Additive manufacturing metal part key defect identification method based on defect geometric characteristics

Abstract

The invention provides an additive manufacturing metal part key defect identification method based on defect geometrical characteristics, and relates to the technical field of additive manufacturing fatigue performance evaluation, and the method achieves the purpose of identifying the key defect of an additive manufacturing metal part from the traditional XCT which can only identify the existence of the defect by constructing a fatigue damage parameter model fusing the defect geometrical characteristics and a service load. Therefore, the most dangerous defect can be accurately evaluated, and the problem of lack of quantitative evaluation of defect risk in the prior art is overcome. By establishing a fatigue damage parameter model, fatigue damage parameters of all defects are calculated and sorted by using nominal stress of all the defects and target geometrical characteristic parameters of all the defects extracted based on a two-dimensional slice image, so that critical defects are scientifically identified; the fatigue reliability evaluation precision of the additive manufacturing metal part under the actual working condition is remarkably improved, and a quantifiable and operable technical basis is provided for quality control and life prediction.

Description

Technical Field

[0001] This invention relates to the field of fatigue performance evaluation technology in additive manufacturing, and in particular to a method for identifying key defects in additively manufactured metal parts based on defect geometry features. Background Technology

[0002] Additive manufacturing of metal parts is widely used in aerospace, medical implants and other fields due to its ability to form complex structures. However, this process is prone to introducing microscopic defects such as porosity, lack of fusion, and spheroidization during the forming process. These defects are randomly distributed inside the component and become the preferred sites for fatigue crack initiation, significantly reducing the fatigue life and reliability of the parts.

[0003] Currently, X-ray computed tomography (XCT) is commonly used in industry for non-destructive testing of additively manufactured parts to obtain the distribution and geometry of internal defects. However, existing XCT analysis software is mostly limited to defect morphology recognition and statistical description, lacking the ability to quantitatively assess the "hazard" of defects and determine which defect is most likely to induce fatigue failure. Therefore, there is an urgent need for a method that can identify critical defects to achieve accurate quality control and life prediction. Summary of the Invention

[0004] The purpose of this invention is to provide a method for identifying critical defects in additively manufactured metal parts based on defect geometry features, so as to alleviate the technical problem of lacking quantitative evaluation of defect risk in the prior art.

[0005] In a first aspect, the present invention provides a method for identifying critical defects in additively manufactured metal parts based on defect geometric features, comprising: constructing a fatigue damage parameter model for characterizing the degree of defect hazard in a target batch of additively manufactured metal parts; wherein the input data of the fatigue damage parameter model includes: the nominal stress of the defect and target geometric feature parameters; the output data of the fatigue damage parameter model includes: fatigue damage parameters of the defect; acquiring multiple two-dimensional slice images of the target part, and extracting the target geometric feature parameters of each defect in each two-dimensional slice image; wherein the target part represents any part in the target batch of additively manufactured metal parts; calculating the nominal stress of the defect in the target two-dimensional slice image based on a preset loading load of the target part and the cross-sectional area of ​​the part in the target two-dimensional slice image; wherein the target two-dimensional slice image represents any two-dimensional slice image among multiple two-dimensional slice images; processing the nominal stress of the defect in the target two-dimensional slice image and the target geometric feature parameters of the target defect using the fatigue damage parameter model to obtain the fatigue damage parameters of the target defect; wherein the target defect represents any defect in the target two-dimensional slice image; and taking the defect with the largest fatigue damage parameter among the multiple two-dimensional slice images of the target part as the critical defect of the target part.

[0006] In an optional implementation, a fatigue damage parameter model is constructed to characterize the defect severity of the target batch of additively manufactured metal parts. This includes: obtaining fatigue life and fracture surface analysis results of multiple test samples after undergoing fatigue tests under the same service conditions as the parts; wherein the test samples include any of the following: target batch of additively manufactured metal parts, standard fatigue specimens; the fracture surface analysis results include: nominal stress of defects at the fracture location, size parameters, location parameters, shape parameters, and orientation parameters of two-dimensional defects at the fatigue source of the fracture surface; based on the fatigue life and fracture surface analysis results of multiple test samples, one geometric feature parameter with the highest correlation to fatigue life is selected from each of the size parameter, location parameter, shape parameter, and orientation parameter, and used as the target geometric feature parameter; the fatigue life, nominal stress of defects at the fracture location, and target geometric feature parameter of multiple test samples are fitted using the least squares method to obtain the fatigue damage parameter model.

[0007] In an optional implementation, the standard fatigue specimen is a cylindrical specimen with the same cross-section as the target batch of additively manufactured metal parts, using the same printing equipment and raw materials, and having the same process parameters, heat treatment regime, printing direction, and surface finish.

[0008] In optional embodiments, the dimensional parameters include: the square root of the projected area of ​​the defect in the vertical loading direction, the square root of the area of ​​the circumscribed ellipse of the defect, and the maximum distance between two points on the defect profile; the positional parameters include: the shortest distance from the defect profile to the sample surface, and the distance from the geometric center of the defect to the sample surface; the shape parameters include: the roundness calculated from the projected area of ​​the defect and the maximum distance from the geometric center to the edge of the defect, and the roundness calculated from the projected area of ​​the defect and the perimeter of the defect; the orientation parameters include: the acute angle between the extension of the major axis of the circumscribed ellipse of the defect and the tangent to the sample surface, and the acute angle between the extension of the maximum distance between two points on the defect profile and the tangent to the sample surface.

[0009] In an optional implementation, acquiring multiple two-dimensional slice images of the target component includes: performing XCT detection on the target component to obtain multiple initial two-dimensional slice images; wherein, during XCT detection, the two-dimensional slice plane is perpendicular to the load direction of the target component; and preprocessing the multiple initial two-dimensional slice images to obtain multiple optimized two-dimensional slice images; wherein, the preprocessing includes: image denoising, grayscale enhancement, and edge sharpening.

[0010] In an optional implementation, the output data of the fatigue damage parameter model may also include the fatigue life of the target component.

[0011] In an optional implementation, after obtaining the critical defects of the target component, the method further includes: acquiring a three-dimensional reconstruction model of the defects of the target component; generating a visualization result of the defects of the target component based on the three-dimensional reconstruction model of the defects and the fatigue damage parameters of all defects in the target component; wherein the visualization result is to mark the spatial location of the critical defects and the target geometric feature parameters in the three-dimensional reconstruction model of the defects, and to display the risk level distribution map of different defects in a color-coded manner.

[0012] Secondly, this invention provides a critical defect identification device for additively manufactured metal parts based on defect geometric features, comprising: a construction module for constructing a fatigue damage parameter model for characterizing the defect severity of a target batch of additively manufactured metal parts; wherein the input data of the fatigue damage parameter model includes: the nominal stress of the defect and target geometric feature parameters; the output data of the fatigue damage parameter model includes: fatigue damage parameters of the defect; an acquisition module for acquiring multiple two-dimensional slice images of the target part and extracting the target geometric feature parameters of each defect in each two-dimensional slice image; wherein the target part represents any part in the target batch of additively manufactured metal parts; and calculating... The module is used to calculate the nominal stress of the defect in the target two-dimensional slice image based on the preset loading load of the target component and the cross-sectional area of ​​the component in the target two-dimensional slice image; wherein, the target two-dimensional slice image represents any two-dimensional slice image among multiple two-dimensional slice images; the processing module is used to process the nominal stress of the defect in the target two-dimensional slice image and the target geometric feature parameters of the target defect using a fatigue damage parameter model to obtain the fatigue damage parameters of the target defect; wherein, the target defect represents any defect in the target two-dimensional slice image; the determination module is used to take the defect with the largest fatigue damage parameter among the multiple two-dimensional slice images of the target component as the critical defect of the target component.

[0013] Thirdly, the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the computer program to implement the method for identifying key defects of additive manufacturing metal parts based on defect geometry features as described in any of the foregoing embodiments.

[0014] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the method for identifying key defects in additively manufactured metal parts based on defect geometry features as described in any of the foregoing embodiments.

[0015] This invention provides a method for identifying critical defects in additively manufactured metal parts based on defect geometry features. This method, by constructing a fatigue damage parameter model that integrates defect geometry features and service loads, achieves a leap from traditional XCT, which can only identify the existence of defects, to accurately assessing the most dangerous defects, overcoming the problem of lacking quantitative evaluation of defect hazard in existing technologies. By establishing a fatigue damage parameter model, using the nominal stress of each defect and the target geometric feature parameters of each defect extracted based on two-dimensional slice images, the fatigue damage parameters of each defect are calculated and ranked, thereby scientifically identifying critical defects. This significantly improves the accuracy of fatigue reliability assessment of additively manufactured metal parts under actual working conditions, providing a quantifiable and operable technical basis for quality control and life prediction. Attached Figure Description

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 A flowchart illustrating a method for identifying critical defects in additively manufactured metal parts based on defect geometry features, provided in an embodiment of the present invention; Figure 2 A schematic diagram of the fracture surface of a component with multiple defects, provided for an embodiment of the present invention; Figure 3 A functional block diagram of a key defect identification device for additive manufacturing metal parts based on defect geometry features provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0019] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0020] The following detailed description of some embodiments of the present invention is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0021] Example 1 Figure 1 A flowchart illustrating a method for identifying critical defects in additively manufactured metal parts based on defect geometry features, as provided in this embodiment of the invention, is shown below. Figure 1 As shown, the method specifically includes the following steps: Step S102: Construct a fatigue damage parameter model to characterize the defect risk level of the target batch of additively manufactured metal parts.

[0022] The input data of the fatigue damage parameter model includes: the nominal stress of the defect and the target geometric characteristic parameters; the output data of the fatigue damage parameter model includes: the fatigue damage parameters of the defect.

[0023] Specifically, this invention pre-establishes batch-specific fatigue damage parameter models to quantify the potential hazards of different defects under specific service conditions. The data for constructing the fatigue damage parameter model is obtained by conducting fatigue tests on multiple test samples with fatigue properties consistent with the target batch of additively manufactured metal parts under the same or equivalent service conditions. The fatigue life distribution is then acquired, and the fracture surfaces of the samples are analyzed. Based on the measured data, a model that correlates the fatigue damage parameters of the defect with the target geometric features and nominal stress of the defect can be fitted. The target geometric feature parameters represent the set of parameters most highly correlated with fatigue life, consisting of size parameters, position parameters, shape parameters, and orientation parameters.

[0024] In this embodiment of the invention, the fatigue damage parameter model is not a general theoretical model, but a model calibrated based on experimental data of the same batch of samples. It fully considers the unique defect types of additive manufacturing (such as incomplete fusion, spheroidized pores, and porosity clusters) and their coupling with the microstructure, thereby improving the accuracy of prediction.

[0025] Step S104: Obtain multiple two-dimensional slice images of the target component and extract the target geometric feature parameters of each defect in each two-dimensional slice image.

[0026] The target component refers to any component in the target batch of additively manufactured metal components.

[0027] Specifically, a full-volume scan of the target component is performed using high-resolution X-ray computed tomography (XCT). It is important to note that during XCT scanning, the two-dimensional slice plane must be perpendicular to the load direction of the component to obtain a series of continuous two-dimensional slice images. Next, a pixel-scanning method is used to measure the defects in each two-dimensional slice image to obtain the target geometric feature parameters of each defect. In other words, the geometric feature parameters extracted in this step are consistent with the parameter system used for modeling in step S102, ensuring matching with the dimensions of the model input variables.

[0028] Step S106: Based on the preset loading load of the target component and the cross-sectional area of ​​the component in the target two-dimensional slice image, calculate the nominal stress of the defect in the target two-dimensional slice image.

[0029] Here, the target two-dimensional slice image represents any one of the multiple two-dimensional slice images.

[0030] To provide the nominal stress required for the fatigue damage parameter model, it is first necessary to determine the loads that the target component experiences under actual service conditions. (That is, the preset load), and the cross-sectional area of ​​the component in the target two-dimensional slice image perpendicular to the load plane. Next, using the formula Calculate the nominal stress of the defect in the target two-dimensional slice image. Clearly, the nominal stress of all defects in the same two-dimensional slice image is the same.

[0031] Step S108: The nominal stress of the defect and the target geometric feature parameters of the target defect in the two-dimensional slice image of the target are processed using the fatigue damage parameter model to obtain the fatigue damage parameters of the target defect.

[0032] Here, the target defect refers to any defect in the target two-dimensional slice image.

[0033] For each defect identified in step S104, the extracted target geometric feature parameters and the nominal stress at the slice calculated in step S106 are used as inputs and substituted into the fatigue damage parameter model established in S102. The model output is the fatigue damage parameter value of the defect, which can be understood as the relative tendency or risk index of the defect to induce fatigue crack initiation under a given load.

[0034] Step S110: Among the multiple two-dimensional slice images of the target component, the defect with the largest fatigue damage parameter is taken as the critical defect of the target component.

[0035] Step S108 calculates the fatigue damage parameters of each defect in each two-dimensional slice image. Next, the fatigue damage parameters of all defects in the two-dimensional slice images are sorted in descending order, and the defect corresponding to the highest-ranked fatigue damage parameter is designated as the critical defect (or key defect) of the target component. Simultaneously, the spatial location (e.g., slice number, three-dimensional coordinates), geometric features, and fatigue damage parameter values ​​of this defect are recorded to generate a defect assessment report. In other words, based on this embodiment of the invention, all defects are uniformly and quantitatively assessed, achieving a leap from the "qualitative existence" of defects to their "quantitative ranking."

[0036] This invention provides a method for identifying critical defects in additively manufactured metal parts based on defect geometry features. This method, by constructing a fatigue damage parameter model that integrates defect geometry features and service loads, achieves a leap from traditional XCT, which can only identify the existence of defects, to accurately assessing the most dangerous defects, overcoming the problem of lacking quantitative evaluation of defect hazard in existing technologies. By establishing a fatigue damage parameter model, using the nominal stress of each defect and the target geometric feature parameters of each defect extracted based on two-dimensional slice images, the fatigue damage parameters of each defect are calculated and ranked, thereby scientifically identifying critical defects. This significantly improves the accuracy of fatigue reliability assessment of additively manufactured metal parts under actual working conditions, providing a quantifiable and operable technical basis for quality control and life prediction.

[0037] In an optional implementation, step S102 above, which involves constructing a fatigue damage parameter model to characterize the defect risk level of the target batch of additively manufactured metal parts, specifically includes the following steps: Step S1021: Obtain fatigue life and fracture analysis results of multiple test samples after conducting fatigue tests under the same service conditions as the components; wherein, the test samples include any of the following: target batch additively manufactured metal parts, standard fatigue specimens; the fracture analysis results include: nominal stress of defects at the fracture location, size parameters, location parameters, shape parameters and orientation parameters of two-dimensional defects at the fatigue source of the fracture.

[0038] In this embodiment of the invention, two types of test samples are selected: one is additively manufactured metal parts directly from the target batch, and the other is standard fatigue specimens. The standard fatigue specimens are cylindrical specimens with the same cross-section as the target batch of additively manufactured metal parts, using the same printing equipment and raw materials, and exhibiting the same process parameters, heat treatment regime, printing direction, and surface finish. This ensures the consistency of the formed material's properties. This embodiment of the invention does not specifically limit the number of test samples; users can select according to their actual needs. For example, more than three stress levels can be preset, with 3-5 test samples configured for each stress level.

[0039] After determining the test sample, fatigue tests consistent with service conditions are conducted to obtain measured fatigue life with engineering significance. Fracture surface analysis is then performed on the test sample to obtain the results. Fracture surface analysis tools can include scanning electron microscopes, electron microscopes, and metallographic microscopes. Professional technicians can locate the fatigue source by observing the fracture surface. For additive manufacturing materials, the initiation of fatigue cracks is induced by manufacturing defects, i.e., the critical defects of this test sample. Then, its dimensional parameters, location parameters, shape parameters, and orientation parameters are further obtained. According to the nominal stress calculation method provided above, for any test sample, the nominal stress at the fracture location defect can be calculated based on the load applied to the test sample and the cross-sectional area of ​​its fracture surface.

[0040] In one alternative implementation, such as Figure 2 As shown, the dimensional parameters include: the square root of the projected area of ​​the defect in the perpendicular loading direction. The square root of the area of ​​the circumscribed ellipse of the defect The maximum distance between two points on the defect profile .

[0041] The embodiments of the present invention use Murakami parameters. The defect size is characterized as the square root of the projected area of ​​the defect in the direction perpendicular to the loading. Since a defect rapidly transforms into an ellipse once it begins to expand, the square root of the area of ​​the circumscribed ellipse is defined as the effective size. Additionally, the Feret diameter is used. The defect size is characterized by the maximum distance between two points on the defect profile.

[0042] Location parameters include: the shortest distance from the defect profile to the specimen surface. Geometric center of defect Distance to the sample surface .

[0043] Specifically, in embodiments of the present invention, based on the geometric center of the defect... Distance to the sample surface To indicate the location of the defect on the fracture surface, based on the shortest distance from the defect profile to the specimen surface. To define internal defects, near-surface defects, and surface defects. Specifically, when... When, it is an internal defect, when When, it is a near-surface defect, when At this time, it is a surface defect.

[0044] Shape parameters include: roundness calculated from the defect's projected area and perimeter. The roundness is calculated by combining the defect's projected area with the maximum distance from its geometric center to the defect's edge. .

[0045] Roundness ,in, This represents the projected area of ​​the defect in the direction perpendicular to the loading direction. This indicates the perimeter of the defect. It is known that irregularly shaped defects typically reduce the fatigue life of parts; therefore, embodiments of the present invention also employ defect roundness. To characterize the shape of the defect: ,in, Indicates the geometric center of the defect The maximum distance to the edge of the defect.

[0046] Orientation parameters include: the acute angle between the extension of the major axis of the defect's circumscribed ellipse and the tangent to the specimen surface. The acute angle between the extended line of the maximum distance between two points on the defect profile and the tangent to the sample surface. .

[0047] Step S1022: Based on the fatigue life and fracture analysis results of multiple test samples, select one geometric feature parameter that has the highest correlation with fatigue life from each of the size parameter, position parameter, shape parameter and orientation parameter, and use it as the target geometric feature parameter.

[0048] To identify the key geometric variables dominating fatigue damage behavior from multiple types of geometric feature parameters (i.e., size, position, shape, and orientation parameters), achieving dimensionality reduction and mechanism focusing, after obtaining fatigue life and fracture surface analysis results from multiple test samples, the statistical correlation coefficient (e.g., Pearson correlation coefficient) between each type of geometric feature parameter and the measured fatigue life was calculated. Then, the parameter with the highest correlation to fatigue life among each type of geometric feature parameter was selected as the target geometric feature parameter.

[0049] Taking dimensional parameters as an example, known dimensional parameters include: the square root of the projected area of ​​the defect in the perpendicular loading direction. The square root of the area of ​​the circumscribed ellipse of the defect The maximum distance between two points on the defect profile Therefore, this step requires separate calculations. The correlation coefficient X1 with fatigue life The correlation coefficient X2 with fatigue life The correlation coefficient X3 with fatigue life; if X1>X2>X3, then select the appropriate dimension parameter. As target geometric feature parameters. The selection method for target geometric feature parameters among position parameters, shape parameters, and orientation parameters is similar and will not be repeated here.

[0050] Step S1023: The fatigue life, nominal stress of fracture defects, and target geometric characteristic parameters of multiple test samples are fitted using the least squares method to obtain a fatigue damage parameter model.

[0051] In this embodiment of the invention, the fatigue damage parameter model is expressed as follows: , ,in, Indicates fatigue damage parameters, Indicates fatigue life. Indicates nominal stress, , , , This refers to the size, position, shape, and orientation parameters in the target's geometric features. , , , , , Indicates model parameters.

[0052] The fatigue life, nominal stress of defects at the fracture site, and target geometric characteristic parameters of all test samples are combined into a matrix. The unknown parameter values ​​(i.e. model parameters) in the model are determined by fitting the matrix using the least squares method. The specific expression obtained is the fatigue damage parameter model.

[0053] In one alternative implementation, the output data of the fatigue damage parameter model may further include the fatigue life of the target component.

[0054] According to the expression of the fatigue damage parameter model, it can be seen that the fatigue damage parameter model can not only be used to predict the fatigue damage parameters of various defects in a target component, but also, after determining the critical defects of the target component, predict the fatigue life of the target component based on the fatigue damage parameters corresponding to the critical defects. That is, the critical defects... Substitution You can get the corresponding .

[0055] In an optional implementation, step S104 above, which involves acquiring multiple two-dimensional slice images of the target component, specifically includes the following steps: Step S1041: Perform XCT inspection on the target component to obtain multiple initial two-dimensional slice images; wherein, during XCT inspection, the two-dimensional slice plane is perpendicular to the load direction of the target component.

[0056] Step S1042: Preprocess the multiple initial two-dimensional slice images to obtain multiple optimized two-dimensional slice images; wherein, the preprocessing includes: image denoising, grayscale enhancement and edge sharpening.

[0057] Specifically, XCT equipment is used to inspect the target component. To facilitate subsequent damage parameter analysis, the two-dimensional slicing plane must be perpendicular to the load direction of the component during XCT scanning. This yields multiple "virtual two-dimensional slices" (i.e., initial two-dimensional slice images) of the target component and their three-dimensional reconstruction model. To ensure the accuracy of subsequent defect identification, a series of preprocessing operations are required for each initial two-dimensional slice image after obtaining it.

[0058] First, image denoising is performed to suppress image quality degradation caused by X-ray quantum noise, detector electronic noise, and artificial artifacts (such as stripes and spots) introduced during reconstruction. Optionally, non-local mean denoising, bilateral filtering, wavelet thresholding denoising, or a deep learning-based denoising network can be used to process each slice image. Denoising effectively improves the signal-to-noise ratio, reduces random fluctuations while preserving structural details, and is beneficial to the stability of subsequent feature extraction.

[0059] Then, grayscale enhancement processing is performed to improve image contrast, making low-contrast areas (such as the area between small defects and the substrate) easier to distinguish. Optionally, histogram equalization, adaptive histogram equalization, gamma correction, or Retinex-based methods are used to adjust the grayscale dynamic range, thereby enhancing the grayscale difference between defects and non-defects, improving visual recognizability and the sensitivity of automatic recognition algorithms.

[0060] Finally, edge sharpening is performed to enhance the clarity of object boundaries, defect contours, or internal interfaces, compensating for edge degradation caused by scattering, focus blur, or reconstruction blur. Optionally, Laplacian operators, unsharpened masks, or high-boost filters are applied for high-frequency component compensation to make structural boundaries more distinct, which is helpful for accurate segmentation, geometric measurement, and morphological analysis.

[0061] After the above complete process, a set of high-quality, high-fidelity two-dimensional slice image sequences is obtained. Each image can accurately reflect the internal structural features of the target component on the corresponding cross section, and has good noise control, contrast performance and edge sharpness, which meets the needs of subsequent advanced analysis tasks.

[0062] In one optional embodiment, after obtaining the critical defect of the target component, the present invention further includes the following: Obtain a 3D reconstruction model of the defects in the target component; based on the 3D reconstruction model and the fatigue damage parameters of all defects in the target component, generate a visualization result of the defects in the target component; the visualization result marks the spatial location of critical defects and the target geometric feature parameters in the 3D reconstruction model, and displays the risk level distribution map of different defects in a color-coded manner.

[0063] XCT technology can be used to obtain a 3D reconstruction model of defects in the target component. After calculating the fatigue damage parameters of each defect in each 2D slice image of the target component, the spatial coordinates of each defect can be determined based on the position of each 2D slice image and the position of each defect in the image. Next, the fatigue damage parameters are divided into multiple risk levels using several preset thresholds, and then the corresponding risk level is determined according to the value range of the fatigue damage parameters of each defect in the target component. In the defect visualization results, different risk levels are assigned different colors. Finally, based on the spatial location of each defect, the risk level of each defect is displayed in a color-coded manner, resulting in a risk level distribution map. For example, low risk (green), medium risk (yellow), high risk (red), critical / urgent (flashing red or black border). Furthermore, the spatial location of critical defects and the target geometric feature parameters are highlighted.

[0064] This invention provides a spatial heatmap representation of defect risk across the entire part, allowing users to intuitively perceive the clustering trend of high-risk areas. Color coding enables a clear understanding of the risk situation, facilitating rapid determination of whether rework, scrapping, or monitoring is necessary. Furthermore, all visualized elements can be traced back to the original slice images and inspection data, ensuring the reliability of the results.

[0065] Example 2 This invention also provides a critical defect identification device for additively manufactured metal parts based on defect geometry features. This device is mainly used to execute the critical defect identification method for additively manufactured metal parts based on defect geometry features provided in Embodiment 1 above. The device provided in this invention will be described in detail below.

[0066] Figure 3 A functional block diagram of a critical defect identification device for additively manufactured metal parts based on defect geometry features provided in an embodiment of the present invention is shown below. Figure 3 As shown, the device mainly includes: a construction module 10, an acquisition module 20, a calculation module 30, a processing module 40, and a determination module 50, wherein: Module 10 is used to construct a fatigue damage parameter model to characterize the defect risk level of additively manufactured metal parts in a target batch. The input data of the fatigue damage parameter model includes the nominal stress of the defect and the geometric feature parameters of the target. The output data of the fatigue damage parameter model includes the fatigue damage parameters of the defect.

[0067] The acquisition module 20 is used to acquire multiple two-dimensional slice images of the target part and extract the target geometric feature parameters of each defect in each two-dimensional slice image; wherein, the target part refers to any part in the target batch of additively manufactured metal parts.

[0068] The calculation module 30 is used to calculate the nominal stress of the defect in the target two-dimensional slice image based on the preset loading load of the target component and the cross-sectional area of ​​the component in the target two-dimensional slice image; wherein, the target two-dimensional slice image represents any two-dimensional slice image among multiple two-dimensional slice images.

[0069] The processing module 40 is used to process the nominal stress of the defect and the target geometric feature parameters of the target defect in the target two-dimensional slice image using the fatigue damage parameter model to obtain the fatigue damage parameters of the target defect; wherein, the target defect represents any defect in the target two-dimensional slice image.

[0070] The determination module 50 is used to identify the defect with the largest fatigue damage parameter among multiple two-dimensional slice images of the target component as the critical defect of the target component.

[0071] This invention provides a critical defect identification device for additively manufactured metal parts based on defect geometry features. This device, by constructing a fatigue damage parameter model that integrates defect geometry features and service loads, achieves a leap from traditional XCT, which can only identify the existence of defects, to accurately assessing the most dangerous defects, overcoming the problem of lacking quantitative evaluation of defect hazard in existing technologies. By establishing a fatigue damage parameter model, using the nominal stress of each defect and the target geometric feature parameters of each defect extracted based on two-dimensional slice images, the fatigue damage parameters of each defect are calculated and ranked, thereby scientifically identifying critical defects. This significantly improves the accuracy of fatigue reliability assessment of additively manufactured metal parts under actual working conditions, providing a quantifiable and operable technical basis for quality control and life prediction.

[0072] Optionally, module 10 is specifically used for: Obtain fatigue life and fracture analysis results for multiple test samples after conducting fatigue tests under the same service conditions as the components; wherein, the test samples include any of the following: target batch additively manufactured metal parts, standard fatigue specimens; the fracture analysis results include: nominal stress of defects at the fracture location, size parameters, location parameters, shape parameters, and orientation parameters of two-dimensional defects at the fracture fatigue source.

[0073] Based on the fatigue life and fracture surface analysis results of multiple test samples, one geometric feature parameter with the highest correlation to fatigue life was selected from each of the size parameter, position parameter, shape parameter and orientation parameter as the target geometric feature parameter.

[0074] The fatigue damage parameter model is obtained by fitting the fatigue life, nominal stress of fracture defects, and target geometric characteristic parameters of multiple test samples using the least squares method.

[0075] Optionally, the standard fatigue test specimen is a cylindrical specimen with the same cross-section as the target batch of additively manufactured metal parts, using the same printing equipment and raw materials, and having the same process parameters, heat treatment regime, printing direction, and surface finish.

[0076] Optionally, the dimensional parameters include: the square root of the projected area of ​​the defect in the vertical loading direction, the square root of the area of ​​the circumscribed ellipse of the defect, and the maximum distance between two points on the defect profile.

[0077] The location parameters include: the shortest distance from the defect profile to the sample surface, and the distance from the geometric center of the defect to the sample surface.

[0078] The shape parameters include: the roundness calculated from the defect projection area and the maximum distance from the geometric center to the defect edge, and the roundness calculated from the defect projection area and the defect perimeter.

[0079] Orientation parameters include: the acute angle between the extension of the major axis of the defect's circumscribed ellipse and the tangent to the sample surface, and the acute angle between the extension of the maximum distance between two points on the defect profile and the tangent to the sample surface.

[0080] Optionally, module 20 is specifically used for: XCT inspection is performed on the target component to obtain multiple initial two-dimensional slice images; during XCT inspection, the two-dimensional slice plane is perpendicular to the load direction of the target component.

[0081] Multiple initial two-dimensional slice images are preprocessed to obtain multiple optimized two-dimensional slice images; the preprocessing includes image denoising, grayscale enhancement and edge sharpening.

[0082] Optionally, the output data of the fatigue damage parameter model may also include the fatigue life of the target component.

[0083] Optionally, after obtaining the critical defect of the target component, the device is also used for: Obtain a 3D reconstruction model of the defects in the target component.

[0084] Based on the 3D reconstruction model of the defect and the fatigue damage parameters of all defects in the target component, a defect visualization result of the target component is generated. The visualization result marks the spatial location of the critical defect and the target geometric feature parameters in the 3D reconstruction model of the defect, and displays the risk level distribution map of different defects in a color-coded manner.

[0085] Example 3 See Figure 4This invention provides an electronic device, which includes a processor 60, a memory 61, a bus 62, and a communication interface 63. The processor 60, the communication interface 63, and the memory 61 are connected via the bus 62. The processor 60 is used to execute executable modules, such as computer programs, stored in the memory 61.

[0086] The memory 61 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 63 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc.

[0087] Bus 62 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0088] The memory 61 is used to store programs. After receiving an execution instruction, the processor 60 executes the program. The method executed by the apparatus defined by the process disclosed in any of the foregoing embodiments of the present invention can be applied to the processor 60 or implemented by the processor 60.

[0089] Processor 60 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 60 or by instructions in software form. Processor 60 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 61. Processor 60 reads the information in memory 61 and, in conjunction with its hardware, completes the steps of the above method.

[0090] The computer program product of the method for identifying key defects in additively manufactured metal parts based on defect geometry features provided in this embodiment of the invention includes a computer-readable storage medium storing non-volatile program code executable by a processor. The instructions included in the program code can be used to execute the methods described in the preceding method embodiments. For specific implementation, please refer to the method embodiments, which will not be repeated here.

[0091] In addition, the functional units in the various embodiments of the present invention 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.

[0092] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion 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 invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0093] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0094] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of this invention is in use. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention. In addition, the terms "first," "second," "third," etc., are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0095] Furthermore, terms such as "horizontal," "vertical," and "sag" do not imply that components must be absolutely horizontal or suspended, but rather that they can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal than "vertical," not that the structure must be completely horizontal, but can be slightly tilted.

[0096] In the description of this invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying key defects in additively manufactured metal parts based on defect geometry features, characterized in that, include: A fatigue damage parameter model is constructed to characterize the defect severity of a target batch of additively manufactured metal parts; wherein the input data of the fatigue damage parameter model includes: the nominal stress of the defect and the geometric characteristic parameters of the target; the output data of the fatigue damage parameter model includes: the fatigue damage parameters of the defect; Multiple two-dimensional slice images of the target component are acquired, and the target geometric feature parameters of each defect in each two-dimensional slice image are extracted; wherein, the target component represents any component in the target batch of additively manufactured metal components; Based on the preset loading load of the target component and the cross-sectional area of ​​the component in the target two-dimensional slice image, the nominal stress of the defect in the target two-dimensional slice image is calculated; wherein, the target two-dimensional slice image represents any two-dimensional slice image among the plurality of two-dimensional slice images; The fatigue damage parameter model is used to process the nominal stress of the defect and the target geometric feature parameters of the target defect in the target two-dimensional slice image to obtain the fatigue damage parameters of the target defect; wherein, the target defect represents any defect in the target two-dimensional slice image; Among multiple two-dimensional slice images of the target component, the defect with the largest fatigue damage parameter is taken as the critical defect of the target component.

2. The method for identifying key defects in additively manufactured metal parts based on defect geometry features according to claim 1, characterized in that, A fatigue damage parameter model is constructed to characterize the defect severity of a target batch of additively manufactured metal parts, including: The fatigue life and fracture analysis results of multiple test samples after fatigue testing under the same service conditions as the components are obtained; wherein, the test samples include any of the following: target batch additively manufactured metal parts, standard fatigue specimens; the fracture analysis results include: nominal stress of defects at the fracture location, size parameters, location parameters, shape parameters and orientation parameters of two-dimensional defects at the fatigue source of the fracture; Based on the fatigue life and fracture surface analysis results of the multiple test samples, one geometric feature parameter with the highest correlation to fatigue life was selected from each of the size parameter, position parameter, shape parameter and orientation parameter, and used as the target geometric feature parameter. The fatigue damage parameter model is obtained by fitting the fatigue life, nominal stress of fracture defects, and target geometric characteristic parameters of multiple test samples using the least squares method.

3. The method for identifying key defects in additively manufactured metal parts based on defect geometry features according to claim 2, characterized in that, The standard fatigue specimen is a cylindrical specimen with the same cross-section as the target batch of additively manufactured metal parts, using the same printing equipment and raw materials, and having the same process parameters, heat treatment regime, printing direction, and surface finish.

4. The method for identifying key defects in additively manufactured metal parts based on defect geometry features according to claim 2, characterized in that, Dimensional parameters include: the square root of the projected area of ​​the defect in the vertical loading direction, the square root of the area of ​​the circumscribed ellipse of the defect, and the maximum distance between two points on the defect profile. The location parameters include: the shortest distance from the defect profile to the sample surface, and the distance from the geometric center of the defect to the sample surface; Shape parameters include: roundness calculated from the defect projected area and the maximum distance from the geometric center to the defect edge, and roundness calculated from the defect projected area and the defect perimeter; Orientation parameters include: the acute angle between the extension of the major axis of the defect's circumscribed ellipse and the tangent to the sample surface, and the acute angle between the extension of the maximum distance between two points on the defect profile and the tangent to the sample surface.

5. The method for identifying key defects in additively manufactured metal parts based on defect geometry features according to claim 1, characterized in that, Obtain multiple two-dimensional slice images of the target component, including: XCT detection is performed on the target component to obtain multiple initial two-dimensional slice images; wherein, during XCT detection, the two-dimensional slice plane is perpendicular to the load direction of the target component; The multiple initial two-dimensional slice images are preprocessed to obtain multiple optimized two-dimensional slice images; wherein, the preprocessing includes: image denoising, grayscale enhancement and edge sharpening.

6. The method for identifying key defects in additively manufactured metal parts based on defect geometry features according to claim 1, characterized in that, The output data of the fatigue damage parameter model also includes the fatigue life of the target component.

7. The method for identifying key defects in additively manufactured metal parts based on defect geometry features according to claim 1, characterized in that, After obtaining the critical defect of the target component, the method further includes: Obtain a three-dimensional reconstruction model of the defect in the target component; Based on the three-dimensional reconstruction model of the defect and the fatigue damage parameters of all defects in the target component, a defect visualization result of the target component is generated; wherein, the visualization result marks the spatial location of the critical defect and the target geometric feature parameters in the three-dimensional reconstruction model of the defect, and displays the risk level distribution map of different defects in a color-coded manner.

8. A critical defect identification device for additively manufactured metal parts based on defect geometry features, characterized in that, include: A construction module is used to construct a fatigue damage parameter model to characterize the defect severity of a target batch of additively manufactured metal parts; wherein, the input data of the fatigue damage parameter model includes: the nominal stress of the defect and the target geometric feature parameters; the output data of the fatigue damage parameter model includes: the fatigue damage parameters of the defect; The acquisition module is used to acquire multiple two-dimensional slice images of the target component and extract the target geometric feature parameters of each defect in each two-dimensional slice image; wherein, the target component represents any component in the target batch of additively manufactured metal components; The calculation module is used to calculate the nominal stress of the defect in the target two-dimensional slice image based on the preset loading load of the target component and the cross-sectional area of ​​the component in the target two-dimensional slice image; wherein, the target two-dimensional slice image represents any two-dimensional slice image among the plurality of two-dimensional slice images; The processing module is used to process the nominal stress of the defect and the target geometric feature parameters of the target defect in the target two-dimensional slice image using the fatigue damage parameter model to obtain the fatigue damage parameters of the target defect; wherein, the target defect represents any defect in the target two-dimensional slice image; The determination module is used to identify the defect with the largest fatigue damage parameter among multiple two-dimensional slice images of the target component as the critical defect of the target component.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for identifying key defects in additive manufacturing metal parts based on defect geometry features, as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for identifying key defects in additively manufactured metal parts based on defect geometry features as described in any one of claims 1 to 7.

Images