Laser welding method and device

Abstract

The invention provides a laser welding method and device.The laser welding method comprises the steps that a shooting unit is controlled to obtain multiple frames of images of a part to be welded according to a shooting track; according to the pixel instantaneous movement speed and the pixel difference corresponding to the multiple frames of to-be-welded part images, motion information of the to-be-welded area is determined; the motion information and image information of the multiple frames of images of the to-be-welded part are sent into a pre-trained neural network, and a to-be-welded area of the to-be-welded part is determined; and the welding unit is controlled to weld the to-be-welded area according to the target welding track corresponding to the to-be-welded area. According to the invention, the welding alignment precision is improved.

Description

Technical Field

[0001] The invention relates to the technical field of laser welding, and in particular to a laser welding method and equipment. Background Art

[0002] Compared with traditional welding methods, laser welding has the characteristics of fast speed, large depth and small deformation; The automatic welding technology is that the user installs the parts to be welded into the laser welder, the laser welder identifies the weld seam, and then welds the parts to be welded; However, in high-precision welding, due to the high precision of workpiece assembly and small weld seam, the laser welder cannot accurately identify the weld seam and cannot perform automatic welding of high-precision parts to be welded. Summary of the invention

[0003] The purpose of the present invention is to provide a laser welding method and equipment, aiming to achieve accurate identification of welds.

[0004] The present invention provides a laser welding method, the method comprising: Controlling the shooting unit to obtain multiple frames of images of the workpiece to be welded according to the shooting trajectory; Confirming the motion information of the area to be welded according to the instantaneous moving speed of pixels and pixel differences corresponding to the multiple frames of images of the workpiece to be welded; Sending the motion information and the image information of the multiple frames of images of the workpiece to be welded into a pre-trained neural network to confirm the area to be welded of the workpiece to be welded; The welding unit is controlled to weld the area to be welded according to the target welding trajectory corresponding to the area to be welded.

[0005] In some embodiments, the workpiece to be welded is provided with a mark; and the laser welding method further comprises: Control the shooting unit to shoot the image of the workpiece to be welded, the image of the workpiece to be welded includes the mark; confirming an initial welding trajectory based on the mark, wherein the initial welding trajectory corresponds to the mark one by one; Based on the initial welding trajectory, a shooting trajectory is confirmed.

[0006] In some embodiments, the angle between the shooting trajectory and the trajectory to be initially welded is greater than or equal to 80 degrees and less than or equal to 100 degrees.

[0007] In some embodiments, before the step of controlling the shooting unit to acquire multiple frames of images of the workpiece to be welded according to the shooting trajectory, the method further includes: The turntable on which the parts to be welded are mounted is controlled to move to a target area so that the parts to be welded are located within the field of view of the shooting unit.

[0008] In some embodiments, each frame of the image of the workpiece to be welded includes a complete area to be welded; the method further includes: Obtain the instantaneous moving speed and pixel difference of the image of the workpiece to be welded in adjacent frames corresponding to the time from time T to time T+L, and obtain the instantaneous moving speed image and pixel difference image of the pixel corresponding to the time from time T to time T+L; Obtain the pixel instantaneous moving speed image and pixel difference image corresponding to time T+L+1; The step of sending the motion information and the image information of the multiple frames of images of the parts to be welded into a pre-trained neural network to confirm the areas to be welded of the parts to be welded includes: Based on the pixel instantaneous moving speed image and the pixel difference image from time T+1 to time T+L+1, confirm the area to be welded at time T+L+1; wherein the pixel instantaneous moving speed image and the pixel difference image from time T+1 to time T+L in this step are pre-stored; Repeat the steps of: obtaining the instantaneous pixel movement speed image and the pixel difference image corresponding to the T+L+1 moment; and the steps of: confirming the area to be welded at the T+L+1 moment based on the instantaneous pixel movement speed image and the pixel difference image from the T+1 moment to the T+L+1 moment; obtaining the area to be welded from the T+L+1 moment to the T+L+N moment; and fitting the final area to be welded according to the area to be welded from the T+L+1 moment to the T+L+N moment.

[0009] In some embodiments, the mark includes: a first part and a second part that are perpendicular to each other to align the horizontal axis and the vertical axis of the coordinate system; and the shape of the first part corresponds to different types of parts to be welded.

[0010] In some embodiments, the determining of the area to be welded at time T+L+1 based on the pixel instantaneous moving speed image and the pixel difference image from time T+1 to time T+L+1 includes: The instantaneous pixel moving speed image, the pixel difference image and the image to be welded at each moment from time T+1 to time T+L+1 are sent to a three-way parallel convolutional neural network; the outputs of the three-way parallel convolutional neural network are connected to a fully connected neural network, and the fully connected neural network outputs the spatial feature information from time T+1 to time T+L+1; In chronological order, the spatial feature information from time T+1 to time T+L+1 is sent to the time series neural network to obtain the spatiotemporal feature information; Based on the marks, a coordinate system is established; and according to the spatiotemporal characteristic information, the coordinate information of the area to be welded is determined.

[0011] In some embodiments, obtaining the pixel instantaneous moving speed image and the pixel difference image corresponding to the time T+L+1 includes: Based on the coordinate information of the area to be welded at the previous moment, determining the cutting area at the current moment, the cutting area includes the area to be welded, and the area of ​​the cutting area is at least twice the area of ​​the area to be welded; Generate a cropped image based on the cropped area, wherein the size of the cropped image at each moment is consistent; Based on the cropped image, the corresponding pixel instantaneous movement speed image and pixel difference image are generated.

[0012] In some embodiments, the method further comprises: Controlling the photographing unit to photograph an image of the welded part; and The welding result is confirmed based on the determined area to be welded and the welded image.

[0013] In some embodiments, the step of confirming the welding result based on the determined area to be welded and the welded image includes: aligning the welded image to the coordinate system based on the marking; Sending the image of the area to be welded and the image of the welded area corresponding to the coordinate information of the area to be welded into the twin neural network; The twin neural network outputs a welding result based on the similarity between the image of the area to be welded and the image of the welded area; when the similarity is greater than a preset threshold, the welding result is unwelded.

[0014] The present invention also provides a laser welding device, which comprises: Filming unit; Welding unit; and The control unit is connected to the photographing unit and the welding unit respectively, and the control unit is configured to execute a laser welding program to implement the above-mentioned laser welding method.

[0015] The present invention proposes a laser welding method and equipment, wherein the laser welding method controls a shooting unit to move and shoot multiple frames of images of a workpiece to be welded; obtains motion information of multiple frames of the images of the workpiece to be welded; and then accurately identifies the area to be welded of the workpiece to be welded according to the motion information and the image information of the images of the workpiece to be welded; thereby controlling the welding unit to weld the area to be welded with a target welding trajectory corresponding to the area to be welded. The present invention improves the accuracy of welding alignment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of the working process of a laser welding method according to an embodiment of the present invention; Figure 2It is a schematic diagram of marking of the parts to be welded according to the present invention; Figure 3 A schematic diagram of the working process of another embodiment of the laser welding method of the present invention; Figure 4 Schematic diagram of the neural network structure of the laser welding method of the present invention.

[0017] Figure numbers: weld: 10; mark: 20. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] The present invention provides a laser welding method, which is applicable to laser welding equipment. The laser welding equipment may include: a loading position, a welding position and a unloading position; wherein the loading position and the loading position may be realized by a turntable, and the material is continuously sent to the welding position by the turntable, and after the welding is completed and the detection is passed, the material is sent to the unloading position by the turntable. The above process can be performed during the movement of the product.

[0020] Reference Figure 1 In some embodiments, the laser welding method includes: S100, controlling the shooting unit to obtain multiple frames of images of the workpiece to be welded according to the shooting trajectory; S200, confirming the motion information of the area to be welded according to the instantaneous moving speed and pixel difference of the pixels corresponding to the multiple frames of images of the parts to be welded; S300, sending the motion information and the image information of the multiple frames of the images of the parts to be welded into the pre-trained neural network to confirm the area to be welded of the parts to be welded; S400, controlling the welding unit to weld the area to be welded according to the target welding trajectory corresponding to the area to be welded.

[0021] Before step S100, it also includes: controlling the turntable on which the parts to be welded are installed to move to the target area so that the parts to be welded are located within the field of view of the shooting unit. During the rotation of the turntable, when the turntable delivers the parts to be welded into the target area, the turntable is controlled to stop rotating, and then the shooting unit continuously shoots the target area to obtain multiple frames of images of the parts to be welded. In order to accurately identify the position of the weld 10, the shooting device can be controlled to dynamically shoot the parts to be welded. At this time, in the multiple frames of images of the parts to be welded, the weld 10 is in motion. In the adjacent frames of the images of the parts to be welded, the pixel difference represents the movement of the weld 10, and the instantaneous moving speed of the pixel also represents the position change of the weld 10.

[0022] In this embodiment, the shooting unit can be implemented using an imaging device and a three-axis gimbal or a two-axis gimbal. The control unit controls the gimbal to rotate the imaging device along a preset trajectory to shoot multiple frames of images of the workpiece to be welded.

[0023] In step S200, the instantaneous moving speed of a pixel refers to the instantaneous moving speed of a same pixel point or pixel block between two frames of images of the workpiece to be welded, which can be calculated by the position change of the pixel point or pixel block and the shooting time interval of the two frames of images of the workpiece to be welded. The pixel difference refers to the difference in pixel values ​​between pixels at corresponding positions between two frames of images of the workpiece to be welded.

[0024] In practical applications, the motion information can be represented by a pixel instantaneous moving speed image and a pixel difference image, and the image information of the image of the workpiece to be welded can be represented by the image of the workpiece to be welded.

[0025] In step S300, the pixel instantaneous movement speed image, the pixel difference image and the image of the workpiece to be welded can be sent to a parallel convolutional neural network to output three feature vectors, which are then fused by a fully connected neural network to obtain spatial feature information. The spatial feature information is then sent to a timing neural network in chronological order to obtain the area to be welded, i.e., the weld 10.

[0026] In S400, after the weld 10 is accurately identified and the trajectory and coordinate information of the weld 10 are confirmed, the robot arm equipped with the laser welding device is controlled to work so that the laser welding device moves along the weld 10, thereby welding the weld 10. Compared with the initial welding trajectory, the target welding trajectory eliminates the positional offset caused by the placement of the parts to be welded.

[0027] The laser welding equipment proposed in the present invention controls the shooting unit to move and shoot multiple frames of images of the workpiece to be welded; obtains motion information of the multiple frames of the images of the workpiece to be welded; and then accurately identifies the area to be welded of the workpiece to be welded according to the motion information and the image information of the images of the workpiece to be welded; thereby controlling the welding unit to weld the area to be welded with the target welding trajectory corresponding to the area to be welded. The present invention improves the accuracy of welding alignment.

[0028] Reference Figure 2 In some embodiments, the workpiece to be welded is provided with a mark 20; the laser welding method further comprises: controlling the photographing unit to photograph an image of the workpiece to be welded, the image of the workpiece to be welded comprising the mark 20; confirming the initial welding trajectory based on the mark 20, wherein the initial welding trajectory corresponds to the mark 20 one by one; Based on the initial welding trajectory, a shooting trajectory is confirmed.

[0029] It should be noted that the weld 10 is elongated. In order to better identify the weld 10, the shooting trajectory is preferably moved in the vertical direction of the weld 10. In practical applications, the angle between the shooting trajectory and the initial welding trajectory can be set to be greater than or equal to 80 degrees and less than or equal to 100 degrees. Therefore, in order to determine the shooting trajectory, this embodiment first captures the image of the workpiece to be welded, and then identifies the mark 20. The mark 20 can indicate the initial welding trajectory, and then the shooting trajectory can be confirmed.

[0030] For example, the mark 20 may represent the placement direction of the parts to be welded and the types of the parts to be welded, and the laser welding equipment may pre-store the initial welding trajectory corresponding to the types of the parts to be welded.

[0031] Reference Figure 2 The mark 20 includes a first part and a second part which are perpendicular to each other to align the horizontal axis and the vertical axis of the coordinate system; and the shape of the first part corresponds to different types of parts to be welded.

[0032] For example, the first part is in the shape of a letter "I", indicating that the initial welding trajectory of the welded parts is a straight line. The first part is in the shape of an "o", indicating that the initial welding trajectory of the welded parts is a ring, that is, welding is performed around the target area.

[0033] Exemplarily, the number of the marks 20 is four, which are respectively located at the four corners of the weldment to meet the requirements of establishing a coordinate system.

[0034] Reference Figure 3 The present application also proposes a motion information extraction method suitable for laser welding equipment, which can greatly reduce the amount of calculation while meeting the accuracy requirements.

[0035] Specifically, each frame of the image of the workpiece to be welded includes a complete area to be welded; the method further includes: S500, acquiring the instantaneous pixel movement speed and pixel difference of the image of the workpiece to be welded in adjacent frames corresponding to the time from time T to time T+L, and obtaining the instantaneous pixel movement speed image and pixel difference image corresponding to the time from time T to time T+L; S600, obtaining a pixel instantaneous moving speed image and a pixel difference image corresponding to time T+L+1; Step S300, sending the motion information and the image information of multiple frames of the to-be-welded parts to a pre-trained neural network to confirm the to-be-welded area of ​​the to-be-welded parts, including: S301, based on the pixel instantaneous moving speed image and the pixel difference image from time T+1 to time T+L+1, confirm the area to be welded at time T+L+1; wherein the pixel instantaneous moving speed image and the pixel difference image from time T+1 to time T+L in this step are pre-stored; Repeat the steps of: obtaining the instantaneous pixel movement speed image and the pixel difference image corresponding to the T+L+1 moment; and the steps of: confirming the area to be welded at the T+L+1 moment based on the instantaneous pixel movement speed image and the pixel difference image from the T+1 moment to the T+L+1 moment; obtaining the area to be welded from the T+L+1 moment to the T+L+N moment; and fitting the final area to be welded according to the area to be welded from the T+L+1 moment to the T+L+N moment.

[0036] In this embodiment, each pixel instantaneous moving speed and pixel difference has a numerical value, and by replacing them with pixel values, a corresponding image can be obtained.

[0037] In order to obtain the area to be welded at the current moment, this embodiment uses the instantaneous pixel movement speed image and the pixel difference image of the previous L moments; in order to reduce the amount of calculation, the instantaneous pixel movement speed image and the pixel difference image of the previous L moments are pre-stored rather than calculated in real time.

[0038] In other words, as time goes by, in the process of continuously generating the area to be welded at the current moment, it is only necessary to calculate the instantaneous pixel movement speed image and pixel difference image at each moment, and then reuse the instantaneous pixel movement speed image and pixel difference image calculated at the previous L moments.

[0039] Reference Figure 3, further, the mark 20 includes: a first part and a second part that are perpendicular to each other to align the horizontal axis and the vertical axis of the coordinate system; and the shape of the first part corresponds to different types of parts to be welded; step S301, based on the pixel instantaneous movement speed image and the pixel difference image from time T+1 to time T+L+1, confirming the area to be welded at time T+L+1, includes: S3011, sending the instantaneous pixel moving speed image, the pixel difference image and the image to be welded at each moment from time T+1 to time T+L+1 to a three-way parallel convolutional neural network; the outputs of the three-way parallel convolutional neural network are connected to a fully connected neural network, and the fully connected neural network outputs the spatial feature information from time T+1 to time T+L+1; S3012, in chronological order, sending the spatial feature information from time T+1 to time T+L+1 to the time series neural network to obtain spatiotemporal feature information; S3013, establishing a coordinate system based on the mark 20; and determining the coordinate information of the area to be welded according to the spatiotemporal feature information.

[0040] The neural network architecture proposed in this application is as follows Figure 4 As shown, the instantaneous pixel moving speed image, pixel difference image and image to be welded at each moment are sent to their respective convolutional neural networks for feature extraction to obtain three-way feature maps, which are then flattened into feature vectors by the flattening layer, and finally the three-way feature vectors are concatenated and sent to the fully connected neural network to output spatial feature information. In this embodiment, the convolution kernel size of the convolutional neural network decreases successively.

[0041] Then, in chronological order, the spatial feature information is fed into the time series neural network, and the features output at each moment include time information and spatial information, so it is called spatiotemporal feature information. Exemplarily, the time series neural network of this embodiment is preferably an LSTM network or a GRU network.

[0042] Finally, a coordinate system is established based on the mark 20, and then the coordinates of the weld 10 are confirmed based on the spatiotemporal characteristic information.

[0043] In this embodiment, a coordinate system is established based on the mark 20, so that the parts to be welded can be placed arbitrarily, and the position of the weld 10 in the coordinate system can be identified.

[0044] In some embodiments, step S600, obtaining the instantaneous pixel movement speed image and the pixel difference image corresponding to the time T+L+1, includes: Based on the coordinate information of the area to be welded at the previous moment, the cutting area at the current moment is determined, and the area of ​​the cutting area is at least twice the area of ​​the area to be welded.

[0045] Generate a cropped image based on the cropped area, wherein the size of the cropped image at each moment is consistent; Based on the cropped image, the corresponding pixel instantaneous movement speed image and pixel difference image are generated.

[0046] In this embodiment, the size of the cropped image at each moment is consistent, so the pixel instantaneous motion velocity image and the pixel difference image extraction model can be trained based on the cropped images of the training data. Then, in actual applications, it is only necessary to feed the cropped image into the extraction model to obtain the pixel instantaneous motion velocity image and the pixel difference image, thereby effectively reducing the amount of calculation.

[0047] In some embodiments, the laser welding method further includes: controlling the photographing unit to photograph an image of the welded part; and confirming the welding result based on the determined area to be welded and the welded image.

[0048] In this embodiment, the welding result can be confirmed by a traditional neural network based on the determined area to be welded and the welded image. However, in order to reduce the amount of calculation, and because the difference between the image to be welded and the welded image is only in the welding area, a twin network is used to judge the welding effect, which has a small amount of calculation and sufficient accuracy.

[0049] Therefore, the step of confirming the welding result based on the determined area to be welded and the welded image includes: aligning the welded image to the coordinate system based on the marking 20; Sending the image of the area to be welded and the image of the welded area corresponding to the coordinate information of the area to be welded into the twin neural network; The twin neural network outputs a welding result based on the similarity between the image of the area to be welded and the image of the welded area; when the similarity is greater than a preset threshold, the welding result is unwelded.

[0050] In practical applications, the twin network can calculate the similarity of two input images (the image of the area to be welded and the image of the welded area). When the similarity is greater than the preset threshold, the twin network can determine that it is not welded. When the similarity is less than the preset threshold, the twin network can determine that it is welded. The welding results are output: unwelded and welded.

[0051] Example 2 The present application also proposes a laser welding device, which includes: a shooting unit, a welding unit, and a control unit, the control unit is connected to the shooting unit and the welding unit respectively, and the control unit is configured to execute a laser welding program to implement the above-mentioned laser welding method. In some embodiments, the laser welding method includes: S100, controlling the shooting unit to acquire multiple frames of images of the workpiece to be welded according to a shooting trajectory; S200, confirming the motion information of the area to be welded according to the instantaneous moving speed and pixel difference of the pixels corresponding to the multiple frames of the images of the parts to be welded; S300, sending the motion information and the image information of multiple frames of images of the workpiece to be welded into a pre-trained neural network to confirm the area to be welded of the workpiece to be welded; S400, controlling the welding unit to weld the area to be welded according to a target welding trajectory corresponding to the area to be welded.

[0052] In some embodiments, the workpiece to be welded is provided with a mark 20, and the laser welding method further comprises: Controlling the photographing unit to photograph the image of the workpiece to be welded, wherein the image of the workpiece to be welded includes the mark 20; confirming the initial welding trajectory based on the mark 20, wherein the initial welding trajectory corresponds to the mark 20 one by one; Based on the initial welding trajectory, a shooting trajectory is confirmed.

[0053] In some embodiments, the mark 20 includes a first portion and a second portion that are perpendicular to each other so as to align the horizontal axis and the vertical axis of the coordinate system; and the shape of the first portion corresponds to different types of parts to be welded.

[0054] In some embodiments, the number of the marks 20 is four, which are respectively located at the four corners of the weldment to meet the requirements of establishing a coordinate system.

[0055] In some embodiments, the method further comprises: S500, acquiring the instantaneous pixel movement speed and pixel difference of the image of the workpiece to be welded in adjacent frames corresponding to the time from time T to time T+L, and obtaining the instantaneous pixel movement speed image and pixel difference image corresponding to the time from time T to time T+L; S600, obtaining a pixel instantaneous moving speed image and a pixel difference image corresponding to time T+L+1; Step S300, sending the motion information and the image information of multiple frames of the to-be-welded parts to a pre-trained neural network to confirm the to-be-welded area of ​​the to-be-welded parts, including: S301, based on the pixel instantaneous moving speed image and the pixel difference image from time T+1 to time T+L+1, confirm the area to be welded at time T+L+1; wherein the pixel instantaneous moving speed image and the pixel difference image from time T+1 to time T+L in this step are pre-stored; Repeat the steps of: obtaining the instantaneous pixel movement speed image and the pixel difference image corresponding to the T+L+1 moment; and the steps of: confirming the area to be welded at the T+L+1 moment based on the instantaneous pixel movement speed image and the pixel difference image from the T+1 moment to the T+L+1 moment; obtaining the area to be welded from the T+L+1 moment to the T+L+N moment; and fitting the final area to be welded according to the area to be welded from the T+L+1 moment to the T+L+N moment.

[0056] In some embodiments, the mark 20 includes: a first part and a second part that are perpendicular to each other to align the horizontal axis and the vertical axis of the coordinate system; and the shape of the first part corresponds to different types of parts to be welded; step S301, based on the pixel instantaneous movement speed image and the pixel difference image from time T+1 to time T+L+1, confirming the area to be welded at time T+L+1, includes: S3011, sending the instantaneous pixel moving speed image, the pixel difference image and the image to be welded at each moment from time T+1 to time T+L+1 to a three-way parallel convolutional neural network; the outputs of the three-way parallel convolutional neural network are connected to a fully connected neural network, and the fully connected neural network outputs the spatial feature information from time T+1 to time T+L+1; S3012, in chronological order, sending the spatial feature information from time T+1 to time T+L+1 to the time series neural network to obtain spatiotemporal feature information; S3013, establishing a coordinate system based on the mark 20; and determining the coordinate information of the area to be welded according to the spatiotemporal feature information.

[0057] In some embodiments, step S600, obtaining the instantaneous pixel movement speed image and the pixel difference image corresponding to the time T+L+1, includes: Based on the coordinate information of the area to be welded at the previous moment, the cutting area at the current moment is determined, and the area of ​​the cutting area is at least twice the area of ​​the area to be welded.

[0058] Generate a cropped image based on the cropped area, wherein the size of the cropped image at each moment is consistent; Based on the cropped image, the corresponding pixel instantaneous movement speed image and pixel difference image are generated.

[0059] In some embodiments, the control unit is further configured to: Controlling the photographing unit to photograph an image of the welded part; and The welding result is confirmed based on the determined area to be welded and the welded image.

[0060] In some embodiments, the step of confirming the welding result based on the determined area to be welded and the welded image includes: aligning the welded image to the coordinate system based on the marking 20; Sending the image of the area to be welded and the image of the welded area corresponding to the coordinate information of the area to be welded into the twin neural network; The twin neural network outputs a welding result based on the similarity between the image of the area to be welded and the image of the welded area; when the similarity is greater than a preset threshold, the welding result is unwelded.

[0061] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0062] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A laser welding method, characterized in that: The method comprises: Controlling the shooting unit to obtain multiple frames of images of the workpiece to be welded according to the shooting trajectory; Confirming the motion information of the area to be welded according to the instantaneous moving speed of pixels and pixel differences corresponding to the multiple frames of images of the workpiece to be welded; Sending the motion information and the image information of the multiple frames of images of the workpiece to be welded into a pre-trained neural network to confirm the area to be welded of the workpiece to be welded; The welding unit is controlled to weld the area to be welded according to the target welding trajectory corresponding to the area to be welded.

2. The laser welding method according to claim 1, characterized in that: The workpiece to be welded is provided with a mark; the laser welding method further comprises: Control the shooting unit to shoot the image of the workpiece to be welded, the image of the workpiece to be welded includes the mark; confirming an initial welding trajectory based on the mark, wherein the initial welding trajectory corresponds to the mark one by one; Based on the initial welding trajectory, a shooting trajectory is confirmed.

3. The laser welding method according to claim 2, characterized in that: The angle between the shooting track and the track to be initially welded is greater than or equal to 80 degrees and less than or equal to 100 degrees.

4. The laser welding method according to claim 3, characterized in that: Before the step of controlling the shooting unit to acquire multiple frames of images of the workpiece to be welded according to the shooting trajectory, the method further includes: The turntable on which the parts to be welded are mounted is controlled to move to a target area so that the parts to be welded are located within the field of view of the shooting unit.

5. The laser welding method according to any one of claims 2 to 4, characterized in that: Each frame of the image of the workpiece to be welded includes a complete area to be welded; the method further includes: Obtain the instantaneous moving speed and pixel difference of the image of the workpiece to be welded in adjacent frames corresponding to the time from time T to time T+L, and obtain the instantaneous moving speed image and pixel difference image of the pixel corresponding to the time from time T to time T+L; Obtain the pixel instantaneous moving speed image and pixel difference image corresponding to time T+L+1; The step of sending the motion information and the image information of the multiple frames of images of the parts to be welded into a pre-trained neural network to confirm the areas to be welded of the parts to be welded includes: Based on the pixel instantaneous moving speed image and the pixel difference image from time T+1 to time T+L+1, confirm the area to be welded at time T+L+1; wherein the pixel instantaneous moving speed image and the pixel difference image from time T+1 to time T+L in this step are pre-stored; Repeat the steps of: obtaining the instantaneous pixel movement speed image and the pixel difference image corresponding to the T+L+1 moment; and the steps of: confirming the area to be welded at the T+L+1 moment based on the instantaneous pixel movement speed image and the pixel difference image from the T+1 moment to the T+L+1 moment; obtaining the area to be welded from the T+L+1 moment to the T+L+N moment; and fitting the final area to be welded according to the area to be welded from the T+L+1 moment to the T+L+N moment.

6. The laser welding method according to claim 5, characterized in that: The mark includes: a first part and a second part that are perpendicular to each other to align the horizontal axis and the vertical axis of the coordinate system; and the shape of the first part corresponds to different types of parts to be welded; the pixel instantaneous movement speed image and the pixel difference image from time T+1 to time T+L+1 are used to confirm the area to be welded at time T+L+1, including: The instantaneous pixel moving speed image, the pixel difference image and the image to be welded at each moment from time T+1 to time T+L+1 are sent to a three-way parallel convolutional neural network; the outputs of the three-way parallel convolutional neural network are connected to a fully connected neural network, and the fully connected neural network outputs the spatial feature information from time T+1 to time T+L+1; In chronological order, the spatial feature information from time T+1 to time T+L+1 is sent to the time series neural network to obtain the spatiotemporal feature information; Based on the marks, a coordinate system is established; and according to the spatiotemporal characteristic information, the coordinate information of the area to be welded is determined.

7. The laser welding method according to claim 6, characterized in that: Obtain the instantaneous pixel moving speed image and pixel difference image corresponding to the time T+L+1, including: Based on the coordinate information of the area to be welded at the previous moment, determining the cutting area at the current moment, the cutting area includes the area to be welded, and the area of ​​the cutting area is at least twice the area of ​​the area to be welded; Generate a cropped image based on the cropped area, wherein the size of the cropped image at each moment is consistent; Based on the cropped image, the corresponding pixel instantaneous movement speed image and pixel difference image are generated.

8. The laser welding method according to claim 6, characterized in that: The method further comprises: Controlling the photographing unit to photograph an image of the welded part; and The welding result is confirmed based on the determined area to be welded and the welded image.

9. The laser welding method according to claim 8, characterized in that: The step of confirming the welding result based on the determined area to be welded and the welded image includes: aligning the welded image to the coordinate system based on the marking; Sending the image of the area to be welded and the image of the welded area corresponding to the coordinate information of the area to be welded into the twin neural network; The twin neural network outputs a welding result based on the similarity between the image of the area to be welded and the image of the welded area; when the similarity is greater than a preset threshold, the welding result is unwelded.

10. A laser welding device, characterized in that: include: Filming unit; Welding unit; as well as A control unit is connected to the shooting unit and the welding unit respectively, and the control unit is configured to execute a laser welding program to implement the laser welding method according to any one of claims 1 to 9.

Images