Image recognition-based cable tie plate cable tying method, system, device, and medium

Abstract

The application relates to the technical field of image recognition, in particular to a wire board wiring method and system based on image recognition, equipment and a medium. The application obtains standard format drawing data by pre-processing a cable layout drawing, extracts key features of the wire by using computer vision technology combined with color ID coding rules, and matches an adaptive wire board template from a standard template library; based on the feature data and the template parameters, the system calculates a non-crossing wire layout scheme and an optimal card placement rod distribution scheme; in actual operation, a display dynamically displays a process guide pattern, a camera is used to monitor the operation process in real time, and an alarm is given and a rollback operation is performed in a timely manner when an abnormality is found. The application solves the problems of low efficiency and unstable quality of traditional manual operation, realizes automatic planning of the wiring path, ensures controllability of the operation process, and improves the automation level and product quality of the wire board manufacturing.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image recognition, in particular to a cable tie plate cable tying method, system, device and medium based on image recognition. BACKGROUND

[0002] With the rapid development of industrial automation and intelligent manufacturing, cable wiring is increasingly widely used in various electronic devices, automobiles, aerospace and other fields. As a key tool for cable fixing and organizing, the design and implementation of the cable tie scheme of the cable tie plate directly affects the quality and reliability of the product. Efficient and accurate cable tie scheme generation is of great significance to improve production efficiency and product quality.

[0003] Traditional processes mainly rely on manual completion of drawing drawing, drawing conversion and cable tying operations. Processing a single drawing often takes several hours, and manual identification is prone to confusion of wire models or paths, and the standardization of operations is heavily dependent on the personal experience of the operator.

[0004] Although the prior art introduces some automated equipment for cable tying operations, a large amount of manual intervention is still required in the drawing analysis and layout design process. This semi-automatic operation method cannot achieve intelligent processing of the entire process, especially when faced with cable tying requirements of multiple specifications and complex topologies, the cable tying efficiency is low, and this situation needs to be further improved. SUMMARY

[0005] In order to solve the problem that the existing cable tying operation cannot achieve intelligent processing of the entire process, especially when faced with cable tying requirements of multiple specifications and complex topologies, the cable tying efficiency is low, the present application provides a cable tie plate cable tying method, system, device and medium based on image recognition, which adopts the following technical solutions:

[0006] In a first aspect, the present application provides a cable tie plate cable tying method based on image recognition, comprising the following steps:

[0007] Receiving and preprocessing the cable layout drawing provided by the customer to obtain preprocessed standard format drawing data;

[0008] According to the standard format drawing data, using computer vision to analyze the drawing and combining the pre-set color ID coding rule to obtain a wire key feature data set;

[0009] Based on the wire key feature data set, template matching is performed from a pre-defined standard template library to obtain an adapted cable tie plate template;

[0010] According to the wire key feature data set and the adapted cable tie plate template, the non-crossing wire path and the optimal clamping rod distribution scheme are calculated to obtain an executable cable tying operation instruction set;

[0011] Based on the cable binding operation instruction set, a display is controlled to dynamically render a process drawing and a camera is used to collect a cable rod insertion operation picture in real time to obtain real-time operation state data.

[0012] According to the real-time operation state data, an operation deviation value is calculated and an exception is judged. When an exception is detected, an alarm is triggered and a rollback operation is performed.

[0013] By adopting the technical scheme, the cable layout drawing provided by a customer is preprocessed first, and the cable layout drawing is converted into standard format drawing data. Then, the drawing is analyzed by using computer vision technology, and key feature data of the wires, including wire routing path, model and other information, are extracted by combining with a preset color ID coding rule. Next, a matched cable binding plate template is matched from a predefined standard template library, and a non-crossing wire routing scheme and an optimal cable rod distribution scheme are calculated based on the wire feature data and the template parameters. In the actual operation process, the system dynamically displays a process guidance drawing through a display, and the insertion process of the cable rod is monitored in real time by using a camera. When it is found that the operation deviation exceeds the allowed range, the system will timely alarm and perform a rollback operation to ensure the accurate execution of each process. Not only the problems of low efficiency and unstable quality of traditional manual operation are solved, but also the optimal routing path is automatically planned, and the controllability of the operation process is ensured, which significantly improves the automation level and product quality of the cable binding plate manufacturing.

[0014] Optionally, the wire key feature data set includes cable rod position parameters, cable tie spacing requirements, and a mapping relationship between wire models and cable rods. According to the standard format drawing data, the drawing is analyzed by using computer vision and combining with a preset color ID coding rule to obtain the wire key feature data set, which specifically includes the following steps:

[0015] The standard format drawing data is image segmented to identify the wire routing path, and different wires are identified according to the preset color ID coding rule to determine the cable rod position parameters. The image segmentation is based on the preprocessed wire connection relationship data, endpoint coordinate data and line features in the drawing;

[0016] According to the inflection point and intersection point positions of the wire routing path, the spacing requirements between adjacent wire bundles are calculated by combining with the wire grouping information identified by the color ID, to obtain the cable tie spacing requirements;

[0017] The wire model markings in the drawing are identified, and a mapping relationship between the wire models and the cable rods is established according to the color ID coding rule and the cable rod position parameters;

[0018] The cable rod position parameters, the cable tie spacing requirements, and the mapping relationship between the wire models and the cable rods are integrated to generate the wire key feature data set.

[0019] By adopting the technical scheme, firstly, the standard format drawing data is subjected to image segmentation, the system identifies the conductor wiring path based on the preprocessed conductor connection relationship data, endpoint coordinate data and line features in the drawing, adds an identification to different conductors using a preset color ID coding rule, thereby determining the position parameters of the clamping rod; then the system analyzes the inflection point and intersection point positions in the conductor wiring path, combines the conductor grouping information of the color ID identification, automatically calculates the spacing that should be maintained between adjacent conductor bundles, thereby obtaining reasonable requirements for the cable tie spacing; then the conductor model markings in the drawing are identified, and the color ID coding rule and the clamping rod position parameters are combined to establish a correspondence between the conductor model and the clamping rod; finally, the clamping rod position parameters, the cable tie spacing requirements and the mapping relationship between the conductor model and the clamping rod are integrated to generate a complete conductor key feature data set; the automatic extraction of the conductor key information is realized, and the data acquisition efficiency is greatly improved.

[0020] Optionally, the clamping rod position parameters include main line clamping rod position parameters and branch line clamping rod position parameters, the standard format drawing data is subjected to image segmentation, the conductor wiring path is identified, and the clamping rod position parameters are determined, and the specific steps include the following steps:

[0021] According to the conductor wiring path, the main line direction and the branch line direction are identified, and the main line key nodes and the branch line key nodes are obtained;

[0022] According to the main line key nodes and the branch line key nodes, the main line clamping rod position parameters and the branch line clamping rod position parameters are calculated.

[0023] By adopting the technical scheme, firstly, the conductor wiring path is analyzed, the main direction of the main line and the directions of the branch lines extending therefrom are identified, and the key nodes on the main line and the branch lines are respectively determined, and these key nodes usually include important positions such as conductor convergence points and turning points; then based on these identified key nodes, the system respectively calculates the clamping rod position parameters required by the main line and the branch lines, and in the calculation process, the load bearing requirement of the main line and the flexibility requirement of the branch lines are fully considered; by distinguishing the different characteristics of the main line and the branch lines, the differential arrangement of the clamping rod positions is realized, which not only ensures the stability of the main line, but also guarantees the flexibility of the branch lines, so that the clamping rod layout of the whole cable management board is more reasonable and practical.

[0024] Optionally, according to the conductor key feature data set and the adapted cable management board template, a non-crossing conductor path and an optimal clamping rod distribution scheme are calculated to obtain an executable cable management operation instruction set, and the specific steps include the following steps:

[0025] Based on the mapping relationship between the wire type and the clamping rod in the wire key feature data set, the topological relationship between the wires is calculated to obtain the wire hierarchical distribution information;

[0026] According to the wire hierarchical distribution information and the industry compliance constraint parameters in the adapted cable tie plate template, a non-crossing wire path is calculated;

[0027] Based on the non-crossing wire path, the clamping rod layout is optimized in combination with the cable tie spacing requirement to obtain an optimal clamping rod distribution scheme that minimizes the movement distance of the mechanical arm;

[0028] The non-crossing wire path and the optimal clamping rod distribution scheme are converted into a sequence of executable operation instructions of the device to generate a set of executable cable tie operation instructions, which includes clamping rod insertion instructions and cable tie fixing instructions.

[0029] By adopting the above technical solution, the present application first analyzes the topological relationship between the wires based on the mapping relationship between the wire type and the clamping rod, establishes the hierarchical distribution information of the wires, and clearly defines the spatial positional relationship of the wires; then, in combination with the industry compliance constraint parameters, a wire routing path that avoids crossing is calculated based on the hierarchical distribution information; then, the system optimizes the layout of the clamping rod according to the planned non-crossing path, taking into account the cable tie spacing requirement, and calculates a clamping rod distribution scheme that can minimize the movement distance of the mechanical arm through an algorithm; finally, the planned wire path and the clamping rod layout are converted into a specific sequence of operation instructions, including detailed information such as clamping rod insertion position, sequence, and cable tie fixing point, etc. Not only is the crossing-free arrangement of the wires ensured, but the operation efficiency is also improved by optimizing the movement trajectory of the mechanical arm.

[0030] Optionally, the non-crossing wire path is calculated according to the wire hierarchical distribution information and the industry compliance constraint parameters in the adapted cable tie plate template, specifically including the following steps:

[0031] Detect whether there is a crossing point between the connections of the key nodes of the main line, and if there is a crossing point, obtain the crossing region information;

[0032] According to the crossing region information, the number of affected branch line key nodes is calculated, and the affected branch line key nodes are classified according to the distance to the crossing region to obtain the branch line optimization level;

[0033] Based on the branch line optimization level, in combination with the wire bending radius limit in the industry compliance constraint parameters, the offset range of each branch line key node is calculated;

[0034] If the offset range meets the industry compliance constraint parameter requirements, then adjust the position of the key node of the corresponding branch line and recalculate the connection path with the key node of the main line.

[0035] If the offset range does not meet the preset range requirements, the position of the key node of the corresponding main line will be adjusted, and the connection path of the affected branch line will be updated.

[0036] By adopting the above technical solution, this application first detects the connections between key nodes of the main line to determine whether there are intersections. If so, it records the location and range information of the intersection area in detail. Then, based on the intersection area information, it counts the number of key nodes of all affected branch lines and processes them according to their distance from the intersection area, with the closer the distance, the higher the optimization level. Then, for each branch line key node, it calculates the adjustable position range of the node based on the conductor bending radius limit specified in industry standards. When the calculated offset range meets industry compliance requirements, the system will prioritize adjusting the position of the branch line key node and replan its connection path with the main line. If the offset range of the node exceeds the preset limit, the system will then adjust the position of the main line key node and update the connection path of all affected branch lines accordingly. This achieves automated resolution of conductor intersection problems, ensuring that the optimized cabling scheme meets industry standards and ensuring the stability of the main line through a hierarchical processing strategy, making the entire cabling optimization process more controllable and efficient.

[0037] Optionally, the operation deviation value is calculated based on the real-time operation status data, and anomaly judgment is performed, specifically including the following steps:

[0038] Based on the real-time operation status data, obtain the position deviation information of the locking lever;

[0039] Obtain operation completion information, and trigger a wire position detection command based on the operation completion information;

[0040] Obtain the conductor position detection result information, and based on the conductor position detection result information and the locking rod position deviation information, obtain the current execution status information. The conductor position detection result information refers to the relative positional relationship between the conductor and the locking rod.

[0041] Based on the current execution status information and the wire tying operation instruction set, the operation deviation value is obtained.

[0042] By adopting the technical scheme, the application first analyzes the actual installation position of the clamping rod through the real-time collected operation state data, calculates the deviation value from the design position; after the operation of a certain process is completed, the system automatically triggers the wire position detection instruction, and obtains the relative position relationship between the wire and the clamping rod through the visual detection system; then the result information of the wire position detection and the clamping rod position deviation information obtained before are comprehensively analyzed to generate the execution state information of the current process; finally, the system compares the current execution state information with the original wire binding operation instruction set, calculates the specific operation deviation value, and judges whether abnormal processing is needed; early discovery and timely processing of problems in the wire binding operation process are realized, the consistency of product quality is improved, and the time and cost loss caused by rework is reduced.

[0043] In a second aspect, the application provides a wire binding system for a wire binding board based on image recognition, comprising:

[0044] a drawing preprocessing module, configured to receive and preprocess a cable layout drawing provided by a customer to obtain standard format drawing data after preprocessing;

[0045] an AI analysis module, configured to analyze the drawing by computer vision according to the standard format drawing data and combine a preset color ID coding rule to obtain a wire key feature data set;

[0046] a template matching module, configured to perform template matching from a predefined standard template library based on the wire key feature data set to obtain an adaptive wire binding board template;

[0047] a path planning module, configured to calculate a non-crossing wire path and an optimal clamping rod distribution scheme according to the wire key feature data set and the adaptive wire binding board template to obtain an executable wire binding operation instruction set;

[0048] an automatic execution module, configured to control a display to dynamically render a process pattern based on the wire binding operation instruction set and collect a clamping rod insertion operation picture in real time through a camera to obtain real-time operation state data;

[0049] an abnormal processing module, configured to calculate an operation deviation value according to the real-time operation state data and perform abnormality judgment, trigger an alarm and perform a rollback operation when an abnormality is detected.

[0050] In a third aspect, the application provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the wire binding method for a wire binding board based on image recognition.

[0051] In a fourth aspect, the present application provides a computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the steps of the image recognition-based cable tie plate cable tying method described above.

[0052] In summary, the present application includes at least one of the following beneficial technical effects:

[0053] 1. The present application proposes an image recognition-based cable tie plate cable tying method, which obtains standard format drawing data by pre-processing cable layout drawings, extracts key features of wires using computer vision technology combined with color ID coding rules, and matches suitable cable tie plate templates from a standard template library; based on feature data and template parameters, the system calculates a non-crossing wire layout scheme and an optimal card holder distribution scheme; in actual operation, the process guide pattern is dynamically displayed on the display, and the camera is used to monitor the operation process in real time, and when an abnormality is found, an alarm is given in time and a rollback operation is performed; the present application solves the problems of low efficiency and unstable quality of traditional manual operation, realizes automatic planning of the wiring path, ensures controllability of the operation process, and improves the automation level and product quality of the cable tie plate production;

[0054] 2. The present application identifies the wiring path based on the wire connection relationship, endpoint coordinates and line feature by image segmentation of the standard format drawing data, and determines the card holder position by color ID coding of different wires; the system analyzes the inflection points and intersection points of the wiring path, calculates the cable tie spacing requirements combined with the wire grouping information, identifies the wire model mark and establishes the mapping relationship with the card holder; finally, the complete feature data set is generated by integrating various parameters, realizing automatic extraction of feature information and improving data acquisition efficiency;

[0055] 3. The present application identifies the main line direction and branch line direction by analyzing the wire layout path, determines the key nodes including convergence points and turning points; the system calculates the card holder position parameters of the main line and branch line based on these nodes, considers the load bearing requirement of the main line and the flexibility requirement of the branch line, realizes the differential arrangement of the card holder position, and ensures the rationality and practicability of the layout. BRIEF DESCRIPTION OF DRAWINGS

[0056] Figure 1 is a flowchart of an image recognition-based cable tie plate cable tying method according to an embodiment of the present application;

[0057] Figure 2 is a flowchart of step S200 in the image recognition-based cable tie plate cable tying method according to an embodiment of the present application;

[0058] Figure 3 is a flowchart of step S210 in the image recognition-based cable tie plate cable tying method according to an embodiment of the present application;

[0059] Figure 4 FIG. 4 is a flowchart illustrating step S400 of a cable management method based on image recognition according to an embodiment of the present application;

[0060] Figure 5 FIG. 5 is a flowchart illustrating step S420 of a cable management method based on image recognition according to an embodiment of the present application;

[0061] Figure 6 FIG. 6 is a flowchart illustrating step S600 of a cable management method based on image recognition according to an embodiment of the present application;

[0062] Figure 7 FIG. 7 is a block diagram of a cable management system based on image recognition according to an embodiment of the present application;

[0063] Figure 8 FIG. 8 is a diagram illustrating an internal structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0064] The terminology used in the following embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in the specification and the appended claims, the singular forms "a," "an" and "the" are intended to include both singular and plural forms, unless the context clearly indicates otherwise. It will be further understood that the terms "and / or," as used in the specification and the appended claims, are used to

[0065] Hereinafter, the terms "first" and "second" are used only for the purpose of description and should not be construed as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined with "first" and "second" can explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, the meaning of "a plurality of" is two or more, unless otherwise specified.

[0066] The embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

[0067] In a first aspect, the present application provides a cable management method based on image recognition, referring to Figure 1 , comprising the following steps:

[0068] S100, receiving and pre-processing a cable layout drawing provided by a customer to obtain pre-processed standard format drawing data.

[0069] In this embodiment, the cable layout drawing provided by the customer is the original input of the lacing operation, including hand-drawn sketches, PDF vector drawings, CAD engineering drawings, or on-site photos taken by mobile phones, etc. Due to the problems of inconsistent formats, blurred lines, scattered annotations, etc. in the original drawings, the purpose of preprocessing is to convert them into structured and unified digital data, which is convenient for subsequent computer vision analysis. The standard format drawing data contains the structured expression of key information such as wire path, endpoint, model, color, etc.

[0070] Specifically, first, the original drawings of different types are processed for format normalization. If it is an image file, OpenCV library is used for grayscale, Gaussian blur denoising and Canny edge detection to extract the wire contour and generate a binary mask. If it is a PDF / CAD file, the vector coordinate data is extracted. Then, the coordinate system is unified, and all coordinates are converted to an absolute coordinate system with the "lower left corner of the lacing board" as the origin, x-axis to the right and y-axis to the up, eliminating the difference in drawing scale. Finally, the text annotations (wire model, color) in the drawing are recognized by the OCR tool, and the wire color ID is extracted by the color threshold segmentation algorithm. The wire path coordinates, endpoints, model, color, etc. are integrated into structured data in JSON format.

[0071] S200, according to the standard format drawing data, using computer vision to analyze the drawing and combining with the preset color ID coding rule, the wire key feature data set is obtained.

[0072] In this embodiment, the computer vision analysis is to extract the physical layout information of the wire from the standard format drawing by image processing technology; the preset color ID coding rule is to assign a unique color identifier to different functional or type of wire for quick classification of wire category. The wire key feature data set needs to contain the card rod position parameter, the lacing interval requirement, the mapping relationship between the wire model and the card rod, that is, the matching rule of the guide wire and the card rod.

[0073] Specifically, first, the straight line segments of the wire path are detected, and the wire path is fitted in combination with the endpoint coordinates; then, according to the color ID coding rule, the type of each wire is labeled. For the position parameters of the clamping rod, the coordinates thereof are determined by analyzing the inflection points and branch points of the wire path in combination with experience rules, wherein the inflection point refers to a point at which the path direction changes and is located by calculating the angle between adjacent line segments > 90°, the branch point refers to a path bifurcation point and is located by line segment intersection detection, and the experience rule refers to a rule formulated according to different customer historical demands and industry standards, such as the clamping rod of the main line being located at a position 5 mm above the inflection point and the clamping rod of the branch line being located at a position 20 mm along the branch direction from the branch point. The lacing band spacing requirement is determined by statistically determining the minimum spacing of the same type of wire bundle in combination with industry standards. The mapping relationship between the wire type and the clamping rod is established by querying a preset database. Finally, the above information is integrated into a key feature data set including a clamping rod position list, a lacing band spacing table and a type-clamping rod mapping table.

[0074] S300, template matching is performed from a pre-defined standard template library based on the wire key feature data set to obtain an adapted wire lacing plate template.

[0075] In this embodiment, the standard template library is a set of pre-defined wire lacing plate design schemes, each template including clamping rod layout parameters, industry compliance constraints and applicable scenarios. The purpose of template matching is to select the template that best matches the current wire features from the library to ensure that the physical structure of the wire lacing plate meets the wire layout requirements.

[0076] Specifically, first, the standard template library is indexed by features, and each template is labeled with applicable scenarios, maximum load and maximum number of supported wires, etc. Then, according to the information in the wire key feature data set, such as 8 wires, 5 kg maximum load, and the need to isolate strong / weak electric lines, candidate templates with matching applicable scenarios, a load greater than 5 kg, and more than 8 clamping rods are selected from the template library. Finally, the matching degree of the clamping rod position of the candidate template to the wire key features and the compliance constraint satisfaction degree are weighted scored by rule matching scoring, and the template with the highest score is selected as the adaptation result. If there is no adaptation template, human intervention is triggered to prompt adjustment of the requirements.

[0077] S400, according to the wire key feature data set and the adapted wire lacing plate template, a non-crossing wire path and an optimal clamping rod allocation scheme are calculated to obtain an executable wire lacing operation instruction set.

[0078] In this embodiment, the non-crossing wire path means that any two wires in the adjusted wire path do not physically cross; the optimal clamping rod distribution scheme means the matching scheme of the clamping rod and the wire that minimizes the movement distance of the mechanical arm under the premise of meeting the non-crossing path. The wire binding operation instruction set is a detailed procedure including the clamping rod insertion sequence, position and binding band fixing operation, and is used to guide the actual wire binding operation.

[0079] Specifically, first, the path intersection in the wire key feature data set is detected, all wire path segment combinations are traversed, and the intersection points are identified through a line segment intersection judgment algorithm. If there is an intersection, the affected branch path is adjusted, the branch path offset range is calculated according to the wire bending radius constraint, the branch path closer to the intersection area is preferentially adjusted, and the connection point of the branch path and the main path is re-planned. Subsequently, the optimal clamping rod distribution is calculated, with the minimum total movement distance of the mechanical arm as the target, wherein the objective function is the sum of the Euclidean distances between the insertion positions of the clamping rods, and the clamping rod position parameters and template constraints are combined, such as the clamping rod aperture matching the wire model. From the first wire, the nearest available clamping rod is assigned to it until all wires are assigned. Finally, the adjusted path, the clamping rod distribution sequence and the binding band fixing interval are converted into an executable instruction sequence of the device.

[0080] S500, based on the wire binding operation instruction set, control the display to dynamically render the process pattern and real-time collect the clamping rod insertion operation picture through the camera to obtain real-time operation state data.

[0081] In this embodiment, the dynamic rendering of the process pattern is to visually display the current wire binding step and the target position to assist the operator to perform; the real-time collection of the operation picture is to monitor whether the actual operation meets the instruction requirements to provide data support for abnormal detection. The real-time operation state data includes the actual position of the clamping rod, the relative position of the wire and the clamping rod and the binding band fixing state and other information.

[0082] Specifically, first, the 3D wire binding plate model is rendered on the display, and the current process instruction and the target position are superimposed. Subsequently, the clamping rod in the picture is detected in real time, the bounding box coordinates thereof are identified, and the image coordinates are converted into wire binding plate absolute coordinates through a homography matrix. At the same time, the edge detection algorithm is used to identify the fitting state of the wire and the clamping rod, and the collected clamping rod position, wire fitting state and other information are packaged into real-time operation state data.

[0083] S600, calculate the operation deviation value according to the real-time operation state data and perform abnormality judgment, and trigger an alarm and perform a rollback operation when an abnormality is detected.

[0084] Specifically, first, the insertion position deviation of the clamping rod is calculated, and the position error of each clamping rod is calculated by the Euclidean distance formula. At the same time, the fitting state of the wire and the clamping rod is detected, and whether the cable tie is fixed is detected. Subsequently, an abnormality judgment threshold is set, and if the clamping rod position deviation is greater than 2mm, or the wire fitting offset is greater than 1mm, or the cable tie is not fixed, such as detecting that the cable tie edge is broken, it is determined to be abnormal. When an abnormality is detected, a sound and light alarm is triggered, and a rollback operation is performed, a reverse movement instruction is sent through the mechanical arm control interface to withdraw the clamping rod to the previous step position, and the operation record of the current step is cleared. At the same time, the abnormal information is saved to the log file for subsequent analysis and optimization. If the deviation is within the allowable range and the wire fitting is good, proceed to the next step, repeat S500-S600 until all steps are completed.

[0085] In one embodiment, the wire key feature data set includes clamping rod position parameters, cable tie spacing requirements, wire model and clamping rod mapping relationship; referring to Figure 2 In step S200, according to the standard format drawing data, the drawing is analyzed by computer vision combined with the preset color ID coding rule to obtain the wire key feature data set, which includes the following steps:

[0086] S210, image segmentation is performed on the standard format drawing data, the wire routing path is identified, and different wires are identified according to the preset color ID coding rule to determine the clamping rod position parameters.

[0087] The image segmentation is based on the preprocessed wire connection relationship data, endpoint coordinate data and line features in the drawing.

[0088] In this embodiment, the image segmentation is a technical means for separating the mixed wires, characters, backgrounds and other elements in the drawing, and only the wire area is retained; the preset color ID coding rule is to assign a unique color identification to different functional or type wires for quickly distinguishing the wire categories and providing color association basis for the clamping rod position. The clamping rod position parameters are the physical support point coordinates of the guide wire fixed on the cable tie plate.

[0089] Specifically, first, the wire contour is extracted to generate a binary mask image, the wire area is white and the background is black; for complex intersection regions, straight line segments are detected, and the wire path is fitted combined with the endpoint coordinates. Subsequently, according to the preset color ID coding rule, each wire is labeled. Finally, the clamping rod position is determined based on the geometric features of the wire path.

[0090] S220, according to the inflection point and intersection point position of the wire routing path, combined with the wire grouping information identified by the color ID, the spacing requirement between adjacent wire bundles is calculated to obtain the cable tie spacing requirement.

[0091] In this embodiment, the inflection point of the wire routing path is a point where the direction of the wire changes, and the intersection point is a point where different wire paths intersect; the wire grouping information is to divide the wires into different categories according to the color ID; and the tie spacing requirement is the minimum allowable distance between adjacent wire bundles.

[0092] Specifically, first, the inflection points and intersection points of the wire routing path are detected, and whether there is an intersection point is detected by calculating the included angle of adjacent line segments. Subsequently, the wires are divided into multiple bundles according to the color ID grouping information. For adjacent wire bundles of different groups, the minimum spacing is calculated; and for wire bundles of the same group, the internal spacing is calculated. Finally, the tie spacing requirement is determined in combination with the industry standard. If the actual minimum spacing is less than the industry standard, the tie spacing requirement is taken as the industry standard value; and if the actual spacing is greater than or equal to the industry standard, the actual minimum spacing is taken.

[0093] S230, identify the wire type marking in the drawing, and establish a mapping relationship between the wire type and the clamping rod according to the color ID coding rule and the clamping rod position parameter.

[0094] In this embodiment, the wire type marking is a textual description of the wire specification in the drawing; the color ID coding rule is used to associate the wire type with the function; the clamping rod position parameter includes the physical size of the clamping rod; and the mapping relationship is a one-to-one correspondence rule between the wire type and the applicable clamping rod.

[0095] Specifically, first, the wire type marking in the drawing is identified, and the text region is extracted to obtain the type information of each wire. Subsequently, the wire type is obtained according to the color ID coding rule, and the mapping rule is established in combination with the clamping rod aperture in the clamping rod position parameter. Finally, the mapping table is generated by traversing all the wire types and clamping rod parameters.

[0096] S240, integrate the clamping rod position parameter, the tie spacing requirement, and the mapping relationship between the wire type and the clamping rod to generate a wire key feature dataset.

[0097] In one embodiment, the clamping rod position parameter includes main line clamping rod position parameters and branch line clamping rod position parameters; with reference to Figure 3 In step S210, the standard format drawing data is image segmented to identify the wire routing path and determine the clamping rod position parameter, which specifically includes the following steps:

[0098] S211, according to the wire routing path, identify the main line direction and the branch line direction, and obtain the main line key node and the branch line key node.

[0099] In this embodiment, the backbone line is a core line that bears the main power transmission or signal transmission, usually with the characteristics of long path and connection to key devices; the branch line is a secondary line that branches from the backbone line, used to connect secondary devices, with shorter path and scattered distribution. The key node is a position with significant direction change or important function in the guide wire path, which needs to be fixed by the clamping rod to ensure the stability of the line.

[0100] Specifically, first, the backbone and branch lines are identified based on the geometric characteristics of the wire routing path. The total length of the wire path is calculated. If the path length is greater than a preset value and is connected to a main device, it is determined as a backbone line; otherwise, it is determined as a branch line. Then, the key nodes of the path are extracted. By traversing the line segment combination of the path, the angle between adjacent line segments is detected. If the angle is greater than 90°, the intersection point is a turning point. If there is a branching point in the path, the branching point is a branch point.

[0101] S212, according to the key nodes of the backbone line and the key nodes of the branch line, the position parameters of the clamping rod of the backbone line and the position parameters of the clamping rod of the branch line are calculated.

[0102] In this embodiment, the clamping rod position parameters need to ensure that the wire is fixed without loosening, while considering the operation convenience. The backbone line bears more tension, so the clamping rod needs to be close to the key node to enhance the support; the branch line requires high flexibility, so the clamping rod needs to be appropriately offset from the key node to avoid interference with the backbone line.

[0103] Specifically, for the key node of the backbone line, the key node is taken as the center, and the clamping rod is offset 5mm away from the wire on the side perpendicular to the wire path direction to get the final position. For example, if the direction of the backbone line at the key node (100, 50) is horizontal to the right (the path is from (50, 50) to (150, 50)), the vertical direction is the positive direction of the y-axis, and the clamping rod position is (100, 50+5) = (100, 55). For the key node of the branch line, the key node is taken as the starting point, and the clamping rod is extended 20mm along the branch line direction to get the final position.

[0104] In one embodiment, referring to Figure 4 , in step S400, according to the wire key feature data set and the adapted wire board template, the non-crossing wire path and the optimal clamping rod distribution scheme are calculated to obtain the executable wire binding operation instruction set, which specifically includes the following steps:

[0105] S410, based on the mapping relationship between the wire type and the clamping rod in the wire key feature data set, the topological relationship between the wires is calculated to obtain the wire hierarchical distribution information.

[0106] In this embodiment, the wire topology relationship is the connection dependency relationship of the wires on the cable board, such as the main line providing power or signal input for other lines, and the branch line extending in dependence on the main line; and the wire level distribution information is to divide the wires into different levels according to functions and connection importance, and is used to guide the priority of path planning and clamp rod allocation.

[0107] In step S420, the non-crossing wire path is calculated according to the wire level distribution information and the industry compliance constraint parameters in the adapted cable board template.

[0108] In this embodiment, the industry compliance constraint parameter is a mandatory requirement of the industry standard for wire layout; and the non-crossing wire path means that any two wires in the adjusted wire path do not physically cross.

[0109] In step S430, the clamp rod layout is optimized based on the non-crossing wire path and in combination with the cable tie spacing requirement, to obtain an optimal clamp rod allocation scheme that minimizes the moving distance of the mechanical arm.

[0110] In this embodiment, the cable tie spacing requirement is the minimum allowable distance between adjacent wire bundles; and the optimal clamp rod allocation scheme means the matching scheme of the clamp rod and the wire that minimizes the total moving distance of the mechanical arm under the constraints of the path and non-crossing.

[0111] Specifically, first, the position of the clamp rod that needs to be fixed for each wire is determined according to the non-crossing path; then, the moving distance of the mechanical arm from the current position to each clamp rod position is calculated; and finally, starting from the first wire, the nearest available clamp rod is allocated to it until all wires are allocated.

[0112] In step S440, the non-crossing wire path and the optimal clamp rod allocation scheme are converted into a sequence of executable operation instructions of the device, to generate an executable cable tying operation instruction set, which includes clamp rod insertion instructions and cable tie fixing instructions.

[0113] In one embodiment, referring to Figure 5 In step S420, the non-crossing wire path is calculated according to the wire level distribution information and the industry compliance constraint parameters in the adapted cable board template, specifically including the following steps.

[0114] In step S421, it is detected whether there is a crossing point between the connection lines of the key nodes of the main line, and if there is a crossing point, the crossing region information is obtained.

[0115] In this embodiment, the backbone line key node refers to a position in the backbone line path where the direction changes significantly or the function is important, and its connection is the core trend of the backbone line; the intersection point refers to a point where the connections of different backbone lines intersect, which can cause physical contact or even short circuit of the wires; the intersection area is an area extending outward from the intersection point within a certain range, which is used to locate the range of wires that need to be adjusted.

[0116] S422、According to the intersection area information, the number of affected branch line key nodes is calculated, and the affected branch line key nodes are classified according to the distance to the intersection area to obtain the branch line optimization level.

[0117] In this embodiment, the branch line key node refers to a position in the branch line path connected to the backbone line; the affected branch line key node refers to a branch point close to the intersection area that may need to be adjusted simultaneously due to the adjustment of the backbone line; the classification is to divide the nodes into different priorities according to the distance to the intersection area, which is used to guide the subsequent adjustment order.

[0118] S423、Based on the branch line optimization level, combined with the wire bending radius limit in the industry compliance constraint parameter, the offset range of each branch line key node is calculated.

[0119] In this embodiment, the wire bending radius limit is a mandatory requirement of the industry standard for the degree of wire bending; the offset range is the maximum distance that the branch line key node can move, which needs to meet the requirements of bending radius limit and avoiding intersection with the backbone line.

[0120] Specifically, first, the wire diameter is obtained, and the lower limit of the bending radius is calculated; then, the offset reference is determined according to the branch line optimization level, the offset range of high-priority nodes is 5mm extended outward from the edge of the intersection area; the offset range of medium-priority nodes is 3mm extended outward from the edge of the intersection area; the offset range of low-priority nodes is 1mm extended outward from the edge of the intersection area. At the same time, it is verified whether the path after offset meets the bending radius requirement.

[0121] S424、If the offset range meets the requirements of the industry compliance constraint parameter, adjust the position of the corresponding branch line key node, and recalculate the connection path with the backbone line key node.

[0122] In this embodiment, adjusting the position of the branch line key node means moving the node to the target position within the offset range in a direction perpendicular to the trend of the backbone line; recalculating the connection path means generating a new path of the branch line according to the new node position to ensure no intersection with the backbone line.

[0123] S425、If the offset range does not meet the preset range requirement, adjust the position of the corresponding backbone line key node, and update the connection path of the affected branch line.

[0124] In one embodiment, referring to Figure 6 , in step S600, the operation deviation value is calculated according to the real-time operation state data and the abnormality is judged, which specifically includes the following steps:

[0125] S610, according to the real-time operation state data, the card rod position deviation information is obtained.

[0126] In this embodiment, the card rod position deviation information is the difference between the actual installation position and the target position in the wire binding operation instruction set; the real-time operation state data is obtained through image processing of the card rod insertion picture collected by the camera, and contains real-time coordinate information of the card rod.

[0127] S620, operation completion information is obtained, and a wire position detection instruction is triggered according to the operation completion information.

[0128] In this embodiment, the operation completion information is an identifier of the completion of the card rod insertion action, such as a mechanical arm return signal or an operation interface "insertion complete" button click record; the wire position detection instruction is a detection task automatically generated by the system, which is used to verify the fitting state of the wire and the card rod. For example, after the card rod is inserted, the camera takes pictures at 1 / 3 / 5 seconds respectively, and the average coordinates of the wire edge are obtained after extracting the wire edge.

[0129] S630, wire position detection result information is obtained, and current execution state information is obtained according to the wire position detection result information combined with the card rod position deviation information. The wire position detection result information is the relative position relationship between the wire and the card rod.

[0130] In this embodiment, the wire position detection result information is the position offset of the wire relative to the card rod; the current execution state information is the overall operation state of the card rod installation deviation and the wire fitting state, which is used to judge whether it needs to be handled abnormally.

[0131] Specifically, a local coordinate system is established with the center of the card rod as the origin, and the coordinates of the wire center in the coordinate system are (dx, dy); then, the relative position is converted into the offset in the absolute coordinate system of the wire binding plate combined with the card rod position deviation; finally, the current execution state information is generated.

[0132] S640, according to the current execution state information and the wire binding operation instruction set, the operation deviation value is obtained.

[0133] In this embodiment, the operation deviation value is a quantitative index of the card rod position deviation and the wire fitting offset, which is used to judge whether the operation meets the requirements; the wire binding operation instruction set contains the allowed deviation threshold of each step.

[0134] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0135] In a second aspect, the present application provides a cable tie plate cable tying system based on image recognition. The cable tie plate cable tying system based on image recognition of the present application is described below in combination with the above cable tie plate cable tying method based on image recognition.

[0136] Referring to Figure 7 A cable tie plate cable tying system based on image recognition, comprising:

[0137] A drawing preprocessing module for receiving and preprocessing a cable layout drawing provided by a customer to obtain preprocessed standard format drawing data;

[0138] An AI analysis module for analyzing the drawing using computer vision based on the standard format drawing data and combining a pre-set color ID coding rule to obtain a lead key feature data set;

[0139] A template matching module for matching a template based on the lead key feature data set from a pre-defined standard template library to obtain an adapted cable tie plate template;

[0140] A path planning module for calculating a non-crossing lead path and an optimal clamping rod allocation scheme based on the lead key feature data set and the adapted cable tie plate template to obtain an executable cable tying operation instruction set;

[0141] An automatic execution module for controlling a display to dynamically render a process pattern based on the cable tying operation instruction set and real-time collecting clamping rod insertion operation pictures through a camera to obtain real-time operation state data;

[0142] An exception handling module for calculating an operation deviation value based on the real-time operation state data and performing an exception judgment, triggering an alarm and performing a rollback operation when an exception is detected.

[0143] In one embodiment, the present application provides an electronic device, which can be a server, and its internal structure diagram can be as shown in Figure 8As shown. The electronic device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium, an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the electronic device is used to store data. The network interface of the electronic device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement an image recognition-based wire binding plate wire binding method.

[0144] Those skilled in the art can understand that, Figure 8 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0145] In one embodiment, an electronic device is also provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in the above method embodiments.

[0146] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware. The above-mentioned computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. Any reference to memory, storage, database or other medium used in the embodiments provided by the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not as a limitation, RAM can be in various forms such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0147] The above are the preferred embodiments of the present application, which do not limit the protection scope of the present application, therefore: any equivalent changes made on the structure, shape, principle of the present application shall be covered within the protection scope of the present application.

Claims

1. A wire tying method based on image recognition, characterized in that, Includes the following steps: Receive and preprocess the cable layout drawings provided by the customer to obtain preprocessed standard format drawing data; Based on the standard format drawing data, computer vision is used to parse the drawings and combine them with preset color ID encoding rules to obtain a dataset of key features of the conductors. Based on the aforementioned key feature dataset of the conductor, template matching is performed from a predefined standard template library to obtain a suitable tie plate template; Based on the key feature dataset of the conductor and the adapted tie plate template, calculate the non-crossing conductor path and the optimal clamping rod allocation scheme to obtain an executable tie operation instruction set; Based on the wire tying operation instruction set, the display is controlled to dynamically render the process diagram and the camera is used to capture the card insertion operation screen in real time to obtain real-time operation status data. The operation deviation value is calculated based on the real-time operation status data and anomaly judgment is performed. When an anomaly is detected, an alarm is triggered and a rollback operation is performed. The key feature dataset of the conductor includes the position parameters of the clamping rod, the requirements for the cable tie spacing, and the mapping relationship between the conductor type and the clamping rod. Based on the key feature dataset of the conductors and the adapted binding plate template, the non-crossing conductor paths and the optimal clamping rod allocation scheme are calculated to obtain an executable binding operation instruction set, specifically including the following steps: Based on the mapping relationship between conductor type and clamping rod in the key feature dataset of the conductor, the topological relationship between each conductor is calculated to obtain the conductor hierarchical distribution information. Based on the conductor hierarchy distribution information and the industry compliance constraint parameters in the adapted wire ties template, the non-crossing conductor path is calculated; Based on the non-intersecting wire path and the cable tie spacing requirements, the layout of the clamping rods is optimized to obtain the optimal clamping rod allocation scheme that minimizes the movement distance of the robotic arm. The non-crossing conductor path and the optimal clamping rod allocation scheme are converted into a sequence of executable operation instructions to generate the executable wire tying operation instruction set, which includes clamping rod insertion instructions and cable tie fixing instructions.

2. The wire binding method based on image recognition according to claim 1, characterized in that, Based on the standard format drawing data, computer vision is used to parse the drawings and combine them with preset color ID encoding rules to obtain a key feature dataset of the conductors. The specific steps include the following: The standard format drawing data is image segmented to identify the wire wiring path, and different wires are identified according to the preset color ID encoding rules to determine the position parameters of the clamping rod. The image segmentation is based on the preprocessed wire connection relationship data, endpoint coordinate data and line features in the drawing. Based on the inflection and intersection points of the wire routing path, and combined with the wire grouping information identified by color ID, the spacing requirements between adjacent wire bundles are calculated to obtain the cable tie spacing requirements. Identify the wire type markings in the drawings, and establish a mapping relationship between the wire type and the clamping rod based on the color ID coding rules and the clamping rod position parameters; The key feature dataset of the conductor is generated by integrating the position parameters of the clamping rod, the cable tie spacing requirements, the conductor type and the mapping relationship between the clamping rod.

3. The wire binding method based on image recognition according to claim 2, characterized in that, The pole placement parameters include main line pole placement parameters and branch line pole placement parameters. The standard format drawing data is segmented to identify the conductor wiring path and determine the pole placement parameters. Specifically, this involves the following steps: Based on the wire routing path, identify the main line route and the branch line route, and obtain the key nodes of the main line and the key nodes of the branch line. Based on the key nodes of the main line and the key nodes of the branch lines, calculate the position parameters of the clamping poles on the main line and the position parameters of the clamping poles on the branch lines.

4. The wire binding method based on image recognition according to claim 3, characterized in that, Based on the conductor hierarchy distribution information and the industry compliance constraint parameters in the adapted tie plate template, the non-crossing conductor path is calculated, specifically including the following steps: Detect whether there are intersections between the connections between key nodes of the main line; if there are intersections, obtain the intersection area information. Based on the intersection area information, the number of critical nodes of the affected branch lines is calculated, and the critical nodes of the affected branch lines are classified according to their distance from the intersection area to obtain the branch line optimization level. Based on the branch line optimization level and the conductor bending radius limit in the industry compliance constraint parameters, the offset range of each branch line key node is calculated. If the offset range meets the industry compliance constraint parameter requirements, then adjust the position of the key node of the corresponding branch line and recalculate the connection path with the key node of the main line. If the offset range does not meet the preset range requirements, the position of the key node of the corresponding main line will be adjusted, and the connection path of the affected branch line will be updated.

5. The wire binding method based on image recognition according to claim 1, characterized in that, The calculation of operational deviation values ​​and the judgment of anomalies based on the real-time operational status data specifically include the following steps: Based on the real-time operation status data, obtain the position deviation information of the locking lever; Obtain operation completion information, and trigger a wire position detection command based on the operation completion information; Obtain the conductor position detection result information, and based on the conductor position detection result information and the locking rod position deviation information, obtain the current execution status information. The conductor position detection result information refers to the relative positional relationship between the conductor and the locking rod. Based on the current execution status information and the wire tying operation instruction set, the operation deviation value is obtained.

6. A wire tying system based on image recognition, characterized in that, The wire binding method based on image recognition according to any one of claims 1-5 includes: The drawing preprocessing module is used to receive and preprocess the cable layout drawings provided by the customer to obtain preprocessed standard format drawing data. The AI ​​parsing module is used to parse the standard format drawing data using computer vision and combine it with preset color ID encoding rules to obtain a dataset of key features of the conductor. The template matching module is used to perform template matching from a predefined standard template library based on the key feature dataset of the conductor to obtain a suitable tie plate template; The path planning module is used to calculate the non-crossing conductor path and the optimal clamping pole allocation scheme based on the conductor key feature dataset and the adapted wire tying plate template, and obtain an executable wire tying operation instruction set. The automated execution module is used to control the display to dynamically render the process diagram and capture the insertion operation screen of the carding rod in real time through the camera based on the wire tying operation instruction set, so as to obtain real-time operation status data. The exception handling module is used to calculate the operation deviation value based on the real-time operation status data and make an exception judgment. When an exception is detected, an alarm is triggered and a rollback operation is performed.

7. An electronic device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the image recognition-based wire-tying method according to any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the wire-tying method based on image recognition as described in any one of claims 1-5.

Images