A leak detection system for a steel drum automatic production line

Abstract

The present application relates to the technical field of detection, and more particularly to a leak detection system of a steel pail automatic production line, comprising: an image acquisition module; a feature extraction module; a type determination module; a data analysis module; in the present application, abnormal features and dynamic leakage trend features in image information are extracted to determine the leakage tendency type of the steel pail, the leakage detection method for the steel pail is determined based on the leakage tendency type of the steel pail, abnormal features such as seal rubber ring tearing are locked through image recognition, and actual leakage is verified in combination with the pressure attenuation method or cooperative detection, so as to avoid the missed judgment of potential leakage by single visual detection or the misjudgment of single pressure detection disturbed by temperature, a temperature compensation mechanism is introduced in a targeted manner, a dynamic adaptive compensation strategy is adopted through the time interval of pressure and ultrasonic signals, the influence of environmental temperature fluctuation on pressure detection is effectively eliminated, and especially in the scene of multiple leakage points and large temperature gradient, the detection precision is greatly improved.

Description

Technical Field

[0001] This invention relates to the field of detection technology, and in particular to a leak detection system for an automated steel bucket production line. Background Technology

[0002] The processes used in steel drum production are extensive and can be broadly categorized into three main types: machining, welding, and coating. Existing leak detection technologies on steel drum production lines primarily rely on single detection methods (such as pressure attenuation, ultrasonic testing, and machine vision). Current systems employ the same detection methods for all steel drums without dynamically adjusting the detection scheme based on the actual condition of the drum (such as the degree of surface defects and the level of leakage risk), resulting in low detection efficiency or excessively high costs.

[0003] Chinese Patent Application No. CN202211380752.6 discloses a high-definition method for detecting impurities in steel buckets, comprising the following steps: pre-filtering a diluent to improve its purity; pouring the pre-filtered diluent into the steel bucket to be tested; sealing the bucket opening and shaking it thoroughly to clean the inside; cutting and folding a filter cloth into a funnel shape, and pouring the cleaned diluent from the steel bucket through this funnel-shaped filter cloth; maintaining the funnel-shaped filter cloth, immersing it in a container holding the diluent and then lifting it up, completing the immersion and lifting process at least twice to concentrate the sediment in the bottom corner of the filter cloth; cutting off a section from the sediment-containing area of ​​the funnel-shaped filter cloth, flattening the cut section, and placing it between two glass slides; observing the glass slides and comparing them with a standard slide to determine whether they are qualified. This application can quickly clean and detect impurities in steel buckets, ensuring the cleanliness of the paint inside the bucket.

[0004] However, existing technologies still have the following problems:

[0005] The same testing method was used for all steel buckets without dynamically adjusting the testing plan according to the actual condition of the buckets (such as the degree of surface defects and the level of leakage risk), resulting in low testing efficiency or excessive cost. Summary of the Invention

[0006] To address this issue, the present invention provides a leak detection system for an automated steel bucket production line, which overcomes the problem in the prior art that uses the same detection method for all steel buckets without dynamically adjusting the detection scheme according to the actual condition of the bucket (such as the degree of surface defects and the level of leakage risk), resulting in low detection efficiency or excessive cost.

[0007] To achieve the above objectives, the present invention provides a leak detection system for an automated steel drum production line. It includes:

[0008] The image acquisition module is used to acquire image information of the exterior of the steel bucket;

[0009] A feature extraction module, which is connected to the image acquisition module, is used to extract abnormal features and dynamic leakage trend features from the image information;

[0010] A type determination module, which is connected to the feature extraction module, is used to determine the leakage tendency type of the steel bucket based on the number of extracted abnormal features;

[0011] A data analysis module, connected to the image acquisition module, the feature extraction module, and the type determination module, is used to determine the leak detection method for the steel bucket based on its leakage tendency type, including:

[0012] Leakage testing of the steel bucket was performed using the pressure attenuation method.

[0013] Alternatively, based on the dynamic leakage trend characteristics of the steel bucket, determine whether to adopt a collaborative detection method. If a collaborative detection method is adopted, calculate the time interval between the time node of the pressure micro-fluctuation and the time interval between the ultrasonic sensor capturing the corresponding leak signal, and determine the temperature compensation mechanism based on the time interval.

[0014] Furthermore, the type determination module is used to determine the leakage tendency type of the steel bucket based on the number of extracted abnormal features, including:

[0015] If the number of abnormal features is greater than or equal to the preset number, the type determination module determines that the leakage tendency type of the steel bucket is a strong leakage tendency.

[0016] If the number of abnormal features is less than the preset number, the type determination module determines that the leakage tendency type of the steel bucket is weak leakage tendency.

[0017] Furthermore, the data analysis module is used to determine the leak detection method for the steel bucket based on the leakage tendency type of the steel bucket, including:

[0018] If the leakage tendency of the steel bucket is strong, the data analysis module determines that the pressure decay method should be used to detect the leakage of the steel bucket.

[0019] If the leakage tendency type of the steel bucket is weak leakage tendency, the data analysis module determines whether to adopt a collaborative detection method based on the dynamic leakage tendency characteristics of the steel bucket. Under the condition of adopting the collaborative detection method, the time interval between the time node of the pressure micro-fluctuation and the time interval between the ultrasonic sensor capturing the corresponding leak point signal is calculated, so as to determine the temperature compensation mechanism based on the time interval.

[0020] Furthermore, the abnormal features extracted from the image information by the feature extraction module include: holes, pits, scratches, and features such as tearing, wear, and aging cracking of the rubber ring.

[0021] Furthermore, the dynamic leakage trend features extracted by the feature extraction module in the image information include: the expansion trend of cracks or damage, and the features of the sealing ring deforming over time, aging, or the decrease in the fit between the sealing ring and the sealing surface due to micro-deformation of the barrel.

[0022] Furthermore, the data analysis module is used to determine whether to adopt a collaborative detection method based on the dynamic leakage trend characteristics of the steel bucket, including:

[0023] If the steel bucket exhibits a dynamic leakage tendency, the data analysis module determines to use a collaborative detection method.

[0024] If the steel bucket does not exhibit dynamic leakage characteristics, the data analysis module determines that the steel bucket should be leak-tested using the vacuum chamber static pressure difference precision measurement method.

[0025] Furthermore, the data analysis module is used to determine a temperature compensation mechanism based on the time interval, including:

[0026] If the time interval is greater than the first preset time interval and less than or equal to the second preset time interval, the data analysis module determines to adopt the overall temperature compensation mechanism.

[0027] If the time interval is greater than the second preset time interval, the data analysis module determines to adopt the partition temperature compensation mechanism.

[0028] Furthermore, the data analysis module performs overall temperature compensation based on the overall internal temperature of the steel bucket and the gas state equation, calculating the temperature-pressure correction coefficient.

[0029] Furthermore, the data analysis module divides the steel bucket into several regions, and calculates pressure correction values ​​based on real-time temperature data of several regions, and obtains correction coefficients by weighted summation.

[0030] Furthermore, the collaborative detection method involves using a vacuum chamber static pressure difference precision measurement method and an ultrasonic detection method to perform leak detection on the steel bucket.

[0031] Compared with the prior art, the beneficial effects of the present invention are as follows: In the present invention, abnormal features such as tearing of sealing rings are locked by image recognition, and the actual leakage is verified by pressure attenuation method or collaborative detection. This avoids the omission of potential leakage by single visual detection or the misjudgment of single pressure detection due to temperature interference. A targeted temperature compensation mechanism is introduced. Through the dynamic adaptation compensation strategy of pressure and ultrasonic signal time interval, the influence of ambient temperature fluctuation on pressure detection is effectively eliminated. Especially in scenarios with multiple leak points and large temperature gradients, the detection accuracy is greatly improved.

[0032] Furthermore, in this invention, a quantitative correlation between the "number of abnormal features" and the "actual leakage probability" is established through historical data statistics, making the setting of the preset quantity more scientific rather than subjective experience. Considering that the quality requirements of different production lines (such as chemical drums and ordinary packaging drums) are different, the preset quantity can be customized through historical data to match the classification of leakage tendency types with the risk level of product use (such as a lower preset quantity for chemical drums, which triggers the strong leakage tendency judgment earlier).

[0033] Furthermore, in this invention, for steel buckets with a strong tendency to leak (such as those with multiple holes, severe tearing of the rubber ring, or other high-frequency abnormal features), the pressure attenuation method is directly adopted. This method is simple to operate and has a fast response, and can verify whether there is obvious leakage (such as a rapid drop in pressure) in a short time. It is suitable for rapid screening in high-risk scenarios and avoids delays in the production line due to complex testing procedures. For steel buckets with a weak tendency to leak (such as only 1-2 minor scratches or slight wear of the rubber ring), the testing method is determined by combining dynamic leakage trend characteristics (such as whether the crack is expanding or whether the rubber ring fit is decreasing). When there is no dynamic trend, the vacuum chamber static pressure difference precision measurement method is adopted, which focuses on the accurate identification of minute leaks. When there is a dynamic trend, collaborative detection is enabled and temperature compensation is optimized through time intervals. This ensures the detection accuracy while avoiding the overuse of high-end equipment for low-risk buckets, thus balancing the detection cost and reliability.

[0034] Furthermore, in this invention, for steel buckets exhibiting dynamic leakage tendencies, a collaborative detection method is employed. This method combines the high precision of the vacuum chamber static pressure difference measurement method (capable of identifying minute leaks) with the location capability of ultrasonic detection (locking the leak point location), along with a temperature compensation mechanism to eliminate environmental interference. This ensures accurate assessment of "developing risks" and avoids missed detections due to insufficient detection methods (e.g., using only the static pressure difference method may overlook instantaneous leaks caused by crack propagation). For steel buckets without dynamic leakage tendencies (e.g., stable abnormal characteristics, no propagation, or accelerated aging trend), the lower-cost and simpler-to-operate vacuum chamber static pressure difference measurement method can meet the requirements, reducing detection costs while ensuring detection accuracy.

[0035] Furthermore, in this invention, for statically placed steel buckets without significant temperature gradients (such as weakly inclined buckets without dynamic leakage tendency characteristics), overall temperature compensation does not require partitioned calculations. Correction can be completed solely through a single volume and overall temperature, which is suitable for the real-time detection needs of automated production lines. This avoids complex algorithms slowing down the detection pace. The system automatically selects the compensation method based on the time interval between the pressure and ultrasonic signals. When the time interval is short (few leakage points, small temperature gradient), overall compensation is used (efficient), while when the time interval is long (many leakage points, large gradient), partitioned compensation is used (accurate). This ensures both the detection speed in simple scenarios and the accuracy requirements in complex scenarios. Attached Figure Description

[0036] Figure 1 This is a structural block diagram of the leak detection system for the automatic steel bucket production line of the present invention.

[0037] Figure 2 Flowchart for determining the leakage tendency type of the steel bucket;

[0038] Figure 3 A flowchart for determining the leakage detection method for steel buckets;

[0039] Figure 4 A flowchart for determining whether to use a collaborative detection method. Detailed Implementation

[0040] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0041] It should be noted that the data in this embodiment are all derived from a comprehensive analysis and evaluation of historical data from the six months prior to this determination and the corresponding historical determination results by the system described in this invention. Those skilled in the art will understand that the system described in this invention can determine the above-mentioned parameters for a single item by selecting the value with the highest proportion based on the data distribution as the preset standard parameter, using weighted summation to obtain the value as the preset standard parameter, substituting each historical data point into a specific formula and using the value obtained by that formula as the preset standard parameter, or other selection methods, as long as the system described in this invention can clearly define different specific situations in the single-item determination process through the obtained values.

[0042] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0043] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0044] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0045] Please see Figure 1-4 As shown, Figure 1 This is a structural block diagram of the leak detection system for the automatic steel bucket production line of the present invention. Figure 2 Flowchart for determining the leakage tendency type of the steel bucket; Figure 3 A flowchart for determining the leakage detection method for steel buckets; Figure 4 A flowchart for determining whether to use a collaborative detection method.

[0046] The leak detection system for the automated steel bucket production line provided in this embodiment includes:

[0047] The image acquisition module is used to acquire image information of the exterior of the steel bucket;

[0048] A feature extraction module, which is connected to the image acquisition module, is used to extract abnormal features and dynamic leakage trend features from the image information;

[0049] A type determination module, which is connected to the feature extraction module, is used to determine the leakage tendency type of the steel bucket based on the number of extracted abnormal features;

[0050] A data analysis module, connected to the image acquisition module, the feature extraction module, and the type determination module, is used to determine the leak detection method for the steel bucket based on its leakage tendency type, including:

[0051] Leakage testing of the steel bucket was performed using the pressure attenuation method.

[0052] Alternatively, based on the dynamic leakage trend characteristics of the steel bucket, determine whether to adopt a collaborative detection method. If a collaborative detection method is adopted, calculate the time interval between the time node of the pressure micro-fluctuation and the time interval between the ultrasonic sensor capturing the corresponding leak signal, and determine the temperature compensation mechanism based on the time interval.

[0053] Specifically, in this embodiment, the specific structure of the image acquisition module is not limited, as long as it can achieve the corresponding function, and an industrial camera or an infrared thermal imaging camera can be used.

[0054] Specifically, there are no restrictions on the specific structure of the feature extraction module, the type determination module, and the data analysis module. They can be composed of logical components, including field-programmable processors, computers, and microprocessors in computers.

[0055] In this invention, abnormal features such as tearing of the sealing ring are identified by image recognition, and the actual leakage is verified by pressure attenuation method or collaborative detection. This avoids the omission of potential leakage by single visual detection or the misjudgment of single pressure detection due to temperature interference. A targeted temperature compensation mechanism is introduced. Through a dynamic adaptation compensation strategy of pressure and ultrasonic signal time interval, the influence of ambient temperature fluctuation on pressure detection is effectively eliminated. Especially in scenarios with multiple leaks and large temperature gradients, the detection accuracy is greatly improved.

[0056] Specifically, the type determination module is used to determine the leakage tendency type of the steel bucket based on the number of extracted abnormal features, including:

[0057] If the number of abnormal features is greater than or equal to the preset number, the type determination module determines that the leakage tendency type of the steel bucket is a strong leakage tendency.

[0058] If the number of abnormal features is less than the preset number, the type determination module determines that the leakage tendency type of the steel bucket is weak leakage tendency.

[0059] Specifically, in this embodiment, the preset quantity can be determined in the following way: by analyzing historical detection data of the production line, the correlation between the "number of abnormal features" and the "actual leakage probability" is statistically analyzed. If the data shows that "when the number of abnormal features is ≥3, the actual leakage probability of the steel bucket exceeds 90%", then the preset quantity can be set to 3; if "when the number of abnormal features is <2, the actual leakage probability is less than 5%", then the preset quantity can be set to 2 to reduce misjudgment.

[0060] In this invention, a quantitative correlation between the "number of abnormal features" and the "actual leakage probability" is established through historical data statistics, making the setting of the preset quantity more scientific rather than subjective experience. Considering that the quality requirements of different production lines (such as chemical drums and ordinary packaging drums) are different, the preset quantity can be customized through historical data to match the classification of leakage tendency types with the risk level of product use (such as a lower preset quantity for chemical drums, which triggers the strong leakage tendency judgment earlier).

[0061] Specifically, the data analysis module is used to determine the leak detection method for the steel bucket based on its leakage tendency type, including:

[0062] If the leakage tendency of the steel bucket is strong, the data analysis module determines that the pressure decay method should be used to detect the leakage of the steel bucket.

[0063] If the leakage tendency type of the steel bucket is weak leakage tendency, the data analysis module determines whether to adopt a collaborative detection method based on the dynamic leakage tendency characteristics of the steel bucket. Under the condition of adopting the collaborative detection method, the time interval between the time node of the pressure micro-fluctuation and the time interval between the ultrasonic sensor capturing the corresponding leak point signal is calculated, so as to determine the temperature compensation mechanism based on the time interval.

[0064] Specifically, the abnormal features extracted from the image information by the feature extraction module include: holes, pits, scratches, and features of tearing, wear, aging and cracking of the rubber ring.

[0065] In this invention, for steel buckets with a strong tendency to leak (such as those with multiple holes, severe tearing of the rubber ring, and other high-frequency abnormal features), the pressure attenuation method is directly adopted. This method is simple to operate and has a fast response, and can verify whether there is obvious leakage (such as a rapid drop in pressure) in a short time. It is suitable for rapid screening in high-risk scenarios and avoids delays in the production line due to complex testing procedures. For steel buckets with a weak tendency to leak (such as only 1-2 minor scratches or slight wear of the rubber ring), the testing method is determined by combining dynamic leakage trend characteristics (such as whether the crack is expanding or whether the rubber ring fit is decreasing). When there is no dynamic trend, the vacuum chamber static pressure difference precision measurement method is used to focus on the accurate identification of minute leaks. When there is a dynamic trend, collaborative detection is enabled and temperature compensation is optimized through time intervals. This ensures detection accuracy while avoiding the overuse of high-end equipment for low-risk buckets, thus balancing detection cost and reliability.

[0066] Specifically, the dynamic leakage trend features extracted by the feature extraction module in the image information include: the expansion trend of cracks or damage, and the features of the sealing ring deforming over time, aging, or the decrease in the fit between the sealing ring and the sealing surface due to micro-deformation of the barrel.

[0067] Specifically, the data analysis module is used to determine whether to adopt a collaborative detection method based on the dynamic leakage trend characteristics of the steel bucket, including:

[0068] If the steel bucket exhibits a dynamic leakage tendency, the data analysis module determines to use a collaborative detection method.

[0069] If the steel bucket does not exhibit dynamic leakage characteristics, the data analysis module determines that the steel bucket should be leak-tested using the vacuum chamber static pressure difference precision measurement method.

[0070] In this invention, for steel buckets exhibiting dynamic leakage tendencies, a collaborative detection method is employed. This method combines the high precision of the vacuum chamber static pressure difference measurement method (capable of identifying minute leaks) with the location capability of ultrasonic detection (locking the leak point location), along with a temperature compensation mechanism to eliminate environmental interference. This ensures accurate assessment of "developing risks" and avoids missed detections due to insufficient detection methods (e.g., using only the static pressure difference method may overlook instantaneous leaks caused by crack propagation). For steel buckets without dynamic leakage tendencies (e.g., stable abnormal characteristics, no propagation, or accelerated aging trend), the lower-cost and simpler-to-operate vacuum chamber static pressure difference measurement method can meet the requirements, reducing detection costs while ensuring detection accuracy.

[0071] Specifically, the data analysis module is used to determine a temperature compensation mechanism based on the time interval, including:

[0072] If the time interval is greater than the first preset time interval and less than or equal to the second preset time interval, the data analysis module determines to adopt the overall temperature compensation mechanism.

[0073] If the time interval is greater than the second preset time interval, the data analysis module determines to adopt the partition temperature compensation mechanism.

[0074] Specifically, in this embodiment, the first preset time interval and the second preset time interval can be determined in the following ways: pressure sensor response time: tp = 10ms (the delay from the occurrence of pressure fluctuation to the sensor detecting the signal), ultrasonic sensor response time: tu = 1ms (the delay from the generation of the leak signal to the sensor capturing it), and the system's inherent minimum time interval (excluding equipment error): tmin = tp - tu = 9ms. Through steel bucket tests under different leakage scenarios, the following statistical results were obtained: for a single leak point under normal temperature conditions, the typical time interval is 10ms ≤ Δt ≤ 50ms, and the number of leak points is 1-2; for multiple leak points under conditions of uneven local temperature, the typical time interval is Δt > 50ms, and the number of leak points is greater than or equal to 3. Taking the upper limit of the system's inherent minimum time interval to ensure that the influence of equipment error is excluded, the first preset time interval is set to 10ms. Based on the critical time difference between "single leak point and multiple leak points" in the experimental data, the second preset time interval is set to 50ms.

[0075] Specifically, the data analysis module performs overall temperature compensation based on the overall internal temperature of the steel bucket and the gas state equation to calculate the temperature-pressure correction coefficient.

[0076] Specifically, in this embodiment, combining the gas law (ideal gas law), taking the overall temperature compensation mechanism of the data analysis module as an example, the parameters of the steel bucket are: volume 20L (i.e., 0.02³), and the initial sealed gas inside the bucket is air (which can be approximated as an ideal gas); the detection environment is: a collaborative detection method (vacuum chamber static pressure difference precision measurement method + ultrasonic detection method) is adopted, with a pressure sensor accuracy of ±0.1kPa and a temperature sensor accuracy of ±0.05℃; the baseline state is: at the initial detection, the overall internal temperature of the steel bucket T0 = 293K (20℃), and the initial pressure inside the bucket P0 = 100kPa (standard atmospheric pressure). At this time, it is confirmed that there is no leakage, and it is recorded as the baseline parameter; real-time detection data is: during the detection process, due to the fluctuation of the ambient temperature, the real-time overall temperature inside the bucket T1 = 303K (30℃), and the real-time reading of the pressure sensor P1 = 103kPa; based on the ideal gas law PV = nRT (where n is the amount of gaseous substance, R is the gas constant, and V is the internal volume of the bucket), when there is no leakage, n, V, and R are constants, and the pressure is proportional to the temperature: ,in, This is the theoretical pressure value under leak-free conditions after temperature change; substitute the known data: The correction factor k is defined as the ratio of theoretical pressure to real-time pressure, used to eliminate the effect of temperature on pressure. If the detection objective is "to determine whether there is a leak," then the real-time pressure is converted to the equivalent pressure at the reference temperature using a correction factor. ,at this time, This indicates that the pressure change was caused solely by temperature, and there was no leakage; if The difference is the actual pressure change caused by the leakage.

[0077] In this invention, for statically placed steel buckets without significant temperature gradients (such as weakly inclined buckets without dynamic leakage tendency characteristics), overall temperature compensation does not require partitioned calculations. Correction can be completed solely through a single volume and overall temperature, which is suitable for the real-time detection needs of automated production lines. This avoids complex algorithms slowing down the detection pace. The system automatically selects the compensation method based on the time interval between the pressure and ultrasonic signals. When the time interval is short (few leakage points, small temperature gradient), overall compensation is used (efficient), while when the time interval is long (many leakage points, large gradient), partitioned compensation is used (accurate). This ensures both the detection speed in simple scenarios and the accuracy requirements in complex scenarios.

[0078] Specifically, the data analysis module divides the steel bucket into several regions, calculates pressure correction values ​​based on real-time temperature data of the several regions, and obtains correction coefficients by weighted summation.

[0079] Specifically, in this embodiment, when dividing the area, the parts that are prone to defects during the processing are divided into separate areas, and the weighting coefficient can be determined based on the historical leakage frequency of that location.

[0080] Specifically, in this embodiment, based on the parts of the steel bucket that are prone to defects during processing (combined with historical leakage data), they are divided into 5 key areas. The criteria for dividing each area and the weight coefficient (reflecting the historical leakage frequency) are as follows: Area 1: Bucket opening sealing ring (classification criteria: installation deviation, aging or wear of the sealing ring, a high-frequency leakage point), historical leakage frequency is 35%, weight coefficient is 0.35; Area 2: Longitudinal weld seam of the bucket body (classification criteria: prone to incomplete fusion and porosity during welding, a major structural defect), historical leakage frequency... The historical leakage frequency of Area 1 is 25%, with a weighting coefficient of 0.25; Area 2: Bottom circumferential weld (classification basis: the connection between the bottom and the body of the barrel, which is prone to micro-cracks under stress), with a historical leakage frequency of 20%, and a weighting coefficient of 0.2; Area 3: Bottom circumferential weld (classification basis: the connection between the bottom and the body of the barrel, which is prone to micro-cracks under stress), with a historical leakage frequency of 15%, and a weighting coefficient of 0.15; Area 4: Top handle weld (classification basis: the welding stress is concentrated during the installation of the handle, which is prone to incomplete welds), with a historical leakage frequency of 15%, and a weighting coefficient of 0.15; Area 5: Side wall of the barrel (classification basis: scratches may occur during rolling or handling, but the leakage frequency is low), with a historical leakage frequency of 5%, and a weighting coefficient of 0.05.

[0081] Using distributed temperature sensors (two measuring points per area, average value taken), the real-time temperature Ti of each area is collected. The reference temperature T0 at the initial moment (no leakage state) is detected to be 293K, or 20℃, as follows: Area 1, real-time temperature 295K (22℃), difference from the reference temperature is +2K; Area 2, real-time temperature 294K (21℃), difference from the reference temperature is +1K; Area 3, 296K (23℃), difference from the reference temperature is +3K; Area 4, 293K (20℃), difference from the reference temperature is 0K; Area 5, 292K (19℃), difference from the reference temperature is -1K. Based on the ideal gas law, the pressure correction value Ki for each area is the ratio of the real-time temperature to the reference temperature (reflecting the influence coefficient of temperature on pressure). The pressure correction values ​​for each region are calculated as follows: Region 1, pressure correction value is 295 / 293≈1.0068; Region 2, pressure correction value is 294 / 293≈1.0034; Region 3, pressure correction value is 296 / 293≈1.0102; Region 4, pressure correction value is 293 / 293=1.0000; Region 5, pressure correction value is 292 / 293≈0.9966; The total correction coefficient (K) is the weighted sum of the pressure correction value of each region and the corresponding weight coefficient, and the formula is as follows: Substituting the data, the calculation is as follows: K = (0.35 × 1.0068) + (0.25 × 1.0034) + (0.20 × 1.0102) + (0.15 × 1.0000) + (0.05 × 0.9966) ≈ 1.0051; The total correction coefficient K ≈ 1.0051 is used to correct the overall pressure measurement value of the steel bucket. For example, if the real-time pressure inside the bucket is detected to be 100 kPa, then the corrected equivalent pressure (eliminating the influence of temperature gradient) is 100 × 1.0051 = 100.51 kPa.

[0082] Specifically, the collaborative detection method involves using a vacuum chamber static pressure difference precision measurement method and an ultrasonic detection method to perform leak detection on the steel bucket.

[0083] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0084] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention can have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A leak detection system for an automatic steel drum production line, characterized in that, The method comprises the following steps: an image acquisition module is configured to acquire image information of the outside of the steel drum; a feature extraction module is connected to the image acquisition module and configured to extract abnormal features and dynamic leakage tendency features from the image information; a type determination module is connected to the feature extraction module and configured to determine the leakage tendency type of the steel drum according to the number of the extracted abnormal features, wherein, if the number of abnormal features is greater than or equal to a preset number, the type determination module determines that the leakage tendency type of the steel drum is strong leakage tendency; if the number of abnormal features is less than the preset number, the type determination module determines that the leakage tendency type of the steel drum is weak leakage tendency; a data analysis module is connected to the image acquisition module, the feature extraction module and the type determination module respectively, and is configured to determine the leak detection method for the steel drum based on the leakage tendency type of the steel drum, comprising: using the pressure decay method to perform leak detection on the steel drum; or, determining whether to use the cooperative detection method based on the dynamic leakage tendency features of the steel drum, and under the condition of using the cooperative detection method, calculating the time node of pressure fluctuation and the time interval between the time when the ultrasonic sensor captures the corresponding leak point signal, to determine the temperature compensation mechanism based on the time interval; wherein, if the leakage tendency type of the steel drum is strong leakage tendency, the data analysis module determines to use the pressure decay method to perform leak detection on the steel drum; if the leakage tendency type of the steel drum is weak leakage tendency, the data analysis module determines to determine whether to use the cooperative detection method based on the dynamic leakage tendency features of the steel drum, and under the condition of using the cooperative detection method, calculates the time node of pressure fluctuation and the time interval between the time when the ultrasonic sensor captures the corresponding leak point signal, to determine the temperature compensation mechanism based on the time interval.

2. The leak detection system of the steel drum automatic production line according to claim 1, characterized in that, The abnormal features extracted by the feature extraction module from the image information include: holes, pits, scratches, and features of tear, wear and aging cracking of the rubber ring.

3. The leak detection system of the steel drum automatic production line according to claim 1, characterized in that, The dynamic leakage tendency features extracted by the feature extraction module from the image information include: features of the expansion tendency of cracks or damage, features of the deformation of the sealing rubber ring over time, the aggravation of aging, or the decline of the fit of the rubber ring and the sealing surface due to the micro-deformation of the drum body.

4. The leak detection system of the automatic steel drum production line according to claim 1, characterized in that, The data analysis module is configured to determine whether to use the cooperative detection method based on the dynamic leakage tendency features of the steel drum, comprising: if the steel drum has dynamic leakage tendency features, the data analysis module determines to use the cooperative detection method; if the steel drum has no dynamic leakage tendency features, the data analysis module determines to use the vacuum cavity static pressure difference precision leak detection method to perform leak detection on the steel drum.

5. The leak detection system of the steel drum automatic production line according to claim 1, characterized in that, The data analysis module is configured to determine the temperature compensation mechanism based on the time interval, comprising: if the time interval is greater than a first preset time interval and less than or equal to a second preset time interval, the data analysis module determines to use the overall temperature compensation mechanism; if the time interval is greater than the second preset time interval, the data analysis module determines to use the partition temperature compensation mechanism.

6. The leak detection system of the automatic steel pail production line according to claim 5, characterized in that, The data analysis module performs overall temperature compensation based on the overall temperature inside the steel ladle and in combination with a gas state equation to calculate a correction coefficient of temperature to pressure.

7. The leak detection system of the steel drum automatic production line according to claim 5, characterized in that, The data analysis module divides the steel ladle into several regions, and based on real-time temperature data of the several regions, respectively calculates pressure correction values, and obtains a correction coefficient by weighted summation.

8. The leak detection system of the steel drum automatic production line according to claim 1, characterized in that, The collaborative detection mode is to perform leak detection on the steel ladle by using a vacuum cavity static pressure difference precision measurement method and an ultrasonic wave detection method.

Images