Multi-parameter-based detection system and method for automotive rubber strips

Abstract

This invention relates to the field of automotive rubber strip defect detection technology, and more particularly to a multi-parameter-based automotive rubber strip detection system and method. The invention includes an identification module, a data acquisition module, a pre-analysis module, a defect classification module, and a location detection module. The identification module coats the surface of the rubber strip with fluorescent material to form several sets of fluorescent markers. A stretching unit stretches the rubber strip axially, and the pre-analysis module acquires the local extension characteristics of each set of fluorescent markers to determine suspected defect segments. The defect classification module determines the manifestation category of the suspected defect segments based on changes in fluorescence intensity. The location detection module locates the defect on the rubber strip. Thus, it achieves accurate identification of defect types through multi-parameter collaborative analysis and dynamically adjusts the detection strategy according to the defect type, meeting the high-quality inspection requirements of automotive rubber strips.

Description

Technical Field

[0001] This invention relates to the field of rubber strip defect detection technology, and in particular to a multi-parameter-based detection system and method for automotive rubber strips. Background Technology

[0002] The quality of automotive rubber strips directly affects many important aspects of a vehicle's performance, such as sealing, sound insulation, durability, and overall safety. As the automotive industry accelerates towards electrification and intelligentization, consumers are placing higher demands on the driving experience, making quality control of automotive rubber strips particularly crucial.

[0003] From the perspective of automobile manufacturing, traditional methods for inspecting automotive rubber strips have many limitations. The commonly used manual visual inspection method is not only labor-intensive and time-consuming, but the results are also easily influenced by the subjective factors of the inspectors, making it difficult to guarantee accuracy and consistency. Existing single-parameter-based inspection systems often only test one performance indicator of the rubber strip, failing to provide a comprehensive and integrated assessment of its overall quality. Given the shortcomings of traditional inspection methods and the severity of rubber strip quality issues, developing a comprehensive, accurate, and efficient inspection system and method for automotive rubber strips, capable of precisely locating defects, has become a crucial issue urgently needing to be addressed by the automotive manufacturing industry.

[0004] For example, Chinese Patent Publication No. CN119715542A discloses a method and apparatus for detecting defects in the appearance processing of adhesive strips, relating to the field of visual inspection technology. The detection method includes: setting several photographic points on a light-illuminated detection area to acquire several detection images of the adhesive strip at these points; comparing the detection images with standard images to obtain the feature contours of the detection images; inputting the feature contour images into a defect detection model to extract the photographing parameters and image parameters of the feature contour images; determining several sets of defect comparison data based on the photographing parameters of the feature contour images; analyzing the similarity between the feature contour images and the defect comparison data based on the image parameters; determining the defect comparison data with the highest matching degree to the feature contour images based on the similarity; and outputting the defect type of the adhesive strip. By illuminating the adhesive strip and visually processing its defects, and confirming the defect type of the adhesive strip based on the detection model, the reliability of adhesive strip defect detection can be effectively improved.

[0005] The following problems still exist in the existing technology:

[0006] Existing technologies do not fully incorporate the different causes of rubber strip defects into the design of targeted detection logic. It is difficult to accurately identify defect types through multi-parameter collaborative analysis, and there is also a lack of a complete detection closed loop for precise defect location. The detection strategy cannot be dynamically adjusted according to the defect type, resulting in low accuracy in rubber strip defect identification and insufficient positioning precision, which makes it difficult to meet the high-quality inspection requirements of automotive rubber strips. Summary of the Invention

[0007] To address this issue, the present invention provides a multi-parameter-based automotive rubber strip inspection system and method to overcome the problem that existing technologies cannot dynamically adjust the inspection strategy according to the defect type, resulting in low accuracy in rubber strip defect identification and insufficient positioning precision, making it difficult to meet the high-quality inspection requirements of automotive rubber strips.

[0008] To achieve the above objectives, the present invention provides a multi-parameter-based automotive rubber strip detection system, comprising:

[0009] The marking module is used to coat the surface of the adhesive strip with fluorescent material in a direction perpendicular to the axial direction to form several sets of fluorescent markings, each set of fluorescent markings including several ring fluorescent markings;

[0010] The acquisition module, which is connected to the labeling module, includes a stretching unit for stretching the adhesive strip along the axial direction and an image acquisition unit for acquiring surface images at the positions of each group of fluorescent labels.

[0011] The pre-analysis module, which is connected to the acquisition module, is used to obtain the local stretching characterization of each group of fluorescent markers on the stretched adhesive strip, and to determine the suspected defect interval based on the local stretching characterization.

[0012] The defect classification module, which is connected to the pre-analysis module, is used to acquire surface images of suspected defect segments after stretching under a preset light source to determine fluorescence intensity values ​​at several points, and to determine the performance category of the suspected defect segments based on the changes in fluorescence intensity values.

[0013] The positioning and detection module is connected to the defect classification module and the acquisition module. It is used to control the stretching unit to stretch each suspected defect segment and determine the defect quantitative characterization value for different manifestation categories in order to locate the location of the defect in the rubber strip.

[0014] The defect quantification characterization value is the interval distance between adjacent annular fluorescent markers, or the ring width of the annular fluorescent marker.

[0015] Furthermore, the pre-analysis module is used to obtain the local elongation characterization of each group of fluorescent markers on the stretched adhesive strip, wherein,

[0016] The pre-analysis module is used to obtain the average ring width of each annular fluorescent marker in each group of fluorescent markers before stretching and the average ring width after stretching, so as to calculate the change in the average ring width of each annular fluorescent marker, and determine the standard deviation of the change in the average ring width of the annular fluorescent markers in each group of fluorescent markers as the local stretching characterization quantity.

[0017] Furthermore, the pre-analysis module is used to compare the local extension characterization quantity with the local extension reference characterization quantity, and determine the suspected defect interval segment based on the comparison result, wherein,

[0018] If the local extension characterization quantity is greater than the local extension reference characterization quantity, then the pre-analysis module determines the fluorescent marker position of the local extension characterization quantity as a suspected defect interval segment;

[0019] The local extension reference value is calculated and determined based on the total extension of the stretched rubber strip.

[0020] Furthermore, the suspected defect interval is a strip of adhesive strip of a preset length determined along the axial direction of the adhesive strip with the location of the fluorescent mark as the center reference, and several sets of points are arranged along the axial direction of the adhesive strip within the suspected defect interval.

[0021] Furthermore, the defect classification module is used to determine the changes in fluorescence intensity values, wherein,

[0022] The defect classification module is used to calculate the fluorescence intensity difference between any two points with the same axial position among the points arranged along the axial direction of the adhesive strip in each group, and to determine the standard deviation of the fluorescence intensity difference as the fluorescence intensity change.

[0023] Furthermore, the defect classification module is used to compare the change in fluorescence intensity with a preset reference value for the change in fluorescence intensity to determine the performance category of the suspected defect interval.

[0024] If the change in fluorescence intensity is less than or equal to the reference amount of fluorescence intensity change, the defect classification module determines the performance category of the suspected defect interval as the first performance category.

[0025] If the change in fluorescence intensity is greater than the reference value for the change in fluorescence intensity, the defect classification module determines the performance category of the suspected defect interval as the second performance category.

[0026] Furthermore, the location detection module is used to determine the quantitative characterization value of the defect for different performance categories, wherein,

[0027] The positioning and detection module is used to determine the defect quantification value for the suspected defect interval of the first manifestation category as the interval distance between adjacent ring fluorescent markers.

[0028] The positioning and detection module is used to determine the ring width of the annular fluorescent marker as the defect quantification characterization value for the suspected defect interval of the second manifestation category.

[0029] Furthermore, the positioning detection module is used to locate the position of the defect in the adhesive strip based on the interval between adjacent annular fluorescent markers, wherein,

[0030] The positioning and detection module is used to obtain the interval distance between the ring fluorescent marks after stretching each suspected defect interval segment, and to locate the suspected defect interval segment where the standard deviation of the interval distance is greater than the preset standard deviation threshold of the interval distance as the location where the adhesive strip has a defect.

[0031] Furthermore, the positioning detection module is used to locate the position of the defect in the adhesive strip based on the ring width of the annular fluorescent mark, wherein,

[0032] The positioning and detection module is used to obtain the ring width of the annular fluorescent mark after stretching each suspected defect segment, and to locate the annular fluorescent mark where the ring width is not within the preset range as the location where the adhesive strip has a defect.

[0033] Furthermore, the present invention also provides a multi-parameter-based method for detecting automotive rubber strips, comprising:

[0034] A fluorescent material is coated onto the surface of the adhesive strip in a direction perpendicular to the axial direction to form several sets of fluorescent markings;

[0035] The adhesive strip is stretched along the axial direction, and surface images of each group of fluorescent markings on the stretched adhesive strip are obtained.

[0036] Obtain the local stretching characterization of each group of fluorescent markers on the stretched adhesive strip, and determine the suspected defect interval based on the local stretching characterization;

[0037] Under a preset light source, a surface image of the suspected defective section after stretching is obtained to determine the fluorescence intensity value at several points, and the performance category of the suspected defective section is determined according to the change of fluorescence intensity value.

[0038] Each suspected defect segment is stretched separately, and a quantitative characterization value for the defect is determined for different manifestation categories in order to locate the location of the defect in the adhesive strip.

[0039] Compared with existing technologies, the advantages of this invention lie in its inclusion of a labeling module, an acquisition module, a pre-analysis module, a defect classification module, and a location detection module. The labeling module coats the surface of the adhesive strip with fluorescent material in a direction perpendicular to the axial direction to form several sets of fluorescent labels. A stretching unit stretches the adhesive strip axially. An image acquisition unit acquires surface images of each set of fluorescent labels. The pre-analysis module obtains the local extension characteristics of each set of fluorescent labels to determine suspected defect intervals. The defect classification module determines the manifestation category of the suspected defect intervals based on changes in fluorescence intensity. The location detection module locates the defect on the adhesive strip. Furthermore, this invention achieves accurate identification of defect types through multi-parameter collaborative analysis and dynamically adjusts the detection strategy based on the defect type, meeting the high-quality inspection requirements for automotive adhesive strips.

[0040] Furthermore, this invention uses the standard deviation of the average ring width variation of the annular fluorescent markers within each group as a measure of local stretching. From the perspective of the detection principle, as an elastomer material, under standard tensile conditions, if there are no quality defects, the axial stretching of the adhesive strip should be uniform. Reflected in the annular fluorescent markers, the ring width variation of all annular fluorescent markers within each group should tend to be consistent, and the corresponding standard deviation should be within a small range. However, when there are differences in the stretching capacity of the adhesive strip, the ring width variation of the annular fluorescent markers in that area will exhibit discrete fluctuations, increasing the standard deviation. By defining the standard deviation of the average ring width variation as a measure of local stretching, the abstract characteristic of whether the local stretching of the adhesive strip is uniform is transformed into a comparable, concrete numerical value.

[0041] Furthermore, this invention uses the standard deviation of the fluorescence intensity difference between adjacent points along the axial direction as the fluorescence intensity variation. This is significant because it solves the problem of objectively distinguishing different types of defects in traditional testing. The standard deviation of the fluorescence intensity difference reflects the fluorescence intensity at radial points within the same axial direction. For rubber strips with stable extrusion processes and uniform composition, the fluorescence intensity at radial points within the same axial direction should be consistent, resulting in a low standard deviation. However, when radial component stratification occurs due to poor internal mixing, different radial points within the same axial direction will exhibit discrete differences in fluorescence intensity, resulting in a larger standard deviation. Quantifying this radial difference through the standard deviation provides a basis for accurately distinguishing between extrusion defects and component defects, improving the comprehensiveness and accuracy of defect classification.

[0042] Furthermore, this invention compares the change in fluorescence intensity with a preset reference value to classify the manifestation categories. The significance lies in establishing a clear quantitative standard for defect type determination. The preset reference value establishes a critical threshold for the uniformity of fluorescence intensity changes. When the change in fluorescence intensity, reflecting the dispersion of radial fluorescence intensity differences, exceeds the reference value, it may indicate poor raw material mixing leading to local heterogeneous regions. When the change in fluorescence intensity does not exceed the reference value, it may indicate uniformity defects caused by instability in the extrusion process. By transforming the essential differences between the two types of defects into a directly comparable numerical relationship, the objectivity and consistency of the classification results are ensured.

[0043] Furthermore, this invention uses the standard deviation of the interval between adjacent annular fluorescent markers as the quantitative characterization value for the first manifestation category and uses it to locate defects, thus constructing a precise quantitative positioning mechanism adapted to the characteristics of this type of defect. The characteristic of the first manifestation category in this invention is that the rubber strip has regular and gradual quality fluctuations along the axial direction. This is reflected in the fluorescent markers under tension as discrete changes in the interval between adjacent annular markers. By calculating the standard deviation of the interval distance, this degree of discreteness can be sensitively captured. That is, the larger the standard deviation, the worse the uniformity of the interval. This method of quantifying the uniformity of axial intervals fits the distribution characteristics of this type of defect, realizing the accurate identification of defect types through multi-parameter collaborative analysis, and dynamically adjusting the detection strategy according to the defect type, thus meeting the high-quality inspection requirements of automotive rubber strips.

[0044] Furthermore, this invention uses the ring width of the annular fluorescent marker as a quantitative characterization value for defects in the second performance category and uses it to locate defects. From the perspective of the matching between defect characteristics and detection indicators, the characteristic of the second performance category of this invention is that there may be problems such as poor raw material mixing and component segregation in local areas of the adhesive strip. These defects can cause abrupt changes in the local physical properties of the adhesive strip, which is reflected in the annular fluorescent marker after stretching, manifested as the ring width of a specific marker deviating from the normal range. As is well known to those skilled in the art, the ring width in areas with uniform composition should be stable within the standard range, while the ring width in areas with abnormal composition will show significant deviations due to abrupt changes in material properties. Choosing the ring width as a quantitative indicator directly captures the intuitive manifestation of this type of defect under stretching, forming a precise correspondence with the local characteristic differences caused by component inhomogeneity. This achieves accurate identification of defect types through multi-parameter collaborative analysis, dynamically adjusting the detection strategy according to the defect type, and meeting the high-quality testing requirements of automotive adhesive strips. Attached Figure Description

[0045] Figure 1 This is a system block diagram of a multi-parameter automotive rubber strip detection system according to an embodiment of the present invention;

[0046] Figure 2 A flowchart illustrating the logic for determining suspected defect intervals in an embodiment of the present invention;

[0047] Figure 3 This is a schematic diagram illustrating the selection of points for calculating the fluorescence intensity difference in an embodiment of the present invention;

[0048] Figure 4 A flowchart illustrating the logic for determining the quantification value of defects in an embodiment of the present invention;

[0049] Figure 5 This is a flowchart illustrating the steps of a multi-parameter-based automotive rubber strip testing method according to an embodiment of the present invention.

[0050] In the diagram: 1-colloid, 2-ring fluorescent marker, 3-first group of spots, 4-second group of spots, 5-first spot, 6-second spot. Detailed Implementation

[0051] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0052] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0053] It should be noted that in the description of this invention, the terms "upper," "lower," "inner," "outer," etc., which indicate the direction or positional relationship, are based on the direction or positional relationship shown in the drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0054] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation" and "connection" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0055] Please see Figure 1 The diagram shown is a system block diagram of a multi-parameter automotive rubber strip detection system according to an embodiment of the present invention. The multi-parameter automotive rubber strip detection system of the present invention includes:

[0056] The marking module is used to coat the surface of the adhesive strip with fluorescent material in a direction perpendicular to the axial direction to form several sets of fluorescent markings, each set of fluorescent markings including several ring fluorescent markings 2;

[0057] Specifically, the fluorescent material in this invention can be an erasable fluorescent material, which can be a water-soluble fluorescent agent. After the detection process is completed, it can be oxidized and decomposed by wiping with a solution containing an oxidant, without damaging the adhesive strip substrate.

[0058] Specifically, the number of fluorescent markers set in the implementation of the present invention can be controlled by those skilled in the art based on the interval between two adjacent fluorescent markers. The smaller the interval, the more fluorescent markers are set. Here, a value for the interval between two adjacent fluorescent markers is provided. The interval between two adjacent fluorescent markers can be 1m. Preferably, each fluorescent marker includes 5 annular fluorescent markers, and the initial ring width of each annular fluorescent marker is 2cm.

[0059] Specifically, the marking module in this invention can be an inkjet device. As is well known to those skilled in the art, inkjet devices are widely used to coat pre-edited graphics and numbers onto surfaces such as packaging. This is prior art and will not be elaborated here.

[0060] The acquisition module, which is connected to the labeling module, includes a stretching unit for stretching the adhesive strip along the axial direction and an image acquisition unit for acquiring surface images at the positions of each group of fluorescent labels.

[0061] Specifically, the stretching unit in this invention can be a device that stretches the rubber strip through a clamping component. Devices that stretch rubber strips are widely used in the production process of extrusion molding. In this invention, the stretching of the rubber strip can be controlled by controlling the displacement of the clamping component, which will not be elaborated here.

[0062] Specifically, the image acquisition unit of the present invention includes a high-definition camera and a light intensity acquisition device for acquiring fluorescence intensity values.

[0063] The pre-analysis module, which is connected to the acquisition module, is used to obtain the local stretching characterization of each group of fluorescent markers on the stretched adhesive strip, and to determine the suspected defect interval based on the local stretching characterization.

[0064] Specifically, the pre-analysis module in this invention can be a data processor that uses pre-stored relevant algorithms to call relevant data to calculate local extension characterization quantities and makes result judgments through data analysis and comparison.

[0065] The defect classification module, which is connected to the pre-analysis module, is used to acquire surface images of suspected defect segments after stretching under a preset light source to determine fluorescence intensity values ​​at several points, and to determine the performance category of the suspected defect segments based on the changes in fluorescence intensity values.

[0066] Specifically, the preset light source in this invention can be an ultraviolet LED lamp with a wavelength of 365nm.

[0067] Specifically, the defect classification module in this invention includes an image processor and a register. The image processor analyzes and processes the surface image, and the results of different performance categories are determined based on the analysis results of the fluorescence intensity values ​​and sent to the register for storage.

[0068] The positioning and detection module is connected to the defect classification module and the acquisition module. It is used to control the stretching unit to stretch each suspected defect segment and determine the defect quantitative characterization value for different manifestation categories in order to locate the location of the defect in the rubber strip.

[0069] The defect quantification characterization value is the interval distance between adjacent annular fluorescent markers, or the ring width of the annular fluorescent marker.

[0070] Specifically, the elongation of each suspected defect segment after being stretched by the stretching unit controlled by the positioning detection module is the same. Preferably, in this invention, for a suspected defect segment with a length of 0.5m, the elongation of each suspected defect segment after being stretched by the stretching unit can be 5cm.

[0071] Specifically, the present invention does not limit the specific structure of the positioning detection module, which can be constructed using logic components, such as field-programmable logic components, microprocessors, processors used in computers, etc.

[0072] Specifically, the pre-analysis module is used to obtain the local stretch characterization of each group of fluorescent markers on the stretched adhesive strip, wherein,

[0073] The pre-analysis module is used to obtain the average ring width of each annular fluorescent marker in each group of fluorescent markers before stretching and the average ring width after stretching, so as to calculate the change in the average ring width of each annular fluorescent marker, and determine the standard deviation of the change in the average ring width of the annular fluorescent markers in each group of fluorescent markers as the local stretching characterization quantity.

[0074] Understandably, this invention uses the standard deviation of the average ring width variation of the annular fluorescent markers within each group as a measure of local stretching. From the perspective of the detection principle, as an elastomer material, under standard tensile conditions, if there are no quality defects, the axial stretching of the adhesive strip should be uniform. Reflected in the annular fluorescent markers, the ring width variation of all annular fluorescent markers within each group should tend to be consistent, and the corresponding standard deviation will be within a small range. However, when there are differences in the stretching capacity of the adhesive strip, the ring width variation of the annular fluorescent markers in that area will exhibit discrete fluctuations, increasing the standard deviation. By defining the standard deviation of the average ring width variation as a measure of local stretching, the abstract characteristic of whether the local stretching of the adhesive strip is uniform is transformed into a comparable, concrete numerical value.

[0075] Specifically, please refer to Figure 2 As shown, this is a flowchart illustrating the logic for determining a suspected defect interval in an embodiment of the present invention. The pre-analysis module compares the local extension characterization quantity with the local extension reference characterization quantity, and determines the suspected defect interval based on the comparison result.

[0076] If the local extension characterization quantity is greater than the local extension reference characterization quantity, then the pre-analysis module determines the fluorescent marker position of the local extension characterization quantity as a suspected defect interval segment;

[0077] If the local extension characterization quantity is less than or equal to the local extension reference characterization quantity, then the pre-analysis module determines that the fluorescent marker position of the local extension characterization quantity is not a suspected defect interval segment;

[0078] The local extension reference value is calculated and determined based on the total extension of the stretched rubber strip.

[0079] In this invention, the value of the local extension reference coefficient is (elongation / initial length of the adhesive strip before stretching) × initial ring width of the annular fluorescent mark × local extension reference coefficient. The value range of the local extension reference coefficient is [0.12, 0.18]. Preferably, the value of the local extension reference coefficient is 0.15. The initial length of the adhesive strip before stretching, the elongation of the adhesive strip after stretching, and the initial ring width of the annular fluorescent mark are all directly measurable data. The ring width data of the annular fluorescent mark can be extracted from the surface image using edge detection algorithms, threshold segmentation algorithms, etc., which are widely used in image recognition applications. This is a common technique used by those skilled in the art and will not be elaborated here.

[0080] Understandably, the significance of comparing the local elongation characterization quantity with the local elongation reference characterization quantity determined based on the elongation of the adhesive strip in this invention to determine the suspected defect interval is that when the characterization quantity reflecting the uniformity of local elongation exceeds the reference characterization quantity under the corresponding tensile conditions, it indicates that the elongation characteristics of that area have deviated from the stable state that a qualified adhesive strip should have, thereby accurately identifying the suspicious areas that need further inspection. Furthermore, this avoids over-inspection of normal fluctuation areas while ensuring that potential defect areas are not overlooked, providing accurate inspection targets for subsequent defect classification and precise location, and improving the efficiency and reliability of the entire inspection system.

[0081] Specifically, the extensibility of the rubber strip is directly related to its elongation after stretching. Under different elongations, the variation in the ring width of the annular fluorescent marker in the normal area of ​​the rubber strip exhibits inherent differences: the greater the elongation, the slightly larger the overall fluctuation range of the ring width variation in the normal area may be. If a fixed reference value is used, it is easy to misjudge a normal area as a defect at low elongations or miss minor defects at high elongations. However, dynamically determining the local elongation reference value through the rubber strip's elongation allows the reference standard to match the actual stretching state of the rubber strip.

[0082] Specifically, the suspected defect section is a pre-defined section of the adhesive strip along the axial direction of the adhesive strip, with the location of the fluorescent mark as the center reference. Several sets of points are arranged along the axial direction of the adhesive strip within the suspected defect section.

[0083] Specifically, in this invention, the preset length is less than the interval between two adjacent fluorescent markers. When the interval between two adjacent fluorescent markers is 1m, the preset length of the suspected defect interval can be 0.5m to avoid mutual interference between the analysis and identification of multiple fluorescent markers.

[0084] Specifically, the defect classification module is used to determine the changes in fluorescence intensity values ​​at adjacent locations, wherein,

[0085] The defect classification module is used to calculate the fluorescence intensity difference between any two points with the same axial position among the points arranged along the axial direction of the adhesive strip in each group, and to determine the standard deviation of the fluorescence intensity difference as the fluorescence intensity change.

[0086] It is understandable that this invention uses the standard deviation of the fluorescence intensity difference between adjacent points along the axial direction as the fluorescence intensity variation. The significance lies in solving the problem of objectively distinguishing different types of defects in traditional detection. The standard deviation of the fluorescence intensity difference can reflect the fluorescence intensity of radial points at the same axial position. For rubber strips with stable extrusion process and uniform composition, the fluorescence intensity of radial points at the same axial position should be consistent, and the standard deviation of the difference will be at a low level. However, when radial component stratification is formed due to poor internal mixing, different radial points at the same axial position will show discrete differences in fluorescence intensity, which is reflected in a large standard deviation. Quantifying this radial difference by standard deviation provides a basis for accurately distinguishing extrusion defects from component defects, and improves the comprehensiveness and accuracy of defect classification.

[0087] Please see Figure 3 As shown, this is a schematic diagram of the point selection for calculating the fluorescence intensity difference in an embodiment of the present invention. Two sets of points are arranged along the axial direction of the adhesive strip within the annular fluorescent mark 2 on the colloid 1, namely the first set of points 3 and the second set of points 4. The first point 5 in the first set of points 3 and the second point 6 in the second set of points 4 have the same axial position, so the first point 5 and the second point 6 can be selected to collect and calculate the fluorescence intensity difference.

[0088] Specifically, please refer to Figure 4 As shown, this is a flowchart illustrating the logic for determining the quantitative characterization value of defects according to an embodiment of the present invention. The defect classification module is used to compare the change in fluorescence intensity with a preset reference value for the change in fluorescence intensity to determine the performance category of the suspected defect interval.

[0089] If the change in fluorescence intensity is less than or equal to the reference amount of fluorescence intensity change, the defect classification module determines the performance category of the suspected defect interval as the first performance category.

[0090] If the change in fluorescence intensity is greater than the reference value for the change in fluorescence intensity, the defect classification module determines the performance category of the suspected defect interval as the second performance category.

[0091] In this invention, the preset reference value for fluorescence intensity variation can be obtained from experimental data. Analysis of the experimental data leads to the following conclusions: the standard deviation of fluorescence intensity difference for a qualified adhesive strip is typically stable within 5% of the baseline intensity; when there is slight uneven extrusion, the standard deviation of fluorescence intensity difference is typically stable within 10% of the baseline intensity due to overall deviation; however, uneven internal composition leads to sudden changes in local fluorescence intensity, and the standard deviation of fluorescence intensity difference often exceeds 10%. Based on the experimental data, the reference value for fluorescence intensity variation can be set to 10% of the baseline fluorescence intensity, where the baseline fluorescence intensity is the average fluorescence intensity of several points on the annular fluorescent markings on the adhesive strip before stretching.

[0092] Understandably, this invention compares the change in fluorescence intensity with a preset reference value to classify performance categories. The significance lies in establishing a clear quantitative standard for defect type determination. The preset reference value establishes a critical threshold for the uniformity of fluorescence intensity changes. When the change in fluorescence intensity, reflecting the dispersion of radial fluorescence intensity differences, exceeds the reference value, it may indicate poor raw material mixing leading to localized heterogeneous regions. When the change in fluorescence intensity does not exceed the reference value, it may indicate uniformity defects caused by instability in the extrusion process. By transforming the essential differences between the two types of defects into a directly comparable numerical relationship, the objectivity and consistency of the classification results are ensured.

[0093] Specifically, the location detection module is used to determine the quantitative characterization value of the defect for different performance categories, wherein,

[0094] The positioning and detection module is used to determine the defect quantification value for the suspected defect interval of the first manifestation category as the interval distance between adjacent ring fluorescent markers.

[0095] The positioning and detection module is used to determine the ring width of the annular fluorescent marker as the defect quantification characterization value for the suspected defect interval of the second manifestation category.

[0096] Specifically, the positioning detection module is used to locate the defective position of the adhesive strip based on the interval between adjacent annular fluorescent markers, wherein,

[0097] The positioning and detection module is used to obtain the interval distance between the ring fluorescent marks after stretching each suspected defect interval segment, and to locate the suspected defect interval segment where the standard deviation of the interval distance is greater than the preset standard deviation threshold of the interval distance as the location where the adhesive strip has a defect.

[0098] In this invention, the preset standard deviation threshold for the interval distance can be the product of the interval distance between adjacent annular fluorescent markers in the suspected defect interval segment before stretching and the threshold value factor. In order to avoid the omission of defect detection caused by the standard deviation threshold for the interval distance being too large and the false detection of defects caused by the standard deviation threshold for the interval distance being too small, the threshold value factor can be 0.15.

[0099] It is understood that this invention uses the standard deviation of the interval between adjacent annular fluorescent markers as the quantitative characterization value for defects in the first manifestation category, and uses this value to locate defects. It constructs a precise quantitative positioning mechanism adapted to the characteristics of this type of defect. The characteristic of the first manifestation category in this invention is that the rubber strip has regular and gradual quality fluctuations along the axial direction. This is reflected in the fluorescent markers under tension as discrete changes in the interval between adjacent annular markers. By calculating the standard deviation of the interval distance, this degree of discreteness can be sensitively captured. That is, the larger the standard deviation, the worse the uniformity of the interval. This method of quantifying the uniformity of axial intervals fits the distribution characteristics of this type of defect, and realizes the accurate identification of defect types through multi-parameter collaborative analysis. The detection strategy can be dynamically adjusted according to the defect type to meet the high-quality inspection requirements of automotive rubber strips.

[0100] Specifically, the positioning detection module is used to locate the position of the defect in the adhesive strip based on the ring width of the annular fluorescent mark, wherein,

[0101] The positioning and detection module is used to obtain the ring width of the annular fluorescent mark after stretching each suspected defect segment, and to locate the annular fluorescent mark where the ring width is not within the preset range as the location where the adhesive strip has a defect.

[0102] In this invention, the upper limit of the preset ring width range can be (elongation of the suspected defective segment after stretching / initial length of the suspected defective segment before stretching) × initial ring width of the annular fluorescent marker × 0.93, and the lower limit of the preset ring width range can be (elongation of the suspected defective segment after stretching / initial length of the suspected defective segment before stretching) × initial ring width of the annular fluorescent marker × 1.08.

[0103] It is understood that this invention uses the ring width of the annular fluorescent marker as a quantitative characterization value for defects in the second performance category and uses this value to locate defects. From the perspective of the matching between defect characteristics and detection indicators, the characteristic of the second performance category of this invention is that there may be problems such as poor raw material mixing and component segregation in local areas of the adhesive strip. These defects can cause abrupt changes in the local physical properties of the adhesive strip, which is reflected in the annular fluorescent marker after stretching, manifested as the ring width of a specific marker deviating from the normal range. As is well known to those skilled in the art, the ring width in areas with uniform composition should be stable within the standard range, while the ring width in areas with abnormal composition will show significant deviations due to abrupt changes in material properties. Choosing the ring width as a quantitative indicator directly captures the intuitive manifestation of this type of defect under stretching, forming a precise correspondence with the local characteristic differences caused by component inhomogeneity. This enables accurate identification of defect types through multi-parameter collaborative analysis, and dynamic adjustment of the detection strategy based on the defect type, meeting the high-quality testing requirements of automotive adhesive strips.

[0104] Specifically, please refer to Figure 5The diagram illustrates the steps of a multi-parameter-based automotive rubber strip detection method according to an embodiment of the present invention. The present invention also provides a multi-parameter-based automotive rubber strip detection method, comprising:

[0105] Step S1: Coat the surface of the adhesive strip with fluorescent material in a direction perpendicular to the axial direction to form several sets of fluorescent markings;

[0106] Step S2: Stretch the adhesive strip along the axial direction and obtain surface images of each group of fluorescent markings on the stretched adhesive strip.

[0107] Step S3: Obtain the local stretching characterization of each group of fluorescent markers on the stretched adhesive strip, and determine the suspected defect interval based on the local stretching characterization.

[0108] Step S4: Under a preset light source, acquire a surface image of the suspected defective section after stretching to determine the fluorescence intensity value at several points, and determine the performance category of the suspected defective section based on the change in fluorescence intensity value.

[0109] Step S5: Stretch each suspected defect segment separately and determine the quantitative characterization value of the defect for different manifestation categories in order to locate the location of the defect in the adhesive strip.

[0110] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0111] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A multi-parameter based automotive rubber strip detection system, characterized by, include: The marking module is used to coat the surface of the adhesive strip with fluorescent material in a direction perpendicular to the axial direction to form several sets of fluorescent markings, each set of fluorescent markings including several ring fluorescent markings; The acquisition module, which is connected to the labeling module, includes a stretching unit for stretching the adhesive strip along the axial direction and an image acquisition unit for acquiring surface images at the positions of each group of fluorescent labels. The pre-analysis module, which is connected to the acquisition module, is used to obtain the local stretching characterization of each group of fluorescent markers on the stretched adhesive strip, and to determine the suspected defect interval based on the local stretching characterization. The defect classification module, which is connected to the pre-analysis module, is used to acquire surface images of suspected defect segments after stretching under a preset light source to determine fluorescence intensity values ​​at several points, and to determine the performance category of the suspected defect segments based on the changes in fluorescence intensity values. The positioning and detection module is connected to the defect classification module and the acquisition module. It is used to control the stretching unit to stretch each suspected defect segment and determine the defect quantitative characterization value for different manifestation categories in order to locate the location of the defect in the rubber strip. The defect quantification characterization value is the interval distance between adjacent annular fluorescent markers, or the ring width of the annular fluorescent marker.

2. The multi-parameter based automotive rubber strip detection system as claimed in claim 1, wherein, The pre-analysis module is used to obtain the local stretch characterization of each group of fluorescent markers on the stretched adhesive strip, wherein, The pre-analysis module is used to obtain the average ring width of each annular fluorescent marker in each group of fluorescent markers before stretching and the average ring width after stretching, so as to calculate the change in the average ring width of each annular fluorescent marker, and determine the standard deviation of the change in the average ring width of the annular fluorescent markers in each group of fluorescent markers as the local stretching characterization quantity.

3. The multi-parameter based automotive rubber strip detection system as claimed in claim 2, wherein, The pre-analysis module is used to compare the local extension characterization quantity with the local extension reference characterization quantity, and determine the suspected defect interval segment based on the comparison result. If the local extension characterization quantity is greater than the local extension reference characterization quantity, then the pre-analysis module determines the fluorescent marker position of the local extension characterization quantity as a suspected defect interval segment; The local extension reference value is calculated and determined based on the total extension of the stretched rubber strip.

4. The multi-parameter based automotive rubber strip detection system as claimed in claim 3, wherein, The suspected defect section is a pre-defined section of the adhesive strip along the axial direction of the adhesive strip, with the location of the fluorescent mark as the center reference. Several sets of points are arranged along the axial direction of the adhesive strip within the suspected defect section.

5. The multi-parameter based automotive rubber strip detection system as claimed in claim 4, wherein, The defect classification module is used to determine the changes in fluorescence intensity values, wherein, The defect classification module is used to calculate the fluorescence intensity difference between any two points with the same axial position among the points arranged along the axial direction of the adhesive strip in each group, and to determine the standard deviation of the fluorescence intensity difference as the fluorescence intensity change.

6. The multi-parameter based automotive rubber strip detection system as claimed in claim 5, wherein, The defect classification module is used to compare the fluorescence intensity change with a preset fluorescence intensity change reference value to determine the performance category of the suspected defect interval. If the change in fluorescence intensity is less than or equal to the reference amount of fluorescence intensity change, the defect classification module determines the performance category of the suspected defect interval as the first performance category. If the change in fluorescence intensity is greater than the reference value for the change in fluorescence intensity, the defect classification module determines the performance category of the suspected defect interval as the second performance category.

7. The multi-parameter based automotive rubber strip detection system as claimed in claim 6, wherein, The location detection module is used to determine the quantitative characterization value of the defect for different performance categories, wherein... The positioning and detection module is used to determine the defect quantification value for the suspected defect interval of the first manifestation category as the interval distance between adjacent ring fluorescent markers. The positioning and detection module is used to determine the ring width of the annular fluorescent marker as the defect quantification characterization value for the suspected defect interval of the second manifestation category.

8. The multi-parameter-based automotive rubber strip detection system according to claim 7, characterized in that, The positioning detection module is used to locate the defective position of the adhesive strip based on the spacing between adjacent annular fluorescent markers. The positioning and detection module is used to obtain the interval distance between the annular fluorescent marks after stretching each suspected defect interval segment, and to locate the suspected defect interval segment where the standard deviation of the interval distance is greater than the preset standard deviation threshold of the interval distance as the location where the adhesive strip has a defect.

9. The multi-parameter-based automotive rubber strip detection system according to claim 7, characterized in that, The positioning detection module is used to locate the position of the defect in the adhesive strip based on the ring width of the annular fluorescent mark. The positioning and detection module is used to obtain the ring width of the annular fluorescent mark after stretching each suspected defect segment, and to locate the annular fluorescent mark where the ring width is not within the preset range as the location where the adhesive strip has a defect.

10. A multi-parameter-based method for detecting automotive rubber strips, used in the multi-parameter-based automotive rubber strip detection system according to any one of claims 1-9, characterized in that, include: A fluorescent material is coated onto the surface of the adhesive strip in a direction perpendicular to the axial direction to form several sets of fluorescent markings; The adhesive strip is stretched along the axial direction, and surface images of each group of fluorescent markings on the stretched adhesive strip are obtained. Obtain the local stretching characterization of each group of fluorescent markers on the stretched adhesive strip, and determine the suspected defect interval based on the local stretching characterization; Under a preset light source, a surface image of the suspected defective section after stretching is obtained to determine the fluorescence intensity value at several points, and the performance category of the suspected defective section is determined according to the change of fluorescence intensity value. Each suspected defect segment is stretched separately, and a quantitative characterization value for the defect is determined for different manifestation categories in order to locate the location of the defect in the adhesive strip.

Images