Method and system for quality control of laser cladding layer formation based on molten pool powder island

Abstract

The present application relates to the technical field of laser cladding, and discloses a laser cladding layer forming quality regulation method and system based on a molten pool powder island, which comprises the following steps: constructing a plurality of different process parameter value combinations based on central composite design according to the value range of each process parameter in the laser cladding process; obtaining the molten pool image in the laser cladding process under each process parameter value combination, extracting the molten pool area and the powder island area to obtain the powder island area proportion, and constructing a relationship model between the powder island area proportion and each process parameter value; determining the optimal value range of the powder island area proportion according to the relationship between the laser cladding layer forming quality and the powder island area proportion; and in the laser cladding process, controlling the value of each process parameter in real time according to the relationship model so that the real-time powder island area proportion is within the optimal value range. The present application can optimize the process parameters in real time, improve the efficiency and the laser cladding layer forming quality in the laser cladding process.

Description

Technical Field

[0001] This invention relates to the field of laser cladding technology, and in particular to a method and system for controlling the forming quality of laser cladding layers based on molten pool powder islands. Background Technology

[0002] Laser cladding is a manufacturing technology that uses a high-energy laser beam to melt metal powder or wire, forming a high-performance coating on the surface of a substrate. Laser cladding can repair and strengthen various critical components and is widely used in aerospace, new energy, automotive, and mold industries. With the development of high-power fiber lasers and intelligent control systems, the precision and efficiency of laser cladding have significantly improved, enabling the precise forming of complex geometries.

[0003] To improve the forming quality of laser cladding layers, existing technologies include optimizing and controlling the laser cladding process through process parameters. For example, a single-factor method is used to conduct single-pass experiments under different process parameters to study the effects of laser power, scanning speed, and powder feeding rate on the forming quality of the cladding layer. Based on the influence of laser power, scanning speed, and powder feeding rate on the surface roughness of the single-pass upper surface, the optimal combination of process parameters is determined (see the paper "Mei Youzhu, Zhang Jinchao, Fu Geyan, et al. Study on surface quality of laser internal powder feeding cladding [J]. Mechanical Manufacturing and Automation, 1671-5276.2021.02.001").

[0004] However, this approach involves checking the impact on the cladding layer quality after each process parameter optimization and forming process, which is inefficient and cannot optimize the cladding process. Furthermore, process parameter optimization often suffers from inadequate optimization, leading to defects in the cladding layer quality. For example, during implementation, defects such as high porosity, increased cracks, and poor surface morphology caused by incompatibility between energy input and material properties are common due to insufficient process parameter optimization. Summary of the Invention

[0005] Therefore, the technical problem to be solved by the present invention is to overcome the shortcomings of the prior art and provide a method and system for controlling the forming quality of laser cladding layer based on molten pool powder islands, which can optimize process parameters in real time during the cladding process, improve efficiency and the forming quality of cladding layer.

[0006] To address the aforementioned technical problems, this invention provides a method for controlling the forming quality of laser cladding layers based on molten pool powder islands, comprising:

[0007] Based on the range of values ​​for various process parameters during laser cladding, multiple combinations of different process parameter values ​​are constructed based on the central composite design.

[0008] Acquire images of the molten pool during the laser cladding process under each combination of process parameter values, and extract the molten pool region and powder island region from the molten pool image;

[0009] Based on the area of ​​the molten pool region and the area of ​​the powder island region, the area ratio of the powder island is obtained, and a relationship model between the area ratio of the powder island and the values ​​of various process parameters is constructed.

[0010] Based on the relationship between the forming quality of the laser cladding layer and the area ratio of the powder islands, the optimal range of the area ratio of the powder islands is determined.

[0011] During the laser cladding process, the values ​​of various process parameters are controlled in real time according to the relationship model to ensure that the real-time powder island area ratio is within the optimal range, thereby guaranteeing the forming quality of the laser cladding layer.

[0012] Furthermore, based on the value range of each process parameter during laser cladding, multiple different combinations of process parameter values ​​are constructed according to the central composite design, specifically as follows:

[0013] Obtain the value range of each process parameter during the laser cladding process of the target material, and determine the value of the process parameter at the center point based on the value range of each process parameter;

[0014] Based on the center point process parameter values, multiple values ​​of each process parameter are selected based on the center composite design, and multiple different combinations of process parameter values ​​are constructed based on the multiple values ​​of each process parameter.

[0015] Furthermore, based on the values ​​of the process parameters at the center point, multiple values ​​for each process parameter are selected based on the center composite design, and multiple different combinations of process parameter values ​​are constructed based on these multiple values, specifically:

[0016] The process parameters include laser power, scanning speed, and powder feeding rate, which are used as three experimental factors.

[0017] Using the center point process parameter value as the center point, different cubic point levels and axial point levels are set for each experimental factor to obtain multiple values ​​for each experimental factor.

[0018] Based on the central composite design, 2 were selected. k 2k cubic points, 2k axial points, and n center points are used to construct (2 k +2k+a) groups of different process parameter values, where k represents the number of experimental factors.

[0019] Furthermore, the horizontal axis point is ±α, where α=2. k / 4 .

[0020] Furthermore, the area ratio of the powder islands is:

[0021] ,

[0022] in, This represents the percentage of the area of ​​the powder islands. The area of ​​the powder island region. This represents the area of ​​the molten pool region.

[0023] Furthermore, the process parameters include laser power, scanning speed, and powder feeding rate. When constructing the relationship model between the powder island area ratio and the values ​​of each process parameter, the relationship model is constructed by combining the changing trend of the powder island area ratio with scanning speed, powder feeding rate, and laser power through a polynomial regression model.

[0024] Furthermore, the relational model is as follows:

[0025] λ = k1- k2×P – k3×V – k4×f + k5×P×V + k6×P×f – k7×V×f + k8×P 2 + k9×V 2 + k 10 ×f 2 ,

[0026] in, Where P is the area ratio of the powder islands, V is the laser power, f is the scanning speed, and k1, k2, k3, k4, k5, k6, k7, k8, k9, and k 10 This is for adjusting the coefficient.

[0027] Furthermore, k1, k2, k3, k4, k5, k6, k7, k8, k9 and k 10 The values ​​of k are: k1=185.40037, k2=0.237282, k3=2.0713, k4=15.0165, k5=0.000625, k6=0.002187, k7=0.03125, k8=0.000102, k9=0.385294, k 10 = 1.85566.

[0028] Furthermore, the optimal range for the area ratio of the powder islands is 27% to 28%.

[0029] This invention also provides a laser cladding layer forming quality control system based on molten pool powder islands, comprising:

[0030] The process parameter value combination construction module is used to construct multiple different process parameter value combinations based on the central composite design, according to the value range of each process parameter in the laser cladding process.

[0031] The molten pool image acquisition module is used to acquire molten pool images during the laser cladding process under each combination of the aforementioned process parameter values.

[0032] The relational model construction module is used to extract the molten pool region and powder island region from the molten pool image, obtain the powder island area ratio based on the area of ​​the molten pool region and the area of ​​the powder island region, and construct a relational model between the powder island area ratio and the values ​​of various process parameters.

[0033] The optimal value range acquisition module is used to determine the optimal value range of the powder island area ratio based on the relationship between the laser cladding layer forming quality and the area ratio of the powder island.

[0034] The laser cladding layer forming quality control module is used to control the values ​​of various process parameters in real time according to the relationship model during the laser cladding process, so that the real-time powder island area ratio is within the optimal range, thereby ensuring the forming quality of the laser cladding layer.

[0035] Compared with the prior art, the above-described technical solution of the present invention has the following advantages:

[0036] This invention obtains images of the molten pool during laser cladding under multiple combinations of different process parameter values ​​and extracts the molten pool region and powder island region to obtain the powder island area ratio. Based on this, a relationship model between the powder island area ratio and the values ​​of various process parameters is constructed. In the actual laser cladding process, the values ​​of various process parameters are controlled in real time according to the relationship model to keep the real-time powder island area ratio within the optimal range. This allows for real-time optimization of process parameters during the cladding process, improving efficiency and the forming quality of the laser cladding layer. Attached Figure Description

[0037] To make the content of this invention easier to understand, the invention will be further described in detail below with reference to specific embodiments and accompanying drawings, wherein:

[0038] Figure 1 This is a flowchart of a method in a preferred embodiment of the present invention.

[0039] Figure 2 This is a schematic diagram of the central composite design in a preferred embodiment of the present invention.

[0040] Figure 3 These are images of the molten pool under each combination of process parameter values ​​in a preferred embodiment of the present invention.

[0041] Figure 4This is a contour map showing the laser power, scanning speed, and powder island area ratio in a preferred embodiment of the present invention.

[0042] Figure 5 This is a three-dimensional surface diagram showing the laser power, scanning speed, and powder island area ratio in a preferred embodiment of the present invention.

[0043] Figure 6 This is a contour map showing the scanning speed, powder feeding rate, and powder island area ratio in a preferred embodiment of the present invention.

[0044] Figure 7 This is a three-dimensional surface diagram showing the scanning speed, powder feeding rate, and powder island area ratio in a preferred embodiment of the present invention.

[0045] Figure 8 The image shown is a molten pool image obtained from a single-pass laser cladding process experiment using the method of the present invention in a preferred embodiment of the present invention.

[0046] Figure 9 The image shows the surface morphology of a single-pass cladding layer obtained by conducting a single-pass laser cladding process experiment using the method of the present invention in a preferred embodiment of the present invention.

[0047] Figure 10 The image shown is a three-dimensional morphological cloud map of a single-pass cladding layer obtained by conducting a single-pass laser cladding process experiment using the method of the present invention in a preferred embodiment of the present invention.

[0048] Figure 11 The image shows the cross-sectional morphology of a single-pass cladding layer obtained by conducting a single-pass laser cladding process experiment using the method of the present invention in a preferred embodiment of the present invention. Detailed Implementation

[0049] The present invention will be further described below with reference to the accompanying drawings and specific embodiments, so that those skilled in the art can better understand and implement the present invention. However, the embodiments described are not intended to limit the present invention.

[0050] Response surface methodology (RSM) is a statistical optimization technique that aims to determine optimal process parameters through systematic experimental design and mathematical modeling. This method first obtains representative data samples based on experimental design principles, then constructs a regression model to quantify the mathematical relationship between factors and the target response, and finally optimizes parameters through model analysis. Based on the overall concept of RSM, this invention designs a method for controlling the forming quality of laser cladding layers based on molten pool powder islands, such as… Figure 1 As shown, it includes the following steps:

[0051] S1: Based on the range of values ​​of various process parameters during laser cladding, construct multiple different combinations of process parameter values ​​using Central Composite Design (CCD).

[0052] To address the multi-parameter optimization problem involved in this invention, since there may be unknown interaction effects between various process parameters, and the experimental variables include continuous data and multi-level discrete variables, a central composite design, a response surface experimental design method, is adopted. This method can effectively handle the optimization needs of complex systems with multiple factors. Specifically, based on the value range of each process parameter during laser cladding, multiple different combinations of process parameter values ​​are constructed using the central composite design:

[0053] S1-1: Obtain the value range of each process parameter of the target material during the laser cladding process. In this embodiment, the powder and substrate used are both 316L stainless steel. The value range of the laser cladding process parameters of this material is: laser power of 800~1200W, scanning speed of 2~6mm / s, and powder feeding rate of 2~8g / min.

[0054] S1-2: Determine the center point process parameter values ​​based on the range of values ​​for each process parameter. In this embodiment, the center point process parameters are laser power P = 1000W, scanning speed V = 4mm / s, and powder feeding rate f = 4g / min.

[0055] S1-3: Based on the center point process parameter values, select multiple values ​​for each process parameter based on the center composite design, and construct multiple different combinations of process parameter values ​​based on the multiple values ​​of each process parameter.

[0056] S1-3-1: The process parameters include laser power, scanning speed and powder feeding rate, and the laser power, scanning speed and powder feeding rate are used as three experimental factors.

[0057] S1-3-2: Using the center point process parameter value as the center point, different cubic point levels and axial point levels are set for each experimental factor to obtain different levels (i.e., multiple values) for each experimental factor; the axial point level is ±α, α=2. k / 4 k represents the number of experimental factors. In this embodiment, each factor has 5 levels: ±1 (cubic point), ±α (axial point), and 0 (center point). In this embodiment, k=3, therefore α=2. k / 4 =1.68. The specific values ​​of each experimental factor and level are shown in Table 1.

[0058] Table 1. Table of Experimental Factors and Levels

[0059]

[0060] S1-3-3: Selecting 2 based on central composite design k 2k cubic points, 2k axial points, and n center points are used to construct (2 k +2k+a) groups of different process parameter values ​​are shown in the schematic diagram of the central composite design. Figure 2 As shown, Figure 2 In this example, x1, x2, and x3 represent three experimental factors. Therefore, in this embodiment, a total of 8 cubic points, 6 axial points, and 6 center points are selected, forming 20 different combinations of process parameter values ​​as shown in Table 2.

[0061] Table 2. Table of different combinations of process parameter values

[0062]

[0063] S2: Obtain the molten pool image during the laser cladding process under each combination of process parameter values, and extract the molten pool area and powder island area from the molten pool image. The powder island area refers to the isolated area formed by incomplete melting or discontinuous melting of powder during the evolution of the molten pool.

[0064] In this embodiment, images of the molten pool under 20 combinations of process parameter values ​​are captured by a high-speed camera, as shown below. Figure 3 As shown, the molten pool region and powder island region were extracted separately through image processing. Figure 3 The red circles indicate powder islands, and the white circles indicate molten pools.

[0065] S3: Based on the area of ​​the molten pool region and the area of ​​the powder island region, obtain the powder island area ratio, and construct a relationship model between the powder island area ratio and the values ​​of various process parameters.

[0066] The area ratio of the powder island is:

[0067] ,

[0068] in, This represents the percentage of the area of ​​the powder islands. The area of ​​the powder island region. This represents the area of ​​the molten pool region.

[0069] Considering computational efficiency and generalization ability, this embodiment uses a multinomial regression model to construct the relational model. The multinomial model has low computational complexity and fast convergence characteristics.

[0070] Through analysis such as Figure 4 The contour plots shown depict laser power, scanning speed, and powder island area percentage, as follows: Figure 5 The three-dimensional surface plots shown represent the laser power, scanning speed, and powder island area ratio, as follows: Figure 6 The contour plots shown depict scanning speed, powder feed rate, and powder island area ratio, as follows: Figure 7 The three-dimensional surface plots showing the scanning speed, powder feeding rate, and powder island area ratio are shown. It can be seen that the powder island area ratio increases with the increase of scanning speed and powder feeding rate, and decreases with the increase of laser power.

[0071] Therefore, the relational model constructed in this embodiment is as follows:

[0072] λ = k1- k2×P – k3×V – k4×f + k5×P×V + k6×P×f – k7×V×f + k8×P 2 + k9×V 2 + k 10 ×f 2 ,

[0073] in, Where P is the area ratio of the powder islands, V is the laser power, f is the scanning speed, and k1, k2, k3, k4, k5, k6, k7, k8, k9, and k 10 This is for adjusting the coefficient.

[0074] In this embodiment, the relational model is specifically as follows:

[0075] λ = 185.40037 - 0.237282P - 2.0713V - 15.0165f + 0.000625P×V +0.002187P×f - 0.03125V×f + 0.000102P 2 + 0.385294V 2 + 1.85566f 2 .

[0076] To demonstrate the effectiveness of the relational model, an analysis of variance was performed. The F-value of the relational model was 11.96, and the p-value was 0.0003, indicating significance. The F-value of the lack-of-fit term was 4.84, and the p-value was 0.0542, indicating non-significance. This proves that the derived relational model is effective.

[0077] S4: Determine the optimal range of the powder island area ratio based on the relationship between the laser cladding layer forming quality and the area ratio of the powder island.

[0078] Based on a review of relevant literature on powder islands and existing experimental studies, it is found that when the area ratio of powder islands is below 30%, the surface roughness and porosity of the cladding layer are lower. When the powder islands are small or absent, over-burning of the cladding layer may occur, while when the powder islands are large, powder adhesion may occur, both of which affect surface quality. Therefore, in this embodiment, the optimal range for the powder island area ratio is set to 27%~28%.

[0079] S5: During the laser cladding process, the values ​​of various process parameters are controlled in real time according to the aforementioned relationship model to ensure that the real-time powder island area ratio is within the optimal range, thereby guaranteeing the forming quality of the laser cladding layer. In this embodiment, the optimal combination of process parameters is a laser power of 1087W, a scanning speed of 3.7mm / s, and a powder feeding rate of 4g / min.

[0080] The present invention also discloses a laser cladding layer forming quality control system based on molten pool powder islands, including a process parameter value combination construction module, a molten pool image acquisition module, a relationship model construction module, an optimal value range acquisition module, and a laser cladding layer forming quality control module.

[0081] The process parameter value combination construction module is used to construct multiple different combinations of process parameter values ​​based on the central composite design, according to the value range of each process parameter during laser cladding. The molten pool image acquisition module is used to acquire the molten pool image during the laser cladding process under each of the aforementioned process parameter value combinations. The relationship model construction module is used to extract the molten pool region and powder island region from the molten pool image, obtain the powder island area ratio based on the area of ​​the molten pool region and the area of ​​the powder island region, and construct a relationship model between the powder island area ratio and the values ​​of each process parameter. The optimal value range acquisition module is used to determine the optimal value range of the powder island area ratio based on the relationship between the laser cladding layer forming quality and the powder island area ratio. The laser cladding layer forming quality control module is used to control the values ​​of each process parameter in real time during the laser cladding process according to the relationship model, ensuring that the real-time powder island area ratio is within the optimal value range, thereby guaranteeing the forming quality of the laser cladding layer.

[0082] The present invention also discloses a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a method for controlling the forming quality of laser cladding layers based on molten pool powder islands.

[0083] The present invention also discloses an apparatus including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a method for controlling the forming quality of a laser cladding layer based on molten pool powder islands.

[0084] Compared with the prior art, the advantages of the present invention are:

[0085] 1. By acquiring images of the molten pool during the laser cladding process under multiple different combinations of process parameter values ​​and extracting the molten pool region and powder island region, the area ratio of the powder island is obtained. Based on this, a relationship model between the area ratio of the powder island and the values ​​of various process parameters is constructed. The relationship model is effective and universal.

[0086] 2. In the actual laser cladding process, the values ​​of various process parameters are controlled in real time according to the relationship model so that the real-time powder island area ratio is within the optimal range. This allows for real-time optimization of process parameters during the cladding process and improves the forming quality of the laser cladding layer.

[0087] 3. This invention introduces the intermediate variable powder island, with process parameters as independent variables and cladding layer forming quality as dependent variable. A general relationship model of the area ratio of powder islands obtained by laser cladding with respect to process parameters is established by using response surface methodology. Based on this, the forming quality of the laser cladding layer is adjusted. Compared with the existing technology of adjusting process parameters based solely on experience and trial and error, this invention significantly improves the scientific nature and efficiency of process optimization.

[0088] To further demonstrate the beneficial effects of the present invention, in this embodiment, 316L stainless steel was used as both the powder and the matrix material. A single-pass laser cladding process experiment was conducted using the method of the present invention, and images of the molten pool were captured. The molten pool images obtained using the method of the present invention are shown below. Figure 8 As shown, the powder island area accounts for 27.3%. The surface morphology of the single-pass cladding layer obtained using the method of this invention is as follows. Figure 9 As shown, the three-dimensional morphological cloud map of a single cladding layer is as follows: Figure 10 As shown, from Figure 9 and Figure 10 It can be seen that the surface morphology of the single-layer cladding layer is good and smooth. Figure 10 Based on the results obtained by capturing images of the substrate and the middle part of the cladding layer using a super depth-of-field microscope, the surface roughness (Ra) of a single-pass cladding layer was obtained by averaging several parallel lines arranged along the scanning direction. The average surface roughness of the single-pass cladding layer was 14.45 μm, achieving an excellent level of surface roughness for powder-fed laser cladding of 316L. The cross-sectional morphology of the single-pass cladding layer obtained using the method of this invention is as follows. Figure 11 As shown, from Figure 11 It can be seen that the cross-sectional morphology of the single-pass cladding layer is smooth and uniform, without obvious cracks or porosity defects. Based on this, its width and height were measured, and the aspect ratio was found to be 4.65, which is within a reasonable process range and is beneficial for subsequent overlapping or stacking. Therefore, the cladding layer processed by the method of this invention meets the process requirements and has good forming quality, thus proving the beneficial effects of this invention.

[0089] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0090] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0091] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0092] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0093] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A method for controlling the forming quality of laser cladding layers based on molten pool powder islands, characterized in that, include: Based on the range of values ​​for various process parameters during laser cladding, multiple combinations of different process parameter values ​​are constructed based on the central composite design. Obtain the molten pool image during the laser cladding process under each combination of process parameter values, and extract the molten pool area and powder island area from the molten pool image; Based on the area of ​​the molten pool region and the area of ​​the powder island region, the area ratio of the powder island is obtained, and a relationship model between the area ratio of the powder island and the values ​​of various process parameters is constructed. Based on the relationship between the forming quality of the laser cladding layer and the area ratio of the powder islands, the optimal range of the area ratio of the powder islands is determined. During the laser cladding process, the values ​​of each process parameter are controlled in real time according to the relationship model so that the real-time powder island area ratio is within the optimal range, thereby ensuring the forming quality of the laser cladding layer. Based on the value range of various process parameters during laser cladding, multiple different combinations of process parameter values ​​are constructed using a central composite design, specifically: Obtain the value range of each process parameter during the laser cladding process of the target material, and determine the value of the process parameter at the center point based on the value range of each process parameter; Based on the values ​​of the process parameters at the center point, multiple values ​​of each process parameter are selected based on the center composite design, and multiple different combinations of process parameter values ​​are constructed based on the multiple values ​​of each process parameter. The relational model is as follows: λ = k1 - k2×P – k3×V – k4×f + k5×P×V + k6×P×f – k7×V×f + k8×P 2 + k9×V 2 + k 10 ×f 2 , in, Where P is the area ratio of the powder islands, V is the laser power, f is the scanning speed, and k1, k2, k3, k4, k5, k6, k7, k8, k9, and k 10 This is for adjusting the coefficient.

2. The method for controlling the forming quality of laser cladding layer based on molten pool powder islands according to claim 1, characterized in that: Based on the center point process parameter values, multiple values ​​for each process parameter are selected based on the center composite design. Multiple different combinations of process parameter values ​​are then constructed based on these multiple values. Specifically: The process parameters include laser power, scanning speed, and powder feeding rate, which are used as three experimental factors. Using the center point process parameter value as the center point, different cubic point levels and axial point levels are set for each experimental factor to obtain multiple values ​​for each experimental factor. Based on the central composite design, 2 were selected. k 2k cubic points, 2k axial points, and n center points are used to construct (2 k +2k+a) groups of different process parameter values, where k represents the number of experimental factors.

3. The method for controlling the forming quality of laser cladding layer based on molten pool powder islands according to claim 2, characterized in that: The horizontal axis point is ±α, where α=2. k / 4 .

4. The method for controlling the forming quality of laser cladding layer based on molten pool powder islands according to claim 1, characterized in that: The area ratio of the powder island is: ， in, This represents the percentage of the area of ​​the powder islands. The area of ​​the powder island region. This represents the area of ​​the molten pool region.

5. The method for controlling the forming quality of laser cladding layer based on molten pool powder islands according to claim 1, characterized in that: The process parameters include laser power, scanning speed, and powder feeding rate. When constructing the relationship model between the powder island area ratio and the values ​​of each process parameter, the relationship model is constructed by combining the changing trend of the powder island area ratio with scanning speed, powder feeding rate, and laser power through a multinomial regression model.

6. The method for controlling the forming quality of laser cladding layer based on molten pool powder islands according to claim 1, characterized in that: The k1, k2, k3, k4, k5, k6, k7, k8, k9 and k 10 The values ​​of k are: k1=185.40037, k2=0.237282, k3=2.0713, k4=15.0165, k5=0.000625, k6=0.002187, k7=0.03125, k8=0.000102, k9=0.385294, k 10 =1.85566.

7. The method for controlling the forming quality of laser cladding layer based on molten pool powder islands according to any one of claims 1-6, characterized in that: The optimal range for the area ratio of the powder island is 27% to 28%.

8. A laser cladding layer forming quality control system based on molten pool powder islands, characterized in that, include: The process parameter value combination construction module is used to construct multiple different process parameter value combinations based on the central composite design, according to the value range of each process parameter in the laser cladding process. The molten pool image acquisition module is used to acquire molten pool images during the laser cladding process under each combination of the aforementioned process parameter values. The relational model construction module is used to extract the molten pool region and powder island region from the molten pool image, obtain the powder island area ratio based on the area of ​​the molten pool region and the area of ​​the powder island region, and construct a relational model between the powder island area ratio and the values ​​of various process parameters. The optimal value range acquisition module is used to determine the optimal value range of the powder island area ratio based on the relationship between the laser cladding layer forming quality and the area ratio of the powder island. The laser cladding layer forming quality control module is used to control the values ​​of various process parameters in real time according to the relationship model during the laser cladding process so that the real-time powder island area ratio is within the optimal range, thereby ensuring the forming quality of the laser cladding layer. Based on the value range of various process parameters during laser cladding, multiple different combinations of process parameter values ​​are constructed using a central composite design, specifically: Obtain the value range of each process parameter during the laser cladding process of the target material, and determine the value of the process parameter at the center point based on the value range of each process parameter; Based on the values ​​of the process parameters at the center point, multiple values ​​of each process parameter are selected based on the center composite design, and multiple different combinations of process parameter values ​​are constructed based on the multiple values ​​of each process parameter. The relational model is as follows: λ = k1 - k2×P – k3×V – k4×f + k5×P×V + k6×P×f – k7×V×f + k8×P 2 + k9×V 2 + k 10 ×f 2 , in, Where P is the area ratio of the powder islands, V is the laser power, f is the scanning speed, and k1, k2, k3, k4, k5, k6, k7, k8, k9, and k 10 This is for adjusting the coefficient.

Images