Method, device and processor for determining a welding gap of a welding point

Abstract

This application discloses a method, apparatus, and processor for determining the welding gap of a welding point. The method includes: determining the gap of the next welding point while the welding equipment is welding the current welding point; determining the actual welding parameters of multiple welding points that have been welded before the current welding point; inputting the gap and all the actual welding parameters into a prediction model and obtaining the prediction difference output by the prediction model; and determining the difference between the gap and the prediction difference as the actual welding gap of the next welding point. This allows for determining the actual welding gap of the welding point using only a single acquisition device and prediction model, improving welding accuracy, and enabling timely and accurate determination of gap changes at the welding point, thereby accelerating the welding speed.

Description

Technical Field

[0001] This application relates to the field of intelligent welding technology, and more specifically to a method, apparatus, processor, and storage medium for determining the welding gap of a welding point. Background Technology

[0002] Current welding methods typically involve measuring the gap between the weld points using laser measuring equipment. However, due to the influence of the welding arc and the equipment's installation space, the actual weld point measured by the laser may be further ahead than the weld point itself. When the welding torch is used to weld according to this laser-measured gap, significant errors occur. To avoid these errors, traditional welding processes usually rely on the welder's experience to add a fixed error value to adjust the gap between the weld points, and then control the welding torch based on this adjusted gap. This traditional method relies too heavily on subjective experience and intuition, failing to accurately and objectively calculate the actual weld gap. Furthermore, relying solely on manual judgment and control results in slow welding speeds and low efficiency. Summary of the Invention

[0003] The purpose of this application is to provide a method, apparatus, processor, and storage medium for determining the welding gap of a welding point, so as to solve the problems of inaccurate prediction of welding gap changes and low welding efficiency in the prior art.

[0004] To achieve the above objectives, the first aspect of this application provides a method for determining the welding gap of a welding point, the method comprising:

[0005] While the welding equipment is welding the current welding point, the gap of the next welding point to be welded is determined by the first acquisition device.

[0006] Determine the actual welding parameters for multiple welded points preceding the current weld point;

[0007] Input the gap and all actual welding parameters into the prediction model, and obtain the prediction difference output by the prediction model;

[0008] The difference between the gap and the predicted difference is determined as the actual welding gap of the next welding point.

[0009] In this embodiment of the application, the method further includes: before the welding equipment welds the current welding point, acquiring a first historical gap, a second historical gap, and historical welding parameters for each historical welding point, wherein the first historical gap is acquired by a first historical acquisition device installed in the welding direction behind the historical welding equipment and on the front of the historical welding point, and the second historical gap is acquired by a second historical acquisition device installed in the welding direction behind the historical welding point and on the welding direction. The distance between the first historical acquisition device and the historical welding equipment is greater than the distance between the second historical acquisition device and the historical welding equipment. The historical welding parameters include at least welding temperature, welding length, welding current, and welding voltage. The first historical gap, the second historical gap, and the historical welding parameters of each historical welding point are processed sequentially to train the prediction model, wherein the input of the prediction model is the historical welding parameters of any historical welding point, and the output of the prediction model is the historical prediction difference between the first historical gap and the second historical gap of any historical welding point.

[0010] In this embodiment of the application, obtaining the historical welding parameters of each historical welding point includes: when the historical welding equipment is welding the first welding point, determining the second welding point that the historical first acquisition device is currently acquiring; determining the distance between the first welding point and the second welding point as the target distance; setting a preset data window according to the target distance; and for each historical welding point, determining the historical welding parameters of each welding point located before the historical welding point and within the preset data window as the historical welding parameters corresponding to the historical welding point.

[0011] In this embodiment of the application, the process of processing the first historical gap, the second historical gap, and the historical welding parameters of each historical welding point to train the prediction model includes: removing abnormal welding points from multiple historical welding points, wherein abnormal welding points refer to welding points when the historical welding equipment was in a shaking state; for each of the remaining historical welding points, aligning the first historical gap and the second historical gap of the historical welding point to obtain the gap change of the historical welding point; and for each of the remaining historical welding points, training the prediction model using the first historical gap, the second historical gap, and the historical welding parameters of each historical welding point.

[0012] In this embodiment of the application, the method further includes: after obtaining the gap change of the historical welding points, obtaining the fixed parameters of the historical welding equipment and the dimensional parameters of the welding material, wherein the fixed parameters include the welding angle and bevel angle of the historical welding equipment; for each of the remaining historical welding points, determining the historical welding parameters of the historical welding point, which also include the molten pool temperature, molten pool size, welding length, welding time, and welding speed; for each of the remaining historical welding points, training a prediction model using the fixed parameters, dimensional parameters, historical welding parameters of the historical welding point, the first historical gap, and the second historical gap.

[0013] In this embodiment of the application, the first acquisition device is used to acquire the gap between the welding points to be welded at a preset distance from the current welding point when the welding device is welding the current welding point.

[0014] In this embodiment of the application, determining the actual welding parameters of multiple welded points preceding the current welding point includes: setting a data window according to a preset interval; and determining the welding parameters of multiple welded points preceding the current welding point and located within the data window as the actual welding parameters.

[0015] In this embodiment of the application, the method further includes: after determining the difference between the gap and the predicted difference as the actual welding gap of the next welding point, generating welding control parameters for the next welding point based on the actual welding gap; and controlling the welding equipment to weld the next welding point according to the welding control parameters.

[0016] A second aspect of this application provides a processor configured to perform the above-described method for determining the welding gap of a welding point.

[0017] A third aspect of this application provides an apparatus for determining the welding gap at a welding point, comprising:

[0018] The memory is configured to store instructions; and

[0019] The processor mentioned above.

[0020] A fourth aspect of this application provides a machine-readable storage medium storing instructions for causing a machine to perform the aforementioned method for determining the weld gap at a weld point.

[0021] Through the above technical solution, when the welding equipment is welding the current welding point, the gap of the next welding point to be welded, which is collected by the first acquisition device, can be determined; and the actual welding parameters of multiple welding points that have been welded before the current welding point can be determined; the gap and all the actual welding parameters are fed into the prediction model, and the prediction difference output by the prediction model is obtained, so that the difference between the gap and the prediction difference is determined as the actual welding gap of the next welding point. This achieves the determination of the actual welding gap of the welding point through only one acquisition device and prediction model, improves the welding accuracy, and can determine the gap change of the welding point in a timely and accurate manner, thereby speeding up the welding process.

[0022] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0023] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings:

[0024] Figure 1 The illustration shows a flowchart of a method for determining the welding gap of a welding point according to an embodiment of this application;

[0025] Figure 2 A schematic diagram of a welding system according to an embodiment of this application is shown.

[0026] Figure 3 The diagram illustrates the internal structure of a computer device according to an embodiment of this application. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0028] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0029] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0030] Figure 1 The illustration schematically shows a flow chart of a method for determining the welding gap of a welding point according to an embodiment of this application. Figure 1 As shown in the figure, this application provides a method for determining the welding gap of a welding point, which may include the following steps.

[0031] Step 101: When the welding equipment is welding the current welding point, obtain the gap of the next welding point collected by the first acquisition device.

[0032] While the welding equipment is welding the current welding point, the processor can determine the gap of the next welding point to be acquired by the first acquisition device.

[0033] In this embodiment of the application, the method further includes: before the welding equipment welds the current welding point, acquiring a first historical gap, a second historical gap, and historical welding parameters for each historical welding point, wherein the first historical gap is acquired by a first historical acquisition device installed in the welding direction behind the historical welding equipment and on the front of the historical welding point, and the second historical gap is acquired by a second historical acquisition device installed in the welding direction behind the historical welding point and on the welding direction. The distance between the first historical acquisition device and the historical welding equipment is greater than the distance between the second historical acquisition device and the historical welding equipment. The historical welding parameters include at least welding temperature, welding length, welding current, and welding voltage. The first historical gap, the second historical gap, and the historical welding parameters of each historical welding point are processed sequentially to train the prediction model, wherein the input of the prediction model is the historical welding parameters of any historical welding point, and the output of the prediction model is the historical prediction difference between the first historical gap and the second historical gap of any historical welding point.

[0034] Before the welding equipment welds the current welding point, the processor can acquire the first historical gap, the second historical gap, and historical welding parameters for each historical welding point. The first historical gap is acquired by a first historical acquisition device installed in the welding direction behind the historical welding equipment and facing the historical welding point. The second historical gap is acquired by a second historical acquisition device installed in the welding direction behind the historical welding equipment and facing the historical welding point. The distance between the first historical acquisition device and the historical welding equipment is greater than the distance between the second historical acquisition device and the historical welding equipment. The historical welding parameters include at least welding temperature, welding length, welding current, and welding voltage. The processor can also sequentially process the first historical gap, the second historical gap, and the historical welding parameters for each historical welding point to train a prediction model. The input to the prediction model is the historical welding parameters for any historical welding point, and the output of the prediction model is the historical prediction difference between the first and second historical gaps for that historical welding point.

[0035] In this embodiment of the application, obtaining the historical welding parameters of each historical welding point includes: when the historical welding equipment is welding the first welding point, determining the second welding point that the historical first acquisition device is currently acquiring; determining the distance between the first welding point and the second welding point as the target distance; setting a preset data window according to the target distance; and for each historical welding point, determining the historical welding parameters of each welding point located before the historical welding point and within the preset data window as the historical welding parameters corresponding to the historical welding point.

[0036] While the historical welding equipment is welding the first welding point, the processor can determine the second welding point that the historical first acquisition equipment is currently acquiring. After determining the second welding point, the processor can define the distance between the first welding point and the second welding point as the target distance. After determining the target distance, the processor can set a preset data window based on the target distance. For each historical welding point, the processor can define the historical welding parameters of each welding point located before that historical welding point and within the preset data window as the historical welding parameters corresponding to that historical welding point.

[0037] In this embodiment of the application, the process of processing the first historical gap, the second historical gap, and the historical welding parameters of each historical welding point to train the prediction model includes: removing abnormal welding points from multiple historical welding points, wherein abnormal welding points refer to welding points when the historical welding equipment was in a shaking state; for each of the remaining historical welding points, aligning the first historical gap and the second historical gap of the historical welding point to obtain the gap change of the historical welding point; and for each of the remaining historical welding points, training the prediction model using the first historical gap, the second historical gap, and the historical welding parameters of each historical welding point.

[0038] The processor can sequentially process the first historical gap, second historical gap, and historical welding parameters of each historical weld point to train the prediction model. Specifically, the processor can remove abnormal weld points from multiple historical weld points. Abnormal weld points refer to weld points where the welding equipment was vibrating during welding. After removing abnormal weld points, for each of the remaining historical weld points, the processor can process the first historical gap and second historical gap to obtain the gap variation of the historical weld point. For each of the remaining historical weld points, the processor can train the prediction model using the first historical gap, second historical gap, and historical welding parameters of each historical weld point.

[0039] In this embodiment of the application, the method further includes: after obtaining the gap change of the historical welding points, obtaining the fixed parameters of the historical welding equipment and the dimensional parameters of the welding material, wherein the fixed parameters include the welding angle and bevel angle of the historical welding equipment; for each of the remaining historical welding points, determining the historical welding parameters of the historical welding point, which also include the molten pool temperature, molten pool size, welding length, welding time, and welding speed; for each of the remaining historical welding points, training a prediction model using the fixed parameters, dimensional parameters, historical welding parameters of the historical welding point, the first historical gap, and the second historical gap.

[0040] After obtaining the gap variation of historical weld points, the processor can acquire the fixed parameters of the historical welding equipment and the dimensional parameters of the welding materials. The fixed parameters include the welding angle and bevel angle of the historical welding equipment. For each of the remaining historical weld points, the processor can determine the historical welding parameters for that point, including the molten pool temperature, molten pool size, weld length, welding time, and welding speed. For each of the remaining historical weld points, the processor can train a prediction model using the fixed parameters, dimensional parameters, historical welding parameters of the historical weld point, the first historical gap, and the second historical gap.

[0041] Figure 2 A schematic diagram of a welding system according to an embodiment of this application is shown, such as... Figure 2 As shown, the welding system may include a robotic arm, a welding torch, a thermal imager, auxiliary fixture 1, and auxiliary fixture 2. The welding system can weld materials and collect welding data. The welding torch can be the historical welding device. The first acquisition device can be auxiliary fixture 1, which emits a frontal laser to acquire the first historical gap of historical weld points. The second acquisition device can be auxiliary fixture 2, which emits a back laser to acquire the second historical gap of historical weld points. Auxiliary fixture 1 can be installed on the front of the welding material, ensuring that the frontal laser can acquire the gap data of the weld point 40mm ahead of the point being welded by the welding torch. Auxiliary fixture 2 can be installed on the back of the welding material, ensuring that the back laser can acquire the gap data of the weld point 5mm ahead of the point being welded. The thermal imager can measure the temperature of the molten pool area, the area to be welded, and the location where the frontal laser is refracted.

[0042] While the welding torch is welding the first welding point, the processor can determine the second welding point being acquired by the frontal laser and set the distance of 40mm between the first and second welding points as the target distance. The processor can be set to acquire welding data for one welding point every 2mm. The processor can set 20 data windows based on 40mm and 2mm. For each historical welding point, the processor can determine the historical welding parameters of each welding point located before that historical welding point and within this 20 data windows as the historical welding parameters corresponding to that historical welding point. The processor can remove abnormal welding points based on the welding conditions to eliminate abnormal data. Abnormal welding points are welding points where the welding torch is welding under abnormal welding conditions. Abnormal data can include welding error data, abnormal jitter data, laser tracking deviation data, arc ignition failure data, weld penetration / leakage data, and data outside the normal range, etc.

[0043] For each historical weld point, the processor can align the first historical gap acquired by the front laser and the second historical gap acquired by the back laser, ensuring that the data from both laser acquisitions represent the historical weld point. The processor can then take the difference between the two aligned historical gaps to obtain the gap change of the historical weld point, taking into account the influence of heat input on the weld gap and more accurately reflecting the gap transformation.

[0044] The processor can extract historical welding parameters for this historical weld point, including at least the molten pool temperature, welding zone temperature, frontal laser refraction zone temperature, distance between the highest temperature in the welding zone and the highest temperature in the area to be welded, molten pool size, welding length, welding time, welding voltage, welding current, welding speed, and laser measurement gap. The processor can also acquire the fixed parameters of the welding torch and the dimensional parameters of the welding materials. Fixed parameters may include welding angle and bevel angle. Dimensional parameters may include the width, thickness, and volume of the welding materials. The molten pool temperature reflects the overall heat input during the welding process. The welding zone temperature, primarily the average highest temperature in the welding zone, reflects the combined effects of heat diffusion and speed. The frontal laser refraction zone temperature can be compared with the welding zone temperature to reflect temperature changes. The distance between the highest temperature in the welding zone and the highest temperature in the area to be welded reflects the flow of the molten pool. The molten pool size can be represented by high-temperature pixels on a thermal imager. Welding length and welding time affect heat dissipation. Welding current and welding voltage affect the heat input during welding. Welding speed affects the diffusion of heat effects. Welding angle and bevel angle affect the flow of the molten pool.

[0045] The processor can train a prediction model using fixed parameters, dimensional data, historical welding parameters for each historical weld point, a first historical gap, and a second historical gap. The prediction model can employ LSTM, RNN, or similar methods. The processor can determine the prediction accuracy of the model based on the historical prediction difference for each historical weld point and the gap change for each historical weld point. If the prediction accuracy exceeds a preset threshold, the processor can determine that the prediction model training is complete.

[0046] Step 102: Determine the actual welding parameters of multiple welded points that have been welded before the current welding point.

[0047] Step 103: Input the gap and all actual welding parameters into the prediction model, and obtain the prediction difference output by the prediction model.

[0048] Step 104: Determine the difference between the gap and the predicted difference as the actual welding gap of the next welding point.

[0049] While the welding equipment is welding the current welding point, the processor can acquire the gap of the next welding point to be welded, which is acquired by the first acquisition device. In this embodiment, the first acquisition device is used to acquire the gap of the welding points to be welded at a preset interval from the current welding point while the welding equipment is welding the current welding point. The processor can determine the actual welding parameters of multiple welding points that have been welded before the current welding point. After obtaining the gap of the next welding point and the actual welding parameters of the multiple welding points, the processor can input the gap and all the actual welding parameters into the prediction model and obtain the prediction difference output by the prediction model. After obtaining the prediction difference, the processor can determine the difference between the gap and the prediction difference as the actual welding gap of the next welding point.

[0050] In this embodiment of the application, determining the actual welding parameters of multiple welded points preceding the current welding point includes: setting a data window according to a preset interval; and determining the welding parameters of multiple welded points preceding the current welding point and located within the data window as the actual welding parameters.

[0051] The processor can determine the actual welding parameters of multiple welded joints preceding the current welded joint. Specifically, the processor can set a data window according to a preset interval. After setting the data window, the processor can determine the welding parameters of multiple welded joints preceding the current welded joint and located within the data window as the actual welding parameters.

[0052] In this embodiment of the application, the method further includes: after determining the difference between the gap and the predicted difference as the actual welding gap of the next welding point, generating welding control parameters for the next welding point based on the actual welding gap; and controlling the welding equipment to weld the next welding point according to the welding control parameters.

[0053] After determining the difference between the gap of the next weld point and the predicted difference as the actual weld gap of the next weld point, the processor generates welding control parameters for the next weld point based on the actual weld gap. After determining the welding control parameters of the next weld point, the processor can control the welding equipment to weld the next weld point according to the welding control parameters.

[0054] For example, the welding equipment can be a welding torch, and the first acquisition device can be a front-facing laser device. The front-facing laser device is used to acquire the gap of the next welding point 40mm away from the current welding point while the welding torch is welding the current welding point. While the welding torch is welding the current welding point, the processor can acquire the gap of the next welding point acquired by the front-facing laser device. Specifically, when the welding torch is welding a welding point 40mm before the next welding point, the front-facing laser device is acquiring the gap of the next welding point. The processor can set 20 data windows based on 40mm. The welding parameters of the welded points that are already welded before the current welding point and located within these 20 data windows are determined as the actual welding parameters. After obtaining the actual welding parameters, the processor can input the gap and the actual welding parameters into a prediction model and obtain the prediction difference output by the prediction model. The difference between the gap and the prediction difference is determined as the actual welding gap of the next welding point.

[0055] After determining the actual welding gap, the processor can generate welding control parameters based on the actual welding gap and control the welding torch to weld the next point to be welded according to the welding control parameters.

[0056] After determining the actual welding gap, the processor can also acquire the fixed parameters of the welding torch, the dimensional parameters of the welding material, and the real-time temperature of the next welding point. Based on the actual welding gap, real-time temperature, dimensional parameters, and fixed parameters, the processor determines the welding control parameters for the next welding point. After determining the welding control parameters, the processor can control the welding torch to weld the next welding point according to these parameters.

[0057] The above technical solution enables the determination of the actual welding gap of the welding point using only one acquisition device and prediction model, thereby improving welding accuracy and enabling timely and accurate determination of gap changes at the welding point, thus accelerating the welding speed.

[0058] Figure 1 This is a flowchart illustrating a method for determining the weld gap at a weld point in one embodiment. It should be understood that, although... Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but may be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0059] This application also provides a processor configured to perform the above-described method for determining the welding gap of a welding point.

[0060] This application also provides an apparatus for determining the welding gap of a welding point, comprising:

[0061] The memory is configured to store instructions; and

[0062] The processor mentioned above.

[0063] This application also provides a machine-readable storage medium storing instructions for causing a machine to perform the above-described method for determining the welding gap of a weld point.

[0064] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor A01, a network interface A02, a memory (not shown), and a database (not shown) connected via a system bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02, and a database (not shown). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A04. The database stores data on first historical gaps, second historical gaps, historical welding parameters, historical prediction differences, actual welding parameters, prediction differences, and actual welding gaps. The network interface A02 communicates with external terminals via a network connection. When executed by the processor A01, the computer program B02 implements a method for determining the welding gap of a welding point.

[0065] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0066] This application provides an apparatus including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: when the welding device is welding the current welding point, it determines the gap of the next welding point to be welded, which is acquired by the first acquisition device; it determines the actual welding parameters of multiple welding points that have been welded before the current welding point; it inputs the gap and all the actual welding parameters into the prediction model and obtains the prediction difference output by the prediction model; and it determines the difference between the gap and the prediction difference as the actual welding gap of the next welding point to be welded.

[0067] In one embodiment, the method further includes: before the welding equipment welds the current welding point, acquiring a first historical gap, a second historical gap, and historical welding parameters for each historical welding point, wherein the first historical gap is acquired by a first historical acquisition device installed in the welding direction behind the historical welding equipment and in front of the historical welding point, and the second historical gap is acquired by a second historical acquisition device installed in the welding direction behind the historical welding point and in the welding direction, the distance between the first historical acquisition device and the historical welding equipment is greater than the distance between the second historical acquisition device and the historical welding equipment, and the historical welding parameters include at least welding temperature, welding length, welding current, and welding voltage; and training a prediction model after processing the first historical gap, the second historical gap, and the historical welding parameters for each historical welding point in sequence, wherein the input of the prediction model is the historical welding parameters of any historical welding point, and the output of the prediction model is the historical prediction difference between the first historical gap and the second historical gap of any historical welding point.

[0068] In one embodiment, obtaining the historical welding parameters of each historical welding point includes: when the historical welding equipment is welding the first welding point, determining the second welding point that the historical first acquisition device is currently acquiring; determining the distance between the first welding point and the second welding point as the target distance; setting a preset data window according to the target distance; and for each historical welding point, determining the historical welding parameters of each welding point located before the historical welding point and within the preset data window as the historical welding parameters corresponding to the historical welding point.

[0069] In one embodiment, training the prediction model after processing the first historical gap, second historical gap, and historical welding parameters of each historical welding point in sequence includes: removing abnormal welding points from multiple historical welding points, wherein abnormal welding points refer to welding points when the historical welding equipment was in a shaking state; for each of the remaining historical welding points, aligning the first historical gap and second historical gap of the historical welding point to obtain the gap change of the historical welding point; and training the prediction model for each of the remaining historical welding points using the first historical gap, second historical gap, and historical welding parameters of each historical welding point.

[0070] In one embodiment, the method further includes: after obtaining the gap variation of historical weld points, acquiring the fixed parameters of the historical welding equipment and the dimensional parameters of the welding material, wherein the fixed parameters include the welding angle and bevel angle of the historical welding equipment; for each of the remaining historical weld points, determining the historical welding parameters of the historical weld point, which also include the molten pool temperature, molten pool size, welding length, welding time, and welding speed; and for each of the remaining historical weld points, training a prediction model using the fixed parameters, dimensional parameters, historical welding parameters of the historical weld point, a first historical gap, and a second historical gap.

[0071] In one embodiment, the first acquisition device is used to acquire the gap between the welding points to be welded at a preset distance from the current welding point when the welding device is welding the current welding point.

[0072] In one embodiment, determining the actual welding parameters of multiple welded points preceding the current welding point includes: setting a data window according to a preset interval; and determining the welding parameters of multiple welded points preceding the current welding point and located within the data window as the actual welding parameters.

[0073] In one embodiment, the method further includes: after determining the difference between the gap and the predicted difference as the actual welding gap of the next weld point, generating welding control parameters for the next weld point based on the actual welding gap; and controlling the welding equipment to weld the next weld point according to the welding control parameters.

[0074] This application also provides a computer program product that, when executed on a data processing device, is adapted to perform a program that initializes a method step for determining the weld gap at a weld point.

[0075] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0076] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0077] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0078] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0079] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0080] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0081] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0082] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0083] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for determining the welding gap at a welding point, characterized in that, The method includes: The first historical gap, the second historical gap, and historical welding parameters of each historical welding point are acquired. The first historical gap is acquired by a first historical acquisition device installed in the welding direction behind the historical welding equipment and located in front of the historical welding point. The second historical gap is acquired by a second historical acquisition device installed in the welding direction behind the historical welding equipment and located in the welding direction. The distance between the first historical acquisition device and the historical welding equipment is greater than the distance between the second historical acquisition device and the historical welding equipment. The historical welding parameters include at least welding temperature, welding length, welding current, and welding voltage. The prediction model is trained by processing the first historical gap, the second historical gap, and the historical welding parameters of each historical welding point in sequence. The input of the prediction model is the historical welding parameters of any historical welding point, and the output of the prediction model is the historical prediction difference between the first historical gap and the second historical gap of any historical welding point. While the welding equipment is welding the current welding point, the gap of the next welding point to be welded is determined by the first acquisition device. Determine the actual welding parameters of multiple welded points preceding the current weld point; The gap and all actual welding parameters are input into the prediction model, and the prediction difference output by the prediction model is obtained. The difference between the gap and the predicted difference is determined as the actual welding gap of the next welding point.

2. The method for determining the welding gap of a welding point according to claim 1, characterized in that, The historical welding parameters for each historical welding point include: When the historical welding equipment is welding the first welding point, the second welding point that the historical first acquisition equipment is currently acquiring is determined; The distance between the first welding point and the second welding point is determined as the target distance; Set a preset data window based on the target distance; For each historical welding point, the historical welding parameters of each welding point located before the historical welding point and within the preset data window are determined as the historical welding parameters corresponding to the historical welding point.

3. The method for determining the welding gap at a welding point according to claim 2, characterized in that, The prediction model is trained by processing the first historical gap, the second historical gap, and the historical welding parameters for each historical welding point in sequence, including: Abnormal welding points are removed from multiple historical welding points. Abnormal welding points refer to welding points that were welded when the welding equipment was vibrating. For each of the remaining historical welding points, the first historical gap and the second historical gap of the historical welding point are aligned to obtain the gap change of the historical welding point. For each of the remaining historical welding points, the prediction model is trained using the first historical gap, the second historical gap, and the historical welding parameters of each historical welding point.

4. The method for determining the welding gap at a welding point according to claim 3, characterized in that, The method further includes: After obtaining the gap variation of the historical welding point, the fixed parameters of the historical welding equipment and the dimensional parameters of the welding material are obtained, wherein the fixed parameters include the welding angle and bevel angle of the historical welding equipment; For each of the remaining historical welding points, the historical welding parameters for that historical welding point also include molten pool temperature, molten pool size, welding length, welding time, and welding speed. For each of the remaining historical welding points, the prediction model is trained using the fixed parameters, the size parameters, the historical welding parameters of the historical welding point, the first historical gap, and the second historical gap.

5. The method for determining the welding gap at a welding point according to claim 1, characterized in that, The first acquisition device is used to acquire the gap between the welding points to be welded at a preset distance from the current welding point when the welding device is welding the current welding point.

6. The method for determining the welding gap at a welding point according to claim 5, characterized in that, The determination of the actual welding parameters for multiple welded points preceding the current weld point includes: Set the data window according to the preset interval; The welding parameters of multiple welded points that have been welded before the current welding point and are located within the data window are determined as the actual welding parameters.

7. The method for determining the welding gap at a welding point according to claim 1, characterized in that, The method further includes: After determining the difference between the gap and the predicted difference as the actual welding gap of the next welding point, welding control parameters for the next welding point are generated based on the actual welding gap. The welding equipment is controlled to weld the next point to be welded according to the welding control parameters.

8. A processor, characterized in that, It is configured to perform the method for determining the weld gap of a weld point as described in any one of claims 1 to 7.

9. An apparatus for determining the welding gap at a welding point, characterized in that, include: The memory is configured to store instructions; as well as The processor according to claim 8.

10. A machine-readable storage medium, characterized in that, The machine-readable storage medium stores instructions for causing the machine to perform a method for determining the weld gap of a weld point according to any one of claims 1 to 7.

Images