Welding quality detection method, device and equipment based on digital visualization and medium

Abstract

The invention relates to a welding quality detection method, device and equipment based on digital visualization and a medium, and belongs to the field of welding quality detection. The method comprises the steps that a welding visualization platform is built, the content of the welding visualization platform comprises welding base metal visualization, welding process visualization and welding seam visualization, welding process visualization is achieved through trajectory tracking, a visual welding trajectory is obtained, welding seam visualization is achieved through ray detection, and a visual welding seam is obtained; a welding deviation track is obtained based on a welding visualization platform; and the welding ideal track and the welding deviation value of the welding deviation track are obtained, and the welding deviation is regulated and controlled based on the welding deviation value. According to the method, the welding process is visualized, the welding route and the welding defect area are visually obtained, and the deviation of the welding defect area is detected.

Description

Technical Field

[0001] The present invention belongs to the technical field of welding quality detection, and in particular relates to a welding quality detection method, device, equipment and medium based on digital visualization. Background Art

[0002] Welding is an indispensable manufacturing process in many industries, such as construction, aerospace, petrochemicals, etc. The quality of welding is directly related to the safety and service life of the product. Traditional welding defect detection methods mainly rely on manual inspection, which is not only costly, but also the detection efficiency will drop rapidly over time. Modern non-destructive testing technology and machine vision technology, such as X-ray flaw detection, ultrasonic flaw detection and automatic detection systems based on deep learning, can significantly improve detection efficiency and reduce human errors, but there are defects such as unintuitive results and low error control efficiency. Summary of the invention

[0003] In order to solve the above problems existing in the prior art, the present invention provides a welding quality detection method, device, equipment and medium based on digital visualization.

[0004] The purpose of the present invention can be achieved through the following technical solutions: A welding quality detection method based on digital visualization, the implementation of the welding quality detection method comprises the following steps: Build a welding visualization platform, the contents of which include welding base material visualization, welding process visualization and weld visualization, realize the visualization of the welding process and obtain a visible welding trajectory through trajectory tracking, realize the visualization of the weld and obtain a visible weld through radiographic detection; Obtaining a welding deviation trajectory based on the welding visualization platform; The ideal welding trajectory and the welding deviation amount of the welding deviation trajectory are obtained, and the welding deviation is regulated based on the welding deviation amount.

[0005] Preferably, the construction of the welding visualization platform includes: Projecting the welding base material onto a visualization platform by a visualization method so as to realize visualization of the welding base material; In the welding process, the welding trajectory parameter information is obtained by using a perception sensor, the perception sensor includes a posture sensor, a speed sensor, an acceleration sensor, and a weight sensor, the welding trajectory parameter information includes a welding head posture, a welding head speed, a welding head acceleration, and a welding equipment quality, a welding point trajectory model is obtained based on the welding trajectory parameter information, the welding point trajectory model includes a welding point kinematic model and a welding point dynamic model, and the visual welding trajectory is obtained based on the welding point trajectory model; The weld radiographic detection image is acquired through radiographic detection and the visible weld is extracted.

[0006] Preferably, obtaining a welding point trajectory model based on the welding trajectory parameter information comprises: The welding head posture is obtained by the posture sensor, and the welding head posture includes the welding head position coordinates and the welding head posture angle. The welding head posture is transformed with the center of the welding equipment as the reference point to obtain the kinematic model of the welding point. The mathematical description of the kinematic model of the welding point is: , where (X, Y) is the welding head position coordinate, α is the welding head posture angle, and Z is the welding head posture; The welding spot dynamics model is established by Lagrangian method, and the welding spot dynamics model includes welding head inertia matrix, welding head centripetal force term, welding head gravity term and joint torque.

[0007] Preferably, the step of acquiring a weld radiographic detection image by radiographic detection and extracting the visible weld comprises: Scanning the weld seam radiographic detection image line by line to obtain suspicious weld seam points; Processing the weld seam radiographic detection image by using a Canny edge detection algorithm to obtain a weld seam radiographic detection binary image, wherein the weld seam radiographic detection binary image carries a strong edge; Scan the left and right sides of the suspicious weld point respectively until the strong edges are detected respectively, retain the edge pixels connected to the strong edges 8 on the left and right sides to form a closed edge curve, and expand from each suspicious weld point to the surrounding pixel points until the closed edge curve is reached to form the visible weld.

[0008] Preferably, scanning the weld seam radiographic detection image line by line to obtain suspicious weld seam points comprises: The weld radiographic inspection image is divided into N rows, each row includes M pixels, and the first-order derivative of the grayscale distribution curve is obtained, which is expressed as: ,in, is the first-order derivative of the grayscale distribution curve at the m-th pixel in the n-th row, is the gray value of the m+1th pixel, is the gray value of the mth pixel; Get the second-order derivative of the grayscale distribution curve, the expression is ,in, is the second-order derivative of the grayscale distribution curve at the m-th pixel in the n-th row, is the gray value of the m-1th pixel; According to the first-order derivative of the grayscale distribution curve and the second-order derivative of the grayscale distribution curve, the peak point and the trough point are obtained. >0, <0, and | | is less than a preset threshold, the mth pixel point is defined as the peak point. <0, >0, and | |When the value is less than a preset threshold, the mth pixel point is defined as the trough point; Traverse the trough points in the nth row, scan both sides of the trough point to obtain the two nearest peak points, take the highest peak point between the two as the adjacent peak point, calculate the height difference between the trough point and the adjacent peak point to obtain the trough point protrusion, and select the trough point with the largest trough point protrusion in the nth row as the suspicious weld point in the nth row.

[0009] Preferably, obtaining the welding deviation trajectory based on the welding visualization platform includes: Traversing the visible weld and marking the weld defect area, locating the defect endpoints of the weld defect area, the number of the defect endpoints is 2, which are the points farthest from the center of the weld defect area and are respectively located at the two ends of the weld defect area marked by the visible weld; The coordinates of the defect endpoint are obtained, the coordinates of the visible welding trajectory are traversed, and the two pixel points on the visible welding trajectory closest to the defect endpoint are marked as welding trajectory abnormal points. The visible welding trajectory between the welding trajectory abnormal points is the welding deviation trajectory.

[0010] Preferably, the step of obtaining the welding ideal trajectory and the welding deviation amount of the welding deviation trajectory includes: Eliminating the welding deviation trajectory on the visible welding trajectory to obtain a correct welding trajectory, fitting the points on the correct welding trajectory, and bringing the welding deviation trajectory into the correct welding trajectory to obtain the ideal welding trajectory; Obtain the coordinates of the pixel points in the ideal welding trajectory and the coordinates of the pixel points in the welding deviation trajectory, and calculate the welding deviation. The calculation formula is: , where A is the welding deviation, (X a ,Y a ) is the coordinate of the ath pixel point in the ideal welding trajectory, (X' a ,Y' a ) is the coordinate of the ath pixel point in the welding deviation trajectory.

[0011] A welding quality detection device based on digital visualization, used to execute the welding quality detection method described above, comprising a visualization module, a deviation detection module and a deviation control module; The visualization module is used to build a welding visualization platform, the content of which includes welding base material visualization, welding process visualization and weld visualization. The welding process visualization is realized by trajectory tracking and a visible welding trajectory is obtained. The weld visualization is realized by radiographic detection and a visible weld is obtained. The deviation detection module is used to obtain a welding deviation trajectory based on the welding visualization platform; The deviation control module is used to obtain the ideal welding trajectory and the welding deviation amount of the welding deviation trajectory, and control the welding deviation based on the welding deviation amount.

[0012] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the above-mentioned welding quality detection method is implemented when the processor executes the program.

[0013] A storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute the welding quality detection method described above when executed by a computer processor.

[0014] The beneficial effects of the present invention are: (1) By establishing a welding visualization platform, the welding matrix, welding trajectory, weld and welding defect area are intuitively displayed, which is convenient for locating defect positions and performing deviation control; (2) By obtaining the ideal welding trajectory of the welding deviation trajectory position and obtaining the welding deviation amount, this deviation acquisition method is simple and efficient, and the deviation amount can be intuitively displayed on the visualization platform, and whether there is a deviation and the degree of deviation are clear at a glance; (3) The peak and trough points are located by the first-order derivative and second-order derivative of the grayscale distribution curve, which facilitates the removal of false peaks caused by noise and other distortions, making the subsequent selection of suspicious weld points more accurate; (4) The method is simple and fast to find the abnormal point of the welding trajectory on the visible welding trajectory through the defect endpoint. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0016] Figure 1 The present invention is a flowchart of the steps of a welding quality detection method based on digital visualization. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0018] The working principle and use process of the present invention: See also Figure 1 , a welding quality detection method based on digital visualization, comprising: S1: Building a welding visualization platform, wherein the welding visualization platform includes visualization of welding base materials, visualization of welding processes and visualization of welds, wherein the visualization of welding processes is realized through trajectory tracking and a visible welding trajectory is obtained, and the visualization of welds is realized through radiographic detection and a visible weld is obtained; S2: obtaining a welding deviation trajectory based on the welding visualization platform; S3: Obtaining an ideal welding trajectory and a welding deviation amount of the welding deviation trajectory, and regulating the welding deviation based on the welding deviation amount.

[0019] In this embodiment, building a welding visualization platform can be implemented by the following steps: S101: Projecting the welding base material onto a visualization platform by a visualization method to realize visualization of the welding base material, wherein the visualization method includes but is not limited to three-dimensional scanning and modeling; S102: in the welding process, obtaining welding trajectory parameter information through a perception sensor, the perception sensor includes a posture sensor, a speed sensor, an acceleration sensor, and a weight sensor, the welding trajectory parameter information includes welding head posture, welding head speed, welding head acceleration, and welding equipment quality, obtaining a weld point trajectory model based on the welding trajectory parameter information, the weld point trajectory model includes a weld point kinematic model and a weld point dynamic model, and obtaining the visual welding trajectory based on the weld point trajectory model; S103: Acquire a weld radiographic detection image through radiographic detection and extract the visible weld.

[0020] In this embodiment, the welding point trajectory model is obtained based on the welding trajectory parameter information, which can be implemented by the following steps: S102-1: Acquire the welding head posture through the posture sensor, the welding head posture includes the welding head position coordinates and the welding head posture angle, and transform the welding head posture with the center of the welding equipment as the reference point to obtain the kinematic model of the welding point. The mathematical description of the kinematic model of the welding point is: , where (X, Y) is the welding head position coordinate, α is the welding head posture angle, and Z is the welding head posture; S102-2: The weld spot dynamics model is established by the Lagrangian method. The weld spot dynamics model includes the weld head inertia matrix, the weld head centripetal force term, the weld head gravity term and the joint torque. The weld head inertia matrix reflects the inertia characteristics of the weld head and is related to factors such as the mass, moment of inertia of each part of the welding equipment, and the position and posture of the joint. The weld head centripetal force term is related to the weld head speed and includes effects such as the Coriolis force and centripetal force generated by the motion interaction of each part of the welding equipment. The weld head gravity term depends on the mass of each part of the welding equipment and the gravitational acceleration. The joint torque is the driving torque or external torque acting on the joint.

[0021] In this embodiment, obtaining a weld radiographic detection image and extracting the visible weld by radiographic detection can be specifically implemented by the following steps: S103-1: Scanning the weld radiographic detection image line by line to obtain suspicious weld points, where the suspicious weld points are points in the weld radiographic detection image that may constitute a weld; The weld radiographic inspection image is divided into N rows, each row includes M pixels, and the first-order derivative of the grayscale distribution curve is obtained, which is expressed as: ,in, is the first-order derivative of the grayscale distribution curve at the m-th pixel in the n-th row, is the gray value of the m+1th pixel, is the gray value of the mth pixel; Get the second-order derivative of the grayscale distribution curve, the expression is ,in, is the second-order derivative of the grayscale distribution curve at the m-th pixel in the n-th row, is the gray value of the m-1th pixel; According to the first-order derivative of the grayscale distribution curve and the second-order derivative of the grayscale distribution curve, the peak point and the trough point are obtained. >0, <0, and | | is less than a preset threshold, the mth pixel point is defined as the peak point. <0, >0, and | |When the value is less than a preset threshold, the mth pixel point is defined as the trough point; Traversing the trough points in the nth row, scanning the two sides of the trough points to obtain the two nearest crest points, taking the highest crest point of the two as the adjacent crest point, calculating the height difference between the trough point and the adjacent crest point to obtain the trough point protrusion, and selecting the trough point with the largest trough point protrusion in the nth row as the suspected weld point in the nth row; S103-2: Processing the weld radiographic detection image by using a Canny edge detection algorithm to obtain a weld radiographic detection binary image, wherein the weld radiographic detection binary image carries edge information; The weld radiographic detection image is smoothed by Gaussian filtering and the gradient amplitude and gradient angle of the weld radiographic detection image are calculated by a convolution kernel, non-maximum suppression is performed on the gradient amplitude, and edge pixels are divided into strong edges, weak edges and non-edges by a preset double threshold method, and the strong edges are connected to obtain the weld radiographic detection binary image carrying the edge information; S103-3: Scan the left and right sides of the suspicious weld point respectively until the strong edges are detected respectively, retain the edge pixels connected to the strong edges 8 on the left and right sides to form a closed edge curve, and expand from each suspicious weld point to the surrounding pixel points until the closed edge curve is reached to form the visible weld.

[0022] In this embodiment, the welding deviation trajectory is obtained based on the welding visualization platform, which can be implemented by the following steps: S201: traverse the visible weld and mark the weld defect area, locate the defect endpoints of the weld defect area, the number of the defect endpoints is 2, which are the points farthest from the center of the weld defect area and are respectively located at the two ends of the weld defect area marked by the visible weld; S202: Acquire the coordinates of the defect endpoint, traverse the coordinates of the visible welding trajectory, mark the two pixel points on the visible welding trajectory closest to the defect endpoint as welding trajectory abnormal points, and the visible welding trajectory between the welding trajectory abnormal points is the welding deviation trajectory.

[0023] In this embodiment, obtaining the welding ideal trajectory and the welding deviation amount of the welding deviation trajectory can be specifically implemented by the following steps: S301: Eliminate the welding deviation trajectory on the visible welding trajectory to obtain a correct welding trajectory, perform fitting on the points on the correct welding trajectory, and bring the welding deviation trajectory into the correct welding trajectory to obtain the ideal welding trajectory; S302: Obtain the coordinates of the pixel points in the ideal welding trajectory and the coordinates of the pixel points in the welding deviation trajectory, and calculate the welding deviation. The calculation formula is: , where A is the welding deviation, (X a ,Y a ) is the coordinate of the ath pixel point in the ideal welding trajectory, (X' a ,Y' a ) is the coordinate of the ath pixel point in the welding deviation trajectory.

[0024] A welding quality detection device based on digital visualization, comprising a visualization module, a deviation detection module and a deviation control module; The visualization module is used to build a welding visualization platform, the content of which includes welding base material visualization, welding process visualization and weld visualization. The welding process visualization is realized by trajectory tracking and a visible welding trajectory is obtained. The weld visualization is realized by radiographic detection and a visible weld is obtained. The deviation detection module is used to obtain a welding deviation trajectory based on the welding visualization platform; The deviation control module is used to obtain the ideal welding trajectory and the welding deviation amount of the welding deviation trajectory, and control the welding deviation based on the welding deviation amount.

[0025] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0026] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0027] The program code included on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0028] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A welding quality detection method based on digital visualization, characterized in that: The implementation of the welding quality detection method comprises the following steps: Build a welding visualization platform, the contents of which include welding base material visualization, welding process visualization and weld visualization, realize the visualization of the welding process and obtain a visible welding trajectory through trajectory tracking, realize the visualization of the weld and obtain a visible weld through radiographic detection; Obtaining a welding deviation trajectory based on the welding visualization platform; Acquire an ideal welding trajectory and a welding deviation amount of the welding deviation trajectory, and adjust the welding deviation based on the welding deviation amount; The construction of the welding visualization platform includes: Projecting the welding base material onto a visualization platform by a visualization method so as to realize visualization of the welding base material; In the welding process, the welding trajectory parameter information is obtained by using a perception sensor, the perception sensor includes a posture sensor, a speed sensor, an acceleration sensor, and a weight sensor, the welding trajectory parameter information includes a welding head posture, a welding head speed, a welding head acceleration, and a welding equipment quality, a welding point trajectory model is obtained based on the welding trajectory parameter information, the welding point trajectory model includes a welding point kinematic model and a welding point dynamic model, and the visual welding trajectory is obtained based on the welding point trajectory model; Acquire a weld radiographic detection image through radiographic detection and extract the visible weld; The obtaining of the welding deviation trajectory based on the welding visualization platform includes: Traversing the visible weld and marking the weld defect area, locating the defect endpoints of the weld defect area, the number of the defect endpoints is 2, which are the points farthest from the center of the weld defect area and are respectively located at the two ends of the weld defect area marked by the visible weld; Acquire the coordinates of the defect endpoint, traverse the coordinates of the visual welding trajectory, mark the two pixel points on the visual welding trajectory closest to the defect endpoint as welding trajectory abnormal points, and the visual welding trajectory between the welding trajectory abnormal points is the welding deviation trajectory; The step of obtaining the welding ideal trajectory and the welding deviation amount of the welding deviation trajectory comprises: Eliminating the welding deviation trajectory on the visible welding trajectory to obtain a correct welding trajectory, fitting the points on the correct welding trajectory, and bringing the welding deviation trajectory into the correct welding trajectory to obtain the ideal welding trajectory; Obtain the coordinates of the pixel points in the ideal welding trajectory and the coordinates of the pixel points in the welding deviation trajectory, and calculate the welding deviation. The calculation formula is: , where A is the welding deviation, (X a ,Y a ) is the coordinate of the ath pixel point in the ideal welding trajectory, (X' a ,Y' a ) is the coordinate of the ath pixel point in the welding deviation trajectory.

2. The welding quality detection method according to claim 1, characterized in that: The obtaining of the welding point trajectory model based on the welding trajectory parameter information comprises: The welding head posture is obtained by the posture sensor, and the welding head posture includes the welding head position coordinates and the welding head posture angle. The welding head posture is transformed with the center of the welding equipment as the reference point to obtain the kinematic model of the welding point. The mathematical description of the kinematic model of the welding point is: , where (X, Y) is the welding head position coordinate, α is the welding head posture angle, and Z is the welding head posture; The welding spot dynamics model is established by Lagrangian method, and the welding spot dynamics model includes welding head inertia matrix, welding head centripetal force term, welding head gravity term and joint torque.

3. The welding quality detection method according to claim 1, characterized in that: The step of obtaining a weld radiographic detection image by radiographic detection and extracting the visible weld comprises: Scanning the weld seam radiographic detection image line by line to obtain suspicious weld seam points; Processing the weld seam radiographic detection image by using a Canny edge detection algorithm to obtain a weld seam radiographic detection binary image, wherein the weld seam radiographic detection binary image carries a strong edge; Scan the left and right sides of the suspicious weld point respectively until the strong edges are detected respectively, retain the edge pixels connected to the strong edges 8 on the left and right sides to form a closed edge curve, and expand from each suspicious weld point to the surrounding pixel points until the closed edge curve is reached to form the visible weld.

4. The welding quality detection method according to claim 3, characterized in that: Scanning the weld seam radiographic detection image line by line to obtain suspicious weld seam points includes: The weld radiographic inspection image is divided into N rows, each row includes M pixels, and the first-order derivative of the grayscale distribution curve is obtained, which is expressed as: ,in, is the first-order derivative of the grayscale distribution curve at the m-th pixel in the n-th row, is the gray value of the m+1th pixel, is the gray value of the mth pixel; Get the second-order derivative of the grayscale distribution curve, the expression is ,in, is the second-order derivative of the grayscale distribution curve at the m-th pixel in the n-th row, is the gray value of the m-1th pixel; According to the first-order derivative of the grayscale distribution curve and the second-order derivative of the grayscale distribution curve, the peak point and the trough point are obtained. >0, <0, and | | is less than a preset threshold, the mth pixel point is defined as the peak point. <0, >0, and | |When the value is less than a preset threshold, the mth pixel point is defined as the trough point; Traverse the trough points in the nth row, scan both sides of the trough point to obtain the two nearest peak points, take the highest peak point between the two as the adjacent peak point, calculate the height difference between the trough point and the adjacent peak point to obtain the trough point protrusion, and select the trough point with the largest trough point protrusion in the nth row as the suspicious weld point in the nth row.

5. A welding quality detection device based on digital visualization, characterized in that: The device is applied to the welding quality detection method as described in any one of claims 1 to 4, including a visualization module, a deviation detection module and a deviation control module; The visualization module is used to build a welding visualization platform, the content of which includes welding base material visualization, welding process visualization and weld visualization. The welding process visualization is realized by trajectory tracking and a visible welding trajectory is obtained. The weld visualization is realized by radiographic detection and a visible weld is obtained. The deviation detection module is used to obtain a welding deviation trajectory based on the welding visualization platform; The deviation control module is used to obtain the ideal welding trajectory and the welding deviation amount of the welding deviation trajectory, and control the welding deviation based on the welding deviation amount.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the welding quality detection method as described in any one of claims 1-4 is implemented.

7. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the welding quality detection method as described in any one of claims 1 to 4 when executed by a computer processor.

Images