Optimization method and device of aluminum alloy laser welding process and electronic equipment

Abstract

The application discloses an aluminum alloy laser welding process optimization method, device and electronic equipment. The method comprises the following steps: determining an optimal combination set satisfying a preset requirement in an initial combination set of laser power and welding speed of an aluminum alloy plate during welding; for each original welding detection data in an original welding detection data set, respectively performing visual inspection, welding section inspection and peel test fracture mode evaluation to obtain inspection and evaluation results; in the inspection and evaluation results, determining a welding process parameter combination satisfying a preset judgment rule, obtaining welding process data when welding is performed based on the welding process parameter combination, and adjusting the laser power and the welding speed based on the welding process data. The application solves the technical problems of long authentication cycle, poor quality consistency and difficulty in meeting the welding standard caused by the dependence of related aluminum alloy laser welding process parameters on experience trial and error, lack of systematic evaluation and closed-loop regulation.

Description

Technical Field

[0001] This application relates to the field of laser welding technology, and more specifically, to an optimization method, apparatus, and electronic equipment for aluminum alloy laser welding process. Background Technology

[0002] With the trend towards lightweighting in automobiles, aluminum alloys are increasingly used in vehicle body structures. Laser welding, due to its advantages such as high efficiency and low heat input, has become a key process for joining aluminum alloys. However, aluminum alloys have high reflectivity, high thermal conductivity, and are prone to oxidation, resulting in poor molten pool stability and making them highly susceptible to defects such as porosity and cracks.

[0003] The determination of relevant aluminum alloy laser welding process parameters mainly relies on trial and error based on human experience, lacking a systematic parameter screening model and a multi-dimensional quality evaluation system. This unsystematic development approach results in long process certification cycles, low pass rates, and difficulty in ensuring consistent welding quality under large-scale production, failing to meet the stringent welding standards of modern automobile manufacturing for high-strength, long-life aluminum alloy structural components.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This application provides an optimization method, apparatus, and electronic equipment for aluminum alloy laser welding process, which at least solves the technical problems of long certification cycles, poor quality consistency, and difficulty in meeting welding standards caused by the reliance on experience-based trial and error, lack of systematic evaluation, and closed-loop control in determining relevant aluminum alloy laser welding process parameters.

[0006] According to one aspect of this application, an optimization method for aluminum alloy laser welding process is provided, comprising: obtaining an initial combination set of laser power and welding speed for welding aluminum alloy sheets; comparing welding methods with different spot shapes within the initial combination set to obtain comparison results; and determining a preferred combination set in the initial combination set whose comparison results meet preset requirements; obtaining an original weld inspection data set, wherein the original weld inspection data set includes: first original weld inspection data of a single-spot laser welding device under each preferred combination in the preferred combination set, and second original weld inspection data of a dual-spot laser welding device under each preferred combination in the preferred combination set; performing visual inspection, weld cross-section inspection, and peel test fracture mode evaluation on each original weld inspection data in the original weld inspection data set to obtain inspection and evaluation results; determining a welding process parameter combination that meets preset judgment rules from the inspection and evaluation results; obtaining welding process data when welding based on the welding process parameter combination; and adjusting the laser power and welding speed based on the welding process data.

[0007] Optionally, an initial set of combinations of laser power and welding speed for welding aluminum alloy sheets is obtained, including: laser power in the initial set ranging from 0.5kW to 3.0kW; welding speed in the initial set ranging from 0.8m / min to 2.5m / min; and the ratio of laser power to welding speed in the initial set ranging from 0.3kW. min / m to 1.2kW min / m.

[0008] Optionally, the dual-spot laser welding equipment adopts an annular spot or a beam splitting dual-focus structure; the welding power ratio of the dual-spot laser welding equipment is 1:1 or asymmetrical, wherein the power ratio range of the asymmetrical configuration includes 0.6:1 to 1.4:1.

[0009] Optionally, for each original weld inspection data in the original weld inspection data set, visual inspection and weld cross-section inspection are performed, including: identifying the weld surface image in the original weld inspection data to detect at least one of the following defects: incomplete penetration, arc crater, hole, crack, undercut, spatter, weld discontinuity, weld offset, uneven weld width, abnormal weld reinforcement, and surface oxidation defects; determining a visual quality index based on the detected defect type and quantity, wherein the visual quality index is used to characterize the appearance integrity and defect severity of the weld surface; measuring the metallographic image of the weld cross-section in the original weld inspection data to obtain at least one weld quality indicator among the following: weld penetration, weld width, area of ​​unfused region, porosity distribution density, width of heat-affected zone, and weld centerline offset; and determining a cross-section quality index based on the degree of deviation between the weld quality index and the preset standard value, wherein the cross-section quality index is used to characterize the geometric compliance and metallurgical bonding quality of the internal structure of the weld.

[0010] Optionally, for each original weld inspection data in the original weld inspection data set, a peel test fracture mode evaluation is performed, including: acquiring the fracture morphology features in the original weld inspection data; determining the fracture failure mode based on the fracture morphology features, wherein the fracture failure mode includes any one of weld pull-out failure, interface failure, or mixed fracture mode; in the case of weld pull-out failure, measuring the width of the weld after pull-out and determining whether the ratio of the weld width to the original weld width is not less than a first preset threshold; if so, determining that the evaluation result of the fracture failure mode is qualified; in the case of interface failure, calculating the area of ​​the unconnected region on the interface and determining whether the ratio of the area of ​​the unconnected region to the total weld area is not greater than a second preset threshold; if so, determining that the evaluation result of the fracture failure mode is qualified; in the case of mixed fracture mode, determining the qualification of the pull-out portion and the interface portion respectively, and determining that the evaluation result of the fracture failure mode is qualified if both the pull-out portion and the interface portion are qualified.

[0011] Optionally, after obtaining the inspection and evaluation results, the method further includes: constructing a two-dimensional data structure and determining the two-dimensional data structure as an initial matrix, wherein the initial matrix includes multiple predefined rows and multiple columns, wherein the columns correspond to the visual quality dimension, the cross-sectional quality dimension, and the fracture pass rate dimension, respectively; for each original weld inspection data in the original weld inspection data set, performing the following filling operations: extracting the process parameter combination corresponding to the original weld inspection data, wherein the process parameter combination includes: laser power, welding speed, spot shape, and shielding gas flow rate; generating a process parameter identifier based on the process parameter combination, wherein the process parameter identifier is used to identify the process parameter combination; finding or creating the corresponding target row in the initial matrix according to the process parameter identifier, and determining the correspondence between the target row and the current original weld inspection data; filling the visual quality index, cross-sectional quality index, and fracture pass rate corresponding to the original weld inspection data into the cells of the corresponding visual quality dimension, cross-sectional quality dimension, and fracture pass rate dimension in the target row, respectively, to generate a comprehensive weld quality evaluation matrix.

[0012] Optionally, in the inspection and evaluation results, the welding process parameter combination that meets the preset judgment rules is determined, including: generating a parameter space based on laser power, welding speed, spot morphology, shielding gas flow rate, and dual-spot parameters, wherein the dual-spot parameters include the dual-spot power ratio and spot spacing; executing a first sub-optimization process and a second sub-optimization process in parallel within the parameter space, wherein the first sub-optimization process is for the single-spot mode, using laser power, welding speed, and shielding gas flow rate as decision variables, and employing a multi-objective evolutionary algorithm to maximize the visual quality index, cross-sectional quality index, and fracture pass rate as optimization objectives, and iteratively searching in the single-spot subspace corresponding to the parameter space to obtain the single-spot Pareto optimal solution set; the second sub-optimization process is for the dual-spot mode, using laser power, welding speed, shielding gas flow rate, and dual-spot power ratio as decision variables, and iteratively searching in the single-spot subspace corresponding to the parameter space to obtain the single-spot Pareto optimal solution set; the second sub-optimization process is for the dual-spot mode, using laser power, welding speed, shielding gas flow rate, and dual-spot power ratio as decision variables, and iteratively searching in the single-spot subspace corresponding to the parameter space to obtain the single-spot Pareto optimal solution set; The spot spacing is the decision variable. A multi-objective evolutionary algorithm is used to maximize the visual quality index, cross-sectional quality index, and fracture pass rate as optimization objectives. Iterative search is performed in the dual-spot subspace corresponding to the parameter space to obtain the dual-spot Pareto optimal solution set. The single-spot Pareto optimal solution set and the dual-spot Pareto optimal solution set are merged into a candidate solution set. Non-dominated sorting is performed on the candidate solution set to eliminate dominated solutions, resulting in the global Pareto front. Based on the preset process preference constraints, the welding process parameter combination is obtained by screening in the global Pareto front. The process preference constraints include: under the same welding speed, dual-spot mode solutions are preferred to be retained. The corresponding single-spot mode solution is retained only if at least one of the visual quality index, cross-sectional quality index, or fracture pass rate of the single-spot mode solution is better than that of the corresponding dual-spot mode solution.

[0013] According to another aspect of this application, an optimization device for aluminum alloy laser welding process is also provided, comprising: a first acquisition module, used to acquire an initial combination set of laser power and welding speed for welding aluminum alloy plates, compare welding methods with different spot shapes within the initial combination set, obtain comparison results, and determine a preferred combination set in the initial combination set whose comparison results meet preset requirements; a second acquisition module, used to acquire an original weld inspection data set, wherein the original weld inspection data set includes: first original weld inspection data of a single-spot laser welding device under each preferred combination in the preferred combination set, and second original weld inspection data of a dual-spot laser welding device under each preferred combination in the preferred combination set; an evaluation module, used to perform visual inspection, weld cross-section inspection, and peel test fracture mode evaluation on each original weld inspection data in the original weld inspection data set, respectively, to obtain inspection and evaluation results; and an adjustment module, used to determine the welding process parameter combination that meets preset judgment rules from the inspection and evaluation results, acquire welding process data when welding based on the welding process parameter combination, and adjust the laser power and welding speed based on the welding process data.

[0014] According to another aspect of this application, a non-volatile storage medium is also provided, the storage medium including a stored program, wherein the program, when running, controls the device where the storage medium is located to execute the above-mentioned optimized method for aluminum alloy laser welding process.

[0015] According to another aspect of this application, an electronic device is also provided, comprising: a memory and a processor, the processor being configured to run a program stored in the memory, wherein the program, when running, executes the above-described optimized method for aluminum alloy laser welding process.

[0016] According to another aspect of this application, a computer program is also provided, wherein when the computer program is executed by a processor, it implements the above-described method for optimizing the aluminum alloy laser welding process.

[0017] According to another aspect of this application, a computer program product is also provided, comprising a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, which, when executed by a processor, implements the above-described optimized method for aluminum alloy laser welding process.

[0018] In this application, an initial set of laser power and welding speed combinations for welding aluminum alloy sheets is obtained. Within this initial set, welding methods with different spot shapes are compared to obtain comparison results. An optimal set of combinations that meets preset requirements is then determined from the initial set. A set of original weld inspection data is obtained, including: first original weld inspection data for each optimal combination of the single-spot laser welding equipment, and second original weld inspection data for each optimal combination of the dual-spot laser welding equipment. For each original weld inspection data set, visual inspection, weld cross-sectional inspection, and peeling tests are performed. Fracture mode assessment yields inspection and evaluation results. From these results, welding process parameter combinations that meet preset judgment rules are identified. Welding process data based on these parameter combinations is obtained. Based on this data, laser power and welding speed are adjusted to quickly determine high-quality process windows and achieve real-time dynamic control of the welding process. This significantly shortens the process certification cycle, improves the consistency and stability of welding quality, and meets the technical requirements of high-end automotive welding standards. Furthermore, it solves the technical problems of long certification cycles, poor quality consistency, and difficulty in meeting welding standards caused by relying on experience-based trial and error, lack of systematic evaluation, and closed-loop control in determining relevant aluminum alloy laser welding process parameters. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0020] Figure 1 This is a flowchart of an optimized method for an aluminum alloy laser welding process according to an embodiment of this application;

[0021] Figure 2 This is a schematic diagram of a laser welding structure according to an embodiment of this application;

[0022] Figure 3 This is a schematic diagram of the weld surface of a dual-spot laser weld according to an embodiment of this application;

[0023] Figure 4 This is a schematic diagram of a weld cross-section according to an embodiment of this application;

[0024] Figure 5 This is a schematic diagram of the peeling fracture surface of a dual-spot laser welded sample according to an embodiment of this application;

[0025] Figure 6 This is a schematic diagram of the surface of a single-spot laser weld according to an embodiment of this application;

[0026] Figure 7 This is a schematic diagram of another weld cross-section according to an embodiment of this application;

[0027] Figure 8 This is a schematic diagram of the peeling fracture surface of a single-spot laser welded sample according to an embodiment of this application;

[0028] Figure 9 This is a structural diagram of an optimized apparatus for an aluminum alloy laser welding process according to an embodiment of this application;

[0029] Figure 10 This is a hardware structure block diagram of a computer terminal for an optimized method of aluminum alloy laser welding process according to an embodiment of this application. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] According to an embodiment of this application, an embodiment of an optimized method for aluminum alloy laser welding process is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0033] Figure 1 This is a flowchart of an optimized method for an aluminum alloy laser welding process according to an embodiment of this application, such as... Figure 1 As shown, the method includes the following steps:

[0034] Step S102: Obtain an initial combination set of laser power and welding speed for welding aluminum alloy plates, compare welding methods with different spot shapes within the initial combination set, obtain comparison results, and determine the preferred combination set in the initial combination set that meets the preset requirements.

[0035] In step S102, firstly, based on the characteristics of aluminum alloy materials and welding standards in the automotive industry, an initial parameter space (i.e., an initial combination set) containing various combinations of laser power and welding speed is constructed. The initial combination set can be generated through preset physical constraints, such as setting the laser power between 0.5 kW and 3.0 kW, and the welding speed between 0.8 m / min and 2.5 m / min. The linear energy (the ratio of power to speed, P / v) is initially controlled within a reasonable range of 0.3 to 1.2 kW·min / m to exclude parameter combinations that are obviously unreasonable or prone to defects.

[0036] In this initial set of combinations, comparative welding tests were conducted on aluminum alloy sheets using both single-spot laser welding equipment and dual-spot laser welding equipment (such as annular spot or dual-focus beam splitting structure). By comparing the welding effects of the two different spot shapes under the same power and speed conditions, the surface formation quality of the weld, the back penetration, and the presence of initial defects such as incomplete penetration, porosity, and cracks were determined. Based on preset qualification criteria (such as no severe spatter on the surface, uniform back penetration, and no weld leaks), the parameter combinations with excellent performance were selected to form the aforementioned preferred combination set.

[0037] Step S102 significantly narrows the parameter search space for subsequent fine-tuning through low-cost and high-efficiency preliminary screening, avoiding blind trial and error.

[0038] Step S104: Obtain the original weld inspection data set, wherein the original weld inspection data set includes: the first original weld inspection data of the single-spot laser welding equipment under each preferred combination in the preferred combination set, and the second original weld inspection data of the dual-spot laser welding equipment under each preferred combination in the preferred combination set.

[0039] In step S104, for each set of process parameters (laser power and welding speed) selected in step S102, actual welding tests are conducted using both single-spot laser welding equipment and dual-spot laser welding equipment. For each parameter combination in the preferred combination set, welding is first performed using a single-spot device, and the resulting weld condition data is recorded. This data is called the first raw weld inspection data, which reflects the welding effect of the single-spot mode on the aluminum alloy sheet under given power and speed. For the exact same parameter combination, welding is performed using a dual-spot device, and the resulting weld condition data is recorded. This data is called the second raw weld inspection data, which reflects the welding effect of the dual-spot mode (such as annular spot or dual-focus structure) under the same energy input conditions.

[0040] The raw weld inspection data set in step S104 contains comparative data of two different spot morphologies under the same set of process parameters. It not only covers geometric dimensional information such as weld surface morphology, penetration depth, and weld width, but also records key indicators such as back penetration, surface defect types (such as porosity, cracks, and undercut), and weld pool stability.

[0041] Step S106: For each original weld inspection data in the original weld inspection data set, perform visual inspection, weld cross-section inspection, and peel test fracture mode evaluation to obtain inspection and evaluation results.

[0042] In step S106, visual inspection refers to the process of using auxiliary optical equipment to conduct a macroscopic appearance quality review of the weld surface after laser welding. This is used to identify and record visible defects on the weld surface, specifically including 11 typical defects such as incomplete penetration, arc craters, holes, cracks, undercut, spatter, weld discontinuities, weld misalignment, uneven weld width, abnormal weld reinforcement, and surface oxidation. By statistically analyzing the types and quantities of defects, a visual quality index is calculated and generated. This inspection is used to quantitatively assess the aesthetic appearance of the weld surface and the severity of surface defects.

[0043] Weld cross-section inspection refers to the process of analyzing the microstructure and measuring the geometric dimensions of the weld cross-section by cutting, embedding, grinding, and metallographic etching the weld sample. This inspection is used to evaluate the metallurgical bonding quality and structural integrity of the weld. The main measurement indicators include eight items: weld penetration, weld width, unfused area, porosity distribution, heat-affected zone width, and weld centerline offset. Based on these measurement data, a cross-sectional quality index is calculated to objectively reflect the weld's internal density, penetration, and the presence of hidden defects.

[0044] Peel test fracture mode assessment refers to a mechanical testing process in which a peel load is applied to a welded joint until fracture, and the failure mode of the joint is determined by analyzing the fracture morphology, thereby evaluating its connection strength. This assessment is based on fracture characteristics and is divided into three modes, with corresponding acceptance criteria:

[0045] Weld pull-out failure: The fracture surface shows tearing of the base metal. The remaining weld width after pull-out should not be less than 86% of the original weld width, indicating that the interfacial bonding strength is higher than the strength of the base metal.

[0046] Interface failure: The fracture surface separates along the weld interface, requiring that there are no continuous unconnected areas at the interface, and the total area of ​​the unconnected areas does not exceed 5% of the total weld area;

[0047] Hybrid fracture mode: It includes both pull-out and interface failure characteristics. The pull-out part and the interface part are required to meet the corresponding qualification criteria mentioned above. The whole is judged as qualified only when both are qualified.

[0048] Step S108: In the inspection and evaluation results, determine the welding process parameter combination that meets the preset judgment rules, obtain the welding process data when welding based on the welding process parameter combination, and adjust the laser power and welding speed based on the welding process data.

[0049] In step S108, firstly, based on the inspection and evaluation results generated in step S106, a preset judgment rule is applied for screening. The preset judgment rule can be combined with a multi-objective optimization algorithm to maximize the visual quality index, cross-sectional quality index, and peel test pass rate. For example, when a certain set of parameters (such as dual-spot 700W+900W / 1.2m / min) meets the automotive high-end welding standards in all evaluation dimensions (no surface defects, cross-sectional porosity below the threshold, peel test showing pull-out failure and width meeting the standard), this parameter combination is identified as the optimal process window.

[0050] Secondly, when applying the above optimal parameters to actual welding production, welding process data is collected in real time, with a focus on monitoring the morphological characteristics of the molten pool (such as molten pool length, width, and tail oscillation frequency). Since aluminum alloy welding is easily affected by factors such as plate gaps, surface conditions, or heat accumulation, leading to molten pool fluctuations and thus affecting weld quality, a proportional-integral-derivative (PID) or fuzzy logic control strategy is used, with the control target being that the molten pool width fluctuation does not exceed ±5%, to adjust the laser power and welding speed in real time. For example, when an abnormal increase in molten pool width is detected, the laser power is automatically reduced or the welding speed is increased to suppress excessive molten pool spread.

[0051] Steps S102 to S108 above first use single and dual spot comparison tests to screen the optimal combination of process parameters based on visual inspection, cross-section and peel test multi-dimensional indicators, and then apply the combination to actual welding and dynamically adjust the laser power and welding speed by monitoring the fluctuation of the weld pool width in real time. This achieves the purpose of quickly determining the high-quality process window and realizing real-time dynamic control of the welding process, thereby significantly shortening the process certification cycle, improving the consistency and stability of welding quality, and meeting the technical requirements of high-end automotive welding standards.

[0052] The following are Figure 1 The steps shown are illustrated and explained by way of example.

[0053] According to some optional embodiments of this application, the laser power in the initial assembly ranges from 0.5kW to 3.0kW; the welding speed in the initial assembly ranges from 0.8m / min to 2.5m / min; and the ratio of laser power to welding speed in the initial assembly ranges from 0.3kW·min / m to 1.2kW·min / m.

[0054] In this embodiment, the specific implementation process of obtaining the initial combination set of laser power and welding speed for welding aluminum alloy plates in step S102 can be defined as follows:

[0055] A parameter space containing various combinations of laser power and welding speed is constructed as the initial combination set. In this initial combination set, the laser power is limited to a range of 0.5kW to 3.0kW, covering the entire process range from low-power preheating to high-power penetration; the welding speed is limited to a range of 0.8m / min to 2.5m / min to adapt to welding requirements under different production cycles.

[0056] Furthermore, to ensure the physical rationality of the initial parameter combination and avoid extreme defects such as incomplete fusion or burn-through, the ratio of laser power (P, in kW) to welding speed (v, in m / min) (i.e., the line energy related parameter P / v) is constrained, with its value limited to a range of 0.3 kW·min / m to 1.2 kW·min / m. By generating meshed or discretized parameter combinations within this range, an initial set of combinations is formed, providing a comprehensive and reasonable parameter basis for subsequent comparative experiments.

[0057] According to some other optional embodiments of this application, the dual-spot laser welding equipment adopts an annular spot or a beam splitting dual-focus structure; the welding power ratio of the dual-spot laser welding equipment is 1:1 or asymmetrical, wherein the power ratio range of the asymmetrical configuration includes 0.6:1 to 1.4:1.

[0058] It should be noted that the dual-spot laser welding equipment in steps S102 and S104 has the following technical features: the dual-spot laser welding equipment adopts an annular spot structure or a beam splitting dual-focus structure to form a specific energy distribution pattern in and around the weld center, thereby optimizing the stability of the aluminum alloy molten pool and suppressing the generation of porosity and cracks.

[0059] In terms of power output configuration, the dual-spot laser welding equipment supports two power distribution modes:

[0060] Symmetrical configuration means that the welding power ratio of the two light spots is 1:1, which is suitable for scenarios with high requirements for weld symmetry.

[0061] Asymmetric configuration refers to a power ratio between the two laser spots ranging from 0.6:1 to 1.4:1. By adjusting the asymmetric power ratio, the thermal field distribution and fluid flow characteristics within the molten pool can be flexibly altered, allowing for refined process control for specific aluminum alloy materials or plate thicknesses to further improve welding quality.

[0062] In some optional embodiments of this application, step S106, which involves visual inspection and weld cross-section inspection for each original weld inspection data in the original weld inspection data set, can be achieved through the following steps: Identifying the weld surface image in the original weld inspection data to detect at least one of the following defects: incomplete penetration, arc crater, hole, crack, undercut, spatter, weld discontinuity, weld offset, uneven weld width, abnormal weld reinforcement, and surface oxidation defects; determining a visual quality index based on the detected defect type and quantity, wherein the visual quality index characterizes the appearance integrity and defect severity of the weld surface; measuring the metallographic image of the weld cross-section in the original weld inspection data to obtain at least one weld quality indicator among: weld penetration, weld width, area of ​​unfused region, porosity distribution density, width of heat-affected zone, and weld centerline offset; and determining a cross-section quality index based on the deviation of the weld quality index from a preset standard value, wherein the cross-section quality index characterizes the geometric compliance and metallurgical bonding quality of the weld's internal structure.

[0063] In this embodiment, the weld surface image is first acquired from the original weld inspection data. This weld surface image can be acquired by a high-resolution industrial camera after welding or in real time by an online visual inspection system. A pre-trained computer vision model (such as a convolutional neural network-based object detection algorithm) is then used to perform intelligent recognition processing on the weld surface image. This processing can automatically detect whether the weld surface exhibits at least one of the following 11 typical defects:

[0064] Incomplete penetration: The root of the weld is not fully fused; Arc crater: A depression formed at the end of the weld; Pore: Pores on or near the surface of the weld; Crack: A crack in the weld metal or heat-affected zone; Undercut: A groove formed by the ablation of the base metal at the edge of the weld by an electric arc or laser; Spatter: Metal particles adhering to the surface of the weld or its adjacent area; Weld discontinuity: A break in the middle of the weld; Weld offset: The deviation between the center line of the weld and the center line of the joint; Uneven weld width: Fluctuations in the width along the length of the weld; Abnormal weld reinforcement: The portion of the weld surface that is too high or too low above the base metal; Surface oxidation: Oxidation color or scale on the weld surface caused by poor protection.

[0065] After identifying specific defects, the type and quantity of each defect are statistically analyzed. A preset scoring algorithm is then used to determine the visual quality index. This scoring algorithm can employ a weighted deduction system or a point-based system. For example, initial deduction values ​​are set for each defect. If a weld has a crack (a serious defect), the visual quality index is directly determined to be unacceptable or extremely low; if spatter (a minor defect) is present, points are deducted proportionally based on the quantity and area of ​​the spatter.

[0066] The generated visual quality index can be a quantitative value (such as 0-100 points, or 0-1 levels) used to objectively characterize the appearance integrity and defect severity of the weld surface. The higher the index, the fewer the surface defects and the better the appearance quality.

[0067] Secondly, metallographic images of the weld cross-section are obtained from the original weld inspection data. These images can be obtained by cutting, mounting, grinding, polishing, and etching the welded sample, followed by imaging using a metallographic microscope or scanning electron microscope.

[0068] Image segmentation and measurement analysis are performed on the metallographic images of the weld cross-section to extract at least one or more of the following key weld quality indicators: penetration depth: the depth to which the weld metal penetrates the base metal; weld width: the width of the weld on the surface of the base metal; area of ​​unfused region: the area where the weld metal is not completely fused with the base metal or between weld metal layers; porosity distribution density: the number of pores per unit area or the proportion of the total area of ​​pores; width of heat-affected zone: the width of the area where the microstructure and properties change due to the welding thermal cycle; offset of weld centerline: the horizontal or vertical deviation of the geometric center of the weld relative to the joint center.

[0069] The obtained weld quality indicators are compared with pre-stored preset standard values ​​(i.e., target acceptable range or ideal value). For example, the target value for weld penetration is set as follows: The allowable deviation is ±ΔD. If the actual measured value is... Then calculate the deviation rate | - | / .

[0070] Based on the degree of deviation of each indicator from the standard value, the cross-sectional quality index is calculated and determined through a preset mathematical model (such as Gaussian function or linear regression). If all indicators are within the allowable deviation range, the cross-sectional quality index is set to its maximum value (such as 1.0 or 100 points); if an indicator exceeds the allowable range, points are deducted or the index value is reduced according to the degree of deviation.

[0071] Understandably, the generated cross-sectional quality index is used to objectively characterize the geometric compliance (such as whether the dimensions meet design requirements) and metallurgical bonding quality (such as the presence of internal defects, porosity, lack of fusion, etc.) of the weld's internal structure. The higher the index, the more perfect the internal structure and the higher the welding quality.

[0072] The above steps integrate intelligent identification of weld surface defects and quantitative analysis of cross-sectional metallographic indicators to construct a comprehensive evaluation process that includes both appearance integrity and internal metallurgical quality. This enables precise characterization of aluminum alloy welding quality from macroscopic appearance to microstructure, effectively improving the objectivity and consistency of quality judgment in process certification.

[0073] In some optional embodiments of this application, step S106, which evaluates the fracture mode of each original weld inspection data in the original weld inspection data set through a peel test, can be achieved through the following steps: acquiring the fracture morphology features in the original weld inspection data; determining the fracture failure mode based on the fracture morphology features, wherein the fracture failure mode includes any one of weld pull-out failure, interface failure, or mixed fracture mode; in the case of weld pull-out failure, measuring the width of the weld after pull-out and determining whether the ratio of the weld width to the original weld width is not less than a first preset threshold; if so, determining that the evaluation result of the fracture failure mode is qualified; in the case of interface failure, calculating the area of ​​the unconnected region on the interface and determining whether the ratio of the area of ​​the unconnected region to the total area of ​​the weld is not greater than a second preset threshold; if so, determining that the evaluation result of the fracture failure mode is qualified; in the case of mixed fracture mode, determining the qualification of the pull-out portion and the interface portion respectively, and determining that the evaluation result of the fracture failure mode is qualified if both the pull-out portion and the interface portion are qualified.

[0074] In this embodiment, the fracture morphology image after the peel test is first acquired from the original weld inspection data. Image processing algorithms are then used to identify the morphological details of the fracture surface, thereby determining the current fracture failure mode. The failure modes are classified into three types: weld pull-out failure, interface failure, or mixed fracture mode. Weld pull-out failure is characterized by fracture occurring within the base material rather than at the weld interface; interface failure is characterized by fracture occurring along the weld interface, indicating poor bonding; and the mixed fracture mode includes both pull-out failure and interface failure regions.

[0075] When the failure mode is determined to be weld pull-out failure, it indicates that the bonding strength of the weld interface is higher than the strength of the base material, which is an ideal high-quality weld condition. At this time, the remaining weld width on the base material after pull-out fracture is automatically measured and compared with the original weld width before welding. Specifically, the ratio of the remaining weld width to the original weld width is calculated, and it is determined whether this ratio is not less than a first preset threshold. In this embodiment, the first preset threshold is preferably set to 86%, meaning that the remaining weld width after pull-out is at least 86% of the original weld width. If this condition is met, the evaluation result under this failure mode is considered qualified, proving that the joint has sufficient strength reserve; if the ratio is less than 86%, it is determined to be unqualified, indicating that there may be localized strength deficiency.

[0076] When the fracture failure mode is determined to be interface failure, it indicates that there is a bonding defect at the weld interface. In this case, image segmentation technology is used to calculate the area of ​​the unconnected region (i.e., the area that is not fused or welded) on the interface, and the ratio of this area to the total weld area is calculated to assess the severity of the defect. It is then determined whether this ratio is not greater than a second preset threshold. In this embodiment, the second preset threshold is preferably set to 5%, meaning that the total area of ​​the unconnected region on the interface must not exceed 5% of the total weld area. If this condition is met, the degree of interface failure is considered to be within the allowable range, and the evaluation result is considered qualified; if it exceeds the threshold, it is considered unqualified, indicating that the interface bonding quality is substandard.

[0077] When the fracture failure mode is determined to be a mixed fracture mode, it means that the fracture surface simultaneously contains a pull-out region and an interface region. To accurately evaluate such complex fractures, a zonal evaluation strategy can be adopted, independently determining the pass / fail status of the pull-out portion and the interface portion. Specifically, firstly, the aforementioned weld pull-out failure determination rules are applied to the pull-out portion to check whether its remaining width ratio meets the first preset threshold requirement; simultaneously, the aforementioned interface failure determination rules are applied to the interface portion to check whether its unconnected area ratio meets the second preset threshold requirement. When both the pull-out portion and the interface portion are determined to be passable, the final fracture failure mode evaluation result under this mixed fracture mode is determined to be passable; if any part fails to meet the corresponding threshold requirement, the entire fracture is determined to be failable.

[0078] The above process achieves more refined and objective quality assessment of welded joints by classifying and quantifying pull-out failure, interface failure, and mixed fracture modes based on fracture morphology characteristics and conducting multi-region joint verification, thereby significantly improving the accuracy of failure mode determination and the reliability of process certification results.

[0079] As some optional embodiments of this application, after obtaining the inspection and evaluation results, the following steps can also be performed: constructing a two-dimensional data structure and determining the two-dimensional data structure as an initial matrix, wherein the initial matrix includes multiple predefined rows and multiple columns, wherein the columns correspond to the visual quality dimension, the cross-sectional quality dimension, and the fracture pass rate dimension, respectively; for each original weld inspection data in the original weld inspection data set, performing the following filling operations: extracting the process parameter combination corresponding to the original weld inspection data, wherein the process parameter combination includes: laser power, welding speed, spot shape, and shielding gas flow rate; generating a process parameter identifier based on the process parameter combination, wherein the process parameter identifier is used to identify the process parameter combination; searching for or creating the corresponding target row in the initial matrix according to the process parameter identifier, and determining the correspondence between the target row and the current original weld inspection data; filling the visual quality index, cross-sectional quality index, and fracture pass rate corresponding to the original weld inspection data into the cells of the corresponding visual quality dimension, cross-sectional quality dimension, and fracture pass rate dimension in the target row, respectively, to generate a comprehensive weld quality evaluation matrix.

[0080] In this embodiment, to systematically manage multiple sets of welding test data and establish a mapping relationship between process parameters and welding quality, after obtaining the visual quality index, cross-sectional quality index, and fracture pass rate of each original weld inspection data, a step of constructing a comprehensive weld quality evaluation matrix is ​​further executed. Specifically, a two-dimensional data structure is first constructed and determined as the initial matrix. This initial matrix has multiple predefined rows and columns. The column dimension is divided into three quality assessment dimensions: visual quality dimension, cross-sectional quality dimension, and fracture pass rate dimension; the row dimension is used to store the test results corresponding to different combinations of process parameters. This structured data storage method can aggregate discrete inspection results into an analyzable overall dataset, providing basic data support for subsequent optimal process window identification.

[0081] During the data filling phase, a standardized processing procedure is performed for each raw weld inspection data point in the original weld inspection dataset. First, the corresponding combination of process parameters is extracted from the raw data. This combination specifically includes key variables such as laser power, welding speed, spot morphology (e.g., single or dual spot and their power ratio), and shielding gas flow rate. Based on these extracted process parameter combinations, a unique process parameter identifier is generated. This identifier serves as a unique key value for accurately indexing specific process conditions in the database. For example, if a set of parameters is "laser power 1320W, welding speed 1.2m / min, single spot mode, argon flow rate 25L / min," it can be encoded as a specific string or hash value as the process parameter identifier, ensuring the uniqueness and traceability of different parameter combinations.

[0082] Then, the generated process parameter identifier is used to search in the initial matrix. If a row corresponding to the process parameter identifier already exists in the initial matrix, then that row is determined to be the current target row, and a correspondence between that row and the current original weld inspection data is established; if the process parameter identifier does not yet exist in the initial matrix, a new target row is automatically created, and the process parameter identifier is bound to the new row, while the current original weld inspection data is filled into that row.

[0083] Fill the visual quality index corresponding to the original weld inspection data into the cell corresponding to "Visual Quality Dimension" in the target row, fill the cross-section quality index into the cell corresponding to "Cross-section Quality Dimension", and fill the fracture pass rate into the cell corresponding to "Fracture Pass Rate Dimension".

[0084] Through the above-described filling operation, all experimental data are structurally integrated into the comprehensive weld quality evaluation matrix. For example, each row in the matrix represents a specific combination of process parameters, and each column represents the specific quantitative indicators of the weld in terms of appearance, internal structure, and mechanical properties under that set of parameters, thus forming a complete quality evaluation data array. This facilitates the subsequent rapid selection of the optimal process window that meets the high-end welding quality requirements of automobiles through multi-objective optimization algorithms.

[0085] As some alternative embodiments of this application, determining the welding process parameter combination that meets the preset judgment rules in the inspection and evaluation results in step S108 can be achieved through the following steps: A parameter space is generated based on laser power, welding speed, spot shape, shielding gas flow rate, and dual-spot parameters, wherein the dual-spot parameters include the dual-spot power ratio and spot spacing; a first sub-optimization process and a second sub-optimization process are executed in parallel within the parameter space, wherein the first sub-optimization process is for the single-spot mode, using laser power, welding speed, and shielding gas flow rate as decision variables, and employing a multi-objective evolutionary algorithm to maximize the visual quality index, cross-sectional quality index, and fracture pass rate as optimization objectives, iteratively searching in the single-spot subspace corresponding to the parameter space to obtain the single-spot Pareto optimal solution set; the second sub-optimization process is for the dual-spot mode, using laser power, welding speed, and shielding gas flow rate as decision variables, and employing a multi-objective evolutionary algorithm to maximize the visual quality index, cross-sectional quality index, and fracture pass rate as optimization objectives, and iteratively searching in the single-spot subspace corresponding to the parameter space to obtain the single-spot Pareto optimal solution set; Using protective gas flow rate, dual-spot power ratio, and spot spacing as decision variables, a multi-objective evolutionary algorithm is employed to maximize the visual quality index, cross-sectional quality index, and fracture pass rate as optimization objectives. Iterative search is performed in the dual-spot subspace corresponding to the parameter space to obtain the dual-spot Pareto optimal solution set. The single-spot Pareto optimal solution set and the dual-spot Pareto optimal solution set are merged into a candidate solution set. Non-dominated sorting is performed on the candidate solution set to eliminate dominated solutions, resulting in the global Pareto front. Based on preset process preference constraints, the global Pareto front is used to filter and obtain welding process parameter combinations. These process preference constraints include: at the same welding speed, dual-spot mode solutions are preferentially retained; and the corresponding single-spot mode solution is retained only if at least one of the visual quality index, cross-sectional quality index, or fracture pass rate of the single-spot mode solution is superior to the corresponding dual-spot mode solution.

[0086] In this embodiment, a multi-dimensional parameter space is first constructed based on laser power, welding speed, spot morphology, shielding gas flow rate, and dual-spot-specific parameters (including the dual-spot power ratio and spot spacing). This parameter space comprehensively covers all possible process conditions under both single-spot and dual-spot welding modes, providing a complete search range for subsequent parallel optimization. For example, in dual-spot mode, the dual-spot power ratio can be set to any value between 0.6:1 and 1.4:1, and the spot spacing can be set to any value between 0 mm and 5 mm, thus ensuring the continuity and completeness of the search space.

[0087] Then, the first and second sub-optimization processes are executed in parallel within the constructed parameter space, performing independent iterative searches for single-spot and dual-spot modes respectively to efficiently explore the optimal process boundaries for both welding modes. The first sub-optimization process, for the single-spot mode, uses laser power, welding speed, and shielding gas flow rate as decision variables and employs a multi-objective evolutionary algorithm (such as a non-dominated sorting genetic algorithm or a decomposition-based multi-objective evolutionary algorithm). This process aims to maximize the visual quality index, cross-sectional quality index, and fracture pass rate, and iteratively searches within the single-spot subspace corresponding to the parameter space. After multiple generations of evolutionary iterations, a set of non-dominated solutions is selected, namely the single-spot Pareto optimal solution set. This set of solutions represents the optimal trade-off between visual quality, cross-sectional quality, and fracture pass rate under the single-spot mode.

[0088] Specifically, a non-dominated sorting genetic algorithm or a decomposition-based multi-objective evolutionary algorithm can be used. In the algorithm initialization phase, an initial population is randomly generated, with each individual representing a specific combination of process parameters (i.e., one attempt at laser power, welding speed, and shielding gas flow). To evaluate the quality of each individual, a comprehensive weld quality evaluation model is invoked. Each set of parameters is input into the model, and historical test data is used to predict or retrieve the corresponding visual quality index, cross-sectional quality index, and fracture pass rate. The algorithm executes an iterative evolutionary process with the optimization objectives of maximizing the visual quality index, maximizing the cross-sectional quality index, and maximizing the fracture pass rate. In each iteration, the algorithm generates a new generation of population through selection, crossover, and mutation operations, and uses a non-dominated sorting mechanism to stratify the individuals in the population, identifying the Pareto optimal solution (i.e., the solution that cannot further improve any index without reducing other indices). As the number of iterations increases, the population gradually converges, eventually selecting a set of non-dominated solutions, constituting the single-light Pareto optimal solution set. This set of solutions is used to provide a series of alternative solutions that achieve the best balance among different quality dimensions. For example, some solutions may focus on extremely high cross-sectional penetration depth, while others may focus on defect-free surface appearance, thus providing a rich data foundation for subsequent comprehensive decision-making.

[0089] The second sub-optimization process targets the dual-spot mode, expanding the decision variables to include laser power, welding speed, shielding gas flow rate, dual-spot power ratio, and spot spacing. A multi-objective evolutionary algorithm is also employed, using the same three quality indices (maximizing visual quality index, cross-sectional quality index, and fracture pass rate) as optimization objectives, and iteratively searching within the dual-spot subspace corresponding to the parameter space. By introducing the power ratio and spacing variables unique to dual-spot modes, this process can uncover the potential advantages of dual-spot configuration in improving molten pool stability and reducing porosity and cracks, ultimately obtaining the Pareto optimal solution set for dual-spot modes. This parallel processing mechanism allows for the simultaneous evaluation of the performance potential of both welding modes, ensuring no potential high-quality parameter combinations are overlooked and significantly improving optimization efficiency.

[0090] Specifically, a multi-objective evolutionary algorithm is invoked to iteratively optimize the expanded parameter space. During algorithm initialization, an initial population containing five decision variables is randomly generated, with each individual representing a specific combination of dual-spot process parameters. To evaluate the welding quality of each individual, the comprehensive weld quality evaluation model is invoked again, inputting each set of parameters to obtain the corresponding visual quality index, cross-sectional quality index, and fracture pass rate.

[0091] With the optimization objectives of maximizing visual quality index, cross-sectional quality index, and fracture pass rate, the algorithm iteratively searches within the dual-spot subspace. During the evolutionary process, the algorithm generates new combinations of process parameters through crossover and mutation operations, focusing on the impact of the dual-spot power ratio and spot spacing on molten pool stability, porosity formation tendency, and crack sensitivity. For example, the algorithm can explore specific power ratios to optimize keyhole closure behavior or adjust spot spacing to balance the heat input between preheating and the main molten pool, thereby reducing defects such as porosity and cracks at the microscopic level. As iterations proceed, the population gradually converges, eventually selecting a set of non-dominant solutions, constituting the dual-spot Pareto optimal solution set. The dual-spot Pareto optimal solution set reflects the optimal trade-off between visual, cross-sectional, and mechanical properties achievable under the dual-spot mode through collaborative optimization of specific variables such as power ratio and spacing.

[0092] After obtaining the Pareto optimal solution sets for both single-spot and dual-spot solutions, these two sets are merged into a candidate solution set, and a non-dominated sorting operation is performed on this candidate solution set. Specifically, the dominance relationship between each solution in the candidate solution set and other solutions is calculated, and inferior solutions dominated by other solutions are eliminated, thus obtaining the global Pareto front that reflects the global optimal trade-offs. This global Pareto front includes all combinations of process parameters that perform well in terms of overall quality indicators, providing basic data for the final decision.

[0093] To further select the optimal welding process parameter combination that meets actual production needs, a secondary screening is conducted at the global Pareto front based on preset process preference constraints. The core logic of this process preference constraint is to prioritize the retention of solutions using the dual-spot mode, as dual-spot welding typically provides more stable molten pool control and better overall performance, and is more conducive to achieving consistency in automated production. In specific implementation, for each single-spot mode solution in the global Pareto front, it is compared with the dual-spot mode solution at the corresponding welding speed. A single-spot mode solution is retained only if at least one of the visual quality index, cross-sectional quality index, or fracture pass rate is significantly better than the corresponding index of the corresponding dual-spot mode solution. If the dual-spot mode solution is better than or equal to the single-spot mode solution in all indices, the corresponding single-spot solution is discarded. Through this strategy, the final determined welding process parameter combination ensures high-quality standards while reflecting the priority application of advanced dual-spot welding technology, thereby achieving efficient certification and optimization of the welding process. For example, if a certain set of dual-spot parameters (1000W+1000W, 1.2m / min, power ratio 1:1, spacing 2mm) is superior to a certain set of single-spot parameters (1.32kW, 1.2m / min) in all three indicators, then the dual-spot parameter combination should be selected first to ensure the stability of the production line process.

[0094] In some optional embodiments, adjusting the laser power and welding speed based on welding process data in step S108 can be achieved through the following steps: Real-time detection of the molten pool morphology characteristics during the welding process using a high-speed camera or coaxial photoelectric sensor, wherein the molten pool morphology characteristics include the molten pool length, molten pool width, and oscillation frequency at the tail of the molten pool; comparison of the real-time acquired molten pool width with a preset target molten pool width, and calculation of the deviation value based on the comparison result; generation of feedback adjustment instructions based on the deviation value using a proportional-integral-derivative control strategy or a fuzzy logic control strategy, wherein the feedback adjustment instructions are used to adjust the laser power and / or welding speed; and control the fluctuation of the real-time molten pool width to not exceed ±5% of the target value through the feedback adjustment instructions.

[0095] In this embodiment, the morphological characteristics of the molten pool during the welding process are first monitored in real time using a high-speed camera or a coaxial photoelectric sensor. Specifically, the molten pool morphological characteristics include the length, width, and oscillation frequency at the tail of the molten pool. The width of the molten pool is a key indicator reflecting the heat input and the flow state of the molten pool, while the oscillation frequency at the tail of the molten pool is closely related to the solidification behavior of the molten pool and the stability of the keyhole.

[0096] After acquiring real-time molten pool morphology data, it is compared with the preset target molten pool width to calculate the current deviation value. Subsequently, a feedback adjustment command is generated using either a PID control strategy or a fuzzy logic control strategy. If a PID control strategy is used, the required laser power increment or welding speed adjustment is calculated based on the deviation value and its rate of change to quickly eliminate the deviation and suppress overshoot. If a fuzzy logic control strategy is used, the deviation of the molten pool width and its rate of change are used as fuzzy inputs. A nonlinear control quantity is output through a fuzzy inference rule base (e.g., significantly reducing laser power or increasing welding speed when the deviation is positive and large), thereby more flexibly responding to nonlinear and time-varying interferences during aluminum alloy welding.

[0097] For example, the core control objective is to keep the fluctuation of the real-time weld pool width within ±5% of the target value. To achieve this, the output power of the laser or the walking speed of the welding robot is adjusted in real time based on the calculated adjustment amount. For instance, when the weld pool width is detected to have increased beyond a threshold, the laser power is automatically reduced or the welding speed is increased; conversely, when the weld pool width is detected to have decreased, the laser power is appropriately increased or the welding speed is reduced. Through this high-frequency real-time feedback and adjustment, weld pool fluctuations caused by factors such as changes in plate gaps, surface oxidation, or heat accumulation can be effectively suppressed, ensuring the stability of geometric dimensions such as weld width and penetration depth. This ensures the continuous formation of high-quality welds during dynamic welding, meeting the stringent requirements for welding consistency in automotive structural components.

[0098] The following detailed description of this application is provided with specific examples.

[0099] Example 1: Optimization of dual-spot laser welding process. This example aims to verify the superior performance of dual-spot laser welding process in the connection of aluminum alloy body structural components.

[0100] 1. Experimental equipment and parameter settings.

[0101] A Han's Photon laser was used as the heat source, with the laser type set to continuous wave (CW) and the laser beam angle with the aluminum alloy sheet set to 90°. High-purity argon was used as the shielding gas, with a flow rate set to 25 L / min to ensure the molten pool was protected from oxidation. Welding speeds were set at two levels: 1.2 m / min and 2.4 m / min. In dual-spot mode, asymmetric or symmetric laser power combinations were used, with specific test combinations including 700W+900W, 1000W+1000W, and 1200W+1200W, to investigate the effect of different energy distributions on weld formation.

[0102] 2. Experimental subjects. For example... Figure 2As shown, this example adopts the AL-AA.72 series aluminum alloy sheet composed of an upper plate and a lower plate as the welding base material, which is a commonly used lightweight structural material for automotive bodies.

[0103] 3. Process result analysis. When the dual-spot mode is adopted, the laser power combination is 700W+900W, and the welding speed is 1.2m / min, the experimental results are as follows:

[0104] Appearance inspection: The weld surface is smooth, no macroscopic defects such as incomplete penetration, craters, pores, cracks, and undercut are observed, the back penetration is uniform, and no weld leakage occurs. As shown Figure 3 , the weld surface is well-formed, with uniform color and no obvious spatter. After visual inspection, it is judged as qualified.

[0105] Cross-section inspection: Metallographic analysis is performed on the weld section, as shown Figure 4 , the cross-section inspection shows that the penetration depth is uniform, the weld width is moderate, and no unfused zone is detected. The total area of the weld is 464862μm², of which the pore area is 2451μm², and the pore proportion is only 0.53%, which is far lower than the industry standard limit, with an extremely high cross-section quality index.

[0106] Mechanical property evaluation: A peel test is carried out, and the result shows that the weld undergoes base material tearing, that is, the "pull-out failure" mode. As shown Figure 5 , the material at the peel fracture is completely broken, the weld width before and after peeling is both 47mm, there is no interruption on the fracture surface, no through-thickness pores in the sheet, and no unconnected interface zone is found. This indicates that the joint strength is higher than that of the base metal, which meets the strict requirements on fracture morphology, unconnected zone area (required ≤5%) and pores in the high-end welding quality certification standards of the automotive industry.

[0107] Comprehensive evaluation: Based on the previously established comprehensive weld quality evaluation matrix, this parameter combination obtains full scores in the three dimensions of visual quality index, cross-section quality index and fracture qualification rate, and the system automatically identifies it as the optimal process window under the dual-spot mode.

[0108] Example 2: Optimization of single-spot laser welding process and verification of closed-loop control. This example aims to compare the process performance under the single-spot mode and verify the role of the closed-loop control strategy in stabilizing welding quality.

[0109] 1. Experimental parameter setting. The same laser model as in Example 1 is used, and the welding speed is fixed at 1.2m / min. Under the single-spot mode, the laser power is set to 1.0kW, 1.32kW, 1.4kW and 1.5kW respectively to find the optimal energy input point.

[0110] 2. Process result analysis. When the single-spot laser power is set to 1.32kW, the following operations are performed:

[0111] Visual and cross-sectional inspection: The weld surface quality is qualified, with no macroscopic defects (such as...). Figure 6 As shown), there were no weld leaks on the back. Cross-sectional inspection showed that the weld penetration and width met the requirements, with no incomplete fusion or severe porosity defects (such as...). Figure 7 (As shown).

[0112] Mechanical property assessment: The peel test also showed a pull-out failure mode, such as... Figure 8 As shown, the fracture surface is free of defects, the weld width is 47mm, the joint strength meets the requirements, and the overall evaluation is qualified.

[0113] Optimal Window Comparison: Iterative analysis of the two sets of data using a multi-objective optimization algorithm yielded optimal parameter combinations for both dual-spot mode (700W + 900W, 1.2m / min) and single-spot mode (1.32kW, 1.2m / min). The comparison shows that the dual-spot mode achieves equal or even better quality stability at lower total power and exhibits higher tolerance for process fluctuations.

[0114] 3. Closed-Loop Control Application. In actual production scenarios, the optimal process window identified above (taking dual-spot 700W+900W, 1.2m / min as an example) is input into the closed-loop control system. The system monitors the weld pool width in real time through high-speed sensors and dynamically adjusts the laser power using a PID control strategy. When fluctuations in the weld pool width are detected due to minor changes in the plate gap or heat accumulation, the system automatically adjusts the power to strictly control the weld pool width fluctuation within ±5% of the target value. Experiments show that this closed-loop control strategy significantly improves the consistency of the welding process, ensuring that the final weld quality consistently meets the stringent standards of high-end automakers.

[0115] Figure 9 This is a structural diagram of an optimized apparatus for an aluminum alloy laser welding process according to an embodiment of this application, as shown below. Figure 9 As shown, the device includes:

[0116] The first acquisition module 92 is used to acquire an initial combination set of laser power and welding speed for welding aluminum alloy plates, compare welding methods with different spot shapes within the initial combination set, obtain comparison results, and determine an optimal combination set in the initial combination set that meets the preset requirements for comparison results.

[0117] The second acquisition module 94 is used to acquire the original weld inspection data set, wherein the original weld inspection data set includes: the first original weld inspection data of the single spot laser welding equipment under each preferred combination in the preferred combination set, and the second original weld inspection data of the dual spot laser welding equipment under each preferred combination in the preferred combination set.

[0118] Evaluation module 96 is used to perform visual inspection, weld cross-section inspection and peel test fracture mode evaluation for each original weld inspection data in the original weld inspection data set, and obtain inspection and evaluation results.

[0119] The adjustment module 98 is used to determine the combination of welding process parameters that meets the preset judgment rules in the inspection and evaluation results, obtain welding process data when welding based on the combination of welding process parameters, and adjust the laser power and welding speed based on the welding process data.

[0120] Optionally, the laser power in the initial laser array ranges from 0.5 kW to 3.0 kW; the welding speed in the initial laser array ranges from 0.8 m / min to 2.5 m / min; and the ratio of laser power to welding speed in the initial laser array ranges from 0.3 kW. min / m to 1.2kW min / m.

[0121] Optionally, the dual-spot laser welding equipment adopts an annular spot or a beam splitting dual-focus structure; the welding power ratio of the dual-spot laser welding equipment is 1:1 or asymmetrical, wherein the power ratio range of the asymmetrical configuration includes 0.6:1 to 1.4:1.

[0122] Optionally, the optimization device for aluminum alloy laser welding process further includes: an identification module for performing the following steps: identifying the weld surface image in the original weld inspection data to detect at least one of the following defects: incomplete penetration, arc crater, hole, crack, undercut, spatter, weld discontinuity, weld offset, uneven weld width, abnormal weld reinforcement, and surface oxidation defects; determining a visual quality index based on the detected defect type and quantity, wherein the visual quality index is used to characterize the appearance integrity and defect severity of the weld surface; measuring the metallographic image of the weld cross section in the original weld inspection data to obtain at least one weld quality index among the following: weld penetration, weld width, area of ​​unfused region, porosity distribution density, width of heat-affected zone, and weld centerline offset; and determining a cross-sectional quality index based on the degree of deviation between the weld quality index and a preset standard value, wherein the cross-sectional quality index is used to characterize the geometric compliance and metallurgical bonding quality of the internal structure of the weld.

[0123] Optionally, the optimization device for aluminum alloy laser welding process further includes: a fracture mode evaluation module, used to perform the following steps: acquiring fracture morphology features from the original weld inspection data; determining the fracture failure mode based on the fracture morphology features, wherein the fracture failure mode includes any one of weld pull-out failure, interface failure, or mixed fracture mode; in the case of weld pull-out failure, measuring the width of the weld after pull-out and determining whether the ratio of the weld width to the original weld width is not less than a first preset threshold; if so, determining that the evaluation result of the fracture failure mode is qualified; in the case of interface failure, calculating the area of ​​the unconnected region on the interface and determining whether the ratio of the area of ​​the unconnected region to the total area of ​​the weld is not greater than a second preset threshold; if so, determining that the evaluation result of the fracture failure mode is qualified; in the case of mixed fracture mode, determining the qualification of the pull-out portion and the interface portion respectively, and determining that the evaluation result of the fracture failure mode is qualified if both the pull-out portion and the interface portion are qualified.

[0124] Optionally, the optimization device for aluminum alloy laser welding process further includes: an evaluation matrix construction module, used to perform the following steps after obtaining inspection and evaluation results: constructing a two-dimensional data structure and determining the two-dimensional data structure as an initial matrix, wherein the initial matrix includes multiple predefined rows and multiple columns, wherein the columns correspond to the visual quality dimension, cross-sectional quality dimension, and fracture pass rate dimension, respectively; for each original weld inspection data in the original weld inspection data set, performing the following filling operations: extracting the process parameter combination corresponding to the original weld inspection data, wherein the process parameter combination includes: laser power, welding speed, spot shape, and shielding gas flow rate; generating a process parameter identifier based on the process parameter combination, wherein the process parameter identifier is used to identify the process parameter combination; searching for or creating the corresponding target row in the initial matrix according to the process parameter identifier, and determining the correspondence between the target row and the current original weld inspection data; filling the visual quality index, cross-sectional quality index, and fracture pass rate corresponding to the original weld inspection data into the cells of the corresponding visual quality dimension, cross-sectional quality dimension, and fracture pass rate dimension in the target row, respectively, to generate a comprehensive weld quality evaluation matrix.

[0125] Optionally, the optimization device for aluminum alloy laser welding process further includes: a determination module, used to perform the following steps: generating a parameter space based on laser power, welding speed, spot morphology, shielding gas flow rate, and dual-spot parameters, wherein the dual-spot parameters include the dual-spot power ratio and spot spacing; executing a first sub-optimization process and a second sub-optimization process in parallel within the parameter space, wherein the first sub-optimization process is for the single-spot mode, using laser power, welding speed, and shielding gas flow rate as decision variables, and employing a multi-objective evolutionary algorithm to maximize the visual quality index, cross-sectional quality index, and fracture pass rate as optimization objectives, iteratively searching in the single-spot subspace corresponding to the parameter space to obtain the single-spot Pareto optimal solution set; the second sub-optimization process is for the dual-spot mode, using laser power, welding speed, shielding gas flow rate, and dual-spot power ratio as decision variables, and then... The beam spacing is the decision variable. A multi-objective evolutionary algorithm is used to maximize the visual quality index, cross-sectional quality index, and fracture pass rate as optimization objectives. Iterative search is performed in the dual-beam subspace corresponding to the parameter space to obtain the dual-beam Pareto optimal solution set. The single-beam Pareto optimal solution set and the dual-beam Pareto optimal solution set are merged into a candidate solution set. Non-dominated sorting is performed on the candidate solution set to eliminate dominated solutions, resulting in the global Pareto front. Based on preset process preference constraints, the welding process parameter combination is obtained by screening in the global Pareto front. The process preference constraints include: under the same welding speed, dual-beam mode solutions are preferentially retained, and the corresponding single-beam mode solution is retained only if at least one of the visual quality index, cross-sectional quality index, or fracture pass rate of the single-beam mode solution is better than the corresponding dual-beam mode solution.

[0126] It should be noted that the above Figure 9 The modules in can be program modules (e.g., a set of program instructions that implements a specific function) or hardware modules. For the latter, they can be represented in the following forms, but are not limited to these: each of the above modules is represented by a processor, or the functions of each of the above modules are implemented by a processor.

[0127] It should be noted that, Figure 9 Preferred embodiments of the shown examples can be found in [reference needed]. Figure 1 The relevant descriptions of the embodiments shown will not be repeated here.

[0128] Figure 10 A hardware block diagram of a computer terminal for implementing an optimized method for aluminum alloy laser welding processes is shown.

[0129] like Figure 10 As shown, the computer terminal 100 may include a processor 1002, a memory 1004 for storing data, and a transmission module 1006 for communication functions. The processor 1002 may include one or more processors. For ease of explanation, Figure 10 The diagram illustrates multiple processors, including processor 1 (1002a), processor 2 (1002b), ..., processor n (1002n). Processor 1002 may be a processing device including, but not limited to, a microprocessor (MCU) or a field programmable gate array (FPGA).

[0130] In addition, a computer terminal may also include: a display, an input / output interface (I / O interface), a Universal Serial Bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 10 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, the computer terminal 100 may also include... Figure 10 The more or fewer components shown, or having the same Figure 10 The different configurations shown.

[0131] It should be noted that the aforementioned one or more processors and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be implemented wholly or partially as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be wholly or partially integrated into any other element in the computer terminal 100. As involved in the embodiments of this application, the data processing circuit serves as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0132] The memory 1004 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the optimization method of aluminum alloy laser welding process in this embodiment of the application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 1004, thereby realizing the above-mentioned optimization method of aluminum alloy laser welding process. The memory 1004 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1004 may further include memory remotely located relative to the processor, and these remote memories can be connected to the computer terminal 100 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0133] The transmission module 10010 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 100. In one example, the transmission module 10010 includes a network interface controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission module 10010 may be a radio frequency (RF) module, used for data interaction with external networks or devices via wired and / or wireless network connections.

[0134] The display can be, for example, a touchscreen liquid crystal display (LCD), which allows the user to interact with the user interface of the computer terminal 100. In addition, the computer terminal 100 can also connect to a cursor control device and a keyboard via an input / output interface. The cursor control device (e.g., a mouse, trackball, or touchpad) is mainly used to transmit directional information and command selection to the terminal and control the movement of the cursor on the display; the keyboard is mainly used to receive letters, numbers, and other control commands input by the user, thereby enabling interaction between the user and the computer terminal 100.

[0135] It should be noted here that, in some optional embodiments, the above... Figure 10 The computer terminal shown may include hardware elements (including circuitry), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. It should be noted that... Figure 10 This is only one instance of a specific particular instance, and is intended to illustrate the types of components that may exist in the aforementioned computer terminal.

[0136] It should be noted that, Figure 10 The computer terminal shown is used to execute Figure 1 The optimized method for aluminum alloy laser welding process shown above also applies to this electronic device, and will not be repeated here.

[0137] This application also provides a non-volatile storage medium, which includes a stored program, wherein the program, when running, controls the device where the storage medium is located to execute the above-mentioned optimized method for aluminum alloy laser welding process.

[0138] The non-volatile storage medium performs the following functions: It acquires an initial set of laser power and welding speed combinations for welding aluminum alloy sheets; compares welding methods with different spot shapes within the initial set of combinations, obtains comparison results, and determines an optimal set of combinations within the initial set of combinations whose comparison results meet preset requirements; it acquires a set of original weld inspection data, including: first original weld inspection data for a single-spot laser welding device under each optimal combination in the optimal set of combinations, and second original weld inspection data for a dual-spot laser welding device under each optimal combination in the optimal set of combinations; for each original weld inspection data in the original weld inspection data set, it performs visual inspection, weld cross-section inspection, and peel test fracture mode evaluation, obtaining inspection and evaluation results; from the inspection and evaluation results, it determines the welding process parameter combinations that meet preset judgment rules, acquires welding process data based on the welding process parameter combinations, and adjusts the laser power and welding speed based on the welding process data.

[0139] This application also provides an electronic device, including: a memory and a processor, wherein the processor is used to run a program stored in the memory, wherein the program executes the above-described optimization method for aluminum alloy laser welding process.

[0140] The processor is used to run a program that performs the following functions: acquiring an initial set of laser power and welding speed combinations for welding aluminum alloy sheets; comparing different spot morphology welding methods within the initial set of combinations to obtain comparison results; and determining an optimal set of combinations within the initial set of combinations whose comparison results meet preset requirements. It also acquires a set of raw weld inspection data, which includes: first raw weld inspection data for a single-spot laser welding device under each optimal combination in the optimal set of combinations, and second raw weld inspection data for a dual-spot laser welding device under each optimal combination in the optimal set of combinations. For each raw weld inspection data in the raw weld inspection data set, it performs visual inspection, weld cross-section inspection, and peel test fracture mode evaluation to obtain inspection and evaluation results. Based on the inspection and evaluation results, it determines welding process parameter combinations that meet preset judgment rules, acquires welding process data based on the welding process parameter combinations, and adjusts the laser power and welding speed based on the welding process data.

[0141] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0142] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0143] In the above embodiments of this application, the information collected is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data all comply with relevant laws, regulations and standards, take necessary protective measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse.

[0144] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0145] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0146] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0147] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to related technologies, or all or part of the 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 to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0148] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. An optimized method for aluminum alloy laser welding process, characterized in that, include: An initial set of laser power and welding speed combinations for welding aluminum alloy sheets is obtained. Within the initial set of combinations, welding methods with different spot shapes are compared to obtain comparison results. In the initial set of combinations, an optimal set of combinations that meet the preset requirements is determined. Obtain a set of raw weld inspection data, wherein the set of raw weld inspection data includes: first raw weld inspection data of single spot laser welding equipment under each preferred combination in the set of preferred combinations, and second raw weld inspection data of dual spot laser welding equipment under each preferred combination in the set of preferred combinations; For each original weld inspection data point in the aforementioned original weld inspection data set, visual inspection, weld cross-section inspection, and peel test fracture mode evaluation are performed to obtain inspection and evaluation results; among which, Visual inspection includes: identifying weld surface images in the original weld inspection data; and determining the visual quality index based on the type and number of defects detected. The weld cross-section inspection includes: measuring the metallographic image of the weld cross-section in the original weld inspection data to obtain the weld quality index; and determining the cross-section quality index based on the degree of deviation between the weld quality index and the preset standard value. The fracture mode evaluation of the peel test includes: acquiring the fracture morphology features in the original weld inspection data, and determining the fracture failure mode based on the fracture morphology features, wherein the fracture failure mode includes any one of weld pull-out failure, interface failure, or mixed fracture mode. When the fracture failure mode is weld pull-out failure, the width of the weld after pull-out is measured, and it is determined whether the ratio of the weld width to the original weld width is not less than a first preset threshold. If so, the evaluation result of the fracture failure mode is determined to be qualified. When the fracture failure mode is interface failure, the area of ​​the unconnected region on the interface is calculated, and it is determined whether the ratio of the unconnected region area to the total weld area is not greater than a second preset threshold. If so, the evaluation result of the fracture failure mode is determined to be qualified. When the fracture failure mode is the mixed fracture mode, the qualification of the pull-out portion and the interface portion are determined separately, and if both the pull-out portion and the interface portion are qualified, the evaluation result of the fracture failure mode is determined to be qualified. In the inspection and evaluation results, a welding process parameter combination that meets the preset judgment rules is determined, welding process data is obtained when welding is performed based on the welding process parameter combination, and the laser power and the welding speed are adjusted based on the welding process data. After obtaining the inspection and evaluation results, a two-dimensional data structure is constructed, and this two-dimensional data structure is determined as an initial matrix. The initial matrix includes multiple predefined rows and columns, where the columns correspond to the visual quality dimension, cross-sectional quality dimension, and fracture surface pass rate dimension, respectively. For each original weld inspection data in the original weld inspection data set, the following fill operation is performed: Extract the process parameter combination corresponding to the original weld inspection data, wherein the process parameter combination includes: laser power, welding speed, spot shape, and shielding gas flow rate; generate a process parameter identifier based on the process parameter combination, wherein the process parameter identifier is used to identify the process parameter combination; find or create a corresponding target row in the initial matrix according to the process parameter identifier, and determine the correspondence between the target row and the current original weld inspection data; fill the visual quality index, cross-sectional quality index, and fracture pass rate corresponding to the original weld inspection data into the cells of the corresponding visual quality dimension, cross-sectional quality dimension, and fracture pass rate dimension in the target row, respectively, to generate a comprehensive weld quality evaluation matrix.

2. The method according to claim 1, characterized in that, Obtain an initial set of laser power and welding speed combinations for welding aluminum alloy sheets, including: The laser power in the initial combination set ranges from 0.5kW to 3.0kW; The welding speed range in the initial combination set includes 0.8 m / min to 2.5 m / min; The ratio of the laser power to the welding speed in the initial combination set ranges from 0.3 kW·min / m to 1.2 kW·min / m.

3. The method according to claim 1 or 2, characterized in that, The dual-spot laser welding equipment adopts an annular spot or a beam splitting dual-focus structure; the welding power ratio of the dual-spot laser welding equipment is 1:1 or asymmetrical, wherein the power ratio range of the asymmetrical configuration includes 0.6:1 to 1.4:

1.

4. The method according to claim 1, characterized in that, Identifying the weld surface image in the original weld inspection data includes: detecting whether there is at least one of the following defects: incomplete penetration, arc crater, hole, crack, undercut, spatter, weld discontinuity, weld offset, uneven weld width, abnormal weld reinforcement, and surface oxidation defects. The visual quality index is used to characterize the appearance integrity and defect severity of the weld surface. The weld quality indicators include at least one of the following: weld penetration, weld width, area of ​​unfused region, porosity distribution density, width of heat-affected zone, and weld centerline offset. The cross-sectional quality index is used to characterize the geometric compliance and metallurgical bonding quality of the internal structure of the weld.

5. The method according to claim 1, characterized in that, The welding process parameter combinations that meet the preset judgment rules are determined from the inspection and evaluation results, including: A parameter space is generated based on the laser power, the welding speed, the spot shape, the shielding gas flow rate, and the dual-spot parameters, wherein the dual-spot parameters include the dual-spot power ratio and the spot spacing. The first and second sub-optimization processes are executed in parallel within the parameter space. The first sub-optimization process, for the single-spot mode, uses the laser power, welding speed, and shielding gas flow rate as decision variables. A multi-objective evolutionary algorithm is employed to maximize the visual quality index, the cross-sectional quality index, and the fracture pass rate as optimization objectives. An iterative search is performed in the single-spot subspace corresponding to the parameter space to obtain the single-spot Pareto optimal solution set. The second sub-optimization process, for the dual-spot mode, uses the laser power, welding speed, shielding gas flow rate, dual-spot power ratio, and spot spacing as decision variables. A multi-objective evolutionary algorithm is employed to maximize the visual quality index, the cross-sectional quality index, and the fracture pass rate as optimization objectives. An iterative search is performed in the dual-spot subspace corresponding to the parameter space to obtain the dual-spot Pareto optimal solution set. The single-spot Pareto optimal solution set and the dual-spot Pareto optimal solution set are merged into a candidate solution set. The candidate solution set is then sorted by non-dominated order to eliminate dominated solutions, thus obtaining the global Pareto front. Based on preset process preference constraints, the welding process parameter combination is obtained by screening in the global Pareto front. The process preference constraints include: at the same welding speed, the dual-spot mode solution is preferentially retained, and the corresponding single-spot mode solution is retained only if at least one of the visual quality index, cross-sectional quality index or fracture pass rate of the single-spot mode solution is better than the corresponding dual-spot mode solution.

6. An optimization device for aluminum alloy laser welding process, characterized in that, An optimized method for performing the aluminum alloy laser welding process according to any one of claims 1 to 5, comprising: The first acquisition module is used to acquire an initial combination set of laser power and welding speed for welding aluminum alloy plates, compare welding methods with different spot shapes within the initial combination set, obtain comparison results, and determine an optimal combination set in the initial combination set in which the comparison results meet preset requirements. The second acquisition module is used to acquire the original weld inspection data set, wherein the original weld inspection data set includes: the first original weld inspection data of the single spot laser welding equipment under each preferred combination in the preferred combination set, and the second original weld inspection data of the dual spot laser welding equipment under each preferred combination in the preferred combination set; The evaluation module is used to perform visual inspection, weld cross-section inspection and peel test fracture mode evaluation on each original weld inspection data in the original weld inspection data set to obtain inspection and evaluation results. The adjustment module is used to determine the welding process parameter combination that meets the preset judgment rules in the inspection and evaluation results, obtain welding process data when welding based on the welding process parameter combination, and adjust the laser power and the welding speed based on the welding process data.

7. A non-volatile storage medium, characterized in that, The non-volatile storage medium includes a stored program, wherein, when the program is executed, the device containing the non-volatile storage medium is controlled to perform the optimization method of the aluminum alloy laser welding process according to any one of claims 1 to 5.

8. An electronic device, characterized in that, include: A memory and a processor, the processor being configured to run a program stored in the memory, wherein the program, when running, executes the optimization method for the aluminum alloy laser welding process according to any one of claims 1 to 5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the optimization method for the aluminum alloy laser welding process according to any one of claims 1 to 5.

Images