Welding seam fusion depth control method and system for laser-arc hybrid welding

Abstract

The invention relates to the technical field of welding processes, and discloses a weld penetration control method and system for laser-arc hybrid welding, and the method comprises the steps: constructing a three-dimensional temperature field of a molten pool based on an infrared heat radiation signal of the welding molten pool; the molten pool metal vapor concentration is calibrated based on the specific element spectral line intensity of the plasma spectral signal in the welding molten pool; carrying out coupling analysis on the three-dimensional temperature field of the molten pool and the metal vapor concentration of the molten pool to obtain molten pool state characteristics of the welding molten pool; dynamically dividing a laser-arc energy distribution proportion based on the state characteristics of the molten pool; adjusting the offset position of a laser focus in the depth direction of the welding seam based on the laser-arc energy distribution proportion, and adjusting an arc voltage waveform through an inverter power supply; according to the method, the weld penetration control efficiency of laser-arc hybrid welding can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of welding processes, and in particular to a method and system for controlling weld penetration depth in laser arc hybrid welding. Background Art

[0002] In laser arc hybrid welding, weld penetration is a key parameter affecting weld quality. Precisely controlling weld penetration is crucial for ensuring the mechanical properties and reliability of the welded joint. However, existing technologies for controlling weld penetration in laser arc hybrid welding face the problem of incomplete and inaccurate information on the molten pool state. This makes it difficult to effectively construct the molten pool's three-dimensional temperature field and calibrate the metal vapor concentration, making it difficult to accurately grasp the dynamic characteristics of the molten pool and, consequently, to ensure accurate weld penetration control.

[0003] The existing technology also has the defects of insufficient in-depth analysis of the molten pool state characteristics and lack of dynamic adaptability of the energy distribution strategy. It cannot achieve reasonable distribution of laser and arc energy based on the fluidity and stability parameters of the molten pool, nor can it adjust the laser focus position and arc voltage waveform in real time according to the oscillation state of the molten pool. As a result, the depth of penetration control effect during welding is poor, making it difficult to meet the needs of high-quality welding. Summary of the Invention

[0004] The present invention provides a method and system for controlling weld penetration depth in laser arc hybrid welding, the main purpose of which is to solve the problem of low efficiency in controlling weld penetration depth in laser arc hybrid welding.

[0005] To achieve the above objectives, the present invention provides a method for controlling weld penetration in laser arc hybrid welding, comprising:

[0006] S1. Constructing a three-dimensional temperature field of the weld pool based on the infrared thermal radiation signal of the weld pool;

[0007] S2. Calibrate the metal vapor concentration in the weld pool based on the intensity of the specific element line of the plasma spectral signal in the weld pool;

[0008] S3. Coupling analysis of the three-dimensional temperature field of the molten pool and the metal vapor concentration of the molten pool to obtain the molten pool state characteristics of the welding molten pool;

[0009] S4. Dynamically divide the laser-arc energy distribution ratio based on the characteristics of the molten pool state;

[0010] S5. Adjust the offset position of the laser focus in the weld depth direction based on the laser-arc energy distribution ratio, and adjust the arc voltage waveform through the inverter power supply.

[0011] In a preferred embodiment, the method of constructing a three-dimensional temperature field of the molten pool based on the infrared thermal radiation signal of the welding molten pool includes:

[0012] Performing multi-spectral infrared thermal imaging on the welding molten pool to obtain a multi-band thermal radiation distribution on the surface of the molten pool;

[0013] Performing chromatic aberration separation on the depth characteristic spectrum based on the multi-band thermal radiation distribution to obtain a thermal radiation gradient in the depth direction of the molten pool;

[0014] Mapping the thermal radiation gradient to a spatial filter array to obtain a three-dimensional voxel temperature distribution of the molten pool;

[0015] Isothermal boundary reconstruction is performed on the three-dimensional voxel temperature distribution to obtain a three-dimensional temperature field of the molten pool.

[0016] In a preferred embodiment, the calibrating the metal vapor concentration in the welding pool based on the intensity of the specific element spectrum line of the plasma spectrum signal in the welding pool includes:

[0017] Performing dual-path beam splitting on the plasma spectrum signal to obtain synchronized light intensity signals of characteristic spectrum lines and reference spectrum lines;

[0018] performing differential amplification processing on the synchronous light intensity signal to obtain a relative intensity ratio of elemental spectral lines of the molten pool;

[0019] Performing photoelectric conversion linear calibration on the relative intensity ratio of the elemental spectral lines to obtain a molten pool metal vapor concentration gradient value of the molten pool;

[0020] The boundary of the concentration distribution field is reconstructed based on the vapor concentration gradient value to obtain the molten pool metal vapor concentration field of the molten pool.

[0021] In a preferred embodiment, coupling analysis of the three-dimensional temperature field of the molten pool and the metal vapor concentration of the molten pool to obtain the molten pool state characteristics of the welding molten pool includes:

[0022] Synchronizing the dynamic distribution data of the three-dimensional temperature field of the molten pool with the real-time monitoring data of the metal vapor concentration of the molten pool to obtain a coupled data set of the molten pool;

[0023] Performing vector superposition of the temperature gradient and the steam concentration gradient based on the coupled data set to obtain interactive characteristics of energy transfer and material migration within the molten pool;

[0024] Based on the interaction characteristics, the convection intensity distribution and the vaporization suppression region boundary in the molten pool fluid are identified to obtain the molten pool state characteristics of the welding molten pool.

[0025] In a preferred embodiment, the identifying of the convection intensity distribution and the vaporization suppression region boundary in the molten pool fluid based on the interaction characteristics to obtain the molten pool state characteristics of the welding molten pool includes:

[0026] Collect the plasma light pattern morphology and the ripple direction of the molten pool surface;

[0027] determining a vaporization suppression region boundary according to a contraction width of the plasma light pattern;

[0028] The convection intensity distribution in the molten pool fluid is identified based on the convergence direction of the ripples on the molten pool surface, and the identified convection intensity distribution is used as the molten pool state feature of the welding molten pool.

[0029] In a preferred embodiment, the dynamically dividing the laser-arc energy distribution ratio based on the molten pool state characteristics includes:

[0030] performing orthogonal physical parameter separation based on the state characteristics of the molten pool to obtain the fluidity parameter and stability parameter of the molten pool;

[0031] The fluidity parameter and the stability parameter are superimposed to obtain a dynamic coupling effect of laser energy and arc energy;

[0032] The real-time change trend of the dynamic coupling relationship is adaptively distributed to obtain the laser-arc energy distribution ratio.

[0033] In a preferred embodiment, the orthogonal physical parameter separation based on the molten pool state characteristics to obtain the fluidity parameter and stability parameter of the molten pool includes:

[0034] Mapping the heat flux vector in the molten pool state characteristic to the heat transfer dominant axis to obtain a first orthogonal component representing energy transfer;

[0035] Mapping the melt flow vector in the molten pool state characteristic to the material migration dominant axis to obtain a second orthogonal component characterizing material transport;

[0036] The modulus of the first orthogonal component is used as the melt pool fluidity parameter, and the directional consistency of the second orthogonal component is used as the melt pool stability parameter.

[0037] In a preferred embodiment, adjusting the offset position of the laser focus in the weld depth direction based on the laser-arc energy distribution ratio includes:

[0038] monitoring the oscillation state of the weld pool in real time to obtain the oscillation frequency of the weld pool;

[0039] Performing a dynamic response analysis on the degree of deviation between the oscillation frequency and a preset reference frequency to obtain a penetration control signal of the molten pool;

[0040] Transmitting a displacement instruction to a servo motor based on the penetration control signal to obtain a depth-direction displacement of the molten pool;

[0041] The laser focus position is adjusted based on the depth-direction displacement to obtain an offset position in the depth direction of the weld.

[0042] In a preferred embodiment, the arc voltage waveform is adjusted by an inverter power supply, comprising:

[0043] Extracting a frequency variation in the oscillation frequency to obtain an oscillation frequency variation of the molten pool;

[0044] Mapping the modulation response characteristics to the oscillation frequency variation to obtain the arc voltage waveform parameters of the molten pool;

[0045] The inverter power supply switching sequence is reconstructed based on the arc voltage waveform parameters to obtain a modulated arc voltage waveform.

[0046] In order to solve the above problems, the present invention also provides a weld penetration control system for laser arc hybrid welding, the system comprising:

[0047] The 3D temperature field construction module of the molten pool is used to construct the 3D temperature field of the molten pool based on the infrared thermal radiation signal of the welding molten pool;

[0048] a molten pool metal vapor concentration calibration module, which calibrates the molten pool metal vapor concentration based on the intensity of specific element spectral lines of the plasma spectrum signal in the welding molten pool;

[0049] A comprehensive molten pool state characteristic module couples and analyzes the three-dimensional temperature field of the molten pool with the metal vapor concentration of the molten pool to obtain the molten pool state characteristics of the welding molten pool;

[0050] a laser-arc energy distribution ratio module, which dynamically divides the laser-arc energy distribution ratio based on the molten pool state characteristics;

[0051] The arc voltage waveform adjustment module adjusts the offset position of the laser focus in the weld depth direction based on the laser-arc energy distribution ratio and adjusts the arc voltage waveform through the inverter power supply. Compared with the existing technology, the present invention has the following advantages:

[0052] 1. By constructing a three-dimensional temperature field of the molten pool based on the infrared thermal radiation signal of the welding molten pool, calibrating the metal vapor concentration of the molten pool based on the intensity of the specific element spectral lines of the plasma spectral signal, and coupling the two to analyze the molten pool state characteristics, the temperature distribution, metal vapor concentration and their interaction characteristics of the molten pool can be comprehensively and accurately obtained, providing an accurate state basis for penetration control, thereby effectively improving the accuracy of weld penetration control.

[0053] 2. The laser-arc energy distribution ratio is dynamically divided based on the characteristics of the molten pool state, and the offset position of the laser focus in the weld depth direction is adjusted accordingly. The arc voltage waveform is adjusted through the inverter power supply, realizing real-time dynamic adaptation of the laser arc energy distribution and related parameters. The parameters such as the energy distribution ratio, focus position and arc voltage waveform can accurately match the changes in the molten pool state, significantly improving the accuracy of the parameters and optimizing the weld penetration control effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A schematic flow chart of a method for controlling weld penetration depth in laser arc hybrid welding according to an embodiment of the present invention;

[0055] Figure 2 This is a functional module diagram of a laser arc hybrid welding weld penetration control generation system provided by one embodiment of the present invention;

[0056] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0057] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0058] The embodiment of the present application provides a method for generating weld penetration control for laser arc hybrid welding. The execution subject of the method for generating weld penetration control for laser arc hybrid welding includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for generating weld penetration control for laser arc hybrid welding can be executed by software or hardware installed on a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0059] Reference Figure 1 FIG. 1 is a flow chart of a method for controlling weld penetration depth of laser arc hybrid welding according to an embodiment of the present invention. In this embodiment, the method for generating reference information based on artificial intelligence and smart home includes:

[0060] S1. Constructing a three-dimensional temperature field of the weld pool based on the infrared thermal radiation signal of the weld pool;

[0061] S2. Calibrate the metal vapor concentration in the weld pool based on the intensity of the specific element line of the plasma spectral signal in the weld pool;

[0062] S3. Coupling analysis of the three-dimensional temperature field of the molten pool and the metal vapor concentration of the molten pool to obtain the molten pool state characteristics of the welding molten pool;

[0063] S4. Dynamically divide the laser-arc energy distribution ratio based on the characteristics of the molten pool state;

[0064] S5. Adjust the offset position of the laser focus in the weld depth direction based on the laser-arc energy distribution ratio, and adjust the arc voltage waveform through the inverter power supply.

[0065] S1. Constructing the three-dimensional temperature field of the welding pool based on the infrared thermal radiation signal of the welding pool;

[0066] In an embodiment of the present invention, the step of constructing a three-dimensional temperature field of the welding pool based on the infrared thermal radiation signal of the welding pool includes:

[0067] Performing multi-spectral infrared thermal imaging on the welding molten pool to obtain a multi-band thermal radiation distribution on the surface of the molten pool;

[0068] Performing chromatic aberration separation on the depth characteristic spectrum based on the multi-band thermal radiation distribution to obtain a thermal radiation gradient in the depth direction of the molten pool;

[0069] Mapping the thermal radiation gradient to a spatial filter array to obtain a three-dimensional voxel temperature distribution of the molten pool;

[0070] Isothermal boundary reconstruction is performed on the three-dimensional voxel temperature distribution to obtain a three-dimensional temperature field of the molten pool.

[0071] Specifically, multispectral infrared thermal imaging is performed on the welding pool.

[0072] Furthermore, a multispectral infrared thermal imaging device is used to align with the surface of the welding pool, and the thermal radiation signals of the molten pool surface in different infrared bands are synchronously collected through multiple spectral channels of the device.

[0073] Furthermore, these thermal radiation signals are converted into digital image data through signal amplification and analog-to-digital conversion, thereby obtaining the multi-band thermal radiation distribution of the molten pool surface.

[0074] Furthermore, the distribution contains the thermal radiation intensity information of each area on the molten pool surface at different wavelengths, providing accurate basic data for subsequent depth feature analysis and temperature field construction.

[0075] Specifically, the depth characteristic spectrum is separated by chromatic aberration based on the multi-band thermal radiation distribution.

[0076] Furthermore, the spectral information corresponding to different wavelengths in the multi-band thermal radiation distribution is carefully analyzed to establish a mapping relationship between wavelength and molten pool depth.

[0077] Furthermore, by utilizing the significant differences in infrared spectral absorption and reflection characteristics of the molten pool materials at different depths, a specific wavelength screening threshold is set through spectral color difference analysis technology to separate the characteristic spectrum related to the molten pool depth from the overall spectrum.

[0078] Furthermore, the gradient calculation method is used to calculate the rate of change of thermal radiation intensity at different positions in the depth direction of the molten pool, and the thermal radiation gradient in the depth direction of the molten pool is obtained. This gradient can accurately reflect the trend of change of the molten pool temperature with depth, and provide key parameters for the construction of the three-dimensional temperature field.

[0079] Specifically, the thermal radiation gradient is mapped to a spatial filter array.

[0080] Furthermore, a three-dimensional spatial filter array model is constructed, in which each node of the array corresponds to a tiny voxel in the molten pool space, and the voxel size is set according to the welding process accuracy requirements.

[0081] Furthermore, according to the depth-wise thermal radiation variation law represented by the thermal radiation gradient and in accordance with preset mapping rules, the thermal radiation gradient value at each depth position is accurately allocated to the corresponding spatial filter array node.

[0082] Furthermore, the discrete gradient values ​​are smoothed and three-dimensionally interpolated to convert them into a continuous three-dimensional spatial distribution, thereby obtaining the three-dimensional voxel temperature distribution of the molten pool. This distribution clearly describes the temperature conditions at each spatial position inside the molten pool in units of voxels, realizing the voxelized representation of the temperature field.

[0083] Specifically, isothermal boundary reconstruction is performed on the three-dimensional voxel temperature distribution.

[0084] Furthermore, all voxels in the three-dimensional voxel temperature distribution are traversed, and voxel nodes with the same temperature value are extracted according to a set temperature interval threshold.

[0085] Furthermore, by using the boundary detection technology in 3D image processing, these nodes with the same temperature are connected into a continuous surface through edge tracking and contour extraction algorithms.

[0086] Furthermore, the surface is filled and optimized to eliminate holes and burrs, and isothermal surfaces corresponding to different temperature values ​​are constructed.

[0087] Furthermore, all isothermal surfaces are finally combined in the order of temperature gradient to obtain the three-dimensional temperature field of the molten pool. This temperature field intuitively displays the temperature distribution state in the three-dimensional space inside the molten pool, providing an accurate temperature basis for subsequent molten pool state analysis and energy distribution control.

[0088] In general, multispectral infrared thermal imaging collects multi-band thermal radiation distribution on the molten pool surface, providing accurate data for depth feature analysis, improving the accuracy of temperature field construction, and improving the accuracy of weld penetration control.

[0089] In general, based on the chromatic aberration separation of multi-band thermal radiation distribution, the thermal radiation gradient in the depth direction is obtained, which reflects the temperature change trend, provides key parameters for the construction of the three-dimensional temperature field, and realizes the dynamic adjustment of the melting depth control.

[0090] In general, the thermal radiation gradient is mapped to the spatial filter array to obtain the three-dimensional voxel temperature distribution, realizing the voxel representation of the temperature field, laying the foundation for the reconstruction of the isothermal boundary, ensuring the accurate presentation of the molten pool temperature, and assisting in the setting of the penetration control parameters.

[0091] In general, the isothermal boundaries of the three-dimensional voxel temperature distribution are reconstructed to obtain the three-dimensional temperature field of the molten pool, which intuitively displays the internal temperature state and provides a basis for molten pool state analysis and energy distribution, so that the energy distribution and focus adjustment are in line with the molten pool state, thereby improving the depth of penetration control effect.

[0092] S2. calibrating the metal vapor concentration in the welding pool based on the intensity of the specific element spectral line of the plasma spectrum signal in the welding pool;

[0093] In an embodiment of the present invention, the calibrating the metal vapor concentration in the welding pool based on the intensity of the specific element spectral line of the plasma spectrum signal in the welding pool includes:

[0094] Performing dual-path beam splitting on the plasma spectrum signal to obtain synchronized light intensity signals of characteristic spectrum lines and reference spectrum lines;

[0095] performing differential amplification processing on the synchronous light intensity signal to obtain a relative intensity ratio of elemental spectral lines of the molten pool;

[0096] Performing photoelectric conversion linear calibration on the relative intensity ratio of the elemental spectral lines to obtain a molten pool metal vapor concentration gradient value of the molten pool;

[0097] The boundary of the concentration distribution field is reconstructed based on the vapor concentration gradient value to obtain the molten pool metal vapor concentration field of the molten pool.

[0098] Specifically, dual-path beam splitting is performed on the plasma spectrum signal.

[0099] Furthermore, a dual-path beam splitting system in a spectrum acquisition device is used to split the plasma spectrum signal into two optical signals through a beam splitter.

[0100] Furthermore, one of the optical signals passes through a filter of a specific wavelength to obtain an optical signal containing a characteristic spectrum line of the target metal element, and the other optical signal passes through a filter of a reference wavelength to obtain a reference spectrum line optical signal as a benchmark.

[0101] Furthermore, the light intensity of the two optical signals is collected in real time by a synchronous collection device to obtain a synchronous light intensity signal of the characteristic spectrum line and the reference spectrum line, which includes the light intensity data of the characteristic spectrum line and the reference spectrum line at the same time.

[0102] Specifically, differential amplification processing is performed on the synchronization light intensity signal.

[0103] Furthermore, the light intensity signal of the characteristic spectrum line and the light intensity signal of the reference spectrum line are input into a differential amplifier, and a subtraction operation is performed on the two signals through the differential amplifier to obtain a difference between the two signals.

[0104] Furthermore, the difference signal is amplified to enhance the signal strength for subsequent analysis.

[0105] Furthermore, after processing, the relative intensity ratio of the elemental spectral lines of the molten pool is obtained, which reflects the proportional relationship between the intensity of the characteristic spectral line and the intensity of the reference spectral line, eliminating the influence of interference factors such as background light intensity.

[0106] Specifically, photoelectric conversion linear calibration is performed on the relative intensity ratio of the elemental spectral lines.

[0107] Furthermore, the optical signal corresponding to the relative intensity ratio of the elemental spectral lines is first converted into an electrical signal by a photoelectric detector, and the magnitude of the electrical signal is proportional to the relative intensity ratio of the light intensities.

[0108] Furthermore, a linear relationship model between the relative intensity ratio of element spectral lines and the metal vapor concentration is established using a standard sample with a known metal vapor concentration.

[0109] Furthermore, the measured electrical signal is substituted into the linear relationship model to calculate the corresponding metal vapor concentration value, and further obtain the molten pool metal vapor concentration gradient value of the molten pool, which represents the variation range of the metal vapor concentration at different positions in the molten pool.

[0110] Specifically, the boundary of the concentration distribution field is reconstructed based on the steam concentration gradient value.

[0111] Furthermore, the spatial range of the concentration distribution field is determined according to the geometric shape and size of the molten pool.

[0112] Furthermore, based on the steam concentration gradient value, the concentration value is gradually filled inward starting from the boundary of the molten pool.

[0113] Furthermore, by calculating the concentration changes at adjacent positions point by point and combining the gradient value to determine the concentration distribution trend, a continuous concentration distribution field is constructed.

[0114] Furthermore, during the construction process, the boundaries of the concentration distribution field are corrected and optimized to ensure that the concentration values ​​at the boundaries conform to the actual physical laws, and finally the molten pool metal vapor concentration field of the molten pool is obtained, which intuitively shows the three-dimensional distribution of the metal vapor concentration in the molten pool.

[0115] In general, dual-path beam splitting collects plasma spectral signals and obtains light intensity signals synchronized with the reference spectral lines, providing an accurate concentration data basis for melting depth control.

[0116] In general, differential amplification processes the synchronous light intensity signal to obtain the relative intensity ratio of the element spectral lines, eliminate interference to improve the concentration calibration accuracy, and make the melting depth control more accurate.

[0117] In general, the photoelectric conversion linear calibration intensity ratio is used to obtain the metal vapor concentration gradient value, and the concentration distribution is quantified to support dynamic adjustment of the penetration depth control.

[0118] In general, the concentration distribution field is reconstructed based on the concentration gradient value, and the three-dimensional distribution of metal vapor in the molten pool is intuitively presented, providing a basis for energy distribution for depth control.

[0119] S3, coupling analysis of the three-dimensional temperature field of the molten pool and the metal vapor concentration of the molten pool to obtain molten pool state characteristics of the welding molten pool;

[0120] In an embodiment of the present invention, coupling analysis of the three-dimensional temperature field of the molten pool and the metal vapor concentration of the molten pool to obtain the molten pool state characteristics of the welding molten pool includes:

[0121] Synchronizing the dynamic distribution data of the three-dimensional temperature field of the molten pool with the real-time monitoring data of the metal vapor concentration of the molten pool to obtain a coupled data set of the molten pool;

[0122] Performing vector superposition of the temperature gradient and the steam concentration gradient based on the coupled data set to obtain interactive characteristics of energy transfer and material migration within the molten pool;

[0123] Based on the interaction characteristics, the convection intensity distribution and the vaporization suppression region boundary in the molten pool fluid are identified to obtain the molten pool state characteristics of the welding molten pool.

[0124] The identifying of the convection intensity distribution and the vaporization suppression region boundary in the molten pool fluid based on the interaction characteristics to obtain the molten pool state characteristics of the welding molten pool includes:

[0125] Collect the plasma light pattern morphology and the ripple direction of the molten pool surface;

[0126] determining a vaporization suppression region boundary according to a contraction width of the plasma light pattern;

[0127] The convection intensity distribution in the molten pool fluid is identified based on the convergence direction of the ripples on the molten pool surface, and the identified convection intensity distribution is used as the molten pool state feature of the welding molten pool.

[0128] Specifically, the dynamic distribution data of the three-dimensional temperature field of the molten pool and the real-time monitoring data of the metal vapor concentration of the molten pool are synchronized.

[0129] Furthermore, the three-dimensional temperature field data of the molten pool and the metal vapor concentration data of the molten pool at the same moment are associated with each other by timestamp matching to form a time-aligned data set.

[0130] Furthermore, during the data synchronization process, spatial coordinate mapping is performed on the temperature field data and the concentration data.

[0131] Furthermore, it is ensured that both are analyzed in the same spatial coordinate system, thereby obtaining a coupled data set of the molten pool, which contains the temperature and concentration information at the same time and spatial position.

[0132] Specifically, the temperature gradient and the steam concentration gradient are vector-superimposed based on the coupled data set.

[0133] Furthermore, at each spatial point in the coupled data set, the gradient vector of the temperature field and the gradient vector of the concentration field are calculated respectively. These two vectors represent the rate of change and direction of the temperature and concentration at that point, respectively.

[0134] Furthermore, these two gradient vectors are superimposed in the same proportion to obtain a new vector, which represents the direction and intensity of the combined effect of energy transfer and material migration inside the molten pool.

[0135] Furthermore, the interactive characteristics of energy transfer and material migration inside the molten pool were obtained, which reflects the synergistic effect of temperature and concentration changes.

[0136] Specifically, the convection intensity distribution and the vaporization inhibition region boundary in the molten pool fluid are identified based on the interaction characteristics.

[0137] Furthermore, by analyzing the size and direction of the interaction characteristic vector, the flow trend and intensity of the fluid in the molten pool are determined. The size of the interaction characteristic vector represents the size of the convection intensity, and the direction of the vector represents the direction of fluid flow, thereby obtaining the convection intensity distribution.

[0138] Furthermore, based on the specific combination conditions of temperature and concentration in the interaction characteristics, areas with high steam concentration and large temperature gradient changes in the molten pool are identified. These areas correspond to areas where the vaporization process is suppressed.

[0139] Furthermore, the boundaries of these areas are determined by a boundary detection algorithm, and finally the molten pool state characteristics of the welding pool are obtained, which include the information of the convection intensity distribution in the molten pool and the boundary of the vaporization inhibition area.

[0140] Specifically, the plasma light pattern morphology and the ripple direction of the molten pool surface are collected.

[0141] Furthermore, a high-speed camera is used to aim at the welding pool area, and by setting specific optical filters, the luminous morphology of the plasma light pattern and the ripple pattern formed by the reflected light on the surface of the molten pool are captured respectively.

[0142] Furthermore, the collected image sequence is subjected to frame synchronization processing to ensure that the plasma light pattern and the molten pool ripple in each frame image correspond to the molten pool state at the same moment, thereby obtaining image data containing the plasma light pattern morphology and the ripple direction of the molten pool surface.

[0143] Specifically, the boundary of the vaporization suppression region is determined according to the contraction width of the plasma light ripple morphology.

[0144] Furthermore, the collected plasma light streak image is gray-scaled to enhance the contrast of the light streak edge.

[0145] Furthermore, the outline of the light streak is identified by edge detection technology, and the width of the light streak at different positions is calculated.

[0146] Furthermore, when the width of the light pattern shrinks significantly, the coordinate point of the position is recorded.

[0147] Furthermore, the coordinate points of these contraction positions are connected into a continuous curve, which is the boundary of the vaporization inhibition area, because the contraction of the plasma light pattern reflects the area where the vaporization process on the molten pool surface is inhibited.

[0148] Specifically, the convection intensity distribution in the molten pool fluid is identified based on the convergence direction of the ripples on the molten pool surface, and the identified convection intensity distribution is used as the molten pool state feature of the welding molten pool.

[0149] Furthermore, the ripple image of the molten pool surface is subjected to directional filtering to extract the main direction information of the ripples.

[0150] Furthermore, by analyzing the changing trend of the directions of adjacent ripples, the convergence and divergence points of the ripples are determined.

[0151] Furthermore, in the direction of ripple convergence, the fluid flow velocity is faster, corresponding to a higher convection intensity; while in the direction of ripple divergence, the fluid flow velocity is slower, corresponding to a lower convection intensity.

[0152] Furthermore, the molten pool is divided into different convection intensity regions according to the convergence degree and direction of the ripples, thereby obtaining the distribution of convection intensity in the molten pool fluid, and the distribution is used as the molten pool state characteristic of the welding molten pool.

[0153] In general, the synchronous temperature field and concentration real-time data acquisition coupled data set provides a multi-dimensional fusion analysis basis for melt depth control and improves the accuracy of state judgment.

[0154] In general, the vector superposition of temperature and concentration gradients yields interactive features, revealing the synergistic effect of energy transfer and material migration, and providing a dynamic basis for adjusting the melting depth control parameters.

[0155] In general, the convection intensity and vaporization suppression area are identified based on the interactive features, and the molten pool state characteristics are accurately obtained, so that the laser-arc energy distribution is more in line with the actual needs of the molten pool and the melting depth control effect is optimized.

[0156] In general, the plasma light pattern and the molten pool ripple direction are collected to provide the dynamic characteristic data basis of the molten pool surface for the control of the melting depth.

[0157] In general, the boundary of the vaporization suppression area is determined according to the shrinkage width of the light pattern, and the vaporization state of the molten pool surface is accurately defined, which helps to optimize the energy distribution.

[0158] In general, the convection intensity distribution is identified according to the ripple convergence direction, and the dynamic characteristics of the molten pool fluid are obtained, so that the laser-arc energy distribution is adapted to the molten pool state and the accuracy of the melting depth control is improved.

[0159] S4. Dynamically dividing the laser-arc energy distribution ratio based on the molten pool state characteristics;

[0160] In an embodiment of the present invention, the dynamically dividing the laser-arc energy distribution ratio based on the molten pool state characteristics includes:

[0161] performing orthogonal physical parameter separation based on the state characteristics of the molten pool to obtain the fluidity parameter and stability parameter of the molten pool;

[0162] The fluidity parameter and the stability parameter are superimposed to obtain a dynamic coupling effect of laser energy and arc energy;

[0163] The real-time change trend of the dynamic coupling relationship is adaptively distributed to obtain the laser-arc energy distribution ratio.

[0164] The orthogonal physical parameter separation based on the molten pool state characteristics to obtain the fluidity parameter and stability parameter of the molten pool includes:

[0165] Mapping the heat flux vector in the molten pool state characteristic to the heat transfer dominant axis to obtain a first orthogonal component representing energy transfer;

[0166] Mapping the melt flow vector in the molten pool state characteristic to the material migration dominant axis to obtain a second orthogonal component characterizing material transport;

[0167] The modulus of the first orthogonal component is used as the melt pool fluidity parameter, and the directional consistency of the second orthogonal component is used as the melt pool stability parameter.

[0168] Specifically, orthogonal physical parameter separation is performed based on the molten pool state characteristics.

[0169] Furthermore, the convection intensity distribution and vaporization suppression zone boundary in the molten pool state characteristics are quantitatively analyzed, and the vector direction and velocity amplitude of the convection intensity distribution are converted into the fluidity index of the molten pool through image processing technology. The larger the value of this index, the stronger the flow ability of the molten pool fluid.

[0170] Furthermore, through the boundary stability evaluation method, the fluctuation amplitude and maintenance time of the vaporization inhibition zone boundary are mapped into the stability index of the molten pool. The larger the value of the index, the more stable the boundary state.

[0171] Furthermore, a two-dimensional orthogonal coordinate system is then constructed, with the liquidity index as the horizontal axis and the stability index as the vertical axis, and the two indicators are projected onto the corresponding coordinate axes respectively.

[0172] Furthermore, the correlation between the two is eliminated through coordinate transformation, and the separation of the two physical parameters is achieved, ultimately obtaining the fluidity parameter and stability parameter of the molten pool. These two parameters are independent of each other and describe the physical properties of the molten pool from different dimensions.

[0173] Specifically, the fluidity parameter and the stability parameter are superimposed.

[0174] Furthermore, based on the physical mechanism of the effects of laser energy and arc energy on the molten pool, the preset weight coefficients were determined through preliminary welding process tests, where the laser energy weight was positively correlated with the fluidity parameter, and the arc energy weight was positively correlated with the stability parameter.

[0175] Furthermore, the fluidity parameters and stability parameters are linearly superimposed and combined according to preset weights, and a dynamic adjustment mechanism is set during the superposition process: when the fluidity parameter is greater than the set threshold, the weight ratio of the stability parameter is automatically reduced to avoid excessive tendency of energy distribution towards stable control; when the stability parameter is greater than the set threshold, the weight ratio of the fluidity parameter is reduced accordingly to ensure that the energy distribution meets the requirements of the molten pool state.

[0176] Furthermore, through the weighted superposition method, a parameter is obtained that comprehensively reflects the dynamic coupling effect produced when the laser energy and arc energy act together on the molten pool. This parameter can reflect the interaction intensity and balance relationship between the two energy forms in the molten pool.

[0177] Specifically, adaptive allocation is performed on the real-time change trend of the dynamic coupling relationship.

[0178] Furthermore, a real-time data acquisition system is used to perform high-frequency sampling of the dynamic coupling effect parameters, and a trend analysis algorithm is used to identify the slope and direction of the parameter changes over time.

[0179] Furthermore, when it is monitored that the coupling effect parameters change in the direction of enhancing fluidity, the system automatically triggers the energy distribution adjustment program, reduces the laser energy output and increases the arc energy output according to the preset proportion to enhance the stability of the molten pool; when the coupling effect parameters change in the direction of enhancing stability, the laser energy output is increased and the arc energy output is reduced in the opposite proportion to maintain the necessary fluidity of the molten pool.

[0180] Furthermore, by continuously monitoring the changes in coupling parameters and adjusting the energy distribution in real time, the laser-arc energy distribution ratio is always kept in line with the dynamic changes of the molten pool, and finally a laser-arc energy distribution ratio that can optimally meet the welding requirements of the current molten pool state is obtained, ensuring the weld penetration control effect.

[0181] Specifically, the heat flow vector in the molten pool state characteristics is mapped to the heat transfer dominant axis.

[0182] Furthermore, the three-dimensional temperature field data of the molten pool is analyzed point by point. By comparing the temperature values ​​of adjacent systems, the temperature gradient vector of each spatial point is calculated, and then the direction of the maximum temperature gradient of the entire molten pool is determined, and this direction is set as the dominant axis direction of heat transfer.

[0183] Furthermore, for each heat flow vector, a vector decomposition method is used to decompose it into a component along the dominant axis of heat transfer and a component perpendicular to the axis.

[0184] Furthermore, the vertical component is discarded through coordinate transformation, and only the component along the axis direction is retained, thereby obtaining the first orthogonal component representing energy transfer.

[0185] Furthermore, this component can accurately reflect the intensity of heat flow in the dominant transmission direction, providing key data for subsequent analysis.

[0186] Specifically, the melt flow vector in the molten pool state characteristic is mapped to the material migration dominant axis.

[0187] Furthermore, the metal vapor concentration field data of the molten pool is spatially analyzed by calculating the metal vapor concentration difference at different positions.

[0188] Furthermore, the direction in which the concentration change is most significant, that is, the direction in which the vapor concentration gradient is the largest, is determined and used as the dominant axis direction of the substance migration.

[0189] Furthermore, each melt flow vector is decomposed into a component along the dominant axis of material migration and a component perpendicular to the axis.

[0190] Furthermore, by discarding the vertical component through vector projection and retaining only the component along the axial direction, the second orthogonal component characterizing material transport is obtained. This component can clearly reflect the transport capacity of the solute in the dominant migration direction and provide an important basis for the analysis of the molten pool state.

[0191] Specifically, the modulus of the first orthogonal component is used as the melt pool fluidity parameter, and the directional consistency of the second orthogonal component is used as the melt pool stability parameter.

[0192] Furthermore, the modulus length of the first orthogonal component is directly calculated, and the vector length value of this component is measured and used as the molten pool fluidity parameter. The numerical value of this parameter directly reflects the ability of the heat flow in the molten pool to drive the fluid flow. The larger the value, the stronger the fluidity.

[0193] Furthermore, for the second orthogonal component, a specific analysis area is first defined in the molten pool, and then the cosine value of the angle between the direction of the second orthogonal component at each point in the area and the direction of the dominant axis of material migration is calculated.

[0194] Furthermore, all cosine values ​​are arithmetic averaged and the average value is used as the molten pool stability parameter. The closer the parameter is to 1, the more concentrated the melt flow direction is and the more stable the molten pool state is, providing a reliable stability indicator for energy distribution.

[0195] In general, orthogonal separation of molten pool state characteristics obtains fluidity and stability parameters, providing independent quantitative indicators for energy distribution and improving the accuracy of melt depth control.

[0196] In general, the superposition of the two parameters obtains the dynamic coupling effect of laser-arc energy, and the comprehensive reaction energy synergy makes the energy distribution more in line with the actual needs of the molten pool.

[0197] In general, the real-time changing trend of the dynamic coupling relationship is adaptively distributed, the energy ratio is adjusted in real time, and the dynamic response capability and accuracy of the penetration control are enhanced.

[0198] In general, mapping the heat flux vector to the dominant axis of heat transfer to obtain the first orthogonal component quantifies the energy transfer intensity, provides an accurate indicator for the melt pool fluidity parameters, and helps the melt depth control to dynamically adapt the energy distribution.

[0199] In general, the melt flow vector is mapped to the dominant axis of material migration to obtain the second orthogonal component, and the stability of material transport is characterized by directional consistency, providing a state evaluation basis for penetration control.

[0200] In general, the modulus of the first orthogonal component is used as the fluidity parameter and the directional consistency of the second orthogonal component is used as the stability parameter to achieve orthogonal separation of the molten pool state, lay a quantitative foundation for the dynamic distribution of laser-arc energy, and improve the accuracy of melt depth control.

[0201] S5. Adjust the offset position of the laser focus in the weld depth direction based on the laser-arc energy distribution ratio, and adjust the arc voltage waveform through the inverter power supply.

[0202] In an embodiment of the present invention, adjusting the offset position of the laser focus in the weld depth direction based on the laser-arc energy distribution ratio includes:

[0203] monitoring the oscillation state of the weld pool in real time to obtain the oscillation frequency of the weld pool;

[0204] Performing a dynamic response analysis on the degree of deviation between the oscillation frequency and a preset reference frequency to obtain a penetration control signal of the molten pool;

[0205] Transmitting a displacement instruction to a servo motor based on the penetration control signal to obtain a depth-direction displacement of the molten pool;

[0206] The laser focus position is adjusted based on the depth-direction displacement to obtain an offset position in the depth direction of the weld.

[0207] The method of adjusting the arc voltage waveform by using an inverter power supply comprises:

[0208] Extracting a frequency variation in the oscillation frequency to obtain an oscillation frequency variation of the molten pool;

[0209] Mapping the modulation response characteristics to the oscillation frequency variation to obtain the arc voltage waveform parameters of the molten pool;

[0210] The inverter power supply switching sequence is reconstructed based on the arc voltage waveform parameters to obtain a modulated arc voltage waveform.

[0211] Specifically, the oscillation state of the weld pool is monitored in real time to obtain the oscillation frequency of the weld pool.

[0212] Furthermore, a high-precision oscillation sensor is installed on the welding equipment, and the sensing end of the sensor is aligned with the surface of the weld pool to ensure that the sensor can accurately capture the vibration signal of the weld pool.

[0213] Furthermore, the vibration signals on the surface of the molten pool are collected in real time by sensors and transmitted to the signal processing unit.

[0214] Furthermore, the collected vibration signal is filtered and a bandpass filter is used to remove the interference of environmental noise and irrelevant frequencies, retaining the effective signal related to the oscillation of the molten pool.

[0215] Furthermore, through the spectrum analysis method, the vibration signal in the time domain is converted into a frequency domain signal, the frequency components with concentrated energy are identified in the frequency domain, and the main frequency components of the molten pool oscillation are extracted from them, thereby obtaining the oscillation frequency of the molten pool, which can accurately reflect the dynamic vibration characteristics of the molten pool during the welding process.

[0216] Specifically, a dynamic response analysis is performed on the degree of deviation between the oscillation frequency and a preset reference frequency to obtain a penetration control signal of the molten pool.

[0217] Furthermore, the real-time monitored molten pool oscillation frequency is numerically compared with a pre-set reference frequency, and the frequency difference between the two is calculated.

[0218] Furthermore, according to the magnitude and sign of the frequency difference, a grading standard for the degree of deviation is established, for example, a plurality of different deviation intervals are set, each interval corresponding to a different control signal strength level.

[0219] Furthermore, when the frequency difference is within the allowable normal range, a control signal is generated to maintain the current penetration state; when the frequency difference exceeds the normal range, a corresponding adjustment control signal is generated according to the direction and degree of deviation, thereby obtaining a penetration control signal of the molten pool, which clearly indicates the direction and specific amplitude of the required adjustment of the penetration.

[0220] Specifically, a displacement instruction is transmitted to a servo motor based on the penetration control signal to obtain a depth-direction displacement of the molten pool.

[0221] Furthermore, the penetration control signal is input into the controller of the servo motor. The controller decodes the input signal, parses the direction and magnitude information of the displacement, and then amplifies the signal to generate a corresponding displacement instruction pulse.

[0222] Furthermore, after receiving the command pulse, the servo motor starts the encoder feedback system, monitors the position of the motor rotor in real time through the encoder, and accurately controls the rotation angle of the motor rotor.

[0223] Furthermore, through a transmission mechanism, such as a ball screw or a rack and pinion mechanism, the rotational motion of the motor is converted into linear motion, thereby driving the relevant components to produce displacement in the depth direction of the molten pool. The size and direction of the displacement are strictly determined by the penetration control signal, ensuring the accuracy and timeliness of the displacement and meeting the real-time requirements of penetration control.

[0224] Specifically, the laser focus position is adjusted based on the depth-direction displacement to obtain an offset position in the depth direction of the weld.

[0225] Furthermore, the depth displacement generated by the servo motor is transmitted to the adjustment mechanism of the laser focusing system through a mechanical connection. The adjustment mechanism is usually composed of a precision guide rail and a lens bracket, which can achieve high-precision linear movement.

[0226] Furthermore, when the adjustment mechanism receives the displacement signal, it drives the laser focusing lens to move smoothly in the depth direction of the weld, thereby changing the focusing position of the laser beam.

[0227] Furthermore, the actual position of the laser focus is monitored in real time by a position sensor installed in the focusing system, and the actual position is compared with the target position. If there is a deviation, fine-tuning correction is performed to ensure that the focusing lens moves to the precise position, and finally the offset position in the depth direction of the weld is obtained.

[0228] Furthermore, this position accurately reflects the adjustment result of the laser focus in the depth direction, can well adapt to the current molten pool state, and achieve precise control of the weld penetration depth.

[0229] Specifically, the frequency variation of the oscillation frequency is extracted to obtain the oscillation frequency variation of the molten pool.

[0230] Furthermore, a time series analysis is performed on the real-time monitored molten pool oscillation frequency, and the oscillation frequency is sampled at a fixed sampling interval at consecutive time points to ensure the temporal consistency of the sampled data.

[0231] Furthermore, the frequency difference between adjacent sampling points is calculated to obtain the raw data of frequency change. Through low-pass filtering, an appropriate cutoff frequency is set to remove high-frequency noise in the frequency difference, which may be caused by environmental interference or equipment errors.

[0232] Furthermore, the frequency change trend that truly reflects the change in the molten pool state is retained, thereby obtaining the oscillation frequency change of the molten pool. This change can sensitively reflect the dynamic change of the energy state inside the molten pool and provide an accurate basis for subsequent voltage waveform adjustment.

[0233] Specifically, the modulation response characteristics are mapped to the oscillation frequency variation to obtain the arc voltage waveform parameters of the molten pool.

[0234] Furthermore, a modulation response characteristic database is established in advance through a large number of welding experiments and data analysis.

[0235] Furthermore, the database records in detail the mapping relationship between different oscillation frequency changes and the corresponding optimal arc voltage waveform parameters.

[0236] Furthermore, according to the currently acquired oscillation frequency variation, a linear interpolation or nearest neighbor search method is used in the database to find the best matching mapping entry.

[0237] Furthermore, the corresponding arc voltage waveform parameters are extracted to ensure the best coupling effect between the arc energy input and the oscillation state of the molten pool, so that the arc energy can better adapt to the dynamic changes of the molten pool.

[0238] Specifically, the inverter power supply switching sequence is reconstructed based on the arc voltage waveform parameters to obtain a modulated arc voltage waveform.

[0239] Furthermore, the extracted arc voltage waveform parameters are input into a control unit of the inverter power supply, and a built-in processor of the control unit performs calculations and processing based on the waveform parameters to generate a corresponding pulse width modulation signal.

[0240] Furthermore, the pulse signal is encoded through a logic circuit, and the digital signal is converted into a drive signal that can control the power switching device, thereby reconstructing the on and off timing of the power switching device in the inverter power supply to form a specific switching sequence.

[0241] Furthermore, the power switching device operates precisely according to the reconstructed switching sequence, converting the DC power input into an AC output with specific waveform characteristics. After filtering and shaping, the modulated arc voltage waveform is finally obtained. This waveform can accurately match the energy demand of the current state of the molten pool, thereby realizing precise control of the arc energy.

[0242] In general, real-time monitoring of the molten pool oscillation state to obtain the oscillation frequency provides dynamic data support for penetration control and ensures that the focus adjustment responds to molten pool changes in a timely manner.

[0243] In general, the degree to which the oscillation frequency deviates from the reference frequency is analyzed to obtain the penetration control signal, and the frequency difference is converted into precise control instructions to improve the targetedness of the penetration control.

[0244] In general, the servo motor is driven based on the control signal to generate depth displacement, and millimeter-level precise displacement is achieved through encoder feedback and transmission mechanism to ensure the accuracy of focus adjustment.

[0245] In general, the laser focus position is adjusted according to the depth displacement and corrected in real time, so that the laser energy action depth dynamically adapts to the molten pool state, directly improving the accuracy of weld penetration control.

[0246] In general, extracting the change in oscillation frequency provides a real-time dynamic basis for adjusting the arc voltage waveform, so that the energy output adapts to the molten pool state.

[0247] In general, the modulation response characteristics are mapped to the frequency variation to obtain the arc voltage waveform parameters, ensuring that the voltage waveform accurately matches the molten pool oscillation.

[0248] In general, the inverter power switching sequence is reconstructed to generate a modulated arc voltage waveform, which can realize dynamic control of arc energy and improve the accuracy of penetration control.

[0249] like Figure 2 1 is a functional module diagram of a weld penetration control system for laser arc hybrid welding provided by one embodiment of the present invention.

[0250] The weld penetration control system 100 for laser arc hybrid welding described in the present invention can be installed in an electronic device. Depending on the functionality implemented, the weld penetration control system 100 for laser arc hybrid welding can include a molten pool three-dimensional temperature field construction module 101, a molten pool metal vapor concentration calibration module 102, a comprehensive molten pool state characteristic module 103, a laser-arc energy distribution ratio module 104, and an arc voltage waveform adjustment module 105. The modules described in the present invention, also referred to as units, refer to a series of computer program segments that can be executed by an electronic device processor and perform fixed functions, and are stored in the electronic device's memory.

[0251] In this embodiment, the functions of each module / unit are as follows:

[0252] The molten pool three-dimensional temperature field construction module 101 constructs the molten pool three-dimensional temperature field based on the infrared thermal radiation signal of the welding molten pool;

[0253] The molten pool metal vapor concentration calibration module 102 calibrates the molten pool metal vapor concentration based on the intensity of the specific element spectrum line of the plasma spectrum signal in the welding molten pool;

[0254] The comprehensive molten pool state characteristic module 103 couples and analyzes the molten pool three-dimensional temperature field and the molten pool metal vapor concentration to obtain the molten pool state characteristics of the welding molten pool;

[0255] The laser-arc energy distribution ratio module 104 dynamically divides the laser-arc energy distribution ratio based on the molten pool state characteristics;

[0256] The arc voltage waveform adjustment module 105 adjusts the offset position of the laser focus in the weld depth direction based on the laser-arc energy distribution ratio, and adjusts the arc voltage waveform through an inverter power supply.

[0257] In the several embodiments provided by the present invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the module division is merely a logical function division, and other division methods may be used in actual implementation.

[0258] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0259] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0260] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0261] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0262] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for controlling weld penetration depth in laser arc hybrid welding, characterized in that: The method comprises: S1. Constructing a three-dimensional temperature field of the weld pool based on the infrared thermal radiation signal of the weld pool; S2. Calibrate the metal vapor concentration in the weld pool based on the intensity of the specific element line of the plasma spectral signal in the weld pool; S3. Coupling analysis of the three-dimensional temperature field of the molten pool and the metal vapor concentration of the molten pool to obtain the molten pool state characteristics of the welding molten pool; S4. Dynamically divide the laser-arc energy distribution ratio based on the characteristics of the molten pool state; S5. Adjust the offset position of the laser focus in the weld depth direction based on the laser-arc energy distribution ratio, and adjust the arc voltage waveform through the inverter power supply.

2. The method for controlling weld penetration depth of laser arc hybrid welding according to claim 1, wherein: The method of constructing a three-dimensional temperature field of the molten pool based on the infrared thermal radiation signal of the welding molten pool includes: Performing multi-spectral infrared thermal imaging on the welding molten pool to obtain a multi-band thermal radiation distribution on the surface of the molten pool; Performing chromatic aberration separation on the depth characteristic spectrum based on the multi-band thermal radiation distribution to obtain a thermal radiation gradient in the depth direction of the molten pool; Mapping the thermal radiation gradient to a spatial filter array to obtain a three-dimensional voxel temperature distribution of the molten pool; Isothermal boundary reconstruction is performed on the three-dimensional voxel temperature distribution to obtain a three-dimensional temperature field of the molten pool.

3. The method for controlling weld penetration depth of laser arc hybrid welding according to claim 1, wherein: The method of calibrating the metal vapor concentration in the welding pool based on the intensity of the specific element spectrum line of the plasma spectrum signal in the welding pool includes: Performing dual-path beam splitting on the plasma spectrum signal to obtain synchronized light intensity signals of characteristic spectrum lines and reference spectrum lines; performing differential amplification processing on the synchronous light intensity signal to obtain a relative intensity ratio of elemental spectral lines of the molten pool; Performing photoelectric conversion linear calibration on the relative intensity ratio of the elemental spectral lines to obtain a molten pool metal vapor concentration gradient value of the molten pool; The boundary of the concentration distribution field is reconstructed based on the vapor concentration gradient value to obtain the molten pool metal vapor concentration field of the molten pool.

4. The method for controlling weld penetration depth of laser arc hybrid welding according to claim 1, wherein: The coupling analysis of the three-dimensional temperature field of the molten pool and the metal vapor concentration of the molten pool to obtain the molten pool state characteristics of the welding molten pool includes: Synchronizing the dynamic distribution data of the three-dimensional temperature field of the molten pool with the real-time monitoring data of the metal vapor concentration of the molten pool to obtain a coupled data set of the molten pool; Performing vector superposition of the temperature gradient and the steam concentration gradient based on the coupled data set to obtain interactive characteristics of energy transfer and material migration within the molten pool; Based on the interaction characteristics, the convection intensity distribution and the vaporization suppression region boundary in the molten pool fluid are identified to obtain the molten pool state characteristics of the welding molten pool.

5. The method for controlling weld penetration depth in laser arc hybrid welding according to claim 4, wherein: The identifying of the convection intensity distribution and the vaporization suppression region boundary in the molten pool fluid based on the interaction characteristics to obtain the molten pool state characteristics of the welding molten pool includes: Collect the plasma light pattern morphology and the ripple direction of the molten pool surface; determining a vaporization suppression region boundary according to a contraction width of the plasma light pattern; The convection intensity distribution in the molten pool fluid is identified based on the convergence direction of the ripples on the molten pool surface, and the identified convection intensity distribution is used as the molten pool state feature of the welding molten pool.

6. The method for controlling weld penetration depth in laser arc hybrid welding according to claim 1, wherein: The dynamically dividing the laser-arc energy distribution ratio based on the molten pool state characteristics includes: performing orthogonal physical parameter separation based on the state characteristics of the molten pool to obtain the fluidity parameter and stability parameter of the molten pool; The fluidity parameter and the stability parameter are superimposed to obtain a dynamic coupling effect of laser energy and arc energy; The real-time change trend of the dynamic coupling relationship is adaptively distributed to obtain the laser-arc energy distribution ratio.

7. The method for controlling weld penetration depth in laser arc hybrid welding according to claim 6, wherein: The orthogonal physical parameter separation based on the molten pool state characteristics to obtain the fluidity parameter and stability parameter of the molten pool includes: Mapping the heat flux vector in the molten pool state characteristic to the heat transfer dominant axis to obtain a first orthogonal component representing energy transfer; Mapping the melt flow vector in the molten pool state characteristic to the material migration dominant axis to obtain a second orthogonal component characterizing material transport; The modulus of the first orthogonal component is used as the melt pool fluidity parameter, and the directional consistency of the second orthogonal component is used as the melt pool stability parameter.

8. The method for controlling weld penetration depth in laser arc hybrid welding according to claim 1, wherein: The adjusting the offset position of the laser focus in the weld depth direction based on the laser-arc energy distribution ratio includes: monitoring the oscillation state of the weld pool in real time to obtain the oscillation frequency of the weld pool; Performing a dynamic response analysis on the degree of deviation between the oscillation frequency and a preset reference frequency to obtain a penetration control signal of the molten pool; Transmitting a displacement instruction to a servo motor based on the penetration control signal to obtain a depth-direction displacement of the molten pool; The laser focus position is adjusted based on the depth-direction displacement to obtain an offset position in the depth direction of the weld.

9. The method for controlling weld penetration depth in laser arc hybrid welding according to claim 1, wherein: The method of adjusting the arc voltage waveform by using an inverter power supply comprises: Extracting a frequency variation in the oscillation frequency to obtain an oscillation frequency variation of the molten pool; Mapping the modulation response characteristics to the oscillation frequency variation to obtain the arc voltage waveform parameters of the molten pool; The inverter power supply switching sequence is reconstructed based on the arc voltage waveform parameters to obtain a modulated arc voltage waveform.

10. A weld penetration control system for laser arc hybrid welding, characterized in that: The system comprises: A 3D temperature field construction module for the molten pool is used to construct a 3D temperature field of the molten pool based on the infrared thermal radiation signal of the welding molten pool; A molten pool metal vapor concentration calibration module, used to calibrate the molten pool metal vapor concentration based on the intensity of specific element spectral lines of the plasma spectrum signal in the welding molten pool; A comprehensive molten pool state characteristic module is used to couple the molten pool three-dimensional temperature field with the molten pool metal vapor concentration to obtain the molten pool state characteristics of the welding molten pool; A laser-arc energy distribution ratio module, configured to dynamically divide the laser-arc energy distribution ratio based on the molten pool state characteristics; The arc voltage waveform adjustment module is used to adjust the offset position of the laser focus in the weld depth direction based on the laser-arc energy distribution ratio, and adjust the arc voltage waveform through an inverter power supply.

Images