An industrial welding device, method and system for industrial welding data acquisition

Abstract

The present application relates to the technical field of welding process, and discloses an industrial welding device, an industrial welding data acquisition method and system, the device comprising a welding robot, a welding gun is installed, and welding work is performed according to a control instruction; a molten pool detection camera acquires a molten pool image and a timestamp; a laser sensor is installed at a preset position of a mechanical arm of the welding robot, acquires point cloud data and a timestamp; an upper computer transmits a control instruction to the welding robot, acquires a trajectory position and welding current voltage data, and records a timestamp of the trajectory position and welding current voltage data; the welding information and timestamps of the molten pool detection camera, the laser sensor and the welding robot are fused to obtain welding information of the same timeline and visually display the welding information. Through comprehensive recording of key information in the welding process, multi-source data is fused and processed, corresponding to the same timeline and visually displayed, thereby improving the correlation between various data.

Description

Technical Field

[0001] This invention relates to the field of welding technology, specifically to an industrial welding apparatus, a method and system for industrial welding data acquisition. Background Technology

[0002] Welding is a crucial component of modern manufacturing. With the continuous development of metal processing technology, higher demands are being placed on welding quality. Welding data acquisition technology monitors the welding process, acquiring data such as welding parameters, temperature, and pressure to achieve welding control. However, current data acquisition systems are limited to collecting single or a small number of indicators, exhibiting limitations in analyzing and mining multi-indicator data. They cannot further analyze the relationships between complex welding process parameters. Welding data acquisition systems primarily target data such as current, voltage, and molten pool detection. The poor correlation between these data points significantly hinders in-depth analysis of the welding process, reducing efficiency and impacting welding results. Summary of the Invention

[0003] In view of this, the present invention provides a method for industrial welding data acquisition to solve the problem of how to improve the linkage between data acquired in the welding industry in order to improve welding results.

[0004] In a first aspect, the present invention provides an industrial welding device, comprising: a welding robot, a weld pool detection camera, a laser sensor, and a host computer; the welding robot is equipped with a welding torch and is used to control the welding torch to perform welding work according to control instructions transmitted from the host computer; the weld pool detection camera is used to acquire weld pool images when the welding robot performs welding work and record the timestamps of the weld pool images; the laser sensor is installed at a preset position on the robotic arm of the welding robot and is used to acquire point cloud data when the welding robot performs welding work and record the timestamps of the point cloud data; the host computer is used to transmit control instructions to the welding robot and acquire the trajectory position and welding current and voltage data when the welding robot performs welding work, and record the timestamps of the trajectory position and the welding current and voltage data; and to acquire the weld pool images and timestamps recorded by the weld pool detection camera, and the point cloud data and timestamps recorded by the laser sensor; the welding information and corresponding timestamps generated by the weld pool detection camera, the laser sensor, and the welding robot are fused and processed to obtain the trajectory position, current and voltage data, weld pool image data, and point cloud data corresponding to the same timeline and visualized.

[0005] In this embodiment of the invention, a weld pool detection camera, a laser sensor, a welding robot, and a host computer are used to acquire and record various information in real time during the welding process, including weld pool images, point cloud data, trajectory positions, and welding current and voltage data. All data are timestamped. After the timestamps are fused, the trajectory positions, current and voltage data, weld pool image data, and point cloud data corresponding to the same timeline are obtained and visualized. This improves the correlation between various data, thereby helping operators understand the status of the welding process and facilitating subsequent optimization of the welding process to improve the welding effect.

[0006] In one optional implementation, the coordinates of the point cloud data acquired by the laser sensor are in the same coordinate system as the coordinates of the trajectory position generated by the welding robot.

[0007] This invention uses a laser sensor to place point cloud data and the trajectory coordinates of the welding robot in the same coordinate system, providing a data foundation for subsequent analysis of the relationship between point cloud data and robot motion during welding, thereby helping operators to analyze welding process problems more accurately.

[0008] Secondly, the present invention provides a method for industrial welding data acquisition, based on a host computer of the industrial welding device described in the first aspect. The method includes: transmitting control commands to a welding robot to control the welding robot to perform welding work; acquiring welding information and corresponding timestamps generated by a molten pool detection camera, a laser sensor, and the welding robot during the welding work; fusing the welding information and the corresponding timestamps to obtain welding information corresponding to the same timeline and displaying it visually; wherein the welding information includes at least: the trajectory position of the welding robot when performing the welding work, welding current and voltage data, molten pool image, and point cloud data.

[0009] This invention achieves comprehensive recording of various key information during the welding process by acquiring welding information and corresponding timestamps generated by the molten pool detection camera, laser sensor, and welding robot in real time. By fusing and processing multi-source data and aligning them along the same timeline for visualization, the correlation between various data points is improved, and comprehensive and real-time welding data acquisition is achieved. This effectively helps operators understand the status of the welding process, facilitating subsequent optimization of the welding process.

[0010] In one optional implementation, the step of fusing the welding information and its corresponding timestamps to obtain welding information corresponding to the same timeline and then visualizing it includes: performing data noise reduction, filtering, and enhancement on the welding information to obtain preprocessed welding information; correcting the timestamps corresponding to the preprocessed welding information according to the time sequence to obtain corrected timestamps corresponding to the preprocessed welding information; using the corrected timestamps as keywords, executing a preset fusion function based on the keywords to obtain the preprocessed welding information corresponding to the same timeline; and displaying the preprocessed welding information corresponding to the same timeline using a visualization tool.

[0011] This invention improves data quality by performing noise reduction, filtering, and enhancement on welding information. The timestamps corresponding to the preprocessed welding information are corrected according to the time series to ensure the accuracy of the acquisition time of multi-source data, providing a unified time benchmark for subsequent data fusion. The preprocessed welding information corresponding to the same timeline is displayed through visualization tools, which can intuitively and clearly present various data in the welding process.

[0012] In one optional implementation, after the step of fusing the welding information and the corresponding timestamps to obtain welding information corresponding to the same timeline and displaying it visually, the method further includes: calculating arc data based on the welding current and voltage data; obtaining welding transition parameters based on the arc data and a preset welding transition coefficient using a welding transition formula; training a welding process optimization model based on the welding transition parameters; determining welding process parameters based on the welding process optimization model; and generating optimized control instructions based on the welding process parameters using a control algorithm to control the welding robot to perform welding work.

[0013] This invention improves welding quality and efficiency by determining welding parameters based on the arc characteristics during the actual welding process and by determining welding process parameters based on a trained welding process optimization model. Furthermore, it generates optimized control commands based on the welding process parameters using a control algorithm, thereby achieving optimized and precise control of the welding robot and effectively ensuring welding quality.

[0014] In one optional implementation, after the step of fusing the welding information and the corresponding timestamp to obtain welding information corresponding to the same timeline and displaying it visually, the method further includes: extracting droplet features based on the molten pool image; and generating optimized control instructions based on the droplet features and a control algorithm to control the welding robot to perform welding work.

[0015] This invention enables the monitoring of the droplet formation process and the state of the molten pool during welding by extracting droplet features from the molten pool image. Based on the droplet features, optimized control commands are generated using a control algorithm, allowing the welding process to be adaptively and specifically adjusted according to the actual droplet state, preventing welding defects and effectively ensuring welding quality.

[0016] In one optional implementation, after the step of fusing the welding information and the corresponding timestamp to obtain welding information corresponding to the same timeline and displaying it visually, the method further includes: performing welding simulation using simulation tools based on the welding information corresponding to the same timeline.

[0017] In this embodiment of the invention, welding simulation is performed using simulation tools based on welding information corresponding to the same timeline. This effectively verifies different welding schemes and process routes, thereby helping operators select the best welding scheme before the next actual welding, effectively improving welding accuracy and ensuring welding quality.

[0018] Thirdly, the present invention provides a system for industrial welding data acquisition, the system comprising:

[0019] The communication control module is used to transmit control commands to the welding robot and control the welding robot to perform welding work.

[0020] The data acquisition module is used to acquire welding information and corresponding timestamps generated by the molten pool detection camera, laser sensor, and welding robot during welding operations.

[0021] The data processing module is used to fuse the welding information and the corresponding timestamps to obtain welding information corresponding to the same timeline and to visualize it; wherein, the welding information includes at least: the trajectory position of the welding robot when performing welding work, welding current and voltage data, molten pool image and point cloud data.

[0022] Fourthly, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the industrial welding data acquisition method of the second aspect above or any corresponding embodiment thereof.

[0023] Fifthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the industrial welding data acquisition method of the second aspect above or any corresponding embodiment thereof. Attached Figure Description

[0024] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0025] Figure 1 This is a schematic diagram of the structure of an industrial welding apparatus according to an embodiment of the present invention;

[0026] Figure 2 This is a flowchart illustrating a method for acquiring industrial welding data according to an embodiment of the present invention;

[0027] Figure 3 This is a flowchart illustrating another method for industrial welding data acquisition according to an embodiment of the present invention;

[0028] Figure 4 This is a flowchart illustrating another method for industrial welding data acquisition according to an embodiment of the present invention.

[0029] Figure 5 This is a flowchart illustrating another method for industrial welding data acquisition according to an embodiment of the present invention;

[0030] Figure 6 This is a schematic diagram of the module composition of an industrial welding data acquisition system according to an embodiment of the present invention;

[0031] Figure 7 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] This invention provides an industrial welding apparatus, with reference to... Figure 1 The device includes: a welding robot 10, a molten pool detection camera 20, a laser sensor 30, and a host computer 40;

[0034] Welding robot 10 is equipped with a welding torch, which is used to control the welding torch to perform welding work according to the control instructions transmitted from the host computer.

[0035] It should be noted that a welding robot refers to an automated device that has a robotic arm and welding torch externally, and a robot control module and welding power supply internally. It can communicate with a host computer, parse the welding path and parameters according to the host computer's control instructions, and control the welding torch to perform welding work based on the welding path and parameters, thereby improving welding efficiency.

[0036] The molten pool detection camera 20 is used to acquire images of the molten pool when the welding robot performs welding work and to record the timestamp of the molten pool image;

[0037] It should be noted that the weld pool detection camera can capture images of the weld pool during the welding process and record the timestamp of each frame for subsequent data analysis and welding machine quality control. Before performing welding work, the weld pool camera needs to be installed at a preset position in the weld pool and calibrated, focused, and adjusted to ensure that it can accurately capture changes in the weld pool during the welding process.

[0038] A laser sensor 30 is installed at a preset position on the robotic arm of a welding robot to acquire point cloud data when the welding robot performs welding work and to record the timestamp of the point cloud data.

[0039] It should be noted that a laser sensor is a sensor that uses laser technology for ranging, 3D imaging, or contour detection. In this embodiment, the laser sensor can be a line laser sensor. For example, when a welding robot performs welding work, the line laser sensor projects a line through laser light in a given frame. When this line intersects with the workpiece and weld bead, it generates a point cloud for that frame, which is then captured by the camera inside the sensor, forming the point cloud image data for the current frame. Due to the high sampling frequency, hundreds or even thousands of data points can be collected per second. As the robot moves along the weld bead, these point cloud image data can be stitched together, similar to calculus, to form complete point cloud data of the workpiece and weld bead. This point cloud data can be used to optimize the welding path.

[0040] The host computer 40 is used to transmit control commands to the welding robot, and to acquire the trajectory position and welding current and voltage data of the welding robot when performing welding work, and to record the timestamps of the trajectory position and welding current and voltage data; and to acquire the molten pool image recorded by the molten pool detection camera and the timestamp of the molten pool image, and the point cloud data recorded by the laser sensor and the timestamp of the point cloud data; and to perform fusion processing on the welding information and corresponding timestamps generated by the molten pool detection camera, laser sensor, and welding robot to obtain the trajectory position, current and voltage data, molten pool image data and point cloud data corresponding to the same time line and to perform visualization display.

[0041] It should be noted that the host computer refers to the computer that monitors, controls, and processes data. In the welding equipment, the host computer is responsible for transmitting control commands to the welding robot, such as commands for the robot's linear motion trajectory and emergency stop commands. It also acquires data from the molten pool detection camera and laser sensor during the welding process, processes and fuses the data, and finally displays the various data of the welding process in a visual form.

[0042] In this embodiment of the invention, a weld pool detection camera, a laser sensor, a welding robot, and a host computer are used to acquire and record various information in real time during the welding process, including weld pool images, point cloud data, trajectory positions, and welding current and voltage data. All data are timestamped. After the timestamps are fused, the trajectory positions, current and voltage data, weld pool image data, and point cloud data corresponding to the same timeline are obtained and visualized, which improves the correlation between various data and helps operators understand the status of the welding process, so as to optimize the welding process in the future.

[0043] In one alternative implementation, the coordinates of the point cloud data acquired by the laser sensor are in the same coordinate system as the coordinates of the trajectory position generated by the welding robot.

[0044] It should be noted that setting the coordinates of the point cloud data and the coordinates of the trajectory position generated by the welding robot in the same coordinate system is essentially a process of calibrating the line laser, ensuring that the pixel information of the point cloud data collected by the line laser can be accurately mapped to the actual geometric dimensions in the welding robot coordinate system.

[0045] This invention uses a laser sensor to place point cloud data and the trajectory coordinates of the welding robot in the same coordinate system, providing a data foundation for subsequent analysis of the relationship between point cloud data and robot motion during welding, thereby helping operators to analyze welding process problems more accurately.

[0046] According to an embodiment of the present invention, a method for industrial welding data acquisition is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0047] This embodiment provides a method for industrial welding data acquisition, which can be used with the aforementioned computer equipment. Figure 2 This is a flowchart of a method for industrial welding data acquisition according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0048] Step S201: Transmit control commands to the welding robot to control the welding robot to perform welding work.

[0049] Specifically, after the host computer establishes communication with the welding robot, it transmits control commands. The welding robot's control module then parses these commands to control the robot's motion trajectory, welding speed, welding path, and so on. For example, communication can be established with the welding robot based on the ModBus protocol, transmitting control commands through the welding robot's control module's API or a pre-programmed interface.

[0050] Step S202: Obtain the welding information and corresponding timestamps generated by the molten pool detection camera, laser sensor, and welding robot during the welding operation.

[0051] It should be noted that a timestamp refers to time information recorded at a specific point in time. For example, "20231121193120123" represents a timestamp. In practical applications, the format of a timestamp may vary depending on the specific requirements.

[0052] For example, during welding, a weld pool detection camera might capture images of the weld pool at 1000 frames per second, a laser sensor might record point cloud data of the weld pool at a frequency of 100 times per second, and a welding robot might update its trajectory position and welding current and voltage data at a frequency of once per second. Each recording is accompanied by a timestamp, recording the exact time of data acquisition.

[0053] Understandably, during the welding process, different sensors and devices record data at different frequencies. If this data is not properly time-aligned, it is impossible to comprehensively analyze various aspects of the welding process. For example, it is impossible to effectively correlate the trajectory position of the welding robot with the welding current and voltage data and the molten pool image. Recording timestamps facilitates the time alignment of information from different data sources in subsequent processes, thereby enabling multi-source data to be correctly correlated and achieving comprehensive monitoring of the welding process.

[0054] Step S203: The welding information and the corresponding timestamps are fused to obtain the welding information corresponding to the same timeline and then visualized.

[0055] In this embodiment of the invention, the welding information includes at least: the trajectory position of the welding robot when performing welding work, welding current and voltage data, molten pool image, and point cloud data.

[0056] It should be noted that during the welding process, the trajectory position of the welding robot when performing welding work refers to the movement trajectory of the welding torch in space, which refers to the coordinates in three-dimensional space. Welding current and voltage data refer to the current and voltage data recorded during the welding process, acquired through communication between the welding robot and the welding power source. The molten pool image is an image captured by a molten pool detection camera, showing the state of the molten metal pool during the welding process. Point cloud data is a collection of points in three-dimensional space collected by a laser sensor, displaying the three-dimensional structure of the molten pool during the welding process.

[0057] Specifically, information from different data sources is aligned in time so that welding information can be comprehensively analyzed on the same timeline. Based on visualization development tools, the fused welding information is presented in the form of charts, images or other visualization templates so that engineers or operators can intuitively understand various data in the welding process. For example, it can display the trajectory position drawn at the same time point, the image of the molten pool or the current and voltage curve, etc.

[0058] This invention achieves comprehensive recording of various key information during the welding process by acquiring welding information and corresponding timestamps generated by the molten pool detection camera, laser sensor, and welding robot in real time. By fusing and processing multi-source data and aligning them along the same timeline for visualization, the correlation between various data points is improved, and comprehensive and real-time welding data acquisition is achieved. This effectively helps operators understand the status of the welding process, facilitating subsequent optimization of the welding process.

[0059] This embodiment provides a method for industrial welding data acquisition, which can be used with the aforementioned computer, etc. Figure 3 This is a flowchart of a method for industrial welding data acquisition according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps:

[0060] Step S301: Transmit control commands to the welding robot to control the welding robot to perform welding work. For details, please refer to [link to relevant documentation]. Figure 2 Step S201 of the illustrated embodiment will not be described again here.

[0061] Step S302: Obtain the welding information and corresponding timestamps generated by the weld pool detection camera, laser sensor, and welding robot during the welding operation. For details, please refer to [link to relevant documentation]. Figure 2 Step S202 of the illustrated embodiment will not be described again here.

[0062] Step S303 involves fusing the welding information and its corresponding timestamps to obtain welding information corresponding to the same timeline and then visualizing it. Specifically, step S303 includes:

[0063] Step S3031: Perform data noise reduction, filtering, and enhancement on the welding information to obtain preprocessed welding information.

[0064] In this embodiment, different algorithms and methods are required to process different types of welding information in order to obtain more accurate data.

[0065] For example, for voltage and current data, data denoising can use digital filtering algorithms, such as low-pass filtering and median filtering, to remove noise and interference from the current and voltage signals. Data enhancement can use differential algorithms to calculate the current and voltage difference values ​​at adjacent times to obtain more accurate voltage and current data.

[0066] Step S3032: Correct the timestamps corresponding to the preprocessed welding information according to the time sequence to obtain the corrected timestamps corresponding to the preprocessed welding information.

[0067] For example, during actual data acquisition, there may be acquisition errors. The timestamps recorded by data acquired at the same time may have slight differences. Therefore, it is necessary to calibrate the timestamps so that they can be compared at the same point in time. The calibration method can be performed using mathematical algorithms (such as time synchronization algorithms).

[0068] Specifically, there are three timestamps: trajectory position, welding current and voltage data, and molten pool image. We can first select one of the welding current and voltage data timestamps as the reference time. Then, using the time difference between this selected timestamp and the other two timestamps, we can calculate the relative offsets of these two timestamps relative to the reference time. Based on these relative offsets, we can calibrate them. The corrected timestamps are then sorted according to the time sequence to ensure that the data in subsequent steps can be statistically displayed in the order of acquisition time.

[0069] Step S3033: Using the corrected timestamp as a key, execute a preset fusion function based on the key to obtain the preprocessed welding information corresponding to the same timeline.

[0070] For example, the database stores preprocessed welding information, including corrected timestamps and welding information (trajectory position and corresponding timestamp t1, welding current and voltage data and corresponding timestamp t2, molten pool image and corresponding timestamp t3). A fusion function is predefined, which takes timestamp t as the key as the input parameter. After input, the fusion operation is performed to obtain the preprocessed welding information (trajectory position, welding current and voltage data, and molten pool image corresponding to timestamp t) at the same timeline.

[0071] Step S3034: Display the pre-processed welding information corresponding to the same timeline using visualization tools.

[0072] For example, different functions in the visualization tool plugin can be used to display the pre-processed welding information corresponding to the same timeline in different forms.

[0073] This invention improves data quality by performing noise reduction, filtering, and enhancement on welding information. The timestamps corresponding to the preprocessed welding information are corrected according to the time series to ensure the accuracy of the acquisition time of multi-source data, providing a unified time benchmark for subsequent data fusion. The preprocessed welding information corresponding to the same timeline is displayed through visualization tools, which can intuitively and clearly present various data in the welding process.

[0074] Step S304: Based on the welding information corresponding to the same timeline, use simulation tools to perform welding simulation.

[0075] Understandably, different types of welding information correspond to different simulation methods. Simulation can help operators predict potential welding problems, such as poor weld pool shape and poor weld quality, so as to take measures in advance to avoid these problems from occurring in actual welding.

[0076] For example, for trajectory position simulation, robot kinematics and dynamics simulation tools can be used to simulate the trajectory movement of the welding robot's welding torch based on the welding path and posture corresponding to the trajectory position.

[0077] In this embodiment of the invention, welding simulation is performed using simulation tools based on welding information corresponding to the same timeline. This effectively verifies different welding schemes and process routes, thereby helping operators select the best welding scheme before the next actual welding, effectively improving welding accuracy and ensuring welding quality.

[0078] This embodiment provides a method for industrial welding data acquisition, which can be used with the aforementioned computer, etc. Figure 4 This is a flowchart of a method for industrial welding data acquisition according to an embodiment of the present invention, such as... Figure 4 As shown, the process includes the following steps:

[0079] Step S401: Transmit control commands to the welding robot to control the welding robot to perform welding work. For details, please refer to [link to relevant documentation]. Figure 2 Step S201 of the illustrated embodiment will not be described again here.

[0080] Step S402: Obtain the welding information and corresponding timestamps generated by the weld pool detection camera, laser sensor, and welding robot during the welding operation. For details, please refer to [link to relevant documentation]. Figure 2 Step S202 of the illustrated embodiment will not be described again here.

[0081] Step S403 involves fusing the welding information and its corresponding timestamps to obtain welding information corresponding to the same timeline and then visualizing it. For details, please refer to [link to relevant documentation]. Figure 2 Step S203 of the illustrated embodiment will not be described again here.

[0082] Step S404: Calculate the arc data based on the welding current and voltage data.

[0083] Step S405: Based on the arc data and the preset welding transition coefficient, obtain the welding transition parameters according to the welding transition formula.

[0084] It should be noted that welding transfer formulas include: droplet transfer formula, short-circuit transfer formula, and particle transfer formula. Droplet transfer refers to the formation of droplets during the formation and movement of the molten pool due to surface tension. These droplets may fall into the weld, leading to welding defects. Droplet transfer occurs during high-speed, high-power welding. Short-circuit transfer refers to the weld pool solidifying after the welding arc extinguishes, but the welding wire fails to replenish in time, causing the molten pool to break, resulting in a welding defect called a short circuit. Particle transfer refers to the presence of metal particles in the molten pool during welding. These particles may originate from the welding wire or workpiece material; they may exist isolated in the weld or deposit on the weld surface, leading to welding defects.

[0085] Understandably, to avoid the adverse effects of droplet transfer, short-circuit transfer, and particle transfer on weld quality, it is necessary to carefully control the welding transfer parameters during the welding process. Welding transfer parameters include: droplet transfer parameters, short-circuit transfer parameters, and particle transfer parameters.

[0086] For example, the formula for droplet transition is: P1 = k1 * L * D;

[0087] The short-circuit transient formula is: P2 = k2 * L / (L + D);

[0088] The particle transition formula is: P3=k3*D / (L+D).

[0089] Wherein, P1 is the droplet transition parameter, used to describe the arc characteristics of droplet transition; P2 is the short-circuit transition parameter, used to represent the arc characteristics of short-circuit transition; P3 is the preset particle transition parameter, used to represent the arc characteristics of particle transition; k1 is the droplet transition coefficient; k2 is the preset short-circuit transition coefficient; k3 is the preset particle transition coefficient; L is the arc length; and D is the arc diameter.

[0090] Step S406: Train the welding process optimization model based on the welding transition parameters, and determine the welding process parameters based on the welding process optimization model.

[0091] For example, the welding process optimization model is first trained using these welding transition parameters. It is necessary to collect the welding results corresponding to the welding transition parameters under different currents and voltages in advance, such as weld morphology and weld size, as experimental data. The experimental data is used as training samples and input into a machine learning model for training. The established welding process optimization model takes the welding transition parameters under different currents and voltages as inputs and the weld morphology and weld size as outputs. This model is used to determine specific welding process parameters. For example, if a certain parameter is determined to be A, the specific values ​​of current and voltage a1 and a2 can be derived.

[0092] Step S407: Generate optimized control instructions based on the control algorithm according to the welding process parameters, and control the welding robot to perform welding work.

[0093] For example, based on the specific values ​​a1 and a2 of the current and voltage derived from the derivation, and combined with the control module of the welding robot itself, the welding process parameters are converted into specific control instructions, which control the welding robot to perform welding according to the preset welding path, welding speed, etc.

[0094] This invention improves welding quality and efficiency by determining welding parameters based on the arc characteristics during the actual welding process and by determining welding process parameters based on a trained welding process optimization model. Furthermore, it generates optimized control commands based on the welding process parameters using a control algorithm, thereby achieving optimized and precise control of the welding robot and effectively ensuring welding quality.

[0095] This embodiment provides a method for industrial welding data acquisition, which can be used with the aforementioned computer, etc. Figure 5 This is a flowchart of a method for industrial welding data acquisition according to an embodiment of the present invention, such as... Figure 5 As shown, the process includes the following steps:

[0096] Step S501: Transmit control commands to the welding robot to control the welding robot to perform welding work. For details, please refer to [link to relevant documentation]. Figure 2 Step S201 of the illustrated embodiment will not be described again here.

[0097] Step S502: Obtain the welding information and corresponding timestamps generated by the weld pool detection camera, laser sensor, and welding robot during the welding operation. For details, please refer to [link to relevant documentation]. Figure 2 Step S202 of the illustrated embodiment will not be described again here.

[0098] Step S503 involves fusing the welding information and its corresponding timestamps to obtain welding information corresponding to the same timeline and then visualizing it. For details, please refer to [link to relevant documentation]. Figure 2 Step S203 of the illustrated embodiment will not be described again here.

[0099] Step S504: Extract droplet features based on the molten pool image.

[0100] It should be noted that droplet characteristics refer to the relevant feature parameters of the droplets in the molten pool generated during the welding process, such as droplet size, shape, position, and velocity. Droplet size is the diameter or area of ​​the droplet, which is detected through image processing techniques. Droplet shape is the outer contour of the droplet, obtained by extracting the contour from the molten pool image. Droplet position is the coordinate of the droplet's location on the welded workpiece, which can be obtained through image coordinate transformation in the molten pool image. Droplet velocity is the speed of the droplet's movement, calculated by tracking the position of the same droplet between consecutive image frames.

[0101] Step S505: Based on the droplet characteristics, generate optimized control instructions using a control algorithm to control the welding robot to perform welding work.

[0102] For example, based on the position information of the molten droplets, it can be determined whether the landing point of the molten droplets meets the expectations, or whether the spacing between the molten droplets is uniform. By analyzing the speed of the molten droplets, the splashing situation of the molten droplets can be determined. Based on the above analysis, reasonable parameters are determined, such as welding speed b and welding position offset c millimeters. Combined with the control module of the welding robot itself, the parameters are converted into specific control instructions to control the welding robot to weld according to the preset welding path and welding speed.

[0103] This invention enables the monitoring of the droplet formation process and the state of the molten pool during welding by extracting droplet features from the molten pool image. Based on the droplet features, optimized control commands are generated using a control algorithm, allowing the welding process to be adaptively and specifically adjusted according to the actual droplet state, preventing welding defects and effectively ensuring welding quality.

[0104] This embodiment also provides an industrial welding data acquisition system, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the system described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0105] This embodiment provides a system for industrial welding data acquisition, such as... Figure 6 As shown, it includes:

[0106] The communication control module 601 is used to transmit control commands to the welding robot and control the welding robot to perform welding work.

[0107] The data acquisition module 602 is used to acquire welding information and corresponding timestamps generated by the molten pool detection camera, laser sensor, and welding robot during welding operations.

[0108] The data processing module 603 is used to fuse welding information and corresponding timestamps to obtain welding information corresponding to the same timeline and to visualize it; wherein, the welding information includes at least: the trajectory position of the welding robot when performing welding work, welding current and voltage data, molten pool image and point cloud data.

[0109] In one alternative implementation, the data processing module 603 includes:

[0110] The data filtering subunit is used to perform data noise reduction, filtering, and enhancement on the welding information to obtain preprocessed welding information.

[0111] The time correction subunit is used to correct the timestamps corresponding to the preprocessed welding information according to the time sequence to obtain the corrected timestamps corresponding to the preprocessed welding information.

[0112] The data fusion subunit is used to use the corrected timestamp as a key and execute a preset fusion function based on the key to obtain the preprocessed welding information corresponding to the same timeline.

[0113] The data display sub-unit is used to display pre-processed welding information corresponding to the same timeline based on visualization tools.

[0114] In an optional embodiment, the system further includes: a first welding process optimization module, used to calculate arc data based on welding current and voltage data; obtain welding transition parameters based on welding transition formula according to the arc data and a preset welding transition coefficient; train a welding process optimization model based on the welding transition parameters; determine welding process parameters based on the welding process optimization model; and generate optimized control instructions based on the welding process parameters and a control algorithm to control the welding robot to perform welding work.

[0115] In an optional implementation, the system further includes: a second welding process optimization module, used to extract droplet features based on the molten pool image; and to generate optimized control instructions based on the droplet features and a control algorithm to control the welding robot to perform welding work.

[0116] In an optional implementation, the system further includes a welding information simulation module, used to perform welding simulation using simulation tools based on welding information corresponding to the same timeline.

[0117] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0118] This invention achieves comprehensive recording of various key information during the welding process by acquiring welding information and corresponding timestamps generated by the molten pool detection camera, laser sensor, and welding robot in real time. By fusing and processing multi-source data and aligning them along the same timeline for visualization, the correlation between various data points is improved, and comprehensive and real-time welding data acquisition is achieved. This effectively helps operators understand the status of the welding process, facilitating subsequent optimization of the welding process.

[0119] The industrial welding data acquisition system in this embodiment is presented in the form of functional units. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0120] This invention also provides a computer device having the above-described features. Figure 6 The system shown is for acquiring industrial welding data.

[0121] Please see Figure 7 , Figure 7 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 7As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 7 Take a processor 10 as an example.

[0122] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0123] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0124] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0125] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0126] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0127] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0128] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined herein.

Claims

1. An industrial welding apparatus, characterized in that, The device includes: a molten pool detection camera, a laser sensor, a welding robot, and a host computer; The welding robot is equipped with a welding torch, which is used to control the welding torch to perform welding work according to the control instructions transmitted from the host computer. The molten pool detection camera is used to acquire images of the molten pool when the welding robot performs welding work, and to record the timestamp of the molten pool image; The laser sensor is installed at a preset position on the welding robot arm to acquire point cloud data when the welding robot performs welding work and to record the timestamp of the point cloud data. The host computer is used to transmit control commands to the welding robot, and to acquire the trajectory position and welding current and voltage data of the welding robot when performing welding work, and record the timestamps of the trajectory position and the welding current and voltage data; it also acquires the molten pool image and its timestamp recorded by the molten pool detection camera, and the point cloud data and its timestamp recorded by the laser sensor; it performs fusion processing on the welding information and corresponding timestamps generated by the molten pool detection camera, laser sensor, and welding robot to obtain the trajectory position, current and voltage data, molten pool image data, and point cloud data corresponding to the same timeline and displays them visually; it calculates arc data based on the welding current and voltage data; it obtains welding transition parameters based on the arc data and a preset welding transition coefficient, and the welding transition parameters include: droplet transition parameters, short-circuit transition parameters, and particle transition parameters; it trains a welding process optimization model based on the welding transition parameters, and determines the welding process parameters based on the welding process optimization model; it generates optimized control commands based on the welding process parameters and a control algorithm to control the welding robot to perform welding work. The welding transition formula is as follows: The droplet transition formula is: ; The short-circuit transient formula is: ; The particle transition formula is: ; Wherein, P1 is the droplet transition parameter, used to describe the arc characteristics of droplet transition; P2 is the short-circuit transition parameter, used to represent the arc characteristics of short-circuit transition; P3 is the preset particle transition parameter, used to represent the arc characteristics of particle transition; k1 is the droplet transition coefficient; k2 is the preset short-circuit transition coefficient; k3 is the preset particle transition coefficient; L is the arc length; and D is the arc diameter.

2. The apparatus according to claim 1, characterized in that, The coordinates of the point cloud data acquired by the laser sensor are in the same coordinate system as the coordinates of the trajectory position generated by the welding robot.

3. A method for industrial welding data acquisition, characterized in that, Based on the industrial welding apparatus according to claim 1 or 2, the method includes: The host computer transmits control commands to the welding robot, controlling the welding robot to perform welding work; The host computer acquires welding information and corresponding timestamps generated by the molten pool detection camera, laser sensor, and welding robot during the welding process. The host computer performs fusion processing on the welding information and the corresponding timestamps to obtain welding information corresponding to the same timeline and displays it visually. The welding information includes at least: the trajectory position of the welding robot when performing welding work, welding current and voltage data, molten pool image and point cloud data.

4. The method according to claim 3, characterized in that, The step of fusing the welding information and the corresponding timestamps to obtain welding information corresponding to the same timeline and then visualizing it includes: The welding information is subjected to data noise reduction, filtering, and enhancement to obtain preprocessed welding information; The timestamps corresponding to the preprocessed welding information are corrected according to the time sequence to obtain the corrected timestamps corresponding to the preprocessed welding information. Using the corrected timestamp as a key, a preset fusion function is executed based on the key to obtain the preprocessed welding information corresponding to the same timeline; The pre-processed welding information corresponding to the same timeline is displayed using visualization tools.

5. The method according to claim 3, characterized in that, After the step of fusing the welding information and the corresponding timestamps to obtain welding information corresponding to the same timeline and then visualizing it, the method further includes: Arc data is calculated based on the welding current and voltage data; Based on the arc data and the preset welding transition coefficient, welding transition parameters are obtained using the welding transition formula. A welding process optimization model is trained based on the welding transition parameters, and welding process parameters are determined based on the welding process optimization model. Based on the welding process parameters and a control algorithm, optimized control instructions are generated to control the welding robot to perform welding work.

6. The method according to claim 3, characterized in that, After the step of fusing the welding information and the corresponding timestamps to obtain welding information corresponding to the same timeline and then visualizing it, the method further includes: Extract droplet features based on the molten pool image; Based on the characteristics of the molten droplets, an optimized control command is generated using a control algorithm to control the welding robot to perform welding work.

7. The method according to claim 3 or 4, characterized in that, After the step of fusing the welding information and the corresponding timestamps to obtain welding information corresponding to the same timeline and then visualizing it, the method further includes: Welding simulation is performed using simulation tools based on welding information corresponding to the same timeline.

8. A system for acquiring industrial welding data, characterized in that, The system includes: The communication control module is used to transmit control commands to the welding robot and control the welding robot to perform welding work. The data acquisition module is used to acquire welding information and corresponding timestamps generated by the molten pool detection camera, laser sensor, and welding robot during welding operations. The data processing module is used to fuse the welding information and corresponding timestamps to obtain welding information corresponding to the same timeline and to visualize it; calculate arc data based on welding current and voltage data; obtain welding transition parameters based on the arc data and a preset welding transition coefficient and a welding transition formula; train a welding process optimization model based on the welding transition parameters; determine welding process parameters based on the welding process optimization model; and generate optimized control commands based on the welding process parameters and a control algorithm to control the welding robot to perform welding work. The welding information includes at least: the trajectory position of the welding robot when performing welding work, welding current and voltage data, molten pool image, and point cloud data; the welding transition parameters include: droplet transition parameters, short-circuit transition parameters, and particle transition parameters. The welding transition formula is as follows: The droplet transition formula is: ; The short-circuit transient formula is: ; The particle transition formula is: ; Wherein, P1 is the droplet transition parameter, used to describe the arc characteristics of droplet transition; P2 is the short-circuit transition parameter, used to represent the arc characteristics of short-circuit transition; P3 is the preset particle transition parameter, used to represent the arc characteristics of particle transition; k1 is the droplet transition coefficient; k2 is the preset short-circuit transition coefficient; k3 is the preset particle transition coefficient; L is the arc length; and D is the arc diameter.

9. A computer device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the industrial welding data acquisition method according to any one of claims 3 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the method for industrial welding data acquisition as described in any one of claims 3 to 7.

Images