Modeling method for incidence relation between metal additive manufacturing pore quality and technological parameters
Through orthogonal experiments and multiple test methods, the relationship between pore quality defects and process parameter windows in laser powder bed melt additive manufacturing was systematically established, which solved the problem of lack of systematic modeling methods in the existing technology, realized guidance on process parameter selection and quality defect control, and reduced the occurrence of pore defects.
Patent Information
- Application Number
- CN202311677593.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-08
- Publication Date
- 2025-06-10
AI Technical Summary
There is a lack of systematic modeling methods in the prior art to study the relationship between pore quality defects and process parameters in laser powder bed melt additive manufacturing, which makes quality control difficult.
Through process parameter orthogonal experiments, metallographic observation, porosity testing and X-ray imager scanning, the correlation relationship between pore quality defects in laser powder bed melt additive manufacturing and process parameter window is systematically established.
The accurate search of the process parameter window of the metal laser powder bed melt additive manufacturing process is achieved, and guidance on the selection of process parameters and quality defect control is provided, which effectively reduces the occurrence of internal pore defects.
Smart Images
Figure CN120124237A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of laser metal additive manufacturing, and particularly relates to a method for correlating the pore quality defects and process parameter windows in metal additive manufacturing. Background Art
[0002] Metal additive manufacturing technology has the advantages of short production cycle and high material utilization rate. However, the quality control of its products is a limitation restricting the applicability of additive manufacturing parts and products. Among them, pore defects are the most serious defects affecting product quality.
[0003] The quality problems can be attributed to numerous process parameters. During the LPBF manufacturing process, the interaction between the laser and the metal undergoes complex physical processes, and the process parameters in this process determine the final forming quality of the part. In order to obtain high-quality parts, it is necessary to study the correlation between LPBF process parameters and quality defects. Process parameters are the inputs of the LPBF system and can be divided into predefined parameters and controllable parameters. Predefined parameters are generally not used for feedback control during the processing, and the optimal values of these parameters are determined before the start of processing. Controllable parameters include parameters that can be feedback-controlled, such as laser power, laser beam diameter, scanning speed, scanning mode, and feed rate, and are the objects of study for many researchers. Among them, the two process parameters of laser power and scanning speed have a great impact on the forming quality. Taking the scanning speed as the X-axis and the laser power as the Y-axis, a PV space can be established. Different positions in the PV diagram represent different combinations of process parameters. Marking the forming quality of parts obtained with different parameter combinations in the PV diagram can intuitively reflect the optimal combination of process parameters. The area of the optimal process parameter combination is called the process parameter window.
[0004] Studying the correlation between typical defects and process parameters in metal additive manufacturing, clarifying the influence of process parameters on defect formation, and finding the process parameter window can provide guidance for the selection of process parameters and quality defect control during metal additive manufacturing, and has extremely high engineering application value.
[0005] In previous studies on the correlation between pore quality defects and process parameter windows in laser powder bed fusion additive manufacturing, there has been a lack of research on systematic modeling methods. Through the present invention, the correlation between pore quality defects and process parameter windows in laser powder bed fusion manufacturing of various metal materials can be systematically established, providing guidance for the selection of process parameters and quality defect control during metal additive manufacturing. Therefore, studying methods for finding the process parameter window in metal laser powder bed fusion additive manufacturing has great practical application potential.
[0006] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present invention, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention
[0007] In view of the problems existing in the prior art, the present invention proposes a method for establishing the correlation between the pore quality defects and process parameter windows in metal additive manufacturing. Through orthogonal experiments of process parameters, metallographic observation, porosity testing, and X-ray imager scanning, the correlation between the pore quality defects and process parameter windows in laser powder bed fusion additive manufacturing is systematically established, providing guidance for the selection of process parameters and quality defect control in the laser powder bed fusion additive manufacturing process.
[0008] The object of the present invention is achieved through the following technical solutions. The method for establishing the correlation between the pore quality defects and process parameter windows in metal additive manufacturing includes the following steps.
[0009] In the first step, two parameters, namely laser power and laser scanning speed, during the laser powder bed fusion manufacturing process are selected for orthogonal experiments to obtain a plurality of metal specimens.
[0010] In the second step, a part of the metal specimens is selected at the four corners and the center of the laser powder bed printing range for metallographic polishing to obtain metallographic images. The metallographic images are converted into grayscale images, and through binary segmentation of the images, the pore area used to quantitatively evaluate the degree of pore defects is identified. The pore areas of each specimen are analyzed and compared to find the energy density line of the specimen with the smallest proportion of pore area.
[0011] In the third step, the porosity of all metal specimens is measured by the Archimedes drainage method. Among them, the dry weight, wet weight, and suspended weight of all metal specimens are measured respectively, and the porosity is calculated using the following formula, and a three-dimensional image of the porosity is drawn. Combining with the energy density line, the depression concentration area near the energy density line in the three-dimensional image is selected to determine the position of the preliminary process parameter window.
[0012]
[0013] In the fourth step, correction is performed by using the X-ray imager scanning method. At the steep part of the boundary curve of the preliminary process parameter window, process parameter combinations are selected for interpolation printing experiments to refine and correct the boundary of the process parameter window. The internal pore conditions of the metal specimens are obtained by scanning with the X-ray imager, a three-dimensional pore model of the metal specimens is established, and the porosity of the metal specimens is calculated for subsequent optimization of the boundary of the process parameter window.
[0014] In the fifth step, in combination with the position of the preliminary process parameter window, the process parameter window is optimized according to the results of the X-ray imager scanning.
[0015] In the method described above, in the first step, the laser power is 100W - 450W, and the laser scanning speed is 100mm - 2000mm / s.
[0016] In the method described above, in the second step, Matlab is used to convert the metallographic image into a grayscale image, and the global threshold Otsu method is adopted to determine the binarization threshold. The pixel points with gray levels lower than the threshold are pores, and the black areas are pores. By calculating the number of pore pixel points and dividing it by the total number of pixel points, the proportion S of the pore area in the entire metallographic image is obtained, and the pore condition of the metal specimen is evaluated by the proportion S.
[0017] In the method described above, in the third step, all metal specimens are measured three times respectively, the obtained porosity is classified, and different colors are used to represent the porosity size to draw a three-dimensional porosity test image.
[0018] In the method described above, in the fourth step, an X-ray imager is used to scan and obtain the internal pore condition of the metal specimen, and the ROI segmentation or a deep learning model is used to calculate the porosity of the metal specimen.
[0019] In the method described above, in the fifth step, the position for selecting the interpolation printing experimental parameters is at the steep boundary. During the boundary optimization process, the porosity results scanned by the X-ray imager are mutually verified with the porosity test results of the drainage method to determine the new process window boundary and eliminate the influence of experimental errors. If there are large differences between the two results, the results scanned by the X-ray imager shall prevail.
[0020] In the method described above, there are at least 160 metal specimens.
[0021] In the method described above, the AlSi10Mg material is selected for laser powder bed fusion manufacturing.
[0022] Compared with the prior art, the present invention has the following advantages: effectively establishing the correlation between the pore quality defects and the process parameter window in metal laser powder bed fusion additive manufacturing, providing process parameter guidance for the metal laser powder bed fusion additive manufacturing process, effectively reducing the occurrence of internal pore defects, avoiding quality defects caused by improper selection of process parameters, and improving the processing quality. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] By reading the detailed description of the preferred specific embodiments below, various other advantages and benefits of the present invention will become clear to those of ordinary skill in the art. The accompanying drawings in the specification are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. Moreover, throughout the drawings, the same reference numerals are used to represent the same components.
[0024] In the drawings:
[0025] Figure 1 It is a schematic diagram of the steps of a method for modeling the correlation between pore quality defects and process parameter windows in laser powder bed fusion additive manufacturing according to the present invention;
[0026] Figure 2 It is a schematic diagram of the principle of laser powder bed fusion technology for a method for modeling the correlation between pore quality defects and process parameter windows in laser powder bed fusion additive manufacturing according to the present invention;
[0027] Figure 3 It is a diagram for comparing the serial numbers of process parameters in the orthogonal experiment of process parameters for a method for modeling the correlation between pore quality defects and process parameter windows in laser powder bed fusion additive manufacturing according to the present invention;
[0028] Figure 4 It is a metallographic binary image for a method for modeling the correlation between pore quality defects and process parameter windows in laser powder bed fusion additive manufacturing according to the present invention;
[0029] Figure 5 It is a three-dimensional diagram of porosity measurement for a method for modeling the correlation between pore quality defects and process parameter windows in laser powder bed fusion additive manufacturing according to the present invention;
[0030] Figure 6 It is a diagram of the position of interpolation printing parameters for a method for modeling the correlation between pore quality defects and process parameter windows in laser powder bed fusion additive manufacturing according to the present invention;
[0031] Figure 7 It is a PV diagram of internal pores of AlSi10Mg for a method for modeling the correlation between pore quality defects and process parameter windows in laser powder bed fusion additive manufacturing according to the present invention.
[0032] The present invention will be further explained below with reference to the accompanying drawings and embodiments. Specific Embodiments
[0033] Specific embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although specific embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present invention can be more thoroughly understood and the scope of the present invention can be completely conveyed to those skilled in the art.
[0034] It should be noted that certain words are used in the specification and claims to refer to specific components. Those skilled in the art should understand that technicians may use different nouns to refer to the same component. This specification and claims do not use the difference in nouns as a way to distinguish components, but use the difference in the functions of the components as the criterion for distinction. As mentioned throughout the specification and claims, "including" or "comprising" is an open term, so it should be interpreted as "including but not limited to". The subsequent description of the specification is a preferred embodiment of the present invention, but the description is based on the general principles of the specification and is not intended to limit the scope of the present invention. The scope of protection of the present invention shall be determined by the attached claims.
[0035] To facilitate understanding of the embodiments of the present invention, further explanation will be given below by taking specific embodiments as examples in conjunction with the accompanying drawings, and each of the accompanying drawings does not constitute a limitation on the embodiments of the present invention.
[0036] For better understanding, in one embodiment, Figures 1 to 7 As shown in FIG. 1 , the metal additive manufacturing porosity quality defect and process parameter window correlation modeling method includes the following steps:
[0037] In the first step S1, two parameters, laser power and laser scanning speed, in the laser powder bed fusion manufacturing process are selected to perform an orthogonalization experiment and obtain a plurality of metal samples;
[0038] In the second step S2, a portion of metal samples are selected from the four corners and the center of the laser powder bed printing range for metallographic grinding to obtain a metallographic image, and the metallographic image is converted into a grayscale image. The image is binarized and segmented to identify the pore area used for quantitative evaluation of the degree of pore defects, and the pore areas of each sample are analyzed and compared to find the energy density line of the sample with the smallest pore area ratio;
[0039] In the third step S3, the porosity of all metal samples is tested by the Archimedean drainage method, wherein the dry weight, wet weight and suspended weight of all metal samples are measured respectively, the porosity is calculated using the following formula, and a three-dimensional image of the porosity is drawn. The concave area in the three-dimensional image has a smaller porosity. Combined with the energy density line, the concave concentration near the energy density line in the three-dimensional image is selected, and the position of the process parameter window is preliminarily determined according to the process parameter and sample number comparison table;
[0040]
[0041] In the fourth step S4, in the orthogonal experiment, the parameter step size is relatively large, and there is a relatively steep problem at the boundary of the preliminary process parameter window. It is corrected by using the method of scanning with an X-ray imager. At the relatively steep part of the boundary curve of the preliminary process parameter window, a process parameter combination is selected for interpolation printing experiments to refine and correct the boundary of the process parameter window. The X-ray imager is used to scan to obtain the internal pore conditions of the metal specimen, a three-dimensional model of the pores of the metal specimen is established, and the porosity of the metal specimen is calculated and obtained.
[0042] In the fifth step S5, combining the boundary information of the preliminary process parameter window, according to the accurate porosity results of the interpolation printing specimens near the boundary obtained by scanning with the X-ray imager, the boundary of the process parameter window is smoothed to obtain the final process parameter window.
[0043] In the preferred embodiment of the method described, in the first step S1, the laser power is 100W - 450W, and the laser scanning speed is 100mm - 2000mm / s.
[0044] In the preferred embodiment of the method described, in the second step S2, matlab is used to convert the metallographic image into a grayscale image, and the global threshold Otsu method is used to determine the threshold for binarization. The pixel points with grayscale lower than the threshold are pores, and the black area is pores. By calculating the number of pore pixel points and dividing it by the total number of pixel points, the proportion S of the pore area in the entire metallographic image is obtained. The pore condition of the metal specimen is evaluated by the proportion S, and it is judged to find the process window along the energy density line of the 90th specimen.
[0045] In the preferred embodiment of the method described, in the third step S3, all metal specimens are measured three times respectively, the obtained porosities are classified, and different colors are used to represent the porosity size to draw a three-dimensional image of porosity test.
[0046] In the preferred embodiment of the method described, in the fourth step S4, the X-ray imager is used to scan to obtain the internal pore conditions of the metal specimen, and the porosity of the metal specimen is calculated by ROI segmentation or a deep learning model.
[0047] In the preferred embodiment of the method described, in the fifth step S5, the position where the interpolation printing experiment parameters are selected is at the steep boundary. During the boundary optimization process, the porosity results obtained by scanning with the X-ray imager and the porosity test results by the drainage method are mutually verified to exclude the influence of experimental errors. If there are large differences between the two results, the scanning results of the X-ray imager shall prevail.
[0048] In the preferred embodiment of the method described, there are at least 160 metal specimens.
[0049] In the preferred embodiment of the method described, the AlSi10Mg material is selected for laser powder bed fusion manufacturing.
[0050] In a preferred embodiment of the described method, in the first step, the parameter range is a laser power of 100 W - 450 W and a laser scanning speed of 100 mm - 2000 mm / s; to ensure that the experimental data can more accurately reflect the shape of the process parameter window, the laser power step size is selected as 50 W, the laser scanning speed is 100 mm / s, the slice thickness is 0.030 mm, and the printing path will be automatically generated by E-Hatch software.
[0051] In one embodiment, for better understanding, Figure 1 To find the step schematic diagram of the modeling method for the correlation between the pore quality defect and the process parameter window in the laser powder bed fusion additive manufacturing of AlSi10Mg, as Figure 1 shown, the modeling method for finding the correlation between the pore quality defect and the process parameter window in the laser powder bed fusion additive manufacturing of AlSi10Mg includes the following steps:
[0052] In the first step S1, first, two key parameters, namely the laser power and the laser scanning speed, during the laser powder bed fusion manufacturing process of AlSi10Mg material are selected for an orthogonal experiment. Appropriate parameter ranges are selected and appropriate step sizes are respectively confirmed, and then specimen modeling and parameter filling are carried out. 160 metal specimens are printed, and the specimens are separated from the substrate using a numerically controlled electrical discharge cutting machine;
[0053] In the second step S2, a part of the metal specimens are selected at the four corners and the center of the laser powder bed printing range for metallographic polishing to obtain metallographic images. The metallographic images are converted into grayscale images, and through binary segmentation of the images, the pore area used to quantitatively evaluate the degree of pore defects is identified. The pore areas of each specimen are analyzed and compared, and the energy density line of the specimen with the smallest proportion of pore area is found;
[0054] In the third step S3, the porosity of all metal specimens is measured by the Archimedes drainage method. Among them, the dry weight, wet weight, and suspended weight of all metal specimens are measured respectively, and the porosity is calculated using the following formula, and a three-dimensional image of the porosity is drawn. The sunken area in the three-dimensional image has a smaller porosity. Combining with the energy density line in the second step, the concentrated sunken area near the energy density line in the three-dimensional image is selected, and according to the process parameter and specimen serial number comparison table, the position of the process parameter window is preliminarily determined;
[0055]
[0056] In the fourth step S4, correction is performed by means of X-ray imager scanning. At the steep part of the boundary curve of the preliminary process parameter window, a combination of process parameters is selected for interpolation printing experiments to refine and correct the boundary of the process parameter window. The X-ray imager is used to scan to obtain the internal pore condition of the metal specimen, a three-dimensional model of the pores of the metal specimen is established, and the porosity of the metal specimen is calculated for subsequent optimization of the boundary of the process parameter window.
[0057] In the fifth step S5, in combination with metallographic observation and porosity testing to obtain the position of the process parameter window, the boundary of the process parameter window is optimized according to the results of X-ray imager scanning to obtain an accurate process parameter window.
[0058] In a preferred embodiment of the method for finding the process parameter window of AlSi10Mg laser powder bed fusion additive manufacturing in the present invention, in the first step S1: Orthogonal experiments are carried out on two key parameters, namely laser power and laser scanning speed, during the laser powder bed fusion manufacturing process of AlSi10Mg material. Appropriate parameter ranges are selected and appropriate step sizes are confirmed respectively, and specimen modeling and parameter filling are carried out. 160 metal specimens are printed, and a numerical control wire electrical discharge machine is used to separate the specimens from the substrate; in the preferred embodiment of the present invention, the main components of AlSi10Mg are as shown in Table 1 below, and the orthogonal experiment parameter design is as shown in Table 2 below.
[0059] Table 1 Main components of AlSi10Mg
[0060]
[0061] Table 2 Orthogonal experiment parameter design for laser powder bed fusion
[0062]
[0063] In a preferred embodiment of the method for modeling the correlation between pore quality defects and process parameter window in laser powder bed fusion additive manufacturing in the present invention, in the second step S2: Five specimens are selected from the obtained 160 specimens for metallographic polishing to obtain metallographic images. The metallographic images are converted into grayscale images, and through binary segmentation of the images, the area of the pores is accurately identified for quantitatively evaluating the degree of pore defects. In the preferred embodiment of the method of the present invention, specimens No. 10 (100W - 1000mm / s), No. 20 (100W - 2000mm / s), No. 90 (300W - 1000mm / s), No. 94 (300W - 1400mm / s), and No. 160 (450W - 2000mm / s) are selected for metallographic polishing, which basically covers the entire parameter range of the orthogonal printing experiment. The threshold value for binary segmentation of each metallographic image is calculated by the global threshold Otsu method, and the proportion S of its pore area is used as a quantitative index for the pore condition.
[0064] In a preferred embodiment of the method for modeling the correlation between pore quality defects and process parameter windows in laser powder bed fusion additive manufacturing according to the present invention, in the third step S3: the porosity of all specimens is measured by the Archimedes drainage method. The dry weight, wet weight, and suspended weight of 160 specimens are measured respectively, the porosity is calculated, and a three-dimensional image of the porosity is drawn for analysis to preliminarily determine the position of the process parameter window.
[0065] In a preferred embodiment of the method for modeling the correlation between pore quality defects and process parameter windows in laser powder bed fusion additive manufacturing according to the present invention, in the fourth step S4: in view of the problem of steep boundaries of the preliminary process parameter window, correction is carried out by means of scanning with an X-ray imager. Interpolation printing experiments need to be carried out at the steep boundaries, and the X-ray imager is used to scan to obtain the internal pore conditions of the specimens, and the porosity of the specimens is accurately calculated; where the red dots represent the interpolation positions, the black solid lines represent the rough boundaries of the process parameter window, and the ROI segmentation method is used to accurately calculate the porosity of the specimens.
[0066] In a preferred embodiment of the method for modeling the correlation between pore quality defects and process parameter windows in laser powder bed fusion additive manufacturing according to the present invention, in the fifth step S5: combining metallographic observation and porosity measurement to obtain the position of the process parameter window, and optimizing the boundaries of the process parameter window according to the results of scanning with an X-ray imager to obtain an accurate process parameter window.
[0067] In one embodiment, as Figure 4 shown, from the pore area ratio S of the five specimens and the corresponding process parameter rules, it can be inferred that when the laser power is the same, too high a scanning speed will affect the number of pores; the pore area ratios are all relatively small, and the energy densities differ little, so the range of the process parameter window can be found according to the direction of the energy density. The S of specimen No. 90 is the smallest, only 0.298%, so taking the energy density line of specimen No. 90 as the center, continue to find the parameters with the best printing quality.
[0068] Figure 5 is a three-dimensional porosity test diagram of the method for modeling the correlation between pore quality defects and process parameter windows in laser powder bed fusion additive manufacturing according to the present invention; Figure 6 is an interpolation printing parameter position diagram of the method for modeling the correlation between pore quality defects and process parameter windows in laser powder bed fusion additive manufacturing according to the present invention; from Figure 5 it can be seen that the parameters of most specimens with small porosities are relatively concentrated. The porosities of specimens with printing parameters of 300 - 450 W and scanning speeds of 1200 - 1600 mm / s are relatively small, and the range of the process parameter window is preliminarily locked here; from Figure 6 it can be seen that the boundaries of the preliminarily determined process parameter window are very steep, and the interpolation printing method can be used to further determine the porosity at the boundaries. Figure 7It is a PV diagram of internal pores of AlSi10Mg according to the modeling method of the correlation between pore quality defects and process parameter windows in laser powder bed fusion additive manufacturing of the present invention; from Figure 7 As can be seen, through the optimization and correction of the interpolation printing experiment, the process parameter window becomes smooth, and the X-ray imager scanning results and porosity test results corroborate each other, ensuring the reliability of the process parameter window results, indicating that this method can accurately find the process parameter window for AlSi10Mg laser powder bed fusion additive manufacturing, and provide guidance for the selection of process parameters and quality defect control during the AlSi10Mg additive manufacturing process.
[0069] Although the embodiments of the present invention have been described above in conjunction with the accompanying drawings, the present invention is not limited to the above specific embodiments and application fields. The above specific embodiments are merely illustrative and guiding, rather than restrictive. Those of ordinary skill in the art can also make many forms under the inspiration of this specification and without departing from the scope protected by the claims of the present invention, and all of these fall within the scope of protection of the present invention.
Claims
1. A method for associating and modeling the pore quality defects in metal additive manufacturing with the process parameter window, characterized in that, it includes the following steps, In the first step (S1), two parameters, namely the laser power and the laser scanning speed, during the laser powder bed melting manufacturing process are selected for orthogonal experiments to obtain a plurality of metal specimens; In the second step (S2), a part of the metal specimens are selected at the four corners and the center of the laser powder bed printing range, the pore area used to quantitatively evaluate the degree of pore defects is identified, the pore areas of each specimen are analyzed and compared, and the energy density line of the specimen with the smallest proportion of pore area is found; In the third step (S3), the porosity of all the metal specimens is measured, the porosity rate is calculated, a three-dimensional image of the porosity rate is drawn, and in combination with the energy density line, the depression concentration area near the energy density line in the three-dimensional image is selected and determined as the position of the preliminary process parameter window; In the fourth step (S4), at the steep part of the boundary curve of the preliminary process parameter window, the boundary of the process parameter window is refined and corrected, a three-dimensional model of the pores of the metal specimen is established, the porosity rate of the metal specimen is calculated, and it is subsequently used to optimize the boundary of the process parameter window; In the fifth step (S5), based on the position of the refined and corrected preliminary process parameter window, according to the porosity rate of the metal specimen, the boundary of the preliminary process parameter window is smoothed to obtain the final process parameter window.
2. The method according to claim 1, characterized in that, Preferably, in the first step (S1), the laser power is 100W - 450W, and the laser scanning speed is 100mm - 2000mm / s.
3. The method according to claim 2, characterized in that, In the second step (S2), matlab is used to convert the metallographic image into a grayscale image, the global threshold Otsu method is used to determine the threshold for binarization, the pixel points with gray levels lower than the threshold are pores, the black area is pores, and by calculating the number of pore pixel points and dividing it by the total number of pixel points, the proportion S of the pore area in the entire metallographic image is obtained, and the pore condition of the metal specimen is evaluated by the proportion S.
4. The method according to claim 1, characterized in that, In the third step (S3), all the metal specimens are measured three times respectively, the obtained porosity rates are classified, and different colors are used to represent the size of the porosity rate to draw the three-dimensional image of the porosity test.
5. The method according to claim 1, characterized in that, In the fourth step (S4), an X-ray imager is used to scan and obtain the internal pore condition of the metal specimen, and the porosity rate of the metal specimen is calculated by ROI segmentation or a deep learning model.
6. The method according to claim 1, characterized in that, In the fifth step (S5), the interpolation printing experimental parameter selection position is located at the steep boundary, during the boundary optimization process, the porosity results scanned by the X-ray imager and the porosity test results by the drainage method are mutually verified to determine the new process window boundary, excluding the influence of experimental errors. If there are large differences between the two results, the results of the X-ray imager scan shall prevail.
7. The method according to claim 1, characterized in that, The plurality of metal specimens includes at least 160.
8. The method according to claim 1, characterized in that, Various metal materials can be selected for laser powder bed fusion manufacturing.