Pipeline welding method and equipment based on digital skills, medium and robot

Abstract

The invention discloses a pipeline welding method and device based on digital skills, a medium and a robot, and relates to the technical field of pipeline welding.The method comprises the steps that target molten pool morphology feature data of an area where a to-be-welded pipeline is located and target weld joint morphology feature data of the to-be-welded pipeline are obtained; according to the target molten pool morphology feature data and the target welding seam morphology feature data, target digital skill parameters corresponding to the actual parameters are determined in a preset corresponding relation between the actual parameters and the digital skill parameters; and the to-be-welded pipeline is welded according to the target welding voltage, the target welding circuit and the target welding gun posture data. According to the method, the skill of a welding skilled worker is digitalized, that is, the corresponding relation between the preset actual parameters and the digitalized skill parameters is determined, it is guaranteed that the welding robot can conduct welding according to the optimal welding parameters under different welding conditions, and the requirement for future all-position automatic welding is met.

Description

Background Art

[0002] In the process equipment pipeline projects of the petrochemical industry, it is difficult to form a flow operation during construction because the pipelines have many specifications, complex and diverse materials, many pipe fittings, and unstable geometric dimensions and quality. At present, automatic welding of process pipelines is mostly used in factory prefabrication production lines, and a small amount of individual engineering projects are used for on-site prefabrication and installation of large-diameter thick-walled pipelines. The overall application rate is low. In the process of full-position welding of oil pipelines, skilled welders also need to accumulate rich skills from long-term practice and experience, thereby improving welding quality and efficiency, and at the same time being able to flexibly adapt to different welding environments and welding requirements. However, in recent years, there has been a shortage of excellent welder resources, a limited number of skilled workers, and reliance on manual welding processes will increase production costs and the risk of human errors. Therefore, technological innovation in fully automatic welding of process pipelines is imminent.

[0003] At present, there are still a lot of gaps in the research on the digitization of welding skills, and most of the research focuses on the control of welding systems, welding methods or weld quality. For example, the patent entitled System and Method for Posture Control of Welding Systems, published on May 24, 2017 and with publication number CN106715025A, describes a motion detection system having a detection circuit, a motion recognition circuit and a communication circuit. The detection circuit is configured to detect the posture or movement of the welding system operator. In some embodiments, the detection circuit is configured to detect the posture or movement of the welding operator via an auxiliary device, wherein the auxiliary device communicates wirelessly with the motion detection system. The motion recognition circuit receives the detected posture or movement and converts the detected posture or movement into a welding command. The welding command is transmitted to the welding system via the communication circuit and is configured to adjust the operating parameters of the welding system. However, the motion detection system proposed in this patent essentially controls welding by detecting the posture or movement of the operator, and has little reference value for how to digitize the welding skills of welders.

[0004] The invention patent entitled "A method for fully automatic welding of crude oil insulation pipes" published on December 2, 2022 with publication number CN115415644A records a method for fully automatic welding of crude oil insulation pipes, including the following steps: construction preparation, groove processing, demagnetization, track installation, dehumidification and preheating, pipe mouth assembly, root welding, hot welding, filling welding, cover welding, and rain protection. The welding method proposed in this method is a step for fully automatic welding of pipelines, and it cannot be used as a reference in the digitalization of welding techniques.

[0005] The invention patent entitled "A weld quality detection method based on Transformer neural network" and published on March 29, 2022 with publication number CN114255220A records a weld quality detection method based on Transformer neural network, including the following steps: S1. Install a high-speed molten pool monitoring camera near the welding gun end of the welding manipulator to obtain welding image data in real time and monitor the status of the arc, molten pool, groove, etc.; S2. In addition to implementing basic data enhancement on the acquired data, a multiple image overlapping enhancement method is also used to improve the detection efficiency of small targets such as welds; S3. Construct a visual Transformer neural network weld recognition model based on self-attention; S4. Use a multi-modal related attention method to visualize the changes in the training process of this model and adjust the model structure; S5. Use the trained model to detect the weld quality. In order to avoid problems such as biased welding, porosity, insufficient penetration, etc. caused by environmental or human factors, such as high temperature, dust, strong light radiation, hand shaking, and human accuracy misjudgment, a neural network is used to construct a weld recognition model to monitor the quality of the weld. This model is used for quality inspection after welding, rather than starting from the first weld to improve the quality of the weld and avoid mistakes. The efficiency improvement in welding quality is limited. Summary of the invention

[0006] The technical problem to be solved by the present invention is to address the deficiencies of the prior art, and specifically provide a pipeline welding method, equipment, medium and robot based on digital techniques, as follows:

[0007] 1) In the first aspect, the present invention provides a pipeline welding method based on digital technology, and the specific technical scheme is as follows:

[0008] Obtaining target molten pool morphology feature data of the area where the pipeline to be welded is located and target weld morphology feature data of the pipeline to be welded;

[0009] According to the target molten pool morphology feature data and the target weld morphology feature data, in the preset correspondence relationship between actual parameters and digital skill parameters, the target digital skill parameters corresponding to the actual parameters are determined, the actual parameters include: the target molten pool morphology feature data and the target weld morphology feature data, and the target digital skill parameters include: target welding voltage, target welding current and target welding gun posture data;

[0010] The pipe to be welded is welded according to the target welding voltage, the target welding circuit and the target welding gun posture data.

[0011] The beneficial effects of a pipeline welding method based on digital technology provided by the present invention are as follows:

[0012] By digitizing the skills of skilled welding workers, that is, determining the correspondence between the preset actual parameters and the digitized skill parameters, it is ensured that the welding robot can weld according to the optimal welding parameters under different welding conditions to meet the needs of future full-position automatic welding.

[0013] Based on the above solution, the present invention can also be improved as follows.

[0014] Furthermore, the process of establishing the correspondence between the preset actual parameters and the digitalization skill parameters includes:

[0015] Collect welding voltage data, welding current data, welding gun posture data, molten pool topography data and weld seam topography data of welding power source;

[0016] Establishing a welding skill data set according to the welding voltage data, the welding current data, the welding gun posture data, the molten pool topography feature data and the weld seam topography feature data;

[0017] A welding skill model is trained according to the welding skill data set, and the trained welding skill model is used as the correspondence between the preset actual parameters and the digital skill parameters.

[0018] Furthermore, the welding gun posture data includes: the angle between the welding gun and the normal line at the end point of the welding gun, the welding gun movement direction data and the acceleration data of the welding gun movement obtained by the motion capture unit and the posture sensor.

[0019] Furthermore, the molten pool topographic feature data includes: molten pool area, tail drag angle and arc intensity collected by a monitoring camera.

[0020] Further, the process of obtaining the angle between the welding gun and the normal line at the end point of the welding gun, the welding gun movement direction data and the acceleration data of the welding gun movement through the motion capture unit and the posture sensor is specifically as follows:

[0021] Identify at least one reflective identification point set on the welding gun through a motion capture unit, record the position data of each reflective identification point in real time, integrate all the position data corresponding to each reflective identification point, obtain the motion path corresponding to each reflective identification point, and determine the moving direction data of the welding gun and the acceleration data of the welding gun according to the motion path;

[0022] The angle between the welding gun and the normal line at the end point of the welding gun is determined by the posture sensor.

[0023] Furthermore, the welding voltage data and the welding current data are acquired through a high-speed acquisition device, and the high-speed acquisition device includes a voltage sensor and a current sensor.

[0024] Furthermore, it also includes:

[0025] The position information of the motion capture unit, the posture sensor, the high-speed acquisition device and the monitoring camera is determined, and clock synchronization processing is performed on the motion capture unit, the posture sensor, the high-speed acquisition device and the monitoring camera.

[0026] 2) In a second aspect, the present invention further provides an electronic device, comprising a processor, wherein the processor is coupled to a memory, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor so that the electronic device implements any of the above methods.

[0027] 3) In a third aspect, the present invention further provides a computer-readable storage medium, wherein at least one computer program is stored in the computer-readable storage medium, and the at least one computer program is loaded and executed by a processor to enable a computer to implement any of the above methods.

[0028] 4) In a fourth aspect, the present invention also provides a pipeline robot for executing any of the above methods.

[0029] It should be noted that the beneficial effects achieved by the technical solutions of the second to fourth aspects of the present invention and the corresponding possible implementation methods can be found in the above-mentioned technical effects of the first aspect and its corresponding possible implementation methods, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0031] Figure 1 A schematic diagram of a pipeline welding method based on digital technology according to an embodiment of the present invention;

[0032] Figure 2 The present invention is a structural framework diagram of an electronic device. DETAILED DESCRIPTION

[0033] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0034] like Figure 1 As shown, a pipeline welding method based on digital technology according to an embodiment of the present invention comprises the following steps:

[0035] S1, obtaining target molten pool morphology feature data of the area where the pipeline to be welded is located and target weld morphology feature data of the pipeline to be welded;

[0036] S2, according to the target molten pool morphology feature data and the target weld morphology feature data, in the preset correspondence relationship between actual parameters and digital skill parameters, determining the target digital skill parameters corresponding to the actual parameters, the actual parameters including: the target molten pool morphology feature data and the target weld morphology feature data, the target digital skill parameters including: target welding voltage, target welding current and target welding gun posture data;

[0037] S3, welding the pipe to be welded according to the target welding voltage, the target welding circuit and the target welding gun posture data.

[0038] The beneficial effects of a pipeline welding method based on digital technology provided by the present invention are as follows:

[0039] By digitizing the skills of skilled welding workers, that is, determining the correspondence between the preset actual parameters and the digitized skill parameters, it is ensured that the welding robot can weld according to the optimal welding parameters under different welding conditions to meet the needs of future full-position automatic welding.

[0040] S1, obtaining target molten pool morphology feature data of the area where the pipeline to be welded is located and target weld morphology feature data of the pipeline to be welded; wherein:

[0041] The pipe to be welded refers to any damaged pipe that can be repaired to achieve the purpose of continued use.

[0042] The area where the pipe to be welded is located refers to a circular area with the welding point (the location of the welding point to be welded) as the center and a preset length as the radius.

[0043] The target molten pool morphology characteristic data refers to: molten pool area, tail angle and arc intensity.

[0044] The molten pool refers to the part of the base material that is melted into a pool due to the heat of the welding arc, and the liquid metal part with a certain geometric shape formed on the weldment during fusion welding.

[0045] The molten pool area refers to the surface area of ​​the molten pool.

[0046] The tail drag angle refers to the angle formed by the farthest point corresponding to the tail of the molten pool image and the maximum width of the molten pool after image processing.

[0047] Arc intensity refers to the ultraviolet radiation intensity of each wavelength of the collected electric welding arc.

[0048] The target weld morphology characteristic data include: welding area type, welding area, and welding material.

[0049] S2, according to the target molten pool morphology feature data and the target weld morphology feature data, in the preset correspondence relationship between actual parameters and digital skill parameters, determining the target digital skill parameters corresponding to the actual parameters, the actual parameters including: the target molten pool morphology feature data and the target weld morphology feature data, the target digital skill parameters including: target welding voltage, target welding current and target welding gun posture data;

[0050] The correspondence between the preset actual parameters and the digitalization skill parameters is established in the following way:

[0051] S21, collecting welding voltage data, welding current data, welding gun posture data, molten pool morphology feature data and weld seam morphology feature data of the welding power source;

[0052] Among them, the posture sensor and motion capture unit are used to collect the welding gun posture data and motion path;

[0053] The welding gun posture data includes: the angle between the welding gun and the normal line at the end point of the welding gun.

[0054] An inertial sensor (posture sensor) is used to obtain welding gun posture data and welding acceleration data of the welding gun. The inertial sensor can be set on the welding gun, and the sampling frequency of the inertial sensor can be 400 to 3000 frames.

[0055] The motion capture unit obtains the position of the reflective marking point by identifying the reflective marking point, and obtains the welding motion path by collecting the left and right positions of all the reflective marking points in the entire welding process and arranging them in time sequence. The reflective marking point identification can be set on the arm or welding gun. The sampling frequency of the motion capture unit is 20 to 60 frames.

[0056] Use high-speed acquisition equipment (current sensor and voltage sensor) to collect welding voltage data and welding current data of the welding power supply.

[0057] Use a molten pool monitoring camera to record the molten pool morphology characteristic data and weld morphology characteristic data.

[0058] It should be further explained that the monitoring camera can only collect images or videos, and the collected image or video data needs to be analyzed and processed through a preset processing model to obtain the molten pool morphology feature data and the weld morphology feature data.

[0059] S22. Establish a welding skill data set according to the welding voltage data and welding current data of the welding power source, the welding gun posture data, the molten pool morphology data and the weld morphology feature data, wherein the welding skill data set includes the welding voltage data set, the welding current data set, the welding gun posture data set, the molten pool morphology feature data set and the weld morphology feature data set.

[0060] S23, training the welding skill data set to obtain a welding skill model.

[0061] The welding skill dataset is trained using a Gaussian mixture model.

[0062] The welding skill data set may also include: the position coordinates of the high-speed acquisition device, the posture sensor, the motion capture unit and the molten pool monitoring camera.

[0063] That is, calibration technology is used to confirm the relative position relationship among the high-speed acquisition device, attitude sensor, motion capture unit and molten pool monitoring camera. According to the relative position relationship, the position coordinates of the high-speed acquisition device, attitude sensor and molten pool monitoring camera can be confirmed based on the position coordinates of the motion capture unit. The position coordinates of the motion capture unit can be confirmed based on the initial coordinates obtained during the motion capture unit calibration and the position relationship of the motion capture unit. The initial coordinates can be calibrated by collecting the motion trajectory data of the calibration rod to solve and confirm the position relationship between the cameras.

[0064] In another embodiment of the present solution, the welding skill data set is also preprocessed.

[0065] The preprocessing includes: processing the welding skill data set using sensor clock synchronization technology.

[0066] The sensor clock synchronization technology adopts hard processing technology, and the inertial sensor triggers the motion capture unit to collect 1 frame every 20 to 50 times.

[0067] S3, welding the pipe to be welded according to the target welding voltage, the target welding circuit and the target welding gun posture data.

[0068] The target molten pool morphology feature data and the target weld morphology feature data are obtained through the visual sensing unit, and the target molten pool morphology feature data and the target weld morphology feature data are input into the welding skill model to obtain welding current and voltage data as well as welding gun posture data, and the welding robot is controlled to perform welding according to the current and voltage data as well as welding gun posture data.

[0069] The visual sensing unit may be a surveillance camera.

[0070] Furthermore, the process of establishing the correspondence between the preset actual parameters and the digitalization skill parameters includes:

[0071] Collect welding voltage data, welding current data, welding gun posture data, molten pool topography data and weld seam topography data of welding power source;

[0072] Establishing a welding skill data set according to the welding voltage data, the welding current data, the welding gun posture data, the molten pool topography feature data and the weld seam topography feature data;

[0073] A welding skill model is trained according to the welding skill data set, and the trained welding skill model is used as the correspondence between the preset actual parameters and the digital skill parameters.

[0074] Furthermore, the welding gun posture data includes: the angle between the welding gun and the normal line at the end point of the welding gun, the welding gun movement direction data and the acceleration data of the welding gun movement obtained by the motion capture unit and the posture sensor.

[0075] Furthermore, the molten pool topographic feature data includes: molten pool area, tail drag angle and arc intensity collected by a monitoring camera.

[0076] Further, the process of obtaining the angle between the welding gun and the normal line at the end point of the welding gun, the welding gun movement direction data and the acceleration data of the welding gun movement through the motion capture unit and the posture sensor is specifically as follows:

[0077] Identify at least one reflective identification point set on the welding gun through a motion capture unit, record the position data of each reflective identification point in real time, integrate all the position data corresponding to each reflective identification point, obtain the motion path corresponding to each reflective identification point, and determine the moving direction data of the welding gun and the acceleration data of the welding gun according to the motion path;

[0078] The angle between the welding gun and the normal line at the end point of the welding gun is determined by the posture sensor.

[0079] Furthermore, the welding voltage data and the welding current data are acquired through a high-speed acquisition device, and the high-speed acquisition device includes a voltage sensor and a current sensor.

[0080] Furthermore, it also includes:

[0081] The position information of the motion capture unit, the posture sensor, the high-speed acquisition device and the monitoring camera is determined, and clock synchronization processing is performed on the motion capture unit, the posture sensor, the high-speed acquisition device and the monitoring camera.

[0082] Compared with the prior art, the beneficial effects of the present invention include at least one of the following:

[0083] (1) The present invention can effectively reduce the harm to operators caused by heat sources, arc light, harmful gases, etc. during the welding process, empower high-quality development, and activate the lasting driving force for healthy development.

[0084] (2) The digital technology of the present invention can record and analyze the welding skills of skilled workers, extract them into numerical processes or motion parameters that the robot needs to execute, and use algorithms to process them into models that can be used by welding robots. It can also open up data links between design, process and construction based on the digital model, which can greatly improve management efficiency and quality.

[0085] (3) The present invention studies and analyzes the digital technology of skilled workers' skills, establishes a dynamic self-optimizing process database, automates the welding process, improves welding quality and production efficiency, and at the same time reduces the demand for high-skilled welder resources, greatly saves labor costs, and reduces the labor intensity of welders.

[0086] In the above embodiments, although the steps are numbered S1, S2, etc., these are only specific embodiments given by the present invention. Those skilled in the art may adjust the execution order of S1, S2, etc. according to actual conditions, which is also within the protection scope of the present invention. It can be understood that in some embodiments, some or all of the above embodiments may be included.

[0087] like Figure 2 As shown, an electronic device 300 according to an embodiment of the present invention includes a processor 320, the processor 320 is coupled to a memory 310, and the memory 310 stores at least one computer program 330, and the at least one computer program 330 is loaded and executed by the processor 320, so that the electronic device 300 implements any of the above methods, specifically:

[0088] The electronic device 300 may have relatively large differences due to different configurations or performances, and may include one or more processors 320 (Central Processing Units, CPU) and one or more memories 310, wherein the one or more memories 310 store at least one computer program 330, and the at least one computer program 330 is loaded and executed by the one or more processors 320, so that the electronic device 300 implements a pipeline welding method based on digital skills provided in the above embodiment. Of course, the electronic device 300 may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output, and the electronic device 300 may also include other components for realizing device functions, which will not be repeated here.

[0089] A computer-readable storage medium according to an embodiment of the present invention stores at least one computer program, and the at least one computer program is loaded and executed by a processor so that a computer implements any one of the above methods.

[0090] Optionally, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0091] In an exemplary embodiment, a computer program product or a computer program is also provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device performs any of the above methods.

[0092] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects and represent the definition of a specific order or sequence. The order of use of similar objects can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than the order shown or described.

[0093] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), or it can be a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code.

[0094] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A 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 thereof. More specific examples (a 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 thereof. 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 conjunction with an instruction execution system, device, or device.

[0095] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A pipeline welding method based on digital technology, characterized in that: include: Obtaining target molten pool morphology feature data of the area where the pipeline to be welded is located and target weld morphology feature data of the pipeline to be welded; According to the target molten pool morphology feature data and the target weld morphology feature data, in the preset correspondence relationship between actual parameters and digital skill parameters, the target digital skill parameters corresponding to the actual parameters are determined, the actual parameters include: the target molten pool morphology feature data and the target weld morphology feature data, and the target digital skill parameters include: target welding voltage, target welding current and target welding gun posture data; The pipe to be welded is welded according to the target welding voltage, the target welding circuit and the target welding gun posture data.

2. A pipeline welding method based on digital technology according to claim 1, characterized in that: The process of establishing the correspondence between the preset actual parameters and the digitalization skill parameters includes: Collect welding voltage data, welding current data, welding gun posture data, molten pool topography data and weld seam topography data of welding power source; Establishing a welding skill data set according to the welding voltage data, the welding current data, the welding gun posture data, the molten pool topography feature data and the weld seam topography feature data; A welding skill model is trained according to the welding skill data set, and the trained welding skill model is used as the correspondence between the preset actual parameters and the digital skill parameters.

3. A pipeline welding method based on digital technology according to claim 2, characterized in that: The welding gun posture data includes: the angle between the welding gun and the normal line at the end point of the welding gun, the welding gun movement direction data and the acceleration data of the welding gun movement obtained by the motion capture unit and the posture sensor.

4. A pipeline welding method based on digital technology according to claim 2, characterized in that: The molten pool topographic feature data include: molten pool area, tail drag angle and arc intensity collected by a monitoring camera.

5. A pipeline welding method based on digital skills according to claim 4, characterized in that: The process of obtaining the angle between the welding gun and the normal line at the end point of the welding gun, the welding gun movement direction data and the acceleration data of the welding gun movement through the motion capture unit and the posture sensor is specifically as follows: Identify at least one reflective identification point set on the welding gun through a motion capture unit, record the position data of each reflective identification point in real time, integrate all the position data corresponding to each reflective identification point, obtain the motion path corresponding to each reflective identification point, and determine the moving direction data of the welding gun and the acceleration data of the welding gun according to the motion path; The angle between the welding gun and the normal line at the end point of the welding gun is determined by the posture sensor.

6. A pipeline welding method based on digital skills according to claim 5, characterized in that: The welding voltage data and the welding current data are acquired through a high-speed acquisition device, and the high-speed acquisition device includes a voltage sensor and a current sensor.

7. A pipeline welding method based on digital skills according to claim 6, characterized in that: Also includes: The position information of the motion capture unit, the posture sensor, the high-speed acquisition device and the monitoring camera is determined, and clock synchronization processing is performed on the motion capture unit, the posture sensor, the high-speed acquisition device and the monitoring camera.

8. An electronic device, characterized in that: The electronic device comprises a processor, the processor is coupled to a memory, at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor so that the electronic device implements the method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one computer program, and the at least one computer program is loaded and executed by a processor so that a computer implements the method according to any one of claims 1 to 7.

10. A pipeline robot, characterized in that: Used to perform the method according to any one of claims 1 to 7.

Images