Laser-arc hybrid welding method and system and welding regulation and control mechanism

Abstract

The invention relates to the technical field of welding, and discloses a laser-arc hybrid welding method and system and a welding regulation and control mechanism. The method comprises the steps that a target weldment is welded according to initial welding parameters, and when the welding speed reaches a target value, the welding speed is dynamically adjusted based on molten pool state data obtained in real time, so that heat input in the welding process is matched with the solidification rate of a molten pool till welding is completed. According to the method, the target weldment is firstly welded according to the initial welding parameters, and after the welding speed reaches the target value, the dynamic adjustment stage is started, so that the heat input and the solidification rate of the molten pool are always kept in dynamic balance, and the generation of weld beading is effectively controlled, so that the mechanical property of the weldment is improved, and the universal applicability and safety of a product are improved.

Description

Technical Field

[0001] This application relates to the field of welding technology, and in particular, to a laser-arc hybrid welding method, system, and welding control mechanism. Background Art

[0002] Laser-arc hybrid welding is a highly efficient welding method that has many advantages when welding medium-thick metal materials, such as high energy utilization rate and low heat input. However, this method also has a problem, that is, a phenomenon called hump bead is likely to occur during welding. Hump bead is caused by factors such as unstable molten pool and surface tension being less than the self-gravity of the molten pool during welding, and it appears as a hump-shaped protrusion on the back of the weld. Hump bead not only affects the appearance of the welded workpiece, but more importantly, it will seriously affect its mechanical properties, resulting in poor welding quality, thus posing a potential hazard to subsequent work production. Summary of the Invention

[0003] In view of this, in order to solve the problem that laser-arc hybrid welding in the prior art is prone to produce hump bead, resulting in poor welding quality, this application provides a laser-arc hybrid welding method, system, and welding control mechanism.

[0004] In a first aspect, this application provides a laser-arc hybrid welding method, including:

[0005] Welding a target workpiece according to preset initial welding parameters;

[0006] If the welding speed reaches the target value, based on the molten pool state data obtained in real time during welding, dynamically adjust the welding speed so that the heat input during welding matches the solidification rate of the molten pool until welding is completed.

[0007] In an optional embodiment, the dynamically adjusting the welding speed based on the molten pool state data obtained in real time during welding includes:

[0008] Collecting the molten pool state data during welding in real time, where the molten pool state data includes the molten pool temperature field and morphology, and inputting the molten pool state data into a preset prediction model to obtain the prediction results of the molten pool solidification rate and the hump bead risk index;

[0009] Adjusting the welding speed according to the prediction results.

[0010] In an optional embodiment, the adjusting the welding speed according to the prediction results includes:

[0011] If the molten pool solidification speed is less than a preset threshold, determine to reduce the welding speed;

[0012] When the solidification speed of the molten pool is not less than the preset threshold, maintain the original welding speed or increase the welding speed.

[0013] In an alternative embodiment, the determination of reducing the welding speed includes:

[0014] If the bead formation risk index is within the first grade range, reduce the welding speed step by step according to the first step size;

[0015] If the bead formation risk index is within the second grade range, reduce the welding speed step by step according to the second step size; the first step size is greater than the second step size.

[0016] In an alternative embodiment, when the solidification speed of the molten pool is less than the preset threshold, it further includes:

[0017] Increase the laser frequency in the initial welding parameters by the third step size;

[0018] And / or increase the arc current in the initial welding parameters by the fourth step size;

[0019] The third step size is different from the fourth step size.

[0020] In an alternative embodiment, when the solidification speed of the molten pool is not less than the preset threshold, maintaining the original welding speed or increasing the welding speed includes:

[0021] If it is determined that the current welding speed is lower than the target value, preferentially increase the current welding speed by the fifth step size.

[0022] In an alternative embodiment, the training process of the prediction model includes:

[0023] Collect the molten pool monitoring data under different welding parameters as training data. The molten pool monitoring data includes temperature distribution, morphological changes, and weld quality information;

[0024] Establish a finite element model of the molten pool solidification rate to solve the heat conduction equation;

[0025] Use the heat conduction equation and the training data to train a deep neural network model, and optimize the model parameters of the deep neural network model using the cross-validation method to obtain a prediction model.

[0026] In an alternative embodiment, the initial welding parameters include welding direction, welding sequence, and angle;

[0027] The welding direction is welding against the arc welding wire feeding direction; the welding sequence is laser first and arc second; the angle between the welding torch and the weld is 45°;

[0028] Before welding the target weldment according to the preset initial welding parameters, the following steps are also included:

[0029] Use a grinding wheel to clean the rust on the surface of the target weldment, fix the cleaned target weldment on the welding fixture at a clamping position preset distance from the weld edge, and penetrate the entire weld bead;

[0030] The preset distance is 18 - 23 mm.

[0031] In a second aspect, the present application provides a laser - arc hybrid welding system, including a molten pool monitoring mechanism and a welding control mechanism;

[0032] The molten pool monitoring mechanism is used to obtain the molten pool state data in real - time during the welding process;

[0033] The welding control mechanism is used to weld the target weldment according to the preset initial welding parameters. If the welding speed reaches the target value, based on the molten pool state data, the welding speed is dynamically adjusted to make the heat input during the welding process match the solidification rate of the molten pool until the welding is completed.

[0034] In a third aspect, the present application provides a welding control mechanism, including a welding component, a processor, and a memory. The memory stores a computer program, and the processor is used to execute the computer program to drive the welding component to implement the aforementioned laser - arc hybrid welding method.

[0035] The embodiments of the present application have the following beneficial effects:

[0036] The embodiments of the present application provide a laser - arc hybrid welding method. First, start welding the target weldment according to the preset welding parameters. When the welding speed reaches the target value, enter the dynamic adjustment stage to dynamically adjust the welding parameters, so that the heat input and the solidification rate of the molten pool are always in dynamic balance, reducing the generation of weld beads. And because the reduction of weld beads improves the mechanical properties of the weldment, improving the general applicability and safety of the product. In addition, in the whole welding process of the present application, only the welding parameters are adjusted in stages, without performing the process of adding a backing at the bottom of the weldment to prevent weld beads, thus effectively controlling weld beads while reducing costs and improving economic benefits. Description of the Drawings

[0037] To more clearly illustrate the technical solutions of the present application, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present application, so they should not be regarded as limiting the protection scope of the present application. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0038] Figure 1 shows a schematic structural diagram of a laser-arc hybrid welding system provided by an embodiment of the present application;

[0039] Figure 2 shows another schematic structural diagram of a laser-arc hybrid welding system provided by an embodiment of the present application;

[0040] Figure 3 shows a schematic flow diagram of a laser-arc hybrid welding method provided by an embodiment of the present application. Detailed implementation manners

[0041] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0042] Generally, the components of the embodiments of the present application described and illustrated herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the present application claimed, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0043] In the following text, the terms "including", "having" and their cognates that can be used in various embodiments of the present application are only intended to represent specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be construed as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or increasing the possibility of one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items.

[0044] In addition, the terms "first", "second", "third", etc. are only used for descriptive distinction and cannot be understood as indicating or implying relative importance.

[0045] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which various embodiments of the present application belong. The terms (such as those defined in a general-use dictionary) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning unless clearly defined in various embodiments of the present application.

[0046] The following will describe in detail some embodiments of the present application in conjunction with the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0047] A molten pool refers to a locally melted metal area formed by heating with a heat source (such as an arc, laser, electron beam, etc.) during the welding or additive manufacturing process. When the heat source is removed, the molten pool cools and solidifies to form a weld or a deposited layer.

[0048] The temperature field of the molten pool reflects the temperature changes in different regions within the molten pool and is an important manifestation of physical processes such as heat conduction, hydrodynamics, and phase change during the melting process.

[0049] The molten pool morphology includes the shape and size of the molten pool and its dynamic changes during the welding or 3D printing process.

[0050] Heat Input refers to the energy applied per unit length of the weld, usually expressed in joules per millimeter (J / mm). The magnitude of the heat input directly affects the formation of the molten pool, the cooling rate, and the quality of the final weld.

[0051] The Solidification Rate of the Melt Pool determines the morphology of the material microstructure, the grain size, and the possible defects (such as cracks, pores, etc.).

[0052] The formation process of the hump is related to many factors. During the welding process, due to a large heat input, a slow arc welding speed, and a relatively intensive energy input in a short period of time, the molten pool becomes unstable. Factors such as surface tension and its own gravity result in the surface tension being less than the self-gravity of the molten pool, thus causing a hump-shaped hump to appear on the back of the welded part.

[0053] Based on the formation reasons of the hump, in order to reduce the generation of humps during the welding process and ensure the welding quality, the embodiments of the present application provide a laser-arc hybrid welding system. By monitoring the welding process of the target welded part through this system, the welding parameters are adjusted so that the heat input and the stability of the molten pool reach a dynamic balance during the welding process, thereby reducing the generation of humps.

[0054] Exemplarily, as Figure 1 shown, the system includes a molten pool monitoring mechanism 110 and a welding control mechanism 120; among them, the molten pool monitoring mechanism 110 operates in the molten pool area, and this molten pool monitoring mechanism 110 is used to monitor the change of the molten pool state during the welding process.

[0055] Combined with Figure 2As shown, the welding control mechanism 120 operates in the welding area. The welding control mechanism 120 includes a processor 121 and multiple welding components 122 (such as welding component 1, welding component 2, …, welding component N shown in the figure, N≥1). The combined action of several welding components 122 is used to achieve the welding work of the target weldment. The processor 121 is used to control and manage the welding process of the target weldment, including but not limited to setting welding parameters, receiving data input by the molten pool monitoring mechanism 110, and processing the received data to adjust welding parameters and thereby drive the operating states of each welding component. The welding component 120 includes but is not limited to welding tooling fixtures, etc.

[0056] Exemplarily, the molten pool monitoring mechanism 110 includes an infrared thermometer, a high-speed camera, and a multispectral sensor. Among them, the high-precision infrared thermometer has a temperature measurement range covering the possible temperature range (1000°C - 3000°C) of the molten pool during the welding process, and the accuracy can reach ±10°C. The infrared thermometer is installed at a distance of 50 - 100 mm from the welding area to ensure accurate measurement of the surface temperature distribution of the molten pool.

[0057] Furthermore, the frame rate of the high-speed camera is set to 1000 - 2000 frames per second, and the resolution reaches 1920×1080 pixels, which is used to capture the dynamic morphological changes of the molten pool. The shooting angle of the high-speed camera is precisely calibrated in advance before use to ensure that the molten pool area can be completely and clearly photographed.

[0058] The multispectral sensor can collect the radiation information of the molten pool at multiple specific wavelengths. By analyzing the radiation intensity at different wavelengths, more comprehensive information about the temperature and composition of the molten pool can be obtained. Among them, the multispectral sensor is installed at a position that works in coordination with the infrared thermometer and the high-speed camera to ensure the consistency and complementarity of the collected data.

[0059] In short, the combined action of the infrared thermometer, the high-speed camera, and the multispectral sensor is used to collect the temperature, morphology, and spectral data of the molten pool in real time.

[0060] Next, all the collected data is transmitted to the welding control mechanism 120 through a high-speed data transmission line (such as an optical fiber, etc.). The transmission rate can be set above 10 Gbps to ensure the real-time and integrity of the data. The welding control mechanism 120 performs preliminary filtering, noise reduction, and other preprocessing on the collected raw data to remove interference signals and improve the data quality. Then, the welding process is analyzed in real time based on the processed data to dynamically adjust the welding parameters, and the current operating states of each welding component are controlled according to the adjusted welding parameters.

[0061] In one example, the system may further include a welding control software platform with a friendly human-machine interface. The welding regulation mechanism 120 and the molten pool monitoring mechanism 110 communicate with the platform respectively. Furthermore, the operator can input welding process parameters, start or stop the welding process, view real-time monitoring data and system operation status on the interface, enabling the platform to achieve automatic control of the entire welding process, including the coordinated work of molten pool monitoring, solidification rate prediction, heat input parameter adjustment, etc., without excessive manual intervention, greatly improving the stability and production efficiency of the welding process.

[0062] Based on the above system, an embodiment of the present application provides a laser-arc hybrid welding method for dynamically controlling the welding parameters of a target weldment during the welding process. Among them, the key lies in dynamically adjusting the welding speed among the welding parameters to ensure stable starting and ending of the arc, reduce the generation of weld beads during the welding process, and improve the welding quality.

[0063] As Figure 3 shown, the laser-arc hybrid welding method may include the following steps during the entire laser welding process:

[0064] S310, welding the target weldment according to the preset initial welding parameters.

[0065] In this embodiment, the welding parameters include but are not limited to welding sequence, welding direction, welding speed, angle, laser power, and arc current, etc.; among them, the welding sequence in the initial welding parameters is that the laser is in front and the arc is behind; the welding direction is welding against the wire feeding direction of the arc welding; the angle between the welding torch and the weld seam is 45°; the laser power is 1.02 - 1.45 KW, the arc current is 180 - 240 A; the voltage is 0 - 10 V; the defocus amount is -3 mm.

[0066] In one implementation, before welding, first use a grinding wheel to clean the rust on the surface of the target weldment until the surface is bright and rust-free; then fix the cleaned target weldment at the clamping position at a preset distance from the weld seam edge on the welding fixture, and penetrate the entire weld bead to keep the weldment stable without shifting during the welding process. Among them, the clamping position is preset to be at a distance from the weld seam edge to avoid the movement of the target weldment during welding, and the value of this preset distance can be set according to actual needs. For example, this preset distance can be 18 - 23 mm.

[0067] Next, weld according to the initial welding parameters, and keep the initial welding parameters unchanged during this process until the welding speed reaches the target value, and then adjust the welding parameters according to the molten pool state data obtained in real time during the welding process.

[0068] S320. If the welding speed reaches the target value, based on the molten pool state data obtained in real time during the welding process, dynamically adjust the welding speed so that the heat input during the welding process matches the solidification rate of the molten pool until the welding is completed.

[0069] It should be noted that when dynamically adjusting the welding parameters in this embodiment, the welding speed is adjusted preferentially, and while adjusting the welding speed, the remaining welding parameters are kept unchanged. During the welding process, the spatter situation during the welding process is monitored in real time to ensure stable starting and ending of the arc.

[0070] In one example, the entire welding process is divided into multiple stages. In each stage, only the value of the welding speed is adjusted, and other welding parameters remain unchanged. Among them, at the beginning of welding, the welding speed gradually increases from zero and enters the acceleration stage. When the welding speed reaches the target value, it enters the constant speed or deceleration or acceleration stage. Obviously, the entire welding process can be roughly divided into two stages according to the change of the welding speed: the acceleration stage and the adjustment stage.

[0071] It can be understood that in the acceleration stage of this embodiment, while maintaining the remaining welding parameters except the welding speed, by gradually increasing the welding speed, the heat input to the weld during the welding process is reduced, so that a dynamic balance is achieved between the heat input and the stability of the molten pool during the welding process, thereby reducing the generation of weld beads, ensuring the welding quality, and thus eliminating the need to add a backing during the welding process to solve the weld beads, which greatly improves the economic benefits. Moreover, the reduction of the weld beads also improves the mechanical properties of the welded parts, which can greatly improve the general applicability and safety of the products. At the same time, by increasing the welding speed, the welding speed can enter a stable change period as soon as possible to ensure the stability of the welding process.

[0072] After transitioning from the acceleration stage to the adjustment stage, at this time, the welding process enters a stable period. Based on this, the welding speed can be dynamically adjusted according to the actual changes in the molten pool during the welding process to ensure the stability of the welding process, so that the heat input and the stability of the molten pool always maintain a dynamic balance, and finally high-quality welding is completed.

[0073] In some examples, multiple sub-stages can be further divided in the acceleration stage and the adjustment stage. That is to say, the acceleration stage can be divided into multiple sub-stages. In each sub-stage, the current welding speed is increased at a fixed change rate, and the initial value of the current welding speed in each sub-stage is the end value of the welding speed in the previous sub-stage. The change rate of each sub-stage can be the same or different, that is, the step size used to change the welding speed in each sub-stage under the acceleration stage can be the same or different, and the specific value can be set according to actual needs. This embodiment does not limit this.

[0074] Similarly, the adjustment stage can also be divided into multiple sub-stages. In each sub-stage, the current welding speed is changed with different step sizes, and the initial value of the current welding speed in each sub-stage is the end value of the welding speed in the previous sub-stage. Among them, the step size of each sub-stage can be set according to actual needs, and this embodiment does not limit it.

[0075] In the adjustment stage, specifically, the adjustment strategy is determined through the molten pool state data obtained in real time, and then the change direction (increase or decrease) and magnitude of the welding speed in the next sub-stage are determined.

[0076] It should be noted that in the adjustment stage of the welding speed, try to keep the value of the welding speed within a target range. The aforementioned target value is an intermediate value within the target range (that is, the target value is greater than or equal to the lower limit value of the target range and less than the upper limit value of the target range); among them, the specific values of the target range and the target value can be set according to actual needs, and this embodiment does not limit this.

[0077] It is worth noting that the inventor has proved through multiple experiments that keeping the welding speed within the target range and maintaining the values of the remaining welding parameters unchanged can significantly reduce the generation of hump-shaped weld beads to ensure the welding quality.

[0078] Preferably, the target range can be (35 mm / s, 50 mm / s), and the target value is greater than or equal to the lower limit value of the target range (i.e., 35 mm / s) and less than the upper limit value of the target range (50 mm / s).

[0079] In this embodiment, the molten pool state data includes the molten pool temperature field and morphology data; in this embodiment, the molten pool temperature field and morphology data are collected through the molten pool monitoring mechanism 110 of the above system; and then the collected data is input into a preset prediction model to predict the molten pool solidification rate and weld bead risk index based on the input data; and then subsequently, the welding parameters can be dynamically adjusted according to the prediction results.

[0080] It can be understood that in this embodiment, a pre-constructed prediction model is used to predict the current molten pool solidification speed and weld bead risk index based on the input molten pool state data, and then the adjustment strategy and the magnitude of the adjustment parameters at the next moment are determined by combining the prediction results of the two. That is, the change direction and magnitude of the welding speed in the next stage are determined according to the prediction results of the molten pool solidification speed and the weld bead risk index.

[0081] Exemplarily, an infrared thermometer, a high-speed camera or a multi-spectral sensor is used to monitor the temperature distribution and morphology of the molten pool in real time. And the monitored data is input into the prediction model, and the heat input parameters are adjusted based on the prediction results of the model. Among them, in this embodiment, the heat input parameters are indirectly adjusted by adjusting the welding speed.

[0082] Furthermore, if the solidification speed of the molten pool in the prediction result is less than a preset threshold, it is determined to reduce the welding speed. The value of the preset threshold can be custom - set according to requirements, and is not limited in this embodiment.

[0083] In an alternative embodiment, if the weld bead risk index is within the first - level range, the welding speed is sequentially reduced according to the first step - length; if the weld bead risk index is within the second - level range, the welding speed is sequentially reduced according to the second step - length; where the first step - length is greater than the second step - length.

[0084] Among them, the values of the first - level range, the second - level range, the first step - length, and the second step - length are not limited and can be set according to actual needs; for example, the first - level range can be (0, 0.7), the second - level range can be (0.7, 1); the value of the first step - length can be 0.01 - 0.08 m / min, and the second step - length can be 0.1 - 0.3 m / min;

[0085] In an example, the first - level range and the second - level range can be further divided, and the values of the first step - length and the second step - length are synchronously divided. That is, the process of reducing the welding speed is divided into multiple sub - stages to more finely adjust the welding speed.

[0086] Exemplarily, the first - level range can be divided into multiple sub - ranges, and each sub - range corresponds to a sub - step - length in the first step - length. Taking two sub - ranges as an example, the first sub - range is (0, 0.3), the second sub - range is (0.3, 0.7). Further, the first step - length can also be correspondingly divided into two sub - step - lengths. The first sub - step - length corresponding to the first sub - range is 0.01 - 0.04 m / min, and the second sub - step - length corresponding to the second sub - range is 0.04 - 0.08 m / min. The specific division process can be custom - set according to actual needs and is not limited thereto.

[0087] By analogy, the second - level range can also be divided into multiple sub - ranges, and each sub - range corresponds to a sub - step - length in the second step - length. The division of the second - level range and the second step - length is the same as that of the foregoing first - level range and the first step - length, so it will not be elaborated here.

[0088] In this embodiment, when it is determined to reduce the welding speed, the stages of reducing the speed, the corresponding conditions for each stage, and the magnitudes of the adjustment values can be further divided, so as to achieve more refined adjustment and avoid the instantaneous change of the welding speed from affecting the welding quality.

[0089] In an alternative embodiment, when it is determined to reduce the welding speed, while reducing the welding speed, this embodiment can also adjust parameters such as laser frequency and arc current to more quickly reduce the weld bead risk index, avoid the generation of weld beads, thereby further optimizing the welding effect and ensuring the welding quality.

[0090] Exemplarily, taking the case where the weld bead risk index is within the second grade range as an example, while sequentially reducing the welding speed according to the second step length, the laser frequency in the initial welding parameters is increased according to the third step length; and / or the arc current in the initial welding parameters is increased according to the fourth step length; the third step length is different from the fourth step length.

[0091] Among them, while reducing the welding speed, one or more of the welding parameters such as laser frequency and arc current can be selected for synchronous adjustment, thereby triggering diversified heat input compensation, achieving heat input compensation faster and more efficiently, and ensuring that the response speed matches the high-speed welding process.

[0092] Furthermore, if the solidification speed of the molten pool is not less than the preset threshold, the original welding speed is maintained or increased.

[0093] It can be understood that when the solidification speed of the molten pool is not less than the preset threshold, the weld bead risk index can be not considered, but the original welding speed can be directly maintained or the current welding speed can be further increased.

[0094] In an alternative embodiment, if the solidification speed of the molten pool is not less than the preset threshold and it is determined that the current welding speed is lower than the target value, the current welding speed is preferentially increased by the fifth step length. Among them, the fifth step length is different from the aforementioned first to fourth step lengths, and the specific value can be custom-set according to requirements.

[0095] It can be understood that in the previous adjustment stage, it is determined to reduce the welding speed, and the end value of the welding speed at the previous moment (i.e., the initial value of the welding speed at the current moment) is lower than the target value, so the current welding speed can be preferentially increased to ensure that the value of the welding speed is within the aforementioned target range.

[0096] It should be noted that during the process of sequentially reducing the welding speed, this embodiment also determines the adjustment strategy for the next moment (whether to continue reducing the welding speed or maintaining the current welding speed) through the molten pool state data obtained in real time; that is, during the entire process of dynamically adjusting the welding parameters, this embodiment realizes dynamic feedback through real-time molten pool state data to determine the adjustment strategy at each moment.

[0097] In some examples, this embodiment can pre-construct a prediction model based on a machine learning model or a physical modeling method, and based on this prediction model, the solidification rate of the molten pool and the weld bead risk index during the welding process can be predicted.

[0098] Before model training, a large amount of molten pool monitoring data under different welding process parameters (such as laser power, arc current, welding speed, plate material and thickness, etc.) is collected in advance, including temperature distribution, morphological changes, and corresponding weld quality information. These data are used to train a deep neural network model, such as a convolutional neural network (CNN) or a recurrent neural network (RNN), to obtain a preliminary prediction model. During the model training process, methods such as cross-validation are used to optimize the model parameters and improve the generalization ability and prediction accuracy of the model. Among them, the model input is the preprocessed molten pool monitoring data, and the output is the predicted solidification rate of the molten pool.

[0099] At the same time, based on physical principles such as heat transfer and fluid mechanics, a mathematical-physical model of molten pool solidification during laser-arc hybrid welding is established. Considering factors such as the energy distribution of laser and arc heat sources, the flow of liquid metal in the molten pool, heat conduction, and heat exchange with the surrounding environment, the model equations are solved by numerical calculation methods (such as the finite element method) to obtain the quantitative relationship between the molten pool solidification rate and welding process parameters.

[0100] That is, a finite element model of the molten pool solidification rate is established, and the heat conduction equation is solved:

[0101]

[0102] In the formula, represents the rate of change of temperature with time; α is the thermal diffusivity; is the Laplace operator; Q is the heat input per unit volume (such as the heating power density of laser or arc, with the unit of W / m 3 ); T is the temperature field; t represents time (in seconds s); ρ is the density; c p is the specific heat capacity at constant pressure; ρc p represents the volume heat capacity (the heat required for a unit volume of substance to increase by 1 °C), and its unit is J / (m 3 ·°C).

[0103] The solidification front propagation rate is calculated through the above heat conduction equation combined with phase change kinetics, and the preliminary prediction model is optimized through this heat conduction equation and training data to obtain the final prediction model. That is, the calculation results of the physical model are cross-validated with the actual monitoring data multiple times, and the model parameters are continuously optimized through the quantitative relationship to improve the model accuracy.

[0104] Subsequently, according to the results predicted by the prediction model, the heat sources (such as laser power, welding current) can be dynamically adjusted through a closed-loop control strategy to achieve the best matching of heat input and solidification rate.

[0105] That is, the collected molten pool data is input into the prediction model to calculate the current solidification rate of the molten pool. According to the deviation between the target solidification rate and the actual value, the heat input parameters are adjusted through the feedback control system. The above process is repeated until the predetermined welding or manufacturing quality standard is achieved.

[0106] Exemplarily, during the actual welding parameter adjustment process, the heat source parameters can be dynamically adjusted using a closed-loop control strategy based on the predicted solidification rate of the molten pool. An objective function between the heat input and the solidification rate of the molten pool is established to achieve the best matching between the two. When the predicted solidification rate deviates from the target value, the control system calculates the heat source parameters (such as laser power, welding current) that need to be adjusted according to the magnitude and direction of the deviation through the PID (Proportional-Integral-Derivative) control algorithm or PID controller, and drives each welding component to perform welding operations on the target workpiece according to the adjusted heat source parameters.

[0107] For the adjustment of laser power, a high-precision laser power supply controller is used, and its power adjustment accuracy can reach ±0.1 kW. The controller quickly adjusts the drive current of the laser generator according to the instructions issued by the control system, thereby achieving precise adjustment of laser power. For the adjustment of welding current, by adjusting the inverter circuit parameters of the arc welding power supply, rapid and precise control of the arc current is achieved, and the current adjustment accuracy can reach ±1 A. While adjusting the heat source parameters, the changes in the molten pool state are monitored in real time, and the new monitoring data is fed back to the prediction model and the control system to form a closed-loop control loop, ensuring that the heat input and the solidification rate are always in the best matching state.

[0108] It can be understood that the actual welding process is as follows: an infrared thermometer measures the surface temperature distribution of the molten pool in real time, a high-speed camera captures the morphological changes of the molten pool, and a multi-spectral sensor collects the spectral information of the molten pool. The collected data is quickly transmitted through optical fibers to the data processing module in the welding regulation mechanism 120 for preprocessing.

[0109] The preprocessed monitoring data is input into a prediction model based on machine learning. The model is trained to predict the solidification rate of the molten pool under the current welding conditions according to the input data.

[0110] Based on the physical modeling method to predict the solidification rate of the molten pool, it is found that if the solidification rate is too fast, it may lead to poor weld formation, then the system automatically reduces the welding speed to a set value.

[0111] Moreover, during the welding process, the molten pool state is continuously monitored, the predicted solidification rate and the weld bead risk index are continuously updated, and the heat input parameters are adjusted in real time according to the deviation. After welding, non-destructive testing is performed on the weld.

[0112] That is, after welding, post-weld inspection is performed on the target workpiece, including workpiece appearance, weld porosity, surface slag inclusion, etc.

[0113] In some embodiments, while adjusting the parameters, the content of carbon dioxide in the shielding gas can be increased or a backing can be added at the bottom of the workpiece to further reduce the risk of bead formation and ensure the welding quality.

[0114] In this embodiment, by increasing the welding speed, the heat input to the weld during the welding process can be effectively reduced, so that the heat input and the stability of the molten pool reach a dynamic balance, thereby effectively controlling the formation of beads; and there is no need to perform the process of adding a backing at the bottom of the welded part to prevent beads, which reduces the cost and improves the economic benefits; in addition, this embodiment can also be combined with a corresponding welding system to intelligently collect and monitor the corresponding data, analyze and predict the results, and adjust the welding parameters, reducing manual intervention, making it applicable to the welding of various medium and thick plate metal materials, especially suitable for occasions with high requirements for welding quality. At the same time, due to the reduction of beads, the mechanical properties of the welded part are also improved, enhancing the general applicability and safety of the product.

[0115] In summary, in this embodiment, the welding parameters, especially the welding speed, are dynamically adjusted by intelligent means, so that the heat input during the welding process is balanced with the solidification rate of the molten pool. This method can not only significantly reduce the formation of beads, but also improve the welding efficiency and product quality, and has high practical value and promotion prospects.

[0116] This application also provides a welding control mechanism. Exemplarily, the welding control mechanism includes a plurality of welding components, a processor, and a memory. Among them, the memory stores a computer program, and the processor runs the computer program to enable the welding control mechanism to execute the above laser-arc hybrid welding method.

[0117] Among them, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including at least one of a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application.

[0118] The memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. Among them, the memory is used to store computer programs, and after receiving the execution instruction, the processor can execute the computer program accordingly.

[0119] This application also provides a computer storage medium for storing the computer program used in the above-mentioned processor. Among them, the computer storage medium can be a readable storage medium, a non-volatile storage medium or a volatile storage medium. For example, the computer storage medium can include, but is not limited to: USB flash drives, mobile hard disks, Read Only Memory (ROM), Random Access Memory (RAM), magnetic disks or optical discs and other various media that can store program codes.

[0120] In several embodiments provided by this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are only illustrative. For example, the flowcharts and structure diagrams in the drawings show the possible architectures, functions, and operations of the devices, methods, and computer program products according to multiple embodiments of this application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in the alternative implementation, the functions marked in the blocks can occur in a different order from that marked in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the structure diagram and / or flowchart, and the combination of blocks in the structure diagram and / or flowchart, can be implemented by a dedicated hardware-based system that executes the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0121] In addition, in each embodiment of this application, each functional module or unit can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.

[0122] When the above-mentioned functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a welding control mechanism (which can be a welding device, a welding fixture, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application.

[0123] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application.

Claims

1. A laser arc hybrid welding method, characterized in that: include: Welding the target weldment according to the preset initial welding parameters; If the welding speed reaches the target value, the welding speed is dynamically adjusted based on the molten pool state data acquired in real time during the welding process, so that the heat input during the welding process matches the molten pool solidification rate until the welding is completed.

2. The laser arc hybrid welding method according to claim 1, characterized in that: The method of dynamically adjusting the welding speed based on the molten pool state data acquired in real time during the welding process includes: Collecting the molten pool state data in the welding process in real time, wherein the molten pool state data includes the molten pool temperature field and morphology, and inputting the molten pool state data into a preset prediction model to obtain the prediction results of the molten pool solidification rate and the weld nodule risk index; The welding speed is adjusted according to the prediction result.

3. The laser arc hybrid welding method according to claim 2, characterized in that: The step of adjusting the welding speed according to the prediction result comprises: If the solidification speed of the molten pool is less than a preset threshold, determining to reduce the welding speed; If the solidification speed of the molten pool is not less than the preset threshold, the original welding speed is maintained or increased.

4. The laser arc hybrid welding method according to claim 3, characterized in that: The determining to reduce the welding speed comprises: If the weld nodule risk index is within the first level, the welding speed is sequentially reduced according to the first step; If the weld nodule risk index is within the second level range, the welding speed is reduced in sequence according to the second step length; the first step length is greater than the second step length.

5. The laser arc hybrid welding method according to claim 3 or 4, characterized in that: If the solidification speed of the molten pool is less than a preset threshold, the method further includes: increasing the laser frequency in the initial welding parameters by a third step; and / or, increasing the arc current in the initial welding parameters by a fourth step; The third step size is different from the fourth step size.

6. The laser arc hybrid welding method according to claim 3, characterized in that: If the solidification speed of the molten pool is not less than the preset threshold, maintaining the original welding speed or increasing the welding speed comprises: If it is determined that the current welding speed is lower than the target value, the current welding speed is preferentially increased by a fifth step.

7. The laser arc hybrid welding method according to claim 2, characterized in that: The training process of the prediction model includes: Collecting molten pool monitoring data under different welding parameters as training expectations, the molten pool monitoring data including temperature distribution, morphological changes and weld quality information; A finite element model of the molten pool solidification rate was established to solve the heat conduction equation; The heat conduction equation and the training prediction are used to train a deep neural network model, and a cross-validation method is used to optimize the model parameters of the deep neural network model to obtain a prediction model.

8. The laser arc hybrid welding method according to claim 1, characterized in that: The initial welding parameters include welding direction, welding sequence and angle; The welding direction is welding in the opposite direction of arc welding wire feeding; the welding sequence is laser first and arc second; the angle between the welding gun and the weld is 45°; Before welding the target weldment according to the preset initial welding parameters, the method further includes: Use a grinding wheel to clean the rust on the surface of the target weldment, fix the cleaned target weldment on the welding fixture at a clamping position at a preset distance from the edge of the weld, and run through the entire weld; The preset distance is 18 to 23 mm.

9. A laser arc hybrid welding system, characterized in that: It includes a molten pool monitoring mechanism and a welding control mechanism; The molten pool monitoring mechanism is used to obtain molten pool status data in real time during the welding process; The welding control mechanism is used to weld the target weldment according to the preset initial welding parameters. If the welding speed reaches the target value, the welding speed is dynamically adjusted based on the molten pool state data so that the heat input during the welding process matches the molten pool solidification rate until the welding is completed.

10. A welding control mechanism, characterized in that It comprises a welding component, a processor and a memory, wherein the memory stores a computer program, and the processor is used to execute the computer program to drive the welding component to implement the laser arc hybrid welding method described in any one of claims 1-8.

Images