Welding process parameter determination method, device, equipment, medium and program product

Abstract

The invention relates to the technical field of welding, and provides a welding process parameter determining method, device and equipment, a medium and a program product. According to characteristic parameters in the welding material information, at least one reference variable quantity of the characteristic parameters is determined; the reference variable quantity is a deviation value between the characteristic parameter and a preset reference quantity; taking the at least one reference variation as a target reference variation, and determining a first welding process parameter of the welding material according to the target reference variation and preset logic association information; the logical association information is used for representing a logical relationship between the reference variation and the welding process parameters. According to the welding material information and the logic relation between the reference variation and the welding process parameters, optimization of the welding process parameters is achieved, the stability of the welding quality and the production efficiency are improved, and the cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of welding technology, and in particular to a method, device, equipment, medium and program product for determining welding process parameters. Background Art

[0002] In the welding production process of thick plate cylindrical container shells, although automated welding technology has greatly improved production efficiency, it still faces many challenges in practical applications, especially when the consistency of incoming materials in the previous process is poor, the automatic welding station usually has welding defects, quality fluctuations and other problems. These problems not only affect the welding quality, but also lead to additional man-hours (such as gouging, repair welding, grinding, etc.), increase production costs, and affect production progress. Based on this, how to optimize the welding process parameters has become an urgent problem to be solved. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a method for determining welding process parameters, which realizes the optimization of welding process parameters through the welding material information and the logical relationship between the reference change amount and the welding process parameters, thereby improving the stability of welding quality, production efficiency, and reducing costs.

[0004] The present invention also provides a welding process parameter determination device, an electronic device, a non-transitory computer-readable storage medium and a computer program product.

[0005] A method for determining welding process parameters according to a first embodiment of the present invention includes: Get welding material information; Determine at least one reference variation of the characteristic parameter according to the characteristic parameter in the welding material information; the reference variation is a deviation between the characteristic parameter and a preset reference variation; At least one of the reference changes is used as a target reference change, and a first welding process parameter of the welding material is determined according to the target reference change and preset logical association information; the preset logical association information is used to represent the logical relationship between the reference change and the welding process parameter.

[0006] According to an embodiment of the present invention, determining the first welding process parameter of the welding material according to the target reference variation and the preset logical association information includes: In the case where one of the reference changes is used as the target reference change, the target reference change is input as an input parameter into a first relationship model in the logical association information to obtain a first welding process parameter of the welding material output by the first relationship model; In the case where at least two of the reference changes are used as the target reference changes, at least two of the target reference changes are input into a second relationship model in the logical association information to obtain a first welding process parameter of the welding material output by the second relationship model; The input parameter of the first relationship model is a single target reference change, and the input parameter of the second relationship model is at least two target reference changes.

[0007] According to an embodiment of the present invention, the first relationship model is determined based on the following method: Acquiring a sample characteristic parameter, and measuring a change value of a sample welding process parameter while changing a sample reference change amount of the sample characteristic parameter; Under multiple sample reference value change ranges, respectively record the change values ​​of the sample welding process parameters to form multiple groups of first data points; Performing curve fitting on the plurality of groups of the first data points to obtain first curve information for describing the relationship between the sample baseline variation and the sample welding process parameters; The first relationship model is determined according to the first curve information.

[0008] According to one embodiment of the present invention, the second relationship model is determined based on the following method: Acquire a sample characteristic parameter, and determine a reference amount adjustment range of the sample characteristic parameter according to a weight of the sample characteristic parameter; According to the reference amount adjustment amplitude of the sample characteristic parameter, the sample reference variation amounts of a plurality of the sample characteristic parameters are changed simultaneously to measure the variation value of the sample welding process parameter; Under multiple sample base value variation ranges, respectively recording the variation values ​​of the sample welding process parameters to form multiple groups of second data points; Performing curve fitting on the plurality of groups of the second data points to obtain second curve information for describing the relationship between the sample baseline variation and the sample welding process parameters; The second relationship model is determined according to the second curve information.

[0009] According to one embodiment of the present invention, the weight of the sample characteristic parameter is determined based on the following method: Analyze historical welding data to determine the influence of the sample characteristic parameters on the welding results; Determining a first weight of the sample feature parameter according to the influence information; Analyze a plurality of welding scenes to determine a second weight of the sample characteristic parameter in each of the welding scenes; The weight of the sample feature parameter is determined according to the first weight and the second weight.

[0010] According to an embodiment of the present invention, determining the first relationship model according to the first curve information includes: Optimizing the first curve information according to a first process parameter interval in which a deviation exists in the first curve information, or a second process parameter interval that affects welding quality; Determining the first relationship model according to the optimized first curve information; The determining the second relationship model according to the second curve information includes: Optimizing the second curve information according to a third process parameter interval in which a deviation exists in the second curve information, or a fourth process parameter interval that affects welding quality; The second relationship model is determined according to the optimized second curve information.

[0011] According to an embodiment of the present invention, after determining the first welding process parameter of the welding material according to the target reference variation and the preset logical association information, the method further includes: Perform a welding operation according to the first welding process parameters; During the welding process, collect welding pictures and / or welding waveforms; Performing image analysis on the welding image and / or the welding waveform image to determine the welding result; Determining a second welding process parameter of the welding material according to the welding result; A welding operation is performed according to the second welding process parameters.

[0012] According to a second aspect of the present invention, a device for determining welding process parameters includes: An acquisition module, used to acquire welding material information; A deviation determination module, used to determine at least one reference variation of the characteristic parameter according to the characteristic parameter in the welding material information; the reference variation is the deviation of the characteristic parameter from a preset reference value; The welding process parameter determination module is used to use at least one of the reference changes as a target reference change, and determine the first welding process parameter of the welding material according to the target reference change and preset logical association information; the preset logical association information is used to represent the logical relationship between the reference change and the welding process parameter.

[0013] According to an embodiment of the third aspect of the present invention, the electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, it implements any one of the above-mentioned methods for determining welding process parameters.

[0014] According to the non-transitory computer-readable storage medium of the fourth aspect of the present invention, a computer program is stored thereon, and when the computer program is executed by a processor, the method for determining welding process parameters as described in any one of the above is implemented.

[0015] A computer program product according to an embodiment of the fifth aspect of the present invention comprises a computer program, and when the computer program is executed by a processor, the computer program implements any one of the above-mentioned methods for determining welding process parameters.

[0016] The above one or more technical solutions in the embodiments of the present invention have at least one of the following technical effects: According to the welding material information and the logical relationship between the reference change and the welding process parameters, the welding process parameters are optimized, which improves the stability of welding quality, production efficiency and reduces costs; By deploying a real-time online monitoring system during the welding process, continuously tracking various key parameters of the welding process, and making dynamic adjustments based on real-time collected data, this closed-loop control can not only solve the quality fluctuations caused by inconsistent dimensions (such as groove angle, gap, misalignment, etc.) during the welding process, but also improve the quality and consistency of the welded joints by optimizing the welding process parameters in real time.

[0017] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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.

[0019] Figure 1 It is a flow chart of a method for determining welding process parameters provided in an embodiment of the present invention.

[0020] Figure 2 It is a schematic diagram of a curve showing a change in swing amplitude versus groove width provided in an embodiment of the present invention.

[0021] Figure 3 It is a schematic diagram of a curve showing a change in welding current versus groove width provided in an embodiment of the present invention.

[0022] Figure 4 It is a structural schematic diagram of a welding process parameter determination device provided in an embodiment of the present invention.

[0023] Figure 5 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0025] In the description of the embodiments of the present invention, it should be noted that the terms “first”, “second” and “third” are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0026] In the embodiments of the present invention, unless otherwise clearly specified and limited, the first feature being "above" or "below" the second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, the first feature being "above", "above" and "above" the second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. The first feature being "below", "below" and "below" the second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0027] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0028] In the welding production process of thick plate cylindrical container shells, there are the following problems: 1) The dimensional consistency of the incoming material groove angle, misalignment, gap, etc. is poor, and the automatic welding cannot cover the current errors, resulting in problems such as welding penetration and molten pool collapse; 2) There will be welding spots inside the groove. Some welding spots fill the weld groove, making it difficult for the automatic welding setting current to penetrate the welding spot position, resulting in defects such as lack of fusion; 3) After rolling, the straightness of the cylinder is poor, which will form bulges or depressions, resulting in uncontrollable back penetration and defects.

[0029] In related technologies, welding automation equipment mainly relies on preset standard parameters and cannot be dynamically adjusted and optimized according to variables in the actual production process. The lack of optimization methods for intelligent systems makes it difficult for production lines to achieve refined control of the welding process, resulting in frequent quality fluctuations.

[0030] Based on the above problems, the present invention proposes a method for determining welding process parameters, specifically a welding process optimization technology based on an online welding quality monitoring system.

[0031] Figure 1 Schematic diagram of a method for determining welding process parameters provided by an embodiment of the present invention. Figure 1 , an embodiment of the present invention provides a method for determining welding process parameters, comprising: Step 101, obtaining welding material information.

[0032] The executor of the present invention may be welding equipment, welding device, etc., wherein the welding equipment, welding device, etc. are provided with an arc welding online monitoring system, which includes a closed-loop optimization function for welding process parameters.

[0033] Welding material information can be obtained through external information before welding, or it can be detected and identified by the system during the welding process. Among them, welding materials can be understood as the process of cutting, sandblasting, rolling and other processes in the entire pre-welding process, and finally the various parts are combined together through the assembly link to form a complete structural unit to be welded. The assembled material is the "incoming material" that the arc welding online monitoring system pays attention to. It contains all the previously processed parts, and these parts have been preliminarily configured in position and shape according to the requirements of welding.

[0034] Step 102: Determine at least one reference variation of the characteristic parameter according to the characteristic parameter in the welding material information.

[0035] Before welding, the arc welding online monitoring system will extract characteristic parameters from the welding material information, where the characteristic parameters may include: plate thickness, which indicates the thickness of the welding workpiece; length, which indicates the length of the workpiece; diameter, if it is a welding workpiece with a circular cross-section such as a pipe, its diameter needs to be obtained; groove angle, which indicates the groove angle of the welding joint, which usually affects the heat input and molten pool shape during welding; gap, which indicates the gap size of the joint part of the welding workpiece; misalignment, which indicates the degree of misalignment of the joint part of the welding workpiece.

[0036] After extracting the characteristic parameters, each characteristic parameter is compared with its corresponding preset reference quantity to calculate the deviation between the two, that is, the reference change (δ m). For example, assuming that the groove angle measured during the welding process is 21 degrees, and the design requires the groove angle to be 20 degrees, then the reference change (δ m) is 21-20=1 degree. Among them, the reference change (δ m) can be positive or negative: positive deviation, that is, the actual measurement value is greater than the reference value, indicating that the size is too large; negative deviation, that is, the actual measurement value is less than the reference value, indicating that the size is too small.

[0037] Step 103: taking at least one of the reference changes as a target reference change, and determining a first welding process parameter of the welding material according to the target reference change and preset logical association information.

[0038] It can be understood that the target reference variation includes at least one reference variation, and the logical association information is used to represent the logical relationship between the reference variation and the welding process parameters, and the logical association information can be represented by a function. Among them, the welding process parameters can include parameters such as welding current, voltage, swing amplitude, welding speed, etc.

[0039] At least one reference variation is used as a target reference variation, and the first welding process parameters of the welding material are determined according to the target reference variation and the preset logical association information. For example, the reference variation corresponding to the groove angle, gap, misalignment, etc. is pre-established with a logical relationship with the welding process parameters (such as welding current, voltage, swing amplitude, welding speed), and then the welding process parameters are optimized and recommended in combination with the target reference variation. Among them, the first welding process parameters can be understood as the optimal welding process parameters, which are a set of process parameter combinations that can maximize welding efficiency, save energy and materials, and reduce defects while ensuring welding quality. Optionally, the optimal process parameters are a dynamic adjustment process that can be fed back and adjusted in real time, especially in a changing production environment.

[0040] In one embodiment, when a baseline change is used as a target baseline change, the target baseline change is input as an input parameter into a first relationship model in the logical association information to obtain a first welding process parameter of the welding material output by the first relationship model; when at least two baseline changes are used as target baseline changes, at least two target baseline changes are input into a second relationship model in the logical association information to obtain a first welding process parameter of the welding material output by the second relationship model; wherein the input parameter of the first relationship model is a single target baseline change, and the input parameter of the second relationship model is at least two target baseline changes.

[0041] It can be understood that both the first relationship model and the second relationship model are used to describe the logical relationship between the reference variation and the welding process parameters. Specifically, the first function expression corresponding to the first relationship model can be a univariate multivariate function including an independent variable, which is used to describe the logical relationship between a reference variation and a welding process parameter. By adjusting the reference variation, the welding process parameter can be optimized. The second function expression corresponding to the second relationship model can be a multivariate linear function including more than two independent variables, which is used to describe the logical relationship between multiple reference variations and a welding process parameter. By adjusting multiple reference variations, a welding process parameter can be jointly optimized. Among them, the independent variable is the sample reference variation of the sample characteristic parameter.

[0042] For example, suppose is the passive variable (i.e. welding process parameter), is the baseline change, where Indicates Baseline changes, Indicates The first benchmark change corresponds to welding process parameters.

[0043] if and There is a one-to-one corresponding change relationship, and the first function expression can be expressed as: ; (1) in, , , , , are all constants and can be obtained by curve fitting; and In the logical relationship of Figure 2 , the logical relationship between the swing amplitude and the groove width is: ; refer to Figure 3 , the logical relationship between welding current and groove width is: .

[0044] if and There is a one-to-many change relationship, and the second function expression can be expressed as: ; (2) in, , , , It is obtained based on formula (1). By expanding formula (2) with reference to formula (1), we can obtain: ; (3) in, Welding process parameters determined by multiple reference variations; , , , , are all constants and can be obtained by curve fitting; and In the logical relationship, the corresponding constants are different.

[0045] Optionally, the second function expression may also be a multivariate function including multiple independent variables, as shown in formula (3).

[0046] After determining the logical relationship between the reference variation and the welding process parameters, the welding process parameters can be optimized based on the logical relationship. For example, assuming that the reference variation includes: the reference variation of the groove angle and the gap, and the welding process parameter to be determined is the swing amplitude. At this time, the reference variation of the groove angle can be used as an input parameter and input into the first relationship model. The first relationship model outputs the swing amplitude corresponding to the reference variation of the groove angle through formula (1), and the reference variation of the gap can be used as an input parameter and input into the first relationship model. The first relationship model outputs the swing amplitude corresponding to the reference variation of the gap through formula (1); the reference variation of the groove angle and the gap can also be used as input parameters at the same time and input into the second relationship model. The second relationship model outputs the swing amplitude corresponding to the reference variation of the groove angle and the gap through formula (2).

[0047] The welding process parameter determination method provided by the embodiment of the present invention obtains welding material information; determines at least one reference variation of the characteristic parameter according to the characteristic parameter in the welding material information; the reference variation is the deviation between the characteristic parameter and the preset reference variation; uses at least one reference variation as the target reference variation, and determines the first welding process parameter of the welding material according to the target reference variation and preset logical association information; the logical association information is used to represent the logical relationship between the reference variation and the welding process parameter. The present invention realizes the optimization of welding process parameters according to the welding material information and the logical relationship between the reference variation and the welding process parameter, improves the stability of welding quality, production efficiency, and reduces costs.

[0048] Based on the above embodiment, the first function expression is determined based on the following method: Step 110, obtaining a sample characteristic parameter, and measuring a change value of a sample welding process parameter while changing a sample reference change amount of the sample characteristic parameter; Step 111, recording the change values ​​of the sample welding process parameters under multiple sample reference value change ranges respectively to form multiple groups of first data points; Step 112, performing curve fitting on the plurality of groups of the first data points to obtain first curve information for describing the relationship between the sample baseline variation and the sample welding process parameters; Step 113: determine the first relationship model according to the first curve information.

[0049] Specifically, each time a sample benchmark change (such as groove angle) is changed, the corresponding change values ​​of other sample welding process parameters (such as welding current, filling amount, swing amplitude, etc.) are measured; under different sample benchmark change amplitudes (such as different degrees of forward and reverse changes in groove angle), the corresponding change values ​​of the sample welding process parameters are recorded respectively to form multiple groups of first data points, and finally the multiple groups of first data points collected are curve fitted to obtain a function used to describe the relationship between the sample benchmark change and the sample welding process parameters, and the function is used as the first function expression.

[0050] Taking the relationship between welding current and groove angle as an example, when the angle of the groove changes relative to the standard groove, the welding current and other welding process parameters (such as filling amount, swing, etc.) also need to be adjusted accordingly. For example, assuming that the groove becomes larger by 10 degrees, in order to prevent welding through, the original current is too large. At this time, it is necessary to determine the appropriate welding current and filling amount and other parameters. This set of data (such as the change in current and filling amount corresponding to the groove change of 10 degrees) is a data point. Similarly, when the groove changes by 5 degrees and 15 degrees, there will be corresponding appropriate values ​​of current, swing and other parameters. At the same time, it is also necessary to consider the forward and reverse directions to determine the data points, that is, not only the case where the groove becomes larger (forward), but also the case where the groove becomes smaller (reverse). By determining the appropriate values ​​of welding current, swing and other parameters corresponding to the groove under different changes (such as ±5 degrees, ±10 degrees, ±15 degrees, etc.), multiple data points are obtained. After obtaining these data points, express them in a coordinate system (the X-axis can be the change in the groove angle, and the Y-axis can be the change in the corresponding welding process parameters, such as current, filling amount, swing, etc.). Use mathematical methods (curve fitting) to connect these data points into a curve (such as Figure 2-Figure 3 As shown in Figure 2, the mathematical expression of this curve is used to describe the logical relationship between the welding process parameters and the groove angle. Based on the curve information obtained by fitting, the first relationship model is established.

[0051] In one embodiment, the first curve information is optimized according to a first process parameter interval in which a deviation exists in the first curve information, or a second process parameter interval that affects welding quality; and a first relationship model is determined according to the optimized first curve information.

[0052] It is understandable that, since the actual welding situation is very complex and is affected by many factors, the preliminary fitting curve may have a large discrepancy with the actual situation in some intervals. For example, when welding workpieces with different material combinations and a large range of groove angle variations, it is possible to operate according to the welding current corresponding to the preliminary fitting curve within a certain groove angle interval, but find that the welding effect is not good, and problems such as unsightly weld formation and insufficient penetration appear. This indicates that there is a large deviation between the fitting situation in this interval and the actual situation, that is, the first process parameter interval. In addition, there are some intervals that involve key control points of welding quality, and the precise matching of parameters is very high. For example, when welding some pressure vessel welds that have extremely high requirements for strength and sealing, the matching accuracy requirements between parameters such as groove size and welding current are far beyond ordinary welding. If there are deviations in these intervals, it will lead to serious quality risks, so it is necessary to accurately determine the key interval of parameters, that is, the second process parameter interval that affects welding quality.

[0053] For the intervals with large deviations in the first curve information (i.e., the first process parameter interval) or the critical intervals (i.e., the second process parameter interval), more refined measurements and experiments can be taken to re-determine the process parameters of each point in these intervals to improve the accuracy of the fitting curve in these intervals. For example, in the intervals with large deviations, the density of experimental data is increased, and as much experimental data as possible is collected, especially in places where the key parameters change greatly. Through more accurate experimental results, it can be ensured that the fitting curve can better reflect the dynamic changes in the actual welding process. After obtaining more accurate parameter values, the nodes in the fitting curve are adjusted and the points are reconnected, so that the final fitting curve is more accurate in these critical intervals. Finally, according to the optimized fitting curve, the first relationship model is established. By optimizing the fitting curve to better reflect the relationship between the actual welding process parameters, especially in the intervals with large changes or deviations in the welding process, by accurately adjusting the parameter values ​​of these intervals, the accuracy of the fitting curve can be improved, thereby providing more reliable guidance for the actual welding operation and ensuring the stability and consistency of the welding quality.

[0054] The embodiment of the present invention determines the appropriate values ​​of the welding process parameters under different changing conditions through actual measurement and adjustment, and then uses mathematical curve fitting to obtain a first function expression describing the relationship between the sample baseline change and the sample welding process parameters, so as to achieve the optimization of the welding process parameters based on the first function expression.

[0055] Based on the above embodiment, the second function expression is determined based on the following method: Step 120, obtaining sample characteristic parameters, and determining a reference adjustment range of the sample characteristic parameters according to the weights of the sample characteristic parameters; Step 121, adjusting the amplitude according to the reference amount of the sample characteristic parameter, and changing the sample reference variation of a plurality of the sample characteristic parameters at the same time, so as to measure the variation value of the sample welding process parameter; Step 122, recording the change values ​​of the sample welding process parameters under multiple sample base value change ranges respectively to form multiple groups of second data points; Step 123, performing curve fitting on the plurality of groups of the second data points to obtain second curve information for describing the relationship between the sample baseline variation and the sample welding process parameters; Step 124: Determine the second relationship model according to the second curve information.

[0056] Each characteristic parameter (such as plate thickness, groove angle, current, etc.) has an unequal impact on the welding process parameters. The weight is introduced to quantify the difference in this impact so as to more accurately optimize the welding process parameters. The weight can be determined through historical welding data, welding scenarios, experience or experiments to quantify the importance of each characteristic parameter.

[0057] In one embodiment, the weight of the sample characteristic parameter is determined based on the following method: analyzing historical welding data to determine the influence information of the sample characteristic parameter on the welding result; determining the first weight of the sample characteristic parameter based on the influence information; analyzing multiple welding scenes to determine the second weight of the sample characteristic parameter in each welding scene; determining the weight of the sample characteristic parameter based on the first weight and the second weight.

[0058] Specifically, by analyzing historical welding data, the influence of each sample characteristic parameter (such as current, voltage, welding speed, etc.) on the welding results (such as welding quality, weld strength, etc.) is evaluated. Based on this analysis, the relative importance of each sample characteristic parameter in the entire data set is determined to obtain a first weight. For example, statistical methods (such as regression analysis, correlation analysis, etc.) can be used to evaluate the relationship between sample characteristic parameters and welding results.

[0059] Welding scenarios may involve different factors such as materials, plate thickness, and welding methods. In different welding scenarios, the same sample characteristic parameters may have different effects on the welding results. Therefore, multiple welding scenarios are analyzed, and the second weight of each sample characteristic parameter is determined according to the degree of influence of each sample characteristic parameter in each scenario. For example, suppose the welding scenarios include: scenario A: thin plate welding (e.g., 2mm steel plate); scenario B: thick plate welding (e.g., 10mm steel plate). In scenario A, the welding speed may have a greater impact on the welding quality, because thin plates are more easily affected by the welding speed. Welding too fast may result in incomplete penetration, and too slow may result in overheating. In scenario B, the current may have a greater impact on the welding quality, because thicker plates require higher currents to ensure good fusion. By analyzing the welding results in different scenarios, the second weight of each sample characteristic parameter can be obtained. Assume that the following conclusions are obtained through analysis: Scenario A (thin plate welding): the second weight of current (I) is 0.3, and the second weight of welding speed (V) is 0.7; Scenario B (thick plate welding): the second weight of current (I) is 0.8, and the second weight of welding speed (V) is 0.2.

[0060] Finally, the first weight and the second weight are combined to obtain the comprehensive weight of each sample feature parameter. For example, the first weight and the second weight are weighted and summed to obtain the comprehensive weight. The comprehensive weight can more accurately reflect the relative importance of each feature in different scenarios, thereby providing more precise guidance for the optimization of the welding process.

[0061] By combining the first weight obtained from historical data analysis with the second weight obtained in different scenarios, a more accurate and flexible feature weight can be obtained. Based on this, it is possible to cope with the different effects of parameters on the results in different welding scenarios, thereby providing a scientific basis for the optimization of the actual welding process.

[0062] According to the weight of the sample characteristic parameter, the adjustment range of the base quantity of the sample characteristic parameter is determined. For example, if the weight of the plate thickness is large, the adjustment range of the plate thickness is large; if the weight of the groove angle is small, the adjustment range of the groove angle is small. According to the adjustment range of the base quantity of the sample characteristic parameter, multiple sample base quantity changes (such as groove angle) are changed each time, and the corresponding change values ​​of other sample welding process parameters (such as welding current, filling amount, swing amplitude, etc.) are measured; under different sample base quantity change ranges (such as different degrees of forward and reverse changes in groove angle), the corresponding change values ​​of the sample welding process parameters are recorded respectively to form multiple groups of second data points, and finally the collected multiple groups of second data points are curve fitted to obtain a function used to describe the relationship between the sample base quantity change and the sample welding process parameters, and the function is used as the second function expression.

[0063] Taking the relationship between welding current, groove angle and plate thickness as an example, the initial standard groove angle is set to 30 degrees, the standard plate thickness is 6mm, and the corresponding standard welding current is 100A. This set of initial values ​​is used as the benchmark for subsequent changes. Change the groove angle and plate thickness, and record the corresponding welding current: when the groove angle increases to 40 and the plate thickness remains unchanged at 6mm, after multiple welding tests, it is found that in order to ensure the welding quality, the welding current needs to be adjusted to 85A, and the data points (10 degrees, 6, 15A) are obtained. Among them, the change in groove angle is used as the first independent variable of the X-axis, the plate thickness is the second independent variable of the X-axis, and the change in welding current is used as the dependent variable of the Y-axis. When the groove angle is reduced to 25 degrees, the plate thickness is still 6mm, and the welding current should be adjusted to 110A, and the data points (-5 degrees, 6, 10A) are obtained. When the groove angle is 35 degrees, the plate thickness increases to 8mm, the welding current is adjusted to 90A, and the data points (5 degrees, 8, 10A) are recorded. When the groove angle is maintained at 30 degrees, the plate thickness is reduced to 4mm, and the welding current becomes 120A, the corresponding data points are (0 degrees, 4, 20A). Continue to change the combination of groove angle and plate thickness, such as the groove angle becomes 45 degrees, the plate thickness is 7mm, and the welding current is adjusted to 75A, forming data points (15 degrees, 7, 25A). Considering that the influence of groove angle and plate thickness on welding current may be more complicated and not a simple linear relationship, multivariate linear or multivariate multivariate functions are selected for fitting, and the above collected data points are substituted into the fitting function to obtain the influence function of groove angle and plate thickness on welding current. Based on this influence function, the second relationship model is established.

[0064] In one embodiment, the second curve information is optimized according to the third process parameter interval in which a deviation exists in the second curve information, or the fourth process parameter interval that affects the welding quality; and the second relationship model is determined according to the optimized second curve information.

[0065] It can be understood that the third process parameter interval has the same meaning as the first process parameter interval, and both represent intervals with large deviations of the preliminary fitting curve. For the intervals with large deviations in the second curve information (i.e., the third process parameter interval) or the fourth process parameter interval that affects the welding quality, more precise measurements and experiments can be taken to re-determine the process parameters of each point in these intervals to improve the accuracy of the fitting curve in these intervals. For example, in intervals with large deviations, the density of experimental data is increased, and as much experimental data as possible is collected, especially in places where key parameters change greatly. More accurate experimental results can ensure that the fitting curve can better reflect the dynamic changes in the actual welding process. After obtaining more accurate parameter values, the nodes in the fitting curve are adjusted and the points are reconnected, so that the final fitting curve is more accurate in these key intervals. Finally, according to the optimized fitting curve, a second relationship model is established. By optimizing the fitting curve to better reflect the relationship between the actual welding process parameters, especially in intervals with large changes or deviations in the welding process, the accuracy of the fitting curve can be improved by accurately adjusting the parameter values ​​of these intervals, thereby providing more reliable guidance for actual welding operations and ensuring the stability and consistency of welding quality.

[0066] The embodiment of the present invention determines the appropriate values ​​of the welding process parameters under different changing conditions through actual measurement and adjustment, and then uses mathematical curve fitting to obtain a second function expression describing the relationship between the sample baseline change and the sample welding process parameters, so as to achieve the optimization of the welding process parameters based on the second function expression.

[0067] Based on the above embodiment, after determining the first welding process parameter of the welding material according to the target reference variation and the preset logical association information, the method further includes: Step 130, performing a welding operation according to the first welding process parameters; Step 131, during the welding process, collecting welding pictures and / or welding waveforms; Step 132, performing image analysis on the welding image and / or the welding waveform image to determine the welding result; Step 133, determining a second welding process parameter of the welding material according to the welding result; Step 134: performing a welding operation according to the second welding process parameters.

[0068] After determining the first welding process parameters (i.e., the optimal welding process parameters), the system performs the welding operation based on the first welding process parameters. In the actual welding process, the welding equipment will collect real-time data through sensors, cameras or other detection devices. These data may include: welding pictures, which can capture images of the welding process through high-resolution cameras, such as welding arcs, welding pools, welds, etc.; welding waveforms, which generate waveforms reflecting welding current changes, voltage fluctuations, etc. through real-time collection of current, voltage and other signals.

[0069] Then, the pictures of the welding process are analyzed using image processing techniques (such as edge detection, image segmentation, morphological analysis, etc.). Among them, image analysis can help detect welding defects such as uneven welds, weld spatter, weld porosity, and weld defects. By analyzing the welding waveform, it can be determined whether the current and voltage during the welding process are within the predetermined range and whether they fluctuate smoothly. For example, excessive current fluctuations may mean that there is a problem in the welding process, resulting in unstable welding quality. Based on the analysis of images and waveforms, the system can automatically evaluate the welding quality and determine whether it has reached the predetermined standard.

[0070] Based on the results of the first welding process parameters (i.e., the evaluation of welding quality), the system will adjust the welding process parameters. If welding defects are detected or the welding quality does not meet the standards, the system will automatically adjust the welding process parameters (such as current, voltage, welding speed, etc.) according to the analysis results to obtain the second welding process parameters. This process is a key part of closed-loop control. By adjusting the welding process parameters in real time, it ensures that subsequent welding operations can improve quality and reduce defects.

[0071] The welding operation is performed according to the second welding process parameters. The welding process parameters have been optimized according to the feedback during the welding process, and the purpose is to improve the welding quality through adjustment. Through this closed-loop control method, the system can dynamically adjust the process parameters under different welding conditions, thereby continuously improving the welding quality.

[0072] In one embodiment, welding problems that occur in the welding system are determined based on the welding results; then, welding alarm information is generated based on the welding problems. Among them, the evaluation of the welding results can reveal problems or defects in the system (for example, weak welding, uneven welds, too large heat-affected zones, etc.). These problems may be caused by unreasonable process parameter settings, equipment failure, improper operation, etc. The system needs to be able to identify potential problems based on feedback (pictures, waveforms, etc.) during the welding process. If the system detects certain welding problems (for example, defects or abnormal parameters during welding), a welding alarm message will be generated. The alarm information may include welding defect types (such as pores, cracks, cold welds, etc.), abnormal process parameters (such as excessive current, too fast welding speed, etc.), equipment failures or operating problems. The welding alarm information can promptly notify the operator or automatically adjust the equipment parameters to avoid further deterioration of quality problems.

[0073] The embodiment of the present invention deploys a real-time online monitoring system during the welding process to continuously track various key parameters of the welding process and make dynamic adjustments based on the real-time collected data. This closed-loop control can not only solve the quality fluctuations caused by inconsistent dimensions (such as groove angle, gap, misalignment, etc.) during the welding process, but also improve the quality and consistency of the welded joint by optimizing the welding process parameters in real time.

[0074] The welding process parameter determination device provided by the present invention is described below. The welding process parameter determination device described below and the welding process parameter determination method described above can be referred to each other.

[0075] refer to Figure 4 The welding process parameter determination device provided by the present invention includes an acquisition module 401, a deviation determination module 402 and a welding process parameter determination module 403.

[0076] An acquisition module 401 is used to acquire welding material information; The deviation determination module 402 is used to determine at least one reference variation of the characteristic parameter according to the characteristic parameter in the welding material information; the reference variation is the deviation of the characteristic parameter from a preset reference value; The welding process parameter determination module 403 is used to take at least one of the reference changes as a target reference change, and determine the first welding process parameter of the welding material according to the target reference change and preset logical association information; the preset logical association information is used to represent the logical relationship between the reference change and the welding process parameter.

[0077] The welding process parameter determination device provided by the embodiment of the present invention obtains welding material information; determines at least one reference variation of the characteristic parameter according to the characteristic parameter in the welding material information; the reference variation is the deviation between the characteristic parameter and the preset reference variation; uses at least one reference variation as the target reference variation, and determines the first welding process parameter of the welding material according to the target reference variation and preset logical association information; the logical association information is used to represent the logical relationship between the reference variation and the welding process parameter. The present invention realizes the optimization of welding process parameters according to the welding material information and the logical relationship between the reference variation and the welding process parameter, improves the stability of welding quality, production efficiency, and reduces costs.

[0078] In one embodiment, the welding process parameter determination module 403 is specifically used to: when one of the benchmark changes is used as the target benchmark change, the target benchmark change is input as an input parameter into the first relationship model in the logical association information to obtain the first welding process parameter of the welding material output by the first relationship model; when at least two of the benchmark changes are used as the target benchmark changes, at least two of the target benchmark changes are input into the second relationship model in the logical association information to obtain the first welding process parameter of the welding material output by the second relationship model; wherein the input parameter of the first relationship model is a single target benchmark change, and the input parameter of the second relationship model is at least two target benchmark changes.

[0079] In one embodiment, the welding process parameter determination module 403 is also used to: obtain sample characteristic parameters, and measure the change value of the sample welding process parameters when changing the sample baseline change amount of the sample characteristic parameters; record the change value of the sample welding process parameters under multiple sample baseline change amplitudes to form multiple groups of first data points; perform curve fitting on the multiple groups of first data points to obtain first curve information for describing the relationship between the sample baseline change amount and the sample welding process parameters; and determine the first relationship model based on the first curve information.

[0080] In one embodiment, the welding process parameter determination module 403 is also used to: obtain sample characteristic parameters, and determine the baseline adjustment amplitude of the sample characteristic parameters according to the weight of the sample characteristic parameters; according to the baseline adjustment amplitude of the sample characteristic parameters, simultaneously change the sample baseline variation of multiple sample characteristic parameters to measure the change value of the sample welding process parameters; under multiple sample baseline variation amplitudes, respectively record the change value of the sample welding process parameters to form multiple groups of second data points; perform curve fitting on the multiple groups of second data points to obtain second curve information for describing the relationship between the sample baseline variation and the sample welding process parameters; and determine the second relationship model according to the second curve information.

[0081] In one embodiment, the welding process parameter determination module 403 is also used to: analyze historical welding data to determine the influence information of the sample characteristic parameters on the welding results; determine the first weight of the sample characteristic parameters based on the influence information; analyze multiple welding scenes to determine the second weight of the sample characteristic parameters in each welding scene; determine the weight of the sample characteristic parameters based on the first weight and the second weight.

[0082] In one embodiment, the welding process parameter determination module 403 is also used to: optimize the first curve information according to the first process parameter interval in which there is a deviation in the first curve information, or the second process parameter interval that affects the welding quality; determine the first relationship model according to the optimized first curve information; optimize the second curve information according to the third process parameter interval in which there is a deviation in the second curve information, or the fourth process parameter interval that affects the welding quality; determine the second relationship model according to the optimized second curve information.

[0083] In one embodiment, the welding process parameter determination module 403 is also used to: perform welding operation according to the first welding process parameter; during the welding process, collect welding pictures and / or welding waveforms; perform image analysis on the welding pictures and / or the welding waveforms to determine the welding results; determine the second welding process parameters of the welding material according to the welding results; and perform welding operation according to the second welding process parameters.

[0084] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the following method: obtaining welding material information; determining at least one reference variation of the characteristic parameter according to the characteristic parameter in the welding material information; the reference variation is the deviation between the characteristic parameter and the preset reference variation; taking at least one of the reference variations as the target reference variation, and determining the first welding process parameter of the welding material according to the target reference variation and the preset logical association information; the preset logical association information is used to represent the logical relationship between the reference variation and the welding process parameter.

[0085] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0086] On the other hand, an embodiment of the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the welding process parameter determination method provided in the above-mentioned embodiments, for example, including: obtaining welding material information; determining at least one baseline change amount of the characteristic parameter based on the characteristic parameters in the welding material information; the baseline change amount is the deviation amount between the characteristic parameter and a preset baseline amount; using at least one of the baseline change amounts as a target baseline change amount, and determining a first welding process parameter of the welding material based on the target baseline change amount and preset logical association information; the preset logical association information is used to represent the logical relationship between the baseline change amount and the welding process parameter.

[0087] On the other hand, an embodiment of the present invention discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the welding process parameter determination method provided by the above-mentioned method embodiments, for example, including: obtaining welding material information; determining at least one baseline change of the characteristic parameter based on the characteristic parameters in the welding material information; the baseline change is the deviation of the characteristic parameter from a preset baseline; using at least one of the baseline changes as a target baseline change, and determining a first welding process parameter of the welding material based on the target baseline change and preset logical association information; the preset logical association information is used to represent the logical relationship between the baseline change and the welding process parameter.

[0088] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0089] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

[0091] The above embodiments are only used to illustrate the present invention, but not to limit the present invention. Although the present invention is described in detail with reference to the embodiments, it should be understood by those skilled in the art that various combinations, modifications or equivalent substitutions of the technical solutions of the present invention do not depart from the spirit and scope of the technical solutions of the present invention, and should be included in the scope of the present invention.

Claims

1. A method for determining welding process parameters, characterized in that: include: Get welding material information; Determining at least one reference variation of the characteristic parameter according to the characteristic parameter in the welding material information; The reference variation is the deviation between the characteristic parameter and the preset reference value; Taking at least one of the reference changes as a target reference change, and determining a first welding process parameter of the welding material according to the target reference change and preset logical association information; The preset logical association information is used to represent the logical relationship between the reference variation and the welding process parameters.

2. The method for determining welding process parameters according to claim 1, characterized in that: The step of determining the first welding process parameter of the welding material according to the target reference variation and the preset logical association information includes: In the case where one of the reference changes is used as the target reference change, the target reference change is input as an input parameter into a first relationship model in the logical association information to obtain a first welding process parameter of the welding material output by the first relationship model; In the case where at least two of the reference changes are used as the target reference changes, at least two of the target reference changes are input into a second relationship model in the logical association information to obtain a first welding process parameter of the welding material output by the second relationship model; The input parameter of the first relationship model is a single target reference change, and the input parameter of the second relationship model is at least two target reference changes.

3. The method for determining welding process parameters according to claim 2, characterized in that: The first relationship model is determined based on the following method: Acquiring a sample characteristic parameter, and measuring a change value of a sample welding process parameter while changing a sample reference change amount of the sample characteristic parameter; Under multiple sample base value variation ranges, respectively recording the variation values ​​of the sample welding process parameters to form multiple groups of first data points; Performing curve fitting on the plurality of groups of the first data points to obtain first curve information for describing the relationship between the sample baseline variation and the sample welding process parameters; The first relationship model is determined according to the first curve information.

4. The method for determining welding process parameters according to claim 3, characterized in that: The second relationship model is determined based on the following method: Acquire a sample characteristic parameter, and determine a reference amount adjustment range of the sample characteristic parameter according to a weight of the sample characteristic parameter; According to the reference amount adjustment amplitude of the sample characteristic parameter, the sample reference variation amounts of a plurality of the sample characteristic parameters are changed simultaneously to measure the variation value of the sample welding process parameter; Under multiple sample base value variation ranges, respectively recording the variation values ​​of the sample welding process parameters to form multiple groups of second data points; Performing curve fitting on the plurality of groups of the second data points to obtain second curve information for describing the relationship between the sample baseline variation and the sample welding process parameters; The second relationship model is determined according to the second curve information.

5. The method for determining welding process parameters according to claim 4, characterized in that: The weights of the sample characteristic parameters are determined based on the following method: Analyze historical welding data to determine the influence of the sample characteristic parameters on the welding results; Determining a first weight of the sample feature parameter according to the influence information; Analyze a plurality of welding scenes to determine a second weight of the sample characteristic parameter in each of the welding scenes; The weight of the sample feature parameter is determined according to the first weight and the second weight.

6. The method for determining welding process parameters according to claim 4, characterized in that: Determining the first relationship model according to the first curve information includes: Optimizing the first curve information according to a first process parameter interval in which a deviation exists in the first curve information, or a second process parameter interval that affects welding quality; Determining the first relationship model according to the optimized first curve information; The determining the second relationship model according to the second curve information includes: Optimizing the second curve information according to a third process parameter interval in which a deviation exists in the second curve information, or a fourth process parameter interval that affects welding quality; The second relationship model is determined according to the optimized second curve information.

7. The method for determining welding process parameters according to any one of claims 1 to 6, characterized in that: After determining the first welding process parameter of the welding material according to the target reference variation and the preset logical association information, the method further includes: Perform a welding operation according to the first welding process parameters; During the welding process, collect welding pictures and / or welding waveforms; Performing image analysis on the welding image and / or the welding waveform image to determine the welding result; Determining a second welding process parameter of the welding material according to the welding result; A welding operation is performed according to the second welding process parameters.

8. A device for determining welding process parameters, characterized in that: include: An acquisition module, used to acquire welding material information; A deviation determination module, used to determine at least one reference variation of the characteristic parameter according to the characteristic parameter in the welding material information; the reference variation is the deviation of the characteristic parameter from a preset reference value; A welding process parameter determination module, used to use at least one of the reference variation as a target reference variation, and determine a first welding process parameter of the welding material according to the target reference variation and preset logical association information; The preset logical association information is used to represent the logical relationship between the reference variation and the welding process parameters.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for determining welding process parameters according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for determining welding process parameters according to any one of claims 1 to 7 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for determining welding process parameters according to any one of claims 1 to 7 is implemented.

Images