Method, system and equipment for detecting finished product forming degree of rubber part and medium

Abstract

The invention relates to a rubber part finished product forming degree detection method, system and equipment and a medium, and belongs to the technical field of rubber part forming degree detection. The molding degree detection method comprises the following steps: receiving surface point cloud data and surface geometric position information of a to-be-detected rubber part; constructing a three-dimensional surface contour model of the rubber part to be detected; mapping the surface pressure distribution data to the three-dimensional surface contour model, and detecting a pressure abnormal distribution area; extracting light scattering characteristic data according to the optical image data; comparing the light scattering characteristic data with the pressure abnormal distribution area to obtain a defect area analysis result; dynamic deformation characteristics of the rubber part to be tested under the dynamic environment simulation test are obtained; marking the three-dimensional surface contour model, and constructing a comprehensive feature model of the rubber part to be detected; and carrying out difference analysis on the comprehensive feature model to obtain a feature difference result of the to-be-detected rubber part, and generating a forming degree scoring report of the to-be-detected rubber part. According to the invention, the molding degree of the rubber part can be accurately detected.

Description

Technical Field

[0001] The present application relates to the technical field of rubber part molding degree detection, and in particular to a method, system, equipment and medium for detecting the finished molding degree of a rubber part. Background Art

[0002] Rubber parts are widely used in many industrial fields, such as seals in the automotive industry, shock absorbers in the construction field, and precision components in the medical industry. The quality and performance of rubber parts usually depend on their degree of molding, and the degree of molding detection is directly related to the sealing, durability and overall function of the product. However, since rubber parts usually have complex geometric shapes, multiple material combinations and different usage environments, the detection of their degree of molding still poses significant challenges in the existing technology.

[0003] At present, most of the molding degree detection methods of rubber parts are mainly focused on the measurement of geometric dimensions and simple identification of surface defects. Traditional detection methods (such as mechanical contact detection or two-dimensional image scanning) are insufficient in comprehensive coverage. Mechanical contact detection is difficult to capture overall geometric information due to the limited contact range, and the flexible characteristics of rubber parts can easily cause mechanical contacts to cause slight deformation or damage to their surfaces, thus affecting the accuracy of detection. On the other hand, although two-dimensional image scanning can avoid contact, its detection method based on surface projection is difficult to effectively identify deep concave areas or complex parts with internal structures, and there are detection blind spots.

[0004] Secondly, the material properties of rubber parts make it difficult for surface defects (such as blistering, cracks, collapse, etc.) to be accurately captured by traditional methods. For example, for tiny surface flaws, visual inspection relies on manual experience, and the detection results are easily affected by subjective factors; optical scanning is less sensitive to certain minor defects due to the complexity of reflected light, resulting in a high missed detection rate. In addition, for the performance of rubber parts in dynamic and complex environments, especially when facing some complex working conditions, existing technical methods cannot accurately detect the dynamic performance of rubber parts, which may cause the quality assessment results to be inconsistent with the actual performance, and thus fail to fully evaluate the stability and reliability of the molding degree. Summary of the invention

[0005] In order to achieve accurate detection of the molding degree of rubber parts, the present application provides a method, system, equipment and medium for detecting the molding degree of finished rubber parts.

[0006] In a first aspect, the present application provides a method for detecting the degree of finished product molding of a rubber part, which adopts the following technical solution: A method for detecting the degree of molding of a finished product of a rubber part, the method comprising: Receive surface point cloud data and surface geometric position information of the rubber part to be tested; Based on the three-dimensional contour model of the standard rubber part, and according to the surface point cloud data and the surface geometric position information, construct a three-dimensional surface contour model of the rubber part to be tested; Receiving surface pressure distribution data of the rubber part to be tested; Mapping the surface pressure distribution data to the three-dimensional surface contour model to detect the abnormal pressure distribution area of ​​the rubber part to be tested; Receiving optical image data collected from the surface of the rubber part to be tested under multi-angle optical scanning; extracting light scattering characteristic data according to the optical image data; Comparing the light scattering characteristic data with the pressure abnormal distribution area to obtain defect area analysis results; Acquiring dynamic deformation characteristics of the rubber component to be tested under a dynamic environment simulation test; Annotating the three-dimensional surface contour model according to the abnormal pressure distribution area, light scattering characteristic data, defect area analysis results and dynamic deformation characteristics, and constructing a comprehensive feature model of the rubber part to be tested; Performing difference analysis on the comprehensive characteristic model based on the standard characteristic data of the standard rubber part to obtain a characteristic difference result of the rubber part to be tested; A molding degree scoring report of the rubber part to be tested is obtained based on the characteristic difference results.

[0007] By adopting the above technical solutions, after collecting, processing and integrating multi-dimensional data, a comprehensive detection system for the molding degree of rubber parts is constructed, which can realize accurate evaluation from static geometric features to dynamic performance changes. Especially when facing some rubber parts with complex geometric shapes, the three-dimensional surface contour model constructed by point cloud data provides a basis for the precision analysis of geometric features; the combination of pressure distribution and optical feature mapping effectively reveals the specific location and type of surface defects; dynamic environmental simulation further verifies the deformation stability and weather resistance of rubber parts in actual working conditions. Combining these multi-source information, the system generates a comprehensive feature model through intelligent feature annotation, and derives the molding degree score and comprehensive defect report based on the difference analysis with standard parts. The technical solution of this application not only significantly improves the accuracy and reliability of detection, but also can quickly output intuitive and complete quality assessment results, providing an efficient and innovative solution for quality control and optimization in industrial production.

[0008] Optionally, the step of mapping the surface pressure distribution data to the three-dimensional surface contour model and detecting the abnormal pressure distribution area of ​​the rubber part to be tested includes: Mapping the surface pressure distribution data to the surface vertices of the three-dimensional surface contour model to obtain a three-dimensional surface contour model containing pressure value projection information; Generate a color gradient according to the pressure value projection information, and render the color gradient to the three-dimensional surface contour model to generate a surface pressure distribution map; Based on the pressure threshold range in the standard database, performing an abnormality analysis on each pressure point in the surface pressure distribution diagram, and marking the pressure points exceeding the pressure threshold range as abnormal points; Adjacent abnormal points are aggregated based on a clustering algorithm based on spatial density to obtain the abnormal pressure distribution area and corresponding characteristic parameters.

[0009] By adopting the above technical solution, the pressure distribution data is mapped to the three-dimensional surface contour model to generate a pressure distribution map, and the abnormal area is accurately detected by combining the spatial density clustering algorithm. This technical solution realizes the deep integration of pressure data and geometric models, and can intuitively and efficiently identify the pressure abnormal distribution area and generate detailed abnormal information. It not only improves the accuracy and precision of pressure anomaly detection, but also provides clear and reliable data support for the subsequent comprehensive evaluation of molding degree. Through the visual display of results, the intuitiveness and ease of use of the detection process are improved, meeting the needs of high-precision molding degree detection in industrial production.

[0010] Optionally, the step of comparing the light scattering characteristic data with the abnormal pressure distribution area to determine the defect area includes: Extracting a light scattering abnormal area based on the light scattering characteristic data; Aligning the spatial coordinates of the light scattering anomaly region and the pressure anomaly distribution region; Matching the central coordinates of the abnormal light scattering area with the central coordinates of the abnormal pressure distribution area in spatial position, and calculating the corresponding spatial distance; Determining whether the spatial distance is less than a preset distance threshold; If the distance is less than a preset distance threshold, it is determined that the light scattering abnormal area and the pressure abnormal distribution area have a spatial overlap relationship and are marked as a matching area; Comparing the characteristic parameters of the light scattering abnormal area with the characteristic parameters of the pressure abnormal distribution area in an overlapping relationship to determine whether there is a matching relationship; If there is a matching relationship, the matching area is determined as a defect area, and the corresponding defect type is determined according to the matching relationship to obtain the defect area analysis result; If there is no matching relationship, the matching area is determined as the area to be observed.

[0011] By adopting the above technical solution, the surface defects of rubber parts can be accurately located and classified through comparison and analysis of light scattering characteristic data and pressure abnormal distribution areas. The spatial alignment and position matching of the light scattering abnormal area and the pressure abnormal area clarify the geometric relationship between the two. The comparison of characteristic parameters further verifies the correlation of abnormal areas, thereby accurately identifying warpage defects and collapse defects. At the same time, areas with no matching characteristic parameters are marked as areas to be observed, providing a basis for subsequent analysis. This technical solution greatly improves the accuracy and reliability of defect detection, and provides comprehensive and accurate technical support for the quality assessment of rubber parts with complex geometric shapes.

[0012] Optionally, the step of obtaining the dynamic deformation characteristics of the rubber component to be tested under a dynamic environment simulation test includes: Receiving geometric deformation data and stress distribution data of the rubber part to be tested under a dynamic environment simulation test; wherein the dynamic environment simulation test includes performing a dynamic environment test under high temperature, low temperature or corrosive medium according to preset dynamic environment parameters; Performing time stamp synchronization on the geometric deformation data and the stress distribution data; Obtaining initial state data of the rubber part to be tested based on the three-dimensional surface contour model of the rubber part to be tested; Based on the initial state data, differential calculations are performed with the geometric deformation data and the stress distribution data to obtain dynamic deformation characteristics of the rubber component to be tested; wherein the dynamic deformation characteristics include geometric offset and stress distribution change data.

[0013] By adopting the above technical solution, the geometric deformation data and stress distribution data under dynamic environment simulation test are received, and combined with the initial three-dimensional model, the deformation characteristics of rubber parts in dynamic environment are accurately extracted. Timestamp synchronization ensures data consistency, and differential calculation quantifies geometric offset and stress changes, providing a scientific basis for dynamic stability assessment. The dynamic deformation feature data finally generated not only significantly improves the accuracy of rubber part molding detection, but also intuitively reveals its adaptability and reliability in actual working conditions, providing strong support for quality optimization.

[0014] Optionally, the step of obtaining a molding degree score report of the rubber part to be tested based on the characteristic difference result includes: Extract each type of feature difference data according to the feature difference result, and calculate the deviation mean of each type of feature difference data respectively; Based on the preset weight of each feature difference data, weighted calculation is performed according to the deviation mean of each feature difference data to obtain a comprehensive forming degree score; Determine defect distribution information and defect type according to the characteristic difference data and defect area analysis results; The comprehensive molding degree score, defect distribution information and defect type are integrated to obtain a molding degree score report of the rubber part to be tested.

[0015] By adopting the above technical solution, the differences in geometry, pressure, light scattering and dynamic deformation characteristics of the rubber parts to be tested are quantified, the defect type and distribution location are accurately identified, and the molding quality is intuitively displayed in the form of scores and visual reports. This technical solution realizes multi-dimensional feature fusion and clear data processing logic, which can effectively guide the quality optimization and production improvement of rubber parts.

[0016] Optionally, after the step of obtaining the comprehensive forming degree score, the following step is further included: Receiving dynamic environment test data of the rubber part to be tested under a dynamic environment simulation test; wherein the dynamic environment test data includes surface point cloud data, surface pressure distribution data, geometric offset data and stress distribution change data that change with time; Preprocessing the dynamic environment test data and performing time stamp synchronization to obtain a time series dynamic feature matrix; Extracting fatigue life key factors based on the time series dynamic characteristic matrix to obtain a fatigue life key factor data set; Based on the fatigue life key factor data set, construct a fatigue life prediction model; Inputting the time series dynamic characteristic matrix into the fatigue life prediction model, and calculating the fatigue life prediction value of the rubber part to be tested point by point; Based on a cluster analysis algorithm, generating a fatigue life prediction distribution of each area of ​​the rubber part to be tested according to the fatigue life prediction value; Calculating a comprehensive fatigue life score of the rubber component to be tested based on the fatigue life prediction distribution; The comprehensive fatigue life score and the comprehensive molding degree score are combined to obtain a comprehensive score of the rubber part to be tested.

[0017] By adopting the above technical solutions, a comprehensive evaluation of the molding quality and life characteristics of rubber parts is achieved through the collection and analysis of dynamic environmental test data, the construction of fatigue life prediction model, life distribution prediction and comprehensive score calculation. The final comprehensive score quantifies the overall performance of rubber parts under static and dynamic conditions, providing a scientific basis for quality optimization, design improvement and reliability evaluation of rubber parts.

[0018] Optionally, based on a cluster analysis algorithm, the step of generating a fatigue life prediction distribution of each region of the rubber component to be tested according to the fatigue life prediction value includes: Normalizing the fatigue life prediction value and the surface point cloud data, and performing spatial alignment to obtain a fatigue life distribution data set; Based on a clustering algorithm, each point in the fatigue life distribution data set is divided into a plurality of clusters, and a cluster center position is calculated for each cluster; Determine each region of the rubber part to be tested based on the cluster center position, and calculate the average fatigue life of each region to obtain the fatigue life prediction distribution of each region of the rubber part to be tested; The area where the average fatigue life value is higher than the preset life threshold is marked as a high-risk area.

[0019] By adopting the above technical solution, based on the fatigue life distribution prediction method of cluster analysis, the life characteristics of rubber parts are divided into multiple regions, each of which represents similar life characteristics. The fatigue life prediction distribution intuitively shows the life distribution on the surface of rubber parts, helping to quickly locate high-risk areas of life. This technical solution combines the annotation of cluster centers and regional boundaries, providing a scientific basis for optimizing the molding quality, improving life, and controlling risks of rubber parts.

[0020] In a second aspect, the present application provides a finished product molding degree detection system for rubber parts, which adopts the following technical solution: A finished product molding degree detection system for a rubber part, the molding degree detection system comprising: The first receiving module is used to receive the surface point cloud data and surface geometric position information of the rubber part to be tested; A model building module, for building a three-dimensional surface contour model of the rubber part to be tested based on a three-dimensional contour model of a standard rubber part and according to the surface point cloud data and surface geometric position information; A second receiving module is used to receive the surface pressure distribution data of the rubber part to be tested; A pressure anomaly detection module, used for mapping the surface pressure distribution data to the three-dimensional surface contour model, and detecting an abnormal pressure distribution area of ​​the rubber part to be tested; A third receiving module is used to receive optical image data collected from the surface of the rubber part to be tested under multi-angle optical scanning; An extraction module, used for extracting light scattering characteristic data according to the optical image data; A comparison module, used to compare the light scattering characteristic data with the pressure abnormal distribution area to obtain a defect area analysis result; An acquisition module, used for acquiring the dynamic deformation characteristics of the rubber part to be tested under a dynamic environment simulation test; A model annotation module, used to annotate the three-dimensional surface contour model according to the abnormal pressure distribution area, light scattering characteristic data, defect area analysis results and dynamic deformation characteristics, and construct a comprehensive feature model of the rubber part to be tested; A difference analysis module, used for performing a difference analysis on the comprehensive characteristic model based on the standard characteristic data of the standard rubber part to obtain a characteristic difference result of the rubber part to be tested; A scoring report generating module is used to obtain a molding degree scoring report of the rubber part to be tested based on the characteristic difference result.

[0021] In a third aspect, the present application provides a computer device, which adopts the following technical solution: A computer device comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method as described in the first aspect.

[0022] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program that can be loaded by a processor and execute any one of the methods in the first aspect.

[0023] In summary, the present application includes at least one of the following beneficial technical effects: The present application is applicable to the quality control and performance evaluation of complex-shaped rubber parts, especially in industrial applications requiring high-precision detection, and can effectively detect surface defects, mechanical problems, and insufficient deformation under dynamic environments. By generating a scoring report, it provides a scientific basis for quality improvement, design optimization, and performance improvement of rubber parts, thereby enhancing product reliability and service life, and has a wide range of industrial application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a first flow chart of a method for detecting the degree of finished product molding of a rubber part according to one embodiment of the present application.

[0025] Figure 2 It is a second flow chart of a method for detecting the degree of finished product molding of a rubber part according to one embodiment of the present application.

[0026] Figure 3 It is a third flow chart of a method for detecting the degree of finished product molding of a rubber part according to one embodiment of the present application.

[0027] Figure 4 It is a fourth flow chart of a method for detecting the degree of finished product molding of a rubber part according to one embodiment of the present application.

[0028] Figure 5 It is a fifth flow chart of a method for detecting the degree of finished product molding of a rubber part according to one embodiment of the present application.

[0029] Figure 6 It is a sixth flow chart of a method for detecting the degree of finished product molding of a rubber part according to one embodiment of the present application.

[0030] Figure 7 It is a seventh flow chart of a method for detecting the degree of finished product molding of a rubber part according to one embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solutions and advantages of this application more clear, the following Figure 1-7 It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0032] The embodiment of the present application discloses a method for detecting the degree of finished product molding of a rubber part.

[0033] Reference Figure 1 , a method for detecting the degree of molding of a finished product of a rubber part, the method for detecting the degree of molding comprising: Step S101, receiving surface point cloud data and surface geometric position information of the rubber part to be tested; In some embodiments, a flexible scanning device can be combined with a displacement sensor to collect detailed point cloud data on the surface of the rubber part. The point cloud data is composed of the three-dimensional coordinates of multiple discrete points on the surface (such as (x, y, z)), providing a spatial geometric description of the surface of the rubber part. At the same time, the displacement sensor provides accurate surface geometric position information, providing a reference for the positioning of the point cloud and subsequent modeling.

[0034] For example, the surface of the rubber part is scanned by a flexible scanning probe, and the point cloud data format collected is: P1 (x1, y1, z1), P2 (x2, y2, z2), ..., Pn (x n ,y n ,z n ), where n is the total number of sampling points. The density of the points determines the refinement of the model, and the displacement sensor records the relative positions of these points to ensure that the model is aligned in the spatial coordinate system.

[0035] It should be noted that for some complex curved rubber parts, such as U-shaped or ring-shaped parts, the scanning equipment needs to collect data at multiple angles to cover each surface area.

[0036] Step S102, based on the three-dimensional contour model of the standard rubber part, according to the surface point cloud data and the surface geometric position information, construct a three-dimensional surface contour model of the rubber part to be tested; Among them, a geometric modeling algorithm is used to fit and reconstruct the collected point cloud data to generate a three-dimensional surface contour model of the rubber part to be tested. By aligning it with the three-dimensional contour model of the standard rubber part, a preliminary analysis of key geometric parameters can be performed in the modeling stage, such as local bending radius, corrugation amplitude and other characteristics.

[0037] Specifically, after preprocessing the surface point cloud data, the point cloud data can be fitted based on the least squares method or polynomial fitting algorithm to generate local surface segments, and then the fitted local surface segments are aligned and smoothed to generate a preliminary complete surface model. The residuals between the point cloud and the fitted surface are compared, and the areas with large errors are fitted twice to improve the model accuracy, so that the preliminary generated three-dimensional surface contour model of the rubber part to be tested can be obtained. Based on the three-dimensional contour model of the standard rubber part, the iterative closest point algorithm (ICP) is used to accurately align the model of the part to be tested with the standard model. During the alignment process, the model matching degree is optimized according to specific features (such as edge points or reference markers). At the same time, the surface smoothing algorithm (such as Laplace smoothing) is used to optimize the model surface to reduce the fitting error, and a high-precision three-dimensional surface contour model of the rubber part to be tested is obtained.

[0038] It can be understood that by establishing a complete and high-precision three-dimensional surface contour model, it provides a basis for subsequent feature analysis and annotation, and quickly detects obvious geometric anomalies.

[0039] Step S103, receiving surface pressure distribution data of the rubber part to be tested; In one of the embodiments of the present application, a dynamic pressure sensor can be embedded in a flexible scanning probe, and the surface of the rubber part to be tested can be scanned using a dynamic pressure sensor array to measure its pressure distribution characteristics in the contact area. The pressure distribution data records the pressure value of each contact point (such as (x, y, z, p)), which is the key information for analyzing local molding defects (such as collapse, warping, etc.).

[0040] Step S104, mapping the surface pressure distribution data to a three-dimensional surface contour model to detect an abnormal pressure distribution area of ​​the rubber part to be tested; Specifically, the pressure data is projected onto the three-dimensional surface contour model through the pressure-contour mapping algorithm to form a corresponding model of "geometric features-pressure distribution". The pressure analysis algorithm is used to detect abnormal areas, and the pressure concentration points and abnormal distribution areas are marked according to their spatial positions to achieve the fusion of pressure and geometric features. The location of the abnormal area is visualized to provide guidance for subsequent optical feature analysis.

[0041] In some embodiments, after the mapping is completed, a pressure distribution map is generated on the three-dimensional surface contour model, and the color distinguishes the pressure size: blue indicates low pressure, and red indicates high pressure. It is found that the pressure value of the local area exceeds the normal range, and its coordinate area is marked, such as: Area 1: P1 (x1, y1, z1), p = 25Pa (collapse); Area 2: P2 (x2, y2, z2), p = 160Pa (warping).

[0042] Step S105, receiving optical image data collected from the surface of the rubber part to be tested under multi-angle optical scanning; Among them, the reflected light image data of the rubber surface is collected by a multi-angle optical scanning device. These image data record the light scattering characteristic data of the rubber surface, including reflection brightness, refraction intensity and scattering distribution, which is the basis for analyzing surface defects (such as bubbles and cracks).

[0043] In some embodiments, a 360° surface optical scan of the rubber part can be performed by installing a multi-angle light source and a high-resolution camera. For example, the optical scanning image shows the brightness distribution of the rubber part surface under different angles of illumination. For example, the brightness of area A is significantly lower than the standard, indicating that cracks may exist; the brightness of area B is uniform and has no abnormalities, indicating that there are no defects in this area.

[0044] Step S106, extracting light scattering characteristic data according to the optical image data; The light scattering characteristic data includes the light scattering abnormal area extracted from the optical image data and its spatial position and characteristic parameters (such as reflection brightness, scattering direction, and refraction intensity); Specifically, the image processing algorithm is used to extract optical characteristics such as reflection brightness, refraction intensity and scattering distribution from the optical image data to analyze the optical characteristics of surface defects. For example, if the extracted scattering characteristic parameter is reflection brightness B=0.5 and the standard value is B=1.0, it means that the refraction intensity is weak and the scattering distribution is uneven, which may correspond to the presence of surface cracks or bubbles, and the corresponding light scattering abnormal area can be determined.

[0045] Step S107, comparing the light scattering characteristic data with the pressure abnormal distribution area to obtain the defect area analysis result; Among them, by comparing the light scattering characteristic data with the pressure abnormal distribution area, it is verified whether the surface defect is related to the mechanical properties, and the defect area and type are further clarified. For example, if the comparison finds that the light scattering abnormal area overlaps with the pressure concentration area, it is further confirmed that there is a warpage defect area at that location.

[0046] Step S108, obtaining the dynamic deformation characteristics of the rubber component to be tested under the dynamic environment simulation test; In some embodiments, the rubber part to be tested can be placed in an environmental simulation cavity to simulate the actual use environment (such as high temperature, low temperature or corrosive conditions), and then high-precision displacement sensors and stress sensors are used to collect geometric deformation and stress distribution data under environmental changes in real time to evaluate the molding stability and weather resistance of the rubber part under real working conditions. For example, under high temperature conditions, the geometric offset of the rubber part is detected to be 0.3mm, which is lower than the standard allowable range; in a corrosive environment, deformation occurs in the local stress concentration area.

[0047] Step S109, annotating the three-dimensional surface contour model according to the pressure abnormal distribution area, light scattering characteristic data, defect area analysis results and dynamic deformation characteristics, and constructing a comprehensive characteristic model of the rubber part to be tested; Among them, the pressure distribution, light scattering characteristic data, defect area and dynamic deformation characteristics are integrated to generate a fully annotated comprehensive feature model. The comprehensive feature model marks the defect area in three-dimensional space and annotates the specific type (such as blistering, cracking, warping) and the corresponding performance changes under dynamic conditions.

[0048] Specifically, the data of the abnormal pressure area is mapped to the corresponding surface vertices of the three-dimensional surface contour model, and the size and distribution area of ​​the pressure value are marked; the light scattering characteristic data is mapped to the three-dimensional model surface, and the abnormal light scattering area is marked; the defect area is mapped to the three-dimensional model surface, and the defect type is marked; the geometric offset data and stress distribution change data in the dynamic deformation characteristics are mapped to the model surface vertices.

[0049] Step S110, performing difference analysis on the comprehensive characteristic model based on the standard characteristic data of the standard rubber part to obtain a characteristic difference result of the rubber part to be tested; Among them, by comparing the comprehensive characteristic model of the rubber part to be tested with the standard characteristic data, it is possible to quantify the characteristic differences, locate the abnormal areas and determine the degree of difference; illustratively, the comparison results show that the pressure distribution deviation of the rubber part to be tested is 10%, and the dynamic deformation deviation is 0.5mm.

[0050] Step S111, obtaining a molding degree score report of the rubber part to be tested based on the characteristic difference result.

[0051] Among them, the forming degree score can be calculated based on the difference results and combined with the weighted algorithm to generate a comprehensive report including the overall score, defect location and defect type. For example, the forming degree score report shows that the comprehensive forming degree score is 85 / 100, with 1 pressure anomaly and 2 warpage defect areas.

[0052] In one of the embodiments of the present application, the system extracts the geometric features, pressure distribution, light scattering characteristics and dynamic deformation data of the rubber part to be tested from the feature difference analysis stage. These data include the deviation amount, over-standard area and statistical information of each feature. Then, the system quantifies and weights the feature difference results. The deviation amount of each feature (such as the average value of the geometric offset, the percentage of pressure distribution deviation, etc.) is quantified into a specific value and allocated according to the weight. For example, the geometric feature weight is set to 40%, the pressure distribution weight is 30%, the light scattering characteristic weight is 20%, and the dynamic deformation weight is 10%. These weights reflect the importance of different features in the molding degree score. By setting a comprehensive scoring formula, the system substitutes the feature deviation value and weight one by one to calculate the final molding degree score.

[0053] In addition, after the scoring calculation is completed, the system further analyzes and classifies the defects. Combined with the characteristic difference data, the specific defect types of rubber parts are identified, such as warping defects, collapse defects, pressure abnormal areas, and light scattering abnormal areas. Each defect type is accurately located and the corresponding deviation information is attached, such as position coordinates, deviation size, and type label. The system also counts the defect areas and calculates the distribution area and proportion of each defect type. These classification results provide a qualitative supplement to the molding degree score.

[0054] In the above implementation, a comprehensive detection system for the degree of molding of rubber parts is constructed through the collection, processing and fusion of multi-dimensional data, which can realize accurate evaluation from static geometric features to dynamic performance changes. When facing some rubber parts with complex geometric shapes, this technical solution can use the three-dimensional surface contour model constructed by point cloud data to provide a basis for the precision analysis of geometric features; the combination of pressure distribution and optical feature mapping can effectively reveal the specific location and type of surface defects; dynamic environmental simulation further verifies the deformation stability and weather resistance of rubber parts in actual working conditions. Combining these multi-source information, the system generates a comprehensive feature model through intelligent feature annotation, and derives a molding degree score and a comprehensive defect report based on the difference analysis with standard parts.

[0055] The technical solution of this application not only significantly improves the accuracy and reliability of detection, but also can quickly output intuitive and complete quality assessment results, providing an efficient and innovative solution for quality control and optimization in industrial production.

[0056] Reference Figure 2 As an implementation method of step S104, the step of mapping the surface pressure distribution data to the three-dimensional surface contour model and detecting the abnormal pressure distribution area of ​​the rubber part to be tested includes: Step S201, mapping the surface pressure distribution data to the surface vertices of the three-dimensional surface contour model to obtain the three-dimensional surface contour model containing the pressure value projection information; The collected pressure distribution data (x, y, z, p) is matched with the vertex set of the three-dimensional surface contour model to establish the corresponding relationship between the pressure value and the geometric vertex. The pressure value can be distributed to the vertices of the three-dimensional model surface through the nearest neighbor interpolation algorithm or weight distribution to ensure that each vertex is associated with a pressure value.

[0057] For example, it is assumed that the three-dimensional surface contour model of the rubber part includes vertices (x i ,y i ,z i ), the collected pressure distribution data is (x k ,y k ,z k ,p k), through nearest neighbor interpolation, vertex (x i ,y i ,z i ) is assigned to the nearest data point (x k ,y k ,z k ) corresponds to the pressure value p k .

[0058] Step S202, generating a color gradient according to the pressure value projection information, and rendering the color gradient to a three-dimensional surface contour model to generate a surface pressure distribution map; Among them, a color gradient is generated according to the size of the pressure value, corresponding to different colors from low to high (such as blue to red), and the color gradient is rendered to the surface vertices of the three-dimensional surface contour model to intuitively represent the pressure distribution.

[0059] For example, assuming that the pressure value range is [20,200]Pa, p<50: rendered in blue, indicating low pressure; 50≤p≤150: rendered in green to yellow, indicating normal pressure; p>150: rendered in red, indicating high pressure; the pressure distribution map presented on the three-dimensional surface contour model can clearly show the pressure changes in each area.

[0060] Step S203, based on the pressure threshold range in the standard database, performing an abnormality analysis on each pressure point in the surface pressure distribution diagram, and marking the pressure points that exceed the pressure threshold range as abnormal points; The pressure range threshold stored in the standard database (for example, the normal range is [50, 150] Pa) is used to compare the pressure values ​​on the surface pressure distribution diagram point by point, and the pressure points that exceed the normal range are marked as abnormal points.

[0061] For example, assuming that the pressure range of the standard database is [50,150] Pa: the pressure point (x1, y1, z1, p1=30) is lower than the lower limit of the range and is marked as a "collapse anomaly point"; the pressure point (x2, y2, z2, p2=170) is higher than the upper limit of the range and is marked as a "warping anomaly point".

[0062] Step S204: clustering adjacent abnormal points based on a spatial density clustering algorithm to obtain an abnormal pressure distribution area and corresponding characteristic parameters.

[0063] Among them, the characteristic parameters of the pressure abnormal distribution area include abnormal type, pressure value range, distribution pattern, etc.

[0064] Specifically, a spatial density clustering algorithm (such as DBSCAN) is used to cluster adjacent abnormal points in space to form a complete abnormal area and extract the boundary information of the area. The clustering algorithm can identify the distribution pattern of abnormal points, aggregate scattered abnormal points into abnormal distribution areas, determine the spatial range and shape of abnormal areas, and provide a basis for regional annotation and statistics.

[0065] For example, assume that the marked abnormal points are as follows: the distance between (x1, y1, z1, p1 = 30) and (x2, y2, z2, p2 = 35) is less than the set neighborhood threshold ϵ = 5 mm, then they can be clustered into the same "collapse area"; the distance between (x3, y3, z3, p3 = 170) and (x4, y4, z4, p4 = 165) is less than the threshold ϵ = 5 mm, then they can be clustered into the same "warping area".

[0066] It can be understood that the abnormal areas formed by clustering are marked, including the abnormal type (collapse or warping), the average pressure value of the area and the spatial coordinate center, and the average pressure value and area in the area are calculated to provide detailed information for the subsequent forming degree evaluation.

[0067] In the above implementation, the pressure distribution data is mapped to the three-dimensional surface contour model to generate a pressure distribution map, and the abnormal area is accurately detected by combining the spatial density clustering algorithm. This technical solution realizes the deep integration of pressure data and geometric models, and can intuitively and efficiently identify the pressure abnormal distribution area and generate detailed abnormal information, which not only improves the accuracy and precision of pressure abnormality detection, but also provides clear and reliable data support for the subsequent comprehensive evaluation of molding degree. Through the visual display of results, the intuitiveness and ease of use of the detection process are improved, meeting the needs of high-precision molding degree detection in industrial production.

[0068] Reference Figure 3 As an implementation of step S107, comparing the light scattering characteristic data with the pressure abnormal distribution area, the step of determining the defect area includes: Step S301, extracting a light scattering abnormal area based on light scattering characteristic data; Among them, the light scattering abnormal area is extracted through the light scattering characteristic data (such as reflection brightness, scattering direction, refraction intensity, etc.), and the image processing algorithm is used to detect the abnormal characteristic area in the optical image and obtain its spatial coordinate range.

[0069] For example, assuming that the normal value range of brightness in the light scattering image is [0.7, 1.0], if the brightness of a certain area is lower than 0.5 (such as 0.3 or 0.4), the area is marked as a light scattering abnormal area, and its spatial coordinate range (x1, y1, z1) to (x2, y2, z2) is extracted.

[0070] It can be understood that by analyzing the light scattering characteristic data and extracting the abnormal area, a foundation is laid for the subsequent spatial alignment and matching.

[0071] Step S302, aligning the spatial coordinates of the light scattering abnormal area and the pressure abnormal distribution area; Among them, through coordinate mapping or coordinate system calibration, the data of the light scattering anomaly area and the pressure anomaly distribution area are unified into the same spatial reference system to ensure the consistency of the geometric correspondence of the areas in the subsequent comparison process.

[0072] For example, the coordinate system reference of the light scattering anomaly area is the pixel coordinates of the optical image, while the coordinates of the pressure anomaly distribution area are based on the three-dimensional surface contour model. The coordinates of the light scattering anomaly area can be converted into the coordinate system of the three-dimensional surface contour model through a three-dimensional interpolation algorithm.

[0073] Step S303, spatially matching the central coordinates of the light scattering abnormal area with the central coordinates of the pressure abnormal distribution area, and calculating the corresponding spatial distance; Among them, the spatial position matching algorithm is used to calculate the Euclidean distance between the center of the light scattering anomaly area and the center of the pressure anomaly distribution area as a similarity measure of the spatial positions of the two.

[0074] For example, assuming that the center coordinates of the light scattering abnormal area are (x g ,y g ,z g ), the center coordinate of the pressure anomaly distribution area is (x p ,y p ,z p ), the calculated spatial distance Δd is: .

[0075] It can be understood that by obtaining the spatial relationship between the light scattering abnormality area and the pressure abnormality area, an accurate geometric basis is provided for determining the overlapping relationship of the areas.

[0076] Step S304, determining whether the spatial distance is less than a preset distance threshold; if it is less than the preset distance threshold, jumping to step S305; if it is greater than the preset distance threshold, no operation is performed; The calculated spatial distance Δd is compared with the preset threshold ϵ. If Δd≤ϵ, it is considered that there is a spatial overlap between the light scattering anomaly area and the pressure anomaly area.

[0077] Step S305, determining that there is a spatial overlap between the light scattering abnormal area and the pressure abnormal distribution area, and marking them as matching areas; For example, if the threshold is set to ϵ=5 mm and Δd=3.2 mm, it is determined that the two types of abnormal regions have a spatial overlap and are marked as matching regions.

[0078] Step S306, comparing the characteristic parameters of the light scattering abnormal region with the characteristic parameters of the pressure abnormal distribution region having an overlapping relationship; Among them, characteristic matching analysis is performed on the light scattering characteristic parameters (such as brightness and scattering direction) and pressure distribution characteristic parameters (such as pressure value distribution and pressure concentration degree) of the overlapping area to determine whether there is a correlation.

[0079] Step S307, determine whether there is a matching relationship; if there is a matching relationship, jump to step S308; if there is no matching relationship, jump to step S309; Step S308, determining the matching area as a defect area, and determining the corresponding defect type according to the matching relationship, and obtaining a defect area analysis result; Among them, defect types include warpage defects and collapse defects; In some specific embodiments, if the light scattering anomaly matches a high-pressure area, the area is determined to be a defect area, and the defect type is a "warping defect"; if the light scattering anomaly matches a low-pressure area, the area is marked as a defect area, and the defect type is a "collapse defect".

[0080] Step S309: determine the matching area as the area to be observed.

[0081] It is understandable that if there is no obvious correlation between the light scattering characteristic parameters and the pressure distribution characteristic parameters, the overlapping area is marked as an "area to be observed", indicating that further analysis of possible complex defects is required.

[0082] In the above implementation, by comparing and analyzing the light scattering characteristic data with the pressure abnormal distribution area, the surface defects of the rubber parts are accurately located and classified. The spatial alignment and position matching of the light scattering abnormal area and the pressure abnormal area clarify the geometric relationship between the two, and the comparison of the characteristic parameters further verifies the correlation of the abnormal areas, thereby accurately identifying warping defects and collapse defects. At the same time, the areas with no matching characteristic parameters are marked as areas to be observed, providing a basis for subsequent analysis. This technical solution greatly improves the accuracy and reliability of defect detection, and provides comprehensive and accurate technical support for the quality assessment of rubber parts with complex geometric shapes.

[0083] Reference Figure 4 As an implementation of step 108, the step of obtaining the dynamic deformation characteristics of the rubber part to be tested under the dynamic environment simulation test includes: Step S401, receiving geometric deformation data and stress distribution data of the rubber part to be tested under a dynamic environment simulation test; Among them, the dynamic environment simulation test includes dynamic environment testing under high temperature, low temperature or corrosive media according to preset dynamic environment parameters; Specifically, the dynamic environment simulation test is carried out under preset dynamic environment parameters (such as high temperature, low temperature or corrosive conditions), using high-precision displacement sensors and stress sensors to collect real-time geometric deformation and stress distribution data of rubber parts at different test stages; these data are stored in the form of time series, and each sampling point at each moment is associated with a timestamp, geometric coordinates and stress value.

[0084] For example, in a 120°C environment, the geometric deformation data collected by the displacement sensor is: P1(t1)=(x1+Δx1,y1+Δy1,z1+Δz1), the stress distribution data collected by the stress sensor is: σ1(t1)=σ x (t1),σ y (t1),σ z (t1).

[0085] Step S402, synchronizing the geometric deformation data and the stress distribution data with timestamps; Among them, the geometric deformation data and stress distribution data may be collected by different sensors, and the sampling frequencies are not completely consistent, so the data needs to be synchronized through timestamps to ensure the consistency of the geometric and stress states at each time point. For example, if the displacement sensor samples 10 times per second and the stress sensor samples 5 times per second, the two sets of data are interpolated and matched according to the timestamps to ensure the consistency of the dynamic data and provide a data basis for the accuracy of subsequent differential calculations.

[0086] Step S403, obtaining initial state data of the rubber part to be tested based on the three-dimensional surface contour model of the rubber part to be tested; Among them, the geometric data of the initial state (such as coordinate points (x, y, z) and stress distribution (σ x ,σ y ,σ z ) as a reference benchmark for dynamic environmental changes.

[0087] Step S404, based on the initial state data, differential calculation is performed with the geometric deformation data and the stress distribution data to obtain the dynamic deformation characteristics of the rubber component to be tested; Among them, the dynamic deformation characteristics include geometric offset and stress distribution change data.

[0088] Specifically, by performing point-by-point differentiation between the real-time data under the dynamic environment simulation test and the initial state data, the geometric offset and stress distribution change of the rubber part are calculated, thereby extracting the deformation characteristics of the rubber part under the dynamic environment and quantifying the dynamic change area.

[0089] The calculation formula of geometric offset is: ; In the above formula, x t ,y t ,z t It is the real-time geometric deformation data under dynamic environment simulation test, and x0, y0, z0 are the initial geometric deformation data.

[0090] The calculation formula for the change in stress distribution is: ; In the above formula, σ xt、 σ yt、 σ zt is the real-time stress distribution data under dynamic environment simulation test, Δσ x0， Δσ y0， Δσ z0 is the initial stress distribution data.

[0091] For example, assuming that the initial point is P1=(10,20,5) and the dynamic data point is P1(t)=(10.2,20.3,5.1), the geometric offset is ΔP1=(0.2,0.3,0.1) and the stress change is Δσ1=(Δσ x =5 MPa,Δσ y =3 MPa,Δσ z =−1 MPa).

[0092] In the above implementation, the geometric deformation data and stress distribution data under the dynamic environment simulation test are received, and combined with the initial three-dimensional model, the deformation characteristics of the rubber parts in the dynamic environment are accurately extracted. Timestamp synchronization ensures data consistency, and differential calculation quantifies geometric offset and stress changes, providing a scientific basis for dynamic stability assessment. The dynamic deformation feature data finally generated not only significantly improves the accuracy of rubber part molding detection, but also intuitively reveals its adaptability and reliability in actual working conditions, providing strong support for quality optimization.

[0093] In one embodiment of the present application, the specific steps of performing difference analysis on the comprehensive feature model based on the standard feature data include: First, by performing a differential analysis on the pressure distribution data in the pressure abnormality area, the deviation between the actual pressure value of the rubber part to be tested and the standard pressure value is calculated point by point, the overall deviation percentage of the pressure distribution is quantified, and it is determined whether the pressure concentration area or the pressure distribution pattern deviates from the standard. The specific location and range of the pressure exceeding the standard area are marked to form a pressure abnormality distribution map. This analysis provides basic support for the subsequent difference evaluation of light scattering characteristics and dynamic deformation characteristics.

[0094] Next, the light scattering characteristic data is analyzed for differences. By comparing the light scattering characteristic data of the rubber part to be tested (such as brightness deviation and scattering direction change) with the standard characteristic data, the abnormal light scattering areas are identified and marked. For example, significant changes in brightness deviation and scattering direction offset angle may be directly associated with pressure concentration areas or other defect types. The difference analysis of light scattering characteristic data can not only help identify surface defect areas, but also provide a characterization basis for subsequent dynamic performance evaluation.

[0095] Subsequently, the dynamic deformation characteristics are analyzed for differences, focusing on the differences in geometric offset and stress changes of rubber parts under dynamic environment simulation conditions. By comparing the dynamic deformation data of the rubber parts to be tested with the standard data, the dynamic offset and stress change differences are calculated point by point, and the areas where the dynamic deformation deviation exceeds the standard are marked. The difference analysis of dynamic characteristics can reveal the adaptive deviation of rubber parts under actual use conditions and lay the foundation for dynamic performance evaluation.

[0096] Finally, the geometric feature data is analyzed for differences. The geometric shape of the comprehensive feature model of the rubber part to be tested and the geometric offset of the standard three-dimensional model are calculated point by point, the excess area is marked, and the average and maximum values ​​of the geometric offset are quantified. The geometric feature difference analysis is the final verification of the pressure distribution and dynamic deformation characteristics, and comprehensively reveals the accuracy of the overall deformation of the rubber part.

[0097] Through the difference analysis of the above multi-dimensional features, the characteristic differences between the rubber parts to be tested and the standard rubber parts are quantified, and the molding degree score is calculated by combining the weighted algorithm, and finally a molding degree score report can be generated.

[0098] Reference Figure 5 As an implementation of step S111, the step of obtaining a molding degree score report of the rubber part to be tested based on the characteristic difference result includes: Step S501, extracting each type of feature difference data according to the feature difference result, and calculating the deviation mean of each type of feature difference data respectively; Among them, the specific data of each feature is extracted from the feature difference analysis results, including geometric features, pressure distribution, light scattering characteristics and dynamic deformation data, and the deviation mean of each feature data is calculated respectively to quantify the degree of difference between the rubber part to be tested and the standard rubber part.

[0099] Specifically, the average value and the percentage of the area exceeding the standard are calculated for the geometric offset; the pressure deviation percentage is calculated for the pressure distribution data; the brightness deviation mean and the scattering direction deviation angle are calculated for the light scattering characteristic data; and the mean value of the geometric offset and stress change are calculated for the dynamic deformation data.

[0100] Step S502, based on the preset weight of each feature difference data, weighted calculation is performed according to the deviation mean of each feature difference data to obtain a comprehensive forming degree score; Specifically, weights are assigned according to the importance of each feature, and weighted calculation is performed in combination with the deviation mean to generate a comprehensive shaping score. The scoring formula is as follows: ; In the above formula, S is the comprehensive forming degree score; w i is the feature weight, such as geometric features 40%, pressure distribution 30%, light scattering characteristics 20%, and dynamic deformation 10%; Δi is the mean of the feature deviation.

[0101] For example, the weight of geometric offset is 40%, the mean is 0.3; the weight of pressure distribution is 30%, the deviation percentage is 8%; the weight of light scattering is 20%, the brightness deviation is 12%; the weight of dynamic deformation is 10%, and the offset is 0.4. Therefore, the comprehensive score is: S=100−(0.4×0.3+0.3×8+0.2×12+0.1×0.4)=85.2.

[0102] It can be understood that by comprehensively considering the weights and deviations of each feature, these weights reflect the importance of different features in the molding degree score. By setting the comprehensive scoring formula, the system inputs the feature deviation values ​​and weights one by one to calculate the final molding degree score, thereby realizing the quantitative fusion of multi-dimensional features and generating an overall molding quality score for the rubber part to be tested.

[0103] Step S503, determining defect distribution information and defect type according to the feature difference data and defect area analysis results; Among them, by analyzing the characteristic difference results, the defect area distribution and defect type of the rubber part are identified, and the defect information is annotated in the 3D model. By accurately identifying the defect type and distribution, an intuitive representation of the molding quality of the rubber part is provided, providing guidance for production improvement.

[0104] In some embodiments, defect types are classified according to the overlapping relationship of multidimensional features. For example, when an area where the geometric offset exceeds the standard overlaps with an area where pressure is concentrated, it is determined to be a warping defect area; when an area where the geometric offset exceeds the standard overlaps with an area where pressure is sparse, it is determined to be a collapse defect area; when an area where the brightness deviation or direction offset exceeds the standard, it is determined to be an abnormal light scattering area.

[0105] Step S504 , integrating the comprehensive molding degree score, defect distribution information and defect type to obtain a molding degree score report of the rubber part to be tested.

[0106] Among them, the comprehensive score, defect distribution information and dynamic performance results are integrated to generate a structured score report, including the overall score, defect type and location distribution, dynamic performance evaluation, etc. The report is visualized in the form of tables, graphs or three-dimensional models.

[0107] In the above implementation, the differences in geometry, pressure, light scattering and dynamic deformation characteristics of the rubber parts to be tested are quantified, the defect types and distribution locations are accurately identified, and the molding quality is intuitively displayed in the form of scores and visual reports. This technical solution realizes multi-dimensional feature fusion and clear data processing logic, which can effectively guide the quality optimization and production improvement of rubber parts.

[0108] Reference Figure 6 As a further implementation of the detection method, after the step of obtaining the comprehensive forming degree score, it also includes: Step S601, receiving dynamic environment test data of the rubber component to be tested under a dynamic environment simulation test; Among them, the dynamic environment test data includes surface point cloud data, surface pressure distribution data, geometric offset data and stress distribution change data that change with time; Specifically, the dynamic environment simulation test is designed to simulate the dynamic performance of rubber parts under actual working conditions. High-precision sensors are used to collect surface point cloud data (x, y, z) and surface pressure distribution data (p t ), geometric offset data (ΔL t ) and stress distribution change data (Δσ t ), these data reflect the geometric deformation and stress response of rubber parts under different dynamic conditions.

[0109] For example, in a high temperature dynamic test, the surface pressure distribution of a rubber part changes with time: t ={p1,p2,…,p n}; where p n Indicates time t n The pressure value at the moment.

[0110] It should be noted that, unlike the surface point cloud data and surface pressure distribution data collected statically before, the static data provides the initial state information of the rubber part to be tested, while the surface point cloud data and surface pressure distribution data in the dynamic environment reveal the behavior characteristics of the rubber part under real working conditions, including deformation, pressure change and fatigue characteristics. By combining the simulated environment cavity and modern sensing technology, high-precision collection of dynamic data can be achieved under laboratory conditions, providing a scientific basis for the molding quality inspection and life prediction of rubber parts.

[0111] Step S602, preprocessing the dynamic environment test data and performing time stamp synchronization to obtain a time series dynamic feature matrix; Specifically, the dynamic environment test data collected above is preprocessed and time-stamp synchronized to form a unified time-series dynamic feature matrix; the preprocessing steps include noise elimination, outlier filtering and data standardization, and time-stamp synchronization ensures that the data collected by different sensors are consistent.

[0112] Among them, the time series dynamic feature matrix is ​​M t =[x,y,z,p t ,ΔL t ,Δσ t ]; In the above formula, p t is the surface pressure distribution data changing with time t, ΔL t is the geometric offset data changing with time t, Δσ t is the stress distribution change data changing with time t.

[0113] For example, in a time series, the dynamic characteristic matrix of the dynamic pressure distribution and geometric offset of the rubber part changing with time is: Mt={[x1,y1,z1,p t1 ,ΔL t1 ,Δσ t1 ],…,[x n ,y n ,z n ,p tn ,ΔL tn ,Δσ tn ]}.

[0114] Step S603, extracting fatigue life key factors based on the time series dynamic characteristic matrix to obtain a fatigue life key factor data set; Specifically, key factors related to fatigue life are extracted from the time series dynamic characteristic matrix, which directly reflect the dynamic response characteristics of rubber parts. For example, stress amplitude (Δσ amp ) represents the maximum stress variation range, and the stress average value (σ mean) represents the center value of stress distribution, and the geometric offset amplitude (ΔL amp ) represents the extreme difference in dynamic offset.

[0115] Step S604, constructing a fatigue life prediction model based on the fatigue life key factor data set; Among them, according to the fatigue life theory (such as the SN curve model), a fatigue life prediction model is constructed, and the material constant C and fatigue index m are calibrated through experiments. The model formula is: ; In the above formula, T is the fatigue life prediction value, Δσ amp is the stress amplitude, C and m are the empirical constants and fatigue exponents of the material; the values ​​of C and m are calibrated experimentally, and the fatigue life model parameters are optimized to match the dynamic characteristic factor distribution.

[0116] In addition, the fatigue life prediction model can be further verified and adjusted based on the finite element simulation results of the material. By simulating dynamic working conditions, multiple sets of verification data can be generated to ensure the adaptability of the model.

[0117] Step S605, inputting the time series dynamic characteristic matrix into the fatigue life prediction model, and calculating the fatigue life prediction value of the rubber component to be tested point by point; Among them, the fatigue life prediction model is used to calculate the life value T(x, y, z) of each point on the rubber part to be tested, and the fatigue life prediction value of each point is predicted; Step S606, generating fatigue life prediction distribution of each area of ​​the rubber component to be tested according to the fatigue life prediction value based on a cluster analysis algorithm; Among them, the fatigue life distribution is divided into regions based on the clustering algorithm to show the fatigue characteristics of each area of ​​the rubber part to be tested, and at the same time help locate high-risk areas of life.

[0118] Step S607, calculating the comprehensive fatigue life score of the rubber component to be tested based on the fatigue life prediction distribution; Among them, the comprehensive fatigue life score of the rubber parts is calculated according to the fatigue life distribution: ; In the above formula, T i is the average fatigue life of region i, A i is the area of ​​the region.

[0119] Step S608, combining the comprehensive fatigue life score and the comprehensive molding degree score to obtain a comprehensive score of the rubber part to be tested.

[0120] Among them, the formability score is combined with the fatigue life score to generate a comprehensive score: ; In the above formula, S form S is the molding degree score, L is the fatigue life score, and α and β are weighting factors.

[0121] In the above implementation, after the collection and analysis of dynamic environment test data, the construction of fatigue life prediction model, life distribution prediction and comprehensive score calculation, a comprehensive evaluation of the molding quality and life characteristics of the rubber parts is achieved. The overall performance of the rubber parts under static and dynamic conditions is quantified through the final comprehensive score, which provides a scientific basis for the quality optimization, design improvement and reliability evaluation of the rubber parts.

[0122] Reference Figure 7 As an implementation of step S606, based on a cluster analysis algorithm, the step of generating fatigue life prediction distribution of each region of the rubber component to be tested according to the fatigue life prediction value includes: Step S701, normalizing the fatigue life prediction value and the surface point cloud data, and performing spatial alignment to obtain a fatigue life distribution data set; Among them, the fatigue life prediction value and surface point cloud data have different numerical ranges and physical meanings. The data needs to be normalized to eliminate scale differences. At the same time, spatial alignment is used to ensure that the fatigue life value corresponds to the corresponding point cloud coordinates one by one, providing consistent input for subsequent clustering analysis and ensuring that the clustering algorithm can accurately identify the spatial distribution relationship between the point cloud and the life value.

[0123] Step S702, dividing each point in the fatigue life distribution data set into a number of clusters based on a clustering algorithm, and calculating the cluster center position for each cluster; Among them, the fatigue life distribution data set is grouped through a clustering algorithm, and each cluster represents an area with similar life values ​​and point cloud characteristics; the cluster center position is to calculate the centroid of each cluster, which reflects the average characteristics of the area. By dividing the different life areas on the surface of rubber parts, it lays the foundation for fatigue characteristic area analysis and high-risk area positioning.

[0124] In some embodiments, the clustering algorithm may adopt the K-Means algorithm or the DBSCAN algorithm. The K-Means algorithm can assign points to k clusters according to the Euclidean distance by presetting the number of clusters k; the DBSCAN algorithm divides points according to point density, which is suitable for situations where data is unevenly distributed.

[0125] Step S703, determining each region of the rubber component to be tested based on the cluster center position, and calculating the average fatigue life of each region to obtain the fatigue life prediction distribution of each region of the rubber component to be tested; Among them, each cluster corresponds to a fatigue life region of the rubber part. The region boundary is determined by the distribution of cluster points. The region position is calibrated by the cluster center, and the average fatigue life in each region is calculated to quantitatively evaluate the life characteristics of different regions on the surface of the rubber part.

[0126] Step S704: marking the area where the average fatigue life value is higher than the preset life threshold as a high-risk area.

[0127] Among them, by comparing the average fatigue life of the area with the preset life threshold, the areas with life below the threshold are marked as high-risk areas, and the areas on the surface of the rubber parts that may fail are accurately located, providing a basis for design improvement and life extension.

[0128] In the above implementation, based on the fatigue life distribution prediction method of cluster analysis, the life characteristics of rubber parts are divided into multiple regions, each of which represents similar life characteristics. The fatigue life prediction distribution intuitively displays the life distribution on the surface of the rubber parts, helping to quickly locate high-risk life areas. This technical solution combines the annotation of cluster centers and regional boundaries to provide a scientific basis for optimizing the molding quality, improving life, and controlling risks of rubber parts.

[0129] In actual application, the technical solution of this application is suitable for quality control and performance evaluation of complex-shaped rubber parts, especially in industrial applications that require high-precision detection, and can effectively detect surface defects, mechanical problems, and insufficient deformation in dynamic environments. By generating a visual scoring report, it provides a scientific basis for quality improvement, design optimization, and performance improvement of rubber parts, thereby enhancing product reliability and service life, and has a wide range of industrial application value.

[0130] The embodiment of the present application also discloses a system for detecting the degree of molding of a finished product of a rubber part.

[0131] A finished product molding degree detection system for a rubber part, the molding degree detection system comprising: The first receiving module is used to receive the surface point cloud data and surface geometric position information of the rubber part to be tested; A model building module is used to build a three-dimensional surface contour model of the rubber part to be tested based on the three-dimensional contour model of the standard rubber part according to the surface point cloud data and the surface geometric position information; A second receiving module is used to receive surface pressure distribution data of the rubber part to be tested; The pressure anomaly detection module is used to map the surface pressure distribution data to the three-dimensional surface contour model and detect the pressure anomaly distribution area of ​​the rubber part to be tested; A third receiving module is used to receive optical image data collected from the surface of the rubber part to be tested under multi-angle optical scanning; An extraction module, used for extracting light scattering characteristic data according to the optical image data; A comparison module is used to compare the light scattering characteristic data with the pressure abnormal distribution area to obtain the defect area analysis results; An acquisition module is used to acquire the dynamic deformation characteristics of the rubber part to be tested under a dynamic environment simulation test; Model annotation module, used to annotate the 3D surface contour model according to the pressure abnormal distribution area, light scattering characteristic data, defect area analysis results and dynamic deformation characteristics, and construct a comprehensive feature model of the rubber part to be tested; A difference analysis module is used to perform a difference analysis on the comprehensive characteristic model based on the standard characteristic data of the standard rubber part to obtain the characteristic difference result of the rubber part to be tested; The scoring report generation module is used to obtain a molding degree scoring report of the rubber part to be tested based on the characteristic difference results.

[0132] In the above implementation, through the collaborative work of multiple modules, the whole process from data reception to model construction, feature extraction, defect analysis, dynamic deformation detection, comprehensive feature modeling and forming degree scoring can be automated. The system accurately integrates pressure, light scattering characteristics and dynamic deformation data with the three-dimensional surface model, and uses the difference analysis and scoring report module to provide a comprehensive forming degree evaluation, which improves the detection accuracy and efficiency and reduces the error of human intervention.

[0133] A finished product molding degree detection system for rubber parts in an embodiment of the present application can implement any of the above-mentioned finished product molding degree detection methods, and the specific working process of each module in the finished product molding degree detection system can refer to the corresponding process in the above-mentioned method embodiment.

[0134] In the several embodiments provided in this application, it should be understood that the provided methods and systems can be implemented in other ways. For example, the system embodiments described above are only illustrative; for example, the division of a certain module is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed.

[0135] The embodiment of the present application also discloses a computer device.

[0136] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, a method for detecting the finished product molding degree of a rubber part as described above is implemented.

[0137] The embodiment of the present application also discloses a computer-readable storage medium.

[0138] A computer-readable storage medium stores a computer program that can be loaded by a processor and execute any one of the above-mentioned methods for detecting the degree of finished product molding of a rubber part.

[0139] Among them, computer-readable storage media can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus or device; the program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0140] It should be noted that in the above embodiments, the description of each embodiment has different emphases, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0141] The above are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Any feature disclosed in this specification (including the abstract and drawings), unless otherwise stated, can be replaced by other equivalent or alternative features with similar purposes. That is, unless otherwise stated, each feature is only an example of a series of equivalent or similar features.

Claims

1. A method for detecting the degree of finished product molding of a rubber part, characterized in that: The forming degree detection method comprises: Receive surface point cloud data and surface geometric position information of the rubber part to be tested; Based on the three-dimensional contour model of the standard rubber part, and according to the surface point cloud data and the surface geometric position information, construct a three-dimensional surface contour model of the rubber part to be tested; Receiving surface pressure distribution data of the rubber part to be tested; Mapping the surface pressure distribution data to the three-dimensional surface contour model to detect the abnormal pressure distribution area of ​​the rubber part to be tested; Receiving optical image data collected from the surface of the rubber part to be tested under multi-angle optical scanning; extracting light scattering characteristic data according to the optical image data; Comparing the light scattering characteristic data with the pressure abnormal distribution area to obtain defect area analysis results; Acquiring dynamic deformation characteristics of the rubber component to be tested under a dynamic environment simulation test; Annotating the three-dimensional surface contour model according to the abnormal pressure distribution area, light scattering characteristic data, defect area analysis results and dynamic deformation characteristics, and constructing a comprehensive feature model of the rubber part to be tested; Performing difference analysis on the comprehensive characteristic model based on the standard characteristic data of the standard rubber part to obtain a characteristic difference result of the rubber part to be tested; A molding degree scoring report of the rubber part to be tested is obtained based on the characteristic difference results.

2. The method for detecting the degree of finished product molding of a rubber part according to claim 1, characterized in that: The step of mapping the surface pressure distribution data to the three-dimensional surface contour model and detecting the abnormal pressure distribution area of ​​the rubber part to be tested comprises: Mapping the surface pressure distribution data to the surface vertices of the three-dimensional surface contour model to obtain a three-dimensional surface contour model containing pressure value projection information; Generate a color gradient according to the pressure value projection information, and render the color gradient to the three-dimensional surface contour model to generate a surface pressure distribution map; Based on the pressure threshold range in the standard database, performing an abnormality analysis on each pressure point in the surface pressure distribution diagram, and marking the pressure points exceeding the pressure threshold range as abnormal points; Adjacent abnormal points are aggregated based on a clustering algorithm based on spatial density to obtain the abnormal pressure distribution area and corresponding characteristic parameters.

3. The method for detecting the degree of finished product molding of a rubber part according to claim 2, characterized in that: The step of comparing the light scattering characteristic data with the abnormal pressure distribution area to determine the defect area includes: Extracting a light scattering abnormal area based on the light scattering characteristic data; Aligning the spatial coordinates of the light scattering anomaly region and the pressure anomaly distribution region; Matching the central coordinates of the abnormal light scattering area with the central coordinates of the abnormal pressure distribution area in spatial position, and calculating the corresponding spatial distance; Determining whether the spatial distance is less than a preset distance threshold; If the distance is less than a preset distance threshold, it is determined that the light scattering abnormal area and the pressure abnormal distribution area have a spatial overlap relationship and are marked as a matching area; Comparing the characteristic parameters of the light scattering abnormal area with the characteristic parameters of the pressure abnormal distribution area in an overlapping relationship to determine whether there is a matching relationship; If there is a matching relationship, the matching area is determined as a defect area, and the corresponding defect type is determined according to the matching relationship to obtain the defect area analysis result; If there is no matching relationship, the matching area is determined as the area to be observed.

4. The method for detecting the degree of finished product molding of a rubber part according to claim 1, characterized in that: The step of obtaining the dynamic deformation characteristics of the rubber part to be tested under the dynamic environment simulation test includes: Receiving geometric deformation data and stress distribution data of the rubber part to be tested under a dynamic environment simulation test; wherein the dynamic environment simulation test includes performing a dynamic environment test under high temperature, low temperature or corrosive medium according to preset dynamic environment parameters; Performing time stamp synchronization on the geometric deformation data and the stress distribution data; Obtaining initial state data of the rubber part to be tested based on the three-dimensional surface contour model of the rubber part to be tested; Based on the initial state data, differential calculations are performed with the geometric deformation data and the stress distribution data to obtain dynamic deformation characteristics of the rubber component to be tested; wherein the dynamic deformation characteristics include geometric offset and stress distribution change data.

5. A method for detecting the degree of finished product molding of a rubber part according to any one of claims 1 to 4, characterized in that: The step of obtaining a molding degree score report of the rubber part to be tested based on the characteristic difference result comprises: Extract each type of feature difference data according to the feature difference result, and calculate the deviation mean of each type of feature difference data respectively; Based on the preset weight of each feature difference data, weighted calculation is performed according to the deviation mean of each feature difference data to obtain a comprehensive forming degree score; Determine defect distribution information and defect type according to the characteristic difference data and defect area analysis results; The comprehensive molding degree score, defect distribution information and defect type are integrated to obtain a molding degree score report of the rubber part to be tested.

6. A method for detecting the degree of finished product molding of a rubber part according to claim 5, characterized in that: After the step of obtaining the comprehensive forming degree score, it also includes: Receiving dynamic environment test data of the rubber part to be tested under a dynamic environment simulation test; wherein the dynamic environment test data includes surface point cloud data, surface pressure distribution data, geometric offset data and stress distribution change data that change with time; Preprocessing the dynamic environment test data and performing time stamp synchronization to obtain a time series dynamic feature matrix; Extracting fatigue life key factors based on the time series dynamic characteristic matrix to obtain a fatigue life key factor data set; Based on the fatigue life key factor data set, construct a fatigue life prediction model; Inputting the time series dynamic characteristic matrix into the fatigue life prediction model, and calculating the fatigue life prediction value of the rubber part to be tested point by point; Based on a cluster analysis algorithm, generating a fatigue life prediction distribution of each area of ​​the rubber part to be tested according to the fatigue life prediction value; Calculating a comprehensive fatigue life score of the rubber component to be tested based on the fatigue life prediction distribution; The comprehensive fatigue life score and the comprehensive molding degree score are combined to obtain a comprehensive score of the rubber part to be tested.

7. A method for detecting the degree of finished product molding of a rubber part according to claim 6, characterized in that: Based on the cluster analysis algorithm, the step of generating fatigue life prediction distribution of each area of ​​the rubber component to be tested according to the fatigue life prediction value includes: Normalizing the fatigue life prediction value and the surface point cloud data, and performing spatial alignment to obtain a fatigue life distribution data set; Based on a clustering algorithm, each point in the fatigue life distribution data set is divided into a plurality of clusters, and a cluster center position is calculated for each cluster; Determine each region of the rubber part to be tested based on the cluster center position, calculate the average fatigue life of each region, and obtain the fatigue life prediction distribution of each region of the rubber part to be tested; The area where the average fatigue life value is higher than the preset life threshold is marked as a high-risk area.

8. A finished product molding degree detection system for rubber parts, characterized in that: The forming degree detection system comprises: The first receiving module is used to receive the surface point cloud data and surface geometric position information of the rubber part to be tested; A model building module, used to build a three-dimensional surface contour model of the rubber part to be tested based on the three-dimensional contour model of the standard rubber part and according to the surface point cloud data and surface geometric position information; A second receiving module is used to receive the surface pressure distribution data of the rubber part to be tested; A pressure anomaly detection module, used for mapping the surface pressure distribution data to the three-dimensional surface contour model, and detecting an abnormal pressure distribution area of ​​the rubber part to be tested; A third receiving module is used to receive optical image data collected from the surface of the rubber part to be tested under multi-angle optical scanning; An extraction module, used for extracting light scattering characteristic data according to the optical image data; A comparison module, used to compare the light scattering characteristic data with the pressure abnormal distribution area to obtain a defect area analysis result; An acquisition module, used for acquiring dynamic deformation characteristics of the rubber component to be tested under a dynamic environment simulation test; A model annotation module, used to annotate the three-dimensional surface contour model according to the abnormal pressure distribution area, light scattering characteristic data, defect area analysis results and dynamic deformation characteristics, and construct a comprehensive feature model of the rubber part to be tested; A difference analysis module, used for performing a difference analysis on the comprehensive characteristic model based on the standard characteristic data of the standard rubber part to obtain a characteristic difference result of the rubber part to be tested; A scoring report generating module is used to obtain a molding degree scoring report of the rubber part to be tested based on the characteristic difference result.

9. A computer device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the program.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 7.

Images