rule defines a region as a high-stress-sensitive region where the stress gradient component exceeds a preset gradient threshold and the diffusion path density exceeds a preset density threshold.

6. The method for online testing of the sealing performance of a sealing component according to claim 1, characterized in that, High-frequency signal acquisition is performed in high-stress sensitive areas, and low-frequency signal acquisition is performed in low-stress sensitive areas to obtain pressure signals and flow signals of the leaking medium at the sealing contact interface, including: Based on the coordinate sets of high-stress sensitive areas and low-stress sensitive areas, configure the deployment locations of pressure sensor arrays and flow sensors; The high-frequency signal acquisition frequency is allocated according to the risk level of the high-stress sensitive area, and the risk level is quantified by the product of the stress gradient component and the diffusion path density. Low-frequency signal acquisition frequencies are allocated to low-stress sensitive areas; Synchronize the acquisition timestamps of the pressure sensor array and flow sensor to obtain the pressure signal and flow signal of the leaking medium at the sealing contact interface in real time.

7. The method for online testing of the sealing performance of a sealing component according to claim 1, characterized in that, Pressure and flow signals are mapped to high-dimensional point cloud data. Continuous cohomology barcodes are calculated from the high-dimensional point cloud data, and barcode entropy values ​​are extracted. Regional weights are assigned based on the spatiotemporal distribution correlation of barcode entropy values ​​in high-stress-sensitive and low-stress-sensitive regions, generating a compensation priority sequence, including: Pressure and flow signals are sliced ​​into time windows, and the signal sequence within each time window is mapped into high-dimensional point cloud data through time delay embedding. Continuous cohomology analysis is performed on high-dimensional point cloud data to generate continuous cohomology barcodes. The generation of continuous cohomology barcodes adopts the Vietoris-Rips complex construction method. The barcode entropy value is calculated based on the length distribution of the continuous homology barcode. The barcode entropy value is the Shannon entropy. A regional sensitivity weighting coefficient is introduced in the calculation. The regional sensitivity weighting coefficient is the ratio of the average lifespan of the barcode in the high-stress sensitive area to that in the low-stress sensitive area. Regional weights are assigned based on the spatiotemporal distribution correlation of barcode entropy values ​​in high-stress-sensitive and low-stress-sensitive regions. The compensation priority sequence is generated by sorting the regions in descending order of their weights. The rule for generating the compensation priority sequence is to prioritize the high-frequency signal acquisition regions with the same weights. The Shannon entropy is calculated by taking the negative logarithm of the probability distribution of barcode lengths, where the probability distribution is the proportion of each barcode length to the total length.

8. The method for online testing of the sealing performance of a sealing component according to claim 7, characterized in that, The embedding dimension and delay parameters of the time-delay embedding method are adaptively adjusted based on the dynamic ratio of the high-frequency signal acquisition frequency in the high-stress sensitive area to the low-frequency signal acquisition frequency in the low-stress sensitive area.

9. The method for online testing of the sealing performance of a sealing component according to claim 7, characterized in that, The spatiotemporal distribution correlation is calculated by spatial gridding and time window sliding correlation. The division of the spatial grid is aligned with the cluster boundary of the high stress sensitive area, and the length of the time window is inversely proportional to the signal acquisition frequency.

10. The method for online testing of the sealing performance of a sealing component according to claim 1, characterized in that, Dynamic compensation is performed on high-weight regions based on a compensation priority sequence, and the corrected sealing performance test results are output, including: Extract the high-weight regions that are ranked first from the compensation priority sequence. The number of high-weight regions is determined according to a preset ratio range based on the total number of regions in the compensation priority sequence. Dynamic compensation is performed on the pressure signal in the high-weight region. The dynamic compensation method is to adjust the compensation coefficient based on the pressure signal deviation value. Dynamic compensation is performed on the flow signal in high-weight areas. The dynamic compensation method is to adjust the compensation coefficient based on the flow signal deviation value. The compensated pressure and flow signals are then weighted and fused with the original signals from the uncompensated area by multiplying the area weight by the compensation coefficient. The output includes the weighted and fused corrected sealing performance test results, including pressure distribution cloud map and leakage flow trend curve.

Images