Modeling method, device, equipment, medium and product of welding system

Abstract

The application provides a modeling method, device, equipment, medium and product of a welding system, the method comprising: obtaining pre-obtained welding experiment data; the welding experiment data is data obtained by welding experiment of the welding system; determining first model parameters and second model parameters based on the welding experiment data; determining a corresponding nonlinear system model of the welding system based on the first model parameters, an initial system model, the second model parameters and an initial compensation model. The modeling method, device, equipment, medium and product of the welding system provided by the application are used for modeling the welding system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of simulation, welding and the like, and in particular to a modeling method, device, equipment, medium and product of a welding system. BACKGROUND

[0002] Welding (also known as fusion welding) is a manufacturing process and technology that joins metals or other thermoplastic materials (such as plastics) by heating, high temperature or high pressure. With the development of science and technology, intelligent and automatic welding emerges in order to improve welding efficiency and save labor.

[0003] Intelligent penetration control (i.e., control of the back surface fusion width) of a welding system in a welding process can improve the welding quality of a gap. In order to achieve intelligent penetration control of the welding system in the welding process, a system model of the welding system needs to be established. Therefore, in the related art, how to establish the system model of the welding system becomes a technical problem to be solved. SUMMARY

[0004] The present application provides a modeling method, device, equipment, medium and product of a welding system, to solve the modeling of the welding system.

[0005] The present application provides a modeling method of a welding system, comprising:

[0006] obtaining welding experiment data obtained in advance; the welding experiment data is data obtained by a welding system in a welding experiment;

[0007] obtaining first model parameters and second model parameters based on the welding experiment data;

[0008] determining a nonlinear system model corresponding to the welding system based on the first model parameters, an initial system model, the second model parameters and an initial compensation model.

[0009] According to the present application, a modeling method of a welding system is provided, the welding experiment data includes dynamic experiment data and steady-state experiment data, the dynamic experiment data includes a plurality of first welding current values and a plurality of first real weld bead fusion widths, and the steady-state experiment data includes a plurality of second welding current values and a plurality of second real weld bead fusion widths;

[0010] determining the first model parameters and the second model parameters based on the welding experiment data, comprising:

[0011] obtaining the first model parameters by identifying and processing the plurality of first welding current values and the plurality of first real weld bead fusion widths through a least square method;

[0012] obtaining the second model parameters by identifying and processing the plurality of second welding current values and the plurality of second real weld bead fusion widths through a genetic algorithm.

[0013] A modeling method of a welding system is provided according to the present application, and the nonlinear system model corresponding to the welding system is determined based on the first model parameter, the initial system model, the second model parameter and the initial compensation model, and the modeling method comprises the following steps:

[0014] The model parameter of the initial system model is modified to the first model parameter to obtain a target system model;

[0015] The model parameter of the initial compensation model is modified to the second model parameter to obtain a nonlinear compensation model;

[0016] The sum of the target system model and the nonlinear compensation model is determined as the nonlinear system model corresponding to the welding system.

[0017] The initial system model in the modeling method of the welding system provided according to the present application is as follows:

[0018] y(k+1) = a1y(k) + a2y(k-1) + b1u(k) + b2u(k-1);

[0019] wherein y(k+1) is the predicted fusion width at the (k+1)th time, y(k) is the predicted fusion width at the kth time, y(k-1) is the predicted fusion width at the (k-1)th time, u(k) is the welding current value at the kth time, u(k-1) is the welding current value at the (k-1)th time, a1, a2, b1 and b2 are the model parameters of the initial system model.

[0020] The initial compensation model in the modeling method of the welding system provided according to the present application is as follows:

[0021] x(k-1) = c1tan -1 (c2u(k-1) + c3) + c4;

[0022] wherein x(k-1) is the compensation value at the (k-1)th time, u(k-1) is the welding current value at the (k-1)th time, c1, c2, c3 and c4 are the model parameters of the initial compensation model.

[0023] The present application provides a modeling method of a welding system, and the dynamic experimental data is obtained by welding a first sample gap based on a plurality of first welding current values by the welding system;

[0024] The plurality of first welding current values are a plurality of amplitude values of a pseudo-random signal.

[0025] The steady-state experimental data is obtained by welding a plurality of second sample gaps based on a plurality of second welding current values by the welding system.

[0026] The application further provides a modeling device of a welding system, comprising:

[0027] an acquisition module, configured to acquire pre-stored welding experiment data, wherein the welding experiment data is obtained by welding of the welding system according to a plurality of preset current values;

[0028] a parameter determination module, configured to perform identification processing on the welding experiment data to obtain first model parameters and second model parameters;

[0029] a model determination module, configured to determine a nonlinear system model corresponding to the welding system based on the first model parameters, an initial system model, the second model parameters and an initial compensation model.

[0030] The application provides a modeling device of a welding system, wherein the welding experiment data comprises dynamic experiment data and steady-state experiment data, the dynamic experiment data comprises a plurality of first welding current values and a plurality of first real weld widths, and the steady-state experiment data comprises a plurality of second welding current values and a plurality of second real weld widths.

[0031] The parameter determination module is specifically configured to:

[0032] determine the first model parameters and the second model parameters based on the welding experiment data, comprising:

[0033] perform identification processing on the plurality of first welding current values and the plurality of first real weld widths by using a least square method to obtain the first model parameters;

[0034] perform identification processing on the plurality of second welding current values and the plurality of second real weld widths by using a genetic algorithm to obtain the second model parameters.

[0035] The model determination module is specifically configured to:

[0036] modify model parameters of the initial system model to the first model parameters to obtain a target system model;

[0037] modify model parameters of the initial compensation model to the second model parameters to obtain a nonlinear compensation model;

[0038] determine the sum of the target system model and the nonlinear compensation model as the nonlinear system model corresponding to the welding system.

[0039] The application provides a modeling device of a welding system, wherein the initial system model is:

[0040] y(k+1)=a1y(k)+a2y(k-1)+b1u(k)+b2u(k-1);

[0041] Wherein, y(k+1) is the predicted fusion width at the (k+1) th time, y(k) is the predicted fusion width at the k th time, y(k-1) is the predicted fusion width at the (k-1) th time, u(k) is the welding current value at the k th time, u(k-1) is the welding current value at the (k-1) th time, a1, a2, b1, b2 are model parameters of the initial system model.

[0042] According to the present application, a modeling device of a welding system is provided, and the initial compensation model is:

[0043] x(k-1)=c1tan -1 (c2u(k-1)+c3)+c4;

[0044] Wherein, x(k-1) is the compensation value at the (k-1) th time, u(k-1) is the welding current value at the (k-1) th time, c1, c2, c3, c4 are model parameters of the initial compensation model.

[0045] According to the present application, a modeling device of a welding system is provided, and the dynamic experimental data is obtained by welding a first sample gap based on a plurality of first welding current values by the welding system;

[0046] The plurality of first welding current values are a plurality of amplitude values of a pseudo-random signal.

[0047] The steady-state experimental data is obtained by welding a plurality of second sample gaps based on a plurality of second welding current values by the welding system.

[0048] The present application also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the program to implement any of the above modeling methods of the welding system.

[0049] The present application also provides a non-transitory computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement any of the above modeling methods of the welding system.

[0050] The present application also provides a computer program product, comprising a computer program, and the computer program is executed by a processor to implement any of the above modeling methods of the welding system.

[0051] The present application provides a modeling method, device, equipment, medium and product of a welding system, the method comprising: obtaining welding experiment data obtained in advance; the welding experiment data is data obtained by welding experiment of the welding system; determining first model parameters and second model parameters based on the welding experiment data; determining a nonlinear system model corresponding to the welding system based on the first model parameters, an initial system model, the second model parameters and an initial compensation model. In the present application, the first model parameters and the second model parameters are obtained through actual welding experiment data, and then a nonlinear system model corresponding to the welding system is determined based on the first model parameters, the initial system model, the second model parameters and the initial compensation model, so that modeling of the welding system can be realized. In addition, the model parameters of the nonlinear system model are obtained based on the welding experiment data, so that the nonlinear system model has greater similarity with the actual welding system, the predicted fusion width obtained through the nonlinear system model is infinitely close to the real fusion width obtained through the welding system, and the accuracy of the nonlinear system model is improved. BRIEF DESCRIPTION OF DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.

[0053] Figure 1 A schematic diagram of a welding structure related to the present application;

[0054] Figure 2 A flowchart of the modeling method of the welding system provided by the present application;

[0055] Figure 3 A schematic diagram of a simulation model provided by the present application;

[0056] Figure 4 A fitting result diagram of fitting the real fusion width according to formula 9 provided by the present application;

[0057] Figure 5 A schematic diagram of a pseudo-random signal provided by the present application;

[0058] Figure 6 A schematic diagram of a plurality of first weld real fusion widths provided by the present application;

[0059] Figure 7 A schematic diagram of the actual contour of a plurality of first weld real fusion widths provided by the present application;

[0060] Figure 8A comparison diagram for predicting the fusion width in different ways is provided for the present application;

[0061] Figure 9 A result diagram for verifying the non-linear system model is provided for the present application;

[0062] Figure 10 A structure diagram of the modeling device of the welding system is provided for the present application;

[0063] Figure 11 A physical structure diagram of the electronic device is provided for the present application. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below in combination with the drawings in the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0065] Firstly, the professional terms involved in the present application are explained.

[0066] Welding wire refers to the wire material melted and filled in the gap on the welding part due to arc heat. The material of the welding wire is usually the same as that of the welding part.

[0067] Melt pool refers to the part of the base material melted into a pool due to arc heat. The part of the liquid metal with a certain geometric shape formed on the welding part during welding is called a melt pool.

[0068] Welding seam refers to the joint formed by melting and connecting the welding wire and the material at the gap.

[0069] Welding seam back fusion width refers to the width of the back melt pool of the welding seam.

[0070] The penetration state of the melt pool includes the non-penetration state, the full penetration state and the over penetration state. The penetration state is related to the welding seam back fusion width. When the welding seam back fusion width is less than 0, the penetration state is the non-penetration state; when the welding seam back fusion width is not less than 0 and not greater than the expected fusion width, the penetration state is the full penetration state; when the welding seam back fusion width is greater than the expected fusion width, the penetration state is the over penetration state.

[0071] Actual fusion width refers to the fusion width measured after welding on the back of the welding seam. Predicted fusion width refers to the fusion width calculated based on the non-linear system model.

[0072] Welding current refers to the welding current used by the welding system during welding.

[0073] The welding current value is a current value of the welding current.

[0074] Next, combining Figure 1 The welding structure is exemplarily illustrated. Figure 1 The welding structure is exemplarily illustrated. Figure 1 As shown in the figure, the welding structure includes a welding wire, a welding piece, a gap, a welding seam, a molten pool and a back-melt width of the welding seam.

[0075] In the related art, the robot usually welds the gap on the welding piece according to the received motion behavior instruction. In the process of robot welding, the back-melt width of the welding seam cannot be controlled in real time, so that the welding quality is poor.

[0076] The modeling method of the welding system provided by the present application will be described below in combination with specific embodiments.

[0077] Figure 2 The modeling method of the welding system provided by the present application will be described below in combination with specific embodiments. Figure 2 As shown in the figure, the method includes:

[0078] In step S201, pre-obtained welding experiment data is acquired, the welding experiment data being data obtained by welding experiment of the welding system.

[0079] Optionally, the execution subject of the embodiment of the present application can be an electronic device, or a modeling device of the welding system arranged in the electronic device, and the modeling device can be realized by combination of software and / or hardware.

[0080] Optionally, the welding experiment data can include dynamic experiment data.

[0081] Optionally, the welding experiment data can include dynamic experiment data and steady-state experiment data.

[0082] Optionally, the dynamic experiment data includes a plurality of first welding current values and a plurality of first welding seam real melt widths.

[0083] Optionally, the steady-state experiment data includes a plurality of second welding current values and a plurality of second welding seam real melt widths.

[0084] In step S202, the welding experiment data is identified to obtain first model parameters and second model parameters.

[0085] In some embodiments, when the welding experiment data includes dynamic experiment data and steady-state experiment data, the dynamic experiment data includes a plurality of first welding current values and a plurality of first welding seam real melt widths, and the steady-state experiment data includes a plurality of second welding current values and a plurality of second welding seam real melt widths, step S202 specifically includes:

[0086] The first model parameter and the second model parameter are determined based on welding experiment data, including:

[0087] The first model parameter is obtained by identifying the plurality of first welding current values and the plurality of first real weld widths through a least square method.

[0088] The second model parameter is obtained by identifying the plurality of second welding current values and the plurality of second real weld widths through a genetic algorithm.

[0089] In step S203, the nonlinear system model corresponding to the welding system is determined based on the first model parameter, the initial system model, the second model parameter, and the initial compensation model.

[0090] In some embodiments, the initial system model is as follows:

[0091] y(k+1) = a1y(k) + a2y(k-1) + b1u(k) + b2u(k-1) Formula 1

[0092] wherein y(k+1) is the predicted weld width of the initial system model at the (k+1)th time, y(k) is the predicted weld width of the initial system model at the kth time, y(k-1) is the predicted weld width of the initial system model at the (k-1)th time, u(k) is the welding current value of the initial system model at the kth time, u(k-1) is the welding current value of the initial system model at the (k-1)th time, a1, a2, b1, and b2 are model parameters of the initial system model.

[0093] In some embodiments, the first model parameter obtained by identifying the plurality of first welding current values and the plurality of first real weld widths through a least square method includes, for example, a1 = 1.8663, a2 = -0.8882, b1 = 0.0093, and b2 = -0.0082.

[0094] In some embodiments, the initial compensation model is as follows:

[0095] x(k-1) = c1tan -1 (c2u(k-1) + c3) + c4 Formula 2

[0096] wherein x(k-1) is the compensation value of the initial compensation model at the (k-1)th time, u(k-1) is the welding current value of the initial compensation model at the (k-1)th time, c1, c2, c3, and c4 are model parameters of the initial compensation model.

[0097] In some embodiments, the second model parameters include: c1 equals to 5.5260, c2 equals to 0.2088, c3 equals to 8.3048, and c4 equals to -8.4166, by genetic algorithm, for example, identifying and processing a plurality of second welding current values and a plurality of second real weld width included in the steady-state experiment data shown in Table 3.

[0098] Further, step S203 specifically includes:

[0099] modifying the model parameters of the initial system model to the first model parameters to obtain a target system model;

[0100] modifying the model parameters of the initial compensation model to the second model parameters to obtain a nonlinear compensation model;

[0101] determining the sum of the target system model and the nonlinear compensation model as the nonlinear system model corresponding to the welding system.

[0102] The initial system model and the initial compensation model are models pre-stored in the electronic device.

[0103] In a case where the first model parameters include: a1 equals to 1.8663, a2 equals to -0.8882, b1 equals to 0.0093, and b2 equals to -0.0082, the target system model is as follows:

[0104] y(k+1) = 1.8663y(k) - 0.8882y(k-1) + 0.0093u(k) - 0.0082u(k-1) Formula 3.

[0105] In a case where the second model parameters include: c1 equals to 5.5260, c2 equals to 0.2088, c3 equals to 8.3048, and c4 equals to -8.4166, the nonlinear compensation model is as follows:

[0106] x(k-1) = 5.5260tan -1 (0.2088u(k-1) + 8.3048) - 8.4166 Formula 4.

[0107] Further, on the basis of Formula 3 and Formula 4, the nonlinear system model is as follows:

[0108] z(k+1) = y(k+1) + x(k-1)

[0109] = 1.8663y(k) - 0.8882y(k-1) + 0.0093u(k) - 0.0082u(k- 1) + 5.5260tan -1(0.2088u(k-1) + 8.3048) - 8.4166 Equation 5.

[0110] In Figure 2 The modeling method of the welding system provided by the embodiment can realize modeling of the welding system by obtaining the first model parameter and the second model parameter from actual welding experiment data, and then determining the nonlinear system model corresponding to the welding system based on the first model parameter, the initial system model, the second model parameter, and the initial compensation model. In addition, the model parameter of the nonlinear system model is obtained based on the welding experiment data, so that the nonlinear system model has greater similarity with the actual welding system, the predicted weld width obtained by the nonlinear system model is infinitely close to the real weld width obtained by the welding system, and the accuracy of the nonlinear system model is improved.

[0111] In some embodiments, the dynamic experiment data can be obtained by welding the first sample gap based on a plurality of first welding current values by the welding system.

[0112] The plurality of first welding current values are a plurality of amplitude values of a pseudo-random signal.

[0113] Optionally, the pseudo-random signal can be a pseudo-random quinary signal (PRQS), a pseudo-random ternary signal, or the like.

[0114] In actual applications, the dynamic experiment data can be obtained by the following method: determining a time parameter of the welding system; designing a pseudo-random signal according to the time parameter; welding the first sample gap based on the pseudo-random signal by the welding system, and measuring the weld back width corresponding to the first sample gap to obtain a plurality of first weld real widths.

[0115] The time parameter is an important parameter for designing the pseudo-random signal of the dynamic welding experiment. In actual applications, the dynamic welding experiment is used to obtain the dynamic experiment data. The dynamic welding experiment includes a first dynamic welding experiment and a second dynamic welding experiment. The pseudo-random signal corresponds to the welding current in actual applications.

[0116] In a two-dimensional (X-Y) coordinate system (X-axis represents time, and Y-axis represents current), the pseudo-random signal has a plurality of first welding current values on the Y-axis.

[0117] The time parameter is obtained based on a time-domain model (as shown in Equation 9) of the welding system and the first dynamic welding experiment.

[0118] The time parameter is obtained based on a time-domain model (as shown in Equation 9) of the welding system and the first dynamic welding experiment. Figure 3 The time-domain model of the welding system used to obtain the time parameter is described below. Figure 3A schematic diagram of a simulation model provided by the present application is shown in FIG. 1. Figure 3 As shown in FIG. 1, the time-frequency domain model of the welding system includes a time domain model and a frequency domain model.

[0119] The time domain model includes u(t) input to the welding system and y(t) output from the welding system.

[0120] The frequency domain model includes a Laplace transform U(s) corresponding to u(t), a Laplace transform Y(s) corresponding to y(t), and a transfer function G(s) corresponding to the welding system.

[0121] U(s) is as shown in Equation 6 below:

[0122]

[0123] where A represents a preset constant, and s indicates time t in u(t).

[0124] G(s) is as shown in Equation 7 below (for a first-order system):

[0125]

[0126] where K represents an amplification coefficient, and T represents a time constant.

[0127] Y(s) is as shown in Equation 8 below:

[0128] Y(s) = U(s) x G(s) Equation 8.

[0129] Taking the inverse Laplace transform of Equation 9, we obtain Equation 9 below:

[0130]

[0131] where L -1 represents the inverse Laplace transform, and K and T are values to be determined.

[0132] In some embodiments, the time parameter can be an average value of multiple T.

[0133] In some embodiments, multiple T and multiple K are obtained through a first dynamic welding experiment.

[0134] The process of the first dynamic welding experiment is described below.

[0135] Based on the experimental parameters shown in Table 1 below, based on the control variable method, a first dynamic welding experiment including three stages is designed to obtain the true weld width of each stage, and the true weld width of each stage is fitted according to Equation 9 to obtain the corresponding K and T of each stage.

[0136] Table 1

[0137] Welding parameter Value Unit Welding current 50-100 A Welding speed 1.7 mm / s

[0138] The real fusion widths of the three stages are fitted based on the formula 9 to obtain the K and T corresponding to each stage in the three stages.

[0139] Figure 4 The results of fitting the real fusion width by the formula 9 provided by the present application are shown in the schematic diagram. Figure 4 As shown, it includes welding current, fitted fusion width, real fusion width. The time periods of the three stages are, for example, 0s-20s, 20s-40s, 40s-60s respectively.

[0140] For each stage, the real fusion width is the real fusion width measured on the back fusion width of the weld after the welding system performs welding experiment according to the welding current corresponding to the stage, and the fitted fusion width is obtained by fitting the real fusion width corresponding to the stage according to the formula 9.

[0141] According to the fitted fusion width in the formula 9, Figure 4 The K and T corresponding to each stage in the three stages are obtained. For example, the K and T corresponding to each stage in the three stages are shown in Table 2.

[0142] Table 2

[0143]

[0144] Further, on the basis of Table 2, the average value 2.4157 of the T corresponding to the first stage (equal to 2.9124), the T corresponding to the second stage (equal to 2.2884), and the T corresponding to the third stage (equal to 2.0462) can be determined as the time parameter of the welding system.

[0145] The second dynamic welding experiment is to weld the first sample gap according to the pseudo-random signal of the welding system to the gap, to realize the PRQS response experiment.

[0146] After the second dynamic welding experiment, the back fusion width of the weld corresponding to the first sample gap is measured to obtain a plurality of first weld real fusion widths.

[0147] Figure 5 The schematic diagram of the pseudo-random signal provided by the present application is shown in the schematic diagram.

[0148] Figure 6 The schematic diagram of the plurality of first weld real fusion widths provided by the present application is shown in the schematic diagram. Figure 6 As shown, the plurality of first weld real fusion widths forms a real fusion width curve.

[0149] Figure 7 The actual contour schematic diagram of the plurality of first weld real fusion widths provided by the present application is shown in the schematic diagram. Figure 7As shown, the actual profile includes: a preheating stage and a PRQS response experiment stage. The preheating stage is before the PRQS response experiment stage.

[0150] In the preheating stage, a 5s actual welding can be performed with a welding current of 60 amperes (A) and a welding speed of 1.7 millimeters per second (mm / s) to achieve preheating treatment, and the preheating stage is completed.

[0151] In practice, the steady-state experiment data is obtained by the welding system welding a plurality of second sample gaps based on a plurality of second welding current values. The plurality of second welding current values are pre-set current values.

[0152] Optionally, the plurality of second sample gaps are the same gap. For example, the total number of the plurality of second sample gaps is 19. Each second sample gap has a corresponding serial number (as shown in Table 3 below)

[0153] Specifically, the steady-state experiment data can be as shown in Table 3 below.

[0154] Table 3

[0155] Serial number Second welding current value (A) Second weld real fusion width (mm) 1 55 1.2912 2 56 1.7480 3 57 2.7270 4 58 2.7928 5 59 2.7326 6 60 3.2584 7 61 3.4180 8 62 3.0034 9 63 3.8126 10 64 2.9842 11 65 3.9662 12 66 3.8088 13 67 4.1482 14 68 4.1160 15 69 4.5206 16 70 4.8524 17 71 4.7354 18 72 4.8944 19 75 5.0388

[0156] Optionally, the steady-state experiment data shown in Table 3 above can be obtained by the welding system welding a plurality of second sample gaps of the same structure based on the plurality of second welding current values shown in Table 3 above at a welding speed of 1.7 mm / s. After the welding is completed, the weld back melt width of each second sample gap is measured to obtain a plurality of second weld true melt widths.

[0157] Figure 8 A comparison diagram of the predicted melt widths obtained by different methods is provided for the present application. As shown, Figure 8 includes: a plurality of second weld true melt widths in the steady-state experiment data, a predicted melt width obtained by Formula 3, and a predicted melt width obtained by Formula 5.

[0158] Figure 9 A result diagram for verifying the nonlinear system model is provided for the present application. As shown, Figure 9 includes: a first weld formed true melt width, and a predicted melt width obtained by the nonlinear system model.

[0159] Comparison Figure 9The first weld seam true fusion width and the predicted fusion width in the first weld seam true fusion width, the maximum of the predicted fusion width is greater than the maximum in the first weld seam true fusion width, the minimum of the predicted fusion width is less than the minimum in the first weld seam true fusion width, therefore the predicted fusion width obtained through the nonlinear system model has a wider weld back penetration width expression capability, the change trend of the predicted fusion width is closer to the change trend of the true fusion width, the accuracy of the nonlinear system model is higher.

[0160] Figure 10 The modeling device of the welding system provided by the present application is shown in the structural diagram. As shown in FIG. 10, the modeling device of the welding system comprises:

[0161] The acquisition module 110 is configured to acquire pre-stored welding experiment data, wherein the welding experiment data is obtained by the welding system according to a plurality of preset current values.

[0162] The parameter determination module 120 is configured to determine the first model parameter and the second model parameter based on the welding experiment data.

[0163] The model determination module 130 is configured to determine the nonlinear system model corresponding to the welding system based on the first model parameter, the initial system model, the second model parameter and the initial compensation model.

[0164] The modeling device of the welding system provided by the present application has the same beneficial effects as the modeling method of the welding system described above, which will not be repeated here.

[0165] The modeling device of the welding system provided by the present application comprises welding experiment data, wherein the welding experiment data comprises dynamic experiment data and steady-state experiment data, the dynamic experiment data comprises a plurality of first welding current values and a plurality of first weld seam true fusion widths, and the steady-state experiment data comprises a plurality of second welding current values and a plurality of second weld seam true fusion widths.

[0166] The first model parameter is obtained by identifying the plurality of first welding current values and the plurality of first weld seam true fusion widths through the least square method.

[0167] The second model parameter is obtained by identifying the plurality of second welding current values and the plurality of second weld seam true fusion widths through the genetic algorithm.

[0168] The model determination module 130 is configured to modify the model parameter of the initial system model to the first model parameter to obtain a target system model, modify the model parameter of the initial compensation model to the second model parameter to obtain a nonlinear compensation model, and determine the sum of the target system model and the nonlinear compensation model as the nonlinear system model corresponding to the welding system.

[0169] The application provides a modeling device of a welding system, and an initial system model is:

[0170] y(k+1)=a1y(k)+a2y(k-1)+b1u(k)+b2u(k-1);

[0171] wherein y(k+1) is a predicted fusion width at the (k+1)th moment, y(k) is a predicted fusion width at the kth moment, y(k-1) is a predicted fusion width at the (k-1)th moment, u(k) is a welding current value at the kth moment, u(k-1) is a welding current value at the (k-1)th moment, a1, a2, b1 and b2 are model parameters of the initial system model.

[0172] The application provides a modeling device of a welding system, and an initial compensation model is:

[0173] x(k-1)=c1tan -1 (c2u(k-1)+c3)+c4;

[0174] wherein x(k-1) is a compensation value at the (k-1)th moment, u(k-1) is a welding current value at the (k-1)th moment, c1, c2, c3 and c4 are model parameters of the initial compensation model.

[0175] The application provides a modeling device of a welding system, and dynamic experimental data are obtained by welding a first sample gap based on a plurality of first welding current values by the welding system;

[0176] The plurality of first welding current values are a plurality of amplitude values of a pseudo-random signal.

[0177] The steady-state experimental data are obtained by welding a plurality of second sample gaps based on a plurality of second welding current values by the welding system.

[0178] The modeling device of the welding system provided by the application has the same beneficial effects as the modeling method of the welding system, and details are not repeated here.

[0179] Figure 11 The application provides an entity structure schematic diagram of an electronic device. Figure 11As shown, the electronic device can include a processor 210, a communications interface 220, a memory 230, and a communications bus 240, wherein the processor 210, the communications interface 220, and the memory 230 can communicate with each other through the communications bus 240. The processor 210 can invoke a logic instruction in the memory 230 to execute a modeling method of a welding system, the method including: obtaining pre-obtained welding experiment data; the welding experiment data being data obtained by welding experiment on the welding system; determining a first model parameter and a second model parameter based on the welding experiment data; and determining a nonlinear system model corresponding to the welding system based on the first model parameter, an initial system model, the second model parameter, and an initial compensation model.

[0180] In addition, the logic instruction in the memory 230 described above can be implemented in the form of a software functional unit and sold or used as an independent product, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or parts of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0181] On the other hand, the present application also provides a computer program product, the computer program product including a computer program, the computer program being stored on a non-transitory computer readable storage medium, and the computer program being executed by a processor, the computer being capable of executing the modeling method of the welding system provided by the above-mentioned methods, the method including: obtaining pre-obtained welding experiment data; the welding experiment data being data obtained by welding experiment on the welding system; determining a first model parameter and a second model parameter based on the welding experiment data; and determining a nonlinear system model corresponding to the welding system based on the first model parameter, an initial system model, the second model parameter, and an initial compensation model.

[0182] In yet another aspect, the present application also provides a non-transitory computer readable storage medium having stored thereon a computer program, which, when executed by a processor, implements the modeling method of the welding system provided by the above method, and the method comprises: obtaining welding experiment data obtained in advance; the welding experiment data is data obtained by welding experiment on the welding system; determining first model parameters and second model parameters based on the welding experiment data; and determining a nonlinear system model corresponding to the welding system based on the first model parameters, an initial system model, the second model parameters, and an initial compensation model.

[0183] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0184] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus necessary universal hardware platforms, and of course can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods of the various embodiments or some parts of the embodiments.

[0185] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A modeling method for a welding system, characterized in that, include: Obtain pre-obtained welding experiment data; The welding experiment data is the data obtained from welding experiments conducted on the welding system. Based on the welding experiment data, the parameters of the first model and the parameters of the second model are determined. Based on the first model parameters, the initial system model, the second model parameters, and the initial compensation model, the nonlinear system model corresponding to the welding system is determined. The step of determining the nonlinear system model corresponding to the welding system based on the first model parameters, the initial system model, the second model parameters, and the initial compensation model includes: The model parameters of the initial system model are modified to the first model parameters to obtain the target system model; The model parameters of the initial compensation model are modified to the second model parameters to obtain a nonlinear compensation model; The sum of the target system model and the nonlinear compensation model is determined as the nonlinear system model corresponding to the welding system; The initial system model is as follows: ； in, For the ( Predicted melt width at time ) The predicted melt width at time k. For the ( Predicted melt width at time ) Let be the welding current value at time k. For the ( The welding current value at time ) , , , These are the model parameters of the initial system model; The initial compensation model is as follows: ； in, For the ( The compensation value at time ) For the ( The welding current value at time ) , , , These are the model parameters of the initial compensation model.

2. The modeling method for a welding system according to claim 1, characterized in that, The welding experimental data includes dynamic experimental data and steady-state experimental data. The dynamic experimental data includes multiple first welding current values ​​and multiple first weld widths. The steady-state experimental data includes multiple second welding current values ​​and multiple second weld widths. Based on the welding experiment data, the first model parameters and the second model parameters are determined, including: The first model parameters are obtained by identifying the multiple first welding current values ​​and the multiple first weld widths using the least squares method. The genetic algorithm is used to identify the multiple second welding current values ​​and the multiple second weld widths to obtain the second model parameters.

3. The modeling method for a welding system according to claim 2, characterized in that, The dynamic experimental data is obtained by the welding system welding the first sample gap based on the multiple first welding current values. The plurality of first welding current values ​​are plurality of amplitude values ​​of pseudo-random signals; The steady-state experimental data is obtained by the welding system welding multiple second sample gaps based on the multiple second welding current values.

4. A modeling device for a welding system, characterized in that, include: The acquisition module is used to acquire pre-stored welding experiment data; The welding experiment data were obtained by the welding system based on multiple preset current values. The parameter determination module is used to determine the first model parameters and the second model parameters based on the welding experiment data. The model determination module is also used to determine the nonlinear system model corresponding to the welding system based on the first model parameters, the initial system model, the second model parameters, and the initial compensation model; Specifically, the model determination module is used to: modify the model parameters of the initial system model to the first model parameters to obtain the target system model; The model parameters of the initial compensation model are modified to the second model parameters to obtain a nonlinear compensation model; The sum of the target system model and the nonlinear compensation model is determined as the nonlinear system model corresponding to the welding system; The initial system model is as follows: ； in, For the ( Predicted melt width at time ) The predicted melt width at time k. For the ( Predicted melt width at time ) Let be the welding current value at time k. For the ( The welding current value at time ) , , , These are the model parameters of the initial system model; The initial compensation model is as follows: ； in, For the ( The compensation value at time ) For the ( The welding current value at time ) , , , These are the model parameters of the initial compensation model.

5. 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 program, it implements the modeling method for the welding system as described in any one of claims 1 to 3.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the modeling method for the welding system as described in any one of claims 1 to 3.

7. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the modeling method for the welding system as described in any one of claims 1 to 3.

Images