Integrated large thin-wall die casting defect infiltration evaluation method and device

Abstract

The invention discloses an integrated large thin-wall die casting defect infiltration assessment method and device, and relates to the technical field of die casting process optimizing.The method comprises the steps that a micro-X-ray computed tomography technology is used for imaging an impregnated die casting sample, and two-dimensional and three-dimensional CT images of the sample are obtained, the die casting sample is obtained through vacuum pressure impregnation treatment; segmenting the CT image through a machine learning image segmentation technology, and identifying an aluminum alloy, an air pore and an infiltration sealant in the die casting; measuring the effective atomic number of the sealant material through a dual-energy X-ray quantitative analysis technology so as to identify the infiltrated sealing material; and evaluating the infiltrating effect of the die casting defect.

Description

Technical Field

[0001] The present application relates to the technical field of die casting process optimization, and in particular to a defect infiltration evaluation method and device for an integrated large-scale thin-walled die casting. Background Art

[0002] In modern manufacturing, especially in the fields of automobiles, aerospace, precision instruments, etc., die castings are widely used due to their high integration, good mechanical properties and cost control advantages. However, various defects such as pores and cracks are inevitable in the die casting process. These defects not only affect the aesthetics of the castings, but more importantly, they reduce their mechanical properties and durability, and may even lead to serious safety accidents. Therefore, the detection and repair of die casting defects has become an important technical issue.

[0003] At present, the detection of die casting defects mainly adopts X-ray computed tomography (CT) technology. CT technology uses X-rays to perform tomography on objects and generates a three-dimensional image of the object through a reconstruction algorithm, thereby realizing high-precision detection of the internal structure of the object. In the detection of die casting defects, CT technology can clearly display the pores, cracks and other defects inside the casting, providing an important basis for subsequent repair work. In terms of defect repair, impregnation treatment is a commonly used method. Impregnation treatment immerses the die casting in a solution containing an impregnation sealant, so that the sealant penetrates into the defects inside the casting, and forms a dense filling layer after solidification, thereby improving the sealing and mechanical properties of the casting. At present, commonly used impregnation sealants include polymer materials such as epoxy resin and polyurethane.

[0004] Although CT technology and impregnation treatment have played an important role in die casting defect detection and repair, there are still some defects in the existing technology. In terms of CT imaging, although CdTe sensors are widely used due to their good energy resolution and spatial resolution, their imaging quality may not meet the needs of higher precision in some specific application scenarios. For example, for the detection of tiny defects, higher resolution imaging technology is required to capture finer structural details. In terms of impregnation treatment, existing impregnation sealants may not be able to fully adapt to the needs of different casting materials or process conditions. Different casting materials have different chemical properties and physical properties, which puts higher requirements on the selection of impregnation sealants. In addition, different process conditions (such as temperature, pressure, etc.) may also affect the permeability and curing effect of the impregnation sealant. In addition, the existing impregnation treatment method may have some other problems, such as large amount of impregnation liquid, limited loading capacity, poor stability, etc. These problems not only increase production costs, but also may affect the effect and efficiency of impregnation treatment. Summary of the invention

[0005] The purpose of the present application is to provide a method and device for evaluating defect infiltration of an integrated large thin-walled die casting.

[0006] To achieve the above objectives, this application provides the following solutions: In a first aspect, the present application provides a method for evaluating defect infiltration of a one-piece large thin-walled die casting, comprising: Imaging the die-cast sample after impregnation using micro X-ray computed tomography technology to obtain two-dimensional and three-dimensional CT images of the sample, wherein the die-cast sample is obtained by vacuum pressure impregnation treatment; Segmenting the CT image using machine learning image segmentation technology to identify aluminum alloy, air pores, and infiltration sealant in the die casting; The effective atomic number of the sealant material is determined by dual-energy X-ray quantitative analysis technology to identify the infiltrated sealant material; Evaluate the wetting effect on die casting defects.

[0007] Optionally, the die casting sample is prepared by: selecting a die casting to be evaluated and ensuring that its surface is clean and dry; and pre-treating the die casting to remove any impurities that may affect the impregnation effect.

[0008] Optionally, the step of imaging the die casting sample after impregnation using micro X-ray computed tomography technology comprises: Place the impregnated die casting sample on the scanning table and set the sample's rotation speed and scanning parameters; Collect the projection image of the sample and record it as data on the FPD based on the charge-integrating CdTe sensor; The acquired projection images are processed to reconstruct two-dimensional and three-dimensional CT images of the sample.

[0009] Optionally, the step of segmenting the CT image by using a machine learning image segmentation technique comprises: preparing a CT image dataset containing aluminum alloy, air pores, and infiltrated sealant; Using a random forest classifier to train the dataset to establish an image segmentation model; The image segmentation model is applied to segment the target CT image to identify and distinguish aluminum alloy, air pores and infiltrative sealant.

[0010] Optionally, the step of determining the effective atomic number of the sealant material by dual-energy X-ray quantitative analysis technology to identify the infiltrated sealing material includes: Use photon counting sensors for X-ray scanning and set different X-ray energy thresholds; Calibrate the scan data to eliminate background noise and systematic errors; Based on the calibrated data, the effective atomic number of the sealant material is calculated and compared with the theoretical value to identify the wetted seal material.

[0011] Optionally, the step of evaluating the wetting effect of the die casting defect comprises: Based on the segmented CT images, the distribution of the infiltration sealant in the defects of the die casting is analyzed; Combined with the results of dual-energy X-ray quantitative analysis, the filling effect of the sealant on the defects of the die casting was evaluated; Based on the evaluation results, the final assessment of the defect wetting effect of the die casting is given.

[0012] Optionally, the defect infiltration assessment method for a one-piece large thin-wall die casting further includes: In the CT imaging process, high-resolution X-ray sensors are used to replace CdTe sensors to improve imaging quality; During the impregnation process, other high-efficiency polymer resins are used as impregnation sealants to adapt to the needs of different casting materials or process conditions.

[0013] In a second aspect, the present application provides an integrated large thin-wall die casting defect infiltration assessment device, comprising: An acquisition module, used to image the die-casting sample after impregnation using micro X-ray computed tomography technology to obtain two-dimensional and three-dimensional CT images of the sample, wherein the die-casting sample is obtained by vacuum pressure impregnation treatment; an identification module, for segmenting the CT image by machine learning image segmentation technology to identify aluminum alloy, air pores and infiltration sealant in the die casting; The effective atomic number of the sealant material is determined by dual-energy X-ray quantitative analysis technology to identify the infiltrated sealant material; Evaluation module for assessing the wetting effect on defects in die castings.

[0014] Optionally, the die casting sample is prepared by: selecting a die casting to be evaluated and ensuring that its surface is clean and dry; and pre-treating the die casting to remove any impurities that may affect the impregnation effect.

[0015] Optionally, the acquisition module is further used to: Place the impregnated die casting sample on the scanning table and set the sample's rotation speed and scanning parameters; Collect the projection image of the sample and record it as data on the FPD based on the charge-integrating CdTe sensor; The acquired projection images are processed to reconstruct two-dimensional and three-dimensional CT images of the sample.

[0016] Optionally, the identification module is further used to: preparing a CT image dataset containing aluminum alloy, air pores, and infiltrated sealant; Using a random forest classifier to train the dataset to establish an image segmentation model; The image segmentation model is applied to segment the target CT image to identify and distinguish aluminum alloy, air pores and infiltrative sealant.

[0017] Optionally, the identification module is further used to: Use photon counting sensors for X-ray scanning and set different X-ray energy thresholds; Calibrate the scan data to eliminate background noise and systematic errors; Based on the calibrated data, the effective atomic number of the sealant material is calculated and compared with the theoretical value to identify the wetted seal material.

[0018] Optionally, the assessment module is further used to: Based on the segmented CT images, the distribution of the infiltration sealant in the defects of the die casting is analyzed; Combined with the results of dual-energy X-ray quantitative analysis, the filling effect of the sealant on the defects of the die casting was evaluated; Based on the evaluation results, the final assessment of the defect wetting effect of the die casting is given.

[0019] Optionally, the acquisition module is further used to: In the CT imaging process, high-resolution X-ray sensors are used to replace CdTe sensors to improve imaging quality; During the impregnation process, other high-efficiency polymer resins are used as impregnation sealants to adapt to the needs of different casting materials or process conditions.

[0020] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the defect infiltration assessment method for a one-piece large thin-walled die casting described in any one of the above.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the above-mentioned methods for defect infiltration assessment of large-scale one-piece thin-walled die castings.

[0022] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any one of the above-mentioned one-piece large thin-walled die casting defect infiltration assessment methods.

[0023] According to the specific embodiments provided in this application, this application discloses the following technical effects: This application provides an integrated large-scale thin-wall die casting defect infiltration evaluation method and device, which can realize accurate identification and quantitative analysis of internal defects of die castings, including pores, cracks, etc., and accurately evaluate the infiltration effect of sealants in defects by combining micro X-ray computed tomography technology, machine learning image segmentation technology, dual-energy X-ray quantitative analysis technology and systematic infiltration effect evaluation method. This process not only improves the accuracy and efficiency of the evaluation, but also provides a scientific basis for optimizing the impregnation treatment process, selecting suitable sealant materials, and improving the overall quality and reliability of die castings, thereby significantly enhancing the market competitiveness of the product. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 A schematic diagram of a flow chart of a defect infiltration assessment method for an integrated large thin-walled die casting provided in one embodiment of the present application; Figure 2 One of the principle schematic diagrams of a defect infiltration assessment method for an integrated large thin-walled die casting provided in one embodiment of the present application; Figure 3 A second schematic diagram of the principle of a defect infiltration assessment method for an integrated large thin-walled die casting provided in an embodiment of the present application; Figure 4 A schematic diagram of functional modules of an integrated large thin-wall die casting defect infiltration assessment device provided in one embodiment of the present application; Figure 5 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0027] like Figure 1 As shown, some embodiments of the present application provide a method for evaluating defect infiltration of a one-piece large thin-walled die casting, which includes the following steps 101 to 104. Among them: Step 101, using micro X-ray computed tomography technology to image the die-casting sample after impregnation, to obtain two-dimensional and three-dimensional CT images of the sample, wherein the die-casting sample is obtained by vacuum pressure impregnation treatment.

[0028] In the embodiment of the present application, micro-X-ray computed tomography (Micro-CT) technology is used to obtain the internal structure information of the die casting sample after impregnation. Micro-X-ray CT is a high-resolution imaging technology, which is particularly suitable for small objects or occasions requiring fine structural analysis. Its working principle is that X-rays are emitted by an X-ray source, and the X-rays are received by the detector after penetrating the sample. Since different substances have different absorption capacities for X-rays, the data collected by the detector can reconstruct two-dimensional and three-dimensional images of the sample.

[0029] Two-dimensional CT images provide a view of the internal structure of a sample on a certain plane, which helps to observe the layered structure or details of a specific layer of the sample.

[0030] Three-dimensional CT images are created by superimposing multiple two-dimensional images to construct a three-dimensional model of the sample, thereby providing a comprehensive understanding of the internal structure of the sample, including pores, cracks, inclusions, etc.

[0031] The die casting samples have been subjected to vacuum pressure impregnation, which means that the interior of the samples may have been filled with some kind of sealant to reduce porosity and cracks.

[0032] X-ray computed tomography A includes: recording the projection image of the die casting infiltrated sample on the FPD based on the charge-integrating CdTe sensor, setting the sample rotation speed ω, and rotating the sample 360°. Before acquiring the projection data of the alloy sample, the flat panel detector (FPD) was calibrated at 6 different x-ray tube currents, and the number of projection images n1 of each sample was recorded at a speed of 30 to 60 frames per second. The distance from the X-ray source to the sample is x1, the distance from the X-ray source to the sensor is x2, and all projection images are captured using the same X-ray tube. A cone beam CT type is used, such as Figure 2The captured projection image is processed to obtain a CT cross-sectional image of the sample, and 2D and 3D CT images of the sample are obtained.

[0033] like Figure 3 As shown, X-ray computed tomography B is performed using a photon counting sensor. After calibrating the background data, the rotation speed ω is set to capture the projection image of the ROI (region of interest) in sample 1 over 360° at a rotation rate of ω. Four different X-ray energy thresholds (above 15, 20, 40, and 60 keV) are defined, and the number of projection images n2 is obtained. Then, FBP is used to construct the corresponding CT images of the low-energy and high-energy windows.

[0034] Step 102 , segmenting the CT image by machine learning image segmentation technology to identify aluminum alloy, air pores and infiltration sealant in the die casting.

[0035] In the present application, machine learning image segmentation technology is used to automatically identify and separate different components in CT images. Image segmentation is a process of dividing an image into multiple regions or objects, each of which has similar characteristics. In the segmentation of die casting CT images, the goal is to identify and separate aluminum alloy, air pores, and infiltrative sealants.

[0036] The machine learning model is trained to learn and recognize different features in the image, such as color, texture, shape, etc. In the segmentation of die casting CT images, the model needs to learn to distinguish the different features of aluminum alloy, air pores and sealants. Once the model is trained, it can be used to automatically segment CT images. The model will identify the aluminum alloy area, air pore area and sealant area in the image and mark them separately.

[0037] Step 103, determining the effective atomic number of the sealant material by dual energy X-ray quantitative analysis technology to identify the infiltrated sealant material.

[0038] In the embodiment of the present application, dual-energy X-ray quantitative analysis technology is used to determine the effective atomic number of the sealant material. Dual-energy X-ray technology uses two X-ray beams of different energies to irradiate the sample. Since different elements have different absorption capabilities for X-rays of different energies, the atomic number of the elements in the sample can be calculated by measuring the attenuation of the X-rays at the two energies.

[0039] The effective atomic number is a comprehensive indicator of a material's ability to absorb X-rays, and is related to the atomic number and content of the various elements in the material. By measuring the effective atomic number of the sealant material, its composition and properties can be further confirmed.

[0040] Based on the linear attenuation coefficients of the low and high energy windows of the aluminum alloy and sealant in the casting defect area of ​​the sample, the derived effective atomic number values ​​Z4 are calculated using formula (1). These derived effective atomic number values ​​are then compared with their theoretical effective atomic number values ​​to identify the wetted sealing material. Formula (1) is as follows: Z4=(µ(E2)G(E1,Z) - µ(E1)G(E2,Z)) / (µ(E1)F(E2,Z) - µ(E2)F(E1,Z)) (1) Among them, µ(E1) and µ(E2) represent the linear attenuation coefficients related to the low and high energy windows, G(E1, Z) and G(E2, Z) are the electron cross sections of the scattering terms in the two energy windows, and F(E1, Z) and F(E2, Z) represent the photoelectric effects in the low and high energy windows, respectively.

[0041] Step 104 , evaluating the wetting effect of the die casting defects.

[0042] In the embodiment of the present application, the wetting effect of the die casting defects is evaluated based on the CT image obtained in the previous step and the effective atomic number of the sealant material. The wetting effect refers to the degree and effect of the sealant filling the internal defects (such as pores, cracks, etc.) of the die casting.

[0043] First, the location and morphology of defects inside the die casting can be identified through CT images. Then, the filling degree and distribution of the sealant in the defect can be evaluated by combining the effective atomic number of the sealant material and the segmentation results in the CT image. If the sealant can evenly fill the defect and cover its surface, the infiltration effect is considered to be good; conversely, if the sealant is incompletely filled or unevenly distributed, the infiltration effect needs to be further improved.

[0044] The embodiment of the present application combines micro X-ray computed tomography technology, machine learning image segmentation technology, dual-energy X-ray quantitative analysis technology and a systematic infiltration effect evaluation method to achieve accurate identification and quantitative analysis of internal defects of die castings, including pores, cracks, etc., and accurately evaluate the infiltration effect of sealants in defects. This process not only improves the accuracy and efficiency of the evaluation, but also provides a scientific basis for optimizing the impregnation treatment process, selecting suitable sealant materials, and improving the overall quality and reliability of die castings, thereby significantly enhancing the market competitiveness of the product.

[0045] Optionally, the die casting sample is prepared by selecting the die casting to be evaluated and ensuring that its surface is clean and dry, and pre-treating the die casting to remove any impurities that may affect the impregnation effect.

[0046] In the embodiments of the present application, these die-cast parts may have potential internal defects due to production process, material batch or other factors, and their ability to be wetted by the sealant needs to be verified through subsequent steps.

[0047] Before any pretreatment or impregnation treatment, it is critical to ensure that the surface of the die casting is clean and dry. Oil, dust or other impurities on the surface may hinder the effective infiltration of the sealant and affect the accuracy of the evaluation results. Therefore, it is usually necessary to clean it with an appropriate detergent and water or organic solvent, and ensure that the surface is thoroughly dry by natural air drying or using drying equipment.

[0048] The pretreatment step is intended to remove any impurities that may be present on the surface and inside of the die casting, which may include but are not limited to oxides, residual grease, tiny metal fragments, etc., which may have a negative impact on the subsequent impregnation process. Pretreatment methods may include pickling, alkaline cleaning, ultrasonic cleaning, etc., depending on the material of the die casting, the surface condition, and the type of impurities to be removed. The pretreatment process may also include removing surface roughness or performing other surface modifications to improve the adhesion between the sealant and the die casting.

[0049] Optionally, the step 101 includes: Step 1011, placing the impregnated die casting sample on a scanning table, and setting the rotation speed and scanning parameters of the sample.

[0050] In the embodiment of the present application, the die casting sample that has been impregnated (i.e., filled with sealant) is carefully placed on the scanning table of a micro X-ray computed tomography (CT) device. This step requires ensuring that the sample is placed stably to avoid movement during the scanning process, thereby affecting the image quality.

[0051] Next, the sample's rotation speed and scanning parameters are set according to the sample's material, size, and expected scanning resolution and contrast. The rotation speed is usually determined based on the performance of the scanning equipment and the complexity of the sample to ensure that a sufficient number of projection images are obtained in a reasonable time. The scanning parameters include X-ray energy, exposure time, scanning range, etc. The selection of these parameters is crucial to obtaining high-quality CT images.

[0052] Step 1012, collecting a projection image of the sample and recording it as data on a FPD based on a charge-integrating CdTe sensor.

[0053] In the embodiment of the present application, after the scanning parameters are set, the scanning program is started, and the X-ray source starts to emit X-rays and penetrate the sample. After passing through the sample, these X-rays are captured by the FPD based on the charge-integrating CdTe sensor.

[0054] FPD is a high-resolution digital imaging device that can convert received X-rays into electrical signals and record them. The charge-integrating CdTe sensor has excellent energy resolution and spatial resolution, which can accurately capture the subtle differences in the internal structure of the sample and provide high-quality raw data for subsequent image reconstruction.

[0055] Step 1013: Process the acquired projection images to reconstruct two-dimensional and three-dimensional CT images of the sample.

[0056] In the embodiments of the present application, the projection images recorded on the FPD are processed using advanced image processing algorithms and reconstruction techniques. These processing steps may include image denoising, correction, enhancement, etc. to improve the quality and clarity of the image. Subsequently, the processed projection images are converted into two-dimensional and three-dimensional CT images of the sample through CT image reconstruction algorithms (such as filtered back projection, iterative reconstruction, etc.). These images can intuitively show the detailed structure inside the sample, including the aluminum alloy matrix, air pores, infiltration sealant, and the interface relationship between them. The reconstructed CT image not only provides an intuitive basis for the subsequent evaluation of the infiltration effect, but can also be used for further analysis and measurement, such as porosity calculation, sealant filling degree evaluation, etc.

[0057] Optionally, the step 102 includes: Step 1021 , preparing a CT image dataset including aluminum alloy, air pores, and infiltrative sealant.

[0058] In an embodiment of the present application, it is first necessary to collect a series of die-casting sample images acquired by micro X-ray computed tomography (CT). These images should include a clear display of different components and structures such as the aluminum alloy matrix, air pores, and sealants after infiltration. The preparation of the data set is the basis of the machine learning image segmentation task. In order to ensure the generalization ability of the model, the data set should be as diverse as possible, including die-casting sample images of different materials, sizes, defect types, and degrees of infiltration. Preprocessing the data set is also one of the key steps, which may include image enhancement, normalization, annotation, etc. In particular, for the annotation work, professionals are required to accurately annotate the aluminum alloy, air pores, and infiltration sealants in each image to provide accurate supervision information for subsequent model training.

[0059] Step 1022: Use a random forest classifier to train the data set to establish an image segmentation model.

[0060] In the embodiment of the present application, random forest is an ensemble learning method that improves the accuracy of classification or regression by constructing multiple decision trees and combining their prediction results. In image segmentation tasks, random forest classifiers can be used to classify pixels or voxels and distinguish different tissue structures or materials.

[0061] The preprocessed CT image dataset is fed into a random forest classifier for training. During the training process, the classifier learns how to distinguish aluminum alloy, air pores, and infiltrative sealants based on image features such as grayscale value, texture, shape, etc.

[0062] By continuously adjusting the parameters of the classifier (such as the number of trees, maximum depth, splitting criteria, etc.) and using strategies such as cross-validation to evaluate the performance of the model, we ultimately obtain an image segmentation model that can accurately segment different components in CT images.

[0063] Step 1023, applying the image segmentation model to segment the target CT image, identifying and distinguishing aluminum alloy, air pores and infiltration sealant.

[0064] In an embodiment of the present application, after the model training is completed, it can be applied to a new target CT image for segmentation. The target CT image is input into the trained image segmentation model. The model will classify each pixel or voxel in the image according to the learned knowledge, and distinguish different components such as aluminum alloy, air pores and infiltration sealant. The segmentation results are usually displayed in the form of an image, in which different components are represented by different colors or grayscale levels for easy observation and analysis. By comparing the segmentation results with the original image or annotation information, the segmentation accuracy and robustness of the model can be evaluated.

[0065] Optionally, the step 103 includes: Step 1031 , use a photon counting sensor to perform X-ray scanning and set different X-ray energy thresholds.

[0066] In an embodiment of the present application, a photon counting sensor is used as an X-ray detector to perform X-ray scanning of a die-casting sample. The photon counting sensor can accurately record the energy of each incident photon, thereby achieving high-sensitivity and high-resolution X-ray imaging. During the scanning process, different X-ray energy thresholds are set to obtain the response of the sample at different energy levels. Different materials have different absorption and scattering characteristics of X-rays, so by changing the X-ray energy, more information about the internal structure and composition of the sample can be obtained. Setting the energy threshold also helps to distinguish materials with different atomic numbers. The interaction between X-rays and matter (such as Compton scattering, photoelectric effect, etc.) is closely related to the atomic number of the material, so by adjusting the energy threshold, the signal of certain materials can be selectively enhanced or suppressed.

[0067] Step 1032, calibrate the scan data to eliminate background noise and system errors.

[0068] In the embodiment of the present application, after acquiring the X-ray scanning data, data calibration is required to eliminate background noise and system errors. Background noise may come from the dark current of the detector itself, environmental radiation, etc., while system errors may be caused by factors such as equipment instability and inaccurate calibration.

[0069] The calibration process usually includes dark current correction, gain correction, energy scale correction and other steps. Dark current correction is used to eliminate the output signal of the detector when there is no X-ray incident; gain correction is used to adjust the output signal intensity of different energy channels to make it linearly related to the X-ray energy; energy scale correction is used to ensure that the energy value output by the detector is consistent with the actual X-ray energy. Through calibration, the accuracy and reliability of the data can be improved, providing a solid foundation for subsequent analysis and processing.

[0070] Step 1033, calculate the effective atomic number of the sealant material based on the calibrated data and compare it with the theoretical value to identify the wettable sealant material.

[0071] In an embodiment of the present application, after completing the data calibration, the calibrated data is used to calculate the effective atomic number of the sealant material. The effective atomic number is a physical quantity that reflects the material's ability to absorb X-rays and is related to the material's atomic number and density. By analyzing the X-ray transmission data at different energy thresholds, the effective atomic number of the sealant material can be calculated. This calculation process usually involves complex physical models and algorithms, such as the Compton scattering model, the photoelectric effect model, and the like. Finally, the calculated effective atomic number is compared with the theoretical value. If the two match or are close, it can be confirmed that the corresponding part in the scan result is composed of the expected wetted sealing material. If there is a difference, it may be necessary to further check whether there is a problem with the scanning conditions, the calibration process, or the sample itself.

[0072] Optionally, the step 104 includes: Step 1041 , analyzing the distribution of the infiltrative sealant in the defects of the die casting based on the segmented CT image.

[0073] In the embodiment of the present application, the CT image is first processed using the aforementioned image segmentation technology (such as random forest classifier, etc.) to separate the different components such as the aluminum alloy matrix, air pores and infiltration sealant. In this way, the specific distribution of the infiltration sealant inside the die casting can be clearly seen.

[0074] When analyzing the distribution of the infiltrative sealant, attention should be paid to its filling degree in defects (such as pores, cracks, etc.), distribution morphology, and whether there are unfilled or unevenly filled areas. This information is crucial for evaluating the infiltration effect of the sealant.

[0075] By observing and analyzing the segmented CT images, we can intuitively understand the penetration ability of the infiltration sealant in the defects of the die casting, the filling effect and the combination with the matrix material, providing an intuitive visual basis for subsequent evaluation.

[0076] Step 1042 , combining the result of dual-energy X-ray quantitative analysis, evaluating the filling effect of the sealant on the defects of the die casting.

[0077] In the embodiment of the present application, dual-energy X-ray quantitative analysis is an advanced detection technology that can distinguish and quantify different components in a sample by using the different absorption characteristics of X-rays of different energies on a substance. In this step, the dual-energy X-ray quantitative analysis technology will be used to scan the die casting sample to obtain quantitative data on the sealant filling effect.

[0078] By analyzing the dual-energy X-ray scanning data, key parameters such as the filling ratio of the sealant in the defect, density distribution, and relative content with the base material can be calculated. These data provide an objective and quantitative basis for evaluating the filling effect of the sealant.

[0079] Combining the results of dual-energy X-ray quantitative analysis with the segmented CT images can more comprehensively evaluate the effect of the sealant on the defects of the die casting. For example, it can be observed whether the sealant completely fills the defect space, how uniform the filling is, and whether there is any residual air or other impurities.

[0080] Step 1043, based on the evaluation results, a final evaluation of the die casting defect wetting effect is given.

[0081] In the embodiment of the present application, after completing the detailed analysis of the distribution of the infiltration sealant and the filling effect, it is necessary to give a final assessment of the infiltration effect of the die casting defects based on the evaluation results. This assessment should comprehensively consider the results of the segmented CT image observations, dual-energy X-ray quantitative analysis data, and other possible detection methods (such as mechanical properties testing, microstructure observation, etc.).

[0082] The evaluation results should clearly indicate the degree of filling of die casting defects by the sealant, whether the wetting effect meets the expected requirements, and whether there are potential quality problems or room for improvement. At the same time, targeted suggestions or measures can be put forward based on the evaluation results to optimize the impregnation process and improve product quality and reliability.

[0083] Optionally, the one-piece large thin-wall die casting defect infiltration assessment method further includes: in the CT imaging process, using a high-resolution X-ray sensor to replace the CdTe sensor to improve the imaging quality. In the impregnation process, using other high-efficiency polymer resins as infiltration sealants to meet the needs of different casting materials or process conditions.

[0084] In the embodiment of the present application, in CT imaging technology, the choice of sensor has a crucial impact on the imaging quality. CdTe (cadmium telluride) sensors are widely used in the field of X-ray imaging due to their good energy resolution and spatial resolution. However, in certain specific application scenarios, higher resolution imaging may be required to capture finer structural details. It is decided to use high-resolution X-ray sensors to replace CdTe sensors to improve the quality of CT imaging. High-resolution sensors generally have smaller pixel sizes and higher sensitivity, and can capture more detailed information, thereby generating clearer images. The selection of alternative sensors needs to be based on specific application requirements, cost considerations, and the feasibility of existing technologies. Once selected, the CT imaging system needs to be upgraded or modified accordingly to ensure that the new sensor can work properly and integrate with the existing system. By adopting high-resolution X-ray sensors, it is expected that more detailed structural information, higher contrast, and lower noise levels can be obtained during CT imaging, thereby improving the ability to identify features such as internal defects and material distribution of die castings.

[0085] Impregnation is a commonly used surface treatment technology to improve the sealing, corrosion resistance and mechanical properties of castings. During the impregnation process, the choice of impregnation sealant is crucial to the final treatment effect. It is decided to use other high-efficiency polymer resins as impregnation sealants to replace the materials that may have been used before. This decision may be based on considerations of different casting material properties, the need to adapt to specific process conditions, or the pursuit of optimization of sealant performance. When selecting a new polymer resin as an impregnation sealant, factors such as its chemical stability, compatibility with casting materials, curing speed, sealing performance, and cost-effectiveness need to be considered. In addition, sufficient testing and verification are required to ensure that the new sealant can meet the expected treatment effect and quality requirements. By using other high-efficiency polymer resins as impregnation sealants, it can be expected to better adapt to the needs of different casting materials or process conditions, improve the effect and efficiency of impregnation treatment, and further improve the quality and performance of castings.

[0086] Based on the same inventive concept, the embodiment of the present application also provides an integrated large thin-walled die casting defect infiltration assessment device for implementing the integrated large thin-walled die casting defect infiltration assessment method mentioned above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more integrated large thin-walled die casting defect infiltration assessment devices provided below can refer to the limitations of the integrated large thin-walled die casting defect infiltration assessment method above, and will not be repeated here.

[0087] In an exemplary embodiment, Figure 4As shown, an integrated large thin-wall die casting defect infiltration assessment device 20 is provided, comprising: An acquisition module 201 is used to image the die-casting sample after impregnation using micro X-ray computed tomography technology to obtain two-dimensional and three-dimensional CT images of the sample, wherein the die-casting sample is obtained by vacuum pressure impregnation treatment; An identification module 202 is used to segment the CT image by machine learning image segmentation technology to identify aluminum alloy, air pores and infiltration sealant in the die casting; The effective atomic number of the sealant material is determined by dual-energy X-ray quantitative analysis technology to identify the infiltrated sealant material; The evaluation module 203 is used to evaluate the wetting effect of the die casting defects.

[0088] Optionally, the die casting sample is prepared by: selecting a die casting to be evaluated and ensuring that its surface is clean and dry; and pre-treating the die casting to remove any impurities that may affect the impregnation effect.

[0089] Optionally, the acquisition module 201 is further used to: Place the impregnated die casting sample on the scanning table and set the sample's rotation speed and scanning parameters; Collect the projection image of the sample and record it as data on the FPD based on the charge-integrating CdTe sensor; The acquired projection images are processed to reconstruct two-dimensional and three-dimensional CT images of the sample.

[0090] Optionally, the identification module 202 is further configured to: preparing a CT image dataset containing aluminum alloy, air pores, and infiltrated sealant; Using a random forest classifier to train the dataset to establish an image segmentation model; The image segmentation model is applied to segment the target CT image to identify and distinguish aluminum alloy, air pores and infiltrative sealant.

[0091] Optionally, the identification module 202 is further configured to: Use photon counting sensors for X-ray scanning and set different X-ray energy thresholds; Calibrate the scan data to eliminate background noise and systematic errors; Based on the calibrated data, the effective atomic number of the sealant material is calculated and compared with the theoretical value to identify the wetted seal material.

[0092] Optionally, the assessment module 203 is further used to: Based on the segmented CT images, the distribution of the infiltration sealant in the defects of the die casting is analyzed; Combined with the results of dual-energy X-ray quantitative analysis, the filling effect of the sealant on the defects of the die casting was evaluated; Based on the evaluation results, the final assessment of the defect wetting effect of the die casting is given.

[0093] Optionally, the acquisition module 201 is further used to: In the CT imaging process, high-resolution X-ray sensors are used to replace CdTe sensors to improve imaging quality; During the impregnation process, other high-efficiency polymer resins are used as impregnation sealants to adapt to the needs of different casting materials or process conditions.

[0094] The embodiment of the present application combines micro X-ray computed tomography technology, machine learning image segmentation technology, dual-energy X-ray quantitative analysis technology and a systematic infiltration effect evaluation method to achieve accurate identification and quantitative analysis of internal defects of die castings, including pores, cracks, etc., and accurately evaluate the infiltration effect of sealants in defects. This process not only improves the accuracy and efficiency of the evaluation, but also provides a scientific basis for optimizing the impregnation treatment process, selecting suitable sealant materials, and improving the overall quality and reliability of die castings, thereby significantly enhancing the market competitiveness of the product.

[0095] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store one-piece large thin-walled die-casting defect infiltration assessment data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a one-piece large thin-walled die-casting defect infiltration assessment method is implemented.

[0096] Those skilled in the art will understand that Figure 5The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0097] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0098] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0099] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0100] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0101] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0102] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0103] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0104] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A defect infiltration assessment method for a one-piece large thin-wall die casting, characterized in that: The defect infiltration evaluation method of the one-piece large thin-walled die casting comprises: Imaging the die-cast sample after impregnation using micro X-ray computed tomography technology to obtain two-dimensional and three-dimensional CT images of the sample, wherein the die-cast sample is obtained by vacuum pressure impregnation treatment; Segmenting the CT image using machine learning image segmentation technology to identify aluminum alloy, air pores, and infiltration sealant in the die casting; The effective atomic number of the sealant material is determined by dual-energy X-ray quantitative analysis technology to identify the infiltrated sealant material; Evaluate the wetting effect on die casting defects.

2. The defect infiltration evaluation method of a one-piece large thin-walled die casting according to claim 1 is characterized in that: The die casting samples are prepared by selecting the die castings to be evaluated and ensuring that their surfaces are clean and dry; and pre-treating the die castings to remove any impurities that may affect the impregnation effect.

3. The defect infiltration evaluation method of a one-piece large thin-walled die casting according to claim 1, characterized in that: The step of imaging the die casting sample after impregnation using micro X-ray computed tomography technology comprises: Place the impregnated die casting sample on the scanning table and set the sample's rotation speed and scanning parameters; Collect the projected image of the sample and record it as data on the FPD based on the charge-integrating CdTe sensor; The acquired projection images are processed to reconstruct two-dimensional and three-dimensional CT images of the sample.

4. The defect infiltration evaluation method of a one-piece large thin-walled die casting according to claim 1, characterized in that: The step of segmenting the CT image by using a machine learning image segmentation technique comprises: preparing a CT image dataset containing aluminum alloy, air pores, and infiltrated sealant; Using a random forest classifier to train the dataset to establish an image segmentation model; The image segmentation model is applied to segment the target CT image to identify and distinguish aluminum alloy, air pores and infiltrative sealant.

5. The defect infiltration evaluation method of a one-piece large thin-walled die casting according to claim 1, characterized in that: The step of determining the effective atomic number of the sealant material by dual-energy X-ray quantitative analysis technology to identify the infiltrated sealant material comprises: Use photon counting sensors for X-ray scanning and set different X-ray energy thresholds; Calibrate the scan data to eliminate background noise and systematic errors; Based on the calibrated data, the effective atomic number of the sealant material is calculated and compared with the theoretical value to identify the wetted seal material.

6. The defect infiltration evaluation method of a one-piece large thin-walled die casting according to claim 1, characterized in that: The step of evaluating the wetting effect of the die casting defect comprises: Based on the segmented CT images, the distribution of the infiltration sealant in the defects of the die casting is analyzed; Combined with the results of dual-energy X-ray quantitative analysis, the filling effect of the sealant on the defects of the die casting was evaluated; Based on the evaluation results, the final assessment of the defect wetting effect of the die casting is given.

7. The defect infiltration evaluation method of a one-piece large thin-walled die casting according to claim 1, characterized in that: The defect infiltration assessment method of the one-piece large thin-walled die casting also includes: In the CT imaging process, high-resolution X-ray sensors are used to replace CdTe sensors to improve imaging quality; During the impregnation process, other high-efficiency polymer resins are used as impregnation sealants to adapt to the needs of different casting materials or process conditions.

8. An integrated large thin-wall die casting defect infiltration assessment device, characterized in that: The one-piece large thin-wall die casting defect infiltration assessment device comprises: An acquisition module, used to image the die-casting sample after impregnation using micro X-ray computed tomography technology to obtain two-dimensional and three-dimensional CT images of the sample, wherein the die-casting sample is obtained by vacuum pressure impregnation treatment; an identification module, for segmenting the CT image by machine learning image segmentation technology to identify aluminum alloy, air pores and infiltration sealant in the die casting; The effective atomic number of the sealant material is determined by dual-energy X-ray quantitative analysis technology to identify the infiltrated sealant material; Evaluation module for assessing the wetting effect on defects in die castings.

9. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the defect infiltration assessment method for a one-piece large thin-walled die casting according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the defect infiltration evaluation method for a one-piece large thin-walled die casting described in any one of claims 1 to 7 are implemented.

Images