Online monitoring method and system for wet winding water-resistant cable production

Abstract

The invention relates to the technical field of cable production, and discloses an on-line monitoring method and system for wet winding water-resistant cable production, and the method comprises the steps: continuously shooting a wrapped cable surface image through a high-speed industrial camera, obtaining an image frame sequence, and transmitting the image frame sequence to an on-line monitoring industrial control computer for processing. Secondly, analyzing the surface of the cable in each frame of image by using an image recognition technology so as to extract a time sequence of pitches; whether the uniformity of the pitch time sequence meets a preset standard or not is evaluated through analysis of the pitch time sequence, and once the condition that the uniformity does not meet the requirement is found, a production state abnormity early warning prompt is automatically generated. Therefore, high-precision real-time monitoring on the pitch uniformity of the cable is realized, the production efficiency and the product quality control level are remarkably improved, and the defect that real-time and accurate detection is difficult to realize in the prior art is overcome.

Description

Technical Field

[0001] The present application relates to the technical field of cable production, and more specifically, to an online monitoring method and system for wet-winding water-resistant cable production. Background Art

[0002] In the production process of wet-wound water-resistant cables, ensuring the uniformity of the cables is crucial to ensuring their electrical performance and mechanical strength. The pitch of the cable, that is, the distance between two adjacent windings, is a key parameter to measure the quality of the cable. An ideal cable should have a uniform pitch, which not only helps to improve the water resistance and durability of the cable, but also ensures its stability and safety during use. However, in actual production, due to changes in equipment accuracy, material properties and process conditions, the cable pitch may be uneven, thus affecting the quality of the final product. Therefore, how to effectively detect whether the cable is uniform has become an urgent problem to be solved in the production process.

[0003] Traditional cable quality inspection methods mainly rely on manual inspection or offline measurement technology. These methods usually require operators to manually measure the pitch of the cable surface and judge its uniformity based on experience. Although this method can meet basic quality control requirements to a certain extent, it has obvious limitations. First, manual inspection is inefficient and difficult to adapt to the needs of large-scale production. Secondly, due to the influence of human factors, such as the operator's experience level and fatigue, the inspection results often lack consistency and reliability. In addition, although offline measurement technology can improve the inspection accuracy to a certain extent, due to its non-real-time characteristics, it is impossible to detect and correct problems in the production process in time, which easily leads to an increase in the defective rate. More importantly, whether it is manual inspection or offline measurement, it is difficult to achieve comprehensive monitoring of the entire production process, so that some potential quality risks may be overlooked, which in turn affects the overall quality of the final product.

[0004] Therefore, an optimized online monitoring solution for the production of wet-wound water-resistant cables is expected. Summary of the invention

[0005] In order to solve the above technical problems, this application is proposed. The embodiments of this application provide an online monitoring method and system for wet-winding water-resistant cable production, which uses image recognition and processing technology to monitor the uniformity of cable pitch in real time, significantly improving production efficiency and product quality control level, and overcoming the defects of the prior art that it is difficult to achieve real-time and accurate detection.

[0006] According to one aspect of the present application, there is provided an online monitoring method for the production of wet-wound water-resistant cables, comprising: continuously photographing the surface images of the cable after wrapping by a high-speed industrial camera to obtain an image frame sequence of the surface images of the cable after wrapping; transmitting the image frame sequence of the surface images of the cable after wrapping to an online monitoring industrial computer; on the online monitoring industrial computer, performing image recognition processing on each of the image frame sequence of the surface images of the cable after wrapping to obtain a time series of pitches; on the online monitoring industrial computer, determining whether the pitch uniformity meets preset requirements based on the time series of pitches; on the online monitoring industrial computer, generating an abnormal production status warning prompt in response to the pitch uniformity not meeting the preset requirements.

[0007] In the above-mentioned online monitoring method for the production of wet-wound water-resistant cables, the online monitoring industrial computer performs image recognition processing on each of the image frame sequence of the cable surface image after wrapping to obtain a time series of pitches, including: edge detection on the cable surface image after wrapping to obtain an edge map of the cable after wrapping; line fitting based on Hough transform on the cable edge map after wrapping to obtain a wrapping edge line equation; based on the wrapping edge line equation, identifying key positioning points from the cable edge map after wrapping; based on the key positioning points, identifying the corresponding edges of two adjacent wrapping turns; and calculating the pitch based on the corresponding edges of the two adjacent wrapping turns.

[0008] In the above-mentioned online monitoring method for the production of wet-wound water-resistant cables, edge detection is performed on the surface image of the cable after wrapping to obtain an edge map of the cable after wrapping, including: edge detection is performed on the surface image of the cable after wrapping based on the Canny operator to obtain the edge map of the cable after wrapping.

[0009] In the above-mentioned online monitoring method for the production of wet-wound water-resistant cables, based on the winding edge line equation, key positioning points are identified from the cable edge image after winding, including: selecting the vertical center line of the image of the cable edge image after winding as a reference line; calculating the intersection between the equation of the reference line and the equation of the winding edge line as the key positioning point.

[0010] In the above-mentioned online monitoring method for the production of wet-winding water-resistant cables, the pitch is calculated based on the corresponding edges of the two adjacent windings, including: setting the two adjacent windings as the i-th winding and the i+1-th winding; selecting point P1 in the i-th winding, and searching for point P2 corresponding to point P1 in the i+1-th winding along a direction perpendicular to the winding direction; calculating the axial pixel distance between point P1 and point P2; and multiplying the axial pixel distance by the pixel size ratio to obtain the pitch.

[0011] In the above-mentioned online monitoring method for the production of wet-winding water-resistant cables, the pitch is calculated based on the corresponding edges of the two adjacent windings, including: setting the two adjacent windings as the i-th winding and the i+1-th winding; selecting point P1 in the i-th winding, and searching for point P2 corresponding to point P1 in the i+1-th winding along a direction perpendicular to the winding direction; calculating the axial pixel distance between point P1 and point P2; multiplying the axial pixel distance by the pixel size ratio to obtain an initial pitch; and constraining the initial pitch with coordinate geometry to obtain the pitch.

[0012] In the above-mentioned online monitoring method for wet-winding water-resistant cable production, the initial pitch is constrained by coordinate geometry to obtain the pitch, including: for the key points P1 and P2 corresponding to each initial pitch, the Hough transform angular space representation corresponding to the key points P1 and P2 is calculated by the following formula to obtain the key point angular space representation corresponding to each initial pitch, wherein the formula is: ;in, and are the spatial coordinates of the key points P1 and P2 respectively, and The keypoint angular space representation corresponding to each initial pitch.

[0013] Based on the key point angle space representation corresponding to each initial pitch, the vertical slope reference correction amount corresponding to each initial pitch is calculated using the following formula, wherein the formula is: ;in, represents the initial pitch, Indicates the vertical slope reference correction.

[0014] Based on the key point angle space representation corresponding to each initial pitch, the axial intersection constraint correction amount corresponding to each initial pitch is calculated using the following formula, wherein the formula is: ;in, Represents the axial intersection constraint correction.

[0015] Based on the vertical slope reference correction amount and the axial intersection constraint correction amount, the initial pitch is corrected using the following formula, wherein the formula is: ;in, Indicates pitch.

[0016] In the above-mentioned online monitoring method for the production of wet-winding water-resistant cables, the online monitoring industrial computer determines whether the pitch uniformity meets the preset requirements based on the time series of the pitch, including: defining the target pitch and the absolute tolerance band; calculating the acceptable range of pitches based on the target pitch and the absolute tolerance band; judging whether each pitch in the time series of the pitch is within the acceptable range of the pitch to obtain a set of out-of-tolerance judgment results; if the proportion of the number of out-of-tolerance judgment results that are not within the acceptable range of the pitch in the set of out-of-tolerance judgment results exceeds a preset threshold, it is determined that the pitch uniformity does not meet the preset requirements.

[0017] According to another aspect of the present application, there is also provided an online monitoring system for the production of wet-wound water-resistant cables, the online monitoring system for the production of wet-wound water-resistant cables comprising: a cable surface image acquisition module, for continuously photographing the cable surface image after wrapping by a high-speed industrial camera to obtain an image frame sequence of the cable surface image after wrapping; a cable surface image transmission module, for transmitting the image frame sequence of the cable surface image after wrapping to an online monitoring industrial computer; a cable surface image recognition and processing module, for performing image recognition processing on each of the image frame sequence of the cable surface image after wrapping in the online monitoring industrial computer to obtain a time series of pitches; a pitch uniformity evaluation module, for determining on the online monitoring industrial computer whether the pitch uniformity meets preset requirements based on the pitch time series; and a production status abnormality warning module, for generating a production status abnormality warning prompt on the online monitoring industrial computer in response to the pitch uniformity not meeting the preset requirements.

[0018] Compared with the prior art, the online monitoring method and system for the production of wet-winding water-resistant cables provided by the present application continuously capture the surface image of the cable after wrapping with a high-speed industrial camera, obtain the image frame sequence, and transmit it to the online monitoring industrial computer for processing. Then, the cable surface in each frame of the image is analyzed using image recognition technology to extract the time series of the pitch. By analyzing the pitch time series, it is evaluated whether its uniformity meets the preset standards. Once it is found that it does not meet the requirements, an abnormal production status warning prompt is automatically generated. In this way, high-precision real-time monitoring of the uniformity of cable pitch is achieved, which significantly improves the production efficiency and product quality control level, and overcomes the defects of the prior art that it is difficult to achieve real-time and accurate detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0020] Figure 1 A schematic flow chart of an online monitoring method for wet-winding water-resistant cable production according to an embodiment of the present application is illustrated.

[0021] Figure 2 The diagram illustrates a schematic flow chart of S3 in the online monitoring method for wet-winding water-resistant cable production according to an embodiment of the present application.

[0022] Figure 3 The figure illustrates a schematic flow chart of S33 in the online monitoring method for wet-winding water-resistant cable production according to an embodiment of the present application.

[0023] Figure 4 The figure illustrates a schematic flow chart of S35 in the online monitoring method for wet-winding water-resistant cable production according to an embodiment of the present application.

[0024] Figure 5 The figure illustrates a schematic flow chart of a preferred embodiment of S35 in the online monitoring method for wet-winding water-resistant cable production according to an embodiment of the present application.

[0025] Figure 6 The diagram illustrates a schematic flow chart of S4 in the online monitoring method for wet-winding water-resistant cable production according to an embodiment of the present application.

[0026] Figure 7 A schematic block diagram of an online monitoring system for wet-winding water-resistant cable production according to an embodiment of the present application is illustrated. DETAILED DESCRIPTION

[0027] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0028] Figure 1 The figure shows a schematic flow chart of an online monitoring method for wet-winding water-resistant cable production according to an embodiment of the present application. Figure 1As shown, the present application provides an online monitoring method for the production of wet-wound water-resistant cables, including: S1, continuously photographing the surface images of the cable after wrapping by a high-speed industrial camera to obtain an image frame sequence of the surface images of the cable after wrapping; S2, transmitting the image frame sequence of the surface images of the cable after wrapping to an online monitoring industrial computer; S3, on the online monitoring industrial computer, performing image recognition processing on each surface image of the cable after wrapping in the image frame sequence of the surface images of the cable after wrapping to obtain a time series of pitches; S4, on the online monitoring industrial computer, determining whether the pitch uniformity meets the preset requirements based on the time series of the pitches; S5, on the online monitoring industrial computer, generating an abnormal production status warning prompt in response to the pitch uniformity not meeting the preset requirements.

[0029] Exemplarily, in step S1, a high-speed industrial camera is used to continuously capture images of the cable surface after wrapping to obtain an image frame sequence of the cable surface image after wrapping. It should be understood that, compared with traditional manual inspection or offline measurement methods, high-speed industrial cameras can be used to carefully inspect cables of every meter or even shorter length without affecting the speed of the production line. This high-frequency data acquisition method allows any subtle changes to be recorded, thereby providing a solid foundation for subsequent quality control. In addition, due to the use of digital image processing technology, data can be quickly analyzed and the cable quality can be instantly judged according to preset standards to see whether it meets the standards. Therefore, this method greatly improves the detection efficiency and accuracy and reduces the defective rate.

[0030] In one embodiment, a high-speed industrial camera system is installed directly on the production line. The system typically includes one or more high-speed industrial cameras, a light source, and a computer system connected thereto. High-speed industrial cameras should be installed at key locations on the cable production line to ensure that the entire area to be monitored can be covered. In order to obtain clear images, proper lighting is essential. The choice of light source must take into account the reflective properties of the cable material to avoid overexposure or shadows that affect image quality. Once the hardware setup is complete, the high-speed industrial camera will continuously capture images of the cable surface at a predetermined frame rate (e.g., hundreds of frames per second) and transmit these image frames to the online monitoring industrial computer for further processing. In this way, it can be seamlessly integrated into existing production lines without significantly changing the existing equipment layout.

[0031] Exemplarily, in step S2, the image frame sequence of the cable surface image after wrapping is transmitted to the online monitoring industrial computer. It should be understood that a large amount of image data captured by a high-speed industrial camera needs to be processed and analyzed by powerful computing resources. The online monitoring industrial computer has sufficient computing power and storage space to efficiently process these high-resolution image frame sequences and execute complex image recognition algorithms to extract key information, such as cable pitch. In addition, the online monitoring industrial computer can also instantly determine whether the cable quality meets the standards according to the preset standards, and quickly generate early warning prompts when problems are found, so that corrective measures can be taken in time. This not only improves the detection efficiency, but also greatly reduces the defective rate and improves the overall performance of the production line.

[0032] In one embodiment, wireless communication technology is used to complete the transmission of image frame sequences. With the development of 5G and other high-speed wireless communication technologies, it is now possible to use wireless networks to send image frames from high-speed industrial cameras to online monitoring industrial computers without sacrificing transmission speed and data integrity. This method is particularly suitable for scenarios where wiring is difficult or the location of equipment needs to be adjusted frequently. For example, on some temporary production lines or when production equipment needs to be moved regularly, wireless transmission solutions provide great flexibility.

[0033] Exemplarily, in step S3, the online monitoring industrial computer performs image recognition processing on each of the image frame sequences of the cable surface images after wrapping to obtain a time series of pitches. It should be understood that in the production process of wet-winding water-resistant cables, ensuring uniform cable pitch is crucial to ensuring product quality. By continuously photographing the cable surface images after wrapping with a high-speed industrial camera and transmitting these image frame sequences to the online monitoring industrial computer for further processing, real-time monitoring and evaluation of cable quality can be achieved. The core of this process is to use image recognition technology to analyze the cable surface features in each frame of the image to extract the time series of pitches.

[0034] In one embodiment, Figure 2 As shown, in step S3, the online monitoring industrial computer performs image recognition processing on each of the image frame sequence of the cable surface image after wrapping to obtain a time series of pitches, including: S31, edge detection on the cable surface image after wrapping to obtain an edge map of the cable after wrapping; S32, line fitting based on Hough transform on the cable edge map after wrapping to obtain a wrapping edge line equation; S33, based on the wrapping edge line equation, identifying key positioning points from the cable edge map after wrapping; S34, based on the key positioning points, identifying the corresponding edges of two adjacent wrapping turns; S35, calculating the pitch based on the corresponding edges of the two adjacent wrapping turns.

[0035] Specifically, first, edge detection is performed on the cable surface image after wrapping to obtain an edge map of the cable after wrapping. In one embodiment, edge detection is performed on the cable surface image after wrapping to obtain an edge map of the cable after wrapping, including: edge detection is performed on the cable surface image after wrapping based on the Canny operator to obtain the edge map of the cable after wrapping. Specifically, the Canny operator is a classic edge detection algorithm, which calculates the gradient direction and amplitude of each pixel in the image, and then applies non-maximum suppression (Non-Maximum Suppression) and double threshold processing to determine the edge position.

[0036] Then, since the wrapping is usually spiral, the edges presented in the local image are approximated to straight lines or slightly curved curves. Therefore, Hough transform can be used to detect and fit these lines. Specifically, Hough transform is a line detection algorithm that can map points in image space to parameter space and then find all possible lines. Assume that the wrapping edge line equation is in the form of: ; can be solved by Hough transform and Specifically, for edge images Every point in , we can construct a and The equation is: ; and map it to the parameter space. By counting each point in the parameter space The number of times it is mapped can find the point with the highest frequency as the optimal solution. Therefore, the edge line equation of the wrapping can be obtained by the following method: ;in, is the Dirac function, which indicates that The count increases by one.

[0037] Based on the above-mentioned wrapping edge line equation, key positioning points are identified from the cable edge map after wrapping. Figure 3 As shown, in step S33, based on the wrapping edge line equation, the key positioning point is identified from the cable edge image after wrapping, including: S331, selecting the image vertical center line of the cable edge image after wrapping as a reference line, and its equation can be expressed as ,in is half of the image width; S332, calculating the intersection between the equation of the reference line and the equation of the wrapping edge line as the key positioning point, assuming that the equation of the wrapping edge line is , then the key positioning point satisfy: ; Then, the corresponding edges of two adjacent wrapping circles are identified based on the key positioning points. Specifically, the slope and position of the fitted straight line / curve are grouped, and roughly parallel lines are classified into one category. Search perpendicular to the wrapping direction (or approximately perpendicular) to find the closest edge of the same type belonging to the next circle (for example, both front edges or both rear edges).

[0038] Finally, the pitch is calculated based on the corresponding edges of the two adjacent windings. Figure 4 As shown, in step S35, the pitch is calculated based on the corresponding edges of the two adjacent windings, including: S351, setting the two adjacent windings as the i-th winding and the (i+1)-th winding; S352, selecting point P1 in the i-th winding, and searching for point P2 in the (i+1)-th winding corresponding to point P1 along a direction perpendicular to the winding direction; S353, calculating the axial pixel distance between point P1 and point P2; S354, multiplying the axial pixel distance by the pixel size ratio to obtain the pitch.

[0039] In particular, for the time series of pitch, for example, it can be expressed as , each of which corresponds to a pair of key positioning points corresponding to the edge line equation of the package, and the pair of edge line equations of the package will have the discreteness based on the straight line features in the image space, that is, the discrete peak distribution of the line space based on the line fitting of the Hough transform. Therefore, due to the mapping of the discrete points in the parameter space to the time-series space distribution, the time-series space distribution is no longer limited to the discreteness assumption of the original parameter space. In order to make the time-series distribution of the pitch based on the axial distance more accurate, it is necessary to establish the coordinate geometry relationship constraint of the pitch.

[0040] Therefore, in a preferred embodiment, Figure 5 As shown, in step S35, the pitch is calculated based on the corresponding edges of the two adjacent windings, including: S351, setting the two adjacent windings as the i-th winding and the i+1-th winding; S352, selecting point P1 in the i-th winding, and searching for point P2 corresponding to point P1 in the i+1-th winding along a direction perpendicular to the winding direction; S353, calculating the axial pixel distance between point P1 and point P2; S354, multiplying the axial pixel distance by the pixel size ratio to obtain an initial pitch; S355, performing coordinate geometry constraints on the initial pitch to obtain a pitch.

[0041] In a specific embodiment, the initial pitch is constrained by coordinate geometry to obtain the pitch, including: for the key points P1 and P2 corresponding to each initial pitch, the Hough transform angular space representation corresponding to the key points P1 and P2 is calculated by the following formula to obtain the key point angular space representation corresponding to each initial pitch, wherein the formula is: ;in, and are the spatial coordinates of the key points P1 and P2 respectively, and The keypoint angular space representation corresponding to each initial pitch.

[0042] Based on the key point angle space representation corresponding to each initial pitch, the vertical slope reference correction amount corresponding to each initial pitch is calculated using the following formula, wherein the formula is: ;in, represents the initial pitch, Indicates the vertical slope reference correction.

[0043] Based on the key point angle space representation corresponding to each initial pitch, the axial intersection constraint correction amount corresponding to each initial pitch is calculated using the following formula, wherein the formula is: ;in, Represents the axial intersection constraint correction.

[0044] Based on the vertical slope reference correction amount and the axial intersection constraint correction amount, the initial pitch is corrected using the following formula, wherein the formula is: ;in, Indicates pitch.

[0045] That is, the vertical slope reference is introduced into the explicit geometric reference standard of the axial intersection constraint, thereby limiting the search space of the timing distribution and reducing the timing correlation mismatch caused by continuous breaks or ambiguity caused by discreteness, thereby improving the accuracy of the timing distribution of the pitch.

[0046] In one embodiment, Figure 6 As shown, in step S4, the online monitoring industrial computer determines whether the pitch uniformity meets the preset requirements based on the time series of the pitch, including: S41, defining the target pitch and the absolute tolerance band; S42, calculating the acceptable range of the pitch based on the target pitch and the absolute tolerance band; S43, judging whether each pitch in the time series of the pitch is within the acceptable range of the pitch to obtain a set of out-of-tolerance judgment results; S44, if the proportion of the number of out-of-tolerance judgment results that are not within the acceptable range of the pitch in the set of out-of-tolerance judgment results exceeds a preset threshold, it is determined that the pitch uniformity does not meet the preset requirements.

[0047] Specifically, first of all, defining the target pitch and the absolute tolerance zone is the basis of the entire evaluation process. The target pitch refers to the distance that should be maintained between two adjacent winding turns under ideal conditions. Usually, this value is determined by the production process design. For example, a specific model of cable may be designed with a target pitch of 50 mm. The absolute tolerance zone is the allowable pitch deviation range, usually expressed as a positive or negative percentage or a fixed value. In a specific embodiment, for the above-mentioned target pitch of 50 mm, assuming that the maximum allowable deviation is ±2 mm, the absolute tolerance zone is [-2, +2] mm.

[0048] Based on the target pitch and the absolute tolerance band, the acceptable range of the pitch can be calculated. The target pitch is , the absolute tolerance band is , then the acceptable range of pitch , in the above embodiment, This means that any pitch value that falls within this range is considered acceptable, while any pitch outside this range is considered unacceptable.

[0049] Next, the online monitoring IPC will judge each pitch value in the pitch time series to see whether it falls within the acceptable range. Specifically, for each pitch value , check whether it meets the following conditions: , if a certain pitch value If the above conditions are not met, it will be marked as out of tolerance. To better understand this process, in a specific embodiment, assume that the pitch time series of a certain cable section is [50.1 mm, 49.9 mm, 52.3 mm, 47.8 mm, 50.5 mm], the target pitch is 50 mm, and the absolute tolerance band is ±2 mm. Based on the above conditions, the following conclusions can be drawn: 50.1 mm: qualified; 49.9 mm: qualified; 52.3 mm: unqualified (out of tolerance); 47.8 mm: unqualified (out of tolerance); 50.5 mm: qualified.

[0050] Finally, the number of out-of-tolerance pitches is counted and compared with the preset threshold to determine whether the pitch uniformity meets the preset requirements. In this specific embodiment, the preset threshold is set to 5%, that is, no more than 5% of the pitch values ​​are allowed to exceed the acceptable range. In this example, there are 5 pitch values, of which 2 are out-of-tolerance pitches, accounting for 40%. Obviously, 40% is much higher than the preset threshold of 5%, so it can be determined that the pitch uniformity of this section of cable does not meet the preset requirements. Of course, the above is only an example, and the specific values ​​can be adjusted according to actual conditions or experiments, and this application does not make specific restrictions.

[0051] Exemplarily, in step S5, in the online monitoring industrial computer, in response to the pitch uniformity not meeting the preset requirements, an abnormal production status warning prompt is generated. It should be understood that by automatically generating an abnormal production status warning prompt, not only the detection efficiency and accuracy are improved, but also a quick response can be made when a problem occurs to avoid further production of defective products. At the same time, through continuous monitoring and timely adjustment, the production process can be optimized, and the overall production efficiency and product quality can be improved. In addition, the early warning prompt can also be integrated with other automated control systems to achieve more efficient production management and quality control. In other examples, when the system detects that the pitch uniformity does not meet the requirements, it can not only issue a warning, but also automatically adjust the production equipment parameters to reduce the need for human intervention and further improve the level of automation in production.

[0052] In summary, the online monitoring method for the production of wet-winding water-resistant cables provided by the present application continuously captures images of the cable surface after wrapping with a high-speed industrial camera, obtains an image frame sequence, and transmits it to an online monitoring industrial computer for processing. Then, the cable surface in each frame of the image is analyzed using image recognition technology to extract the time series of the pitch. By analyzing the pitch time series, it is evaluated whether its uniformity meets the preset standards. Once a situation that does not meet the requirements is found, an abnormal production status warning prompt is automatically generated. In this way, high-precision real-time monitoring of the uniformity of cable pitch is achieved, which significantly improves production efficiency and product quality control level, and overcomes the defects of the prior art that it is difficult to achieve real-time and accurate detection.

[0053] The present application also provides an online monitoring system for wet-winding water-resistant cable production, such as Figure 7 As shown, the online monitoring system 700 for the production of wet-winding water-resistant cables includes: a cable surface image acquisition module 710, which is used to continuously shoot the cable surface image after wrapping through a high-speed industrial camera to obtain an image frame sequence of the cable surface image after wrapping; a cable surface image transmission module 720, which is used to transmit the image frame sequence of the cable surface image after wrapping to the online monitoring industrial computer; a cable surface image recognition and processing module 730, which is used to perform image recognition processing on each of the cable surface images after wrapping in the image frame sequence of the cable surface image after wrapping on the online monitoring industrial computer to obtain a time series of pitches; a pitch uniformity evaluation module 740, which is used to determine whether the pitch uniformity meets the preset requirements based on the pitch time series on the online monitoring industrial computer; a production status abnormality warning module 750, which is used to generate a production status abnormality warning prompt on the online monitoring industrial computer in response to the pitch uniformity not meeting the preset requirements.

[0054] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0055] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0056] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0057] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0058] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. An online monitoring method for wet-winding water-resistant cable production, characterized in that: include: Continuously photographing the surface image of the cable after wrapping by a high-speed industrial camera to obtain an image frame sequence of the surface image of the cable after wrapping; Transmitting the image frame sequence of the cable surface image after wrapping to an online monitoring industrial computer; On the online monitoring industrial computer, image recognition processing is performed on each of the image frames of the image of the cable surface after wrapping to obtain a time series of pitches; In the online monitoring industrial computer, determining whether the pitch uniformity meets the preset requirements based on the time series of the pitch; In the online monitoring industrial computer, in response to the pitch uniformity not meeting the preset requirements, an abnormal production status warning is generated.

2. The online monitoring method for wet-wound water-resistant cable production according to claim 1, characterized in that: On the online monitoring industrial computer, image recognition processing is performed on each of the image frame sequences of the cable surface images after wrapping to obtain a time series of pitches, including: edge detection is performed on the cable surface images after wrapping to obtain an edge map of the cable after wrapping; line fitting is performed on the cable edge map after wrapping based on Hough transform to obtain a wrapping edge line equation; based on the wrapping edge line equation, key positioning points are identified from the cable edge map after wrapping; based on the key positioning points, corresponding edges of two adjacent wrapping turns are identified; and based on the corresponding edges of the two adjacent wrapping turns, the pitch is calculated.

3. The online monitoring method for wet-winding water-resistant cable production according to claim 2 is characterized in that: Performing edge detection on the surface image of the wrapped cable to obtain an edge map of the wrapped cable includes: performing edge detection on the surface image of the wrapped cable based on a Canny operator to obtain an edge map of the wrapped cable.

4. The online monitoring method for wet-wound water-resistant cable production according to claim 2, characterized in that: Based on the wrapping edge line equation, key positioning points are identified from the cable edge image after wrapping, including: selecting the vertical center line of the image of the cable edge image after wrapping as a reference line; calculating the intersection between the equation of the reference line and the wrapping edge line equation as the key positioning point.

5. The online monitoring method for wet-winding water-resistant cable production according to claim 2, characterized in that: The pitch is calculated based on the corresponding edges of the two adjacent windings, including: setting the two adjacent windings as the i-th winding and the (i+1)-th winding; selecting point P1 on the i-th winding, and searching for point P2 on the (i+1)-th winding corresponding to point P1 along a direction perpendicular to the winding direction; calculating the axial pixel distance between point P1 and point P2; and multiplying the axial pixel distance by the pixel size ratio to obtain the pitch.

6. The online monitoring method for wet-wound water-resistant cable production according to claim 2, characterized in that: The pitch is calculated based on the corresponding edges of the two adjacent windings, including: setting the two adjacent windings as the i-th winding and the i+1-th winding; selecting point P1 on the i-th winding, and searching for point P2 on the i+1-th winding corresponding to point P1 along a direction perpendicular to the winding direction; calculating the axial pixel distance between point P1 and point P2; multiplying the axial pixel distance by the pixel size ratio to obtain an initial pitch; and performing coordinate geometry constraints on the initial pitch to obtain the pitch.

7. The online monitoring method for wet-winding water-resistant cable production according to claim 6, characterized in that: The initial pitch is constrained by coordinate geometry to obtain the pitch, including: for P1 and P2 corresponding to each initial pitch, calculating the Hough transform angular space representation corresponding to P1 and P2 by the following formula to obtain the key point angular space representation corresponding to each initial pitch, wherein the formula is: ;in, and are the spatial coordinates of the key points P1 and P2 respectively, and The key point angle space representation corresponding to each initial pitch; based on the key point angle space representation corresponding to each initial pitch, the vertical slope reference correction amount corresponding to each initial pitch is calculated by the following formula, wherein the formula is: ;in, represents the initial pitch, represents the vertical slope reference correction; based on the key point angle space representation corresponding to each initial pitch, the axial intersection constraint correction corresponding to each initial pitch is calculated by the following formula, wherein the formula is: ;in, represents the axial intersection constraint correction; based on the vertical slope reference correction and the axial intersection constraint correction, the initial pitch is corrected by the following formula, wherein the formula is: ;in, Indicates pitch.

8. The online monitoring method for wet-winding water-resistant cable production according to claim 1, characterized in that: In the online monitoring industrial computer, whether the pitch uniformity meets the preset requirements is determined based on the time series of the pitch, including: defining a target pitch and an absolute tolerance band; calculating an acceptable range of pitches based on the target pitch and the absolute tolerance band; judging whether each pitch in the time series of the pitch is within the acceptable range of the pitch to obtain a set of out-of-tolerance judgment results; if the proportion of the number of out-of-tolerance judgment results that are not within the acceptable range of the pitch in the set of out-of-tolerance judgment results exceeds a preset threshold, it is determined that the pitch uniformity does not meet the preset requirements.

9. An online monitoring system for wet-winding water-resistant cable production, characterized in that: include: A cable surface image acquisition module is used to continuously shoot the cable surface image after wrapping through a high-speed industrial camera to obtain an image frame sequence of the cable surface image after wrapping; A cable surface image transmission module, used for transmitting the image frame sequence of the cable surface image after wrapping to an online monitoring industrial computer; A cable surface image recognition processing module is used to perform image recognition processing on each of the wrapped cable surface images in the image frame sequence of the wrapped cable surface images on the online monitoring industrial computer to obtain a time series of pitches; A pitch uniformity evaluation module, used for determining whether the pitch uniformity meets the preset requirements based on the time series of the pitch in the online monitoring industrial computer; The production status abnormality warning module is used to generate a production status abnormality warning prompt in response to the pitch uniformity not meeting the preset requirements in the online monitoring industrial computer.

Images