Method and apparatus for determining the end point of sealing of an oxide film on an aluminum profile

Abstract

The application is suitable for the technical field of aluminum profiles, and particularly relates to an aluminum profile oxidation film sealing end point determination method and device. The aluminum profile oxidation film sealing end point determination method comprises the following steps: continuously acquiring initial sealing hole images within a first preset time; based on multiple initial sealing hole images, a determination time is generated; after the determination time, an aluminum profile sealing hole determination image is acquired; and based on the aluminum profile sealing hole determination image, an aluminum profile sealing hole end time is obtained. The method can capture the dynamic evolution law of the sealing process, the determination time generated thereby can accurately match the key stage of the sealing process, and finally, the sealing end point of the aluminum profile sealing hole determination image acquired at the determination time is determined. The entire process does not need to continuously observe the sealing process, thereby reducing the data processing workload and operation load, and through real-time online monitoring, the sealing efficiency of the aluminum profile oxidation film is improved compared with the traditional determination method.

Description

Technical Field

[0001] This application belongs to the field of aluminum profile technology, and in particular relates to a method and equipment for determining the end point of oxide film sealing in aluminum profiles. Background Technology

[0002] Aluminum and aluminum alloys are widely used in construction, transportation, aerospace, and electronics due to their low density, high specific strength, excellent thermal and electrical conductivity, and good processability. However, aluminum is a chemically reactive metal that readily reacts with oxygen in the natural environment to form an oxide film. This natural oxide film is thin and porous, failing to effectively protect the aluminum profile substrate and easily leading to corrosion failure, severely impacting its service life and application safety. In industrial production, anodizing is typically used to prepare a uniform and dense artificial oxide film on the surface of aluminum profiles. However, the surface of the anodized oxide film contains numerous micropores, which can become channels for corrosive media to penetrate, reducing the protective effect of the oxide film. Therefore, sealing treatment is necessary. Sealing treatment is a crucial step following the anodizing process for aluminum profiles. Its core purpose is to fill and seal the pores of the oxide film using chemical or physical methods, further improving the density and corrosion resistance of the oxide film and ensuring the product quality of the aluminum profile.

[0003] In existing technologies, the commonly used methods for determining the endpoint of aluminum profile oxide film sealing mainly include traditional chemical titration, weighing, electrochemical testing, and manual visual observation. These methods are generally cumbersome and time-consuming, and require continuous observation or monitoring of the sealing process by humans or equipment before determination, resulting in low sealing efficiency and difficulty in meeting the needs of large-scale industrial production. Summary of the Invention

[0004] This application provides a method and equipment for determining the end point of sealing the oxide film on aluminum profiles, which can solve the problem that the existing sealing efficiency is not high and it is difficult to meet the needs of large-scale industrial production.

[0005] In a first aspect, embodiments of this application provide a method for determining the endpoint of oxide film sealing on aluminum profiles, including:

[0006] Initial sealing images are continuously acquired within a first preset time period; wherein, the initial sealing images are used to indicate the images of bubbles generated when the aluminum profile is immersed in the sealing liquid;

[0007] Based on multiple initial sealing images, a determination time is generated; wherein, the determination time is used to indicate the timing for determining the end point of the sealing.

[0008] After the aforementioned determination time, an aluminum profile sealing determination image is obtained; wherein, the aluminum profile sealing determination image is used to indicate the image on the surface of the aluminum profile oxide film;

[0009] Based on the sealing determination image of the aluminum profile, the sealing end time of the aluminum profile is obtained.

[0010] The technical solutions described in this application embodiment have at least the following technical effects:

[0011] The method for determining the sealing endpoint of aluminum profile oxide film provided in this application firstly acquires initial sealing images within a first preset time period to indicate the bubbles generated when the aluminum profile is immersed in the sealing liquid; then, based on multiple initial sealing images, a determination time is generated to indicate the timing for determining the sealing endpoint. When the determination time is reached, the sealing characteristics of the aluminum profile oxide film can more accurately reflect the current sealing process of the aluminum profile oxide film, thereby improving the accuracy of determining the sealing endpoint; after the first preset time ends and the determination time is reached, an aluminum profile sealing determination image is acquired to indicate the surface of the aluminum profile oxide film; finally, based on the aluminum profile sealing determination image, the sealing end time of the aluminum profile is obtained. This method captures the dynamic changes of bubbles generated during the sealing process by taking an initial sealing image within a first preset time period, thus capturing the dynamic evolution of the sealing process. The resulting judgment time can accurately match the key stages of the sealing process. Finally, the sealing endpoint is determined by taking the sealing judgment image of the aluminum profile obtained at the judgment time. The entire process does not require continuous observation of the sealing process, reducing the workload and computational load of data processing. That is, the phased acquisition and accurate judgment mode replaces continuous observation, greatly simplifying the amount of data acquisition and processing. Moreover, through real-time online monitoring, the sealing efficiency of the aluminum profile oxide film is improved compared with traditional judgment methods.

[0012] Secondly, embodiments of this application provide a system for determining the endpoint of oxide film sealing on aluminum profiles, including:

[0013] The first acquisition module is used to continuously acquire initial sealing images within a first preset time period; wherein, the initial sealing images are used to indicate the images of bubbles generated when the aluminum profile is immersed in the sealing liquid;

[0014] The first generation module is used to generate a determination time based on multiple initial sealing images; wherein the determination time is used to indicate the timing for determining the end point of the sealing.

[0015] The second acquisition module is used to acquire an aluminum profile sealing determination image after the determination time has elapsed; wherein, the aluminum profile sealing determination image is used to indicate the image on the surface of the aluminum profile oxide film;

[0016] The second generation module is used to obtain the sealing end time of the aluminum profile based on the sealing determination image of the aluminum profile.

[0017] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in any one of the first aspects above.

[0018] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any one of the first aspects above.

[0019] Fifthly, embodiments of this application provide a computer program product that, when run on an electronic device, causes the electronic device to execute the aluminum profile oxide film sealing endpoint determination method described in any of the first aspects above.

[0020] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating the method for determining the sealing endpoint of the aluminum profile oxide film according to an embodiment of this application.

[0023] Figure 2 This is a schematic diagram of the aluminum profile oxide film sealing endpoint determination system provided in the embodiments of this application;

[0024] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0025] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0026] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0027] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0028] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determination" or "if the described condition or event is detected" may be interpreted, depending on the context, as "once determination," "in response to determination," "once the described condition or event is detected," or "in response to the detection of the described condition or event."

[0029] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0030] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0031] In existing technologies, commonly used methods for determining the sealing endpoint of aluminum profile oxide films mainly include traditional chemical titration, weighing, electrochemical testing, and manual visual observation. These methods are generally cumbersome and time-consuming. With the development of image processing technology, online image detection has also been applied to the determination of the sealing endpoint of aluminum profile oxide films. However, this generally involves continuous acquisition, processing, and analysis of data during the sealing process, which can lead to a delay or advance in the determination, affecting the accuracy of the sealing endpoint determination. Furthermore, all of the above methods require continuous observation or monitoring of the sealing process by humans or equipment, resulting in low sealing efficiency and making it difficult to meet the needs of large-scale industrial production.

[0032] To address the aforementioned issues, this application provides a method and apparatus for determining the sealing endpoint of an aluminum profile oxide film. The method first involves continuously acquiring initial sealing images within a first preset time period, indicating the formation of bubbles when the aluminum profile is immersed in a sealing liquid. Then, based on multiple initial sealing images, a determination time is generated to indicate the timing for determining the sealing endpoint. Upon reaching the determination time, the sealing characteristics of the aluminum profile oxide film more accurately reflect the current sealing process, thereby improving the accuracy of the sealing endpoint determination. After the first preset time has elapsed until the determination time, an aluminum profile sealing determination image is acquired, indicating the surface of the aluminum profile oxide film. Finally, based on the aluminum profile sealing determination image, the sealing end time of the aluminum profile is obtained. This method captures the dynamic changes of bubbles generated during the sealing process by taking an initial sealing image within a first preset time period, thus capturing the dynamic evolution of the sealing process. The resulting judgment time can accurately match the key stages of the sealing process. Finally, the sealing endpoint is determined by taking the sealing judgment image of the aluminum profile obtained at the judgment time. The entire process does not require continuous observation of the sealing process, reducing the workload and computational load of data processing. That is, the phased acquisition and accurate judgment mode replaces continuous observation, greatly simplifying the amount of data acquisition and processing. Moreover, through real-time online monitoring, the sealing efficiency of the aluminum profile oxide film is improved compared with traditional judgment methods.

[0033] The method for determining the end point of aluminum profile oxide film sealing provided in this application embodiment can be applied to electronic devices. In this case, the electronic device is the executing subject of the method for determining the end point of aluminum profile oxide film sealing provided in this application embodiment. This application embodiment does not impose any restrictions on the specific type of electronic device.

[0034] For example, electronic devices can be desktop computers, tablets, laptops, mobile phones, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, personal digital assistants (PDAs), smart screens, smart TVs, and other terminal devices, handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, Internet of Things (IoT) terminals, computers, laptops, customer premises equipment (CPEs), and / or other devices used for communication over wireless systems, as well as next-generation communication systems, such as mobile terminals in 5G networks or mobile terminals in future evolved Public Land Mobile Networks (PLMNs).

[0035] To better understand the method for determining the end point of aluminum profile oxide film sealing provided in the embodiments of this application, the specific implementation process of the method for determining the end point of aluminum profile oxide film sealing provided in the embodiments of this application will be described by way of example below.

[0036] Figure 1 This paper presents a schematic flowchart illustrating a method for determining the endpoint of aluminum profile oxide film sealing according to an embodiment of this application. The method includes:

[0037] S100, continuously acquire initial sealing images within a first preset time period; wherein, the initial sealing images are used to indicate the images of bubbles generated when the aluminum profile is immersed in the sealing liquid.

[0038] It is understandable that the first preset time, the pre-set monitoring period, can be manually input, obtained from a sealing database, etc., but is not limited to these methods. The sealing database refers to a database containing information such as the type of sealing liquid (e.g., boiling water sealing liquid, chromate sealing liquid, nickel salt sealing liquid, etc.), oxide film thickness, and corresponding first preset time periods. This data can be obtained through laboratory experiments, on-site measurements and monitoring, and past experience. After acquisition, the collected data is organized, classified, and archived, useful information and patterns are extracted, and the relevant data is then saved to the database to form the sealing database. Initial sealing images can be acquired using industrial high-definition cameras or other imaging equipment, with the acquisition frequency set to 1-5 frames / second.

[0039] S200, based on multiple initial sealing images, generates a determination time; wherein, the determination time is used to indicate the timing for determining the end point of the sealing.

[0040] It is understandable that during the sealing process, the generation of bubbles is directly related to the degree of filling of the oxide film pores: In the initial stage of sealing, moisture and residual electrolyte in the oxide film pores react chemically with the sealing liquid, and a large amount of gas (such as hydrogen and carbon dioxide) escapes, resulting in a fast bubble generation rate, high density, and uneven particle size; as the pores are gradually filled with sealing products (such as aluminum hydroxide, chromium chromate, and nickel salt compounds), the reaction rate slows down, the bubble generation rate decreases, the density decreases, and the particle size tends to be more uniform; when the sealing process is close to the end, the amount of bubble generation is extremely small and tends to stabilize. Determining the timing essentially involves in-depth analysis of the bubble characteristics in the initial sealing image to pinpoint the key time points in the sealing process that best reflect the trend towards the end point.

[0041] For example, a bubble feature change curve can be obtained based on multiple initial sealing images, and then an effective bubble feature sequence can be obtained based on the initial bubble feature sequence. Finally, a judgment time can be generated through the effective bubble feature sequence. Alternatively, the peak generation rate and the corresponding peak time point can be extracted from the bubble feature change curve, and then the time required for the bubble generation rate to decay to a preset benchmark value (such as 30% of the peak value) can be calculated. Finally, the peak time point can be superimposed to obtain the judgment time, etc., but not limited to these methods.

[0042] In one possible implementation, in step S200, a determination time is generated based on multiple initial sealing images, including:

[0043] S210, based on multiple initial sealing images, obtain the bubble feature change curve.

[0044] It is understandable that for each frame of the initial sealing image, noise interference is eliminated through image preprocessing (such as grayscale conversion, Gaussian filtering, and binarization segmentation). Then, morphological operations (such as erosion and dilation) are used to separate the adhering bubbles. Subsequently, the core feature parameters of the bubbles are extracted. Then, the feature parameters extracted from each frame are arranged in the order of acquisition time to form a time-feature sequence (such as time-density sequence, time-particle size sequence, etc.). The time interval of the sequence is consistent with the image acquisition frequency (such as 1 second for 1 frame / second) so that the sequence can truly reflect the continuous change of bubble features over time. Finally, curve fitting and optimization are performed. Appropriate mathematical models (such as polynomial fitting, exponential fitting, and smooth spline fitting) are used to perform curve fitting on each feature sequence to eliminate feature fluctuations caused by random noise and obtain a smooth bubble feature change curve.

[0045] For example, an initial bubble feature sequence can be generated based on multiple initial sealing images. Then, based on the initial bubble feature sequence, a valid bubble feature sequence for generating the determination time is selected. Finally, a bubble feature change curve is obtained based on the valid bubble feature sequence. Alternatively, an initial bubble feature curve can be directly fitted based on multiple initial sealing images. Then, the initial bubble feature curve can be optimized using methods such as sliding window smoothing and extreme point correction to obtain the bubble feature change curve. That is, for the bubble features of each frame image, such as bubble density values, a polynomial fitting (2nd-3rd order polynomial) is used in time sequence to quickly obtain the initial density curve. Then, sliding window smoothing is used, with a window size of 5-10 frames. The initial density curve is calculated by moving average to smooth out local sharp fluctuations (such as the peak of a sudden increase in density in a certain frame being offset by the average of adjacent valid data within the window), making the curve tend to be flat. Then, extreme point correction is used to identify extreme points in the initial curve that exceed the reasonable range, and linear interpolation of adjacent valid data is used to replace them to obtain the bubble feature change curve.

[0046] In one possible implementation, in step S210, based on multiple initial sealing images, a bubble feature change curve is obtained, including:

[0047] S211, Based on multiple initial sealing images, generate an initial bubble feature sequence.

[0048] This can be understood as follows: the feature parameters extracted from each frame of the image are arranged sequentially according to the acquisition timestamp to form a structured time-series data sequence. Each record in the sequence contains fields such as timestamp, bubble density, average particle size, maximum particle size, minimum particle size, particle size standard deviation, bubble generation rate, average bubble roundness, and bubble coverage. For example: "20250801100001.000, 105 bubbles / cm², 0.32mm, 0.85mm, 0.12mm, 0.18mm, 8 bubbles / (cm²)". s), 0.75, 35%.

[0049] S212, based on the initial bubble feature sequence, obtain the effective bubble feature sequence.

[0050] For example, multi-feature classification can be performed based on the initial bubble feature sequence to obtain bubble density feature chains and bubble particle size feature chains; then, stability identification can be performed on the bubble density feature chains and bubble particle size feature chains to obtain density stable segments and particle size stable segments; finally, based on the density stable segments and particle size stable segments, an effective bubble feature sequence can be obtained; alternatively, a global trend curve can be generated first using the moving average method (window size 10 frames) to identify abnormal data segments in the sequence that deviate significantly from the global trend (such as the density value of a certain data segment deviating from the trend curve by more than 20%); then, invalid segments can be eliminated by combining process logic, such as feature missing segments caused by the reaction not starting in the early stage of sealing; finally, local optimization can be performed on the remaining effective data segments, and linear interpolation can be used to fill in a small number of missing data points to ensure the continuity and integrity of the sequence, and finally, an effective bubble feature sequence can be obtained.

[0051] In one possible implementation, step S212, based on the initial bubble feature sequence, obtains an effective bubble feature sequence, including:

[0052] S2121, based on the initial bubble feature sequence, multi-feature classification is performed to obtain the bubble density feature chain and the bubble particle size feature chain; among them, the bubble density feature chain is used to reflect the change in the distribution density of bubbles generated on the surface of aluminum profiles in the sealing liquid at different times, and the bubble particle size feature chain is used to reflect the change in the particle size distribution of bubbles at different times.

[0053] It is understandable that bubble density is directly related to the intensity of the sealing reaction; that is, the more vigorous the reaction, the more gas is generated and the higher the density. Bubble particle size distribution is closely related to the mass transfer efficiency of the sealing liquid and the stability of the reaction interface; that is, when the mass transfer efficiency is high, bubble generation and escape are more uniform, and the particle size distribution is more concentrated. For the bubble density feature chain, the bubble density value and density change rate (the difference between the current density and the density at the previous moment divided by the time interval) corresponding to each time stamp are extracted from the initial bubble feature sequence and arranged sequentially according to the time stamps, forming a three-dimensional feature chain of time-density-density change rate. For example, a record at a certain time stamp might be "00:00:05, 98 bubbles / cm², +4 bubbles / (cm²)". The density change rate is positive, indicating an increasing trend in bubble density and reflecting a stronger reaction intensity; conversely, a negative density change rate indicates a decreasing trend in bubble density and reflecting a weaker reaction intensity. For the bubble size characteristic chain, multi-dimensional particle size-related parameters can be extracted: such as average particle size (reflecting the overall size level of bubbles), particle size standard deviation (reflecting the uniformity of particle size distribution), and the proportion of particle size distribution intervals (e.g., the proportion of bubbles with diameters of 0.1-0.3 mm, 0.3-0.5 mm, and above 0.5 mm). These are arranged in time stamp order to form a four-dimensional characteristic chain of time-average particle size-particle size standard deviation-distribution proportion. For example, a record at a certain time stamp is "00:00:15, 0.28 mm, 0.11 mm, 72%, 25%, 3%", indicating that the average bubble size is small, the standard deviation is small, and small-diameter bubbles are dominant, reflecting that the sealing reaction has entered a relatively stable stage.

[0054] S2122, stability identification of bubble density characteristic chain and bubble particle size characteristic chain, to obtain density stable segment and particle size stable segment.

[0055] It can be understood that the core of the density stability stage is that the rate of change of bubble density approaches zero, meaning that the fluctuation range of bubble density per unit time is extremely small. This reflects that the gas generation rate in the sealing reaction has stabilized, and the pore filling of the oxide film has entered a gradual stage. The particle size stability stage, on the other hand, is characterized by the rate of change of bubble particle size approaching zero, with a uniform particle size distribution and no significant fluctuations. This indicates that the mass transfer efficiency of the sealing liquid and the reaction interface state have reached stability, and the bubble generation and escape patterns are consistent. These two stability stages are essentially key indicators of the transition from dynamic change to static stability in the sealing reaction. For example, the density fluctuation variance of the bubble density feature chain within a unit time can be compared with a first preset threshold. The time point when the density fluctuation variance is less than or equal to the first preset threshold is taken as the density segmentation point, and the segment of the bubble density feature chain after the density segmentation point is identified as the density stable segment. Similarly, the particle size fluctuation variance of the bubble particle size feature chain within a unit time can be compared with a second preset threshold. The time point when the particle size fluctuation variance is less than or equal to the second preset threshold is taken as the particle size segmentation point, and the segment of the bubble particle size feature chain after the particle size segmentation point is identified as the particle size stable segment. Alternatively, a sliding window of 10-15 seconds can be used to segment the density feature chain, and linear fitting can be performed on the density data within each window. The slope of the fitted line is calculated (the smaller the absolute value of the slope, the gentler the trend), and a slope threshold is set (e.g., ±0.1 particles / (cm²)). When the fitting slope of three consecutive windows meets the threshold requirement and the standard deviation of the density value within the window is less than or equal to the first preset threshold, the start time of the first window is taken as the density segmentation point. The identification logic for the stable particle size segment is the same, and it is determined by double verification of the window slope (e.g., ±0.005 mm / s) and standard deviation of the fitted average particle size.

[0056] In one possible implementation, step S2122 involves stability identification of the bubble density characteristic chain and the bubble particle size characteristic chain to obtain a density stable segment and a particle size stable segment, including:

[0057] S21221, compare the density fluctuation variance of the bubble density feature chain within a unit time with a first preset threshold, take the time point when the density fluctuation variance is less than or equal to the first preset threshold as the density segment point, and confirm the segment of the bubble density feature chain after the density segment point as the density stable segment.

[0058] It is understandable that the first preset threshold and unit time are pre-set values, which can be manually input, obtained from the sealing database, etc., but are not limited to these. The variance of bubble density fluctuation is the core quantitative indicator reflecting the dispersion of density data. The smaller the variance, the smoother the change in bubble density per unit time, indicating a more stable gas generation rate in the sealing reaction and a smoother pore filling stage in the oxide film. First, extract all density data (ρ1, ρ2, ..., ρ...) within a certain unit time. n Then calculate the mean density ρ = Σρ per unit time. i / n (n is the number of data points); then calculate the sum of squared deviations of each density data point from the mean Σ(ρ i -ρ)²; Finally, divide the sum of squared deviations by the number of data points n to obtain the density fluctuation variance σ per unit time. 密度 ²=Σ(ρ i -ρ)² / n. For example, if the mean density ρ=99 per unit time, the sum of squared deviations is (98-99)²+(100-99)²+(99-99)²+(101-99)²+(97-99)²+(99-99)²=1+1+0+4+4+0=10, and the variance σ 密度 ² = 10 / 6 ≈ 1.67 (pieces / cm²)².

[0059] S21222, compare the particle size fluctuation variance of the bubble particle size feature chain per unit time with the second preset threshold, take the time point when the particle size fluctuation variance is less than or equal to the second preset threshold as the particle size segment, and confirm the segment of the bubble particle size feature chain after the particle size segment as the particle size stable segment.

[0060] It is understandable that the second preset threshold is a pre-set value. Extract all average particle size data (d1, d2, ..., d...) within a certain unit of time. n The second step is to calculate the average particle size d = Σd within that unit of time. i / n; The third step is to calculate the sum of squared deviations Σ(d) of each average particle size data from the mean. i -d)²; Fourth step, divide the sum of squared deviations by the number of data points n to obtain the particle size fluctuation variance σ. 粒径 ²=Σ(d i -d)² / n. For example, the average particle size data per unit time are 0.28, 0.29, 0.27, 0.28, 0.29, 0.28 (mm), with a mean d=0.28. The sum of squares of the deviations is (0)²+(0.01)²+(-0.01)²+(0)²+(0.01)²+(0)²=0.0003, and the variance σ 粒径 ²=0.0003 / 6=0.00005 (mm)².

[0061] This setup, by independently setting a first preset threshold and a second preset threshold, and using a quantitative method that compares the fluctuation variance per unit time with the preset threshold, identifies the stability of the bubble density feature chain and the bubble particle size feature chain to determine the density stable segment and the particle size stable segment. This adapts to the different process fluctuation characteristics of the two types of features, density and particle size, and reduces the risk of judgment timing deviation.

[0062] S2123, based on the density stable segment and the particle size stable segment, obtains an effective bubble characteristic sequence.

[0063] For example, by aligning the density-stable segment and the particle size-stable segment along the time axis, continuous feature segments that overlap in the time dimension can be selected as effective feature segments. Then, feature association can be performed on the effective feature segments to obtain an effective bubble feature sequence. Alternatively, the feature parameters of the density-stable segment and the particle size-stable segment can be matched one by one according to the timestamp, retaining the time point data where both types of features meet the stability condition, eliminating isolated data points where only a single feature is stable, and then filling in a small number of missing matching data through linear interpolation to form an effective bubble feature sequence, and so on, but not limited to these methods.

[0064] This setup first splits the initial sequence into two core feature chains: density and particle size, focusing on the variation patterns of the sealing reaction intensity and mass transfer efficiency, respectively, reducing mutual interference between different features. Then, through stability identification, segments in which both types of features tend to be stable are selected, so that the effective data can truly reflect the smooth stage of the sealing reaction, providing a high-quality basis for subsequent bubble feature change curve fitting and determination time generation.

[0065] In one possible implementation, in step S2123, based on the density stability segment and the particle size stability segment, an effective bubble characteristic sequence is obtained, including:

[0066] S21231: Align the density-stable segment and the particle size-stable segment along the time axis, and select continuous feature segments that overlap in the time dimension as effective feature segments.

[0067] It can be understood that, taking the initial acquisition time of the sealing image as zero, all feature data of the density-stable segment and the particle size-stable segment are uniformly mapped onto the same time axis according to the timestamp (accurate to milliseconds). For example, the density value at t=21.2 seconds in the density-stable segment and the average particle size value at t=21.2 seconds in the particle size-stable segment are perfectly aligned on the time axis. By traversing the feature chain data, the start time t1_start and end time t1_end (which is the first preset end time t_total) of the density-stable segment, as well as the start time t2_start and end time t2_end (also t_total) of the particle size-stable segment, are recorded. For example, t1_start = 15 seconds, t1_end = 60 seconds; t2_start = 23 seconds, t2_end = 60 seconds. The time overlap region is recalculated: the start time of the overlap region is the maximum of the start times of the two stable segments [t_overlap_start=max(t1_start,t2_start)], and the end time is the minimum of the end times of the two stable segments [t_overlap_end=min(t1_end,t2_end)]. t_overlap_start=max(15,23)=23 seconds, t_overlap_end=min(60,60)=120 seconds, therefore the overlap time region is 23 seconds to 60 seconds. Finally, continuous feature segments are extracted from the overlap region: all density feature data (density value, density change rate) from t_overlap_start to t_overlap_end are extracted from the density stable segment, and all particle size feature data (average particle size, particle size standard deviation, distribution percentage) within the same time range are extracted from the size stable segment. The two types of data are matched one-to-one by timestamp to form continuous feature segments, i.e., effective feature segments.

[0068] S21232, perform feature association on the effective feature segments to obtain the effective bubble feature sequence.

[0069] This setup first locks overlapping, continuous feature segments with stable density and particle size by aligning the time axis, eliminating interfering data with only a single stable feature, so that the effective feature segments can truly reflect the synergistic stability of the sealing reaction; then, it establishes the intrinsic relationship between density and particle size through feature correlation, so that the effective bubble feature sequence can comprehensively characterize the synergistic law of bubble dynamic changes, providing a high-quality basis for subsequent bubble feature change curve fitting and determination time generation.

[0070] S213, based on the effective bubble feature sequence, the bubble feature change curve is obtained.

[0071] This setup first generates an initial bubble feature sequence containing complete dynamic information based on multiple frames of initial sealing images. Then, through purification processing of the effective bubble feature sequence, invalid data such as instantaneous fluctuations are eliminated, while retaining the core information that can truly reflect the sealing reaction law. Finally, a bubble feature change curve is constructed based on the purified effective sequence, so that the curve can accurately depict the real evolution trend of bubble features and provide a reliable basis for determining the time generation.

[0072] S220 generates a determination time based on the bubble characteristic change curve.

[0073] For example, the peak value of bubble generation rate and the corresponding peak time point can be extracted based on the bubble characteristic change curve, and then the judgment time can be generated based on the peak value of bubble generation rate and the peak time point; alternatively, multiple key features of the curve (peak value, inflection point, duration of stable segment) can be extracted and weighted, for example, the peak value contributes 40%, the inflection point contributes 30%, and the stable segment contributes 30%, and the judgment time is obtained by combining them.

[0074] This setup, through feature extraction and curve fitting of multiple initial sealing images, fully depicts the dynamic evolution of core parameters such as bubble density and particle size, making the sealing reaction process visible and quantitative, and providing objective data support for the generation of the judgment time. Furthermore, based on the key features of the curve (such as peaks, inflection points, and stable segments), the judgment node is locked, providing a scientific basis for the generation of the judgment time and improving the consistency and reliability of the sealing endpoint judgment.

[0075] In one possible implementation, step S220 involves generating a determination time based on the bubble characteristic change curve, including:

[0076] S221, based on the bubble characteristic change curve, extract the peak value of bubble generation rate and the corresponding peak time point.

[0077] It is understandable that the bubble formation rate is directly related to the real-time intensity of the sealing reaction. In the initial stage of sealing, a large number of oxide film pores are exposed, reacting violently with the sealing liquid, and the bubble formation rate rises rapidly. When the reaction reaches its most vigorous state, the formation rate reaches its peak. Subsequently, the pores are gradually filled by the sealing product, the reaction rate slows down, the formation rate decreases and tends to stabilize. The peak value is the critical transition point from rapid to gradual slowdown in the sealing reaction, and the peak time point is the specific time sequence of this critical state. The formation rate within that time period is obtained by dividing the density difference between two adjacent time stamps by the time interval (positive when density increases, negative when density decreases; a negative rate indicates that the bubble escape rate is greater than the formation rate). For example, if the density is 90 bubbles / cm² at time t1 and 102 bubbles / cm² at time t2 (t2-t1=1 second), then the formation rate is 12 bubbles / cm². By comparing the generation rates of all adjacent timestamps, the peak value of the bubble generation rate and the corresponding peak time point can be obtained.

[0078] S222, the generation determination time is based on the peak value of the bubble generation rate and the peak time point.

[0079] It is understandable that the peak value of the bubble formation rate reflects the maximum intensity of the sealing reaction. The larger the peak value, the more vigorous the initial reaction, the faster the pore filling rate, and the shorter the required subsequent stabilization transition time. Conversely, the smaller the peak value, the more gradual the reaction, and the longer the required transition time. The timing of the peak bubble formation rate reflects the progress rhythm of the reaction system. The earlier the peak value appears, the faster the reaction starts and the higher the initial pore filling efficiency. The later the peak value appears, the slower the reaction starts or the presence of early interference. For example, a base judgment time can be matched based on the peak time point, and an adjustment coefficient can be applied based on the peak bubble formation rate generation time. Then, a judgment time can be generated based on the base judgment time and the time adjustment coefficient. Alternatively, an exponential decay model can be established based on the peak value to calculate the time required for the formation rate to decay from the peak value to a preset benchmark value (such as 30% of the peak value). This time can then be superimposed on the peak time point to obtain the judgment time, and so on, but not limited to these methods.

[0080] This setup, by extracting the peak value of bubble formation rate and its corresponding peak time point from the bubble characteristic change curve, and quantifying and deriving the judgment time based on these two factors, achieves precise, dynamic, and process-adaptive judgment time generation, effectively improving the accuracy and consistency of the determination of the sealing endpoint of aluminum profile oxide film. The peak value of bubble formation rate directly reflects the maximum intensity of the sealing reaction, and the peak time point accurately anchors the core timing node of the reaction transitioning from intense to gradual. The combination of these two factors can fully conform to the objective laws of pore filling rate and reaction process rhythm in the sealing reaction, and can dynamically generate an adaptive judgment time according to the differences in reaction intensity and start-up efficiency under different working conditions.

[0081] In one possible implementation, in step S222, a determination time is generated based on the peak bubble generation rate and the peak time point, including:

[0082] S2221, based on the basic judgment time corresponding to the peak time point.

[0083] It is understandable that different peak points correspond to a basic decision time. For example, this can be achieved by matching the peak time points with the corresponding basic decision times in a sealing database; alternatively, the peak time points can be input into a learning model, which outputs the corresponding basic decision times, and so on, but is not limited to these methods. The learning model is trained using multiple sets of training data, each set of which includes a peak time point and its corresponding basic decision time.

[0084] S2222, adjustment coefficient based on peak bubble generation rate.

[0085] It is understood that different peak bubble formation rates correspond to a time adjustment factor. For example, the peak bubble formation rate can be matched with the corresponding time adjustment factor in a sealing database; or the peak bubble formation rate can be input into a learning model, and the learning model can output the corresponding time adjustment factor, etc., but not limited to these.

[0086] S2223, Generate the decision time based on the basic decision time and the time adjustment coefficient.

[0087] It is understandable that the judgment time = basic judgment time × time adjustment coefficient.

[0088] This setup anchors the baseline judgment time to the peak time point, aligning with the varying pace of the sealing reaction. An earlier peak occurs, the more closely the baseline judgment time matches the rapid start-up of the reaction; a later peak occurs, adapting to a slower start-up or conditions with initial interference, ensuring the rationality of the baseline judgment time sequence. On the other hand, a dedicated time adjustment coefficient is generated based on the peak bubble formation rate, enabling dynamic correction of the baseline judgment time. A larger peak results in a shorter transition time, adapting to more vigorous reaction conditions with faster pore filling rates; a smaller peak results in a longer transition time, adapting to milder reaction conditions with slower pore filling rates. This technical solution quantifies and collaboratively calculates the two core influencing factors: reaction pace and reaction intensity. It can generate highly adaptive judgment times for different oxide film pore states and varying sealing liquid reactivity, ensuring that the judgment time corresponds to the optimal node when the sealing reaction enters the stable prediction stage, providing a highly accurate timing basis for subsequent sealing endpoint determination.

[0089] S300, after the determination time, acquire the aluminum profile sealing determination image; wherein, the aluminum profile sealing determination image is used to indicate the image of the aluminum profile oxide film surface.

[0090] It is understandable that images of aluminum profile sealing can intuitively and completely present the true state of the aluminum profile oxide film surface, clearly indicating characteristics such as residual bubbles, pore filling, and adhesion of sealing products on the oxide film surface. These images can be acquired using cameras or other imaging devices.

[0091] S400, based on the aluminum profile sealing determination image, obtains the sealing end time of the aluminum profile.

[0092] For example, sealing features can be extracted from the sealing judgment image of aluminum profiles, and the remaining sealing time can be obtained based on the sealing features. Then, the remaining sealing time can be accumulated on the judgment time to obtain the sealing end time node. Alternatively, the feature parameters of the sealing judgment image can be directly compared with the preset sealing compliance threshold to obtain the feature parameter difference. The sealing interval time can be calculated based on the feature parameter difference to obtain the sealing end time, and so on, but not limited to these.

[0093] In one possible implementation, in step S400, based on the aluminum profile sealing determination image, the sealing end time of the aluminum profile is obtained, including:

[0094] S410: Extract sealing features from aluminum profile sealing determination image, and obtain remaining sealing time based on sealing features.

[0095] It is understandable that converting the intuitive visual information of the sealing judgment image into quantified process feature parameters, and then deriving the remaining sealing time through the mapping relationship between features and time, is the core quantitative step in determining the sealing end time. The sealing features extracted from the sealing judgment image cover core indicators such as the pore filling rate of the oxide film surface, the residual bubble density, the uniformity of sealing product adhesion, and the film smoothness. These features are strongly correlated with the completion of the sealing reaction. Higher pore filling rate, lower residual bubble density, and more uniform distribution of sealing products indicate that the sealing process is closer to the end, and the required remaining sealing time is shorter; conversely, a longer remaining sealing time is required. By pre-establishing a quantitative mapping model of sealing features and remaining sealing time based on massive process data, the extracted feature parameters can be substituted into the model to directly output the accurate remaining sealing time required to meet the sealing quality standards.

[0096] S420, the sealing end time of the aluminum profile is obtained based on the remaining sealing time.

[0097] It can be understood that the sealing end time = judgment time + remaining sealing time.

[0098] This setup, through a layered judgment logic that extracts sealing features to deduce the remaining sealing time and determines the sealing end time based on the remaining sealing time, achieves the quantification and precise determination of the sealing end time for aluminum profiles. Relying on the intuitive features of the sealing judgment image, the final anchoring of the sealing endpoint is completed, providing a clear and practical time basis for starting and stopping the sealing process, effectively improving the operability and standardization of sealing endpoint determination. At the same time, by strongly binding the sealing end time with the sealing features, the endpoint can be strictly deduced based on the actual sealing state of the oxide film surface, ensuring that the sealing process always matches the actual progress of oxide film pore filling, balancing the sealing quality and production efficiency of aluminum profiles.

[0099] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0100] Corresponding to the aluminum profile oxide film sealing endpoint determination method described in the above embodiments, this application also provides an aluminum profile oxide film sealing endpoint determination system, the various modules of which can realize the various steps of the aluminum profile oxide film sealing endpoint determination method. Figure 2 The diagram shows a structural block diagram of the aluminum profile oxide film sealing endpoint determination system provided in the embodiments of this application. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0101] Reference Figure 2 The aluminum profile oxide film sealing endpoint determination system includes:

[0102] The first acquisition module is used to continuously acquire initial sealing images within a first preset time period; wherein, the initial sealing images are used to indicate the images of bubbles generated when the aluminum profile is immersed in the sealing liquid.

[0103] The first generation module is used to generate a determination time based on multiple initial sealing images; wherein the determination time is used to indicate the timing for determining the end point of the sealing.

[0104] The second acquisition module is used to acquire an aluminum profile sealing determination image after a determination time has elapsed; wherein, the aluminum profile sealing determination image is used to indicate the image of the aluminum profile oxide film surface.

[0105] The second generation module is used to obtain the sealing end time of the aluminum profile based on the sealing judgment image.

[0106] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0107] Those skilled in the art will understand that, for the sake of convenience and brevity, the above-described module division is merely an example. In practical applications, the above functions can be assigned to different modules as needed, that is, the internal structure of the system can be divided into different modules to complete all or part of the functions described above. The modules in the embodiments can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0108] This application also provides an electronic device. Figure 3 This is a schematic diagram of the structure of an electronic device 6 provided in an embodiment of this application. Figure 3 As shown, the electronic device 6 of this embodiment includes: at least one processor 60 ( Figure 3 Only one is shown in the image), at least one memory 61 ( Figure 3 (Only one is shown in the image) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, it causes the electronic device 6 to perform the steps in any of the above embodiments of the aluminum profile oxide film sealing endpoint determination method, or causes the electronic device 6 to perform the functions of each module in the above system embodiments.

[0109] For example, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 62 in the electronic device 6.

[0110] The electronic device 6 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. This electronic device may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that... Figure 3 This is merely an example of electronic device 6 and does not constitute a limitation on electronic device 6. It may include more or fewer components than shown, or combine certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0111] The processor 60 can be a Central Processing Unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0112] In some embodiments, the memory 61 may be an internal storage unit of the electronic device 6, such as a hard disk or memory of the electronic device 6. In other embodiments, the memory 61 may be an external storage device of the electronic device 6, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 6. Furthermore, the memory 61 may include both internal and external storage units of the electronic device 6. The memory 61 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory 61 can also be used to temporarily store data that has been output or will be output.

[0113] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0114] This application provides a computer program product that, when run on an electronic device 6, causes the electronic device to perform the steps in any of the above method embodiments.

[0115] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to an electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0116] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0117] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0118] In the embodiments provided in this application, it should be understood that the disclosed devices and systems can be implemented in other ways. For example, the embodiment of the aluminum profile oxide film sealing endpoint determination system described above is merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0119] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0120] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for determining the endpoint of oxide film sealing on aluminum profiles, characterized in that, include: Initial sealing images are continuously acquired within a first preset time period; wherein, the initial sealing images are used to indicate the images of bubbles generated when the aluminum profile is immersed in the sealing liquid; Based on multiple initial sealing images, a determination time is generated; wherein, the determination time is used to indicate the timing for determining the end point of the sealing. After the aforementioned determination time, an aluminum profile sealing determination image is obtained; wherein, the aluminum profile sealing determination image is used to indicate the image on the surface of the aluminum profile oxide film; Based on the aluminum profile sealing determination image, the sealing end time of the aluminum profile is obtained; The step of generating a determination time based on multiple initial sealing images includes: Based on multiple initial sealing images, a bubble feature change curve is obtained; Based on the bubble characteristic change curve, a determination time is generated; The step of obtaining the bubble feature change curve based on multiple initial sealing images includes: Based on multiple initial sealing images, an initial bubble feature sequence is generated; Based on the initial bubble feature sequence, an effective bubble feature sequence is obtained; Based on the effective bubble feature sequence, the bubble feature change curve is obtained; The process of obtaining an effective bubble feature sequence based on the initial bubble feature sequence includes: Based on the initial bubble feature sequence, multi-feature classification is performed to obtain a bubble density feature chain and a bubble particle size feature chain; wherein, the bubble density feature chain is used to reflect the change in the distribution density of bubbles generated on the surface of aluminum profiles in the sealing liquid at different times, and the bubble particle size feature chain is used to reflect the change in the particle size distribution of bubbles at different times. Stability identification is performed on the bubble density characteristic chain and the bubble particle size characteristic chain to obtain density stable segment and particle size stable segment; Based on the density stability segment and the particle size stability segment, an effective bubble characteristic sequence is obtained.

2. The method for determining the end point of oxide film sealing on aluminum profiles as described in claim 1, characterized in that, The step of identifying the stability of the bubble density characteristic chain and the bubble particle size characteristic chain to obtain a density stable segment and a particle size stable segment includes: The density fluctuation variance of the bubble density feature chain per unit time is compared with a first preset threshold. The time point when the density fluctuation variance is less than or equal to the first preset threshold is taken as the density segment point, and the segment of the bubble density feature chain after the density segment point is identified as the density stable segment. The variance of the bubble particle size characteristic chain within a unit time is compared with a second preset threshold. The time point when the variance of the particle size fluctuation is less than or equal to the second preset threshold is taken as the particle size segmentation point, and the segment of the bubble particle size characteristic chain after the particle size segmentation point is identified as the particle size stable segment.

3. The method for determining the end point of oxide film sealing on aluminum profiles as described in claim 1, characterized in that, The effective bubble characteristic sequence obtained based on the density stability segment and the particle size stability segment includes: Align the density-stable segment and the particle size-stable segment along the time axis, and select continuous feature segments that overlap in the time dimension as effective feature segments; The effective feature segments are correlated to obtain an effective bubble feature sequence.

4. The method for determining the end point of oxide film sealing on aluminum profiles as described in claim 1, characterized in that, The step of generating a determination time based on the bubble characteristic change curve includes: Based on the bubble characteristic change curve, extract the peak value of bubble generation rate and the corresponding peak time point; The generation determination time is determined based on the peak bubble generation rate and the peak time point.

5. The method for determining the end point of oxide film sealing on aluminum profiles as described in claim 4, characterized in that, The generation of a determination time based on the peak bubble generation rate and the peak time point includes: Based on the peak time point, match the corresponding basic judgment time; Based on the peak generation time adjustment coefficient of the bubble generation rate; A determination time is generated based on the basic determination time and the time adjustment coefficient.

6. The method for determining the end point of oxide film sealing on aluminum profiles as described in claim 1, characterized in that, The step of obtaining the sealing end time of the aluminum profile based on the sealing determination image includes: Based on the image of the aluminum profile sealing determination, the sealing features are extracted, and the remaining sealing time is obtained based on the sealing features; The sealing end time of the aluminum profile is obtained based on the remaining sealing time.

7. An electronic device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as claimed in any one of claims 1 to 6.

Images