Laser marking position monitoring method and system for brake drum production

Abstract

The present invention discloses a laser marking position monitoring method and system for brake drum production, which relates to the field of image data processing technology, including: obtaining a standard position and a standard straight-line distance, collecting an original surface image, and identifying a real-time position of a hole; obtaining a pixel abnormality; judging whether the pixel abnormality is less than a first threshold, if so, obtaining the center position of the mark, otherwise issuing an abnormality notification; obtaining a real-time straight-line distance, obtaining a hole offset; judging whether the hole offset is less than a second threshold, if so, obtaining a gray surface image, otherwise issuing an abnormality notification; obtaining a threshold dot matrix composed of multiple gray abnormality thresholds, and obtaining the number of pixel points in the gray surface image that exceed the threshold dot matrix as the abnormal number, and judging whether the abnormal number is less than a third threshold, if so, completing the monitoring operation, otherwise issuing an abnormality notification. The present invention has the advantages of accurate recognition, multi-level judgment, and good monitoring effect.

Description

Technical Field

[0001] The invention relates to the technical field of image data processing, and in particular to a laser marking position monitoring method and system for brake drum production. Background Art

[0002] In the production process of brake drums, laser marking technology is widely used to mark key data such as product information, production date, manufacturer logo, etc. This technology not only improves production efficiency, but also ensures the clarity and durability of the marked information. However, with the continuous expansion of production scale and the increasingly stringent product quality, higher requirements are placed on the accuracy and consistency of laser marking position.

[0003] The traditional method of monitoring the position of brake drum laser marking mainly relies on manual visual inspection. This method is not only time-consuming and labor-intensive, but also easily affected by human factors, resulting in missed detection or misjudgment. In order to improve the accuracy and efficiency of monitoring, some automated monitoring technologies have gradually been introduced into the production process of brake drums. However, these technologies can often only achieve simple position recognition or defect detection. For complex laser marking patterns and changing production environments, their monitoring effects are not ideal.

[0004] In particular, there are usually multiple holes on the brake drum for installation or positioning. The position and spacing of these holes are crucial to the function and performance of the product. During the laser marking process, if there is a deviation in the relative relationship between the position of the print and these holes, it may cause product assembly problems or misinterpretation of the identification information. Therefore, for the monitoring of the laser marking position, it is necessary to be able to accurately identify the position of the holes and accurately calculate the relative distance between the print and the holes. In addition, the quality of laser marking is also affected by many factors, such as laser power, scanning speed, material properties, etc. Changes in these factors may cause changes in the grayscale value of the marking area, thereby affecting the readability of the marking information. Traditional monitoring methods often find it difficult to accurately detect these subtle grayscale changes, resulting in unstable product quality. Summary of the invention

[0005] In view of the defects in the prior art, the present invention provides a laser marking position monitoring method and system for brake drum production.

[0006] A method for monitoring the position of laser marking for brake drum production, comprising: obtaining the standard positions of multiple holes on a standard brake drum and the standard straight-line distances between the multiple holes and the marking, and collecting the original surface image of the marking surface of the brake drum after marking in real time, and identifying the real-time position of each hole in the original surface image according to the standard position; obtaining the degree of pixel abnormality within a first preset range around each hole based on an abnormality calculation model, the real-time position of each hole and the original surface image; judging whether the degree of pixel abnormality of each hole is less than a first threshold, if so, obtaining the center position of the marking where the center point of the marking is located in the original surface image, otherwise issuing an abnormality notification; based on the distance calculation model, the real-time position of each hole, and the original surface image, obtaining the degree of pixel abnormality within a first preset range around each hole; judging whether the degree of pixel abnormality of each hole is less than a first threshold, if so, obtaining the center position of the marking where the center point of the marking is located in the original surface image, and otherwise issuing an abnormality notification; The real-time straight-line distance between each hole and the printing mark is obtained based on the real-time position of the hole and the center position of the printing mark, and the hole offset between each hole and the printing mark is obtained based on the real-time straight-line distance and the standard straight-line distance between each hole and the printing mark; it is judged whether the hole offsets between each hole and the center point of the printing mark are all less than the second threshold value, if so, a grayscale surface image is obtained based on the grayscale conversion model and the original surface image, if otherwise, an abnormal notification is issued; according to the printing mark specifications, a threshold dot matrix composed of multiple grayscale abnormal thresholds is obtained, and the number of pixel points in the grayscale surface image that exceed the threshold dot matrix is ​​obtained as the abnormal number, and it is judged whether the abnormal number is less than the third threshold value, if so, the monitoring operation is completed, if otherwise, an abnormal notification is issued.

[0007] Optionally, the abnormality calculation model for obtaining the degree of pixel abnormality within a first preset range around each hole based on the abnormality calculation model, the real-time position of each hole and the original surface image includes: defining each first preset range as a neighborhood formed with the real-time position of each hole as the center and a preset distance as the radius, wherein the preset distance is greater than the hole radius; and obtaining the degree of pixel abnormality in each neighborhood based on the abnormality calculation model and the original surface image.

[0008] Optionally, the abnormal degree of pixels in each neighborhood is obtained based on the abnormal calculation model and expressed as: ;in, is the pixel abnormality of the i-th hole, is the real-time position of the ith hole, For the preset distance, is the radius of the ith hole, is the pixel value of the current pixel in the neighborhood of the i-th hole, is the average pixel value of all pixels in the neighborhood of the i-th hole except the hole, is the weight factor.

[0009] Optionally, the distance calculation model in obtaining the real-time straight-line distance between each hole and the center point of the printing mark based on the distance calculation model, the real-time hole position of each hole and the center position of the printing mark is expressed as: ;in, is the real-time straight-line distance between the ith hole and the printing mark, is the real-time position of the ith hole, It is the center position of the printed mark.

[0010] Optionally, the hole offset between each hole and the printing mark is obtained according to the real-time straight-line distance and the standard straight-line distance between each hole and the printing mark and is expressed as: ;in, is the hole offset between the ith hole and the printing mark, is the real-time straight-line distance between the ith hole and the printed mark, is the standard straight-line distance between the ith hole and the printing mark.

[0011] Optionally, a grayscale surface image representation is obtained based on the grayscale conversion model and the original surface image: ;in, is the pixel point in the grayscale surface image The gray value of is the pixel point in the original surface image The red channel value of is the pixel point in the original surface image The green channel value of is the pixel point in the original surface image The blue channel value of

[0012] Optionally, obtaining a threshold dot matrix composed of multiple grayscale abnormality thresholds according to the printing mark specifications includes: obtaining a printing mark area according to the printing mark specifications, and dividing the printing mark area into multiple printing mark pixels; setting a grayscale abnormality threshold at each printing mark pixel, and forming a threshold dot matrix with multiple grayscale abnormality thresholds according to the positions of the printing mark pixels.

[0013] A laser marking position monitoring system for brake drum production is also provided, the system comprising: a standard acquisition and module for acquiring the standard positions of multiple holes on a standard brake drum and the standard straight-line distances between the multiple holes and the print mark, and real-time acquisition of the original surface image of the print surface of the brake drum after marking, and identification of the real-time position of each hole in the original surface image according to the standard position; a first calculation module for acquiring the degree of pixel abnormality within a first preset range around each hole based on an abnormality calculation model, the real-time position of each hole and the original surface image; a first judgment and processing module for judging whether the degree of pixel abnormality of each hole is less than a first threshold, and if so, acquiring the center position of the print mark where the center point of the print mark is located in the original surface image, and otherwise issuing an abnormality notification; a second calculation module for Based on the distance calculation model, the real-time straight-line distance between each hole and the printing mark, the real-time straight-line distance between each hole and the printing mark and the standard straight-line distance are used to obtain the hole offset between each hole and the printing mark; the second judgment and processing module is used to judge whether the hole offsets between each hole and the center point of the printing mark are all less than the second threshold value, if so, a grayscale surface image is obtained based on the grayscale conversion model and the original surface image, otherwise an abnormal notification is issued; the third judgment and processing module is used to obtain a threshold dot matrix composed of multiple grayscale abnormal thresholds according to the printing mark specifications, and obtain the number of pixel points in the grayscale surface image that exceed the threshold dot matrix as the abnormal number, and judge whether the abnormal number is less than the third threshold value, if so, the monitoring operation is completed, otherwise an abnormal notification is issued.

[0014] Optionally, the first calculation module is also used to: define each first preset range as a neighborhood formed with the real-time position of each hole as the center and a preset distance as the radius, wherein the preset distance is greater than the hole radius; and obtain the degree of pixel abnormality in each neighborhood based on the abnormality calculation model and the original surface image.

[0015] Optionally, the third judgment and processing module is also used to: obtain the printing area according to the printing specifications, and divide the printing area into multiple printing pixels; set a grayscale abnormality threshold at each printing pixel, and form a threshold dot matrix with multiple grayscale abnormality thresholds according to the positions of the printing pixels.

[0016] The beneficial effects of the present invention are embodied in:

[0017] In the entire laser marking position monitoring method for brake drum production, the standard position of the hole on the standard brake drum and the standard straight-line distance between the hole and the printed mark are accurately obtained, and the surface image of the brake drum after marking is collected in real time to identify the real-time position of the hole, thereby ensuring the accuracy of the position information; then, the abnormality calculation model is used to evaluate the abnormality of the pixels around the hole, and the image abnormalities that may affect the position accuracy are effectively identified; after confirming that the image quality is normal, the distance calculation model is used to accurately calculate the real-time straight-line distance and offset between the hole and the printed mark, and after comparing with the standard value, the position deviation can be discovered in time; in addition, the grayscale conversion model and threshold dot matrix are used to perform a fine analysis of the pixels of the grayscale surface image, and subtle changes in the marking quality, such as grayscale value abnormalities, are accurately detected, thereby avoiding minor defects that are difficult to capture with traditional methods; this series of automated high-precision monitoring steps not only reduces missed detections and misjudgments caused by human factors, but also greatly improves the monitoring efficiency, ensures the quality and functional stability of brake drum products, reduces the defective rate, and improves the reliability and efficiency of the overall production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0019] Figure 1 A schematic diagram of the steps of the laser marking position monitoring method for brake drum production according to the present invention;

[0020] Figure 2 It is a schematic diagram of step S2 in the laser marking position monitoring method for brake drum production of the present invention;

[0021] Figure 3 It is a schematic diagram of some steps of S6 in the laser marking position monitoring method for brake drum production of the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0023] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. In addition, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0025] like Figure 1 As shown, a laser marking position monitoring method for brake drum production is provided, comprising:

[0026] S1, obtaining the standard positions of multiple holes on a standard brake drum and the standard straight-line distances between the multiple holes and the printed mark, and collecting the original surface image of the printed mark surface of the brake drum in real time after the printing, and identifying the real-time position of each hole in the original surface image according to the standard position;

[0027] S2, obtaining the degree of pixel abnormality within a first preset range around each hole based on the abnormality calculation model, the real-time position of each hole and the original surface image;

[0028] S3, determining whether the pixel abnormality of each hole is less than a first threshold, if so, obtaining the center position of the printed mark where the center point of the printed mark in the original surface image is located, if not, issuing an abnormality notification;

[0029] S4, obtaining the real-time straight-line distance between each hole and the printing mark based on the distance calculation model, the real-time hole position of each hole and the center position of the printing mark, and obtaining the hole offset between each hole and the printing mark according to the real-time straight-line distance and the standard straight-line distance between each hole and the printing mark;

[0030] S5, determining whether the hole offsets between each hole and the center point of the printing mark are all less than a second threshold value, if so, obtaining a grayscale surface image based on the grayscale conversion model and the original surface image, if not, issuing an abnormal notification;

[0031] S6. Obtain a threshold dot matrix composed of multiple grayscale abnormality thresholds according to the printing specification, and obtain the number of pixel points in the grayscale surface image that exceed the threshold dot matrix as the abnormal number, and determine whether the abnormal number is less than a third threshold. If so, complete the monitoring operation, otherwise issue an abnormal notification.

[0032] In this embodiment, it should be noted that, in S1, first, the standard positions of multiple holes on the standard brake drum are obtained. This step requires accurate measurement and recording of the standard positions of all key holes on the brake drum; these position information are usually determined in the brake drum design stage. The standard brake drum size can be obtained from drawings or other design materials. The distance can be directly measured by measuring tools (such as laser rangefinders, three-coordinate measuring machines, etc.), or calculated by design software, and used as a benchmark for subsequent production and monitoring. Then, the standard straight-line distance between the multiple holes and the printed mark is obtained. In the design process of the brake drum, the position of the printed mark is usually predetermined, and there is a certain geometric relationship (such as distance, angle, etc.) between the hole and the printed mark. The task of this step is to measure and record these standard straight-line distances for comparison in the subsequent monitoring process. Finally, the original surface image of the printed surface of the brake drum after marking is collected in real time, and the real-time position of each hole in the original surface image is identified according to the standard position. After the brake drum is laser marked, the image of its printed surface needs to be collected immediately, and then the real-time position of each hole is identified from the image using image processing technology (such as edge detection, template matching, etc.) and the standard position information of the holes.

[0033] Assume that there is a brake drum with four key holes (A, B, C, D) distributed on it, and there is a specific geometric relationship between these holes and the printed mark. During the brake drum design stage, the standard positions of these four holes relative to the center of the brake drum (such as A(x1, y1), B(x2, y2), C(x3, y3), D(x4, y4)) have been measured and recorded using high-precision measurement tools. At the same time, the standard straight-line distances between the printed mark and the four holes (such as LA, LB, LC, LD) are also measured. During the production process, when the brake drum is laser marked, a high-resolution camera is used to immediately capture its printed surface to obtain an original surface image. Then, using image processing technology and the standard position information of the holes, the real-time positions of the four holes (such as A'(x1', y1'), B'(x2', y2'), C'(x3', y3'), D'(x4', y4')) are identified from the image.

[0034] In S2, the abnormality calculation model is used to evaluate the degree of pixel abnormality in a specific area of ​​the image. This model can be designed and adjusted according to actual needs to identify different types of abnormalities. In this embodiment, the abnormality calculation model takes into account the pixel value to comprehensively evaluate the image quality around the hole. In step S1, the real-time position of each hole has been identified by image processing technology, and this position information will be used to determine the analysis range of the abnormality calculation model. Among them, the original surface image is taken after the brake drum is laser marked, and contains key information such as the mark and the hole; the first preset range is an area with a specific radius or side length centered on the real-time position of the hole. The size of this range can be adjusted according to actual needs to ensure that it can cover the possible abnormal area; the abnormality calculation model will analyze each pixel in the first preset range and calculate the degree of abnormality according to the preset evaluation criteria. Finally, the abnormality calculation model will output a value representing the degree of pixel abnormality. The larger the value, the greater the difference between the pixel and the normal state.

[0035] Assume that there is a brake drum with four key holes (A, B, C, D) distributed on it, and the real-time positions of these holes have been identified through step S1. Now, taking hole A as an example, the execution process of step S2 will be described in detail. Assume that the first preset range is set as a circular area with a radius of 10 pixels centered on the real-time position of hole A. The anomaly calculation model will analyze each pixel in this circular area, calculate the degree of anomaly according to the preset evaluation criteria, and finally output a value representing the degree of pixel anomaly of 0.3 (this value is an assumption, and the actual value depends on the specific implementation of the anomaly calculation model).

[0036] In S3, before making a judgment, a first threshold needs to be set. The first threshold is a preset value used to distinguish between normal and abnormal states. The setting of the first threshold needs to be adjusted according to the actual situation. For example, carefully check the manufacturing standards of the brake drum to understand the size of the hole, the position accuracy and the specific requirements of laser marking. These standards usually stipulate the allowable deviation range between the hole and the print, as well as the image quality evaluation standard, which only needs to be able to identify the anomalies that may affect the hole position accuracy or image quality. For each hole, S3 will compare the pixel abnormality value with the first threshold. If the pixel abnormality value is less than the first threshold, it is considered that the image quality around the hole is normal and is not affected by the abnormality. If the pixel abnormality value is greater than or equal to the first threshold, it is considered that there is an abnormality around the hole, which may affect the hole position accuracy or image quality, thereby affecting the subsequent marking position monitoring results. Specifically, if the pixel abnormality values ​​of all holes are less than the first threshold, S3 will continue to obtain the center position of the print mark where the center point of the print mark is located in the original surface image, and use existing image processing technology (such as template matching, feature extraction, etc.) to identify the print mark in the original surface image. This usually involves comparing the print mark part in the image with the preset print mark template to find the most matching area. Once the print mark is identified, it is necessary to calculate the center point position, which can be achieved by calculating the geometric center of the print mark area; if there is any hole whose pixel abnormality value is greater than or equal to the first threshold, S3 will issue an abnormal notification to prompt the operator to pay attention to possible problems and take corresponding measures.

[0037] Assume that there is a brake drum with four key holes (A, B, C, D) distributed on it, and the real-time positions of these holes have been identified through step S1, and the pixel abnormality values ​​around these holes have been calculated through step S2. Now, taking hole A as an example, the execution process of step S3 will be described in detail. Assume that the first threshold value set is 0.5. This value is obtained after adjustment according to the actual situation and is used to distinguish between normal and abnormal states. In step S2, the pixel abnormality value of hole A has been calculated to be 0.3. The pixel abnormality value of hole A 0.3 is compared with the first threshold 0.5. Since 0.3 is less than 0.5, it is considered that the image quality of hole A is normal and is not affected by the abnormality. Finally, the existing image processing technology (such as template matching, feature extraction, etc.) is used to identify the printed mark in the original surface image, which usually involves comparing the printed mark part in the image with the preset printed mark template to find the best matching area. Once the printed mark is identified, its center point position needs to be calculated, which can be achieved by calculating the geometric center of the printed mark area.

[0038] In S4, the distance calculation model is used to calculate the distance between two points based on their coordinates. In the monitoring scenario of brake drums, this model is usually used to calculate the straight-line distance between the real-time position of the hole and the center position of the print mark. The input data of step S4 include: the real-time position of each hole (such as A'(x1', y1'), B'(x2', y2'), etc., which are identified by the image processing technology in S1); the center position of the print mark (which is calculated by the print mark recognition technology in S3). For each hole, the distance calculation model is used to calculate the straight-line distance between it and the center position of the print mark, which involves basic geometric operations in the distance calculation model. The distance obtained is the real-time straight-line distance between the hole and the print mark. Finally, the calculated real-time straight-line distance is compared with the standard straight-line distance (which is measured and recorded during the brake drum design stage), and the difference between the two is calculated, that is, the hole offset between the hole and the print mark is obtained.

[0039] In S5, the first step is to compare the hole offset with the preset second threshold value; the second threshold value is a key parameter set according to the brake drum manufacturing standard and laser marking requirements. It represents the maximum allowable offset between the hole and the mark. This value is usually determined during the brake drum design phase based on the product's functional requirements, assembly accuracy, and the characteristics of the laser marking technology. If the offset of all holes is less than the second threshold value, a grayscale surface image will be obtained based on a grayscale conversion model and the original surface image. The grayscale conversion model is usually a mathematical or algorithmic model that can convert a color image into a grayscale image to retain important information in the image. If the offset of any hole is greater than or equal to the second threshold value, then the S5 step will immediately issue an abnormal notification; this notification usually contains the hole information with an excessive offset, the specific value of the offset, and the possible abnormal cause, so that the operator can quickly locate the problem and take appropriate treatment measures; the abnormal notification can be issued in the form of a sound alarm, a light prompt, a screen display, etc., depending on the design of the monitoring system and the operator's preference.

[0040] Assume that there is a brake drum with four key holes (A, B, C, D) distributed on it, and the real-time positions of these holes have been identified, the pixel abnormality has been calculated, the center position of the print mark has been identified, and the hole offset has been calculated through S1 to S4. Now, the execution process of S5 will be described in detail by taking hole A as an example. Assume that the set second threshold is 2mm (this value is determined comprehensively based on the manufacturing standards of the brake drum and the laser marking requirements). In S4, the offset between hole A and the center point of the print mark has been calculated to be 0.15mm. The offset of hole A, 1.5mm, is compared with the second threshold of 0.2mm. Since 0.15mm is less than 0.2mm, it is considered that the relative position relationship between hole A and the center point of the print mark is normal, so a grayscale surface image will be obtained based on the grayscale conversion model and the original surface image. If the offset of any hole is found to be greater than or equal to the second threshold value (for example, the offset of hole B is 0.25 mm), S5 will immediately issue an abnormal notification, which may include the following information: "The offset between hole B of the brake drum and the center point of the mark exceeds the limit (0.25 mm). Please check whether the laser marking position and hole position are accurate and take appropriate measures."

[0041] In S6, the change of grayscale value can reflect the influence of various factors (such as laser power, scanning speed, material properties, etc.) in the laser marking process. Therefore, accurate monitoring of grayscale value is an important means to evaluate the quality of marking. According to the specifications of the printed mark, a threshold dot matrix composed of multiple grayscale abnormality thresholds is obtained. This threshold dot matrix is ​​usually determined comprehensively based on the design shape of the printed mark, material properties and process parameters of the laser marking; each threshold in the threshold dot matrix corresponds to the grayscale value range of a specific area or feature in the printed mark; if the grayscale value of a certain area exceeds the corresponding threshold range, it may indicate that there is a problem with the marking quality of the area; in the grayscale surface image, traverse each pixel point, compare its grayscale value with the threshold value of the corresponding position in the threshold dot matrix, and count the number of pixels whose grayscale value exceeds the threshold dot matrix range as the number of abnormalities. This number reflects the degree of abnormal grayscale value in the marking area. A third threshold is set to determine whether the number of abnormalities is acceptable. The setting of the third threshold needs to comprehensively consider factors such as the readability of the printed mark, the functional requirements of the product, and the fault tolerance rate in the production process; if the number of abnormalities is less than the third threshold, the label printing quality is considered acceptable and the monitoring operation is completed; if the number of abnormalities is greater than or equal to the third threshold, an abnormal notification is issued to prompt the operator to pay attention to possible problems with the label printing quality and take corresponding treatment measures.

[0042] Assume that there is a brake drum with a printed mark containing multiple characters and numbers. According to the specifications of the printed mark, a threshold dot matrix consisting of multiple grayscale abnormality thresholds has been obtained. This threshold dot matrix contains the grayscale abnormality threshold 5 corresponding to each position of the printed mark (the shape of the printed mark can be broken down into individual pixels), which is determined by the material properties and the process parameters of the laser marking. In the production process, when the brake drum is laser marked, the original surface image of its printed surface is collected and converted into a grayscale surface image using a grayscale conversion model. Then, each pixel in the grayscale surface image is traversed and its grayscale value is compared with the threshold of the corresponding position in the threshold dot matrix. During the comparison process, it is found that the grayscale values ​​of 10 pixels in the grayscale surface image exceed the range of the threshold dot matrix. The third threshold is set to 5 pixels. Since the number of abnormalities (10 pixels) is greater than the third threshold (5 pixels), the marking quality is considered unacceptable and an abnormality notification is issued immediately. The abnormal notification may include the following information: "There is an abnormal grayscale value in the marking area of ​​the brake drum (10 pixels are beyond the threshold range). Please check the laser marking process parameters and material properties, and take corresponding treatment measures." Finally, after inspection, these 10 pixels are mainly distributed around a certain character of the mark, which may indicate that there is a problem with the marking quality of the character.

[0043] In summary, in the entire laser marking position monitoring method for brake drum production, the standard position of the hole on the standard brake drum and the standard straight-line distance between the hole and the printed mark are accurately obtained, and the surface image of the brake drum after marking is collected in real time to identify the real-time position of the hole, thereby ensuring the accuracy of the position information; then, the abnormality calculation model is used to evaluate the abnormality of the pixels around the hole, and the image abnormalities that may affect the position accuracy are effectively identified; after confirming that the image quality is normal, the real-time straight-line distance and offset between the hole and the printed mark are accurately calculated by the distance calculation model, and after comparison with the standard value, the position deviation can be discovered in time; in addition, the grayscale conversion model and threshold dot matrix are used to perform a fine analysis of the pixels of the grayscale surface image, and subtle changes in the marking quality, such as grayscale value abnormalities, are accurately detected, thereby avoiding minor defects that are difficult to capture with traditional methods; this series of automated high-precision monitoring steps not only reduces missed detections and misjudgments caused by human factors, but also greatly improves the monitoring efficiency, ensures the quality and functional stability of brake drum products, reduces the defective rate, and improves the reliability and efficiency of the overall production line.

[0044] like Figure 2 As shown, in one embodiment, obtaining the pixel abnormality degree within a first preset range around each hole based on the abnormality calculation model, the real-time hole position of each hole and the original surface image in S2 includes:

[0045] S21, defining each first preset range as a neighborhood formed with the real-time position of each hole as the center and a preset distance as the radius, wherein the preset distance is greater than the hole radius;

[0046] S22. Obtain the degree of pixel abnormality in each neighborhood based on the abnormality calculation model and the original surface image.

[0047] In this embodiment, it should be noted that in S21, we need to define a first preset range for each hole. This range is a circular neighborhood with the real-time position of the hole as the center and the preset distance as the radius. The purpose of this neighborhood is to capture the image information around the hole for subsequent analysis of possible abnormalities; the center of the circle is the real-time position of the hole, which is identified by the image processing technology in S1; the preset distance is a key parameter, which determines the size of the neighborhood. This distance needs to be greater than the radius of the hole to ensure that the image information around the hole can be fully covered. At the same time, the preset distance cannot be too large, it only needs to meet the evaluation requirements, that is, it can reflect the quality problems of the hole. Optionally, the preset distance is 1.5 times the pixel length occupied by the hole radius.

[0048] For example, suppose there is a hole A on the brake drum, and its real-time position is (x1', y1'). The radius of hole A is 10 pixels, and we set the preset distance to 15 pixels. Then, the first preset range of hole A is a circular neighborhood with (x1', y1') as the center and a radius of 15 pixels.

[0049] In S22, we will use the anomaly calculation model to analyze the degree of pixel anomaly in each neighborhood; the anomaly calculation model is a complex algorithm or model that can evaluate the degree of pixel anomaly based on the pixel value in the image; the input of the anomaly calculation model includes the original surface image and the definition of each neighborhood (i.e., the center coordinates and radius); the model will traverse the pixels in each neighborhood except the holes, because the pixels in the holes are the background of the collected rear brake drum and have no reference value; then calculate the overall degree of anomaly; the output of the model is a value representing the degree of pixel anomaly. The larger the value, the greater the difference from the normal state, and the hole may be abnormal.

[0050] For example, for the neighborhood of hole A, the anomaly calculation model will analyze each pixel in the neighborhood and calculate the degree of anomaly based on the preset evaluation criteria. Assuming that the degree of anomaly of hole A calculated by the model is 0.4 (this value is an assumption, and the actual value depends on the specific implementation of the anomaly calculation model), it provides a reliable basis for subsequent position monitoring and marking quality inspection.

[0051] In one embodiment, the abnormal degree of pixels in each neighborhood obtained based on the abnormal calculation model in S22 is expressed as:

[0052] ;in,

[0053] is the pixel abnormality of the i-th hole, is the real-time position of the ith hole, For the preset distance, is the radius of the ith hole, is the pixel value of the current pixel in the neighborhood of the i-th hole, is the average pixel value of all pixels in the neighborhood of the i-th hole except the hole, is the weight factor.

[0054] In this embodiment, it should be noted that the expression calculates a weighted average absolute pixel difference, which is calculated within an annular region centered on the hole and extending from the boundary of the hole (radius ) to a preset distance .

[0055] is a normalization factor used to ensure that the calculated abnormality The factors are comparable in neighborhoods of different sizes, and this factor is the neighborhood area. Subtract hole area The countdown after. This outer integral represents the radius of the hole. Starting at and ending at a preset distance R, this defines a circular area. This inner integral represents the angle at each angle in the annular region. Calculations are performed on all of them, covering the entire circumference. The pixel value of each pixel in the annular area is calculated by comparing it with the average pixel value of the annular area (excluding the hole itself). The absolute difference between the current pixel and the average gray value indicates the degree of deviation between the current pixel and the average gray value, which is a measure of the degree of surface abnormality. is the differential element of the integral, is a weight factor, which ensures that each pixel in the annular region is appropriately weighted. In general, is equal to r, which means that the weight is proportional to the distance to the center of the hole. The introduction of the weight factor a provides additional flexibility, allowing the contribution of different pixels or regions to the calculation of the degree of abnormality to be adjusted according to the specific application scenario. At the same time, since we normalize after integration, the influence of this weight is averaged. In summary, this mathematical expression calculates the weighted sum of the difference between the gray value of each pixel in the neighborhood of the hole and the average gray value (and normalizes it), thereby scientifically and effectively evaluating the degree of surface abnormality around the hole.

[0056] In one embodiment, the distance calculation model in S4 for obtaining the real-time straight-line distance between each hole and the center point of the printing mark based on the distance calculation model, the real-time hole position of each hole and the center position of the printing mark is expressed as:

[0057] ;in,

[0058] is the real-time straight-line distance between the ith hole and the printing mark, is the real-time position of the ith hole, It is the center position of the printed mark.

[0059] In this embodiment, it should be noted that the expression directly calculates the straight-line distance between two points without introducing any additional assumptions or approximations, and therefore, it provides an accurate measure of the distance between the hole and the center of the print mark; the calculation of the expression is relatively simple, and only basic arithmetic operations (subtraction, square, summation, and square root) are required to quickly calculate the distance between the hole and the center of the print mark, thereby supporting real-time applications, which makes it efficiently implemented on various computing platforms, such as real-time tracking, monitoring, and feedback; the expression can be easily extended to the case of multiple holes, and the distance between each hole and the center of the print mark can be calculated by traversing the position coordinates of all holes.

[0060] In one embodiment, the hole offset between each hole and the printing mark is obtained according to the real-time straight-line distance and the standard straight-line distance between each hole and the printing mark in S4 and is expressed as:

[0061] ;in,

[0062] is the hole offset between the ith hole and the printing mark, is the real-time straight-line distance between the ith hole and the printed mark, is the standard straight-line distance between the ith hole and the printing mark.

[0063] In this embodiment, it should be noted that the expression is used to calculate the offset of the i-th hole in the image relative to the printing mark; by calculating the difference between the real-time straight-line distance and the standard straight-line distance, the offset degree of the hole relative to the printing mark is quantified, which makes the offset a specific value that can be measured and compared. , provides a clear standard for evaluating the offset of holes to determine whether the holes deviate from the acceptable range. It can be applied to the case of multiple holes. By calculating the offset of each hole from the print mark, a comprehensive analysis of the holes in the entire image can be performed. It can be set according to the specific application scenario. The expression has high flexibility. For example, the standard distance can be adjusted as needed under different production batches or process conditions.

[0064] In one embodiment, the grayscale surface image obtained based on the grayscale conversion model and the original surface image in S5 is expressed as:

[0065] ;in,

[0066] is the pixel point in the grayscale surface image The gray value of is the pixel point in the original surface image The red channel value of is the pixel point in the original surface image The green channel value of is the pixel point in the original surface image The blue channel value of

[0067] In this embodiment, it should be noted that in this expression, The coefficients 0.299, 0.587, and 0.114 are set according to the sensitivity of the human eye to different color channels; the human eye is most sensitive to green, followed by red, and finally blue. Therefore, the weight of the green channel is the largest, followed by red, and the smallest is blue. In this way, the converted grayscale image can be better processed later and can also facilitate real-time viewing by staff. Furthermore, grayscale images only contain brightness information, not color information. Therefore, compared with color images, grayscale images have a smaller amount of data and are simpler and more efficient to process.

[0068] like Figure 3 As shown, in one embodiment, obtaining a threshold dot matrix consisting of a plurality of grayscale abnormality thresholds according to the printing mark specification in S6 includes:

[0069] S61, obtaining a printing mark area according to the printing mark specification, and dividing the printing mark area into a plurality of printing mark pixels;

[0070] S62, setting a grayscale abnormality threshold at each print mark pixel point, and forming a threshold dot matrix with multiple grayscale abnormality thresholds according to the positions of the print mark pixel points.

[0071] In this embodiment, it should be noted that in S61, the actual position of the print mark on the brake drum and the area it occupies are determined according to the specific specifications of the print mark, and this area is further subdivided into a series of discrete pixel points. This step is crucial for the subsequent setting of grayscale abnormality thresholds and analysis of grayscale surface images. Specifically, first, it is necessary to obtain the specification information of the printing mark from the design drawing or database of the printing mark, which includes the size (such as length, width), shape, arrangement of characters or patterns, etc. The specifications of the printing mark are usually determined in the design stage and will serve as the basis for subsequent production and monitoring; then, based on the obtained printing mark specifications and the actual size and shape of the brake drum, the specific position of the printing mark on the brake drum and the area it occupies can be determined. This step usually requires the use of image processing technology to assist in completion to ensure the accuracy of the printing mark area; once the printing mark area is determined, it is necessary to further subdivide this area into a series of discrete pixels. The number and density of pixels depend on the required monitoring accuracy. Generally speaking, the denser the pixels, the higher the monitoring accuracy, but correspondingly, the amount of calculation and data storage will also increase. The division of pixels can be achieved through image processing software or algorithms. These software and algorithms can usually divide the image into a uniform pixel grid according to the specified resolution and size. At the same time, it is necessary to ensure that the size of the printing mark pixels when the printing mark area is divided is consistent with the size of the pixels of the grayscale surface image of the printing mark surface, so that subsequent comparison and judgment can be carried out.

[0072] Assume that the mark on a brake drum is a rectangular area containing letters and numbers, with a length of 5mm and a width of 3mm. According to this specification, this rectangular area can be divided into a 50x30 pixel grid (assuming that the size of each pixel is 0.1mm, and the pixel size of the grayscale surface image of the printed surface is also 0.1mm), so we get 1500 printed pixels.

[0073] In S62, it involves setting a grayscale abnormality threshold at each printed mark pixel point divided in S61, and arranging these thresholds into a threshold dot matrix according to the position of the pixel point. Specifically, the grayscale abnormality threshold means that if the grayscale value of a pixel point in the grayscale surface image exceeds this threshold range, the pixel point is considered to be abnormal.

[0074] The grayscale abnormality threshold is a fixed value. The setting of the grayscale abnormality threshold needs to be determined according to the material characteristics of the printed mark, the process parameters of the laser marking, and the required monitoring accuracy. For example, different printed materials may have different colors and textures. These characteristics will affect the distribution of grayscale values. It is necessary to fully understand the color, texture and other characteristics of the printed materials in order to select the appropriate threshold range; the reflectivity and transmittance of the material will also affect the measurement of the grayscale value. For materials with high reflectivity or high transmittance, the grayscale value setting may need to be adjusted to accurately reflect its characteristics; changes in laser power and frequency will affect the clarity of the mark and the distribution of grayscale values. The grayscale abnormality threshold needs to be adjusted according to the actual laser marking process parameters; the marking speed and depth will also affect the measurement of grayscale values. Faster marking speeds may lead to uneven distribution of grayscale values, and the threshold needs to be adjusted accordingly; the resolution and sensitivity of the monitoring system determine the minimum grayscale change that can be detected. According to the required monitoring accuracy, a suitable grayscale abnormality threshold needs to be set to ensure that abnormalities can be accurately detected. When actually setting the grayscale abnormality threshold, first of all, you need to fully understand the color, texture and other characteristics of the printed mark and the background; then, through experiments and analysis, select a grayscale value range that can better distinguish the printed mark from the background (or the abnormal area from the normal area) as the threshold; as needed, you can appropriately adjust the brightness and contrast of the image to improve the contrast between the printed mark and the background.

[0075] Once the grayscale abnormality threshold is set for each printed mark pixel, these thresholds can be arranged into a threshold dot matrix according to the position of the pixel points. Each element in the threshold dot matrix corresponds to the grayscale abnormality threshold of a printed mark pixel point. The size and shape of the threshold dot matrix are the same as the size and shape of the printed mark area, and the position of each element corresponds one-to-one to the position of the corresponding printed mark pixel point.

[0076] By accurately dividing the marking area and pixel points, and setting a suitable grayscale abnormal threshold for each pixel point, the abnormal area in the grayscale surface image can be effectively detected, thereby ensuring the quality of laser marking on the brake drum. This series of steps not only improves the accuracy and efficiency of monitoring, but also reduces the risk of missed detection and misjudgment caused by human factors, providing strong technical support for the production process of brake drums.

[0077] A laser marking position monitoring system for brake drum production is also provided, the system comprising:

[0078] A standard acquisition module is used to acquire the standard positions of multiple holes on a standard brake drum and the standard straight-line distances between the multiple holes and the printed mark, and to collect the original surface image of the printed mark surface of the brake drum after the printing in real time, and to identify the real-time hole positions of each hole in the original surface image according to the standard positions;

[0079] A first calculation module is used to obtain the degree of pixel abnormality within a first preset range around each hole based on the abnormality calculation model, the real-time hole position of each hole and the original surface image;

[0080] A first judgment and processing module is used to judge whether the pixel abnormality of each hole is less than a first threshold value, and if so, obtain the center position of the printing mark where the center point of the printing mark in the original surface image is located, and if not, issue an abnormality notification;

[0081] A second calculation module is used to obtain the real-time straight-line distance between each hole and the printing mark based on the distance calculation model, the real-time hole position of each hole and the center position of the printing mark, and to obtain the hole offset between each hole and the printing mark according to the real-time straight-line distance and the standard straight-line distance between each hole and the printing mark;

[0082] A second judgment and processing module is used to judge whether the hole offsets between each hole and the center point of the printing mark are all less than a second threshold value, and if so, obtain a grayscale surface image based on the grayscale conversion model and the original surface image, and if not, issue an abnormal notification;

[0083] The third judgment and processing module is used to obtain a threshold dot matrix composed of multiple grayscale abnormality thresholds according to the printing specification, and obtain the number of pixel points in the grayscale surface image that exceed the threshold dot matrix as the number of abnormalities, and judge whether the number of abnormalities is less than the third threshold. If so, the monitoring operation is completed, otherwise, an abnormal notification is issued.

[0084] In one embodiment, the first calculation module is also used to: define each first preset range as a neighborhood formed with the real-time position of each hole as the center and a preset distance as the radius, wherein the preset distance is greater than the hole radius; and obtain the degree of pixel abnormality in each neighborhood based on the abnormality calculation model and the original surface image.

[0085] In one embodiment, the third judgment and processing module is also used to: obtain the printing area according to the printing specifications, and divide the printing area into multiple printing pixels; set a grayscale abnormality threshold at each printing pixel, and form a threshold dot matrix with multiple grayscale abnormality thresholds according to the positions of the printing pixels.

[0086] In this embodiment, it should be noted that regarding the above-mentioned laser marking position monitoring system for brake drum production, the specific method of performing the operation has been described in detail in the embodiment of the laser marking position monitoring method for brake drum production, and will not be elaborated here.

[0087] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0088] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0089] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A laser marking position monitoring method for brake drum production, characterized in that: include: Obtaining the standard positions of multiple holes on a standard brake drum and the standard straight-line distances between the multiple holes and the printed mark, and collecting the original surface image of the printed mark surface of the brake drum after the marking in real time, and identifying the real-time hole positions of each hole in the original surface image according to the standard positions; Obtaining the degree of pixel abnormality within a first preset range around each hole based on the abnormality calculation model, the real-time position of each hole and the original surface image; The abnormality calculation model includes: defining each first preset range as a neighborhood formed with the real-time position of each hole as the center and the preset distance as the radius, wherein the preset distance is greater than the hole radius; obtaining the degree of pixel abnormality in each neighborhood based on the abnormality calculation model and the original surface image; Among them, the degree of pixel abnormality in each neighborhood is obtained based on the abnormal calculation model as follows: ;in, is the pixel abnormality of the i-th hole, is the real-time position of the ith hole, For the preset distance, is the radius of the ith hole, is the pixel value of the current pixel in the neighborhood of the i-th hole, is the average pixel value of all pixels in the neighborhood of the i-th hole except the hole, is the weight factor; Determine whether the pixel abnormality of each hole is less than a first threshold value, if so, obtain the center position of the printing mark where the center point of the printing mark in the original surface image is located, if not, issue an abnormality notification; Based on the distance calculation model, the real-time position of each hole and the center position of the printing mark, the real-time straight-line distance between each hole and the printing mark is obtained, and the hole offset between each hole and the printing mark is obtained according to the real-time straight-line distance and the standard straight-line distance between each hole and the printing mark; Determine whether the hole offsets between each hole and the center point of the print mark are all less than a second threshold value, if so, obtain a grayscale surface image based on the grayscale conversion model and the original surface image, if not, issue an abnormal notification; According to the printing specification, a threshold dot matrix composed of multiple grayscale abnormality thresholds is obtained, and the number of pixel points in the grayscale surface image that exceeds the threshold dot matrix is ​​obtained as the abnormal number, and it is determined whether the abnormal number is less than the third threshold. If so, the monitoring operation is completed, otherwise an abnormal notification is issued.

2. The laser marking position monitoring method for brake drum production according to claim 1 is characterized in that: The distance calculation model for obtaining the real-time straight-line distance between each hole and the center point of the printing mark based on the distance calculation model, the real-time hole position of each hole and the center position of the printing mark is expressed as: ;in, is the real-time straight-line distance between the ith hole and the printing mark, is the real-time position of the ith hole, It is the center position of the printed mark.

3. The laser marking position monitoring method for brake drum production according to claim 2 is characterized in that: The hole offset between each hole and the printing mark is obtained according to the real-time straight-line distance and the standard straight-line distance between each hole and the printing mark as follows: ;in, is the hole offset between the ith hole and the printing mark, is the real-time straight-line distance between the ith hole and the printed mark, is the standard straight-line distance between the ith hole and the printing mark.

4. The laser marking position monitoring method for brake drum production according to claim 1 is characterized in that: The grayscale surface image obtained based on the grayscale conversion model and the original surface image is expressed as: ;in, is the pixel point in the grayscale surface image The gray value of is the pixel point in the original surface image The red channel value of is the pixel point in the original surface image The green channel value of is the pixel point in the original surface image The blue channel value of 5. The laser marking position monitoring method for brake drum production according to claim 1 is characterized in that: The step of obtaining a threshold dot matrix composed of a plurality of grayscale abnormality thresholds according to the printing mark specification includes: Acquire a printing mark area according to the printing mark specification, and divide the printing mark area into a plurality of printing mark pixels; A grayscale abnormality threshold is set at each print mark pixel point, and multiple grayscale abnormality thresholds are combined to form a threshold dot matrix according to the positions of the print mark pixels.

6. A laser marking position monitoring system for brake drum production, characterized in that: The system comprises: A standard acquisition module is used to acquire the standard positions of multiple holes on a standard brake drum and the standard straight-line distances between the multiple holes and the printed mark, and to collect the original surface image of the printed mark surface of the brake drum after the printing in real time, and to identify the real-time hole positions of each hole in the original surface image according to the standard positions; A first calculation module is used to obtain the degree of pixel abnormality within a first preset range around each hole based on the abnormality calculation model, the real-time hole position of each hole and the original surface image; The first calculation module is also used to: define each first preset range as a neighborhood formed with the real-time position of each hole as the center and the preset distance as the radius, wherein the preset distance is greater than the hole radius; and obtain the degree of pixel abnormality in each neighborhood based on the abnormality calculation model and the original surface image; Among them, the degree of pixel abnormality in each neighborhood is obtained based on the abnormal calculation model as follows: ;in, is the pixel abnormality of the i-th hole, is the real-time position of the ith hole, For the preset distance, is the radius of the ith hole, is the pixel value of the current pixel in the neighborhood of the i-th hole, is the average pixel value of all pixels in the neighborhood of the i-th hole except the hole, is the weight factor; A first judgment and processing module is used to judge whether the pixel abnormality of each hole is less than a first threshold value, and if so, obtain the center position of the printing mark where the center point of the printing mark in the original surface image is located, and if not, issue an abnormality notification; A second calculation module is used to obtain the real-time straight-line distance between each hole and the printing mark based on the distance calculation model, the real-time hole position of each hole and the center position of the printing mark, and to obtain the hole offset between each hole and the printing mark according to the real-time straight-line distance and the standard straight-line distance between each hole and the printing mark; A second judgment and processing module is used to judge whether the hole offsets between each hole and the center point of the printing mark are all less than a second threshold value, and if so, obtain a grayscale surface image based on the grayscale conversion model and the original surface image, and if not, issue an abnormal notification; The third judgment and processing module is used to obtain a threshold dot matrix composed of multiple grayscale abnormality thresholds according to the printing specification, and obtain the number of pixel points in the grayscale surface image that exceed the threshold dot matrix as the number of abnormalities, and judge whether the number of abnormalities is less than the third threshold. If so, the monitoring operation is completed, otherwise, an abnormal notification is issued.

7. The laser marking position monitoring system for brake drum production according to claim 6 is characterized in that: The third judgment and processing module is also used for: Acquire a printing mark area according to the printing mark specification, and divide the printing mark area into a plurality of printing mark pixels; A grayscale abnormality threshold is set at each print mark pixel point, and multiple grayscale abnormality thresholds are combined to form a threshold dot matrix according to the positions of the print mark pixels.

Images