Method and system for detecting sealing performance of automobile skylight sealing strip

Abstract

The invention provides a sealing performance detection method and system for an automobile skylight sealing strip, and relates to the technical field of performance detection, and the method comprises the steps: obtaining an automobile skylight processing log, carrying out the abnormal calibration to obtain an abnormal calibration result, traversing the calibration result, deploying a wind power sensor, closing the internal and external airflow channels of an automobile, and activating a wind power gun. A wind power vector set is collected, feature fusion is carried out through a sealing anomaly analysis assembly, a sealing anomaly level label is obtained, and finally, the sealing anomaly level label and an abnormal position calibration result are stored in an associated mode and sent to a sealing performance detection management end. The technical problems that in the prior art, abnormal position positioning is difficult, automatic detection is lacked, tracing and management are difficult, and performance detection is inaccurate can be solved, the accuracy and efficiency of automobile skylight sealing performance detection can be improved, the production cost is reduced, and the product quality and the customer satisfaction degree are improved.

Description

Technical Field

[0001] This application relates to the technical field of performance detection, and particularly relates to a method and system for detecting the sealing performance of an automotive sunroof sealant strip. Background Art

[0002] As an important part of a vehicle, an automotive sunroof not only provides additional light and ventilation inside the vehicle compartment but also enhances the driving and riding comfort. However, if the sealing performance of the sunroof is poor, it may cause external pollutants such as rainwater and dust to enter the interior of the vehicle compartment, and may even affect the structural integrity of the vehicle and the comfort of the occupants.

[0003] In practical applications, the sunroof sealant strip may be affected by various factors such as temperature, humidity, ultraviolet radiation, and mechanical stress. These factors may cause the sealant strip to age, deform, or break, thereby affecting its sealing performance. Therefore, the detection method needs to fully consider these factors to ensure that the sealant strip can maintain good sealing performance in various environments.

[0004] Currently, traditional sealing performance detection is usually a manual-based detection method with low automation, resulting in poor efficiency.

[0005] In summary, in the prior art, it is difficult to locate abnormal positions, there is a lack of automated detection, and tracing and management are relatively difficult, resulting in inaccurate performance detection. Summary of the Invention

[0006] The purpose of this application is to provide a method and system for detecting the sealing performance of an automotive sunroof sealant strip to solve the technical problems in the prior art that it is difficult to locate abnormal positions, there is a lack of automated detection, and tracing and management are relatively difficult, resulting in inaccurate performance detection.

[0007] In view of the above problems, this application provides a method and system for detecting the sealing performance of an automotive sunroof sealant strip.

[0008] In a first aspect, the present application provides a method for detecting the sealing performance of an automotive sunroof sealing strip. The method is implemented through a system for detecting the sealing performance of an automotive sunroof sealing strip. Among them, the method includes: obtaining an automotive sunroof processing log, where the automotive sunroof processing log includes vehicle model information and sunroof sealing process records; performing sealing anomaly calibration based on the vehicle model information and the sunroof sealing process records to obtain an anomaly location calibration result; deploying wind sensors by traversing the anomaly location calibration result, closing the internal and external air flow channels of the vehicle, activating a wind gun to blow air according to a preset output power and a preset blowing position, traversing the anomaly location calibration result to blow air, and collecting a wind vector set of the wind sensors, where the anomaly location calibration result and the wind vector set are in one-to-one correspondence; through a sealing anomaly analysis component, performing feature fusion on the wind vector set to obtain a sealing anomaly level label; associating and storing the sealing anomaly level label and the anomaly location calibration result, and sending them to a sealing performance detection management terminal.

[0009] In a second aspect, the present application further provides a system for detecting the sealing performance of an automotive sunroof sealing strip, which is used to execute a method for detecting the sealing performance of an automotive sunroof sealing strip as described in the first aspect. Among them, the system includes: a processing log acquisition module, which is used to obtain an automotive sunroof processing log, where the automotive sunroof processing log includes vehicle model information and sunroof sealing process records; an anomaly location acquisition module, which is used to perform sealing anomaly calibration based on the vehicle model information and the sunroof sealing process records to obtain an anomaly location calibration result; a wind speed vector set acquisition module, which is used to deploy wind sensors by traversing the anomaly location calibration result, close the internal and external air flow channels of the vehicle, activate a wind gun to blow air according to a preset output power and a preset blowing position, traverse the anomaly location calibration result to blow air, and collect a wind vector set of the wind sensors, where the anomaly location calibration result and the wind vector set are in one-to-one correspondence; a feature fusion module, which is used to perform feature fusion on the wind vector set through a sealing anomaly analysis component to obtain a sealing anomaly level label; an association storage module, which is used to associate and store the sealing anomaly level label and the anomaly location calibration result, and send them to a sealing performance detection management terminal.

[0010] One or more technical solutions provided in the present application have at least the following technical effects or advantages: By obtaining the processing log of the vehicle sunroof, where the processing log of the vehicle sunroof includes vehicle model information and sunroof sealing process records; performing sealing anomaly calibration based on the vehicle model information and the sunroof sealing process records to obtain an anomaly location calibration result; traversing the anomaly location calibration result to deploy a wind sensor, closing the internal and external air flow channels of the vehicle, activating a wind gun to blow air according to a preset output power and a preset blowing position, traversing the anomaly location calibration result to blow air, and collecting a wind vector set of the wind sensor, where the anomaly location calibration result and the wind vector set are in one-to-one correspondence; through a sealing anomaly analysis component, performing feature fusion on the wind vector set to obtain a sealing anomaly level label; associating and storing the sealing anomaly level label and the anomaly location calibration result, and sending them to the sealing performance detection management terminal. This effectively solves the technical problems in the prior art that it is difficult to locate the anomaly position, lacks automated detection, and is difficult to trace and manage, resulting in inaccurate performance detection, and can improve the accuracy and efficiency of the sealing performance detection of the vehicle sunroof, reduce production costs, and improve product quality and customer satisfaction.

[0011] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the present application more obvious and understandable, the following specifically illustrates the embodiments of the present application. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings described below are only exemplary, and for those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0013] Figure 1 It is a schematic flowchart of a method for detecting the sealing performance of a vehicle sunroof sealing strip according to the present application; Figure 2 It is a schematic structural diagram of a system for detecting the sealing performance of a vehicle sunroof sealing strip according to the present application.

[0014] Description of the reference numerals: Processing log acquisition module 11, anomaly location acquisition module 12, wind speed vector set acquisition module 13, feature fusion module 14, association storage module 15. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0015] By providing a method and system for detecting the sealing performance of an automotive sunroof sealing strip, the present application solves the technical problems in the prior art, such as difficult positioning of abnormal positions, lack of automated detection, difficult traceability and management, resulting in inaccurate performance detection. It can improve the accuracy and efficiency of detecting the sealing performance of automotive sunroofs, reduce production costs, and improve product quality and customer satisfaction.

[0016] Next, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application. Additionally, it should be noted that for the sake of description, only the parts related to the present application are shown in the accompanying drawings rather than all of them.

[0017] Embodiment 1 Please refer to the attached Figure 1 , the present application provides a method for detecting the sealing performance of an automotive sunroof sealing strip. Among them, the method is applied to a system for detecting the sealing performance of an automotive sunroof sealing strip, and the method specifically includes the following steps: Step 1: Obtain the processing log of the automotive sunroof. Among them, the processing log of the automotive sunroof includes vehicle model information and sunroof sealing process records; Specifically, the specific content of the obtained processing log of the automotive sunroof includes, but is not limited to, vehicle model information, sunroof sealing process records, etc. Those skilled in the art define the format of the log in advance, such as data fields, data types, data units, etc. Determine the storage location of the processing log of the automotive sunroof, which may be a database, a file server, or cloud storage, etc. Establish a connection with the data source according to the type of the data source and the access rights. Write corresponding query statements according to the type of the data source and the format of the log for retrieving and extracting vehicle model information and sunroof sealing process records. Run the query statements to retrieve and extract the required log data from the data source. Verify the extracted data to ensure the accuracy and integrity of the data. Clean the extracted raw data, including removing duplicate data, handling missing values, correcting incorrect data, etc. Format the cleaned data according to the predefined format. Store the formatted data in a suitable location, such as a database, a data warehouse, or a file, for subsequent use and analysis. Among them, the vehicle model information includes vehicle model, model year, model number, production batch, production location, vehicle configuration overview, etc., and the sunroof sealing process records include sealing strip type, sealing strip specification, auxiliary materials used such as cleaners, lubricants, adhesives, coating trajectories, etc.

[0018] Step 2: Perform seal anomaly calibration based on the vehicle model information and the skylight seal process record to obtain the anomaly location calibration result; Specifically, match the vehicle model information with the skylight seal process record. Ensure that each vehicle model is associated with its corresponding seal process record through database query. Standardize the different seal process standards that may exist for different vehicle models. This includes converting various parameters such as coating trajectories, flow rates, etc. into comparable units or metrics. By analyzing the standardized data, identify the outliers that do not conform to the normal process parameter range. Use statistical methods such as mean, standard deviation analysis or machine learning algorithms such as anomaly detection algorithms. Once the outliers are identified, determine the specific locations corresponding to these outliers. For example, the original skylight seal process record can be reviewed to find the coating trajectory corresponding to the outlier. Record the information of each anomaly location in detail, including the vehicle model, anomaly type such as insufficient coating, excessive coating, etc., and the specific description of the anomaly location such as which part of the skylight, which point on the coating trajectory, etc.

[0019] Step 3: Deploy wind sensors by traversing the anomaly location calibration result, close the air flow channels inside and outside the vehicle, activate the wind gun according to the preset output power and preset blowing position, traverse the anomaly location calibration result to blow air, and collect the wind vector set of the wind sensors, where the anomaly location calibration result and the wind vector set are in one-to-one correspondence; Specifically, ensure that there are a sufficient number of wind sensors, and these sensors are calibrated to accurately measure the magnitude and direction of the wind. Prepare a wind gun with adjustable output power and blowing position, and ensure that it is working properly and can meet the test requirements. Close the air flow channels inside and outside the vehicle to exclude the interference of external air flow on the test results. Based on the anomaly location calibration result, formulate a test sequence to ensure that each anomaly location can be effectively tested. Deploy a wind sensor near each anomaly location to ensure that the sensor can accurately measure the wind generated by the wind gun. Ensure that the sensor is firmly fixed at the test position to avoid movement or shaking during the blowing process. Set the output power and blowing position of the wind gun according to the test requirements. Ensure that these parameters remain consistent during the test. According to the planned test sequence, blow air at each anomaly location one by one. At each location, activate the wind gun and blow air according to the preset parameters. During the blowing process, record the wind vectors measured by each wind sensor in real time, including the magnitude and direction. Ensure that these data correspond one-to-one with the anomaly locations. Organize the collected wind vector data to form a complete wind vector set. This set should contain the wind vector information at all test locations. Analyze the distribution of the wind at the anomaly locations based on the wind vector set. This helps to understand the degree of influence of the seal anomaly on the air flow and the possible leakage paths.

[0020] Step 4: Through the seal anomaly analysis component, perform feature fusion on the wind force vector set to obtain a seal anomaly level label; Specifically, ensure the integrity and accuracy of the data in the wind force vector set, and remove any outliers or incorrect data. Standardize each feature in the wind force vector set, such as wind force magnitude, direction, etc., to eliminate the influence of dimensions and units, making different features comparable. Select features related to seal anomalies from the wind force vector set. These features may include the magnitude, direction, stability, etc. of the wind force. According to the nature and importance of the selected features, select a suitable feature fusion method. This includes weighted average, principal component analysis, neural network fusion, etc. Use the selected feature fusion method to fuse multiple features into one or more comprehensive features, which can more comprehensively reflect the seal anomaly situation. According to actual needs, define different levels of seal anomalies, such as minor, moderate, severe, etc. Set corresponding thresholds for each anomaly level based on historical data. These thresholds can be determined by expert experience or statistical methods. Compare the fused comprehensive features with the set thresholds, and assign corresponding seal anomaly level labels to each anomaly location.

[0021] Step 5: Associatively store the seal anomaly level label and the anomaly location calibration result, and send them to the seal performance detection management terminal.

[0022] Specifically, organize the sealed abnormal level labels obtained after feature fusion in a unified format to ensure that each label corresponds to a specific abnormal position. Check whether the number of abnormal position calibration results is consistent with the number of sealed abnormal level labels. If there are any mismatches, adjust or supplement the data to ensure a one-to-one correspondence. Generate a unique identifier for each item in the abnormal position calibration result, which can be a serial number, UUID, etc., to ensure uniqueness in the dataset. Correlate the generated unique identifier with the sealed abnormal level label. According to the data volume and query requirements, select a suitable database management system or storage system, such as the relational database MySQL, the NoSQL database MongoDB, etc. Create or update the table structure in the database to store the abnormal position calibration results and the sealed abnormal level labels and reflect the association relationship between them. The table design should consider query efficiency and scalability. Import the organized data into the database to ensure that the associated key values are stored correctly and can reflect the association between the calibration results and the labels. According to the requirements of the management terminal, write a script or use existing data conversion tools to convert the data in the database into a format acceptable to the management terminal, such as CSV, XML, JSON, etc. According to the sensitivity and security requirements of the data, select a suitable transmission protocol. If the data contains sensitive information, an encrypted transmission protocol, such as SFTP or HTTPS, should be used. Configure the necessary transmission parameters according to the selected protocol, such as the server address, port number, authentication method, etc. Write an automated script to extract the data from the source database at regular intervals or on demand, format it into the specified format, and then send it to the target management terminal through the configured transmission protocol. Alternatively, if the data volume is small or the changes are infrequent, these steps can also be performed manually. Configure a corresponding service in the sealed performance detection management terminal to receive the data, which can be an FTP server, a web server, or a dedicated API interface, etc. The receiving service should authenticate the sender and perform an integrity check on the received data to ensure that it has not been tampered with during transmission. The management terminal needs to store the received data in its own database for subsequent query and analysis. This includes steps such as data parsing, cleaning, and conversion.

[0023] Further, step two of this application also includes: The skylight sealing process record includes sealant coating trajectory information, sealant coating flow rate information, and sealant coating duration information; Taking the sealant coating trajectory information, the sealant coating flow rate information, the sealant coating duration information, and the vehicle model information as retrieval constraints, collect a sealed detection record dataset; Traverse the sealed detection record dataset to extract the positions of seal anomalies, obtaining the first seal anomaly position set, the second seal anomaly position set, up to the Nth seal anomaly position set, where N≥1 and N is an integer; Perform high-frequency position analysis on the first seal anomaly position set, the second seal anomaly position set, up to the Nth seal anomaly position set to obtain the anomaly position calibration result.

[0024] Specifically, collect the skylight sealing process records, which include sealant coating trajectory information, sealant coating flow rate information, and sealant coating duration information. Use the vehicle model information as an additional retrieval constraint condition. Different models of vehicles may have different skylight designs and sealing requirements, so the model information is necessary for accurate analysis. Use the above-mentioned sealant coating trajectory, flow rate, duration, and vehicle model information as retrieval constraints to retrieve the relevant sealed detection record dataset from the database. This dataset will contain multiple historical records of sealed detections. Traverse the retrieved sealed detection record dataset and analyze the record content one by one. For each record, apply an anomaly detection algorithm or a preset anomaly determination criterion to identify the position of the seal anomaly. These criteria may be based on trajectory deviation, flow rate anomaly, or too long / too short coating duration, etc. Classify and store the identified anomaly positions into different sets, such as the first seal anomaly position set, the second seal anomaly position set, up to the Nth seal anomaly position set. Here, N represents the number of anomaly position sets, which is an integer greater than or equal to 1. Among them, the sealant includes the brand, model, etc. used, the coating trajectory includes the path or pattern, and the flow rate information includes the coating rate or quantity.

[0025] Furthermore, this application also includes: Construct a seal process deviation evaluation function: , , , , where represents the first seal process record, represents the ith position of the first seal process record, represents the sealant coating flow rate at the ith position of the first seal process record, represents the sealant coating duration at the ith position of the first seal process record, represents the second seal process record, represents the ith position of the second seal process record, Characterize the sealant application flow rate recorded in the second sealing process at the i-th position, Characterize the sealant application duration recorded in the second sealing process at the i-th position, Characterize the first deviation coefficient, Characterize the second deviation coefficient, M represents the total number of positions recorded in the first sealing process, and L represents the total number of positions recorded in the second sealing process, Characterize the Euclidean distance between the record at the i-th position in the first sealing process and the record at the i-th position in the second sealing process in a unified coordinate system, Characterize the distance deviation threshold, Characterize the flow rate deviation threshold, Characterize the duration deviation threshold, and are pre-configured weights, and the sum of the two is equal to 1, Characterize the second deviation coefficient; Taking the vehicle model information as the primary retrieval constraint, collect the first sealing detection record dataset; Traverse the first sealing process record set in the first sealing detection record dataset, and perform deviation evaluation with the sealant application trajectory information, the sealant application flow rate information, and the seal application duration information to obtain a binary deviation coefficient set; According to the first deviation coefficient threshold and the second deviation coefficient threshold, based on the binary deviation coefficient set, sort the first sealing detection record dataset to obtain the sealing detection record dataset, where sorting is performed when both the first deviation coefficient threshold and the second deviation coefficient threshold are satisfied.

[0026] Specifically, the specific obtaining process of the above-mentioned sealing process deviation evaluation function is as follows: First, assume that the standard record in the vehicle sunroof sealing process is , and the actual record to be evaluated is , denoted as: Standard process record: ; Actual process record: .

[0027] Then, construct a position deviation evaluation function (first deviation coefficient): Step A: Define the single-point position deviation. For any i-th position, define the Euclidean distance between two trajectory positions: , where (x, y, z) are the coordinate values in the coordinate system.

[0028] Step B: Introduce a distance threshold to determine the criterion for position deviation. Set the distance deviation threshold as . When the deviation at the same position of the two records exceeds or is equal to the threshold, it is defined as a position deviation: .

[0029] Step C: Count the number of deviation times at all positions of the trajectory. To ensure that each point can be effectively corresponded, the number of positions counted is the shorter one of the two records, min(M, L): .

[0030] Step D: Construct the formula for the position deviation coefficient (normalization processing). To make the coefficients comparable and fall within the interval, normalize using the larger value of the total number of positions, max(M, L), as the denominator: .

[0031] Next, construct the flow and duration deviation evaluation function (the second deviation coefficient): Step A: Define the single-point flow and duration deviation judgment criteria respectively. Given the flow deviation threshold Δflow and the duration deviation threshold Δt, define the flow and duration deviation functions for a single point: Flow deviation: ; Duration deviation: .

[0032] Step B: Count the number of flow and duration deviation times at all positions, count the flow and duration respectively, and count to the min(M, L)th position: Total number of flow deviation times: ; Total number of duration deviation times: .

[0033] Step C: Define the weight coefficient, and weighted synthesize the flow and duration deviation. Since the importance of flow and duration is different, introduce the weight coefficient , where = 1, and define it as: .

[0034] Step D: Construct the flow-duration deviation coefficient (normalization processing), normalize with the larger number of positions max(M, L) as the denominator, and obtain the second deviation coefficient: . Among them, the numerator in the first deviation coefficient and the second deviation coefficient uses and the denominator uses , mainly to more scientifically and fairly measure the process deviation when comparing sealing process records of different lengths. The specific reasons are as follows: Unify the comparison scale: The number of positions in the automotive sunroof sealing process record may be different, and directly comparing the deviations will be inaccurate. Using the form with the numerator as and the denominator as can unify the deviations of records of different lengths to the same scale, eliminate the influence of record length differences, and make the deviation coefficients more comparable.

[0035] Highlight the effective comparison range: The numerator uses , only focus on the corresponding positions that exist in both of the two sealing process records. For example, if one record has 10 positions and the other has 8 positions, only compare the deviations of these 8 corresponding positions to avoid interference from extra positions and accurately reflect the process deviation degree of the same positions.

[0036] Control the deviation coefficient range: Use the denominator , and the deviation coefficient value can be controlled within [0, 1]. The coefficient is 1 when the deviation is the largest and 0 when they are exactly the same. This facilitates setting a threshold to judge whether the process is abnormal. For example, if the first deviation coefficient threshold is set to 0.3, exceeding the threshold may indicate a risk of sealing abnormality.

[0037] Finally, combine to form a sealing process deviation evaluation function. Through the derivation of the above two deviation coefficients, the final sealing process deviation evaluation function combination is: .

[0038] Characterize the first sealing process record, Characterize the i-th position of the first sealing process record, Characterize the sealing glue coating flow rate at the i-th position of the first sealing process record, Characterize the sealing glue coating duration at the i-th position of the first sealing process record, Characterize the second sealing process record, Characterize the i-th position of the second sealing process record, Characterize the sealing glue coating flow rate at the i-th position of the second sealing process record, Characterize the sealing glue coating duration at the i-th position of the second sealing process record, Characterize the first deviation coefficient, Characterize the second deviation coefficient, M represents the total number of positions of the first sealing process record, L represents the total number of positions of the second sealing process record, Characterize the Euclidean distance at the i-th position of the first sealing process record and the i-th position of the second sealing process record in a unified coordinate system, Characterize the distance deviation threshold (set by those skilled in the art according to the standard ISO11926-1 "Hydraulic Fluid Power - Ports and Stud Ends with ISO 725 Threads and O-Ring Seals - Part 1: Ports with O-Ring Seals in Stub End Housing"). Optionally, the sealing surface position deviation ≤ 0.1 mm), Characterize the flow rate deviation threshold (set by those skilled in the art according to the standard SAE J200 "Rubber Material Classification System". The standard stipulates the fluctuation range of the sealing glue coating flow rate (such as ±10%)), Characterize the duration deviation threshold (set by those skilled in the art according to the standard ASTM D2000 "Automotive Rubber Products Classification System"), Based on the vulcanization time calculation formula (such as T90 + 5%), combined with the production line beat set to ±2 seconds, and are pre-configured weights, and the sum of the two is equal to 1, characterizes the second deviation coefficient; using the vehicle model information as the primary retrieval constraint, collect the first set of seal detection records related to this model from the database. This dataset should contain multiple seal process records, and each record contains information such as the trajectory, flow rate, and duration of sealant application. Traverse each seal process record in the first set of seal detection records and compare it with the known sealant application trajectory information, sealant application flow rate information, and seal application duration information, and perform deviation evaluation through the seal process deviation evaluation function. The purpose of deviation evaluation is to measure the difference between the actual record and the standard or expected value. For each seal process record, calculate its deviation coefficient from the standard value. The deviation coefficient can be a numerical value indicating the degree of difference between the actual value and the standard value. After calculating the deviation coefficients of all records, a binary deviation coefficient set is obtained. It contains the deviation coefficients related to the trajectory information and the flow rate and duration information.

[0039] The sorting principle of the binary deviation coefficient set is as follows: for each element in the binary deviation coefficient set, check whether its two deviation coefficients simultaneously meet the requirements of the first deviation coefficient threshold and the second deviation coefficient threshold. If both are met (that is, when De1 ≥ the first threshold and De2 ≥ the second threshold, it is determined as an abnormal record, where the settings of the first and second thresholds are obtained by those skilled in the art based on a large amount of experimental data), then retain this record in the new set of seal detection records; if not, filter it out.

[0040] After screening, a new and more accurate set of seal detection records is obtained, and this dataset only contains those seal process records related to a specific vehicle model and meeting the preset standards.

[0041] Furthermore, this application also includes: Statistically analyze according to the first set of seal abnormal positions, the second set of seal abnormal positions until the Nth set of seal abnormal positions to obtain the abnormal detection position set and the first abnormal detection frequency set; Obtain the position deviation threshold; According to the position deviation threshold, traverse the abnormal detection position set and statistically analyze the adjacent position abnormal detection frequency set; Sum the corresponding adjacent position abnormal detection frequency set and the first abnormal detection frequency set to obtain the second abnormal detection frequency set; According to the abnormal detection frequency threshold, sort the abnormal detection position set based on the second abnormal detection frequency set to obtain the abnormal position calibration result.

[0042] Specifically, statistics are performed on the first set of seal abnormal positions, the second set of seal abnormal positions, up to the Nth set of seal abnormal positions. The purpose of this statistics is to identify all the positions where abnormalities occur and record the frequency of occurrence of abnormalities at each position. The abnormal positions in all the seal abnormal position sets are merged to form a set containing all the unique abnormal positions. For each position in the abnormal detection position set, calculate the total number of times it appears in all the seal abnormal position sets to form the first abnormal detection frequency set. Each element in this set represents the abnormal detection frequency of a specific position. The selection of the position deviation threshold should be determined according to the specific sealing process and application scenario. Factors that may need to be considered include the coating accuracy of the sealant, the size and shape of the skylight, etc. By obtaining the position deviation threshold, traverse the abnormal detection position set. For each position, find its neighboring positions, that is, other positions whose distance is less than or equal to the position deviation threshold, and count the abnormal detection frequencies of these neighboring positions to form the neighboring position abnormal detection frequency set. The purpose of this step is to take into account that abnormalities may occur not only at the same exact position but also at adjacent positions. Add the obtained neighboring position abnormal detection frequency set to the obtained first abnormal detection frequency set. Add its own abnormal detection frequency to the abnormal detection frequencies of its neighboring positions to obtain the second abnormal detection frequency set. Comprehensively consider the abnormal frequencies of each position and its neighboring positions to obtain a more comprehensive abnormal assessment. Set an abnormal detection frequency threshold by those skilled in the art. This threshold is used to determine which positions have abnormal frequencies high enough to be considered real abnormalities. Then, based on the second abnormal detection frequency set and this threshold, sort the abnormal detection position set to obtain the abnormal position calibration result.

[0043] Further, step four of the present application includes: Interact with the wind gun control component to obtain the blowing vector set of the wind vector set; Calculate the vector cosine eigenvalue set according to the wind vector set and the blowing vector set; Calculate the reduction percentage eigenvalue set according to the wind vector set and the blowing vector set; Construct a vector cosine feature matrix and a reduction percentage feature matrix according to the vector cosine eigenvalue set and the reduction percentage eigenvalue set; Through the seal abnormal analysis component, analyze the vector cosine feature matrix and the reduction percentage feature matrix to obtain the seal abnormal level label.

[0044] Specifically, data regarding wind vectors is obtained through the control component of the wind gun. The wind gun may generate a series of wind vectors, which represent the blowing direction and intensity of the wind gun at different times and with different settings. These data are collected to form a wind vector set, where each vector represents the blowing condition at a specific time point. The wind vector set and the blowing vector set are used to calculate the cosine value between the vectors. The cosine value is a number between -1 and 1, which is used to measure the similarity between two vectors. A cosine value of 1 indicates that the two vectors are exactly the same, -1 indicates they are exactly opposite, and 0 indicates they are orthogonal (i.e., uncorrelated). The cosine values between all wind vectors and blowing vectors are calculated to form a vector cosine eigenvalue set. A reduced percentage eigenvalue set is calculated. This eigenvalue set may involve comparing the difference in the modulus lengths of the wind vectors and the blowing vectors and converting it into a percentage form. Using the vector cosine eigenvalue set and the reduced percentage eigenvalue set, two feature matrices, the vector cosine feature matrix and the reduced percentage feature matrix, are constructed. These matrices organize the eigenvalues in a two-dimensional table for convenient subsequent analysis and processing. The above two feature matrices are analyzed using the seal anomaly analysis component. This analysis process may include pattern recognition, statistical analysis, or machine learning methods to identify abnormal behaviors that do not conform to the normal operation mode. Based on these analysis results, a seal anomaly level label is assigned to each wind vector or a series of vectors. This label may be a number or a classification such as "normal", "mild anomaly", "severe anomaly", etc., which is used to indicate potential problems during the sealing process.

[0045] Furthermore, this application also includes: Calculating the set of absolute values of the modulus deviations of the wind vector set and the blowing vector set; Respectively calculating the percentage occupancy of the absolute value of the modulus deviation in the blowing vector set to obtain the reduced percentage eigenvalue set.

[0046] Specifically, for each vector in the wind vector set and the blowing vector set, its modulus value is calculated. For each corresponding wind vector and blowing vector, we need to calculate the deviation of their modulus values. The deviation can be calculated by the following formula: deviation = ∣modulus value of wind vector - modulus value of blowing vector∣. All the calculated absolute values of the modulus deviations are collected to form a set of absolute values of the modulus deviations. For each value in the set of absolute values of the modulus deviations, calculate its percentage occupancy in the modulus value of the corresponding blowing vector. The percentage occupancy can be calculated by the following formula: percentage occupancy = absolute value of the modulus deviation of the blowing vector × 100%. All the calculated percentage occupancies are collected to form the reduced percentage eigenvalue set. Each value in this set represents the reduced percentage of the corresponding wind vector and blowing vector in terms of the modulus value.

[0047] Furthermore, this application also includes: Collect a dataset for detecting abnormal sealing records, where the dataset for detecting abnormal sealing records includes wind vector record data, blowing vector record data, and true values of abnormal sealing levels; Construct a vector cosine record matrix, a reduction percentage record matrix, and the true value of the abnormal sealing level based on the blowing vector record data and the wind vector record data; Configure the abnormal sealing analysis component with the true value of the abnormal sealing level as the supervised data and the vector cosine record matrix and the reduction percentage record matrix as the inputs.

[0048] Specifically, collect data from the actual sealing process. This dataset should include wind vector record data, blowing vector record data, and the corresponding true values of abnormal sealing levels. These data can be collected in real time during the sealing operation through various sensors and monitoring systems. Wind vector record data refers to the records of the direction and intensity of the wind generated by the wind gun at different times and settings. Blowing vector record data refers to the records of the direction and intensity of the wind actually acting on the sealing material. The true value of the abnormal sealing level is determined by the quality inspection system and is used to identify whether an abnormal sealing has occurred under specific wind and blowing conditions and the severity of the abnormality. Construct the required matrices. Vector cosine record matrix: Calculate the cosine similarity between each wind vector record and the corresponding blowing vector record, and organize these values into a matrix. Reduction percentage record matrix: Calculate the percentage difference between the norm of each wind vector record and the norm of the corresponding blowing vector record, and organize these values into another matrix. This matrix will reveal the attenuation of the wind when it is transmitted to the sealing material. Configure the abnormal sealing analysis component. The internal working principle of the model is preferably to construct a two-dimensional coordinate system with vector cosine and reduction percentage as the coordinate axes; then the user divides the abnormal sealing level area in the two-dimensional coordinate system. Generally, the larger the angle, the higher the level, and the larger the reduction percentage, the higher the level. Then, several levels are obtained based on the output matrix set, and the model internally fits the mode values of several levels as the output value of the model.

[0049] In summary, the sealing performance detection method for an automotive sunroof seal provided by this application has the following technical effects: By obtaining the processing log of the automotive sunroof, where the processing log of the automotive sunroof includes vehicle model information and sunroof sealing process records; performing sealing anomaly calibration based on the vehicle model information and the sunroof sealing process records to obtain an anomaly location calibration result; traversing the anomaly location calibration result to deploy a wind sensor, closing the internal and external air flow channels of the vehicle, activating a wind gun to blow air according to a preset output power and a preset blowing position, traversing the anomaly location calibration result to blow air, and collecting a wind vector set of the wind sensor, where the anomaly location calibration result and the wind vector set are in one-to-one correspondence; through a sealing anomaly analysis component, performing feature fusion on the wind vector set to obtain a sealing anomaly level label; associating and storing the sealing anomaly level label and the anomaly location calibration result, and sending them to a sealing performance detection management terminal. This effectively solves the technical problems in the prior art such as difficult anomaly location, lack of automated detection, difficult traceability and management, resulting in inaccurate performance detection, can improve the accuracy and efficiency of automotive sunroof sealing performance detection, reduce production costs, and improve product quality and customer satisfaction.

[0050] Embodiment 2 Based on a method for detecting the sealing performance of an automotive sunroof seal in the foregoing embodiment, with the same inventive concept, the present application also provides a system for detecting the sealing performance of an automotive sunroof seal. Please refer to the attached Figure 2 , the system includes: A processing log acquisition module 11, which is used to obtain the processing log of the automotive sunroof, where the processing log of the automotive sunroof includes vehicle model information and sunroof sealing process records; An anomaly location acquisition module 12, which is used to perform sealing anomaly calibration based on the vehicle model information and the sunroof sealing process records to obtain an anomaly location calibration result; A wind speed vector set acquisition module 13, which is used to traverse the anomaly location calibration result to deploy a wind sensor, close the internal and external air flow channels of the vehicle, activate a wind gun to blow air according to a preset output power and a preset blowing position, traverse the anomaly location calibration result to blow air, and collect a wind vector set of the wind sensor, where the anomaly location calibration result and the wind vector set are in one-to-one correspondence; A feature fusion module 14, which is used to perform feature fusion on the wind vector set through a sealing anomaly analysis component to obtain a sealing anomaly level label; An association storage module 15, which is used to associate and store the sealing anomaly level label and the anomaly location calibration result, and send them to a sealing performance detection management terminal.

[0051] Further, the anomaly location acquisition module 12 in the system is further used for: The skylight sealing process record includes sealant application trajectory information, sealant application flow rate information, and sealant application duration information; Taking the sealant application trajectory information, the sealant application flow rate information, the sealant application duration information, and the vehicle model information as retrieval constraints, a seal detection record data set is collected; Traverse the seal detection record data set to extract the seal abnormality detection positions, and obtain the first seal abnormality position set, the second seal abnormality position set until the Nth seal abnormality position set, where N≥1 and N is an integer; Perform high-frequency position analysis on the first seal abnormality position set, the second seal abnormality position set until the Nth seal abnormality position set to obtain the abnormality position calibration result.

[0052] Furthermore, the system further includes a detection record set acquisition module, and the detection record acquisition module is used for: Construct a seal process deviation evaluation function: , , , , Wherein, represents the first seal process record, represents the ith position of the first seal process record, represents the sealant application flow rate of the first seal process record at the ith position, represents the sealant application duration of the first seal process record at the ith position, represents the second seal process record, represents the ith position of the second seal process record, represents the sealant application flow rate of the second seal process record at the ith position, represents the sealant application duration of the second seal process record at the ith position, represents the first deviation coefficient, represents the second deviation coefficient, M represents the total number of positions of the first seal process record, and L represents the total number of positions of the second seal process record, represents the Euclidean distance between the ith position of the first seal process record and the ith position of the second seal process record in a unified coordinate system, represents the distance deviation threshold, represents the flow rate deviation threshold, represents the duration deviation threshold, and are pre-configured weights, and the sum of the two is equal to 1, representing the second deviation coefficient; Taking the vehicle model information as the primary retrieval constraint, collect the first sealed detection record dataset; Traverse the first sealed process record set of the first sealed detection record dataset, and perform deviation evaluation with the sealant application trajectory information, the sealant application flow rate information, and the sealant application duration information to obtain a binary deviation coefficient set; According to the first deviation coefficient threshold and the second deviation coefficient threshold, based on the binary deviation coefficient set, sort the first sealed detection record dataset to obtain the sealed detection record dataset, where sorting is performed when both the first deviation coefficient threshold and the second deviation coefficient threshold are satisfied.

[0053] Furthermore, the system further includes a calibration result acquisition module, and the calibration result acquisition module is used for: Perform statistics based on the first sealed abnormal position set, the second sealed abnormal position set until the Nth sealed abnormal position set to obtain an abnormal detection position set and a first abnormal detection frequency set; Obtain a position deviation threshold; According to the position deviation threshold, traverse the abnormal detection position set and count the adjacent position abnormal detection frequency set; Sum the corresponding adjacent position abnormal detection frequency set and the first abnormal detection frequency set to obtain a second abnormal detection frequency set; According to the abnormal detection frequency threshold, sort the abnormal detection position set based on the second abnormal detection frequency set to obtain the abnormal position calibration result.

[0054] Furthermore, the feature fusion module 14 in the system is further used for: Interact with the air gun control component to obtain the blowing vector set of the wind vector set; Calculate the vector cosine eigenvalue set according to the wind vector set and the blowing vector set; Calculate the reduction percentage eigenvalue set according to the wind vector set and the blowing vector set; Construct a vector cosine feature matrix and a reduction percentage feature matrix according to the vector cosine eigenvalue set and the reduction percentage eigenvalue set; Through the sealed abnormal analysis component, analyze the vector cosine feature matrix and the reduction percentage feature matrix to obtain the sealed abnormal level label.

[0055] Furthermore, the system further includes an eigenvalue set acquisition module, and the eigenvalue set acquisition module is used for: Calculate the set of absolute values of the modulus deviations of the wind force vector set and the blowing vector set; Calculate the percentage occupancy of the absolute values of the modulus deviations in the blowing vector set respectively to obtain the set of reduced percentage eigenvalue.

[0056] Furthermore, for the analysis component configuration module, the component configuration module is used for: Collect a sealed anomaly detection record data set, wherein the sealed anomaly detection record data set includes wind force vector record data, blowing vector record data and the true value of the sealed anomaly level; Construct a vector cosine record matrix, a reduced percentage record matrix and the true value of the sealed anomaly level according to the blowing vector record data and the wind force vector record data; Configure the sealed anomaly analysis component with the true value of the sealed anomaly level as the supervised data and the vector cosine record matrix and the reduced percentage record matrix as the inputs.

[0057] In the present specification, the various embodiments are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The foregoing Figure 1 The method and specific example for detecting the sealing performance of an automotive sunroof sealing strip in the first embodiment are equally applicable to the system for detecting the sealing performance of an automotive sunroof sealing strip in this embodiment. Through the foregoing detailed description of the method for detecting the sealing performance of an automotive sunroof sealing strip, those skilled in the art can clearly know the system for detecting the sealing performance of an automotive sunroof sealing strip in this embodiment. Therefore, for the sake of simplicity of the specification, it will not be described in detail herein. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For the relevant parts, reference may be made to the description in the method part.

[0058] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0059] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is also intended to include these changes and modifications.

Claims

1. A method for testing the sealing performance of a car sunroof sealing strip, characterized in that: include: Obtaining a car sunroof processing log, wherein the car sunroof processing log includes car model information and sunroof sealing process records; Perform sealing abnormality calibration according to the vehicle model information and the sunroof sealing process record to obtain an abnormal position calibration result; Traversing the abnormal position calibration results to deploy wind sensors, closing the airflow channels inside and outside the car, activating the wind gun to blow air according to a preset output power and a preset blowing position, traversing the abnormal position calibration results, and collecting the wind vector set of the wind sensor, wherein the abnormal position calibration results and the wind vector set correspond one to one; Through the sealing anomaly analysis component, feature fusion is performed on the wind vector set to obtain a sealing anomaly level label; The sealing abnormality level label and the abnormal position calibration result are associated and stored, and sent to the sealing performance detection management end.

2. The method according to claim 1, characterized in that Performing sealing abnormality calibration according to the vehicle model information and the sunroof sealing process record to obtain abnormal position calibration results, including: The skylight sealing process record includes sealant coating trajectory information, sealant coating flow information and sealant coating duration information; Using the sealant coating trajectory information, the sealant coating flow information, the sealant coating duration information and the automobile model information as search constraints, collecting a sealant detection record data set; Traversing the sealing detection record data set to extract the sealing abnormality detection position, and obtaining a first sealing abnormality position set, a second sealing abnormality position set, and finally an Nth sealing abnormality position set, wherein N≥1, and N is an integer; A high-frequency position analysis is performed on the first sealing abnormality position set, the second sealing abnormality position set, and up to the Nth sealing abnormality position set to obtain the abnormal position calibration result.

3. The method according to claim 2, characterized in that The sealant coating trajectory information, the sealant coating flow information, the sealant coating duration information and the car model information are used as search constraints to collect a sealant detection record data set, including: Construct the sealing process deviation evaluation function: ， ， ， ， in, Characterize the first sealing process record, Characterizes the i-th position of the first sealing process record, Characterize the sealant coating flow rate recorded at the i-th position in the first sealing process, Characterizes the sealant coating time recorded at the i-th position in the first sealing process, Characterize the second sealing process record, Characterizes the i-th position of the second sealing process record, Characterize the sealant coating flow rate recorded at the i-th position in the second sealing process, Characterizes the sealant coating time recorded at the i-th position in the second sealing process, Characterizes the first deviation coefficient, represents the second deviation coefficient, M represents the total position of the first sealing process record, L represents the total position of the second sealing process record, Characterize the Euclidean distance between the first sealing process record at position i and the second sealing process record at position i in a unified coordinate system, Characterizes the distance deviation threshold, Characterize the flow deviation threshold, Characterizes the duration deviation threshold, and is the preconfigured weight, the sum of the two is equal to 1, Characterizes the second deviation coefficient; Taking the automobile model information as a primary search constraint, collecting a first sealing detection record data set; Traversing the first sealing process record set of the first sealing detection record data set, performing deviation evaluation on the sealant coating trajectory information, the sealant coating flow information, and the sealant coating duration information, to obtain a binary deviation coefficient set; According to the first deviation coefficient threshold and the second deviation coefficient threshold, based on the binary deviation coefficient set, the first sealing detection record data set is sorted to obtain the sealing detection record data set, wherein the first deviation coefficient threshold and the second deviation coefficient threshold are simultaneously met, that is, sorting.

4. The method according to claim 2, characterized in that Performing high-frequency position analysis on the first sealing abnormality position set, the second sealing abnormality position set, and up to the Nth sealing abnormality position set to obtain the abnormal position calibration result, including: According to the first sealing abnormality position set, the second sealing abnormality position set, and the Nth sealing abnormality position set, statistics are performed to obtain an abnormality detection position set and a first abnormality detection frequency set; Obtaining a position deviation threshold; According to the position deviation threshold, traverse the abnormality detection position set and count the abnormality detection frequency set of adjacent positions; Adding the one-to-one corresponding adjacent position abnormality detection frequency set and the first abnormality detection frequency set to obtain a second abnormality detection frequency set; According to the abnormality detection frequency threshold, the abnormality detection position set is sorted based on the second abnormality detection frequency set to obtain the abnormal position calibration result.

5. The method according to claim 1, characterized in that Through the sealing anomaly analysis component, the wind vector set is feature fused to obtain a sealing anomaly level label, including: An interactive wind gun control component obtains a blowing vector set of the wind vector set; Calculating a vector cosine eigenvalue set according to the wind force vector set and the blowing vector set; Calculating a reduction percentage characteristic value set according to the wind force vector set and the blowing vector set; Constructing a vector cosine feature matrix and a reduction percentage feature matrix according to the vector cosine eigenvalue set and the reduction percentage eigenvalue set; The sealing anomaly analysis component is used to analyze the vector cosine feature matrix and the reduction percentage feature matrix to obtain the sealing anomaly level label.

6. The method according to claim 5, characterized in that Calculating a reduction percentage characteristic value set according to the wind force vector set and the blowing vector set includes: Calculating a set of absolute values ​​of modulus deviations of the wind force vector set and the blowing vector set; The percentages of the absolute values ​​of the modulus deviations in the blowing vector set are calculated respectively to obtain the reduction percentage characteristic value set.

7. The method according to claim 5, characterized in that By means of the sealing anomaly analysis component, the vector cosine feature matrix and the reduction percentage feature matrix are analyzed to obtain the sealing anomaly level label, which includes: Collecting a sealing abnormality detection record data set, wherein the sealing abnormality detection record data set includes wind vector record data, blowing vector record data and sealing abnormality level true value; Constructing a vector cosine record matrix, a reduction percentage record matrix and a true value of the sealing abnormality level according to the blowing vector record data and the wind force vector record data; The sealing anomaly analysis component is configured by taking the true value of the sealing anomaly level as supervision data and taking the vector cosine record matrix and the reduction percentage record matrix as input.

8. A sealing performance detection system for a car sunroof sealing strip, characterized in that: For implementing the steps of the method according to any one of claims 1 to 7, the system comprises: A processing log acquisition module, the processing log acquisition module is used to obtain a car sunroof processing log, wherein the car sunroof processing log includes car model information and sunroof sealing process records; An abnormal position acquisition module, the abnormal position acquisition module is used to perform sealing abnormality calibration according to the vehicle model information and the sunroof sealing process record to obtain an abnormal position calibration result; A wind speed vector set acquisition module, the wind speed vector set acquisition module is used to traverse the abnormal position calibration results to deploy wind sensors, close the air flow channels inside and outside the car, activate the wind gun to blow air according to the preset output power and preset blowing position, traverse the abnormal position calibration results, and collect the wind vector set of the wind sensor, wherein the abnormal position calibration results and the wind vector set correspond one to one; A feature fusion module, the feature fusion module is used to perform feature fusion on the wind vector set through a sealing anomaly analysis component to obtain a sealing anomaly level label; An associated storage module is used to associate and store the sealing abnormality level label with the abnormal position calibration result, and send it to the sealing performance detection management end.

Images