Intelligent maintenance method and system for LED display screen by maintenance robot

Abstract

The invention discloses an intelligent maintenance method and system for an LED display screen by a maintenance robot, and relates to the technical field of maintenance robots, and the method comprises the steps: determining the surface fault feature and model of a corresponding LED display screen based on the image detection of a tabletop image; determining the internal fault characteristics of the LED display screen according to the traceability of the model of the LED display screen; determining a fault optimization process table of the LED display screen according to the surface fault features and the internal fault features of the LED display screen, and determining an intelligent maintenance event of a maintenance support arm of a maintenance robot to each LED display screen based on the fault optimization process table, the model of the LED display screen and the position of the LED display screen; determining an optimization measure of the maintenance progress according to the two maintenance progresses, the task sequence table of the maintenance robot and the current time; the optimization measure comprises batch maintenance of the final maintenance process of each LED display screen, cooperation of external cooperation equipment or adjustment of the action efficiency of a maintenance support arm, and the accuracy of the optimization measure of the maintenance progress is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of maintenance robots, in particular to a method and system for intelligent maintenance of LED display screens by a maintenance robot. BACKGROUND

[0002] With the development of technology, LED display screens are gradually applied to people's lives and serve as one of industrial devices. LED display screens may have some surface faults or internal faults during production and need to be placed on LED display screen maintenance tables. In the prior art, a single maintenance device is used to maintain LED display screens on the LED display screen maintenance tables. However, the single maintenance device can only maintain the surface fault characteristics of the LED display screens and cannot maintain the internal fault characteristics. In addition, the single maintenance device cannot optimize the maintenance progress of the LED display screens on different LED display screen maintenance tables. SUMMARY

[0003] The present application aims to overcome the shortcomings of the prior art and provides a method and system for intelligent maintenance of LED display screens by a maintenance robot.

[0004] The present application provides a method for intelligent maintenance of LED display screens by a maintenance robot, which includes the following steps. Two LED display screen maintenance tables are arranged around the maintenance robot, and two table images are collected based on the ring shooting of the two LED display screen maintenance tables by a camera of the maintenance robot. In the two table images, the surface fault characteristics and the model of the corresponding LED display screen are determined based on image detection of the table images. The internal fault characteristics of the LED display screen are determined according to the model of the LED display screen, and a fault optimization process table of the LED display screen is determined according to the surface fault characteristics and the internal fault characteristics of the LED display screen. The intelligent maintenance events of the maintenance robot on the LED display screens are determined based on the fault optimization process table, the model of the LED display screen, and the position of the LED display screen, and the maintenance progress of the two maintenance arms relative to the corresponding LED display screens is collected. The optimization measures of the maintenance progress are determined according to the two maintenance progresses, a task sequence table of the maintenance robot, and the current time. The optimization measures include batch maintenance of the last maintenance process of each LED display screen, cooperation of external cooperative devices, or adjustment of the action efficiency of the maintenance arms.

[0005] The embodiment of the present application provides a kind of intelligent maintenance system of LED display screen to maintenance robot, the intelligent maintenance system of LED display screen to maintenance robot is applied to the above-mentioned intelligent maintenance method of LED display screen to maintenance robot, the intelligent maintenance system of LED display screen to maintenance robot includes: Table image module, for the periphery of maintenance robot is equipped with two LED display screen maintenance platform, based on the annular shooting of the camera of maintenance robot to two LED display screen maintenance platform and collect two table images; Surface fault module, for in two table images, based on the image detection of table image and determine the surface fault feature and model of corresponding LED display screen; Fault optimization procedure table module, for according to the trace of the model of LED display screen and determine the internal fault feature of LED display screen;According to the surface fault feature and internal fault feature of LED display screen, determine the fault optimization procedure table of the LED display screen; Intelligent maintenance module, for based on the fault optimization procedure table, the model of LED display screen and the position of LED display screen determine the intelligent maintenance event of maintenance robot to each LED display screen by maintenance arm, and collect the maintenance progress of two maintenance arms relative to corresponding LED display screen; Optimization measure module, for according to two maintenance progress, maintenance robot's task sequence table and current time determine the optimization measure of maintenance progress;The optimization measure includes the batch maintenance of last maintenance procedure of each LED display screen, the cooperation of external cooperative equipment or the action efficiency of adjusting maintenance arm.

[0006] Compared with prior art, the beneficial effects of the present application are: In the embodiment of the present application, by the method in the embodiment of the present application, the periphery of maintenance robot is equipped with two LED display screen maintenance platform, based on the annular shooting of the camera of maintenance robot to two LED display screen maintenance platform and collect two table images;In two table images, based on the image detection of table image and determine the surface fault feature and model of corresponding LED display screen;According to the trace of the model of LED display screen and determine the internal fault feature of LED display screen;According to the surface fault feature and internal fault feature of LED display screen, determine the fault optimization procedure table of the LED display screen, introduce the surface fault feature and internal fault feature of LED display screen, realize the overall consideration of the surface fault feature and internal fault feature of LED display screen, improve the precision of the fault optimization procedure table of LED display screen.

[0007] Therefore, based on the fault optimization procedure table, the model of the LED display screen and the position of the LED display screen, the maintenance robot determines the intelligent maintenance event of each LED display screen by the maintenance arm, and collects the maintenance progress of the two maintenance arms relative to the corresponding LED display screen; according to the two maintenance progress, the task sequence table of the maintenance robot and the current time, the optimization measure of the maintenance progress is determined; the optimization measure includes batch maintenance of the last maintenance procedure of each LED display screen, cooperation of external cooperative equipment or adjustment of the action efficiency of the maintenance arm, the maintenance progress of the two maintenance arms relative to the corresponding LED display screen is introduced, the overall consideration of the maintenance progress of the two maintenance arms relative to the corresponding LED display screen, the task sequence table of the maintenance robot and the current time is compatible, the precision of the optimization measure of the maintenance progress is improved, and the LED display screen of the LED display screen maintenance station at different positions is realized. The LED display screen is synchronously maintained and intelligently maintained by one maintenance robot. BRIEF DESCRIPTION OF DRAWINGS

[0008] Figure 1 is a flowchart of the intelligent maintenance method of the LED display screen by the maintenance robot in the embodiment of the application; Figure 2 is a flowchart of step S11 in the intelligent maintenance method of the LED display screen by the maintenance robot in the embodiment of the application; Figure 3 is a flowchart of step S12 in the intelligent maintenance method of the LED display screen by the maintenance robot in the embodiment of the application; Figure 4 is a flowchart of step S13 in the intelligent maintenance method of the LED display screen by the maintenance robot in the embodiment of the application; Figure 5 is a flowchart of step S14 in the intelligent maintenance method of the LED display screen by the maintenance robot in the embodiment of the application; Figure 6 is a flowchart of step S15 in the intelligent maintenance method of the LED display screen by the maintenance robot in the embodiment of the application; Figure 7 is a structural composition diagram of the intelligent maintenance system of the LED display screen by the maintenance robot in the embodiment of the application. DETAILED DESCRIPTION

[0009] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application.

[0010] Please refer to Figures 1 to 7 An intelligent maintenance method of an LED display screen by a maintenance robot, applied to an intelligent maintenance scene of the maintenance robot; the intelligent maintenance method of the LED display screen by the maintenance robot comprises: Step S11: The periphery of the maintenance robot is provided with two LED display screen maintenance tables, and two table images are collected based on the annular shooting of the two LED display screen maintenance tables by the camera of the maintenance robot; Step S12: In the two table images, the surface fault features and the model of the corresponding LED display screen are determined based on the image detection of the table images; Step S13: The internal fault features of the LED display screen are determined according to the tracing of the model of the LED display screen; and the fault optimization process table of the LED display screen is determined according to the surface fault features and the internal fault features of the LED display screen; Step S14: The intelligent maintenance events of the maintenance robot on each LED display screen are determined based on the fault optimization process table, the model of the LED display screen and the position of the LED display screen, and the maintenance progress of the two maintenance arms relative to the corresponding LED display screen is collected; Step S15: The optimization measures of the maintenance progress are determined according to the two maintenance progresses, the task sequence table of the maintenance robot and the current time; the optimization measures include batch maintenance of the last maintenance process of each LED display screen, cooperation of external cooperative equipment or adjustment of the action efficiency of the maintenance arm; Reference Figure 2 In step S11, the periphery of the maintenance robot is provided with two LED display screen maintenance tables, and two table images are collected based on the annular shooting of the two LED display screen maintenance tables by the camera of the maintenance robot; In the specific implementation process of the present application, the specific steps are as follows: S111: The positions of the LED display screen maintenance tables are collected, and another LED display screen maintenance table is determined based on the periphery detection of the LED display screen maintenance table; at this time, the two LED display screen maintenance tables are arranged side by side, and a maintenance work station is provided between the two LED display screen maintenance tables, and the maintenance robot is located in the maintenance work station; S112: The corresponding detection space region is constructed based on the maintenance robot and the two LED display screen maintenance tables; the maintenance robot is provided with a camera, and the annular movement path of the camera is determined based on the spatial position of the camera, the spatial position of the two LED display screen maintenance tables and the activity range of the maintenance robot; S113: The camera moves along the annular movement path under the driving of the maintenance robot, and dynamically shoots the table surfaces of the two LED display screen maintenance tables to collect two table images.

[0011] In the embodiments of the present application, the maintenance robot needs to be equipped with high-precision sensors to collect the positions of the maintenance stations. Laser radar (LiDAR), ultrasonic sensors or visual sensors (such as cameras) can be used; by scanning the surrounding environment with the sensors, the outline and position of the maintenance station are identified; if a visual sensor is used, image recognition technology can be combined to determine the position of the maintenance station through feature point matching or template matching, and the data collected by the sensor is converted into coordinate information and stored in the control system of the robot. Optionally, it is assumed that the maintenance robot is equipped with a laser radar sensor. The laser radar calculates the distance by emitting a laser beam and measuring the time difference of the reflected light. After the robot starts at the maintenance station, the laser radar begins to scan the surrounding environment; the laser radar performs 360-degree scanning with the maintenance robot as the center; the robot control system analyzes the scanning data to identify the outline of the maintenance station. Assuming that the maintenance station is a rectangular structure, the laser radar can detect the coordinates of its four corners; the system converts the coordinates of the four corners of the maintenance station into the coordinates of the center point of a rectangle, for example, the center point coordinates of the first maintenance station are (X1, Y1); at the same time, the system records the size information of the maintenance station, such as the width W1 and the length L1.

[0012] After determining the position of the first maintenance station, the robot needs to continue scanning the surrounding area to find another maintenance station. This can be achieved by expanding the scanning range of the laser radar or adjusting the shooting angle of the camera; the two maintenance stations are arranged side by side, so the position of the second maintenance station usually has a certain spatial relationship with the first maintenance station. For example, they can be on the same straight line or at a certain fixed angle; the position information of the first maintenance station is fused with the detection data of the second maintenance station to ensure that the positional relationship of the two maintenance stations is accurate. Optionally, after determining the position of the first maintenance station, the robot adjusts the scanning direction of the laser radar to continue scanning the area to the right of the first maintenance station; the laser radar scans the area to the right of the first maintenance station and detects the outline of the second maintenance station, the system analyzes the scanning data to determine the coordinates of the four corners of the second maintenance station, and calculates the center point coordinates (X2, Y2), the system records the size information of the second maintenance station, such as the width W2 and the length L2, by comparing the center point coordinates of the two maintenance stations, it is confirmed that they are arranged side by side. For example, X2 = X1 + W1 + interval.

[0013] The maintenance station is the reference position for the maintenance robot to operate, usually located between two maintenance tables. The position of the maintenance station needs to be set in advance, and the robot needs to be able to navigate to this position accurately, two maintenance tables are arranged side by side, and the maintenance station is located between them, ensuring that the robot has enough operating space. This layout facilitates the robot to operate on two maintenance tables, while avoiding collisions with other equipment, safety guards such as grating or emergency stop buttons are set between the maintenance station and the maintenance table to prevent accidents during robot movement.

[0014] Further, the detection space region refers to the three-dimensional space range that the maintenance robot camera can cover, which is used to shoot the table surface of the two LED display maintenance tables. According to the spatial position of the maintenance robot and the two maintenance tables, the boundary of the detection space is determined. This space needs to cover the table surface of the two maintenance tables, and the shooting angle and range of the camera need to be considered. Through sensors such as laser radar or cameras, a three-dimensional model of the environment is obtained, including the contour and height of the maintenance table and the position of the maintenance robot.

[0015] The installation position and initial pose of the camera on the maintenance robot are determined. This can be achieved through sensor calibration or mechanical design, according to the activity range of the mechanical arm of the maintenance robot, the path that the camera can move is determined. The activity range needs to consider the joint angle limit and collision detection of the mechanical arm, based on the detection space region and the activity range of the camera, the ring-shaped movement path of the camera is planned. The path needs to ensure that the camera can shoot the table surface of the two maintenance tables from multiple angles.

[0016] Therefore, the camera moves along the ring-shaped movement path under the drive of the maintenance robot, and dynamically shoots the table surface of the two LED display maintenance tables to collect two table surface images, which introduces the collection of two table surface images.

[0017] At this time, the camera needs to be installed on the end of the mechanical arm or other movable parts of the maintenance robot, to ensure that it can move on the ring-shaped path, before starting shooting, the camera needs to be initialized and calibrated, including focal length adjustment, aperture setting, white balance calibration, etc. to ensure the quality of the shot image, if the robot is equipped with other sensors (such as laser radar or ultrasonic sensor), the shooting data of the camera needs to be fused with the data of other sensors to improve the accuracy of positioning and shooting.

[0018] According to the annular movement path determined in step S112, the motion trajectory of the mechanical arm is planned. The path needs to ensure that the camera can take pictures of the table surface of the maintenance table from multiple angles. Through the control system of the robot, the mechanical arm moves smoothly according to the planned path. The motion speed, acceleration and joint angle of the mechanical arm need to be considered to ensure the smoothness and accuracy of the motion. During the movement, the shooting parameters of the camera (such as focal length, aperture, exposure time, etc.) are adjusted in real time according to the actual shooting effect (such as image clarity, lighting conditions, etc.).

[0019] When the mechanical arm moves to each shooting point, the camera is triggered to take pictures. The triggering of the shooting can be realized through the position sensor of the mechanical arm or time control. The captured images are transmitted to the control system of the robot in real time and stored. Image compression techniques can be used to reduce data transmission volume while ensuring image quality. The collected images are preprocessed, including denoising, contrast enhancement, edge detection, etc. to improve the accuracy of subsequent image analysis. Optionally, assuming that the shooting interval of each shooting point is 30 degrees, the camera is triggered to take pictures when the mechanical arm moves to each shooting point. When the mechanical arm moves to each shooting point, the position sensor detects that the mechanical arm reaches the specified position, and then triggers the camera to take pictures. The images taken by the camera are transmitted to the control system of the robot through the data line and stored on the hard disk. The JPEG compression algorithm is used to compress the images to 10% of the original size to reduce storage space and transmission time. The collected images are preprocessed, such as using Gaussian filter to remove image noise, adjusting contrast to enhance image details, and using edge detection algorithm to extract the outline of the maintenance table.

[0020] Reference Figure 3 In step S12, in the two table images, the surface failure features and the model of the corresponding LED display screen are determined based on the image detection of the table images. In the specific implementation process of the present application, the specific steps are as follows: S121: Real-time monitoring of two table images, image processing of two table images, at this time, multiple image regions are divided under the image processing of each table image, and the surface image and model identification image of the LED display screen are determined according to the screening of multiple image regions; S122: If the surface image and model identification image of the LED display screen are in the same region of the table image, multi-channel recognition is carried out based on the surface image and model identification image of the LED display screen. In the multi-channel recognition of the surface image and model identification image of the LED display screen, the surface morphology and model content of the LED display screen are output, and the surface abnormal area is determined according to the detection of the surface morphology of the LED display screen. S123: Determine a plurality of sub-surface fault features according to the identification of the surface abnormal area, and determine the surface fault feature of the LED display screen according to the position, shape and surface fault feature mapping relationship of the plurality of sub-surface fault features.

[0021] In the embodiment of the present application, the camera of the maintenance robot captures the table surface images of the two LED display screen maintenance tables in real time, the captured image data is transmitted to the control system of the robot in real time through a high-speed interface (such as USB 3.0 or Ethernet), and the captured image is displayed in real time in the control system of the robot for monitoring and subsequent processing.

[0022] The two table surface images are processed. Assuming that the resolution of the captured table surface image is 1920x1080 pixels, a Gaussian filter is applied to each captured image, the filter kernel size is 5x5, the standard deviation is 1.5, the contrast of the image is adjusted by histogram equalization to make the details in the image clearer, and the edge information in the image is extracted using the Canny algorithm, with a low threshold of 50 and a high threshold of 150.

[0023] The table surface image is divided into a plurality of equal-sized grid regions. For example, the image is divided into 4x4 or 8x8 grids, and the image regions are dynamically divided according to the edge information or other features in the image. For example, the image regions are divided using an image segmentation algorithm (such as region growing or watershed algorithm), and optionally, the image regions are dynamically divided from a seed point in the image according to the similarity (such as color or grayscale value) of the pixels. In each divided image region, an image recognition algorithm (such as template matching or feature point detection) is used to identify the surface and model identification of the LED display screen, and according to the identification result, the image regions containing the surface and model identification of the LED display screen are screened out.

[0024] Optionally, assuming that the table surface images collected by the maintenance robot are as follows: Maintenance table 1: image resolution: 1920x1080 pixels; grid division: 8x8 grid, each grid region size: 240x135 pixels; feature recognition result: display screen surface area: row 3, column 4; model identification area: row 5, column 6; Maintenance table 2: image resolution: 1920x1080 pixels; grid division: 8x8 grid, each grid region size: 240x135 pixels; feature recognition result: display screen surface area: row 2, column 3; model identification area: row 4, column 5.

[0025] Further, if the surface image and the model identification image of the LED display screen are in the same area of the table image, multi-channel recognition is performed based on the surface image and the model identification image of the LED display screen; in the multi-channel recognition of the surface image and the model identification image of the LED display screen, the surface morphology and the model content of the LED display screen are output, the surface abnormal area is determined according to the detection of the surface morphology of the LED display screen, the overall consideration of the detection of the surface morphology of the LED display screen is compatible, and the accuracy of the surface abnormal area is ensured.

[0026] At this time, the image area screened through step S121 is checked to determine whether there is an area containing the surface of the LED display screen and the model identification at the same time, if the surface image and the model identification image are in the same area, the position and range of the area are recorded for subsequent multi-channel recognition, the images in the same area are processed in multiple channels, including color channels, gray channels, edge channels, etc., features such as color distribution, texture features, edge intensity are extracted from each channel; the features of different channels are fused and analyzed to improve the accuracy and robustness of recognition.

[0027] Optionally, assuming that the surface image and the model identification image of the LED display screen are detected at the same time in the image area of the 3rd row and the 4th column of the maintenance table 1, each screened image area is checked to confirm whether there is an area containing the surface and the model identification at the same time, the position (3rd row and 4th column) and range (240x135 pixels) of the area are recorded; the information of the three color channels of RGB is extracted; the image is converted into a gray image, and the gray information is extracted; the edge information is extracted using the Canny algorithm; the histogram distribution of each color channel is calculated; the texture features are extracted using the gray level co-occurrence matrix (GLCM); the number and distribution of edge pixels are counted, and the color, gray and edge features are fused to form a comprehensive feature vector.

[0028] Surface morphology recognition: using a pre-trained deep learning model (such as a convolutional neural network CNN) to recognize the surface morphology of the LED display screen, including scratches, stains, damage, etc., at the same time, model content recognition: using optical character recognition (OCR) technology to recognize the model identification content, outputting the recognized surface morphology and model content to the control system, based on the detection result of the surface morphology, using image segmentation algorithm (such as threshold segmentation, region growing, etc.) to recognize the surface abnormal area, marking the detected abnormal area, recording its position and size, and further analyzing the abnormal area to extract its features (such as length, area, shape, etc.).

[0029] Optionally, assuming that in the image region of row 3, column 4, the recognized surface morphology is "light scratch" and the model content is "LED-2023"; using the pre-trained CNN model, input the fused feature vector, and output the surface morphology as "light scratch"; using OCR technology, the model identification content is "LED-2023"; the recognition result is output to the control system, and the surface morphology is recorded as "light scratch" and the model is "LED-2023"; using threshold segmentation algorithm, the region with gray value higher than a certain threshold (such as 128) in the gray image is identified as abnormal region, the detected abnormal region is marked, its position (such as the upper left corner coordinate is (50, 30)) and size (such as the width is 20 pixels and the height is 5 pixels) are recorded, and the abnormal region is further analyzed to extract its features, such as length of 20 pixels, width of 5 pixels, and shape of linear.

[0030] Therefore, according to the recognition of the surface abnormal region, a plurality of sub-surface fault features are determined, and according to the position, morphology and surface fault feature mapping relationship of the plurality of sub-surface fault features, the surface fault feature of the LED display screen is determined, which is compatible with the overall consideration of the position, morphology and surface fault feature mapping relationship of the plurality of sub-surface fault features, and ensures the accuracy of the surface fault feature of the LED display screen.

[0031] At this time, a plurality of sub-surface fault features are extracted from the surface abnormal region, such as scratch length, scratch width, stain area, damage shape, etc., the extracted features are quantified, such as measuring the length and width of the scratch, calculating the area of the stain, etc., the sub-surface fault features are classified according to the type (such as scratch, stain, damage, etc.), and the sub-surface fault features are mapped to specific surface fault features according to the pre-defined rules. For example, a scratch length of more than 10 mm is considered as "serious scratch", and a stain area of more than 0.5 square centimeters is considered as "serious stain". The extracted sub-surface fault features are matched with the pre-defined rules to determine the final surface fault feature, the classification results of all sub-surface fault features are combined to determine the final surface fault feature, and the final surface fault feature is output to the control system of the maintenance robot to provide basis for subsequent maintenance decision.

[0032] Optionally, assuming that in the image region of row 3, column 4 of maintenance station 1, a surface abnormal region is detected, which is a scratch and a stain, the length of the scratch is 20 pixels, the width is 2 pixels, the area of the stain is 100 square pixels, the length of the scratch is 20 mm (assuming the ratio of pixels to actual size is 1:1), the width of the scratch is 2 mm, the area of the stain is 1 square centimeter (assuming the ratio of pixels to actual size is 1:1), the scratch is 20 mm long and 2 mm wide, and the stain is 1 square centimeter.

[0033] Suppose the predefined mapping rules are as follows: scratch: length < 10 mm: slight scratch; length >= 10 mm: serious scratch; stain: area < 0.5 square centimeter: slight stain; area >= 0.5 square centimeter: serious stain; at this time, the length of the scratch is 20 mm, which is determined as "serious scratch" according to the rules, and the area of the stain is 1 square centimeter, which is determined as "serious stain" according to the rules.

[0034] In the image area of the 3rd row and the 4th column of the maintenance station 1, after feature extraction and rule matching, the determined sub-surface fault features are as follows: scratch: serious scratch (length 20 mm, width 2 mm); stain: serious stain (area 1 square centimeter).

[0035] Reference Figure 4 In step S13, the internal fault features of the LED display screen are determined according to the trace of the model of the LED display screen; the fault optimization process table of the LED display screen is determined according to the surface fault features and the internal fault features of the LED display screen; In the specific implementation process of the present application, the specific steps are as follows: S131: Collect the model of the LED display screen, determine the corresponding trace path according to the model of the LED display screen and the processing path of the LED display screen, and determine the past processing events of the LED display screen based on the trace path, the processing database of the LED display screen and the model of the LED display screen; S132: Determine the corresponding processing abnormal event according to the identification of the past processing events of the LED display screen, and determine the internal fault features of the LED display screen according to the process corresponding to the processing abnormal event, the processing process list of the LED display screen and the abnormal data corresponding to the LED display screen; S133: Determine the first fault process table based on the past processing events of the LED display screen and the surface fault features of the LED display screen, determine the second fault process table based on the past processing events of the LED display screen and the internal fault features of the LED display screen, and determine the fault optimization process table of the LED display screen according to the synthesis of the first fault process table and the second fault process table.

[0036] In the embodiment of the present application, the model of the LED display screen is collected, the corresponding trace path is determined according to the model of the LED display screen and the processing path of the LED display screen, and the past processing events of the LED display screen are determined based on the trace path, the processing database of the LED display screen and the model of the LED display screen, which is compatible with the overall consideration of the trace path, the processing database of the LED display screen and the model of the LED display screen, and ensures the accuracy of the past processing events of the LED display screen.

[0037] At this time, the model information is extracted from the model identification image of the display screen by optical character recognition (OCR) technology, the collected model information is verified to ensure its accuracy and integrity, and the collected model information is stored in the control system of the maintenance robot for subsequent use; according to the collected model, the standard processing path of the model LED display screen is queried, and the standard processing path is combined to generate the traceability path of the display screen, which is used to query the processing history and verify the integrity and accuracy of the traceability path to ensure that all related processing events can be traced.

[0038] Optionally, assuming that the model identification is "LED-2023" in the image area of the third row and the fourth column of the maintenance table 1 by OCR, at this time, the model identification image is identified using OCR technology, the model "LED-2023" is extracted, and it is verified whether the extracted model information conforms to the predefined format (such as "LED-XXXX"). The model "LED-2023" is stored in the control system of the maintenance robot, the standard processing path of the model "LED-2023" is queried, and "production line A -> process 1 -> process 2 -> process 3" is obtained. The traceability path is generated to query the processing history of the display screen on the production line A, and it is verified whether the traceability path is complete to ensure that the detailed information of each process can be traced. The standard processing path of the model "LED-2023" is "production line A -> process 1 -> process 2 -> process 3".

[0039] The processing database of the LED display screen is accessed, the processing history of the display screen is queried according to the traceability path, the processing events of the display screen in each process are extracted from the processing database, including normal events and abnormal events, the extracted processing events are arranged to form a complete processing history record, and optionally, assuming that the processing events of the model "LED-2023" on the production line A are recorded in the processing database, at this time, the processing database is accessed, the traceability path "production line A -> process 1 -> process 2 -> process 3" is input, and the processing events of the model "LED-2023" in each process are extracted from the database: process 1: normal completion; process 2: abnormal welding temperature, record time is June 20, 2025; process 3: normal completion; the extracted processing events are arranged into a complete processing history record: process 1: normal completion; process 2: abnormal welding temperature (June 20, 2025); process 3: normal completion.

[0040] Further, according to the identification of the previous processing event of the LED display screen, the corresponding processing abnormal event is determined, according to the processing procedure corresponding to the processing abnormal event, the processing procedure list of the LED display screen and the abnormal data corresponding to the LED display screen, the internal fault characteristics of the LED display screen are determined, the overall consideration of the processing procedure corresponding to the processing abnormal event, the processing procedure list of the LED display screen and the abnormal data corresponding to the LED display screen is compatible, and the accuracy of the internal fault characteristics of the LED display screen is ensured.

[0041] At this time, the processing abnormal event is identified from the previous processing event, which can be realized by analyzing the abnormal records in the processing data (such as temperature abnormality, welding failure, etc.), classifying the identified abnormal events, such as welding abnormality, temperature abnormality, mechanical damage, etc., recording the specific information of each abnormal event, including the occurrence time, procedure, abnormal type and related data, querying the processing procedure list of the LED display screen of this type, understanding the specific content and possible fault points of each procedure, matching the processing abnormal event with the processing procedure list, determining the procedure corresponding to the abnormal event, combining the specific information of the abnormal event and the processing procedure list, and deducing the internal fault characteristics of the LED display screen. For example, welding temperature abnormality may cause virtual welding or insufficient strength of welding point.

[0042] Optionally, assuming that in the image area of the 3rd row and the 4th column of the maintenance table 1, the previous processing event of the type "LED-2023" is queried as follows: procedure 1: normal completion; procedure 2: welding temperature abnormality (June 20, 2025); procedure 3: normal completion. At this time, the welding temperature abnormal event in procedure 2 is identified from the processing event, the abnormal event is classified as "welding abnormality", and the specific information of the abnormal event is recorded: procedure: procedure 2; abnormal type: welding temperature abnormality; occurrence time: June 20, 2025; related data: welding temperature exceeds the standard range (for example, the standard temperature is 250°C, and the actual temperature is 280°C).

[0043] Assuming that the processing procedure list of the type "LED-2023" is as follows: procedure 1: PCB board assembly; procedure 2: welding LED lamp beads; procedure 3: function test; at this time, the processing procedure list of the type "LED-2023" is queried, the specific content of each procedure is determined, the welding temperature abnormal event in procedure 2 is matched with the processing procedure list, it is determined that the abnormal event occurs in the procedure of welding LED lamp beads, and according to the specific information of the welding temperature abnormality (temperature exceeds the standard range), the internal fault characteristics are deduced as "virtual welding of welding point" or "insufficient strength of welding point".

[0044] Therefore, the first fault process table is determined based on the previous processing events of the LED display screen and the surface fault features of the LED display screen, the second fault process table is determined based on the previous processing events of the LED display screen and the internal fault features of the LED display screen, the fault optimization process table of the LED display screen is determined according to the synthesis of the first fault process table and the second fault process table, the synthesis of the first fault process table and the second fault process table is considered as a whole, the accuracy of the fault optimization process table of the LED display screen is ensured, meanwhile, the surface fault features and the internal fault features of the LED display screen are introduced, the surface fault features and the internal fault features of the LED display screen are considered as a whole, and the accuracy of the fault optimization process table of the LED display screen is improved.

[0045] At this time, the previous processing events of the LED display screen are analyzed, the processing links that may affect the surface fault features are identified, the surface fault features are associated with the processing events, the specific processing links that cause the surface faults are determined, and the first fault process table for the surface faults is generated according to the association results. The first fault process table is generated based on the previous processing events of the LED display screen and the surface fault features, and is used to record the processing links related to the surface faults and the corresponding repair processes.

[0046] Optionally, it is assumed that the model of the LED display screen is “LED-2023”, the previous processing events include module assembly, welding, testing and the like. The surface fault feature is “module not bright”; at this time, for the processing events, the module assembly: check whether the power socket of the module is loose; the welding: check whether the welding point is loose; the testing: check whether the power supply during the testing is normal; the surface fault feature “module not bright” may be related to the loose power socket in the module assembly link, and the first fault process table is introduced. The first fault process table is shown in Table 1: Table 1 First fault process table

[0047] The previous processing events of the LED display screen are analyzed, the processing links that may affect the internal fault features are identified, the internal fault features are associated with the processing events, the specific processing links that cause the internal faults are determined, and the second fault process table for the internal faults is generated according to the association results. The second fault process table is generated based on the previous processing events of the LED display screen and the internal fault features, and is used to record the processing links related to the internal faults and the corresponding repair processes.

[0048] Optionally, assuming that the internal fault feature of the LED display screen is "drive circuit failure", for the processing event, module assembly: check whether the drive circuit elements of the module are installed correctly; welding: check the welding quality of the drive circuit elements; test: check whether the circuit function is normal during the test; the internal fault feature "drive circuit failure" may be related to poor welding of the drive circuit elements in the welding link, a second fault process table is introduced, which is shown in Table 2: Table 2 Second fault process table

[0049] The first fault process table and the second fault process table are combined to form a complete fault optimization process table, the process table is optimized according to the severity and maintenance difficulty of the fault feature, the maintenance efficiency is ensured, a weight is assigned to each repair process, the priority of the process is determined according to the weight, the fault optimization process table is generated by combining the surface fault feature and the internal fault feature of the LED display screen, and is an optimized process table for guiding maintenance personnel to efficiently and accurately complete the maintenance task, which integrates the first fault process table (for surface faults) and the second fault process table (for internal faults), and optimizes the process according to the severity of the fault, the maintenance priority and the feasibility of actual operation, to ensure the efficiency and accuracy of the maintenance process. Optionally, the fault optimization process table is collected, and the fault optimization process table is shown in Table 3: Table 3 Fault optimization process table

[0050] Reference Figure 5 In step S14, the intelligent maintenance events of the maintenance arms of the maintenance robot on each LED display screen are determined based on the fault optimization process table, the model of the LED display screen and the position of the LED display screen, and the maintenance progress of the two maintenance arms relative to the corresponding LED display screen is collected; In the specific implementation process of the present application, the specific steps are as follows: S141: collect the fault optimization process table, each LED display screen matches a fault optimization process table, a plurality of fault optimization items are determined according to the analysis of the fault optimization process table, and the maintenance path of the maintenance arms of the maintenance robot on each fault optimization item is determined according to the plurality of fault optimization items and the position of the corresponding LED display screen; S142: determine the corresponding fault optimization content according to the plurality of fault optimization items and the model of the corresponding LED display screen, and determine the corresponding maintenance content according to the fault optimization content and the maintenance type mapping relationship; the maintenance action of the maintenance arm of the maintenance robot is determined according to the maintenance content; S143: The maintenance robot determines the intelligent maintenance events of each LED display screen for the maintenance robot's maintenance arms according to the maintenance paths of the maintenance arms for each failure optimization item and the maintenance actions of the maintenance arms, marks the action sequence of each maintenance action and the re-inspection procedure of each failure optimization item in the completion stage, and simultaneously monitors the maintenance process of the two maintenance arms relative to the corresponding LED display screens in real time and records the maintenance progress of the two maintenance arms relative to the corresponding LED display screens.

[0051] In the embodiments of the present application, the failure optimization procedure table is collected, each LED display screen matches a failure optimization procedure table, a plurality of failure optimization items are determined according to the analysis of the failure optimization procedure table, and the maintenance paths of the maintenance arms of the maintenance robot for each failure optimization item are determined according to the plurality of failure optimization items and the positions of the corresponding LED display screens, which is compatible with the overall consideration of the plurality of failure optimization items and the positions of the corresponding LED display screens, and ensures the accuracy of the maintenance paths of the maintenance arms of the maintenance robot for each failure optimization item.

[0052] At this time, the failure optimization procedure table is obtained from the control system of the maintenance robot. The table usually contains information such as fault characteristics, repair procedures, weights, and scores, verifies the completeness and accuracy of the failure optimization procedure table, ensures that all necessary information has been included, stores the failure optimization procedure table in the control system of the maintenance robot for subsequent processing, extracts each failure optimization item from the failure optimization procedure table, including fault characteristics and corresponding repair procedures, sorts the failure optimization items according to weights or scores, and processes the items with higher weights or scores first, and records the extracted failure optimization items in the control system of the maintenance robot.

[0053] The failure optimization procedure table is obtained from the control system of the maintenance robot, it is checked whether all necessary information such as fault characteristics, repair procedures, weights, and scores is included in the table, the failure optimization procedure table is stored in the control system, the failure optimization items are extracted from the failure optimization procedure table: item 1: virtual welding of welding points, repair procedure is re-welding of welding points; item 2: serious scratch, repair procedure is scratch repair; the items are sorted according to weights: item 1 (virtual welding of welding points, weight 0.9); item 2 (serious scratch, weight 0.8); the extracted failure optimization items are recorded in the control system.

[0054] Obtain the specific position information of the LED display screen, such as the coordinates on the maintenance table, and plan the maintenance path of the maintenance arm according to the fault optimization project and the position of the display screen. Path planning needs to consider the motion range and motion limit of the mechanical arm, optimize the maintenance path, and ensure the shortest path and avoid collision. Path planning algorithms such as A* algorithm or Dijkstra algorithm can be used for optimization. Optionally, assuming that the position of the LED display screen is the 3rd row and the 4th column of the maintenance table 1, the coordinates are (50, 30), obtain the position information of the LED display screen, the coordinates are (50, 30); according to the fault optimization project and the position of the display screen, plan the maintenance path: starting point: maintenance station (coordinates (0, 0)); path 1: move to the welding point position (coordinates (50, 30)); path 2: move to the scratch position (coordinates (80, 60)); end point: return to the maintenance station (coordinates (0, 0)); use A* algorithm to optimize the path, ensure the shortest path and avoid collision.

[0055] Further, according to the plurality of fault optimization projects and the corresponding LED display screen model, the corresponding fault optimization content is determined, and the corresponding maintenance content is determined according to the fault optimization content and the maintenance type mapping relationship; the maintenance action of the maintenance arm of the maintenance robot is determined according to the maintenance content, which is compatible with the overall consideration of the fault optimization content and the maintenance type mapping relationship, and ensures the accuracy of the corresponding maintenance content.

[0056] At this time, according to the model of the LED display screen, the fault characteristics and repair procedures related to the model are extracted from the fault optimization project, the specific fault optimization content is determined by combining the fault optimization project and the model information, the fault optimization content is recorded in the control system of the maintenance robot, a maintenance type mapping table is defined, the corresponding relationship between the fault optimization content and the specific maintenance content is recorded, the corresponding maintenance content is found from the mapping table according to the fault optimization content, the maintenance content is recorded in the control system of the maintenance robot, the corresponding maintenance action is found from the mapping table according to the maintenance content, and the specific operation steps of the maintenance arm are planned according to the maintenance action, including moving, grabbing, welding, repairing and other actions. The maintenance action is recorded in the control system of the maintenance robot.

[0057] Optionally, a preset maintenance type mapping table is collected, as shown in Table Four: Table Four Maintenance Type Mapping Table

[0058] According to the fault optimization content "welding point re-welding" and "scratch repair", the corresponding repair content is found in the mapping table: welding point re-welding -> welding repair; scratch repair -> surface repair; the repair content is recorded in the control system, according to the repair content "welding repair" and "surface repair", the corresponding repair action is found in the mapping table: welding repair -> welding action; surface repair -> scratch repair action; the specific operation steps of the repair arm are planned: move to the welding point position, perform welding operation, move to the scratch position, perform scratch repair operation, the repair action is recorded in the control system.

[0059] Therefore, according to the repair path of the repair arm for each fault optimization item and the repair action of the repair arm, the repair arm of the repair robot determines the intelligent repair event of each LED display screen, marks the action sequence of each repair action and the retest procedure of each fault optimization item in the completion stage, simultaneously, monitors the repair process of the two repair arms relative to the corresponding LED display screen in real time, and records the repair progress of the two repair arms relative to the corresponding LED display screen, which is compatible with the overall consideration of the repair path of the repair arm for each fault optimization item and the repair action of the repair arm, and ensures the accuracy of the intelligent repair event of the repair arm of the repair robot for each LED display screen.

[0060] At this time, according to the repair path and the repair action, the intelligent repair event of each fault optimization item is defined, each repair action is assigned a sequence number to ensure the orderliness of the repair process, after each fault optimization item is completed, the retest procedure that needs to be performed is marked, a real-time monitoring system is set up to monitor the movement and operation state of the repair arm, the start time and end time of each repair action are recorded, the repair progress is calculated, abnormal situations that may occur in the repair process are detected, such as robot arm collision, operation failure, etc., the repair progress record is stored in the control system of the repair robot, a repair progress report is generated for the reference of the repair personnel, and the repair progress is fed back to the repair personnel for timely adjustment of the repair plan.

[0061] Optionally, assuming that the repair path and the repair action are as follows: move to the welding point position (coordinates (50, 30)), perform welding operation; move to the scratch position (coordinates (80, 60)), perform scratch repair operation. At this time, the intelligent repair event is defined: event 1: welding repair (welding point re-welding); event 2: scratch repair (surface repair); each repair action is assigned a sequence number: event 1 (welding repair): action sequence 1; event 2 (scratch repair): action sequence 2; the retest procedure is marked: event 1 (welding repair): the retest procedure is welding point strength test; event 2 (scratch repair): the retest procedure is surface quality detection; the intelligent repair event matching table is collected, which is shown in Table Five: Table Five Intelligent Repair Event Matching Table

[0062] Assuming the repair process is as follows: event 1 (weld repair) start time: June 24, 2025 10:30; event 1 (weld repair) end time: June 24, 2025 10:35; event 2 (scratch repair) start time: June 24, 2025 10:35; event 2 (scratch repair) end time: June 24, 2025 10:40; start real-time monitoring system, monitor the movement and operation state of the repair arm, record the start time and end time of each repair action: event 1 (weld repair): start time 10:30, end time 10:35; event 2 (scratch repair): start time 10:35, end time 10:40, monitor whether there are abnormal situations during the repair process, such as robot collision or operation failure.

[0063] The repair progress record is stored in the control system of the repair robot, a repair progress report is generated for the repair personnel to refer to, and the repair progress is fed back to the repair personnel for timely adjustment of the repair plan.

[0064] Optionally, the repair progress record is stored in the control system, a repair progress report is generated: event 1 (weld repair): completion time 10:35, repair time 5 minutes; event 2 (scratch repair): completion time 10:40, repair time 5 minutes, the repair progress is fed back to the repair personnel for timely adjustment of the repair plan; the repair progress report table is shown in Table 6: Table 6 Repair progress report table

[0065] Reference Figure 6 In step S15, the optimization measures of the repair progress are determined according to the two repair progress, the task sequence list of the repair robot and the current time; the optimization measures include batch repair of the last repair process of each LED display screen, cooperation of external collaborative equipment or adjustment of the action efficiency of the repair arm; In the specific implementation process of the present application, the specific steps are: S151: Collect the task sequence list of the repair robot, determine the current repair task and the remaining repair task according to the analysis of the task sequence list of the repair robot, and mark the trigger time of the remaining repair task, and determine the remaining time of the current repair task according to the trigger time of the remaining repair task and the current time; S152: Determine the first optimization coefficient according to the remaining time of the current repair task and the two repair progress, and determine the second optimization coefficient according to the two repair progress and the task sequence list of the repair robot; S153: Determine the optimization measures for the maintenance progress based on the mapping relationship between the first optimization coefficient, the second optimization coefficient and the optimization measures, and accelerate the maintenance progress based on the execution of the optimization measures. At this time, the optimization measures cover the batch maintenance of the final maintenance process of each LED display screen, the coordination of external collaborative equipment, or the adjustment of the movement efficiency of the maintenance arm.

[0066] In an embodiment of the present application, the task sequence list of the maintenance robot is collected, the current maintenance task and the remaining maintenance tasks are determined based on the analysis of the task sequence list of the maintenance robot, and the trigger time of the remaining maintenance tasks is marked. The remaining time of the current maintenance task is determined based on the trigger time of the remaining maintenance tasks and the current time, which is compatible with the overall consideration of the trigger time and current time of the remaining maintenance tasks, thereby ensuring the accuracy of the remaining time of the current maintenance task.

[0067] At this point, the task sequence table is obtained from the maintenance robot's control system. The task sequence table typically contains detailed information about all maintenance tasks, such as task name, trigger time, and estimated completion time. The completeness and accuracy of the task sequence table are verified to ensure that all necessary information is included. The task sequence table is stored in the maintenance robot's control system for subsequent processing. The task sequence table is parsed and the currently executing maintenance task and the remaining maintenance tasks that have not yet begun are determined based on the current time. The trigger time of the remaining maintenance tasks is marked for subsequent calculation of the remaining time. The remaining time for the current maintenance task is calculated based on the current time and the trigger time of the remaining maintenance tasks.

[0068] Optionally, the maintenance task sequence table is shown in Table 7: Table 7 Maintenance task sequence list

[0069] Obtain the maintenance task sequence table from the control system of the maintenance robot, check whether the task sequence table contains all necessary information, such as task name, trigger time, and estimated completion time, and store the task sequence table in the control system. Assume that the current time is 2025-06-24 10:32, the current maintenance task is: welding repair (trigger time 10:30, estimated completion time 10:35) and the remaining maintenance tasks are: scratch repair (trigger time 10:35, estimated completion time 10:40); surface quality inspection (trigger time 10:40, estimated completion time 10:45); at the same time, the trigger time of scratch repair is 10:35; the trigger time of surface quality inspection is 10:40; the remaining time of the current maintenance task (welding repair): 3 minutes (10:35 - 10:32); the current maintenance task is: welding repair; the remaining time is 3 minutes; the remaining maintenance tasks are: scratch repair (trigger time 10:35); the surface quality inspection (trigger time 10:40).

[0070] Further, the first optimization coefficient is determined according to the remaining time of the current maintenance task and the two maintenance progress, and the second optimization coefficient is determined according to the two maintenance progress and the task sequence list of the maintenance robot, which is compatible with the overall consideration of the two maintenance progress and the task sequence list of the maintenance robot, and ensures the accuracy of the second optimization coefficient.

[0071] At this time, according to the trigger time and the current time of the current maintenance task, the remaining time is calculated, the progress information of the two maintenance tasks is obtained, including the actual completion time and the expected completion time, and the first optimization coefficient is calculated according to the remaining time and the maintenance progress. The coefficient reflects the urgency of the current maintenance task.

[0072] Optionally, it is assumed that the current time is 2025-06-24 10:32; the current maintenance task is “welding repair”, the trigger time is 10:30, and the expected completion time is 10:35; the progress information of the two maintenance tasks is as follows: welding repair: actual start time 10:30, expected completion time 10:35; scratch repair: actual start time 10:35, expected completion time 10:40.

[0073] At this time, the remaining time of the current maintenance task (welding repair) is 3 minutes (10:35 - 10:32); the actual progress of welding repair is 2 minutes completed and 3 minutes remaining; the actual progress of scratch repair is not started yet; the first optimization coefficient = 1 / remaining time = 1 / 3 ≈ 0.33; the first optimization coefficient: 0.33.

[0074] The actual progress and the expected progress of the two maintenance tasks are summarized, the task sequence list is analyzed, the average progress of all tasks is determined, and the second optimization coefficient is calculated according to the summarized maintenance progress and the task sequence list. The coefficient reflects the efficiency of the overall maintenance progress.

[0075] Optionally, the task sequence list is collected, the actual progress of welding repair is 2 minutes completed and 3 minutes remaining, the actual progress of scratch repair is not started yet, and the actual progress of surface quality detection is not started yet; the average progress of all tasks is (5 minutes + 5 minutes + 5 minutes) / 3 = 5 minutes; the second optimization coefficient = 1 / average progress = 1 / 5 = 0.2; the second optimization coefficient: 0.2.

[0076] Therefore, the optimization measure of the maintenance progress is determined based on the mapping relationship among the first optimization coefficient, the second optimization coefficient and the optimization measure, and the maintenance progress is accelerated based on the execution of the optimization measure, at this time, the optimization measure covers the batch maintenance of the last maintenance process of each LED display screen, the cooperation of the external collaborative equipment or the action efficiency adjustment of the maintenance arm, is compatible with the overall consideration of the mapping relationship among the first optimization coefficient, the second optimization coefficient and the optimization measure, guarantees the accuracy of the optimization measure of the maintenance progress, at the same time, the maintenance progress of the two maintenance arms relative to the corresponding LED display screen is introduced, is compatible with the overall consideration of the maintenance progress of the two maintenance arms relative to the corresponding LED display screen, the task sequence table of the maintenance robot and the current time, improves the accuracy of the optimization measure of the maintenance progress, and realizes the synchronous maintenance and intelligent maintenance of the LED display screen on the LED display screen maintenance table at different positions by one maintenance robot.

[0077] At this time, an optimization measure mapping table is defined to record the optimization measures corresponding to different optimization coefficient ranges, and the appropriate optimization measure is selected from the mapping table according to the first optimization coefficient and the second optimization coefficient. The optimization measure can include batch maintenance, cooperation of external collaborative equipment or action efficiency adjustment of the maintenance arm. If the optimization measure includes batch maintenance, the last maintenance process of multiple LED display screens is arranged to be performed at the same time. If the optimization measure includes cooperation of external collaborative equipment, the external equipment is notified to prepare for the cooperative operation. If the optimization measure includes action efficiency adjustment of the maintenance arm, the motion parameters of the mechanical arm are optimized to improve the efficiency. The execution effect of the optimization measure is monitored in real time to ensure that the maintenance progress is accelerated. At the same time, the first optimization coefficient is an index calculated based on the remaining time of the current maintenance task and the maintenance progress, which is used to reflect the urgency of the current maintenance task. It helps the maintenance robot to evaluate the priority of the current task so as to take optimization measures when necessary. The second optimization coefficient is an index calculated based on the average progress of all maintenance tasks and the task sequence table, which is used to reflect the efficiency of the overall maintenance progress. It helps the maintenance robot to evaluate the execution of the overall maintenance task so as to take optimization measures when necessary.

[0078] Optionally, an optimization measure mapping table is collected, which is shown in Table Eight: Table Eight Optimization Measure Mapping Table

[0079] At this time, an optimization measure mapping table is created to record the optimization measures corresponding to different optimization coefficient ranges. According to the first optimization coefficient (0.33) and the second optimization coefficient (0.2), the appropriate optimization measure is selected from the mapping table. According to the selected optimization measure, the specific execution content is described. The first optimization coefficient is 0.33. The second optimization coefficient is 0.2. The selected optimization measure is the cooperation of the external collaborative equipment.

[0080] Referring to Figure 7 , Figure 7 is a structural composition diagram of the intelligent maintenance system of the maintenance robot for the LED display screen in the embodiment of the present application; the intelligent maintenance system of the maintenance robot for the LED display screen comprises: a table image module 21, two LED display screen maintenance tables are arranged around the maintenance robot, and two table images are collected based on the annular shooting of the two LED display screen maintenance tables by the camera of the maintenance robot; a surface fault module 22, the surface fault features and the model of the corresponding LED display screen are determined based on the image detection of the table image in the two table images; a fault optimization procedure table module 23, the internal fault features of the LED display screen are determined according to the trace of the model of the LED display screen; the fault optimization procedure table of the LED display screen is determined according to the surface fault features and the internal fault features of the LED display screen; an intelligent maintenance module 24, the intelligent maintenance events of the maintenance arms of the maintenance robot to each LED display screen are determined based on the fault optimization procedure table, the model of the LED display screen and the position of the LED display screen, and the maintenance progress of the two maintenance arms relative to the corresponding LED display screen is collected; an optimization measure module 25, the optimization measures of the maintenance progress are determined according to the two maintenance progress, the task sequence table of the maintenance robot and the current time; the optimization measures include the batch maintenance of the last maintenance procedure of each LED display screen, the cooperation of the external cooperative equipment or the adjustment of the action efficiency of the maintenance arm.

[0081] Any combination of the technical features of the above embodiments is possible, in order to make the description simple, all the combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered that it is within the scope of the present application.

Claims

1. An intelligent maintenance method for LED display screens using a maintenance robot, characterized in that: include: There are two LED display maintenance tables around the maintenance robot. The camera of the maintenance robot captures the two LED display maintenance tables in a circular manner and collects images of the two tables. In the two table images, the surface fault characteristics and model of the corresponding LED display screen are determined based on image detection of the table images; Determine the internal fault characteristics of the LED display screen by tracing the model of the LED display screen; Determine the fault optimization process table of the LED display screen according to the surface fault characteristics and internal fault characteristics of the LED display screen; Based on the fault optimization process table, the model of the LED display screen, and the location of the LED display screen, the intelligent maintenance events of the maintenance arm of the maintenance robot on each LED display screen are determined, and the maintenance progress of the two maintenance arms relative to the corresponding LED display screen is collected; Determine the optimization measures for the maintenance progress based on the two maintenance progresses, the task sequence list of the maintenance robot and the current time; the optimization measures include batch maintenance of the final maintenance process of each LED display, coordination of external collaborative equipment or adjustment of the movement efficiency of the maintenance arm.

2. The intelligent maintenance method for LED display screens using a maintenance robot according to claim 1, characterized in that: Two LED display screen maintenance tables are provided around the maintenance robot. The camera of the maintenance robot captures the two LED display screen maintenance tables in a circular manner to collect two table surface images, including: The position of the LED display maintenance station is collected, and another LED display maintenance station is determined based on the peripheral detection of the LED display maintenance station. At this time, the two LED display maintenance stations are arranged side by side, and a maintenance station is set between the two LED display maintenance stations. The maintenance robot is at the maintenance station; A corresponding detection space area is constructed based on the maintenance robot and two LED display maintenance platforms. The maintenance robot is equipped with a camera, and the circular movement path of the camera is determined based on the spatial position of the camera, the spatial positions of the two LED display maintenance platforms, and the activity range of the maintenance robot. Driven by the maintenance robot, the camera moves along a circular path and dynamically captures the surfaces of the two LED display maintenance tables to collect images of the two surfaces.

3. The intelligent maintenance method for LED display screens using a maintenance robot according to claim 1, characterized in that: The method of determining the surface fault characteristics and model of the corresponding LED display screen based on image detection of the two table images includes: Monitor two table images in real time and perform image processing on the two table images. At this time, divide each table image into multiple image areas under image processing, and determine the surface image and model identification image of the LED display screen based on the screening of the multiple image areas; If the surface image of the LED display and the model identification image are within the same area of ​​the table image, multi-channel recognition is performed based on the surface image of the LED display and the model identification image; in the multi-channel recognition of the surface image of the LED display and the model identification image, the surface morphology and model content of the LED display are output, and the surface abnormality area is determined based on the detection of the surface morphology of the LED display; A plurality of sub-surface fault features are determined based on the identification of the surface abnormal area, and the surface fault features of the LED display are determined based on the positions, shapes and surface fault feature mapping relationships of the plurality of sub-surface fault features.

4. The intelligent maintenance method for LED display screens using a maintenance robot according to claim 1, characterized in that: The internal fault characteristics of the LED display screen are determined based on the tracing of the model of the LED display screen; According to the surface fault characteristics and internal fault characteristics of the LED display, the fault optimization process table of the LED display is determined, including: Collect the model of the LED display screen, determine the corresponding traceability path according to the model of the LED display screen and the processing path of the LED display screen, and determine the previous processing events of the LED display screen based on the traceability path, the processing database of the LED display screen and the model of the LED display screen; The corresponding abnormal processing event is determined based on the identification of the previous processing events of the LED display screen, and the internal fault characteristics of the LED display screen are determined based on the process corresponding to the abnormal processing event, the processing process list of the LED display screen and the abnormal data corresponding to the LED display screen.

5. The intelligent maintenance method for LED display screens using a maintenance robot according to claim 4, characterized in that: The internal fault characteristics of the LED display screen are determined based on the tracing of the model of the LED display screen; The fault optimization process table of the LED display screen is determined based on the surface fault characteristics and internal fault characteristics of the LED display screen, and also includes: The first fault process table is determined based on the previous processing events of the LED display and the surface fault characteristics of the LED display, the second fault process table is determined based on the previous processing events of the LED display and the internal fault characteristics of the LED display, and the fault optimization process table of the LED display is determined based on the synthesis of the first fault process table and the second fault process table.

6. The intelligent maintenance method for LED display screens using a maintenance robot according to claim 1, characterized in that: The method of determining the intelligent maintenance events of the maintenance arms of the maintenance robot on each LED display screen based on the fault optimization process table, the model of the LED display screen, and the location of the LED display screen, and collecting the maintenance progress of the two maintenance arms relative to the corresponding LED display screen, includes: The fault optimization process table is collected, and each LED display screen is matched with a fault optimization process table. Multiple fault optimization items are determined based on the analysis of the fault optimization process table. The maintenance path of the maintenance robot's maintenance arm for each fault optimization item is determined based on the multiple fault optimization items and the corresponding LED display screen positions; The corresponding fault optimization content is determined according to multiple fault optimization items and the corresponding LED display screen models, and the corresponding maintenance content is determined according to the mapping relationship between the fault optimization content and the maintenance type; and the maintenance action of the maintenance arm of the maintenance robot is determined according to the maintenance content.

7. The intelligent maintenance method for LED display screens using a maintenance robot according to claim 6, characterized in that: The method further includes determining the intelligent maintenance events of the maintenance arms of the maintenance robot on each LED display screen based on the fault optimization process table, the model of the LED display screen, and the location of the LED display screen, and collecting the maintenance progress of the two maintenance arms relative to the corresponding LED display screen. According to the maintenance path and maintenance actions of the maintenance arm for each fault optimization project, the intelligent maintenance events of the maintenance arm of the maintenance robot for each LED display are determined, and the action sequence of each maintenance action and the retest process of each fault optimization project in the completion stage are marked. At the same time, the maintenance process of the two maintenance arms relative to the corresponding LED display is monitored in real time, and the maintenance progress of the two maintenance arms relative to the corresponding LED display is recorded.

8. The intelligent maintenance method for LED display screens using a maintenance robot according to claim 1, characterized in that: The optimization measures for determining the maintenance progress based on the two maintenance progresses, the maintenance robot's task sequence list, and the current time; the optimization measures include batch maintenance of the final maintenance process of each LED display screen, coordination of external collaborative equipment, or adjustment of the operation efficiency of the maintenance arm, including: Collect the task sequence list of the maintenance robot, determine the current maintenance task and the remaining maintenance tasks based on the analysis of the task sequence list of the maintenance robot, mark the trigger time of the remaining maintenance tasks, and determine the remaining time of the current maintenance task based on the trigger time of the remaining maintenance tasks and the current time.

9. The intelligent maintenance method for LED display screens using a maintenance robot according to claim 8, characterized in that: The optimization measures for the maintenance progress are determined based on the two maintenance progresses, the task sequence list of the maintenance robot, and the current time; the optimization measures include batch maintenance of the final maintenance process of each LED display screen, coordination of external cooperative equipment, or adjustment of the operation efficiency of the maintenance arm, and also include: Determine a first optimization coefficient based on the remaining time of the current maintenance task and the two maintenance progresses, and determine a second optimization coefficient based on the two maintenance progresses and the task sequence list of the maintenance robot; Based on the mapping relationship between the first optimization coefficient, the second optimization coefficient and the optimization measures, the optimization measures for the maintenance progress are determined, and the maintenance progress is accelerated based on the execution of the optimization measures. At this time, the optimization measures cover the batch maintenance of the final maintenance process of each LED display screen, the coordination of external collaborative equipment, or the adjustment of the movement efficiency of the maintenance arm.

10. An intelligent maintenance system for LED display screens using a maintenance robot, characterized in that: The intelligent maintenance system for LED display screens by the maintenance robot is applied to the intelligent maintenance method for LED display screens by the maintenance robot according to any one of claims 1 to 9. The intelligent maintenance system for LED display screens by the maintenance robot comprises: The tabletop image module is used to capture images of two LED display maintenance tables located around the maintenance robot. The maintenance robot's camera captures the two tables in a circular pattern. A surface fault module is used to determine the surface fault characteristics and model of the corresponding LED display screen based on image detection of the two table images; The fault optimization process table module is used to determine the internal fault characteristics of the LED display screen according to the tracing of the model of the LED display screen; and determine the fault optimization process table of the LED display screen according to the surface fault characteristics and internal fault characteristics of the LED display screen; An intelligent maintenance module is used to determine the intelligent maintenance events of the maintenance arms of the maintenance robot on each LED display based on the fault optimization process table, the model of the LED display and the location of the LED display, and to collect the maintenance progress of the two maintenance arms relative to the corresponding LED display; The optimization measures module is used to determine the optimization measures for the maintenance progress based on the two maintenance progresses, the task sequence list of the maintenance robot and the current time; the optimization measures include batch maintenance of the final maintenance process of each LED display, coordination of external collaborative equipment or adjustment of the movement efficiency of the maintenance arm.

Images