Welding robot monitoring method and device, medium, controller and program product

Abstract

The invention provides a welding robot monitoring method and device, a medium, a controller and a program product, and the method comprises the steps that when a welding robot executes welding operation, an image of a welding area of the welding robot collected when an unmanned aerial vehicle flies along with the welding robot is obtained; feature extraction is conducted on the image, collected by the unmanned aerial vehicle, of the welding area, welding seam features are obtained, the extracted welding seam features are analyzed, and whether welding seam defects exist or not is recognized; and if yes, whether the current welding quality is qualified or not is judged according to a preset quality standard. According to the scheme provided by the invention, real-time monitoring and quality evaluation of the welding process can be realized.

Description

Technical Field

[0001] This invention relates to the field of control, and more particularly to a method, apparatus, medium, controller, and program product for monitoring welding robots. Specifically, it designs a method, apparatus, storage medium, robot controller, and computer program product for monitoring welding robots based on unmanned aerial vehicles (UAVs). Background Technology

[0002] Welding is a crucial step in shipbuilding. Traditional welding relies primarily on manual labor, resulting in high labor intensity, low efficiency, and inconsistent quality. In recent years, welding robots have been increasingly applied to ship welding, improving welding precision and efficiency. However, these welding robots lack real-time monitoring and feedback mechanisms for welding quality, making it difficult to detect weld defects and other anomalies in a timely manner. This leads to high rework rates, impacting production efficiency and product quality. Summary of the Invention

[0003] The main objective of this invention is to overcome the deficiencies of the aforementioned related technologies and provide a welding robot monitoring method, device, medium, controller, and program product to solve the problem that welding robots in the related technologies lack a real-time monitoring and feedback mechanism for welding quality during the welding process.

[0004] This invention provides a method for monitoring welding robots based on unmanned aerial vehicles (UAVs), comprising:

[0005] When the welding robot performs welding operations, the drone follows the welding robot and collects images of the welding area of ​​the welding robot; the drone extracts features from the images of the welding area collected by the welding area to obtain weld features, and analyzes the extracted weld features to identify whether there are weld defects; if weld defects are identified, the current welding quality is judged to be qualified according to the preset quality standards.

[0006] Optionally, it also includes: if the current welding quality is determined to be unqualified, adjusting the welding parameters of the welding robot according to the defect type of the existing weld defect.

[0007] Optionally, the welding defects include at least one of the following: lack of fusion, porosity, slag inclusion, cracks, insufficient penetration, excessively wide weld, weld burn-through, and uneven surface; and / or, the preset quality standards include at least one of the following: weld width error range, penetration error range, surface flatness scoring threshold, and defect number threshold.

[0008] Optionally, if the current welding quality is determined to be unqualified, the welding parameters of the welding robot are adjusted according to the defect type of the existing weld defect, including: adjusting the welding parameters according to the defect type and according to the preset parameter adjustment rules corresponding to different defect types.

[0009] Optionally, the welding parameters include at least one of current, voltage, and speed; the preset parameter adjustment rules corresponding to different defect types include increasing or decreasing at least one of current, voltage, and speed according to different defect types.

[0010] Optionally, the method further includes: after adjusting the welding parameters of the welding robot, acquiring images of the welding area of ​​the welding robot again by the drone following the welding robot; extracting features from the images of the welding area acquired by the drone to obtain weld features, and analyzing the extracted weld features to determine whether the weld defects have been eliminated.

[0011] Optionally, it also includes generating a defect feedback report containing the defect type, location, and severity if a weld defect is identified.

[0012] Optionally, it also includes: after the welding robot completes the welding operation, storing the images collected during the welding process, the welding quality judgment results, and the welding parameter adjustment records, and generating a welding quality report.

[0013] Another aspect of the present invention provides a welding robot monitoring device based on a drone, comprising: an acquisition unit, configured to acquire images of the welding area of ​​the welding robot collected by the drone while the welding robot is performing a welding operation; an identification unit, configured to extract features from the images of the welding area collected by the drone to obtain weld features, and analyze the extracted weld features to identify whether weld defects exist; and a judgment unit, configured to determine whether the current welding quality is qualified according to a preset quality standard if the identification unit identifies the presence of weld defects.

[0014] Optionally, it further includes: an adjustment unit, used to adjust the welding parameters of the welding robot according to the defect type of the existing weld defect if the judgment unit determines that the current welding quality is unqualified.

[0015] Optionally, the welding defects include at least one of the following: lack of fusion, porosity, slag inclusion, cracks, insufficient penetration, excessively wide weld, weld burn-through, and uneven surface; and / or, the preset quality standards include at least one of the following: weld width error range, penetration error range, surface flatness scoring threshold, and defect number threshold.

[0016] Optionally, if the judgment unit determines that the current welding quality is unqualified, the adjustment unit adjusts the welding parameters of the welding robot according to the defect type of the existing weld defect, including: adjusting the welding parameters according to the defect type and according to the preset parameter adjustment rules corresponding to different defect types.

[0017] Optionally, the welding parameters include at least one of current, voltage, and speed; the preset parameter adjustment rules corresponding to different defect types include increasing or decreasing at least one of current, voltage, and speed according to different defect types.

[0018] Optionally, the control unit is further configured to: after the adjustment unit adjusts the welding parameters of the welding robot, acquire again the image of the welding area of ​​the welding robot collected by the UAV following the welding robot; the recognition unit is further configured to: extract features from the image of the welding area collected by the UAV to obtain weld features, and analyze the extracted weld features to determine whether the weld defect has been eliminated.

[0019] Optionally, it further includes: a generation unit, configured to generate a defect feedback report containing the defect type, location, and severity if the identification unit identifies a weld defect.

[0020] Optionally, it also includes: a storage unit, used to store the images, welding quality judgment results and welding parameter adjustment records collected during the welding process after the welding robot has completed the welding operation, and to generate a welding quality report.

[0021] In another aspect, the present invention provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0022] In another aspect, the present invention provides a robot controller, including a processor, a memory, and a computer program stored in the memory that can run on the processor, wherein the processor executes the program to implement the steps of any of the methods described above.

[0023] In another aspect, the present invention provides a robot controller, including any of the aforementioned UAV-based welding robot monitoring devices.

[0024] In another aspect, the present invention provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the methods described above.

[0025] According to the technical solution of the present invention, the welding process can be monitored and its quality assessed in real time by using a drone to dynamically track and photograph the welding robot during its operation, thus ensuring full coverage of the welding area.

[0026] According to the technical solution of the present invention, weld defects can be automatically identified and fed back to the welding robot control system to achieve closed-loop control.

[0027] According to the technical solution of the present invention, the UAV and the welding robot control module transmit data through a wireless communication module, thereby improving the system's flexibility and adaptability.

[0028] According to the technical solution of the present invention, by working collaboratively with a drone and a welding robot, multi-angle, real-time image acquisition and analysis of the welding area is achieved, which improves the level of welding quality control, reduces the rework rate, and enhances the safety and intelligence of welding operations. Attached Figure Description

[0029] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:

[0030] Figure 1 This is a schematic diagram of an embodiment of the welding robot monitoring method based on unmanned aerial vehicles provided by the present invention;

[0031] Figure 2 A schematic diagram of the overall system configuration is shown;

[0032] Figure 3 This is a schematic diagram of a specific embodiment of the welding robot monitoring method based on unmanned aerial vehicles provided by the present invention;

[0033] Figure 4 This is a structural block diagram of an embodiment of the welding robot monitoring device based on unmanned aerial vehicles provided by the present invention. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0035] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0036] The welding robots using these technologies lack real-time monitoring and feedback mechanisms for welding quality, making it difficult to detect weld defects or anomalies in a timely manner. Furthermore, these robots typically possess only a single function, failing to achieve dynamic monitoring and data acquisition during the welding process. While some systems incorporate cameras for image acquisition, limitations in installation location and movement range prevent comprehensive coverage of the welding area, especially in complex structures or high-altitude working environments, resulting in limited monitoring effectiveness.

[0037] This invention provides a method and device for monitoring welding robots based on unmanned aerial vehicles (UAVs).

[0038] Specifically, this invention can be a welding robot monitoring system based on unmanned aerial vehicles (UAVs). This system can specifically include a welding robot, a UAV, an image acquisition module, an image processing module, a communication module, and a robot control module.

[0039] Welding robot: As the core equipment for performing welding tasks, it is equipped with a welding torch at its end and its movement trajectory can be controlled by a servo motor to achieve precise welding.

[0040] Drone: Equipped with a camera and image processing module, it is used for real-time photography and image acquisition of the welding area. The drone maintains data synchronization with the welding robot control module via a wireless communication module. Figure 2 A schematic diagram of the overall system configuration of the present invention is shown. For example... Figure 2 As shown, the UAV 3 is equipped with a module 4 that integrates an image acquisition module, an image processing module, and a communication module.

[0041] Image acquisition module: Composed of cameras on the drone, responsible for acquiring images of the welding area from multiple angles and perspectives.

[0042] Image processing module: performs real-time analysis on the acquired images, identifies defects such as weld shape, penetration depth, and porosity, and feeds the results back to the robot control module.

[0043] Communication module: Employs wireless communication (such as Wi-Fi or 5G) to enable data transmission and command interaction between the welding robot control module and the drone.

[0044] Robot control module: Receives the analysis results from the image processing module and determines whether the welding quality is acceptable based on preset standards. If it is unacceptable, it sends adjustment instructions to the welding robot. For example... Figure 2 As shown, the welding robot 1 is connected to the robot control module 2.

[0045] Figure 1 This is a schematic diagram of an embodiment of the welding robot monitoring method based on unmanned aerial vehicles provided by the present invention.

[0046] like Figure 1 As shown, according to an embodiment of the present invention, the UAV-based welding robot monitoring method includes at least steps S110, S120 and S130.

[0047] Step S110: When the welding robot performs the welding operation, the drone follows the welding robot and collects images of the welding area of ​​the welding robot.

[0048] Specifically, the welding robot and drone are started, and each module completes self-testing and calibration. The welding robot completes welding torch position correction and motion trajectory preset; the drone completes camera focus adjustment, flight altitude setting, and communication module connection testing. Based on the structural characteristics of the welding work area, the control system plans the welding robot's movement path and simultaneously plans the drone's flight path to ensure that the drone is always at the optimal shooting angle, covering the welding area. A wireless communication link (such as Wi-Fi or 5G) is established between the welding robot control module and the drone to ensure that image data, control commands, and other information can be transmitted in real time.

[0049] The welding robot starts according to a preset path, and the welding torch begins to move along the preset welding trajectory to perform the welding operation. The drone follows the welding robot. Specifically, the drone is controlled to fly above or to the side of the welding robot, maintaining a relative distance from the welding area, and continuously acquiring images of the welding area. The drone can adopt an automatic following mode, dynamically adjusting its flight attitude according to the position of the welding robot to ensure that the welding robot does not obstruct the welding area. The high-definition camera on the drone captures multi-angle images of the welding area, acquiring real-time images of the weld seam during the welding process, and transmitting the image data to the image processing module.

[0050] Step S120: Extract features from the image of the welding area collected by the UAV to obtain weld features, and analyze the extracted weld features to identify weld defects.

[0051] Specifically, the image of the welding area captured by the drone is first preprocessed; then, feature extraction is performed on the preprocessed image to obtain weld features. The preprocessing may include at least one of denoising, contrast enhancement, and edge detection. For example, after receiving the original image from the drone, the image processing module first performs preprocessing operations such as denoising, contrast enhancement, and edge detection to improve image quality. The feature extraction can be implemented by pre-training a feature extraction model, such as a convolutional neural network model.

[0052] The extracted weld features are analyzed to identify the presence of welding defects and classify the defect types. These welding defects may include, for example, at least one of the following: lack of fusion, porosity, slag inclusions, insufficient penetration due to cracks, excessive weld width, weld burn-through, and surface unevenness. The welding defects can be identified using a pre-trained recognition model, such as a neural network model. For example, after extracting the weld features, the extracted weld feature map is input into the pre-trained recognition model, which outputs the defect type. Preferably, if a weld defect is identified, a feedback report containing information on the defect type, location, and severity is generated.

[0053] For example, after receiving raw images from a drone, the image processing module first performs preprocessing operations such as noise reduction, contrast enhancement, and edge detection to improve image quality. It then analyzes the extracted weld features to identify common welding defects such as lack of fusion, porosity, slag inclusions, and cracks, and classifies these defects. If a defect is found, a feedback report containing information such as defect type, location, and severity is generated. The severity can be determined, for example, based on the number of defects; different numbers of different defects (specifically, the number of defects per unit area) correspond to different degrees of severity. For instance, for the defect type porosity, a quantity exceeding a certain value indicates severity, and so on.

[0054] Step S130: If a weld defect is identified, determine whether the current welding quality is qualified according to the preset quality standard.

[0055] The preset quality standards may specifically include at least one of the following: weld width error range, penetration depth error range, penetration depth error range, surface smoothness scoring threshold, and defect number threshold. That is, it is determined whether the weld width error is within a preset error range, the penetration depth is within a preset penetration depth error range, the surface smoothness score reaches a preset value, and the number of defects per unit area is less than or equal to a preset defect number threshold. If all conditions are met, the current welding quality is deemed acceptable; if any condition is not met, the current welding quality is deemed unacceptable. The surface smoothness score is based on a comprehensive judgment of the number of different types of defects per unit area. For example, different surface smoothness scores are given based on the different quantities of different types of defects within a unit area. The surface smoothness scores for different types of defects are calculated based on the different quantities of different types of defects within a unit area and the preset different quantities of different types of defects within a unit area. Then, the calculated surface smoothness scores for different types of defects are weighted and averaged according to the preset weights of different types of defects to obtain the overall surface smoothness score. For example, the score is obtained by comprehensively judging the quantity of defects such as pores, inclusions, and cracks.

[0056] For example, the quality standards are: weld width error range: ±0.5mm; penetration depth error range: ±0.3mm; surface flatness score ≥0.8; number of defects ≤1 / 1000mm 2 If all indicators are met, the result is considered "qualified"; if any indicator fails to meet the standard, the result is considered "unqualified".

[0057] like Figure 1 As shown, based on the above embodiments, the method may further include step S140.

[0058] Step S140: If the current welding quality is determined to be unqualified, the welding parameters of the welding robot are adjusted according to the defect type of the existing weld defect.

[0059] In one specific implementation, the welding parameters are adjusted according to the defect type and pre-defined parameter adjustment rules corresponding to different defect types. The welding parameters may specifically include at least one of current, voltage, and speed. The parameter adjustment rules corresponding to different defects may specifically include increasing or decreasing at least one of the current, voltage, and welding speed. The increase or decrease in the current, voltage, or welding speed can be obtained through experimental testing. For example, it can be constructed based on welding metallurgy principles and practical process experience, and optimized through training with historical data.

[0060] The parameter adjustment rules for different defects can be found in Table 1 below:

[0061] Table 1

[0062] Defect types Adjust parameters Unfused Current increases, voltage increases, welding speed decreases pores Current ↓, Voltage ↓, Welding speed ↑ Insufficient penetration Current increases, voltage increases, welding speed decreases Weld too wide / burn-through Current ↓, Voltage ↓, Welding speed ↑ Uneven surface Current increases, voltage increases, welding speed decreases

[0063] In this diagram, the upward arrow indicates an increase, and the downward arrow indicates a decrease. For example, when there is an incomplete fusion defect, increasing the current and voltage will decrease the speed.

[0064] For example, if the welding quality is unqualified, the robot control module automatically matches the optimal adjustment strategy according to the defect type, sends adjustment instructions to the welding robot, changes the welding current, voltage, speed, or re-welds the defective area.

[0065] Preferably, after adjusting the welding parameters of the welding robot, the image of the welding area of ​​the welding robot is acquired again by the UAV following the welding robot; feature extraction is performed on the image of the welding area acquired by the UAV to obtain weld features, and the extracted weld features are analyzed to determine whether the weld defects have been eliminated.

[0066] For example, based on received instructions, the welding robot adjusts welding parameters or re-executes the welding action to repair defective areas. The drone continues to acquire images of the corrected welded area, and the image processing module analyzes them again to confirm whether the defect has been eliminated and to ensure that the welding quality meets the standards.

[0067] Optionally, it also includes: after the welding robot completes the welding operation, storing the images collected during the welding process, the welding quality judgment results, and the welding parameter adjustment records, and generating a welding quality report.

[0068] For example, once the welding robot has completed all welding tasks, the system automatically stops operating and prompts the operator to check the welding results. The system stores image data, welding quality judgment results, parameter adjustment records, and other information from the entire welding process in a local database or cloud server, and generates a complete welding quality report for subsequent quality traceability and optimization reference.

[0069] By employing the technical solution of this invention, multiple drones can be deployed to work collaboratively in large ship welding operations, each responsible for image acquisition and analysis in different areas, forming a distributed monitoring network. Each drone can be controlled independently or centrally scheduled by the main control system, improving overall monitoring efficiency and coverage.

[0070] To clearly illustrate the technical solution of the present invention, the execution flow of the UAV-based welding robot monitoring method provided by the present invention will be described below with a specific embodiment.

[0071] Figure 3This is a schematic diagram of a specific embodiment of the welding robot monitoring method based on unmanned aerial vehicles (UAVs) provided by the present invention. Figure 3 As shown, the system is first initialized and deployed, including: starting and calibrating the welding robot and the drone, planning the movement path of the welding robot when performing welding tasks, establishing wireless communication between the welding robot and the drone, and then the welding robot starts working. The drone enters the monitoring state to acquire images, processes the images, identifies and classifies defects, and performs quality analysis to determine whether welding parameters need to be adjusted. Control feedback and welding correction are performed, images of the corrected welding area are acquired, and it is determined whether the defects have been eliminated. The operation ends, and the image data, quality analysis results, and parameter adjustment records of the entire welding process are stored.

[0072] Figure 4 This is a structural block diagram of an embodiment of the welding robot monitoring device based on a drone provided by the present invention. Figure 4 As shown, the monitoring device 100 includes: an acquisition unit 110, an identification unit 120, and a judgment unit 130.

[0073] The acquisition unit 110 is used to acquire images of the welding area of ​​the welding robot by the drone flying alongside the welding robot when the welding robot performs the welding operation.

[0074] Specifically, the welding robot and drone are started, and each module completes self-testing and calibration. The welding robot completes welding torch position correction and motion trajectory preset; the drone completes camera focus adjustment, flight altitude setting, and communication module connection testing. Based on the structural characteristics of the welding work area, the control system plans the welding robot's movement path and simultaneously plans the drone's flight path to ensure that the drone is always at the optimal shooting angle, covering the welding area. A wireless communication link (such as Wi-Fi or 5G) is established between the welding robot control module and the drone to ensure that image data, control commands, and other information can be transmitted in real time.

[0075] The welding robot starts according to a preset path, and the welding torch begins to move along the preset welding trajectory to perform the welding operation. The drone follows the welding robot. Specifically, the drone is controlled to fly above or to the side of the welding robot, maintaining a relative distance from the welding area, and continuously acquiring images of the welding area. The drone can adopt an automatic following mode, dynamically adjusting its flight attitude according to the position of the welding robot to ensure that the welding robot does not obstruct the welding area. The high-definition camera on the drone captures multi-angle images of the welding area, acquiring real-time images of the weld seam during the welding process, and transmitting the image data to the image processing module.

[0076] The identification unit 120 is used to extract features from the image of the welding area collected by the UAV to obtain weld features, and to analyze the extracted weld features to identify whether there are weld defects.

[0077] Specifically, the image of the welding area captured by the drone is first preprocessed; then, feature extraction is performed on the preprocessed image to obtain weld features. The preprocessing may include at least one of denoising, contrast enhancement, and edge detection. For example, after receiving the original image from the drone, the image processing module first performs preprocessing operations such as denoising, contrast enhancement, and edge detection to improve image quality. The feature extraction can be implemented by pre-training a feature extraction model, such as a convolutional neural network model.

[0078] The extracted weld features are analyzed to identify the presence of welding defects and classify the defect types. These welding defects may include, for example, at least one of the following: lack of fusion, porosity, slag inclusions, insufficient penetration due to cracks, excessive weld width, weld burn-through, and surface unevenness. The welding defects can be identified using a pre-trained recognition model, such as a neural network model. For example, after extracting the weld features, the extracted weld feature map is input into the pre-trained recognition model, which outputs the defect type. Optionally, the device 100 may further include a generation unit (not shown), used to generate a defect feedback report containing the defect type, location, and severity if the recognition unit identifies the presence of a weld defect. The severity can be determined, for example, based on the number of defects; different numbers of different defects (specifically, the number of defects per unit area) correspond to different severity levels. For example, for the defect type porosity, a quantity exceeding a certain value indicates severity, and so on.

[0079] For example, after receiving raw images from a drone, the image processing module first performs preprocessing operations such as noise reduction, contrast enhancement, and edge detection to improve image quality. It then analyzes the extracted weld features to identify common welding defects such as lack of fusion, porosity, slag inclusions, and cracks, and classifies these defects. If a defect is found, a feedback report containing information such as the defect type, location, and severity is generated.

[0080] The judgment unit 130 is used to determine whether the current welding quality is qualified according to the preset quality standard if the identification unit identifies the presence of weld defects.

[0081] The preset quality standards may specifically include at least one of the following: weld width error range, penetration depth error range, penetration depth error range, surface smoothness scoring threshold, and defect number threshold. That is, it is determined whether the weld width error is within a preset error range, the penetration depth is within a preset penetration depth error range, the surface smoothness score reaches a preset value, and the number of defects per unit area is less than or equal to a preset defect number threshold. If all conditions are met, the current welding quality is deemed acceptable; if any condition is not met, the current welding quality is deemed unacceptable. The surface smoothness score is based on a comprehensive judgment of the number of different types of defects per unit area. For example, different surface smoothness scores are given based on the different quantities of different types of defects within a unit area. The surface smoothness scores for different types of defects are calculated based on the different quantities of different types of defects within a unit area and the preset different quantities of different types of defects within a unit area. Then, the calculated surface smoothness scores for different types of defects are weighted and averaged according to the preset weights of different types of defects to obtain the overall surface smoothness score. For example, the score is obtained by comprehensively judging the quantity of defects such as pores, inclusions, and cracks.

[0082] For example, the quality standards are: weld width error range: ±0.5mm; penetration depth error range: ±0.3mm; surface flatness score ≥0.8; number of defects ≤1 / 1000mm 2 If all indicators are met, the result is considered "qualified"; if any indicator fails to meet the standard, the result is considered "unqualified".

[0083] like Figure 4 As shown, the monitoring device 100 may further include an adjustment unit 140, which is used to adjust the welding parameters of the welding robot according to the defect type of the existing weld defect if the judgment unit determines that the current welding quality is unqualified.

[0084] In one specific implementation, the welding parameters are adjusted according to the defect type and pre-defined parameter adjustment rules corresponding to different defect types. The welding parameters may specifically include at least one of current, voltage, and speed. The parameter adjustment rules corresponding to different defects may specifically include increasing or decreasing at least one of the current, voltage, and welding speed. The increase or decrease in the current, voltage, or welding speed can be obtained through experimental testing. For example, it can be constructed based on welding metallurgy principles and practical process experience, and optimized through training with historical data.

[0085] The parameter adjustment rules for different defects can be found in Table 1 below:

[0086] Table 1

[0087] Defect types Adjust parameters Unfused Current increases, voltage increases, welding speed decreases pores Current ↓, Voltage ↓, Welding speed ↑ Insufficient penetration Current increases, voltage increases, welding speed decreases Weld too wide / burn-through Current ↓, Voltage ↓, Welding speed ↑ Uneven surface Current increases, voltage increases, welding speed decreases

[0088] In this diagram, the upward arrow indicates an increase, and the downward arrow indicates a decrease. For example, when there is an incomplete fusion defect, increasing the current and voltage will decrease the speed.

[0089] For example, if the welding quality is unqualified, the robot control module automatically matches the optimal adjustment strategy according to the defect type, sends adjustment instructions to the welding robot, changes the welding current, voltage, speed, or re-welds the defective area.

[0090] Preferably, the acquisition unit 110 is further configured to: after the adjustment unit adjusts the welding parameters of the welding robot, acquire again the image of the welding area of ​​the welding robot collected by the UAV following the welding robot; the identification unit 120 is further configured to: extract features from the image of the welding area collected by the UAV to obtain weld features, and analyze the extracted weld features to determine whether the weld defects have been eliminated.

[0091] For example, based on received instructions, the welding robot adjusts welding parameters or re-executes the welding action to repair defective areas. The drone continues to acquire images of the corrected welded area, and the image processing module analyzes them again to confirm whether the defect has been eliminated and to ensure that the welding quality meets the standards.

[0092] Optionally, the device 100 may further include a storage unit (not shown) for storing images, welding quality judgment results, and welding parameter adjustment records collected during the welding process after the welding robot has completed the welding operation, and generating a welding quality report.

[0093] For example, once the welding robot has completed all welding tasks, the system automatically stops operating and prompts the operator to check the welding results. The system stores image data, welding quality judgment results, parameter adjustment records, and other information from the entire welding process in a local database or cloud server, and generates a complete welding quality report for subsequent quality traceability and optimization reference.

[0094] The present invention also provides a storage medium corresponding to the aforementioned UAV-based welding robot monitoring method, wherein a computer program is stored thereon, and the computer program, when executed by a processor, implements the steps of any of the aforementioned methods.

[0095] The present invention also provides a robot controller corresponding to the aforementioned UAV-based welding robot monitoring method, comprising a processor, a memory, and a computer program stored in the memory that can run on the processor, wherein the processor executes the computer program to implement the steps of any of the aforementioned methods.

[0096] The present invention also provides a robot controller corresponding to the aforementioned drone-based welding robot monitoring device, including any of the aforementioned drone-based welding robot monitoring devices.

[0097] The present invention also provides a computer program product corresponding to the aforementioned UAV-based welding robot monitoring method, comprising a computer program that, when executed by a processor, implements the steps of any of the aforementioned methods.

[0098] Accordingly, the solution provided by the present invention uses a drone equipped with a high-definition camera to dynamically track and film the welding robot during its operation, thereby achieving real-time monitoring and quality assessment of the welding process and ensuring full coverage of the welding area.

[0099] The solution provided by this invention, through the collaborative work of drones and welding robots, enables multi-angle, real-time image acquisition and analysis of the welding area, thereby improving the level of welding quality control, reducing rework rate, and enhancing the safety and intelligence of welding operations.

[0100] The functions described herein can be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions can be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and embodiments are within the scope and spirit of this invention and the appended claims. For example, due to the nature of software, the functions described above can be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Furthermore, the functional units can be integrated into a single processing unit, or each unit can exist physically separately, or two or more units can be integrated into a single unit.

[0101] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0102] The units described as separate components may or may not be physically separate. Similarly, the components of the control device may or may not be physical units; they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0103] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to related technologies, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0104] The above description is merely an embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A method for monitoring a welding robot based on a drone, characterized by, The method comprises the following steps: When the welding robot performs a welding operation, the unmanned aerial vehicle flies following the welding robot to collect images of a welding area of the welding robot; Feature extraction is performed on the images of the welding area collected by the unmanned aerial vehicle to obtain weld features, and analysis is performed on the extracted weld features to identify whether there is a weld defect; If it is identified that there is a weld defect, it is determined whether the current welding quality is qualified according to a preset quality standard.

2. The method of claim 1, wherein, Further comprising: If it is determined that the current welding quality is unqualified, the welding parameters of the welding robot are adjusted according to the defect type of the existing weld defect.

3. The method of claim 1, wherein The welding defect comprises at least one of incomplete fusion, porosity, slag inclusion, crack, insufficient penetration, excessive weld width, weld burn-through, and surface unevenness; And / or The preset quality standard comprises at least one of a weld width error range, a penetration error range, a surface flatness score threshold, and a defect quantity threshold.

4. The method of claim 2, wherein, If it is determined that the current welding quality is unqualified, the welding parameters of the welding robot are adjusted according to the defect type of the existing weld defect, comprising: According to the defect type, the welding parameters are adjusted according to a preset parameter adjustment rule corresponding to different defect types.

5. The method of claim 4, wherein The welding parameter comprises at least one of current, voltage, and speed; The preset parameter adjustment rule corresponding to different defect types comprises increasing or decreasing at least one of the current, voltage, and speed according to different defect types.

6. The method of claim 5, wherein, Further comprising: After the welding parameters of the welding robot are adjusted, the unmanned aerial vehicle flies following the welding robot again to collect images of the welding area of the welding robot; Feature extraction is performed on the images of the welding area collected by the unmanned aerial vehicle to obtain weld features, and analysis is performed on the extracted weld features to determine whether the weld defect has been eliminated.

7. The method according to any one of claims 1 to 6, characterized in that, Further comprising: If it is identified that there is a weld defect, a defect feedback report containing the defect type, location, and severity is generated.

8. The method according to any one of claims 1 to 6, characterized in that, Further comprising: After the welding robot performs a welding operation, the images collected during the welding process, the welding quality determination result, and the welding parameter adjustment record are stored, and a welding quality report is generated.

9. An unmanned aerial vehicle based welding robot monitoring device, characterized in that, The method comprises the following steps: An acquisition unit is configured to acquire images of a welding area of a welding robot collected by an unmanned aerial vehicle flying following the welding robot when the welding robot performs a welding operation; An identification unit is configured to perform feature extraction on the images of the welding area collected by the unmanned aerial vehicle to obtain weld features, and perform analysis on the extracted weld features to identify whether there is a weld defect; A determination unit is configured to determine whether the current welding quality is qualified according to a preset quality standard if the identification unit identifies that there is a weld defect.

10. A storage medium, characterized by A computer program is stored thereon, and the program is executed by a processor to implement the steps of the method of any one of claims 1-8.

11. A robot controller characterized by A computer program product comprising a processor, a memory, and a computer program stored on the memory and loadable on the processor, the processor implementing the steps of the method according to any one of claims 1 to 8 when executing the program, or a monitoring device according to claim 9.

12. A computer program product, characterised in that, A computer program product comprising a computer program, the computer program implementing the steps of the method according to any one of claims 1 to 8 when executed by a processor.

Images