Multi-process integrated control system of intelligent short pipe assembling and welding robot

Abstract

The invention discloses a multi-process integrated control system of a short pipe intelligent assembly welding robot, which belongs to the technical field of welding robots and comprises a visual identification module, a motion control module, a parameter compensation module, a central control module and a data conversion and anomaly identification module. The visual recognition module is used for collecting short pipe welding image data, including short pipe images before welding, during welding and after welding, in different stages of the welding process of the welding robot through an industrial camera and transmitting the collected data into the central control module, and the motion control module comprises a motion controller, a motor driver and an execution motor. The welding robot is controlled to act by receiving a control instruction of the central control module. According to the multi-process integrated control system of the short pipe intelligent assembly welding robot, welding abnormity in the working process of the welding robot is rapidly recognized, and targeted parameter adjustment is conducted in combination with different welding stages, so that the actual welding process of the welding robot is optimized, and the welding quality is improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of welding robots, in particular to a multi-process integrated control system of a short pipe intelligent group welding robot. BACKGROUND

[0002] In the field of modern industrial manufacturing, short pipe welding, as a key process in the pipeline engineering and mechanical manufacturing industries, directly affects the product performance and service life. With the increasing demand for automation and intelligentization in the manufacturing industry, traditional manual welding methods have been unable to meet the requirements of large-scale and high-precision production due to low efficiency, poor quality stability, and high labor intensity. Although short pipe group welding by welding robots can improve welding efficiency, due to the small size and large curvature of short pipes, defects such as uneven weld width, misalignment, porosity, and poor continuity may occur during welding. The existing multi-process integrated control system of welding robots lacks real-time detection capability for small welding defects. Moreover, due to the uneven appearance of welds, it is difficult to quickly locate welding abnormalities and analyze the causes. In addition, different welding parameters during the welding process of welding robots are coupled, and there is a lack of targeted adjustment strategies for welding parameters in different welding stages under welding abnormalities, resulting in the inability to timely correct welding defects and low practicality and functionality. SUMMARY

[0003] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a multi-process integrated control system of a short pipe intelligent group welding robot, which improves the detection method and processing method to solve the above technical problems.

[0004] To achieve the above purpose, the present application adopts the following technical solutions: The multi-process integrated control system of the short pipe intelligent group welding robot comprises a visual recognition module, a motion control module, a parameter compensation module, a central control module, and a data conversion and abnormality recognition module. The visual recognition module uses an industrial camera to collect short pipe welding image data at different stages of the welding process of the welding robot, including short pipe images before, during, and after welding, and transmits the collected data into the central control module. The motion control module comprises a motion controller, a motor driver, and an execution motor, which receives control instructions from the central control module to control the action of the welding robot. The central control module transmits control instructions into the motion control module based on the input welding program, receives parameter compensation content from the parameter compensation module, iteratively replaces welding parameters in the welding program in real time, receives short pipe welding image data from the visual recognition module, pre-processes the images, and transmits them to the data conversion and abnormality recognition module. The data conversion and anomaly identification module is used for line conversion processing of short pipe welding image data obtained in different welding stages in the welding process, identifies short pipe welding anomalies based on the processed short pipe image data after welding, obtains short pipe anomaly data, analyzes the abnormal reasons in combination with the image line data in different welding stages, and transmits the data to the parameter compensation module. The parameter compensation module identifies the parameters to be adjusted in combination with the abnormal reason based on the short pipe anomaly data obtained by the data conversion and anomaly identification module, adjusts the parameters to be adjusted based on the historical data large model, and outputs the final parameter compensation result according to the short pipe image data after parameter adjustment.

[0005] Further, the data conversion and anomaly identification module is used for line conversion processing of short pipe welding image data obtained in different welding stages in the welding process, identifies short pipe welding anomalies based on the processed short pipe image data after welding, obtains short pipe anomaly data, analyzes the abnormal reasons in combination with the image line data in different welding stages, and transmits the data to the parameter compensation module, including the following steps: The edge points in the short pipe welding image data are detected by using an edge detection algorithm, the edge points are converted into continuous lines, and features including weld width, weld length, weld continuity and weld edge roughness are extracted from the processed short pipe image line data after welding. The welding anomalies are identified based on the features in the short pipe image line data after welding, the image line data in different welding stages are associated, the time and space relationship of the line data is established, and the abnormal reasons are analyzed.

[0006] Further, the edge points in the short pipe welding image data obtained in different welding stages in the welding process are identified by using an edge detection algorithm, the edge points are converted into continuous lines, and features including weld width, weld length, weld continuity and weld edge roughness are extracted from the processed short pipe image line data after welding, including the following steps: The edge points in the short pipe welding image data obtained in different welding stages in the welding process are identified by using an edge detection algorithm, including the following steps: The gradients of the image in the x and y directions are calculated by using Sobel operators respectively. The gradients of the image in the x and y directions are calculated by using Sobel operators respectively. The gradients of the image in the x and y directions are calculated by using Sobel operators respectively. The gradients of the image in the x and y directions are calculated by using Sobel operators respectively. The gradients of the image in the x and y directions are calculated by using Sobel operators respectively. The gradients of the image in the x and y directions are calculated by using Sobel operators respectively. The gradients of the image in the x and y directions are calculated by using Sobel operators respectively. The gradients of the image in the x and y directions are calculated by using Sobel operators respectively. The gradients of the image in the x and y directions are calculated by using Sobel operators respectively. wherein, representing the short pipe welding image of different welding stages after pre-processing by the central control module, representing the convolution operation, further calculating the gradient amplitude and gradient direction, wherein the gradient amplitude , the gradient direction ; by double threshold detection to identify strong edge points, including based on threshold and , the gradient amplitude is compared, when > representing the current strong edge point, when < representing the current pixel point is a non-edge point, when ≤ ≤ , if the pixel point is connected with the strong edge point, it is determined as a strong edge point, if the pixel point is connected with the non-edge point, it is determined as a non-edge point; using the Hough transform to detect the straight line in the image, connecting the edge points into continuous lines, including: by calculating the value according to the discretization value range for each strong edge point in the image, wherein , further traversing the accumulator array , finding the point greater than the preset threshold, which is the parameter of the detected straight line, for each satisfying the condition, the straight line in the Cartesian coordinate system is obtained by back calculation; for each straight line detected by the Hough transform, determining two end points and , calculating the angle of each straight line, for two straight lines and , calculating the angle difference , and calculating the minimum value of the end point distance ; based on the distance threshold and the angle difference threshold, when and satisfy respectively less than the distance threshold and the angle difference threshold, then the straight lines and are merged into a new straight line.

[0007] Further, the feature extraction from the processed short pipe welding image line data includes the welding seam width, the welding seam length, the welding seam continuity and the welding seam edge roughness, including the following steps: Based on the line obtained by Hough transform, the distance between two boundary lines in the direction perpendicular to the weld is calculated by determining the boundary lines of the weld, and the average value is taken as the final weld width after multiple calculations at different positions of the weld; Based on the line obtained by Hough transform, the total distance between all pixel points on the line is calculated along the weld line, and the Euclidean distance between adjacent pixel points is accumulated to obtain the weld length. Based on the line obtained by Hough transform, the number of lines is counted as a weld continuity indicator, and when the number of lines exceeds a certain threshold, it represents that the current weld has poor weld continuity. By calculating the distance variance of each pixel point on the edge line and the pixel points in its neighborhood as the weld edge roughness, the larger the variance, the rougher the weld edge.

[0008] Further, the features based on the line data of the short tube image after welding are used to identify welding abnormalities, the image line data of different welding stages are associated, the space-time relationship of the line data is established, and the abnormal reasons are analyzed, including the following steps: Based on the standard or experience of normal welding, set the threshold value of the normal range for each feature, including weld width, weld length, weld continuity, weld edge roughness, and mark the features that are not within the threshold value as abnormal features; Add time labels to each image and corresponding line data of each welding stage to record their order in the welding process, associate the line data of adjacent welding stages according to the time sequence, compare the end point positions and angle differences of the weld lines of adjacent stages, and judge whether they belong to different stages of the same weld, the end point distance and angle difference less than the distance threshold and angle difference threshold are determined as different stages of the same weld, and the welding stages include before welding, during welding and after welding; According to the feature combination and space-time change of the welding abnormality, the welding abnormality reason is output according to the preset rule.

[0009] Further, the short tube abnormal data obtained by the data transformation and abnormality identification module is combined with the abnormal reason identification to adjust the parameters, the historical data model is used to adjust the parameters based on the historical data, and the final parameter compensation result is output according to the parameter adjustment of the short tube image data, including the following steps: Get the short tube abnormal data from the data transformation and abnormality identification module, including the abnormal values of weld width, weld length, weld continuity, weld edge roughness, and the corresponding welding stage and related process parameters, wherein the related process parameters are the process parameter values of the input welding program in different welding stages; By collecting historical welding data, a large-scale parameter adjustment model is established. Combined with the welding process parameters involved in different abnormal causes, parameter adjustment values ​​are generated to perform targeted parameter compensation for the current welding program.

[0010] Furthermore, the step of establishing a large-scale parameter adjustment model by collecting historical welding data, combining welding process parameters involved in different anomalies, generating parameter adjustment values, and performing targeted parameter compensation for the current welding program includes the following steps: Collect a large amount of historical welding data, including short pipe image data of normal and different abnormal welding conditions, corresponding process parameters and welding quality assessment results. Extract features related to welding quality and process parameters from historical data, and train a large model by adjusting parameters through neural networks. Using process parameters as input and welding quality characteristics as output, the training model learns the mapping relationship between process parameters and welding quality. Based on the historical data mean and standard deviation of parameters under different abnormal causes, the model sets an initial adjustment range for the parameters to be adjusted based on the 3σ principle. The current value of the parameter to be adjusted is input into the trained parameter adjustment model to predict the possible welding quality characteristic values ​​after adjustment. The deviation between the predicted welding quality characteristic values ​​and the normal range is calculated. This includes the following steps: According to the lower limit of the normal range Upper limit and predicted values Calculate the deviation : when < hour, ; when > hour, ; when ≤ ≤ hour, ; Based on gradient descent, combined with bias For the parameters to be adjusted Make adjustments when When >0 and the deviation is positive, then When the deviation is negative, then ,in Represents the learning rate. Representative bias about The gradient is then adjusted, and the above adjustment steps are repeated until the predicted welding quality feature value enters the normal range or the maximum number of iterations is reached. Based on the abnormality transmitted by the data conversion and abnormality identification module, the welding quality characteristic value output by the parameter adjustment large model is transmitted into the central control module to adjust the welding program parameters and feed back to the motion control module.

[0011] Further, the central control module transmits the control instruction into the motion control module based on the input welding program, receives the parameter compensation content of the parameter compensation module, and iteratively replaces the welding parameters in the welding program in real time, receives the short pipe welding image data in the visual identification module, pre-processes the image and transmits it to the data conversion and abnormality identification module, including the following steps: The parameter optimization content sent by the parameter compensation module is received through the communication interface, including the welding parameter name to be adjusted and the adjusted parameter value, the welding parameter to be adjusted is searched in the data structure of the welding program, and the parameter value is replaced with the parameter value provided by the parameter compensation module; The short pipe welding image data in the visual identification module is received for pre-processing, including grayscale processing and denoising.

[0012] Compared with the prior art, the beneficial effects of the present application are: 1. In the present application, the line conversion is performed on the recognition image of the short pipe butt welding during the working process of the welding robot to quickly identify the abnormality in the current welding process of the welding robot, analyze the abnormality reason based on different welding stages, adjust the abnormal parameters accordingly, achieve the purpose of real-time adjustment of the welding of the welding robot, and improve the quality of the short pipe group butt welding; 2. In the present application, the abnormality is identified in real time during the welding process, including problems such as uneven weld width and poor continuity, to discover welding defects in time, the deviation in the welding process can be corrected immediately through targeted adjustment of abnormal parameters, defects are prevented from further expanding, the weld quality is ensured to meet the standard requirements, the overall quality of the short pipe group butt welding is improved, the welds in different stages of welding are associated to comprehensively analyze the causes of different welding faults and the involved parameters, and the welding program of the welding robot is adjusted accordingly; 3. In the present application, the closed-loop system of the parameter compensation module, the central control module and the data conversion and abnormality identification module achieves rapid identification of welding abnormality, rapid determination of targeted parameters, and parameter adjustment and compensation, the deviation in the welding process can be corrected in time through real-time feedback and adjustment mechanism, defects are prevented from further expanding, the welding product quality of the welding robot is ensured to always meet the standard requirements, and the practicality is enhanced. BRIEF DESCRIPTION OF DRAWINGS

[0013] Figure 1 The short pipe intelligent group butt welding robot multi-process integrated control system block diagram of the present application. DETAILED DESCRIPTION

[0014] The technical solutions of the present application will be described clearly and completely in combination with the embodiments below. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0015] As shown in the drawings, the multi-process integrated control system of the short pipe intelligent assembly welding robot of the embodiment of the present application comprises a visual recognition module, a motion control module, a parameter compensation module, a central control module, and a data conversion and abnormality recognition module. Figure 1 The visual recognition module is used to collect short pipe welding image data at different stages of the welding process of the welding robot, including short pipe images before, during and after welding, through an industrial camera, and transmits the collected data into the central control module.

[0016] It should be noted that an industrial camera with appropriate resolution is selected according to the size of the short pipe and the detection accuracy requirement, and a high-resolution camera, i.e., an industrial camera with more than 5 million pixels, is usually used to ensure that the details of the short pipe can be clearly captured.

[0017] The motion control module comprises a motion controller, a motor driver and an execution motor, which controls the action of the welding robot by receiving the control instructions of the central control module.

[0018] It should be noted that the motion controller comprises multi-axis motion control, which can control multiple joint axes of the robot at the same time to realize complex motion trajectories, and supports multiple interpolation methods such as linear interpolation and circular interpolation to realize smooth motion trajectories. According to the input path point and speed requirement, the motion parameters of each axis are calculated, and the motor driver needs to select a motor driver with appropriate power according to the load and motion requirement of the joint axis of the robot.

[0019] The central control module transmits control instructions into the motion control module based on the input welding program, receives the parameter compensation content of the parameter compensation module, performs real-time iterative replacement on the welding parameters in the welding program, receives the short pipe welding image data in the visual recognition module, pre-processes the image and transmits it to the data conversion and abnormality recognition module, which comprises the following steps:

[0020] The parameter optimization content sent by the parameter compensation module is received through the communication interface, including the welding parameter name to be adjusted and the adjusted parameter value, the welding parameter to be adjusted is found in the data structure of the welding program, and the parameter value is replaced with the parameter value provided by the parameter compensation module; ​The short tube welding image data in the visual recognition module is preprocessed, including grayscale processing and denoising processing.

[0021] It should be noted that the grayscale processing of the short tube welding image can reduce the color information in the image, facilitating subsequent line conversion of the image, and the formula is: ; In the above formula, is the gray value, represents the red color in the original image, represents the green color in the original image, represents the blue color in the original image, and the denoising processing of the received short tube welding image data can further improve the quality and clarity of the image. The denoising method is mean filtering. For each pixel point in the short tube welding image, the average value of all pixel points in its neighborhood is taken as the new value of the pixel point.

[0022] In this embodiment, the data conversion and abnormality recognition module processes the line conversion of the short tube welding image data obtained in different welding stages of the welding process, recognizes the short tube welding abnormality based on the processed short tube image data after welding, obtains short tube abnormality data, analyzes the abnormality reason in combination with the image line data of different welding stages, and transmits the data to the parameter compensation module, including the following steps: For the short tube welding image data obtained in different welding stages of the welding process, edge points in the short tube welding image data are detected by an edge detection algorithm, the edge points are converted into continuous lines, and features are extracted from the processed short tube image line data after welding, including weld width, weld length, weld continuity, and weld edge roughness, including the following steps: Using the edge detection algorithm, the edge points in the short tube welding image data obtained in different welding stages of the welding process are recognized, including the following steps: The Sobel operator is used to calculate the gradients and of the image in the and directions, respectively, the edge blur is eliminated by non-maximum suppression, and the strong edge points are identified by double-threshold detection, and the algorithm formula is: ; ; Wherein, represents the short tube welding image in different welding stages preprocessed by the central control module, represents the convolution operation, and the gradient amplitude and gradient direction are further calculated, wherein the gradient amplitude , and the gradient direction ; It should be noted that non-maximum suppression is applied to the gradient magnitude in the gradient direction, retaining only local maxima and eliminating edge blurring. Specifically, the gradient magnitude of each pixel is compared with the gradient magnitudes of its two adjacent pixels in the gradient direction. If the gradient magnitude of the pixel is not the largest, it is set to 0. By using an edge detection algorithm, edge points in the obtained image are identified. By judging strong edge points, it is easier to perform line processing on the edge points in the subsequent process, which reduces the amount of computation and improves the response speed in the actual short pipe intelligent welding process. Identifying strong edge points through dual-threshold detection involves steps based on thresholds. and For gradient magnitude When a comparison is performed, > This represents the current strong edge point, when < This indicates that the current pixel is a non-edge point. ≤ ≤ When a pixel is connected to a strong edge point, it is determined to be a strong edge point; when a pixel is connected to a non-edge point, it is determined to be a non-edge point. The Hough transform is used to detect straight lines in an image, connecting edge points into continuous lines, including: By analyzing each strong edge point in the image According to discretization Value range calculation obtained Value, of which Further traverse the accumulator array Find points that are greater than a preset threshold; these are the parameters of the detected line. For each line that meets the condition... By working backwards, we can obtain the representation of a straight line in the Cartesian coordinate system; It should be noted that, It is the perpendicular distance from the origin to the line. This is the angle between the perpendicular line and the positive x-axis, expressed in radians or degrees, typically ranging from 0 to π. The preset threshold needs to be manually adjusted based on image complexity and noise levels, such as to determine whether true straight lines are missed or false noise is detected. The parameters of the detected straight line in polar coordinates; For each straight line detected by the Hough transform, determine the two endpoints. and Calculate the angle of each straight line. For two straight lines and Calculate the angle difference At the same time, the minimum end point distance is calculated ; It should be noted that the minimum end point distance is the minimum value of the distance of the two end points of the straight line to and the distance of the two end points of the straight line to , which indicates that the two straight lines almost touch or overlap by measuring the closeness of the two straight lines in space, and determines whether the two straight lines are the same straight line, and by merging the straight lines determined to pass through, the accuracy in the actual use of the system is improved.

[0023] Based on the distance threshold and the angle difference threshold, when and satisfy the distance threshold and the angle difference threshold respectively, the straight lines and are merged into a new straight line.

[0024] It should be noted that the distance threshold and the angle difference threshold need to be set based on a batch of short tube welding images subjected to Hough transformation to obtain a large number of straight lines, calculate the distance and angle difference between each pair of straight lines, and set the threshold according to the mean and standard deviation combined with experience. A batch of representative short tube welding images are detected by Hough transformation to obtain a large number of straight line segments as original data, and the and between all possible pairs of straight lines are calculated, so as to obtain the distance distribution and the angle difference distribution, and the threshold is obtained by calculating the mean and standard deviation combined with the 3sigma principle; Features are extracted from the processed short tube image after welding, including weld width, weld length, weld continuity, and weld edge roughness, including the following steps: Based on the lines obtained by Hough transformation, the boundary lines of the weld are determined, the distance between the two boundary lines in the direction perpendicular to the weld is calculated, and the average value is taken as the final weld width after multiple calculations at different positions of the weld; Based on the lines obtained by Hough transformation, the total distance between all pixel points on the weld line is calculated, and the Euclidean distance between adjacent pixel points is accumulated to obtain the weld length; Based on the lines obtained by Hough transformation, the number of lines is counted as an index of weld continuity, and when the number of lines exceeds a certain threshold, it represents that the current weld has poor weld continuity; It should be noted that the more the number of lines, the more the breakpoints of the weld, and the threshold needs to be set based on the index parameters of the current welding combined with experience; For example, the vertical distance between the boundary lines is measured at the middle, left end and right end of the weld, respectively, to obtain A1, A2 and A3 as 12.5px, 11.8px and 13.2px, respectively, and the average weld width is (12.5px+11.8px+13.2px) / 3=12.5px, combined with the calibration scale 1px=0.1mm, the current average weld width is calculated to be 1.25mm, which is within the normal range of 1-1.5mm, representing that the current weld is normal. The response speed in actual use can be improved by calculating the simplified line, so as to achieve the effect of timely response and rapid judgment.

[0025] The distance variance of each pixel point on the edge line and the pixel points in its neighborhood is calculated as the weld edge roughness. The greater the variance, the rougher the weld edge.

[0026] It should be noted that the specific calculation method of the weld edge roughness is that for each pixel point on the edge line, the pixel points in its neighborhood are taken, and the distance of these pixel points to the point is calculated, so as to calculate the distance variance.

[0027] Based on the features in the image line data of the short tube after welding, the welding abnormalities are identified, the image line data of different welding stages are associated, the space-time relationship of the line data is established, and the abnormal reasons are analyzed, including the following steps: Based on the standard or experience of normal welding, the threshold of the normal range is set for each feature, including the weld width, the weld length, the weld continuity and the weld edge roughness, and the features not within the threshold range are marked as abnormal features; The image and the corresponding line data of each welding stage are added with a time mark to record the sequence in the welding process, the line data of adjacent welding stages are associated according to the time sequence, the end point position and the angle difference of the weld line of adjacent stages are compared to determine whether they belong to different stages of the same weld, the weld with an end point distance and an angle difference less than the distance threshold and the angle difference threshold is determined as different stages of the same weld, and the welding stages include before welding, during welding and after welding; It should be noted that the values of the distance threshold and the angle difference threshold are consistent with those when determining whether it is the same straight line.

[0028] According to the feature combination and space-time change of the welding abnormality, the welding abnormality reason is output according to the preset rule.

[0029] It should be noted that by using data mining algorithms, including decision trees, association rule mining, etc., a large amount of welding data is analyzed to find the potential relationship between abnormal features and abnormal causes, and preset rules are established, including "if the same weld seam suddenly narrows in different stages of weld seam width and the weld seam edge roughness increases, it is caused by too small welding current", "if the same weld seam is poor in different stages of weld seam continuity and the weld seam length is insufficient, it is caused by too fast welding speed or welding interruption", etc. The final abnormal cause is output based on the abnormal data of different stages of the current weld seam.

[0030] The parameter compensation module, based on the short pipe abnormal data obtained by the data transformation and abnormality identification module, identifies the parameters to be adjusted based on the abnormal causes, adjusts the parameters to be adjusted based on the historical data large model, and outputs the final parameter compensation result based on the short pipe image data after parameter adjustment, including the following steps: Obtain short pipe abnormal data from the data transformation and abnormality identification module, including abnormal values of weld width, weld length, weld continuity, weld edge roughness, and corresponding welding stages and related process parameters, wherein the related process parameters are process parameter values of the recorded welding program in different welding stages; Collect historical welding data to establish a parameter adjustment large model, combine welding process parameters related to different abnormal causes, generate parameter adjustment values, and perform targeted parameter compensation on the current welding program, including the following steps: Collect a large amount of historical welding data, including short pipe image data, corresponding process parameters and welding quality evaluation results of normal and different abnormal cause welding conditions, extract features related to welding quality and process parameters from historical data, and train the parameter adjustment large model through neural network.

[0031] Take process parameters as input and welding quality features as output, train the model to learn the mapping relationship between process parameters and welding quality, set the initial adjustment range for the parameter to be adjusted based on the mean and standard deviation of the parameter adjustment historical data under different abnormal causes based on the 3σ principle, input the current parameter to be adjusted into the trained parameter adjustment large model, predict the welding quality feature value that may be obtained after adjustment, calculate the deviation of the predicted welding quality feature value from the normal range, including the following steps: According to the lower limit of the normal range and the predicted value , the deviation is calculated: When < , ; When > When ; When ≤ ≤ When ; Based on the gradient descent method, combined with the bias Adjust the parameters , when > 0 and the bias is positive, then , when the bias is negative, then , wherein represents the learning rate, represents the bias The gradient of , repeat the above adjustment steps until the predicted welding quality feature value enters the normal range, or the maximum number of iterations is reached.

[0032] It should be noted that if the new welding quality feature meets the normal range requirement, the final adjusted parameter is output as the final parameter compensation result, if it does not meet the requirement, the initial adjustment range or learning rate may need to be adjusted again, and the parameter adjustment iteration is performed again until a satisfactory result is obtained.

[0033] Based on the abnormality transmitted by the data transformation and abnormality identification module, the parameter adjustment large model is output, and the welding quality feature value enters the central control module, and the welding program is adjusted and fed back to the motion control module.

[0034] The short pipe intelligent group welding robot multi-process integrated control system, in use, through the line transformation of the recognition image of the short pipe butt welding in the welding robot working process, the current welding robot welding process is quickly identified, and the abnormality reason is analyzed based on different welding stages, so as to adjust the abnormal parameters, and the purpose of real-time adjustment of the welding of the welding robot is achieved, and the quality of the short pipe group welding is improved.

[0035] Through the closed loop system of the parameter compensation module, the central control module and the data transformation and abnormality identification module, the welding abnormality is quickly identified, the parameters are quickly determined, and the parameters are adjusted and compensated, through the real-time feedback and adjustment mechanism, the deviation in the welding process can be corrected in time, the further expansion of defects is avoided, the welding product quality of the welding robot is ensured to meet the standard requirements at all times, and the practicality is enhanced.

[0036] In the embodiments of the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other manners. For example, the embodiments of the apparatus described above are merely schematic. For example, the division of the modules is merely a logical function division. There can be another division manner for the actual implementation. For example, a plurality of modules or components can be combined or integrated into another system, or some necessary modules or components can be omitted, or some technical characteristics can not be adopted to implement the present application. In addition, the implied division of the modules in the embodiments is merely one logical function division. There can be another division manner for the actual implementation. For example, a plurality of modules or components can be combined or integrated into another system, or some necessary modules or components can be omitted, or some technical characteristics can not be adopted to implement the present application. In addition, the modules or components illustrated as separate components can or can not be physical separate components. The components illustrated as modules can be or can not be physical units. That is, they can be located in one position or distributed to a plurality of network units. Part or all of the modules or components can be selected according to the actual needs to implement the purposes of the embodiments of the present application.

[0037] The above embodiments are merely used for describing the technical solutions of the present application but not for limiting the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application.

Claims

1. A multi-process integrated control system for a short tube intelligent group welding robot, characterized in that: The visual recognition module, the motion control module, the parameter compensation module, the central control module, the data conversion and abnormality identification module; The visual recognition module is used for collecting short pipe welding image data in different stages of the welding process of the welding robot through an industrial camera, including short pipe images before, during and after welding, and transmitting the collected data into the central control module; The motion control module includes a motion controller, a motor driver and an execution motor, which controls the action of the welding robot by receiving control instructions from the central control module; The central control module transmits control instructions into the motion control module based on the input welding program, receives parameter compensation content from the parameter compensation module, iteratively replaces welding parameters in the welding program in real time, receives short pipe welding image data from the visual recognition module, pre-processes the image and transmits it to the data conversion and abnormality identification module; The data conversion and abnormality identification module processes the image line conversion for short pipe welding image data obtained in different welding stages of the welding process, identifies short pipe welding abnormalities based on the processed short pipe image data after welding, analyzes the causes of the abnormalities in combination with image line data in different welding stages, and transmits the data to the parameter compensation module; The parameter compensation module identifies the parameters to be adjusted based on the short pipe abnormality data obtained from the data conversion and abnormality identification module, adjusts the parameters to be adjusted based on the historical data model, and outputs the final parameter compensation result according to the short pipe image data after parameter adjustment.

2. The multi-process integrated control system of a short-pipe intelligent gang-welding robot according to claim 1, characterized in that: The data conversion and abnormality identification module processes the image line conversion for short pipe welding image data obtained in different welding stages of the welding process, identifies short pipe welding abnormalities based on the processed short pipe image data after welding, analyzes the causes of the abnormalities in combination with image line data in different welding stages, and transmits the data to the parameter compensation module, including the following steps: For short pipe welding image data obtained in different welding stages of the welding process, edge detection algorithm is used to detect edge points in the short pipe welding image data, convert the edge points into continuous lines, and extract features from the processed short pipe image line data after welding, including weld width, weld length, weld continuity and weld edge roughness; Based on the features in the short pipe image line data after welding, the welding abnormalities are identified, the image line data in different welding stages are associated, the time and space relationship of the line data is established, and the causes of the abnormalities are analyzed.

3. The multi-process integrated control system of a short-pipe intelligent gang-welding robot according to claim 2, characterized in that: For short pipe welding image data obtained in different welding stages of the welding process, edge detection algorithm is used to detect edge points in the short pipe welding image data, convert the edge points into continuous lines, and extract features from the processed short pipe image line data after welding, including weld width, weld length, weld continuity and weld edge roughness, including the following steps: Use edge detection algorithm to detect and identify edge points in short pipe welding image data obtained in different welding stages of the welding process, including the following steps: The Sobel operator is used to calculate the image at... and gradient in direction and The algorithm eliminates edge blurring through nonmaximum suppression and identifies strong edge points through dual threshold detection. The algorithm formula is as follows: ； ； wherein, representing the short pipe welding image of different welding stages after preprocessing by the central control module, representing a convolution operation, further calculating a gradient magnitude and a gradient direction, wherein the gradient magnitude , the gradient direction ; By double threshold detection to identify strong edge points, the steps include based on threshold With , the gradient amplitude Comparison, when > Then represents the current strong edge point, when < Then the current pixel point is a non-edge point, when ≤ ≤ If the pixel point is connected with the strong edge point, it is determined as a strong edge point, if the pixel point is connected with the non-edge point, it is determined as a non-edge point; The straight lines in the image are detected using the Hough transform, and the edge points are connected into continuous lines, including: By analyzing each strong edge point in the image According to discretization Value range calculation obtained Value, of which Further traverse the accumulator array Find points that are greater than a preset threshold; these are the parameters of the detected line. For each line that meets the condition... By working backwards, we can obtain the representation of a straight line in the Cartesian coordinate system; For each line detected by the Hough transform, determine two end points and Calculate the angle of each line For two lines and Calculate the angle difference while calculating the minimum distance between the end points ; Based on the distance threshold and the angle difference threshold, when and simultaneously satisfy respectively less than the distance threshold and the angle difference threshold, then the straight lines and are merged into a new straight line.

4. The multi-process integrated control system of a short-pipe intelligent gang-welding robot according to claim 3, characterized in that: The features extracted from the processed post-welding short tube image line data include weld width, weld length, weld continuity, and weld edge roughness, including the following steps: Based on the lines obtained by the Hough transform, the boundary lines of the weld are determined, the distance between the two boundary lines in the direction perpendicular to the weld is calculated, and the average value is taken as the final weld width after multiple calculations at different positions of the weld; Based on the lines obtained by the Hough transform, along the weld line, the total distance between all pixel points on the line is calculated, and the Euclidean distance between adjacent pixel points is accumulated to obtain the weld length; Based on the lines obtained by the Hough transform, the number of lines is counted as the weld continuity index, and when the number of lines exceeds the set threshold, it represents that the current welding weld continuity is poor; The edge roughness is calculated by calculating the distance variance of each pixel point on the edge line and the pixel points in its neighborhood, and the larger the variance, the rougher the weld edge.

5. The multi-process integrated control system of a short-pipe intelligent gang-welding robot according to claim 3, characterized in that: Based on the features in the post-welding short tube image line data, the welding abnormalities are identified, the image line data of different welding stages are associated, the space-time relationship of the line data is established, and the abnormal reasons are analyzed, including the following steps: Based on the standard or experience of normal welding, set the threshold value of the normal range for each feature, including weld width, weld length, weld continuity, and weld edge roughness, and mark the features that are not within the threshold value as abnormal features; Each image and corresponding line data of each welding stage is labeled with a time label to record its sequence in the welding process, and the line data of adjacent welding stages are associated according to the time sequence, and the endpoint position and angle difference of the weld line of adjacent stages are compared to determine whether they belong to different stages of the same weld, and the weld with an endpoint distance and angle difference less than the distance threshold and angle difference threshold is determined as different stages of the same weld, including pre-welding, welding, and post-welding; According to the feature combination and space-time change of the welding abnormality, the welding abnormality reason is output according to the preset rule.

6. The multi-process integrated control system of a short-pipe intelligent gang-welding robot according to claim 3, characterized in that: Based on the short tube abnormal data obtained by the data transformation and abnormality identification module, the abnormal reason identification parameter is adjusted, the historical data large model is used to adjust the parameter, and the final parameter compensation result is output according to the parameter adjusted short tube image data, including the following steps: Obtain the short tube abnormal data from the data transformation and abnormality identification module, including the abnormal values of weld width, weld length, weld continuity, and weld edge roughness, as well as the corresponding welding stage and related process parameters, wherein the related process parameters are the process parameter values of the recorded welding program in different welding stages; Collect historical welding data to establish a parameter adjustment large model, combine the welding process parameters involved in different abnormal reasons, generate parameter adjustment values, and perform targeted parameter compensation on the current welding program.

7. The multi-process integrated control system of a short-pipe smart gang welder robot according to claim 6, wherein: The parameter adjustment large model is established by collecting historical welding data, and parameter adjustment values are generated in combination with welding process parameters related to different abnormal reasons, so as to make targeted parameter compensation for the current welding program, including the following steps: A large amount of historical welding data is collected, including short pipe image data, corresponding process parameters and welding quality evaluation results of normal and different abnormal reasons, features related to welding quality and process parameters are extracted from the historical data, and a parameter adjustment large model is trained through a neural network; Taking process parameters as input and welding quality features as output, the trained model learns the mapping relationship between process parameters and welding quality, sets an initial adjustment range for the to-be-adjusted parameters based on the mean and standard deviation of the parameter adjustment historical data under different abnormal reasons and the 3σ principle, inputs the current to-be-adjusted parameter value into the trained parameter adjustment large model, predicts the welding quality feature value that may be obtained after adjustment, and calculates the deviation of the predicted welding quality feature value from the normal range, including the following steps: obtained from the lower limit of the normal range , the upper limit , and the predicted value , the deviation is calculated When < Time, ; When > Time, ; When ≤ ≤ , ; based on the gradient descent method, combined with the bias to the previous to-be-adjusted parameter is adjusted, when > 0 and the bias is positive, then , when the bias is negative, then , wherein represents the learning rate, represents the bias about the gradient of the predicted welding quality characteristic value, the above adjustment steps are repeated until the predicted welding quality characteristic value enters the normal range or the maximum number of iterations is reached; Based on the data conversion and abnormality identification module, the welding quality feature value is output through the parameter adjustment large model and entered into the central control module, the welding program is adjusted in parameters and fed back to the motion control module.

8. The multi-process integrated control system of a short-pipe smart gang welder robot according to claim 7, wherein: The central control module transmits control instructions into the motion control module based on the input welding program, receives parameter compensation content from the parameter compensation module, and iteratively replaces welding parameters in the welding program in real time, receives short pipe welding image data from the visual recognition module, and pre-processes the image and transmits it to the data conversion and abnormality identification module, including the following steps: The parameter optimization content sent by the parameter compensation module is received through the communication interface, including the welding parameter name to be adjusted and the adjusted parameter value, the welding parameter to be adjusted is searched in the data structure of the welding program, and the parameter value is replaced with the parameter value provided by the parameter compensation module; The short pipe welding image data in the visual recognition module is received for preprocessing, including grayscale processing and denoising.

Images