Airtightness monitoring system for sealing test machine based on artificial intelligence

Abstract

The invention relates to the technical field of air tightness testing, and particularly discloses a sealing tester air tightness monitoring system based on artificial intelligence, and the system comprises a sensor module which collects air pressure change parameters in real time through a pressure sensor; the image processing module collects bubble dynamic image information by using a camera; obtaining an inner surface contour image of the sealed cavity; the model construction module inputs the historical air pressure change parameters and the historical bubble dynamic information images into a preset convolutional neural network model for training, constructs a prediction model and obtains bubble motion parameters; the data analysis module inputs the air pressure change parameters and the bubble motion parameters obtained in real time into the prediction model for tracking detection, and air tightness prediction parameters are obtained; and executing an evaluation strategy based on the air tightness prediction parameters, judging whether the air tightness of the sealing test machine has a problem according to an evaluation result, and performing surface defect analysis on the inner surface contour image of the sealing cavity of the sealing space. And the display module displays the alarm result.

Description

Technical Field

[0001] The present invention relates to the technical field of air tightness testing, and in particular to an air tightness monitoring system for a sealing testing machine based on artificial intelligence. Background Art

[0002] In industrial production, sealing testing is an important part of ensuring product quality, especially for products that require high airtightness, such as electronic products, automotive parts, etc. Traditional airtightness monitoring methods usually rely on manual observation or simple pressure sensors, which are not only inefficient but also difficult to guarantee accuracy.

[0003] With the development of artificial intelligence technology, the airtightness monitoring system of sealing testers based on artificial intelligence has emerged; this system usually combines technologies such as computer vision, machine learning and deep learning, and can automatically identify and analyze airtightness problems during the sealing test. For example, by performing image analysis on the bubbles generated during the sealing test, the location and degree of the leak can be accurately detected. In addition, the artificial intelligence-based system can also continuously optimize the detection algorithm and improve the accuracy and efficiency of detection by learning from a large amount of test data.

[0004] The common airtightness monitoring system of the sealing test machine usually performs a cavity airtightness test on the test object, and judges whether the equipment seal of the test machine will leak by directly observing the situation of the connected bubbles, and then determines the location and size of the leak; however, in the process of airtight product testing, only the bubble state and quantity are analyzed, and the specific situation of the leakage of the test object cannot be accurately determined. The existing dry airtightness detection system is combined with a tracking algorithm based on machine vision, and the geometric model and dynamic model of the bubble are combined to obtain the leakage amount of the workpiece, but it is impossible to combine the pressure state and bubble state of the sealing test machine to the sealing performance of the test machine and run the judgment process of the specific leakage degree. Summary of the invention

[0005] The purpose of the present invention is to provide an airtightness monitoring system for a sealing test machine based on artificial intelligence to solve the following technical problems: How to combine the analysis of pressure status and tracking of bubble status based on artificial intelligence technology to achieve accurate judgment of the sealing performance of the sealing testing machine.

[0006] The purpose of the present invention can be achieved through the following technical solutions: An artificial intelligence-based air tightness monitoring system for a sealing tester, the sealing tester comprising a test sealing space and a water box; the test sealing space comprising a sealing cavity and a device under test; the system comprising: The sensor module is used to collect the air pressure change parameters of the device under test in the test sealed space in real time through the pressure sensor after the device under test is inflated; An image processing module is used to collect dynamic image information of bubbles in a water box connected to one side of the test sealed space through an air pipe by using a camera; and to obtain an image of the inner surface contour of the sealed cavity by using image processing technology; A model building module is used to input historical air pressure change parameters and historical bubble dynamic information images into a preset convolutional neural network model for training, build a prediction model, and obtain bubble motion parameters; A data analysis module is used to input the air pressure change parameters and bubble movement parameters obtained in real time into the prediction model for tracking and detection to obtain air tightness prediction parameters; And it is used to execute the evaluation strategy based on the airtightness prediction parameters, and judge whether there is a problem with the airtightness of the sealing test machine according to the evaluation results: If yes, it is determined that the air tightness in the current sealing test machine is unqualified, an alarm signal is generated, and a surface defect analysis is performed on the inner surface contour image of the sealing cavity of the sealed space; If not, it is judged that the air tightness in the current sealing test machine is qualified, and the air tightness monitoring continues; The display module is used to display the alarm results.

[0007] Preferably, the air pressure change parameter is obtained in the following manner: S1, obtaining a first air pressure value at an air filling pipe opening in a sealed space; S2, obtaining a second air pressure value in the sealed space after the continuous inflation reaches a set time; S3, calculating the difference between the first air pressure value and the second air pressure value as the air pressure difference within the set time period; S4. Obtain a curve of the continuous time change of the air pressure difference within a preset time period, and calculate the slope of the curve to determine the air pressure change parameter.

[0008] Preferably, the steps for obtaining the bubble motion parameters are: SS1, predetermine the time interval between adjacent frames of bubble dynamic images; SS2, obtaining the change in the number of bubbles in the bubble dynamic image of continuous frames within a preset time period and the change in the displacement distance of the bubbles corresponding to all time intervals; SS3, obtaining the bubble movement speed according to the change of bubble quantity and bubble displacement distance; SS4. Divide the movement rhythm in each time interval according to the bubble movement speed as the bubble movement parameter.

[0009] Preferably, the data analysis module inputs the air pressure change parameters and bubble movement parameters acquired in real time into the prediction model, and the specific process of tracking detection includes: The statistical airtightness-related features were encoded and normalized; The prediction model performs tracking detection to calculate the loss function between the predicted value of the airtightness-related feature and its target value; Automatically adjust the model parameters of the prediction model using the stochastic gradient descent algorithm to minimize the loss function; After multiple iterations, the prediction model converges and the airtightness prediction parameters are output.

[0010] Preferably, the airtightness prediction parameter is calculated as follows:

[0011] in, For the The airtightness prediction parameters of the test samples; is the preset function; is the preset first conversion function, is the second preset conversion function; For the Air pressure variation parameters of the test samples; is the standard air pressure variation parameter; For the The preset deviation value of the air pressure variation parameter of each test sample; For the Bubble motion parameters of the test samples; is the standard bubble motion parameter; For the The bubble motion parameters of the test samples are preset with deviation values.

[0012] Preferably, the airtightness prediction parameter The threshold value of the airtightness prediction parameter is consistent with the preset standard To compare: like > , it is judged that the current equipment under test has leakage risk and generates early warning information; like ≤ , then it is judged that the current device under test is normal.

[0013] Preferably, the process of the data analysis module executing the evaluation strategy according to the airtightness prediction parameters includes: By formula Calculate the evaluation coefficient ; in, is the total number of test samples, and ∈ ; For the The preset weight coefficients of the test samples; is the standard airtightness prediction parameter, and ≤ .

[0014] Preferably, judging whether there is a problem with the airtightness of the sealing test machine according to the evaluation results specifically includes: The evaluation coefficient With the preset evaluation coefficient threshold To compare: like < , it is judged that there is an airtightness problem in the sealing test machine and an alarm signal is generated; like ≥ , it is judged that there is no airtightness problem in the sealing test machine.

[0015] Preferably, the process of performing surface defect analysis on the inner surface contour image of the sealed cavity of the sealed space is: Identify the inner surface contour image of the sealed cavity and perform grayscale processing; The Canny algorithm is used to extract the contour of the abnormal area in the inner surface contour image; Calculate the area S and perimeter C of the abnormal area contour by the formula Calculate the abnormal area structure value .

[0016] Preferably, it also includes: The abnormal area structure value With preset threshold and For comparison, < : like ≤ , it is judged that there is a slight leakage on the cavity surface of the device under test in the sealed space; like < < , it is judged that there is moderate leakage on the cavity surface of the device under test in the sealed space; like ≥ , it is judged that there is a serious leakage on the cavity surface of the device under test in the sealed space.

[0017] Beneficial effects of the present invention: (1) The present invention realizes the acquisition of data of real-time air pressure change parameters through a pressure sensor by setting a sensor module, acquires real-time images of bubble movement in a water box connected to one side of the sealed space through an air pipe by setting an image processing module, collects bubble dynamic image information using a camera to ensure the acquisition of the continuous movement state of the bubble, and acquires an image of the inner surface contour of the sealed cavity by image processing technology, and realizes the sealing degree of the sealed cavity sealed device under test by the inner surface contour image of the sealed cavity; the present invention realizes the construction of a model based on the operation and processing process of machine learning and computer vision in artificial intelligence by setting a model construction module, constructs a prediction model by inputting historical air pressure change parameters and historical bubble dynamic information images into a preset convolutional neural network model for training, and acquires bubble movement parameters in the sealing process by machine training, and helps to judge the airtightness of the sealing test machine and conduct early warning processing by the bubble movement parameters.

[0018] (2) The present invention realizes tracking and detecting of air pressure change parameters and bubble movement parameters by setting a data analysis module, thereby obtaining airtightness prediction parameters to predict the airtightness of the sealing test machine, and outputs the airtightness prediction parameters according to the tracking detection; and the data analysis module also designs an evaluation strategy based on the airtightness prediction parameters, and obtains the evaluation results by executing the evaluation strategy to determine whether there is a problem with the airtightness of the sealing test machine. If there is an airtightness problem, an early warning is generated and a surface defect analysis is performed on the surface contour image of the current sealing cavity. The data analysis module ensures that the pressure state and bubble state of the sealing test machine are combined, and the specific leakage degree of the sealing performance of the test machine is judged according to the evaluation results.

[0019] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0021] Figure 1 This is a module diagram of an air tightness monitoring system of a sealing test machine based on artificial intelligence of the present invention; Figure 2 This is a step diagram of the method for obtaining air pressure change parameters of the present invention; Figure 3 This is a step diagram of the method for obtaining bubble motion parameters of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] The common airtightness monitoring system of the sealing test machine usually performs a cavity airtightness test on the test object, and judges whether the equipment seal of the test machine will leak by directly observing the connected bubbles, and then determines the location and size of the leak; however, in the process of airtight product testing, only the bubble state and quantity are analyzed, and the specific situation of the leakage of the test object cannot be accurately determined. The existing dry airtightness detection system is combined with a tracking algorithm based on machine vision, and the geometric model and dynamic model of the bubble are combined to obtain the leakage amount of the workpiece, but it is impossible to judge the specific leakage degree of the sealing performance of the test machine in combination with the pressure state and bubble state of the sealing test machine.

[0024] See also Figure 1 As shown, in order to solve the above technical problems, the present invention designs an airtightness monitoring system for a sealing tester based on artificial intelligence, wherein the sealing tester comprises a test sealing space and a water box; the test sealing space comprises a sealing cavity and a device under test; and comprises: The sensor module is used to collect the air pressure change parameters of the device under test in the test sealed space in real time through the pressure sensor after the device under test is inflated; An image processing module is used to collect dynamic image information of bubbles in a water box connected to one side of the test sealed space through an air pipe by using a camera; and to obtain an image of the inner surface contour of the sealed cavity by using image processing technology; A model building module is used to input historical air pressure change parameters and historical bubble dynamic information images into a preset convolutional neural network model for training, build a prediction model, and obtain bubble motion parameters; A data analysis module is used to input the air pressure change parameters and bubble movement parameters obtained in real time into the prediction model for tracking and detection to obtain air tightness prediction parameters; And it is used to execute the evaluation strategy based on the airtightness prediction parameters, and judge whether there is a problem with the airtightness of the sealing test machine according to the evaluation results: If yes, it is determined that the air tightness in the current sealing test machine is unqualified, an alarm signal is generated, and a surface defect analysis is performed on the inner surface contour image of the sealing cavity of the sealed space; If not, it is judged that the air tightness in the current sealing test machine is qualified, and the air tightness monitoring continues; The display module is used to display the alarm results.

[0025] In the above technical scheme, the present invention realizes the airtightness monitoring process based on cavity sealing detection technology, and performs sealing monitoring by setting a test sealing space, a water box, and connecting the test sealing space and the water box; wherein, the test sealing space includes a sealed cavity, a device under test, and the encapsulation of the device under test is realized by a sealed wall; the airtightness monitoring system of the sealing tester based on artificial intelligence of the present design specifically includes a sensor module, an image processing module, a model building module, a data analysis module and a display module, which realizes the analysis of pressure state and tracking of bubble state based on artificial intelligence technology, so as to realize accurate judgment of the sealing performance and leakage degree of the sealing tester.

[0026] By setting a sensor module, the data of real-time air pressure change parameters are obtained through a pressure sensor, and the real-time air pressure value is obtained according to the pressure sensor arranged in the sealed space. The real-time pressure value during the continuous inflation process is analyzed by the data processing technology set inside the pressure sensor, and then the air pressure change parameters during the continuous inflation process are obtained. By setting an image processing module, the real-time image of the real-time bubble movement in the water box connected to one side of the sealed space through the air pipe is obtained, and the bubble dynamic image information is collected by a camera to ensure the acquisition of the continuous movement state of the bubble, and the image processing technology is also used to obtain the inner surface contour image of the sealed cavity, and the sealing degree of the sealed cavity sealed device under test is realized through the inner surface contour image of the sealed cavity; by setting a model construction module, the model is constructed based on the operation processing process of machine learning and computer vision in artificial intelligence, and the construction of the model is based on the image data processing process in the convolutional neural network model. The historical air pressure change parameters and the historical bubble dynamic information images are input into the preset convolutional neural network model for training, and a prediction model is constructed. The bubble movement parameters in the sealing process are obtained by machine training, and the bubble movement parameters are used to help judge the airtightness of the sealing test machine and early warning processing.

[0027] By setting up a data analysis module, it is possible to track and detect the air pressure change parameters and the bubble movement parameters, and then obtain the airtightness prediction parameters to predict the airtightness of the sealing tester. Specifically, the air pressure change parameters and bubble movement parameters obtained in real time are input into the prediction model for tracking and detection, and the airtightness prediction parameters are output according to the tracking and detection; and the data analysis module also designs an evaluation strategy based on the airtightness prediction parameters, and obtains the evaluation results by executing the evaluation strategy to determine whether there is a problem with the airtightness of the sealing tester. For situations where there is an airtightness problem, an early warning is generated and a surface defect analysis is performed on the surface contour image of the current sealing cavity. For situations where there is no airtightness problem, the monitoring is continued. The data analysis module is used to ensure that the pressure state and the bubble state of the sealing tester are combined, and the specific leakage degree of the sealing performance of the tester is judged according to the evaluation results; the display module is set to display the early warning results in a timely manner to ensure that corresponding measures are generated for the leakage information.

[0028] As an embodiment of the present invention, please refer to Figure 2 As shown in the figure, the method of obtaining the air pressure change parameters is: S1, obtaining a first air pressure value at an air filling pipe opening in a sealed space; S2, obtaining a second air pressure value in the sealed space after the continuous inflation reaches a set time; S3, calculating the difference between the first air pressure value and the second air pressure value as the air pressure difference within the set time period; S4. Obtain a curve of the continuous time change of the air pressure difference within a preset time period, and calculate the slope of the curve to determine the air pressure change parameter.

[0029] In the above technical solution, the air pressure change parameter is used to ensure the monitoring of the air pressure change in the inflation state. Specifically, the initial state of the air pressure filling is first judged by the first air pressure value, and the air pressure in the initial state is set as the first air pressure value; then the air pressure value in the sealed space after the set inflation time is reached is used as the second air pressure value; then the difference between the first air pressure value and the second air pressure value is obtained as the air pressure difference within this set time; finally, a curve of the continuous time change of the air pressure difference is generated according to the real-time change of the air pressure difference within the preset time period for the airtight detection. , the pressure change parameters are determined by calculating the slope of the curve, and the pressure change parameters are determined by calculating the slope of the curve. Derivation is performed to obtain the cumulative total number of target time points corresponding to each curve The slope The changes in these slopes The pressure change parameters are obtained by statistical analysis of the changes in the pressure , the specific calculation formula is:

[0030] in, For the The slope value at each time point.

[0031] As an embodiment of the present invention, please refer to Figure 3 As shown, the steps for obtaining the bubble motion parameters are: SS1, predetermine the time interval between adjacent frames of bubble dynamic images; SS2, obtaining the change in the number of bubbles in the bubble dynamic image of continuous frames within a preset time period and the change in the displacement distance of the bubbles corresponding to all time intervals; SS3, obtaining the bubble movement speed according to the change of bubble quantity and bubble displacement distance; SS4. Divide the movement rhythm in each time interval according to the bubble movement speed as the bubble movement parameter.

[0032] In the above technical scheme, the bubble movement parameters are obtained to ensure that the state of bubbles overflowing from the sealed cavity space during the sealing test of the equipment under test is analyzed in a digital manner, and the next step of tracking, detection and judgment is performed according to the size of the bubble movement parameters. The specific process is: first, the bubble dynamic image obtained by the camera is divided into multiple frames, and the time interval between adjacent frames of bubble dynamic images is predetermined; then, the change in the number of bubbles in the bubble dynamic images of consecutive frames within a preset time period and the change in the bubble displacement distance obtained according to the time interval are obtained; then, the bubble movement speed is calculated according to the change in the number of bubbles and the change in the bubble displacement distance. Specifically, the image tracking method is used to record the displacement y of the bubble along the axis of each frame from the generation of a bubble to the approach to the liquid surface. At the same time, the camera frame rate, that is, the time interval between two frames of images, is determined in advance. The curve of the displacement y of the bubble along the Y-axis direction as a inverse of the time t can obviously be expressed by a quadratic polynomial.

[0033] This design uses the common least squares method to fit the motion trajectory of the bubble along the Y-axis direction, such as using polynomial fitting or spline fitting, and then derives the fitting function to get the instantaneous velocity. Specifically, based on the continuous data of the bubble motion trajectory, the instantaneous velocity of a certain point on the trajectory can be obtained by calculating the slope of the tangent to the point; finally, the average velocity of the bubble in each time interval is calculated, and these average velocities can be used as the bubble motion rhythm, and numerical simulation is performed according to the motion rhythm to obtain the specific gravity value of each motion rhythm, and fitting is performed to obtain the bubble motion parameters.

[0034] As an implementation mode of the present invention, the data analysis module inputs the air pressure change parameters and bubble movement parameters acquired in real time into the prediction model, and the specific process of tracking detection includes: The statistical airtightness-related features were encoded and normalized; The prediction model performs tracking detection to calculate the loss function between the predicted value of the airtightness-related feature and its target value; Automatically adjust the model parameters of the prediction model using the stochastic gradient descent algorithm to minimize the loss function; After multiple iterations, the prediction model converges and the airtightness prediction parameters are output.

[0035] In the above technical solution, the process of machine simulation of the acquired air pressure change parameters and bubble movement parameters by the data analysis module is mainly to input them into the trained model, i.e., the prediction model, for further tracking and detection to obtain air tightness prediction parameters. The air tightness prediction parameters reflect the predicted state of the air tightness state in the sealing cavity during the monitoring process of the current sealing test. The specific air tightness prediction parameters are obtained through machine learning: first, determine the features related to air tightness, including the material properties of the container (such as permeability, thickness, etc.), the geometric parameters of the sealing structure (such as sealing width, gap size, etc.), and environmental factors (such as temperature, pressure, etc.). This design is optimized by obtaining the air pressure change parameters and bubble movement parameters as reference values ​​for air tightness characteristics; and the reference values ​​of the air tightness characteristics are encoded as features and then normalized to ensure the unification of subsequent data.

[0036] Then, the normalized airtightness-related feature data is input into the prediction model; the prediction model will output the predicted value of the airtightness-related features; the difference between the predicted value and the target value is measured by the loss function, and the common loss function is the mean square error (MSE); then the loss function is minimized, and in each iteration, the stochastic gradient descent algorithm (SGD) updates the model parameters according to the gradient of the loss function to the model parameters; finally, the SGD algorithm is used multiple times to update the model parameters, and the loss function will gradually decrease as the number of iterations increases; when the value of the loss function no longer decreases significantly or reaches a pre-set convergence condition (such as the value of the loss function is less than a certain threshold, or the change of the loss function in several consecutive iterations is less than a certain value), it proves that the prediction model has converged and outputs the airtightness prediction parameters.

[0037] As an implementation of the present invention, the calculation method of the airtightness prediction parameter is:

[0038] in, For the The airtightness prediction parameters of the test samples; is the preset function; is the preset first conversion function, is the second preset conversion function; For the Air pressure variation parameters of the test samples; is the standard air pressure variation parameter; For the The preset deviation value of the air pressure variation parameter of each test sample; For the Bubble motion parameters of the test samples; is the standard bubble motion parameter; For the The bubble motion parameters of the test samples are preset with deviation values.

[0039] In the above technical solution, the calculation process of the airtightness parameter is through the formula Get the Airtightness prediction parameters of test samples , and according to the airtightness prediction parameters The size of the equipment can be used to estimate the risk of leakage in advance. It is a prediction function set according to historical data to ensure that the airtightness prediction parameters are within a specific reasonable range; the first conversion function is preset , the second preset conversion function All of them are obtained by fitting the test data of the sealing test machine under normal conditions. Therefore, by substituting the air pressure change parameter range of different test samples and the range of variation of bubble motion parameters Then, the airtightness prediction parameters are obtained. To determine whether there is a leak on the device under test; , These are standard data values ​​obtained based on historical experience and will not be elaborated here.

[0040] As an embodiment of the present invention, the airtightness prediction parameter The threshold value of the airtightness prediction parameter is consistent with the preset standard To compare: like > , it is judged that the current equipment under test has leakage risk and generates early warning information; like ≤ , then it is judged that the current device under test is normal.

[0041] In the above technical solution, the standard air tightness prediction parameters are obtained through the machine learning process, and the prediction of whether the equipment of the sealing tester has the risk of leakage is determined through comparative analysis, so as to carry out early warning processing.

[0042] As an embodiment of the present invention, the process in which the data analysis module executes the evaluation strategy according to the airtightness prediction parameters includes: By formula Calculate the evaluation coefficient ; in, is the total number of test samples, and ∈ ; For the The preset weight coefficients of the test samples; is the standard airtightness prediction parameter, and ≤ .

[0043] In the above technical solution, by setting the evaluation strategy and executing the evaluation and analysis process, the impact of the airtightness prediction parameter size on the airtightness problem is evaluated, and then the airtightness problem is determined according to the evaluation coefficient; specifically, the formula Calculate the evaluation coefficient ; Analyze the changes in the airtightness prediction parameters in the cumulative test samples, and determine the airtightness problem of the sealing test machine based on the evaluation coefficient obtained by calculation. Among them, the standard airtightness prediction parameter It is the standard data value obtained based on historical experience; the preset weight coefficient Those selected based on historical experience will not be described in detail here.

[0044] As an implementation mode of the present invention, judging whether there is a problem with the airtightness of the sealing test machine according to the evaluation result specifically includes: The evaluation coefficient With the preset evaluation coefficient threshold To compare: like < , it is judged that there is an airtightness problem in the sealing test machine and an alarm signal is generated; like ≥ , it is judged that there is no airtightness problem in the sealing test machine.

[0045] In the above technical solution, the evaluation results are judged by comparative analysis to determine if the evaluation coefficient Less than the evaluation coefficient threshold , it is considered that the sealing test machine has an airtightness problem and needs to be repaired. The inner surface contour image of the sealing cavity of the sealed space is identified to determine the structural defects. Otherwise, it is judged to be in normal state. Therefore, the sealing test machine does not have an airtightness problem.

[0046] As an embodiment of the present invention, the process of performing surface defect analysis on the inner surface contour image of the sealed cavity of the sealed space is as follows: Identify the inner surface contour image of the sealed cavity and perform grayscale processing; The Canny algorithm is used to extract the contour of the abnormal area in the inner surface contour image; Calculate the area S and perimeter C of the abnormal area contour by the formula Calculate the abnormal area structure value .

[0047] In the above technical scheme, the grayscale image of the inner surface contour image of the sealed cavity is identified, the contour of the test area in the image is screened, and the contour of the abnormal area is obtained by screening; and the shape characteristics of the contour of the abnormal area are calculated, and the structural value of the abnormal area is obtained by calculation to determine the defects of the inner surface contour of the sealed cavity, and then the leakage state of the cavity surface of the device under test is determined based on the defect feature analysis.

[0048] As an embodiment of the present invention, it also includes: The abnormal area structure value With preset threshold and For comparison, < : like ≤ , it is judged that there is a slight leakage on the cavity surface of the device under test in the sealed space; like < < , it is judged that there is moderate leakage on the cavity surface of the device under test in the sealed space; like ≥ , it is judged that there is a serious leakage on the cavity surface of the device under test in the sealed space.

[0049] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0050] The above specific embodiments of this specification are described. Other embodiments are within the scope of the attached documents. In some cases, the actions or steps recorded in this application can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0051] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined in this application, they shall all fall within the protection scope of the present invention.

Claims

1. An artificial intelligence-based air tightness monitoring system for a sealing tester, the sealing tester comprising a test sealing space and a water box; the test sealing space comprising a sealing cavity and a device under test; characterized in that: The system comprises: The sensor module is used to collect the air pressure change parameters of the device under test in the test sealed space in real time through the pressure sensor after the device under test is inflated; An image processing module is used to collect dynamic image information of bubbles in a water box connected to one side of the test sealed space through an air pipe by using a camera; and to obtain an image of the inner surface contour of the sealed cavity by using image processing technology; A model building module is used to input historical air pressure change parameters and historical bubble dynamic information images into a preset convolutional neural network model for training, build a prediction model, and obtain bubble motion parameters; A data analysis module is used to input the air pressure change parameters and bubble movement parameters obtained in real time into the prediction model for tracking and detection to obtain air tightness prediction parameters; And it is used to execute the evaluation strategy based on the airtightness prediction parameters, and judge whether there is a problem with the airtightness of the sealing test machine according to the evaluation results: If yes, it is determined that the air tightness in the current sealing test machine is unqualified, an alarm signal is generated, and a surface defect analysis is performed on the inner surface contour image of the sealing cavity of the sealed space; If not, it is judged that the air tightness in the current sealing test machine is qualified, and the air tightness monitoring continues; The display module is used to display the alarm results.

2. The air tightness monitoring system of a sealing test machine based on artificial intelligence according to claim 1, characterized in that: The air pressure change parameter is obtained in the following manner: S1, obtaining a first air pressure value at an air filling pipe opening in a sealed space; S2, obtaining a second air pressure value in the sealed space after the continuous inflation reaches a set time; S3, calculating the difference between the first air pressure value and the second air pressure value as the air pressure difference within the set time period; S4. Obtain a curve of the continuous time change of the air pressure difference within a preset time period, and calculate the slope of the curve to determine the air pressure change parameter.

3. The air tightness monitoring system for a sealing tester based on artificial intelligence according to claim 1, characterized in that: The steps for obtaining the bubble motion parameters are as follows: SS1, predetermine the time interval between adjacent frames of bubble dynamic images; SS2, obtaining the change in the number of bubbles in the bubble dynamic image of continuous frames within a preset time period and the change in the displacement distance of the bubbles corresponding to all time intervals; SS3, obtaining the bubble movement speed according to the change of bubble quantity and bubble displacement distance; SS4. Divide the movement rhythm in each time interval according to the bubble movement speed as the bubble movement parameter.

4. The air tightness monitoring system for a sealing tester based on artificial intelligence according to claim 1, characterized in that: The data analysis module inputs the air pressure change parameters and bubble movement parameters acquired in real time into the prediction model, and the specific process of tracking detection includes: The statistical airtightness-related features were encoded and normalized; The prediction model performs tracking detection to calculate the loss function between the predicted value of the airtightness-related feature and its target value; Automatically adjust the model parameters of the prediction model using the stochastic gradient descent algorithm to minimize the loss function; After multiple iterations, the prediction model converges and the airtightness prediction parameters are output.

5. The air tightness monitoring system for a sealing tester based on artificial intelligence according to claim 4 is characterized in that: The calculation method of the airtightness prediction parameter is: in, For the The airtightness prediction parameters of the test samples; is the preset function; is the preset first conversion function, is the second preset conversion function; For the The air pressure variation parameters of the test samples; is the standard air pressure variation parameter; For the The preset deviation value of the air pressure variation parameter of each test sample; For the Bubble motion parameters of the test samples; is the standard bubble motion parameter; For the The bubble motion parameters of the test samples are preset with deviation values.

6. The air tightness monitoring system for a sealing tester based on artificial intelligence according to claim 5, characterized in that: The airtightness prediction parameters The threshold value of the airtightness prediction parameter is consistent with the preset standard To compare: like > , it is judged that the current equipment under test has leakage risk and generates early warning information; like ≤ , then it is judged that the current device under test is normal.

7. The air tightness monitoring system for a sealing tester based on artificial intelligence according to claim 5, characterized in that: The process of the data analysis module executing the evaluation strategy according to the airtightness prediction parameters includes: By formula Calculate the evaluation coefficient ; in, is the total number of test samples, and ∈ ; For the The preset weight coefficients of the test samples; is the standard airtightness prediction parameter, and ≤ .

8. The air tightness monitoring system for a sealing tester based on artificial intelligence according to claim 7, characterized in that: The step of judging whether there is a problem with the airtightness of the sealing test machine according to the evaluation results specifically includes: The evaluation coefficient With the preset evaluation coefficient threshold To compare: like < , it is judged that there is an airtightness problem in the sealing test machine and an alarm signal is generated; like ≥ , it is judged that there is no airtightness problem in the sealing test machine.

9. The air tightness monitoring system of a sealing tester based on artificial intelligence according to claim 1, characterized in that: The process of performing surface defect analysis on the inner surface contour image of the sealed cavity of the sealed space is as follows: Identify the inner surface contour image of the sealed cavity and perform grayscale processing; The Canny algorithm is used to extract the contour of the abnormal area in the inner surface contour image; Calculate the area S and perimeter C of the abnormal area contour by the formula Calculate the abnormal area structure value .

10. The air tightness monitoring system of a sealing tester based on artificial intelligence according to claim 9, characterized in that: Also includes: The abnormal area structure value With preset threshold and For comparison, < : like ≤ , it is judged that there is a slight leakage on the cavity surface of the device under test in the sealed space; like < < , it is judged that there is moderate leakage on the cavity surface of the device under test in the sealed space; like ≥ , it is judged that there is a serious leakage on the cavity surface of the device under test in the sealed space.

Images