A method and system for controlling the welding deformation of corrugated plate

Abstract

The embodiments of this specification provide a method and system for controlling the welding deformation of a corrugated plate. The method periodically determines the welding band interval and / or welding parameters of the cycle based on a preset cycle. The preset cycle length is determined by the size or material of the corrugated plate. For any cycle, the method includes: determining the first and second welding paths, which correspond to the welding paths corresponding to the two sides of the corrugated plate respectively; determining the deformation distribution of the cycle based on the welding band interval and the two welding paths of the previous cycle, the deformation distribution includes the deformation position and the deformation value, and the welding band interval refers to the number of corrugated segments between the first welding path and the second welding path; determining the welding band interval and / or welding parameters of the cycle based on the deformation distribution.

Description

Technical Field

[0001] The present invention relates to the field of welding technology, and in particular to a method and system for controlling the welding deformation of a corrugated plate. Background Art

[0002] As a common welding process, corrugated plate welding is widely used in many fields. Corrugated plate welding is done by butting metal corrugated plates and other plates together and applying pressure to them, and then welding them together to form a whole. However, the surface fluctuations of corrugated plates vary greatly, making it difficult to accurately butt the welding position. Especially when the thickness of the corrugated plate is thin, the surface fluctuations may further increase the thermal deformation and residual thermal stress during welding, making it difficult to control the welding quality.

[0003] At present, the industry has adopted some methods to improve the quality of corrugated plate welding. For example, the use of specially designed welding machines combined with calibration detection and control technology can improve the welding accuracy to a certain extent. For example, industrial robots are used for upside-down welding to improve the flexibility and accuracy of welding. However, these methods lack a real-time and accurate monitoring mechanism for the deformation of corrugated plates of different materials and thicknesses during welding. The deformation prevention and control measures during the welding process of corrugated plates are not perfect, and it is difficult to effectively cope with complex welding scenarios.

[0004] Therefore, it is necessary to provide a method and system for controlling the welding deformation of the corrugated plate, which can monitor the welding deformation of the corrugated plate in real time and effectively prevent and control the welding deformation of the corrugated plate. Summary of the invention

[0005] One or more embodiments of the present specification provide a method for controlling the welding deformation of a corrugated plate, the method comprising: periodically determining a welding band interval and / or a welding parameter of at least one welding robot based on a preset cycle, wherein the cycle length of the preset cycle is determined based on the corrugated plate parameters; for any cycle: determining a first welding path and a second welding path of the cycle, wherein the first welding path and the second welding path are welding paths corresponding to two sides of the corrugated plate, respectively; determining a deformation distribution of the cycle based on the welding band interval of the previous cycle, the first welding path and the second welding path; determining the welding band interval of the cycle and / or the welding parameter of the at least one welding robot based on the deformation distribution of the cycle.

[0006] One or more embodiments of the present specification provide a control system for the welding deformation of a corrugated plate, the system comprising a determination module, which periodically determines a welding band interval and / or a welding parameter of at least one welding robot based on a preset cycle, wherein the cycle length of the preset cycle is determined based on the corrugated plate parameters; the determination module comprises: a path determination module, which is configured to determine, for any cycle, a first welding path and a second welding path of the cycle, wherein the first welding path and the second welding path are welding paths corresponding to two sides of the corrugated plate, respectively; a distribution determination module, which is configured to determine, for any cycle, the deformation distribution of the cycle based on the welding band interval of the previous cycle, the first welding path and the second welding path; a parameter determination module, which is configured to determine, for any cycle, the welding band interval and / or the welding parameter of the at least one welding robot of the cycle based on the deformation distribution of the cycle.

[0007] One or more embodiments of the present specification provide a device for controlling the welding deformation of a corrugated plate, comprising a processor, wherein the processor is used to execute a method for controlling the welding deformation of a corrugated plate as described in any embodiment of the present specification.

[0008] One or more embodiments of the present specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method for controlling the welding deformation of a corrugated plate described in any embodiment of the present specification.

[0009] The beneficial effects of the embodiments of this specification include but are not limited to:

[0010] By periodically determining the welding band interval and / or welding parameters of each cycle, the welding strategy can be dynamically adjusted according to the material, thickness and other parameters of the corrugated plate combined with real-time monitoring data to minimize welding deformation and improve welding quality and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0012] Figure 1 is an exemplary module diagram of a control system for the welding deformation of a corrugated plate according to some embodiments of this specification;

[0013] Figure 2 is an exemplary flow chart of a method for controlling the welding deformation of a corrugated plate according to some embodiments of this specification;

[0014] Figure 3is an exemplary schematic diagram of a deformation distribution prediction model according to some embodiments of the present specification. DETAILED DESCRIPTION

[0015] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0016] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0017] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0018] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0019] Figure 1 is an exemplary module diagram of a control system for the welding deformation of a corrugated plate according to some embodiments of this specification. Figure 1 As shown, in some embodiments of the present specification, a control system for the welding deformation of a corrugated plate is provided. In some embodiments, the control system 100 for the welding deformation of a corrugated plate may include a determination module.

[0020] In some embodiments, the determination module is configured to periodically determine the welding band interval and / or the welding parameters of at least one welding robot in the cycle based on a preset cycle.

[0021] In some embodiments, Figure 1 As shown, the determination module may include a path determination module 110 , a distribution determination module 120 and a parameter determination module 130 .

[0022] In some embodiments, the path determination module 110 is configured to determine, for any cycle, a first welding path and a second welding path of the cycle, wherein the first welding path and the second welding path are welding paths corresponding to two sides of the corrugated plate, respectively.

[0023] In some embodiments, the distribution determination module 120 is configured to determine, for any cycle, a deformation distribution of the cycle based on the welding band interval, the first welding path, and the second welding path of the previous cycle.

[0024] In some embodiments, the distribution determination module 120 is further configured to: determine the welding alternating position of the cycle based on the welding band interval, the first welding path and the second welding path of the previous cycle, where the welding alternating position is the alternating position when two welding robots perform welding; and determine the deformation distribution of the cycle based on the welding alternating position of the cycle.

[0025] In some embodiments, the distribution determination module 120 is further configured to: obtain the deformation distribution of the previous cycle through a scanning device; based on the deformation distribution of the previous cycle, the welding alternating position of the cycle, the welding band interval of the previous cycle and the corrugated plate parameters, determine the deformation distribution of the cycle through a deformation distribution prediction model, and the deformation distribution prediction model is a machine learning model.

[0026] In some embodiments, the parameter determination module 130 is configured to determine, for any cycle, a welding band interval of the cycle and / or a welding parameter of at least one welding robot based on the deformation distribution of the cycle.

[0027] In some embodiments, the parameter determination module 130 is further configured to: determine the welding quality based on the deformation distribution of the cycle; in response to the welding quality being lower than a preset welding quality, determine the welding band interval of the cycle and / or the welding parameters of at least one welding robot.

[0028] In some embodiments, the parameter determination module 130 is further configured to: determine candidate welding parameters and candidate welding band intervals; determine an estimated deformation distribution based on the candidate welding parameters, the candidate welding band intervals, the welding temperature of at least one welding robot, and the welding process type; based on the estimated deformation distribution, determine the welding band interval of the cycle and / or the welding parameters of at least one welding robot.

[0029] In some embodiments, the control system 100 for the amount of deformation of corrugated plate welding can be integrated into a processor. The processor can process data and / or information obtained from other devices or system components. The processor can execute program instructions based on these data, information and / or processing results to perform one or more functions described in this specification. As an example only, the processor may include a central processing unit (CPU), an application specific integrated circuit (ASIC), etc., or any combination thereof.

[0030] For detailed description of each module, see Figure 2 , Figure 3 and its related description.

[0031] It should be noted that the above description of the control system and its modules for the corrugated plate welding deformation is only for the convenience of description and cannot limit the present specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from the principle. In some embodiments, Figure 1 The path determination module, distribution determination module and parameter determination module disclosed in the specification can be different modules in a system, or a module can realize the functions of two or more modules. For example, each module can share a storage module, or each module can have its own storage module. Such variations are all within the protection scope of this specification.

[0032] Figure 2 FIG2 is an exemplary flow chart of a method for controlling the welding deformation of a corrugated plate according to some embodiments of the present specification. In some embodiments, process 200 may be executed by a processor.

[0033] In some embodiments, the processor can periodically determine the welding band interval and / or the welding parameters of at least one welding robot based on a preset cycle, and the cycle length of the preset cycle is determined based on the corrugated plate parameters; for any cycle: the processor can determine the first welding path and the second welding path of the cycle, and the first welding path and the second welding path are the welding paths corresponding to the two sides of the corrugated plate respectively; based on the welding band interval, the first welding path and the second welding path of the previous cycle, determine the deformation distribution of the cycle; based on the deformation distribution of the cycle, determine the welding band interval of the cycle and / or the welding parameters of at least one welding robot.

[0034] In some embodiments, the processor may periodically determine the welding band interval and / or the welding parameters of at least one welding robot based on a preset cycle.

[0035] The preset cycle refers to a preset operation cycle for welding the corrugated sheet.

[0036] In the corrugated sheet welding scenario, the spot-welded corrugated sheet will be transported to the positioner, which clamps the corrugated sheet and flips it to the welding position (for example, the corrugated sheet is upright). At this point, the corrugated sheet can be welded according to a preset cycle. For example, the corrugated sheet can be welded to other structures, or multiple sheets of corrugated sheet can be welded together. Other structures may include support frames, support structures, pipes or other connectors.

[0037] In some embodiments, the period length of the preset period can be determined based on the corrugated board parameters. The corrugated board parameters refer to data related to the physical characteristics of the corrugated board.

[0038] In some embodiments, the corrugated board parameters may include at least one of the corrugated board size and the corrugated board material.

[0039] In some embodiments, the dimensions of the corrugated board may include the thickness of the corrugated board, the width and length of the corrugated board, and the wave height, wavelength and waveform of the corrugated board. The wave height of the corrugated board refers to the vertical distance between the peak and the valley of the corrugation. The wavelength of the corrugated board refers to the horizontal distance between two adjacent wave crests (or two wave valleys). The waveform of the corrugated board may include sine, square, trapezoidal or other geometric shapes.

[0040] In some embodiments, the corrugated plate material may include a variety of metal materials, for example, one or more of steel, stainless steel, aluminum, and copper, etc. In some embodiments, the corrugated plate parameters may also include the coating, quality, and density parameters of the corrugated plate, etc.

[0041] In some embodiments, the processor may determine the preset period by searching a preset table based on the size and material of the corrugated board. The preset table may include the size and material of the corrugated board, and the corresponding preset period.

[0042] For example, the smaller the size of the corrugated plate, the easier it is for the corrugated plate material to deform, so the corresponding preset period can be smaller, so that the welding band interval and welding parameters can be determined more frequently to accurately control the welding process and reduce deformation. The preset table can be pre-built based on historical data.

[0043] In some embodiments of the present specification, according to the material of the corrugated plate (for example, the properties and deformation characteristics of the metal material, etc.), a suitable cycle is selected to frequently observe the welding to reduce the heat effect, thereby effectively controlling the deformation.

[0044] The welding band interval refers to the number of bands between any two welding paths (for example, the end points of two welding paths) when performing preset mode welding. In some embodiments, the welding band interval may also be the number of bands on the corrugated plate that are always maintained between two adjacent welding robots when performing preset mode welding. For example, the welding band interval may be 2 bands, 3 bands, 4 bands, etc.

[0045] The preset mode refers to the way in which at least one welding robot works. A welding robot is an automated device used to perform welding tasks.

[0046] In some embodiments, the preset mode may include two welding robots welding at the same time, or two welding robots welding alternately. For example, the preset mode may be: taking the example of using two welding robots to weld in cooperation, after the two welding robots simultaneously scan the corrugated plate on both sides to generate a welding path, one of the welding robots welds from one side first, and after welding a number of bands, the other welding robot welds from the same end and direction of the other side of the corrugated plate. The two sides of the corrugated plate may be the upper and lower sides perpendicular to the extension direction of the wave.

[0047] The welding path refers to the route that the welding robot follows along the surface of the material to be welded during the welding process. Each welding robot can correspond to one welding path.

[0048] A band refers to a unit of repetitive waveforms of a corrugated plate. For example, a band may include a section of waveform formed by a concave and convex portion of the corrugated plate.

[0049] In some embodiments, the preset mode may include more than two welding robots cooperating in welding, for example, three or four welding robots. The number of welding robots is not limited. In the embodiments of this specification, the method of cooperating in welding with two welding robots is used as an example for explanation.

[0050] In the embodiments of the present specification, the welding process is performed by a welding robot, so that the welding parameters can be accurately controlled and the deformation caused by human factors can be reduced. By using two welding robots to perform symmetrical welding on both sides of the corrugated plate, the welds can be distributed symmetrically as much as possible to reduce the uneven thermal stress during the welding process and reduce the overall deformation of the corrugated plate. At the same time, for corrugated plate welding, using a smaller welding current can reduce heat input, thereby reducing deformation.

[0051] By determining the appropriate welding band interval for each cycle, the welding distance can be controlled to disperse the heat, thereby effectively reducing the temperature and deformation caused by temperature difference.

[0052] Welding parameters refer to the parameters related to the welding process performed by the welding robot. In some embodiments, the welding parameters include welding position and welding start and end time. In some embodiments, the welding parameters may also include welding path and welding interval time. Different welding robots may correspond to different welding parameters.

[0053] For any cycle, the processor can determine the welding band interval of the cycle and / or the welding parameters of at least one welding robot. For ease of explanation, the cycle of currently determining the welding band interval and / or the welding parameters of at least one welding robot can be called the target cycle.

[0054] like Figure 2 As shown, process 200 includes the following steps:

[0055] Step 210, determining a first welding path and a second welding path of a cycle.

[0056] The first welding path and the second welding path are welding paths corresponding to two sides of the corrugated plate respectively. The two sides of the corrugated plate refer to two sides perpendicular to the extension direction of the corrugated plate.

[0057] In some embodiments, after the corrugated plate is flipped to the welding position, the processor may scan the corrugated plate on one side of the corrugated plate through each welding robot to generate a welding path corresponding to the welding robot. For example, the processor may generate a first welding path based on the scanning result of the first welding robot on the first side of the corrugated plate, and generate a second welding path based on the scanning result of the second welding robot on the second side of the corrugated plate.

[0058] The welding robot can have the functions of scanning and welding at the same time. After scanning the corrugated plate, the welding robot can obtain a scanned image of the corrugated plate, which includes one or more welds. The welding robot can generate corresponding welding paths according to the positions of these welds.

[0059] Step 220, determining the deformation distribution of the cycle based on the welding band interval, the first welding path and the second welding path of the previous cycle.

[0060] In some embodiments, the welding band interval may be the number of corrugation segments between the first welding path and the second welding path when performing the preset mode welding. The welding band interval and welding parameters determined in the historical cycle (e.g., the previous cycle) may be stored in a storage device, and the processor may directly obtain the relevant data determined in the historical cycle from the storage device.

[0061] The deformation distribution refers to the distribution of the deformation of the corrugated plate after welding in the entire corrugated plate. In some embodiments, the deformation distribution includes the position where the deformation occurs on the corrugated plate (which can be called the deformation position) and the deformation value of the position. The deformation value refers to a numerical value that characterizes the degree of deformation.

[0062] In some embodiments, the processor may determine the deformation distribution of the period in a variety of ways.

[0063] In some embodiments, the processor can calculate the deformation of each sampling point based on at least one sampling point on the first welding path and the second welding path; and obtain the deformation distribution of the cycle (i.e., the target cycle) based on the deformation of each sampling point. The sampling point can be a randomly selected position on the welding path. The weldment (e.g., corrugated sheet) may cause linear shrinkage deformation due to thermal cycling and cooling during the welding process, so the deformation of the sampling point can be calculated by a preset algorithm.

[0064] In some embodiments, for each sampling point, the processor can calculate the welding deformation of the sampling point according to the linear expansion coefficient of the corrugated plate, the length of the corrugated plate, and the temperature difference of the sampling point before and after welding. For example, the processor can calculate by formula (1):

[0065] (1)

[0066] in, represents the welding deformation, represents the linear expansion coefficient of the corrugated sheet, Indicates the length of the corrugated plate, Indicates the temperature difference before and after welding. The linear expansion coefficient of the corrugated plate is related to the material of the corrugated plate, which can be obtained by the processor querying relevant data. The length of the corrugated plate can be measured in advance. When calculating the deformation of each sampling point, and are the same, but the temperature difference before and after welding may be different at different sampling points.

[0067] In some embodiments, the processor can determine the temperature difference of the sampling point before and after welding based on the welding band interval and the welding temperature of the two welding robots. For example, the processor can determine the temperature of the sampling point conducted by the two welding robots through the physical formula of heat conduction, and then calculate the temperature difference of the sampling point before and after welding based on the difference between the temperature conducted by the two welding robots and the temperature before welding. The temperature before welding can be measured in advance.

[0068] In some embodiments, the processor may use a sampling point where deformation has occurred (for example, the welding deformation amount is greater than a preset deformation threshold) and the deformation value of the sampling point as the deformation position and the corresponding deformation value in the deformation distribution.

[0069] In some embodiments, the processor may determine the deformation distribution of the cycle (ie, the target cycle) based on the welding band interval of the previous cycle, the welding parameters of at least one welding robot of the previous cycle, the first welding path, and the second welding path.

[0070] In some embodiments, the processor can construct the welding band interval of the previous cycle, the welding parameters of at least one welding robot of the previous cycle, and the first welding path and the second welding path of the target cycle as a first vector. The processor can construct the welding band interval of the previous cycle of a certain historical cycle in the historical data, the welding parameters of at least one welding robot of the previous cycle of the historical cycle, and the first welding path and the second welding path of the previous historical cycle as a first reference vector. The processor can match the first vector with multiple first reference vectors in the historical data, and use the deformation data measured after welding in the historical cycle corresponding to the first reference vector with the highest similarity to the first vector as the deformation distribution of the target cycle.

[0071] If the target cycle adopts the same welding band interval and welding parameters as the previous cycle, the deformation distribution of the previous cycle can be used as the deformation distribution of the target cycle.

[0072] In some embodiments, the processor can determine the welding alternating position of the target cycle based on the welding band interval of the previous cycle, the first welding path and the second welding path of the target cycle; and determine the deformation distribution of the target cycle based on the welding alternating position of the target cycle.

[0073] The welding alternating position refers to the alternating position of two welding robots when welding. For example, the position where the first welding robot ends welding and the position where the second welding robot starts welding. If the number of welding robots is greater than two, the welding alternating position can be the alternating position of two adjacent welding robots.

[0074] In some embodiments, the processor can determine the welding band range of each welding robot in at least one welding robot based on the welding band interval of the previous cycle; determine the welding alternating position based on the welding band range; and determine the deformation distribution of the target cycle based on the welding alternating position of the target cycle.

[0075] The welding band range refers to the band range of the welding robot when performing a single welding on the corrugated plate, that is, the number of bands that can be affected each time welding. The processor can obtain the welding band range of each welding robot according to the welding band of the starting welding in the previous cycle and the welding position sequence of at least one welding robot. For example, taking the example of two welding robots cooperating in welding, the welding band interval is 3 bands. If the first welding robot starts welding from the first band, the welding band range of the first welding robot can be expressed as (1, 4), and the second welding robot starts welding from the fourth band, and the welding band range of the second welding robot can be expressed as (4, 7).

[0076] In some embodiments, the processor may also use the overlapping position of the welding band range of each welding robot in at least one welding robot and the remaining welding robots as the welding alternating position.

[0077] In some embodiments, the processor can also directly use the welding start and end positions of the welding robot on the welding path as the welding alternating position according to the first welding path and the second welding path. For example, the welding start and end positions of the first welding robot on the first welding path and the welding start and end positions of the second welding robot on the second welding path are used as the welding alternating positions of the target cycle.

[0078] The closer the straight-line distance between the multiple welding alternating positions in the target cycle along the extension direction of the corrugated plate is, the greater the deformation value can be. The processor can match the welding band interval of the previous cycle, the welding parameters of at least one welding robot in the previous cycle, the first welding path and the second welding path of the target cycle, and the welding alternating position of the target cycle in the historical data by vector matching, and use the subsequent measured deformation data corresponding to the most similar data matched in the historical data as the deformation distribution of the target cycle. For an explanation of how to perform vector matching, see step 220.

[0079] Since the main factor causing the deformation of the corrugated plate is uneven temperature, and the position with the most uneven temperature is usually the welding alternating position, at this time, the distance between the two weldings is the shortest, and the deformation of the corrugated plate is also the most serious. Therefore, in the embodiment of this specification, by focusing on the welding alternating position, it is possible to effectively evaluate the welding alternating position, which is conducive to taking subsequent measures to reduce deformation. In addition, in the embodiment of this specification, since the deformation of the welding alternating position with the shortest welding distance (i.e., the most serious deformation) can be reduced, the deformation of the other positions with a longer welding distance (i.e., less deformation) can also be reduced.

[0080] In some embodiments, for any cycle, the processor can obtain the deformation distribution of the previous cycle through a scanning device; based on the deformation distribution of the previous cycle, the welding alternating position of the cycle (i.e., the target cycle), the welding band interval of the previous cycle and the corrugated plate parameters, the deformation distribution of the target cycle is determined through a deformation distribution prediction model.

[0081] In some embodiments, the scanning device may include a laser measuring instrument, a 3D scanner, a 3D photogrammetry system, a full-field strain measurement system, etc.

[0082] In some embodiments, the processor may scan the corrugated plate that has completed the welding process of the previous cycle through a scanning device, and identify the deformation position and the deformation value of the position, that is, the deformation distribution, according to the scanning result. The processor may identify the deformation position and the deformation value of the position according to image processing technology. The image processing technology may include one or more of edge detection, shape matching, three-dimensional reconstruction, digital image correlation method, pattern recognition and machine learning, image registration, deformation analysis, etc.

[0083] The deformation distribution prediction model is a model that can determine the deformation distribution of a period. In some embodiments, the deformation distribution prediction model can be a machine learning model. For example, the deformation distribution prediction model can be one or any combination of a neural network model (NN), a deep neural network model (DNN), etc.

[0084] In some embodiments, Figure 3 As shown, the input of the deformation distribution prediction model 350 may include the deformation distribution 310 of the previous cycle, the welding alternating position 320 of the target cycle, the welding band interval 330 of the previous cycle and the corrugated plate parameter 340, and the output of the deformation distribution prediction model 350 may be the deformation distribution 360 of the target cycle.

[0085] In some embodiments, the processor may train a deformation distribution prediction model based on multiple sets of labeled training samples. In some embodiments, the training samples may include sample welding band intervals, sample corrugated plate parameters, deformation distribution of the first time period of the sample, and welding alternating positions of the second time period of the sample, and the labels corresponding to the training samples may be deformation distributions obtained by actual scanning of the second time period of the sample. The first time period of the sample is earlier than the second time period of the sample.

[0086] In some embodiments, the processor may input a large number of training samples into the initial deformation distribution estimation model, construct a loss function based on the output of the initial deformation distribution estimation model and the labels of the corresponding training samples, and iteratively update the initial deformation distribution estimation model based on the loss function; when the value of the loss function meets the iteration completion condition, the training is completed and a trained deformation distribution estimation model is obtained. The iteration completion condition may include the convergence of the loss function, the number of iterations reaching a threshold, etc.

[0087] In the embodiments of the present specification, the deformation distribution of the cycle is estimated by a deformation distribution estimation model. The self-learning ability of the machine learning model can be used to find patterns from a large amount of historical data to obtain the relationship between the deformation distribution of the previous cycle, the welding alternating position of the cycle, the welding band interval of the previous cycle, the corrugated plate parameters and the deformation distribution of the cycle, etc., thereby improving the accuracy and efficiency of estimating the deformation distribution of the cycle.

[0088] In some embodiments, Figure 3 As shown, the input of the deformation distribution prediction model 350 may also include a welding temperature 370 and a welding process type 380 of at least one welding robot.

[0089] Welding temperature is the temperature at which the welding robot performs the welding process.

[0090] The welding process type refers to the process type of welding performed by the welding robot. In some embodiments, the welding process type may include one or more of metal inert gas shielded welding, tungsten inert gas shielded welding, resistance welding, plasma welding, laser welding, electron beam welding, ultrasonic welding, etc.

[0091] In some embodiments, the training samples of the deformation distribution prediction model may also include sample welding temperatures and sample welding process types. Accordingly, when applying the deformation distribution prediction model, the welding temperature and welding process type of at least one welding robot may also be input into the deformation distribution prediction model.

[0092] Different welding temperatures will cause different deformation positions and degrees of deformation of the material. Different welding process types between welding robots will cause different forces on the corrugated plate and produce different deformations. In the embodiment of this specification, the input of the deformation distribution prediction model includes welding temperature and welding process type, which can take into account the subtle differences caused by the welding robot on the welding plate, so that the determined deformation distribution is more in line with the actual situation.

[0093] Step 230 , determining a welding band interval of a period and / or a welding parameter of at least one welding robot based on the periodic deformation distribution.

[0094] In some embodiments, the processor can determine whether the deformation positions in the deformation distribution of the target cycle are concentrated in the middle of the corrugated plate welded in the target cycle; in response to the deformation positions in the deformation distribution of the target cycle being concentrated in the middle of the corrugated plate welded in the target cycle, the welding band interval of the target cycle and / or the welding parameters of at least one welding robot are determined based on a preset algorithm.

[0095] For example, the processor can appropriately increase the welding band interval of the target cycle and increase the welding interval time of all welding robots at the same time. The processor can further determine the welding parameters of each subsequent welding robot in sequence according to the welding time and welding interval time of the first welding robot. The first welding robot, that is, the welding robot that performs welding first, can be manually specified.

[0096] The processor can determine the welding start time of a welding robot (e.g., a second welding robot) based on the welding completion time and welding interval time of a previous welding robot (e.g., a first welding robot); and determine the welding completion time of the welding robot based on the welding start time and welding band interval of the welding robot.

[0097] In some embodiments, the processor can form multiple cluster centers by clustering the deformation positions of the deformation distribution of the target period; determine the center range of the corrugated plate welded by the welding robot; determine whether the multiple cluster centers fall within the center range; in response to the proportion of cluster centers falling within the center range being greater than a ratio threshold, determine that the deformation positions in the deformation distribution of the target period are concentrated in the middle of the corrugated plate welded by the target period.

[0098] In some embodiments, the processor may establish a coordinate system, use coordinates to represent the deformation position, and then form multiple cluster centers through a clustering algorithm. The clustering algorithm may include K-means clustering, mean shift algorithm, etc.

[0099] In some embodiments, the processor may pre-specify a center range, for example, a range within a preset distance near the central axis of the corrugated plate, wherein the center range refers to the corrugated plates welded by all welding robots within a target cycle, that is, the corrugated plates have only one center range within one cycle.

[0100] In some embodiments, the processor may determine whether the cluster center falls within the center range by determining whether the area where the cluster center is located coincides with the area where the center range is located or is surrounded by the area where the center range is located.

[0101] If the deformation is concentrated in the middle of the corrugated plate, it means that the deformation is caused when the welding temperature on both sides of the corrugated plate is transferred to the middle, which may be caused by the close welding distance. Therefore, by increasing the welding band interval, the heat can be dispersed. At the same time, the welding time interval between two adjacent robots needs to be longer to increase the cooling time of the plate, thereby reducing stress accumulation.

[0102] In some embodiments, the processor may also first determine the welding quality of the target cycle, and then determine whether it is necessary to determine the welding band interval of the target cycle and / or the welding parameters of at least one welding robot.

[0103] In some embodiments, for any cycle, the processor can determine the welding quality based on the deformation distribution of the cycle (i.e., the target cycle); in response to the welding quality being lower than the preset welding quality, determine the welding band interval of the cycle (i.e., the target cycle) and / or the welding parameters of at least one welding robot.

[0104] Welding quality refers to the parameter that measures the effect of welding deformation on the quality of the overall corrugated sheet. The more severe the deformation of the corrugated sheet, the worse the welding quality.

[0105] In some embodiments, the processor may cluster multiple deformation positions in the deformation distribution to obtain multiple cluster centers after clustering, each cluster center may correspond to multiple deformation positions and deformation values; and the welding quality is determined based on the multiple cluster centers. For more information about obtaining multiple cluster centers by clustering, please refer to the above description.

[0106] In some embodiments, the processor may determine the welding quality based on the average deformation value of each cluster center, the number of deformed positions corresponding to each cluster center, and the total number of deformed positions in the deformation distribution. For a single cluster center, the processor may average the deformation values ​​corresponding to all deformed positions of the cluster center to determine the average deformation value of the cluster center.

[0107] For example, the processor can determine the welding quality according to the average deformation value of each cluster center, the number of deformation positions corresponding to each cluster center, and the total number of deformation positions in the deformation distribution through formula (2):

[0108] (2)

[0109] in, Indicates welding quality, represents the average deformation value corresponding to the cluster center, represents the number of deformation positions corresponding to the cluster center, Represents the total number of deformed locations in the deformation distribution.

[0110] The preset welding quality is used to determine whether it is necessary to determine the preset value of the welding band interval and / or welding parameters. In some embodiments, the processor can use the average welding quality of the corrugated plates that pass the factory standard in the historical data as the preset welding quality. The corrugated plates that pass the factory standard refer to the corrugated plates that are qualified after being tested by a detection means (for example, laser detection, etc.).

[0111] In some embodiments, the preset welding quality may be related to the corrugated plate parameters. For example, the easier the corrugated plate material in the corrugated plate parameters is to deform, the lower the preset welding quality may be. In some embodiments, the processor may determine the preset welding quality by searching in a preset welding quality table according to the corrugated plate material. The preset welding quality table may include a variety of corrugated plate materials and corresponding reference preset welding qualities.

[0112] In the embodiments of the present specification, the preset welding quality is related to the corrugated plate parameters, and the influence of the residual value of the corrugated plate on the deformation is taken into consideration, so that it can be more accurately determined whether it is necessary to determine the welding band interval and / or welding parameters.

[0113] In some embodiments, the processor may determine the welding band interval of the target cycle according to the preset welding band interval, the preset welding quality and the welding quality. The preset band interval refers to the welding band interval corresponding to the preset welding quality. For example, the preset band interval may be the average welding band interval of the corrugated plate that passes the factory standard.

[0114] For example, the processor may determine the welding band interval according to the preset welding band interval, the preset welding quality and the welding quality by formula (3):

[0115] (3)

[0116] in, Indicates the welding band interval of the target cycle, Indicates the preset welding band interval, Indicates the preset welding quality, Indicates welding quality.

[0117] In some embodiments, the welding parameters may include a welding interval time, which refers to the time interval between two adjacent welding robots performing welding.

[0118] In some embodiments, the processor may determine the welding parameters of at least one welding robot of the target cycle based on the preset welding interval time, the preset welding quality and the welding quality. The preset welding interval time refers to the welding interval time corresponding to the preset welding quality. For example, the preset welding interval time may be the average welding interval time of the corrugated plate that passes the factory standard.

[0119] For example, the processor can determine the welding band interval according to the preset welding interval time, the preset welding quality and the welding quality by formula (4):

[0120] (4)

[0121] in, Indicates the welding interval time of the target cycle, Indicates the preset welding interval time. Indicates the preset welding quality, Indicates welding quality.

[0122] In some embodiments, in response to the welding quality being not lower than a preset welding quality, the processor may use the welding band interval of the previous cycle and / or the welding parameters of at least one welding robot of the previous cycle as the welding band interval of the target cycle and / or the welding parameters of at least one welding robot.

[0123] In the embodiments of this specification, the welding process is required according to the average condition of the corrugated plates that pass the exit standards, so that the welded corrugated plates can meet the exit quality requirements to a certain extent, at least to the greatest extent, thereby reducing the probability of scrapped products.

[0124] In some embodiments, the processor can determine candidate welding parameters and candidate welding band intervals; determine an estimated deformation distribution based on the candidate welding parameters, candidate welding band intervals, the welding temperature of at least one welding robot, and the welding process type; based on the estimated deformation distribution, determine the periodic welding band interval and / or the welding parameters of at least one welding robot.

[0125] The candidate welding parameter refers to a parameter that can be used as an alternative welding parameter. The candidate welding band interval refers to a value that can be used as an alternative welding band interval. The candidate welding parameter and the candidate welding band interval each include at least one.

[0126] In some embodiments, the processor may use welding parameters with a higher number of times of use in historical data as candidate welding parameters. For example, the processor may use a preset number of welding parameters with the highest number of times of use in historical data as candidate welding parameters.

[0127] In some embodiments, the processor may randomly generate candidate welding parameters and / or candidate welding band intervals. For example, the random generation method may include uniform distribution random generation, normal distribution random generation, discrete distribution random generation, etc.

[0128] The estimated deformation distribution refers to the estimated deformation distribution of the corrugated plate after welding is completed using the candidate welding parameters and the candidate welding band interval in the target cycle.

[0129] In some embodiments, the processor may construct the candidate welding parameters, the candidate welding band interval, the welding temperature of at least one robot, and the welding process type as a second vector, and construct the welding parameters, welding band interval, the welding temperature of at least one robot, and the welding process type in the historical data as a second reference vector. The processor may match the second vector with multiple second reference vectors in the historical data, and use the deformation distribution after welding corresponding to the second reference vector with the highest similarity to the second vector as the estimated deformation distribution.

[0130] In some embodiments, the processor can also determine an estimated deformation distribution based on candidate welding parameters, candidate welding band intervals, welding temperature of at least one welding robot, welding process type, deformation distribution of the previous cycle, welding alternating positions of the target cycle and corrugated plate parameters.

[0131] For relevant information about welding temperature, welding process type, welding alternating positions in the cycle and corrugated plate parameters, please refer to the previous article.

[0132] In some embodiments, the processor may input candidate welding parameters, candidate welding band intervals, welding temperature of at least one welding robot, welding process type, deformation distribution of the previous cycle, welding alternating positions of the target cycle, and corrugated plate parameters into the deformation distribution prediction model, and the deformation distribution prediction model outputs the estimated deformation distribution of the target cycle corresponding to the candidate welding parameters and the candidate welding band interval. For more information about the deformation distribution prediction model, please refer to the above, which will not be repeated here.

[0133] In an embodiment of the present specification, based on candidate welding parameters, candidate welding band intervals, welding temperature of at least one welding robot, welding process type, deformation distribution of the previous cycle, welding alternating positions of the cycle and corrugated plate parameters, a more accurate estimated deformation distribution can be determined to determine the welding band interval or welding parameters of the cycle.

[0134] In some embodiments, for each set of candidate welding parameters and candidate welding band intervals, the processor may determine the candidate welding parameters and candidate welding band intervals corresponding to the minimum average deformation value in the estimated deformation distribution as the welding band interval of the target cycle and / or at least one welding robot welding parameter. The processor may average the deformation values ​​corresponding to all deformation positions in the estimated deformation distribution to determine the average deformation value in the estimated deformation distribution.

[0135] In the embodiments of this specification, by estimating the deformation distribution after the cycle is completed to measure or select the most suitable welding parameters and welding band interval, the welding process can be controlled with the suppression of deformation as the guide, thereby improving the final welding quality of the corrugated plate.

[0136] In the embodiments of this specification, by periodically determining the welding band interval and / or welding parameters of each cycle, the welding strategy can be dynamically adjusted according to parameters such as the material and thickness of the corrugated plate combined with real-time monitoring data to minimize welding deformation and improve welding quality and efficiency.

[0137] It should be noted that the above description of process 200 is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 200 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0138] One or more embodiments of the present specification provide a device for controlling the welding deformation of a corrugated plate, comprising a processor, wherein the processor is used to execute a method for controlling the welding deformation of a corrugated plate as described in any embodiment of the present specification.

[0139] One or more embodiments of the present specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method for controlling the welding deformation of a corrugated plate described in any embodiment of the present specification.

[0140] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0141] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0142] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0143] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0144] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of the range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0145] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification is hereby incorporated by reference in its entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0146] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for controlling the welding deformation of a corrugated plate, characterized in that: The method is executed by a processor, and the method includes: The welding band interval and / or the welding parameters of at least one welding robot are periodically determined based on a preset cycle, wherein the cycle length of the preset cycle is determined based on the corrugated plate parameters; the welding band interval refers to the number of bands between any two welding paths when performing preset mode welding; For any cycle: Determine a first welding path and a second welding path of the cycle, wherein the first welding path and the second welding path are welding paths corresponding to two sides of the corrugated plate respectively; Determining the deformation distribution of the cycle based on the welding band interval of the previous cycle, the first welding path and the second welding path includes: Based on the welding band interval of the previous cycle, the first welding path and the second welding path, determining the welding alternating position of the cycle; the welding alternating position refers to the alternating position of the two welding robots when welding; determining a deformation distribution of the cycle based on the welding alternating positions of the cycle; The welding band interval of the cycle and / or the welding parameters of the at least one welding robot are determined based on the deformation distribution of the cycle.

2. The method according to claim 1, characterized in that Determining the deformation distribution of the cycle based on the welding alternating positions of the cycle includes: Obtain the deformation distribution of the previous cycle through a scanning device; Based on the deformation distribution of the previous cycle, the welding alternating position of the cycle, the welding band interval of the previous cycle and the corrugated plate parameters, the deformation distribution of the cycle is determined by a deformation distribution prediction model, and the deformation distribution prediction model is a machine learning model.

3. The method according to claim 1, characterized in that The step of determining the welding band interval of the cycle and / or the welding parameters of the at least one welding robot based on the deformation distribution of the cycle comprises: determining welding quality based on the deformation distribution of the cycle; In response to the welding quality being lower than a preset welding quality, the welding band interval of the cycle and / or the welding parameters of the at least one welding robot are determined.

4. The method according to claim 3, characterized in that: Determining the welding band interval of the cycle and / or the welding parameters of the at least one welding robot comprises: determining candidate welding parameters and candidate welding band intervals; Determining an estimated deformation distribution based on the candidate welding parameters, the candidate welding band intervals, a welding temperature of at least one welding robot, and a welding process type; Based on the estimated deformation distribution, the welding band interval of the cycle and / or the welding parameters of the at least one welding robot are determined.

5. A control system for the welding deformation of a corrugated plate, characterized in that: The system comprises: A determination module, periodically determining a welding band interval and / or a welding parameter of at least one welding robot based on a preset period, wherein the period length of the preset period is determined based on the corrugated plate parameter; the welding band interval refers to the number of bands between any two welding paths when performing preset mode welding; The determination module comprises: A path determination module is configured to determine, for any cycle, a first welding path and a second welding path of the cycle, wherein the first welding path and the second welding path are welding paths corresponding to two sides of the corrugated plate respectively; The distribution determination module is configured to determine, for any cycle, the deformation distribution of the cycle based on the welding band interval of the previous cycle, the first welding path and the second welding path, and the distribution determination module is further configured to: Based on the welding band interval of the previous cycle, the first welding path and the second welding path, determining the welding alternating position of the cycle; the welding alternating position refers to the alternating position of the two welding robots when welding; determining a deformation distribution of the cycle based on the welding alternating positions of the cycle; The parameter determination module is configured to determine, for any cycle, the welding band interval of the cycle and / or the welding parameters of the at least one welding robot based on the deformation distribution of the cycle.

6. The system according to claim 5, characterized in that The distribution determination module is further configured to: Obtain the deformation distribution of the previous cycle through a scanning device; Based on the deformation distribution of the previous cycle, the welding alternating position of the cycle, the welding band interval of the previous cycle and the corrugated plate parameters, the deformation distribution of the cycle is determined by a deformation distribution prediction model, and the deformation distribution prediction model is a machine learning model.

7. The system according to claim 5, characterized in that The parameter determination module is further configured to: determining welding quality based on the deformation distribution of the cycle; In response to the welding quality being lower than a preset welding quality, the welding band interval of the cycle and / or the welding parameters of the at least one welding robot are determined.

8. A computer-readable storage medium storing computer instructions, characterized in that: After the computer reads the computer instructions in the storage medium, the computer executes the method for controlling the welding deformation of a corrugated plate as described in any one of claims 1 to 4.

Images