A soldering control method and related equipment for complex structure welds

Abstract

The present invention provides a soldering control method for complex structure welds, including: obtaining a two-dimensional surface image and a three-dimensional scanning image of a workpiece to be welded; performing weld recognition processing on the two-dimensional surface image and / or the three-dimensional scanning image to obtain a first weld path of the workpiece to be welded and a path complexity corresponding to the first weld path; if the path complexity is greater than a preset path complexity threshold, then based on the two-dimensional surface image, the three-dimensional scanning image and the soldering characteristics of the workpiece to be welded, a second weld path is determined on the basis of the first weld path; based on the second weld path, control parameters of an automatic soldering machine are determined, and the control parameters are used to control the automatic soldering machine to solder the workpiece to be welded. The present invention solves the problem of the existing welding method's rapid conversion of heterogeneous products with different welding processes, poor adaptability and low welding efficiency, and can provide users with an efficient soldering control experience and improve welding work efficiency.

Description

Technical Field

[0001] The invention relates to the technical field of welding, and in particular to a soldering control method for complex structure welds and related equipment. Background Art

[0002] With the development of modern industry, the requirements for product diversification and quality are constantly increasing. The digitization, automation and intelligence of the welding process are the inevitable trend of future development. In the home appliance industries such as air conditioners, refrigerators, and water heaters, cooling pipes, exhaust pipes, capillaries, process pipes and other pipes are generally welded by flame brazing. Traditional manual flame brazing faces problems such as low production efficiency, unstable welding quality and high labor costs. Robotic flame brazing equipment has the advantages of high efficiency, stable welding quality, reliable operation and strong versatility. It can greatly improve the welding production level and improve the welding health and safety conditions, and has received much attention from the home appliance industry.

[0003] In the actual welding process, the home appliance industry needs to weld a lot of pipe parts, but each pipe part has different shapes and structures, and the welding position and welding process are also different. Therefore, the usual robot flame brazing equipment can only weld a single product, and cannot achieve the rapid conversion of heterogeneous products with different welding processes, resulting in poor adaptability and low welding efficiency. Summary of the invention

[0004] The embodiment of the present invention provides a soldering control method for complex structure welds, aiming to solve the problem of poor adaptability and low welding efficiency of the existing welding method for the rapid conversion of heterogeneous products with different welding processes. By acquiring a two-dimensional surface image and a three-dimensional scanning image of a workpiece to be welded, and performing weld recognition processing on the two-dimensional surface image and / or the three-dimensional scanning image, a first weld path of the workpiece to be welded and a path complexity corresponding to the first weld path are obtained. When the path complexity is greater than a preset path complexity threshold, and based on the two-dimensional surface image, the three-dimensional scanning image and the soldering characteristics of the workpiece to be welded, a second weld path is determined on the basis of the first weld path, and the second weld path is used to determine the control parameters of an automatic soldering machine, and the control parameters are used to control the automatic soldering machine to solder the workpiece to be welded, which solves the problem of poor adaptability and low welding efficiency of the existing welding method for the rapid conversion of heterogeneous products with different welding processes, and can provide users with an efficient soldering control experience and improve welding work efficiency.

[0005] In a first aspect, an embodiment of the present invention provides a soldering control method for a complex structure weld, the method comprising:

[0006] Obtain 2D surface images and 3D scanning images of the workpiece to be welded;

[0007] Performing weld recognition processing on the two-dimensional surface image and / or the three-dimensional scanned image to obtain a first weld path of the workpiece to be welded and a path complexity corresponding to the first weld path;

[0008] If the path complexity is greater than a preset path complexity threshold, a second weld path is determined based on the two-dimensional surface image, the three-dimensional scanned image and the soldering characteristics of the workpiece to be welded, and on the basis of the first weld path, the second weld path is at least one target stress point;

[0009] Based on the second weld path, control parameters of an automatic soldering machine are determined, and the control parameters are used to control the automatic soldering machine to solder the workpiece to be welded.

[0010] Optionally, the step of performing weld recognition processing on the two-dimensional surface image and / or the three-dimensional scanned image to obtain a first weld path of the workpiece to be welded and a path complexity corresponding to the first weld path includes:

[0011] Performing weld seam recognition processing on the two-dimensional surface image and / or the three-dimensional scanning image to obtain a first weld seam path of the workpiece to be welded;

[0012] The path complexity of the first weld path is estimated based on the path straightness to obtain the path complexity corresponding to the first weld path, and the path straightness is negatively correlated with the path complexity.

[0013] Optionally, the step of estimating the path complexity of the first weld path based on the path straightness to obtain the path complexity corresponding to the first weld path includes:

[0014] The first weld path is segmented into straight segments, oblique straight segments, and arc segments to obtain segmented paths of the first weld path, wherein the straight segment is straight with the X-axis of the automatic soldering machine, the oblique straight segment has an angle with the X-axis of the automatic soldering machine, and the arc segment has an arc, and different types of segmented paths correspond to different path straightness;

[0015] Based on the path straightness corresponding to the type of the segmented path, a path complexity estimation is performed on the first weld path to obtain the path complexity corresponding to the first weld path.

[0016] Optionally, the step of estimating the path complexity of the first weld path based on the path straightness corresponding to the type of the segmented path to obtain the path complexity corresponding to the first weld path includes:

[0017] Based on the path straightness corresponding to the type of the segmented path, the path complexity of the first weld path is estimated by a preset complexity estimation formula to obtain the path complexity corresponding to the first weld path;

[0018] The complexity estimation formula is:

[0019]

[0020] Among them, C represents the path complexity, N represents the number of straight segments, T represents the number of oblique straight segments, M represents the number of arc segments, S n represents the nth straight segment, D(S n -S n-1 ) represents the number of segmented paths between the nth straight segment and the n-1th straight segment; L n represents the length of the nth straight segment, S t represents the tth oblique straight segment, θ t represents the angle between the tth oblique straight segment and the X-axis of the automatic soldering machine, L t represents the length of the tth oblique straight segment, D(S t -S t-1 ) represents the number of segmented paths between the t-th oblique straight segment and the t-1-th oblique straight segment; S m represents the mth oblique straight segment, L m represents the arc length of the mth arc segment, S rad,m represents the arc length of the mth arc segment, r m represents the radius corresponding to the mth arc segment, D(S m -S m-1 ) represents the number of segmented paths between the mth oblique straight segment and the m-1th arc segment.

[0021] Optionally, if the path complexity is greater than a preset path complexity threshold, the step of determining a second weld path based on the first weld path based on the two-dimensional surface image, the three-dimensional scanned image and the soldering characteristics of the workpiece to be welded comprises:

[0022] If the path complexity is greater than a preset path complexity threshold, then obtaining the soldering characteristics of the workpiece to be welded;

[0023] Performing first feature point extraction processing on the two-dimensional surface image by using a first stress feature point extraction model to obtain first stress feature point distribution data, wherein the first stress feature point extraction model is obtained by training with a two-dimensional sample image and stress point annotation data of the two-dimensional sample image;

[0024] Performing second feature point extraction processing on the three-dimensional scanned image by using a second stress feature point extraction model to obtain second stress feature point distribution data, wherein the second stress feature point extraction model is obtained by training the three-dimensional sample image and the stress point annotation data of the three-dimensional sample image;

[0025] Based on the soldering characteristics of the workpiece to be welded, the first stress characteristic point distribution data and the second stress characteristic point distribution data, a second weld path is determined on the basis of the first weld path.

[0026] Optionally, the step of determining a second weld path based on the soldering characteristics of the workpiece to be welded, the first stress characteristic point distribution data, and the second stress characteristic point distribution data on the basis of the first weld path includes:

[0027] Mapping the first stress characteristic point and the second stress characteristic point onto the first weld path;

[0028] Based on the soldering characteristics of the workpiece to be welded, performing soldering simulation on the first weld path to obtain a soldering simulation path, wherein the soldering simulation path includes a simulated stress point distribution;

[0029] Based on the strain energy value of the simulated stress point, the simulated stress point whose strain energy value is greater than a strain energy threshold is selected as a target stress point;

[0030] The target stress point is fitted into the first weld path to obtain the second weld path.

[0031] Optionally, the step of determining the control parameters of the automatic soldering machine based on the second weld path includes:

[0032] Performing parameter configuration on the second weld path to obtain soldering path control parameters corresponding to the second weld path;

[0033] Performing parameter correction on the target stress point in the second weld path to obtain a soldering point control parameter corresponding to the target stress point;

[0034] Based on the soldering point control parameters, the soldering path control parameters are corrected to obtain the control parameters of the automatic soldering machine.

[0035] In a second aspect, an embodiment of the present invention further provides a soldering control device for a complex structure weld, the soldering control device for a complex structure weld comprising:

[0036] An acquisition module, used to acquire a two-dimensional surface image and a three-dimensional scanning image of the workpiece to be welded;

[0037] A processing module, used for performing weld seam recognition processing on the two-dimensional surface image and / or the three-dimensional scanned image to obtain a first weld seam path of the workpiece to be welded and a path complexity corresponding to the first weld seam path;

[0038] A first determination module is used to determine a second weld path based on the first weld path, based on the two-dimensional surface image, the three-dimensional scanning image and the soldering characteristics of the workpiece if the path complexity is greater than a preset path complexity threshold, and the second weld path has at least one target stress point;

[0039] The second determination module is used to determine the control parameters of the automatic soldering machine based on the second weld path, and the control parameters are used to control the automatic soldering machine to solder the workpiece to be welded.

[0040] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the soldering control method for complex structure welds provided in an embodiment of the present invention are implemented.

[0041] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the soldering control method for complex structure welds provided in an embodiment of the invention are implemented.

[0042] In an embodiment of the present invention, a two-dimensional surface image and a three-dimensional scanning image of a workpiece to be welded are obtained; weld recognition processing is performed on the two-dimensional surface image and / or the three-dimensional scanning image to obtain a first weld path of the workpiece to be welded and a path complexity corresponding to the first weld path; if the path complexity is greater than a preset path complexity threshold, then based on the two-dimensional surface image, the three-dimensional scanning image and the soldering characteristics of the workpiece to be welded, a second weld path is determined on the basis of the first weld path, and the second weld path has at least one target stress point; based on the second weld path, control parameters of an automatic soldering machine are determined, and the control parameters are used to control the automatic soldering machine to solder the workpiece to be welded. The present invention performs weld recognition processing on a two-dimensional surface image and / or a three-dimensional scanning image of a workpiece to be welded, thereby obtaining a first weld path of the workpiece to be welded and a path complexity corresponding to the first weld path. When the path complexity is greater than a preset path complexity threshold, and based on the two-dimensional surface image, the three-dimensional scanning image and the soldering characteristics of the workpiece to be welded, a second weld path is determined on the basis of the first weld path, and the second weld path is used to determine control parameters of an automatic soldering machine. The control parameters are used to control the automatic soldering machine to solder the workpiece to be welded, which solves the problems of rapid conversion of heterogeneous products with different welding processes, poor adaptability and low welding efficiency of existing welding methods, and can provide users with an efficient soldering control experience and improve welding work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 It is a flow chart of a soldering control method for a complex structure weld provided by an embodiment of the present invention;

[0045] Figure 2 It is a structural schematic diagram of a soldering control device for a weld of a complex structure provided by an embodiment of the present invention;

[0046] Figure 3 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] 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.

[0048] like Figure 1 As shown, Figure 1 The following is a method flow chart of a soldering control method for a complex structure weld provided by an embodiment of the present invention. The soldering control method for a complex structure weld comprises the following steps:

[0049] 101. Obtain a two-dimensional surface image and a three-dimensional scanning image of the workpiece to be welded.

[0050] In an embodiment of the present invention, the above-mentioned soldering control method for complex structure welds can be deployed in an electronic device, and the above-mentioned electronic device can be a server, a gateway device or a user's terminal device, etc. The above-mentioned soldering control method for complex structure welds is used in home appliance industries such as air conditioners, refrigerators, and water heaters.

[0051] The above-mentioned parts to be welded refer to objects that need to be connected or repaired during the welding process, and can be parts, components or equipment made of metal, plastic or other materials.

[0052] The above two-dimensional surface image can be understood as a two-dimensional projection image of the surface of the workpiece to be welded, which can be obtained by a camera or other optical equipment. The two-dimensional surface image can show the shape, size, position and other information of the workpiece to be welded.

[0053] The above-mentioned 3D scanning image can be an image obtained by 3D scanning the workpiece to be welded by a laser scanner or other equipment. The 3D scanning image can provide more comprehensive information, including the 3D shape, size, surface texture, etc. of the workpiece to be welded.

[0054] 102. Perform weld recognition processing on the two-dimensional surface image and / or the three-dimensional scanning image to obtain a first weld path of the workpiece to be welded and a path complexity corresponding to the first weld path.

[0055] In an embodiment of the present invention, the two-dimensional surface image and / or the three-dimensional scanning image can be analyzed and identified through image processing technology and machine learning algorithms to extract information such as the position, shape and direction of the weld, thereby obtaining the first weld path of the workpiece to be welded.

[0056] The above-mentioned weld seam recognition process can be understood as a process of analyzing and recognizing a two-dimensional surface image and / or a three-dimensional scanning image to extract information such as the position, shape and direction of the weld seam.

[0057] The above path complexity can be understood as the complexity of the weld path in space, which can be described by calculating parameters such as the curve length and curvature of the weld path.

[0058] Furthermore, the two-dimensional surface image and / or the three-dimensional scanning image can be processed for weld identification to obtain the first weld path of the workpiece to be welded, and the path straightness is used to estimate the path complexity of the first weld path to obtain the path complexity corresponding to the first weld path. The above-mentioned path straightness is negatively correlated with the path complexity. A quantitative analysis method, such as a curve model, curve segmentation, curve similarity and other algorithms, can be used to estimate the path complexity of the first weld path using the path straightness to obtain the path complexity corresponding to the first weld path.

[0059] 103. If the path complexity is greater than a preset path complexity threshold, a second weld path is determined based on the first weld path based on the two-dimensional surface image, the three-dimensional scanning image and the soldering characteristics of the workpiece to be welded.

[0060] In an embodiment of the present invention, the second weld path includes at least one target stress point. The stress point can be understood as an area where stress concentration occurs during welding.

[0061] The above-mentioned preset path complexity threshold is a pre-set path complexity threshold, which can be a path complexity threshold set according to the requirements and experience of the welding process.

[0062] The soldering characteristics of the above-mentioned parts to be welded can be understood as the characteristic properties of the welding objects in terms of material properties, physical properties and chemical properties. The soldering characteristics of the parts to be welded have an important influence on the stability of the welding process and the quality of welding. For example, factors such as the material type, surface state, oxide film condition, temperature change and other factors of the parts to be welded will affect the welding effect.

[0063] Furthermore, if the path complexity corresponding to the first weld path is greater than a preset path complexity threshold, the soldering characteristics of the workpiece to be welded can be obtained, and the first feature point extraction process is performed on the two-dimensional surface image through the first stress feature point extraction model to obtain the first stress feature point distribution data, and the second feature point extraction process is performed on the three-dimensional scanning image through the second stress feature point extraction model to obtain the second stress feature point distribution data, and according to the soldering characteristics of the workpiece to be welded, the first stress feature point distribution data and the second stress feature point distribution data, the second weld path is determined on the basis of the first weld path.

[0064] The first stress feature point extraction model is obtained by training with two-dimensional sample images and stress point annotation data of the two-dimensional sample images; the second stress feature point extraction model is obtained by training with three-dimensional sample images and stress point annotation data of the three-dimensional sample images. The training process can be supervised training, which is a training method whose core is to use a set of data with known labels to train the model, and optimize the model parameters so that the model can predict the labels of new data or make decisions based on the characteristics of existing data.

[0065] The first stress feature point extraction model can be constructed based on machine learning and deep learning models. The second stress feature point extraction model can also be constructed based on machine learning and deep learning models.

[0066] The above stress characteristic points can be understood as specific points on the stress-strain curve.

[0067] 104. Based on the second weld path, determine control parameters of the automatic soldering machine.

[0068] In the embodiment of the present invention, the control parameter is used to control the automatic soldering machine to solder the workpiece.

[0069] After obtaining the second weld path, the second weld path can be parameterized to obtain the soldering path control parameters corresponding to the second weld path, and the target stress point in the second weld path can be parameterized to obtain the soldering point control parameters corresponding to the target stress point. The soldering point control parameters can be used to correct the soldering path control parameters to obtain the control parameters of the automatic soldering machine. The control parameters are used to control the automatic soldering machine to solder the workpiece to be welded.

[0070] The above parameter configuration can be understood as the process of adjusting and setting various parameters of the welding equipment during the welding process. The parameters include welding current, voltage, welding speed, welding angle, etc. The purpose of the above parameter correction is to make the welding process more stable and the weld quality better. The adaptive control algorithm can be used to dynamically adjust the current, voltage, speed and other parameters according to the real-time feedback of the target stress point in the second weld path.

[0071] The above control parameters include but are not limited to welding speed, soldering temperature, soldering amount, etc.

[0072] In an embodiment of the present invention, the present invention obtains a two-dimensional surface image and / or a three-dimensional scanning image of a workpiece to be welded by using three-dimensional scanning technology for identification and analysis to obtain comprehensive information of the workpiece to be welded, and determines the optimal welding path and automatic soldering machine control parameters in combination with the soldering characteristics of the workpiece to be welded, which can effectively avoid problems arising in the welding process, improve welding quality and improve work efficiency.

[0073] In an embodiment of the present invention, a two-dimensional surface image and a three-dimensional scanning image of a workpiece to be welded are obtained; weld recognition processing is performed on the two-dimensional surface image and / or the three-dimensional scanning image to obtain a first weld path of the workpiece to be welded and a path complexity corresponding to the first weld path; if the path complexity is greater than a preset path complexity threshold, a second weld path is determined based on the two-dimensional surface image, the three-dimensional scanning image and the soldering characteristics of the workpiece to be welded, based on the first weld path; based on the second weld path, control parameters of an automatic soldering machine are determined, and the control parameters are used to control the automatic soldering machine to solder the workpiece to be welded. The present invention performs weld recognition processing on a two-dimensional surface image and / or a three-dimensional scanning image of a workpiece to be welded, thereby obtaining a first weld path of the workpiece to be welded and a path complexity corresponding to the first weld path. When the path complexity is greater than a preset path complexity threshold, and based on the two-dimensional surface image, the three-dimensional scanning image and the soldering characteristics of the workpiece to be welded, a second weld path is determined on the basis of the first weld path, and the second weld path is used to determine control parameters of an automatic soldering machine. The control parameters are used to control the automatic soldering machine to solder the workpiece to be welded, which solves the problems of rapid conversion of heterogeneous products with different welding processes, poor adaptability and low welding efficiency of existing welding methods, and can provide users with an efficient soldering control experience and improve welding work efficiency.

[0074] It should be noted that the soldering control method for complex structure welds provided in the embodiment of the present invention can be applied to refrigerators, smart phones, tablets, computers, servers and other devices that can perform the soldering control method for complex structure welds.

[0075] It is understandable that in the specific implementation of this application, user data, item data, order data and other related data are involved. When the embodiments in this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data, as well as model training, deployment and use, must comply with relevant laws, regulations and standards of relevant countries and regions.

[0076] Optionally, in the step of performing weld recognition processing on the two-dimensional surface image and / or the three-dimensional scanning image to obtain the first weld path of the workpiece to be welded and the path complexity corresponding to the first weld path, weld recognition processing can be performed on the two-dimensional surface image and / or the three-dimensional scanning image to obtain the first weld path of the workpiece to be welded; and the path complexity of the first weld path can be estimated based on the path straightness to obtain the path complexity corresponding to the first weld path.

[0077] In the embodiment of the present invention, the path straightness is negatively correlated with the path complexity. It is understandable that if the weld path is straighter, its complexity is lower; if the weld path is less straight, its complexity is higher.

[0078] Computer vision technology can be used to perform weld recognition processing on the two-dimensional surface image and / or three-dimensional scanning image of the weld to identify the position, shape, direction and other information of the weld, and obtain the first weld path of the weld. The first weld path describes the movement trajectory of the weld during the welding process. The characteristic information of the weld, such as gray value, texture feature, edge feature, etc., can be extracted by processing the two-dimensional surface image and / or three-dimensional scanning image of the weld joint, and then the characteristic information of the weld can be analyzed and classified using algorithms such as machine learning to determine the position and shape of the weld, and the first weld path can be generated based on the position and shape information of the weld.

[0079] The above-mentioned weld recognition processing can be understood as a recognition processing process of performing weld recognition processing on the two-dimensional surface image and / or three-dimensional scanned image of the weld to identify the position, shape, direction and other information of the weld.

[0080] The above path complexity estimation can be understood as a process of analyzing and evaluating the weld path according to the geometry of the weld joint and the welding process requirements, and determining the number of curves, curve length, curve smoothness and other parameters contained in the path to calculate the complexity of the path. Quantitative analysis methods such as curve models, curve segmentation, curve similarity and other algorithms can be used to estimate the path complexity.

[0081] The above path complexity refers to the complexity of the weld path in space.

[0082] Optionally, in the step of estimating the path complexity of the first weld path based on the path straightness to obtain the path complexity corresponding to the first weld path, the first weld path can be divided into segments according to the types of straight segments, oblique straight segments, and arc segments to obtain the segmented paths of the first weld path; based on the path straightness corresponding to the type of segmented path, the path complexity of the first weld path is estimated to obtain the path complexity corresponding to the first weld path.

[0083] In the embodiment of the present invention, the straight section is straight with the X-axis of the automatic soldering machine, the oblique straight section has an angle with the X-axis of the automatic soldering machine, the arc section has an arc, and different types of segmented paths correspond to different path straightness.

[0084] The first weld path includes straight segments, oblique straight segments and arc segments. The straight segment can be understood as the straight part of the welding path, and the X-axis of the automatic soldering machine is parallel to the welding direction, that is, the angle is 0 degrees; the oblique straight segment can be understood as the part of the welding path with a certain inclination angle, and the X-axis of the automatic soldering machine is not parallel to the welding direction, that is, the angle is not 0 degrees; the arc segment can be understood as the arc-shaped part of the welding path.

[0085] The weld path can be segmented according to the types of straight segments, oblique straight segments, and arc segments of the first weld path, and the weld path can be divided into several parts to obtain a segmented path of the first weld path; then, according to the path straightness corresponding to the type of each segmented path, the path complexity of the weld path is estimated, that is, the complexity of the weld path is evaluated, and the path complexity corresponding to the weld path is estimated.

[0086] The above path complexity estimation can be understood as a process of analyzing and evaluating the weld path and calculating the complexity of the path. Quantitative analysis methods such as curve model, curve segmentation, curve similarity and other algorithms can be used to estimate the path complexity.

[0087] The above path complexity can be understood as the complexity of the weld path in space, which can be parameters such as the curve length and curvature of the weld path.

[0088] Optionally, in the step of estimating the path complexity of the first weld path based on the path straightness corresponding to the type of the segmented path to obtain the path complexity corresponding to the first weld path, the path complexity of the first weld path can be estimated based on the path straightness corresponding to the type of the segmented path by a preset complexity estimation formula to obtain the path complexity corresponding to the first weld path;

[0089] The complexity estimation formula is:

[0090]

[0091] Among them, C represents the path complexity, N represents the number of straight segments, T represents the number of oblique straight segments, M represents the number of arc segments, S n represents the nth straight segment, D(S n -S n-1 ) represents the number of segmented paths between the nth straight segment and the n-1th straight segment; L n represents the length of the nth straight segment, S t represents the tth oblique straight segment, θ t represents the angle between the tth oblique straight segment and the X-axis of the automatic soldering machine, L t represents the length of the tth oblique straight segment, D(S t -S t-1 ) represents the number of segmented paths between the t-th oblique straight segment and the t-1-th oblique straight segment; S m represents the mth oblique straight segment, L m represents the arc length of the mth arc segment, S rad,m represents the arc length of the mth arc segment, r m represents the radius corresponding to the mth arc segment, D(S m -S m-1) represents the number of segmented paths between the mth oblique straight segment and the m-1th arc segment.

[0092] In an embodiment of the present invention, when estimating the path complexity of a weld path, it is necessary to consider the path straightness corresponding to the path type. Specifically, for different types of segmented paths, the path complexity is calculated differently. Therefore, it is necessary to estimate the path complexity of the first weld path according to the path straightness corresponding to the type of segmented path, using a preset complexity estimation formula, to obtain the path complexity corresponding to the first weld path. This can better assess the problems and risks that may be encountered during welding, and improve welding efficiency and quality.

[0093] The above preset complexity estimation formula includes calculating the complexity between straight segments, calculating the complexity between oblique straight segments, and calculating the complexity between arc segments. Different types of calculations of segmented paths involve different parameters, such as the number of straight segments, the angle between the oblique straight segment and the X-axis, the curvature of the arc segment, and so on. By adding the calculation results of the straight segment, the oblique straight segment, and the arc segment, the complexity estimation value of the first weld path can be obtained. The complexity estimation value of the first weld path can be used to evaluate the problems and risks that may be encountered during the welding process, optimize the welding process, and improve production efficiency and quality.

[0094] Optionally, if the path complexity is greater than a preset path complexity threshold, then in the step of determining the second weld path based on the first weld path based on the two-dimensional surface image, the three-dimensional scanning image and the soldering features of the workpiece to be welded, if the path complexity is greater than the preset path complexity threshold, the soldering features of the workpiece to be welded are obtained; the first feature point extraction process is performed on the two-dimensional surface image through the first stress feature point extraction model to obtain first stress feature point distribution data, and the second feature point extraction process is performed on the three-dimensional scanning image through the second stress feature point extraction model to obtain second stress feature point distribution data; based on the soldering features of the workpiece to be welded, the first stress feature point distribution data and the second stress feature point distribution data, the second weld path is determined.

[0095] In an embodiment of the present invention, the soldering features of the workpiece to be welded can be obtained by performing soldering feature extraction processing on the workpiece to be welded. The above soldering feature extraction processing can be understood as a process of analyzing and processing the welding image to extract key information that can reflect the welding features. Different algorithms and techniques, such as edge detection, threshold segmentation, directional templates, etc., can be used to identify various patterns and structures in the image, such as weld edges, textures, shapes, etc.

[0096] The first stress feature point extraction model can be a stress feature point extraction model based on machine learning or deep learning. The first stress feature point extraction model is used to detect local features of an image region in a two-dimensional image, so as to identify regions with significant texture, color or shape in the image, and extract these regions as feature points. The first stress feature point extraction model is trained using two-dimensional sample images and stress point annotation data of the two-dimensional sample images.

[0097] The second stress feature point extraction model can be a stress feature point extraction model based on machine learning or deep learning. The second stress feature point extraction model is used to detect local features of an image region in a three-dimensional image, so as to identify regions with significant texture, color or shape in the three-dimensional image, and extract these regions as feature points. The second stress feature point extraction model is trained by using three-dimensional sample images and stress point annotation data of the three-dimensional sample images.

[0098] The above training process can be supervised training. Supervised training is a training method whose core is to use a set of data with known labels to train the model, and optimize the model parameters so that the model can predict the labels of new data or make decisions based on the characteristics of existing data.

[0099] The above stress characteristic point can be understood as a specific point on the stress-strain curve, such as the proportional limit. The stress characteristic point represents the maximum stress at which the material maintains complete elastic deformation.

[0100] Specifically, according to the soldering characteristics of the workpiece to be welded, the first stress characteristic point distribution data and the second stress characteristic point distribution data, the second weld path is determined on the basis of the first weld path. Specifically, the soldering characteristics refer to the material properties and shape characteristics of the surface of the workpiece to be welded, while the stress characteristic point distribution data reflects the stress state of the object under different temperatures and pressures. By analyzing the soldering characteristics of the workpiece to be welded, the first stress characteristic point distribution data and the second stress characteristic point distribution data, and determining the second weld path on the basis of the first weld path, the welding efficiency and quality can be improved.

[0101] Optionally, in the step of determining the second weld path based on the first weld path based on the soldering characteristics of the workpiece to be welded, the first stress characteristic point distribution data and the second stress characteristic point distribution data, the first stress characteristic point and the second stress characteristic point can be mapped to the first weld path; based on the soldering characteristics of the workpiece to be welded, the first weld path is subjected to soldering simulation to obtain a soldering simulation path; based on the strain energy value of the simulated stress point, the simulated stress point having a strain energy value greater than a strain energy threshold is screened out as a target stress point; and the target stress point is fitted into the first weld path to obtain a second weld path.

[0102] In the embodiment of the present invention, the soldering simulation path includes the simulated stress point distribution. The simulated stress point distribution is the position and size information of the simulated stress point obtained by calculating the stress distribution during the welding process by a simulation method.

[0103] The first stress characteristic point and the second stress characteristic point can be mapped to the first weld path, and the welding sequence and position can be determined more accurately to avoid welding defects and damage. For example, a mathematical model or a physical model can be used for mapping. The purpose of mapping is to reflect the stress change information during the welding process into the welding path, thereby optimizing the welding process and improving the welding quality.

[0104] According to the material, shape, size and other characteristics of the welded parts, corresponding mathematical or physical models can be established to simulate physical phenomena such as heat flow and mechanical stress during welding, so as to predict soldering characteristics such as temperature distribution, molten pool morphology, and grain structure during welding. By simulating the first weld path, a more accurate soldering simulation path can be obtained, thereby guiding the actual welding process and improving welding quality and efficiency.

[0105] Specifically, computer simulation software can be used for soldering simulation, such as finite element analysis software, fluid dynamics simulation software, etc. During the simulation process, it is necessary to set corresponding boundary conditions and physical parameters according to the actual situation, calculate and analyze the heat flow and mechanical stress during the welding process, and finally obtain the soldering simulation path. By comparing the actual welding results with the simulation results, the welding process and parameters can be further optimized to improve the welding quality and efficiency.

[0106] During the welding process, due to the deformation of the material and the existence of the heat-affected zone, different stress distributions will be generated in the welded joint. Among them, some stress points may have an important impact on the welding quality, such as defects such as welding cracks and unstable molten pool. The stress distribution during the welding process can be calculated by simulation methods to obtain simulated stress points. By setting a strain energy threshold, simulated stress points with strain energy values ​​greater than the threshold can be screened out and analyzed and processed as target stress points. In this way, stress points that have a greater impact on welding quality can be identified more accurately, providing a basis for the optimization of subsequent welding processes.

[0107] The above strain energy value can be understood as the energy stored and released by an object during the process of being subjected to force or deformation.

[0108] The above fitting can be understood as a process of connecting the target stress points with zone lines and matching them with the first weld path.

[0109] Optionally, in the step of determining the control parameters of the automatic soldering machine based on the second weld path, the second weld path can be parameterized to obtain soldering path control parameters corresponding to the second weld path; the target stress point in the second weld path can be parameter corrected to obtain soldering point control parameters corresponding to the target stress point; based on the soldering point control parameters, the soldering path control parameters can be corrected to obtain the control parameters of the automatic soldering machine.

[0110] In the embodiment of the present invention, the above parameter configuration can be understood as the process of adjusting and setting various parameters of the welding equipment during the welding process. The parameters include welding current, voltage, welding speed, welding angle, etc.

[0111] The purpose of the above parameter correction is to make the welding process more stable and the weld quality better. Adaptive control algorithms can be used to dynamically adjust parameters such as current, voltage, and speed based on real-time feedback from the target stress point in the second weld path.

[0112] The above control parameters are used to control the automatic soldering machine to solder the workpiece.

[0113] Specifically, by configuring the parameters of the second weld path, the soldering path control parameters corresponding to the path can be obtained; then, the parameters of the target stress point in the second weld path are corrected to obtain the soldering point control parameters corresponding to the target stress point; finally, according to the soldering point control parameters, the soldering path control parameters are corrected to obtain the control parameters of the automatic soldering machine. The control parameters are used to control the automatic soldering machine to solder the workpiece to be welded, which can provide users with an efficient soldering control experience and improve work efficiency.

[0114] like Figure 2 As shown, an embodiment of the present invention provides a soldering control device for a complex structure weld, and the soldering control device for a complex structure weld includes:

[0115] An acquisition module 201 is used to acquire a two-dimensional surface image and a three-dimensional scanning image of the workpiece to be welded;

[0116] A processing module 202 is used to perform weld recognition processing on the two-dimensional surface image and / or the three-dimensional scanned image to obtain a first weld path of the workpiece to be welded and a path complexity corresponding to the first weld path;

[0117] A first determination module 203 is configured to determine a second weld path based on the first weld path, based on the two-dimensional surface image, the three-dimensional scanned image and the soldering characteristics of the workpiece if the path complexity is greater than a preset path complexity threshold, wherein the second weld path has at least one target stress point;

[0118] The second determination module 204 is used to determine control parameters of an automatic soldering machine based on the second weld path, where the control parameters are used to control the automatic soldering machine to solder the workpiece to be welded.

[0119] Optionally, the processing module 202 is also used to perform weld recognition processing on the two-dimensional surface image and / or the three-dimensional scanning image to obtain a first weld path of the workpiece to be welded; perform path complexity estimation on the first weld path based on path straightness to obtain the path complexity corresponding to the first weld path, and the path straightness is negatively correlated with the path complexity.

[0120] Optionally, the processing module 202 is also used to segment the first weld path into segments according to the types of straight segments, oblique straight segments, and arc segments to obtain the segmented paths of the first weld path, wherein the straight segment is straight with the X-axis of the automatic soldering machine, the oblique straight segment has an angle with the X-axis of the automatic soldering machine, and the arc segment has an arc, and different types of segmented paths correspond to different path straightnesses; based on the path straightness corresponding to the type of the segmented path, the path complexity of the first weld path is estimated to obtain the path complexity corresponding to the first weld path.

[0121] Optionally, the processing module 202 is further configured to estimate the path complexity of the first weld path based on the path straightness corresponding to the type of the segmented path by using a preset complexity estimation formula to obtain the path complexity corresponding to the first weld path;

[0122] The complexity estimation formula is:

[0123]

[0124] Among them, C represents the path complexity, N represents the number of straight segments, T represents the number of oblique straight segments, M represents the number of arc segments, S n represents the nth straight segment, D(S n -S n-1 ) represents the number of segmented paths between the nth straight segment and the n-1th straight segment; L n represents the length of the nth straight segment, S t represents the tth oblique straight segment, θ t represents the angle between the tth oblique straight segment and the X-axis of the automatic soldering machine, L t represents the length of the tth oblique straight segment, D(S t -S t-1 ) represents the number of segmented paths between the t-th oblique straight segment and the t-1-th oblique straight segment; S m represents the mth oblique straight segment, L m represents the arc length of the mth arc segment, Srad,m represents the arc length of the mth arc segment, r m represents the radius corresponding to the mth arc segment, D(S m -S m-1 ) represents the number of segmented paths between the mth oblique straight segment and the m-1th arc segment.

[0125] Optionally, the first determination module 203 is also used to obtain the soldering characteristics of the workpiece to be welded if the path complexity is greater than a preset path complexity threshold; perform a first feature point extraction process on the two-dimensional surface image through a first stress feature point extraction model to obtain first stress feature point distribution data, and the first stress feature point extraction model is trained by a two-dimensional sample image and stress point annotation data of the two-dimensional sample image; perform a second feature point extraction process on the three-dimensional scanned image through a second stress feature point extraction model to obtain second stress feature point distribution data, and the second stress feature point extraction model is trained by a three-dimensional sample image and stress point annotation data of the three-dimensional sample image; based on the soldering characteristics of the workpiece to be welded, the first stress feature point distribution data and the second stress feature point distribution data, determine a second weld path on the basis of the first weld path.

[0126] Optionally, the first determination module 203 is also used to map the first stress characteristic point and the second stress characteristic point to the first weld path; based on the soldering characteristics of the workpiece to be welded, perform soldering simulation on the first weld path to obtain a soldering simulation path, wherein the soldering simulation path includes a simulated stress point distribution; based on the strain energy value of the simulated stress point, screen out the simulated stress point whose strain energy value is greater than a strain energy threshold as a target stress point; fit the target stress point to the first weld path to obtain the second weld path.

[0127] Optionally, the second determination module 204 is also used to configure parameters of the second weld path to obtain soldering path control parameters corresponding to the second weld path; perform parameter correction on the target stress point in the second weld path to obtain soldering point control parameters corresponding to the target stress point; based on the soldering point control parameters, correct the soldering path control parameters to obtain control parameters of the automatic soldering machine.

[0128] It should be noted that the soldering control device for complex structure welds provided in the embodiment of the present invention can be applied to refrigerators, smart phones, tablets, computers, servers and other equipment that can perform the soldering control method for complex structure welds.

[0129] The soldering control device for complex structure welds provided in the embodiment of the present invention can realize each process realized by the soldering control method for complex structure welds in the above method embodiment, and can achieve the same beneficial effects. To avoid repetition, it will not be described here.

[0130] See also Figure 3 , Figure 3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, it includes: a memory 302, a processor 301, and a computer program for a soldering control method for a complex structure weld stored in the memory 302 and executable on the processor 301, wherein:

[0131] The processor 301 is used to call the computer program stored in the memory 302 and execute the following steps:

[0132] Obtain 2D surface images and 3D scanning images of the workpiece to be welded;

[0133] Performing weld recognition processing on the two-dimensional surface image and / or the three-dimensional scanned image to obtain a first weld path of the workpiece to be welded and a path complexity corresponding to the first weld path;

[0134] If the path complexity is greater than a preset path complexity threshold, a second weld path is determined based on the two-dimensional surface image, the three-dimensional scanned image and the soldering characteristics of the workpiece to be welded, and on the basis of the first weld path, the second weld path is at least one target stress point;

[0135] Based on the second weld path, control parameters of an automatic soldering machine are determined, and the control parameters are used to control the automatic soldering machine to solder the workpiece to be welded.

[0136] Optionally, the step of performing weld recognition processing on the two-dimensional surface image and / or the three-dimensional scanned image to obtain a first weld path of the workpiece to be welded and a path complexity corresponding to the first weld path, performed by the processor 301, includes:

[0137] Performing weld seam recognition processing on the two-dimensional surface image and / or the three-dimensional scanning image to obtain a first weld seam path of the workpiece to be welded;

[0138] The path complexity of the first weld path is estimated based on the path straightness to obtain the path complexity corresponding to the first weld path, and the path straightness is negatively correlated with the path complexity.

[0139] Optionally, the processor 301 performs the step of estimating the path complexity of the first weld path based on the path straightness to obtain the path complexity corresponding to the first weld path, including:

[0140] The first weld path is segmented into straight segments, oblique straight segments, and arc segments to obtain segmented paths of the first weld path, wherein the straight segment is straight with the X-axis of the automatic soldering machine, the oblique straight segment has an angle with the X-axis of the automatic soldering machine, and the arc segment has an arc, and different types of segmented paths correspond to different path straightness;

[0141] Based on the path straightness corresponding to the type of the segmented path, a path complexity estimation is performed on the first weld path to obtain the path complexity corresponding to the first weld path.

[0142] Optionally, the processor 301 performs the step of estimating the path complexity of the first weld path based on the path straightness corresponding to the type of the segmented path to obtain the path complexity corresponding to the first weld path, which includes:

[0143] Based on the path straightness corresponding to the type of the segmented path, the path complexity of the first weld path is estimated by a preset complexity estimation formula to obtain the path complexity corresponding to the first weld path;

[0144] The complexity estimation formula is:

[0145]

[0146] Among them, C represents the path complexity, N represents the number of straight segments, T represents the number of oblique straight segments, M represents the number of arc segments, S n represents the nth straight segment, D(S n -S n-1 ) represents the number of segmented paths between the nth straight segment and the n-1th straight segment; L n represents the length of the nth straight segment, S t represents the tth oblique straight segment, θ t represents the angle between the tth oblique straight segment and the X-axis of the automatic soldering machine, L t represents the length of the tth oblique straight segment, D(S t -S t-1 ) represents the number of segmented paths between the t-th oblique straight segment and the t-1-th oblique straight segment; S m represents the mth oblique straight segment, L m represents the arc length of the mth arc segment, S rad,m represents the arc length of the mth arc segment, r m represents the radius corresponding to the mth arc segment, D(S m -S m-1 ) represents the number of segmented paths between the mth oblique straight segment and the m-1th arc segment.

[0147] Optionally, the step of determining a second weld path based on the first weld path based on the two-dimensional surface image, the three-dimensional scanned image and the soldering characteristics of the workpiece to be welded if the path complexity is greater than a preset path complexity threshold, performed by the processor 301, includes:

[0148] If the path complexity is greater than a preset path complexity threshold, then obtaining the soldering characteristics of the workpiece to be welded;

[0149] Performing first feature point extraction processing on the two-dimensional surface image by using a first stress feature point extraction model to obtain first stress feature point distribution data, wherein the first stress feature point extraction model is obtained by training with a two-dimensional sample image and stress point annotation data of the two-dimensional sample image;

[0150] Performing second feature point extraction processing on the three-dimensional scanned image by using a second stress feature point extraction model to obtain second stress feature point distribution data, wherein the second stress feature point extraction model is obtained by training the three-dimensional sample image and the stress point annotation data of the three-dimensional sample image;

[0151] Based on the soldering characteristics of the workpiece to be welded, the first stress characteristic point distribution data and the second stress characteristic point distribution data, a second weld path is determined on the basis of the first weld path.

[0152] Optionally, the step of determining the second weld path based on the first weld path based on the soldering characteristics of the workpiece to be welded, the first stress characteristic point distribution data, and the second stress characteristic point distribution data performed by the processor 301 includes:

[0153] Mapping the first stress characteristic point and the second stress characteristic point onto the first weld path;

[0154] Based on the soldering characteristics of the workpiece to be welded, performing soldering simulation on the first weld path to obtain a soldering simulation path, wherein the soldering simulation path includes a simulated stress point distribution;

[0155] Based on the strain energy value of the simulated stress point, the simulated stress point whose strain energy value is greater than a strain energy threshold is selected as a target stress point;

[0156] The target stress point is fitted into the first weld path to obtain the second weld path.

[0157] Optionally, the step of determining the control parameters of the automatic soldering machine based on the second weld path performed by the processor 301 includes:

[0158] Performing parameter configuration on the second weld path to obtain soldering path control parameters corresponding to the second weld path;

[0159] Performing parameter correction on the target stress point in the second weld path to obtain a soldering point control parameter corresponding to the target stress point;

[0160] Based on the soldering point control parameters, the soldering path control parameters are corrected to obtain the control parameters of the automatic soldering machine.

[0161] It should be noted that the electronic device provided in the embodiment of the present invention can be applied to smart refrigerators, smart phones, tablets, computers, servers and other devices that can perform soldering control methods for complex structure welds.

[0162] The electronic device provided in the embodiment of the present invention can implement each process implemented by the soldering control method for complex structure welds in the above method embodiment, and can achieve the same beneficial effects. To avoid repetition, it will not be described here.

[0163] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the soldering control method for complex structure welds provided by the embodiment of the present invention are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0164] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The computer-readable storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0165] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A soldering control method for complex structure welds, characterized in that: The method comprises the following steps: Obtain two-dimensional surface images and three-dimensional scanning images of the workpiece to be welded; Performing weld recognition processing on the two-dimensional surface image and / or the three-dimensional scanned image to obtain a first weld path of the workpiece to be welded and a path complexity corresponding to the first weld path; If the path complexity is greater than a preset path complexity threshold, a second weld path is determined based on the two-dimensional surface image, the three-dimensional scanned image and the soldering characteristics of the workpiece to be welded, and on the basis of the first weld path, the second weld path has at least one target stress point; Based on the second weld path, control parameters of an automatic soldering machine are determined, and the control parameters are used to control the automatic soldering machine to solder the workpiece to be welded.

2. The soldering control method for complex structure welds according to claim 1, characterized in that: The step of performing weld seam recognition processing on the two-dimensional surface image and / or the three-dimensional scanned image to obtain a first weld seam path of the workpiece to be welded and a path complexity corresponding to the first weld seam path comprises: Performing weld seam recognition processing on the two-dimensional surface image and / or the three-dimensional scanning image to obtain a first weld seam path of the workpiece to be welded; The path complexity of the first weld path is estimated based on the path straightness to obtain the path complexity corresponding to the first weld path, and the path straightness is negatively correlated with the path complexity.

3. The soldering control method for complex structure welds according to claim 2, characterized in that: The step of estimating the path complexity of the first weld path based on the path straightness to obtain the path complexity corresponding to the first weld path comprises: The first weld path is segmented into straight segments, oblique straight segments, and arc segments to obtain segmented paths of the first weld path, wherein the straight segment is straight with the X-axis of the automatic soldering machine, the oblique straight segment has an angle with the X-axis of the automatic soldering machine, and the arc segment has an arc, and different types of segmented paths correspond to different path straightness; Based on the path straightness corresponding to the type of the segmented path, a path complexity estimation is performed on the first weld path to obtain the path complexity corresponding to the first weld path.

4. The soldering control method for complex structure welds according to claim 3, characterized in that: The step of estimating the path complexity of the first weld path based on the path straightness corresponding to the type of the segmented path to obtain the path complexity corresponding to the first weld path comprises: Based on the path straightness corresponding to the type of the segmented path, the path complexity of the first weld path is estimated by a preset complexity estimation formula to obtain the path complexity corresponding to the first weld path; The complexity estimation formula is: Among them, C represents the path complexity, N represents the number of straight segments, T represents the number of oblique straight segments, M represents the number of arc segments, S n represents the nth straight segment, D(S n -S n-1 ) represents the number of segmented paths between the nth straight segment and the n-1th straight segment; L n represents the length of the nth straight segment, S t represents the tth oblique straight segment, θ t represents the angle between the tth oblique straight segment and the X-axis of the automatic soldering machine, L t represents the length of the tth oblique straight segment, D(S t -S t-1 ) represents the number of segmented paths between the t-th oblique straight segment and the t-1-th oblique straight segment; S m represents the mth oblique straight segment, L m represents the arc length of the mth arc segment, S rad,m represents the arc length of the mth arc segment, r m represents the radius corresponding to the mth arc segment, D(S m -S m-1 ) represents the number of segmented paths between the mth oblique straight segment and the m-1th arc segment.

5. The soldering control method for complex structure welds according to any one of claims 1 to 4, characterized in that: If the path complexity is greater than a preset path complexity threshold, the step of determining a second weld path based on the first weld path based on the two-dimensional surface image, the three-dimensional scanned image and the soldering characteristics of the workpiece to be welded comprises: If the path complexity is greater than a preset path complexity threshold, then obtaining the soldering characteristics of the workpiece to be welded; Performing first feature point extraction processing on the two-dimensional surface image by using a first stress feature point extraction model to obtain first stress feature point distribution data, wherein the first stress feature point extraction model is obtained by training with a two-dimensional sample image and stress point annotation data of the two-dimensional sample image; Performing second feature point extraction processing on the three-dimensional scanned image by using a second stress feature point extraction model to obtain second stress feature point distribution data, wherein the second stress feature point extraction model is obtained by training the three-dimensional sample image and the stress point annotation data of the three-dimensional sample image; Based on the soldering characteristics of the workpiece to be welded, the first stress characteristic point distribution data and the second stress characteristic point distribution data, a second weld path is determined on the basis of the first weld path.

6. The soldering control method for complex structure welds according to claim 5, characterized in that: The step of determining a second weld path based on the soldering characteristics of the workpiece to be welded, the first stress characteristic point distribution data, and the second stress characteristic point distribution data on the basis of the first weld path comprises: Mapping the first stress characteristic point and the second stress characteristic point onto the first weld path; Based on the soldering characteristics of the workpiece to be welded, performing soldering simulation on the first weld path to obtain a soldering simulation path, wherein the soldering simulation path includes a simulated stress point distribution; Based on the strain energy value of the simulated stress point, the simulated stress point whose strain energy value is greater than a strain energy threshold is selected as a target stress point; The target stress point is fitted into the first weld path to obtain the second weld path.

7. The soldering control method for complex structure welds according to claim 6, characterized in that: The step of determining the control parameters of the automatic soldering machine based on the second weld path comprises: Performing parameter configuration on the second weld path to obtain soldering path control parameters corresponding to the second weld path; Performing parameter correction on the target stress point in the second weld path to obtain a soldering point control parameter corresponding to the target stress point; Based on the soldering point control parameters, the soldering path control parameters are corrected to obtain the control parameters of the automatic soldering machine.

8. A soldering control device for complex structure welds, characterized in that: The soldering control device for complex structure welds comprises: An acquisition module, used to acquire a two-dimensional surface image and a three-dimensional scanning image of the workpiece to be welded; A processing module, used for performing weld seam recognition processing on the two-dimensional surface image and / or the three-dimensional scanned image to obtain a first weld seam path of the workpiece to be welded and a path complexity corresponding to the first weld seam path; A first determination module is used to determine a second weld path based on the first weld path, based on the two-dimensional surface image, the three-dimensional scanning image and the soldering characteristics of the workpiece if the path complexity is greater than a preset path complexity threshold, and the second weld path has at least one target stress point; The second determination module is used to determine the control parameters of the automatic soldering machine based on the second weld path, and the control parameters are used to control the automatic soldering machine to solder the workpiece to be welded.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the soldering control method for complex structure welds as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the soldering control method for complex structure welds according to any one of claims 1 to 7 are implemented.

Images