Aluminum alloy castings pore defect grading detection method and system

Abstract

The application discloses a method and system for grading detection of pore defects of aluminum alloy castings, and relates to the technical field of casting detection. The method comprises the following steps: performing multi-angle imaging scanning on the aluminum alloy castings to obtain a sequence of tomographic images; performing image enhancement on the sequence of tomographic images, extracting initial feature information of the pore defects, performing segmentation and identification, obtaining pore defect distribution information for morphological analysis, and obtaining pore morphological defect parameters; performing data bidirectional verification according to the pore defect distribution information and the pore morphological defect parameters, constructing a pore multi-level defect array for grade division, and determining a defect grading result; performing quality rating on the aluminum alloy castings according to the defect grading result, and performing automatic sorting according to the quality grade. The technical problems of low detection precision of pore defects of aluminum alloy castings, difficulty in realizing effective grading evaluation, inaccurate quality control, and insufficient sorting efficiency in the prior art are solved, and the technical effects of improving detection precision and sorting efficiency are achieved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of casting detection, in particular to an aluminum alloy casting pore defect grading detection method and system. BACKGROUND

[0002] Aluminum alloy castings are important basic materials in the fields of automobiles and rail transit, and the internal quality of the aluminum alloy castings directly affects the service life and safety performance of products. In the casting process, due to gas entrainment, metal shrinkage or insufficient process control, pore defects often occur inside the castings. The pores not only reduce the mechanical properties of the castings, but also can cause fatigue cracks, which seriously threaten the service reliability of the products. The existing detection methods mostly adopt single-angle X-ray perspective or ultrasonic flaw detection, and often have problems such as fuzzy defect characteristics, high missed detection rate and inability to realize effective grading evaluation, which leads to inaccurate quality control of the castings and low subsequent sorting efficiency. SUMMARY

[0003] The application provides an aluminum alloy casting pore defect grading detection method and system, and solves the technical problems of low detection precision of aluminum alloy casting pore defects, difficulty in realizing effective grading evaluation, inaccurate quality control and insufficient sorting efficiency in the prior art.

[0004] In a first aspect, the application provides an aluminum alloy casting pore defect grading detection method, which comprises the following steps:

[0005] Multi-angle imaging scanning is performed on the aluminum alloy casting to obtain a tomographic image sequence; image enhancement is performed on the tomographic image sequence, initial feature information of pore defects is extracted for segmentation and identification, pore defect distribution information is obtained for morphological analysis, and pore morphological defect parameters are obtained; data bidirectional verification is performed according to the pore defect distribution information and the pore morphological defect parameters, a pore multi-level defect array is constructed for grade division, and a defect grading result is determined; quality grading is performed on the aluminum alloy casting according to the defect grading result, and automatic sorting is performed according to the quality grade.

[0006] In a second aspect, the application provides an aluminum alloy casting pore defect grading detection system, which comprises the following steps:

[0007] The image acquisition module: multi-angle imaging scanning of the aluminum alloy casting is performed to obtain a sequence of tomographic images; the analysis module: image enhancement is performed on the sequence of tomographic images, initial feature information of the pore defect is extracted for segmentation and identification, pore defect distribution information is obtained for morphological analysis, and pore morphological defect parameters are obtained; the grade division module: data bidirectional verification is performed according to the pore defect distribution information combined with the pore morphological defect parameters, a pore multi-level defect array is constructed for grade division, and a defect grading result is determined; and the casting sorting module: quality rating of the aluminum alloy casting is performed according to the defect grading result, and automatic sorting is performed according to the quality level.

[0008] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0009] Firstly, multi-angle imaging scanning of the aluminum alloy casting is performed to obtain a sequence of tomographic images. Then, image enhancement is performed on the sequence of tomographic images, initial feature information of the pore defect is extracted for segmentation and identification, pore defect distribution information is obtained for morphological analysis, and pore morphological defect parameters are obtained. Then, data bidirectional verification is performed according to the pore defect distribution information combined with the pore morphological defect parameters, a pore multi-level defect array is constructed for grade division, and a defect grading result is determined. Finally, quality rating of the aluminum alloy casting is performed according to the defect grading result, and automatic sorting is performed according to the quality level. The technical problems of low detection precision of the pore defect of the aluminum alloy casting and difficulty in effective grading evaluation in the prior art are solved, which leads to inaccurate quality control and insufficient sorting efficiency, and the technical effects of improving detection precision and sorting efficiency are achieved. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0011] Figure 1 A flowchart of the aluminum alloy casting pore defect grading detection method provided by the embodiment of the present application is shown.

[0012] Figure 2 A structural schematic diagram of the aluminum alloy casting pore defect grading detection system provided by the embodiment of the present application is shown.

[0013] Legend of the drawings: image acquisition module 11, analysis module 12, grade division module 13, and casting sorting module 14. DETAILED DESCRIPTION

[0014] The application provides a method and system for grading detection of pore defects of aluminum alloy castings, and solves the technical problems of low detection accuracy of pore defects of aluminum alloy castings, difficulty in realizing effective grading evaluation, inaccurate quality control, and insufficient sorting efficiency in the prior art.

[0015] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the application.

[0016] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion, for example, a process, method, system, product or server comprising a series of steps or units need not be limited to only those steps or units clearly listed, but can include other steps or modules that are not clearly listed or inherent to the process, method, product or device.

[0017] Embodiment one, as shown in the application provides a method for grading detection of pore defects of aluminum alloy castings, wherein the method comprises: Figure 1

[0018] Multi-angle imaging scanning is performed on the aluminum alloy casting to obtain a sequence of tomographic images.

[0019] In the embodiments of the application, a two-dimensional plane coordinate system of the aluminum alloy casting is established, key point analysis is performed on the casting contour, and a plurality of effective imaging field points are determined; center point clustering is performed based on the plurality of effective imaging field points to obtain an effective field center position; the casting is step-rotated scanned by using an X-ray or industrial CT imaging device with the effective field center as a reference, and a plurality of multi-angle projection image sequences are collected at preset angle intervals during the rotation; the multi-angle projection image sequences are converted into cross-sectional tomographic images of the aluminum alloy casting by a back-projection reconstruction algorithm, so that a sequence of tomographic images covering the overall internal structure of the casting is obtained.

[0020] Further, the method for multi-angle imaging scanning on the aluminum alloy casting to obtain a sequence of tomographic images comprises:

[0021] ​A two-dimensional plane coordinate system of the aluminum alloy casting is constructed, key point analysis is performed on the two-dimensional plane coordinate system, and a plurality of effective imaging field points are determined; a center point cluster is performed according to the plurality of effective imaging field points, and an effective field center is determined; the aluminum alloy casting is scanned according to the effective field center combined with the plurality of effective imaging field points, and an initial two-dimensional projection image is constructed; the initial two-dimensional projection image is step-rotated scanned according to the effective field center, and a multi-angle image acquisition sequence is obtained; the cross-sectional image of the aluminum alloy casting is reconstructed according to the multi-angle image acquisition sequence, and the sequence of tomographic images is constructed.

[0022] Specifically, the aluminum alloy casting to be detected is fixed on the rotating support table of the industrial CT scanning device, the scanning device includes an X-ray source and a flat panel detector, and the X-ray source and the flat panel detector are arranged opposite to each other; a two-dimensional imaging plane of the detector is used to construct a two-dimensional plane coordinate system of the aluminum alloy casting, and edge detection (for example, using a Canny operator) is performed on the acquired contour projection image to extract a plurality of key points of the outer contour of the casting. The key points are analyzed by traversing the two-dimensional plane coordinate system, a candidate point set covering the imaging area is generated, and a plurality of effective imaging field points are selected according to the spatial distribution characteristics of the candidate points. Then, a clustering algorithm (such as K-means clustering) is used to cluster the plurality of effective imaging field points, the cluster center is determined as the effective field center, and the scanning reference range is determined combined with the plurality of effective imaging field points. Under the constraint of the effective field center, the X-ray source and the detector are controlled to locally scan the aluminum alloy casting to obtain an initial two-dimensional projection image. Then, taking the effective field center as the rotation reference point, the rotating support table is driven to rotate at an angle step of 0.5° to 1° in a 360° manner, and a projection image is acquired at each angle position, thereby obtaining a multi-angle image acquisition sequence. Finally, the multi-angle image acquisition sequence is input into a filtered back-projection algorithm or an algebraic reconstruction technique, and the cross section of the aluminum alloy casting is reconstructed layer by layer to obtain a sequence of tomographic images covering the overall internal structure.

[0023] The sequence of tomographic images is image-enhanced, initial feature information of the pore defect is extracted for segmentation and recognition, distribution information of the pore defect is obtained for morphological analysis, and pore morphological defect parameters are obtained.

[0024] Further, the sequence of tomographic images is image-enhanced, initial feature information of the pore defect is extracted for segmentation and recognition, and distribution information of the pore defect is obtained, the method comprising:

[0025] The non-local mean filtering is performed on the sequence of tomographic images to extract a plurality of image edge structures; the sequence of tomographic images is subjected to contrast enhancement according to the plurality of image edge structures to generate a set of contrast-enhanced images; the sequence of tomographic images is subjected to feature preliminary screening based on the set of contrast-enhanced images in combination with historical pore defect images to determine initial feature information of pore defects; boundary recognition is performed based on the initial feature information of pore defects to determine a pore region boundary; segmentation recognition is performed according to the pore region boundary to determine a plurality of pore regions for pore traversal recording to obtain pore defect distribution information.

[0026] Specifically, non-local mean filtering is performed on the sequence of tomographic images frame by frame to reduce image noise and maintain edge texture features, thereby extracting a plurality of image edge structures; the sequence of tomographic images is subjected to contrast enhancement processing based on the extracted plurality of image edge structures, for example, using histogram equalization or adaptive histogram equalization methods, to obtain a set of contrast-enhanced images; feature comparison is performed using the set of contrast-enhanced images and historical pore defect image samples, in combination with a convolutional neural network classification model or a support vector machine discrimination model, to perform feature preliminary screening on pore region candidate blocks to determine initial feature information of pore defects. Boundary recognition is performed on the sequence of tomographic images based on the initial feature information of pore defects to determine a pore region boundary; segmentation recognition is performed on the sequence of tomographic images according to the pore region boundary to determine a plurality of pore regions, and the pore regions are traversed and recorded one by one to form pore defect distribution information.

[0027] Further, the boundary recognition based on the initial feature information of pore defects to determine a pore region boundary includes:

[0028] Local neighborhood gray scale analysis is performed according to the initial feature information of pore defects to determine a segmentation threshold; the sequence of tomographic images is segmented according to the segmentation threshold to generate a binary image for pore recognition to determine a plurality of suspected pore regions; connectedness determination is performed on the plurality of suspected pore regions, and the connected suspected pore regions are taken as seed points; the seed points are taken as centers to extract gray scale gradients of surrounding pixels for region growing to determine the pore region boundary.

[0029] Specifically, for the initial feature information of the air hole defect, the pixel gray value distribution is extracted in the local neighborhood of the fault image sequence, the gray histogram statistical analysis is performed on the neighborhood, and the segmentation threshold is determined based on the variance maximization or mean segmentation principle; the fault image sequence is segmented according to the segmentation threshold, the region with pixel value higher than the threshold is distinguished from the region with pixel value lower than the threshold, and a binary image is generated; by performing morphological processing (such as erosion and dilation operation) on the binary image, isolated noise points can be eliminated and the defect profile can be strengthened, so that a plurality of suspected air hole regions are obtained. On this basis, connected component analysis is performed on the plurality of suspected air hole regions, the regions that are spatially adjacent and pixel connected are judged, the suspected regions judged to be connected are merged into the same connected domain, and the center pixel of the connected domain is selected as the seed point; based on the gray gradient information of the neighborhood pixels, the region growing algorithm is performed with the seed point as the center, the adjacent pixels are expanded layer by layer in the growing process and whether the gray gradient threshold condition is met is judged, until it cannot be expanded, so that the air hole region boundary is obtained.

[0030] Further, the air hole defect distribution information is obtained for morphological analysis, and the air hole morphological defect parameter is obtained, the method comprising:

[0031] The plurality of air hole regions are traversed for area calculation to determine the plurality of region pixel area data; based on the air hole region boundary, pixel conversion is performed to obtain the total number of boundary pixels; the plurality of region pixel area data and the total number of boundary pixels are converted according to the spatial calibration coefficient to obtain the actual physical area and the actual physical perimeter; the air hole is morphologically analyzed according to the actual physical area combined with the actual physical perimeter to calculate the equivalent circle diameter of the air hole, and the air hole morphological defect parameter is obtained.

[0032] Specifically, the number of pixel points in each air hole region is counted by traversing the plurality of air hole regions, and the pixel area data corresponding to the air hole region is obtained by multiplying the number of pixel points by the actual physical area corresponding to a single pixel; based on the air hole region boundary, the boundary pixels are extracted and counted to obtain the total number of boundary pixels. On this basis, combined with the spatial calibration coefficient of the scanning system, the pixel area data and the total number of boundary pixels are converted into the actual physical area and the actual physical perimeter respectively, so that the physical quantity reflecting the real geometric scale of the air hole is obtained. Further, according to the actual physical area and the actual physical perimeter, the air hole morphology is analyzed by using the morphological calculation formula, and the equivalent circle diameter of the air hole can be calculated by the formula , wherein A is the actual physical area of the air hole, and the roundness and compactness of the air hole are calculated in combination with the actual physical perimeter, the roundness can be calculated by the formula , wherein P is the actual physical perimeter of the air hole, which is used to measure the closeness of the air hole shape to the standard circle; the compactness can be calculated by the formula The calculation is performed to characterize the complexity and irregularity of the pore boundary. Finally, multiple indexes such as the equivalent circle diameter of the pore, the actual physical area, the actual physical circumference, and the roundness are combined to form a pore morphology defect parameter for characterizing the geometric characteristics of the pore.

[0033] According to the pore defect distribution information and the pore morphology defect parameter, data bidirectional verification is performed, a pore multi-level defect array is constructed for grade division, and a defect grading result is determined.

[0034] Based on the pore distribution information, the spatial coordinates of each pore region are labeled, and the spatial distribution density of the pores in the three-dimensional grid is calculated. At the same time, based on the pore morphology defect parameter, the equivalent circle diameter, roundness, and compactness of the pores are counted to form a parameter set reflecting the size and morphology of the pores. Subsequently, a first verification rule and a second verification rule are established, wherein the first verification rule is based on the equivalent circle diameter deviation of the pores for threshold judgment, and the second verification rule is based on the spatial distribution density of the pores for rationality judgment. For each pore region, the morphology parameter and the distribution information are respectively imported into the two types of verification rules for cross verification. When the first verification result and the second verification result both satisfy the rules, the pore is determined as an effective defect region. If any verification fails, it is marked as invalid data and excluded. After obtaining the effective defect region, a pore multi-level defect array is constructed: the pores are divided into different size grades according to the numerical range of the equivalent circle diameter, and the aluminum alloy casting is divided into multiple density grades according to the spatial distribution density, and the size grade and the density grade are associated and mapped to form a multi-dimensional defect array. Finally, based on the multi-level defect array, the aluminum alloy casting is comprehensively evaluated, and the pore defect grading result is output.

[0035] Further, according to the pore defect distribution information and the pore morphology defect parameter, data bidirectional verification is performed, and a pore multi-level defect array is constructed, which comprises:

[0036] Based on the pore defect distribution information, the spatial position coordinates of the pores are determined. A first verification rule based on the pore morphology defect parameter and a second verification rule based on the pore defect distribution information are established. The pore defect distribution information is combined with the pore morphology defect parameter for bidirectional cross verification: S1: based on the equivalent circle diameter of the pores, deviation analysis is performed to determine the deviation parameter, which is verified according to the first verification rule to determine the first verification result; S2: based on the spatial position coordinates of the pores, distribution calculation is performed to determine the spatial distribution density, which is verified according to the second verification rule to determine the second verification result; based on the first verification result and the second verification result, bidirectional verification is determined, and the pore multi-level defect array is constructed according to the determination result.

[0037] Based on the distribution information of the stomata defects, the position of each stomata region is identified, the coordinate value in the three-dimensional reconstruction space is extracted, and the spatial position coordinate of the stomata is determined.

[0038] Two types of verification rules are established: one is the first verification rule based on the stomata morphological defect parameters, which is used to constrain the geometric characteristics of the stomata; the other is the second verification rule based on the stomata defect distribution information, which is used to constrain the spatial distribution characteristics of the stomata. Specifically, taking the stomata equivalent circle diameter as the main indicator, the deviation from the set threshold interval is calculated, and when the deviation meets the tolerance range, it is determined to pass the first verification rule, and the first verification result is obtained. Based on the spatial position coordinate of the stomata, the grid division method is used to calculate the number of stomata in a unit volume, and the stomata spatial distribution density is obtained; then the stomata spatial distribution density is compared with the set density threshold interval, and when the distribution density is within a reasonable range, it is determined to pass the second verification rule, and the second verification result is obtained.

[0039] The first verification result and the second verification result are comprehensively verified: when both are valid, the stomata are confirmed as real defects and are included in the stomata multi-level defect array; if either verification fails, it is marked as invalid data and is excluded.

[0040] Further, based on the first verification result and the second verification result, the stomata multi-level defect array is constructed according to the determination result, and the method comprises:

[0041] When the first verification result and the second verification result both pass the two-way verification, it is determined that the stomata defect distribution information and the stomata morphological defect parameters are valid data, then: S1: according to the value range of the stomata equivalent circle diameter, a plurality of stomata size levels are divided according to the value range; S2: according to the stomata spatial position coordinate, the aluminum alloy casting is regionally analyzed, and a plurality of stomata density levels are determined by dividing the key area; S3: the plurality of stomata size levels and the plurality of stomata density levels are associated and mapped, and the stomata multi-level defect array is constructed.

[0042] When the first verification result and the second verification result are both determined to be valid, it is confirmed that the stomata defect distribution information and the stomata morphological defect parameters are reliable data, and the stomata multi-level defect array is constructed accordingly. Specifically: taking the stomata equivalent circle diameter d as the indicator, the diameter interval is divided according to the preset, for example, the stomata with d < 50 μm are divided into size level L1, the stomata with 50 μm ≤ d < 100 μm are divided into size level L2, and so on, thereby obtaining a plurality of stomata size levels.

[0043] Based on the spatial position coordinates of the pores, the three-dimensional model of the aluminum alloy casting is regionally meshed, and the number of pores in each mesh element is counted, and then the spatial distribution density is calculated; different density thresholds are set according to the sensitivity of the key functional areas (such as the stress area, the joint surface, etc.), the pore density is divided into low density level, medium density level and high density level, and multiple pore density levels are obtained.

[0044] The multiple pore size levels and the pore density levels are associated and mapped, for example, in the form of a two-dimensional matrix, the horizontal axis is the pore size level, the vertical axis is the pore density level, and different intersection elements correspond to different defect levels. Thus, a pore multi-level defect array is constructed to realize multi-dimensional quantitative characterization of the pore defects.

[0045] Further, the pore multi-level defect array is constructed for level division to determine the defect grading result, the method comprising:

[0046] Based on the volume discretization analysis of the aluminum alloy casting, a three-dimensional space grid element is constructed; the pore multi-level defect array is mapped to the three-dimensional space grid element for pore defect quantity statistics to obtain the total number of pore defects of multiple grid elements; the pore multi-level defect array is mapped to the three-dimensional space grid element for pore size analysis, the pore equivalent circle diameters of multiple grid elements are processed in descending order, and the first-order pore equivalent circle diameter is extracted as the maximum equivalent diameter; the defect impact factor is generated by defect impact analysis according to the total number of pore defects of multiple grid elements and the maximum equivalent diameter; the multiple grid elements in the three-dimensional space grid element are weighted calculated according to the defect impact factor to obtain the local defect severity index of multiple grid elements, the aluminum alloy casting is evaluated, and the overall defect severity score is obtained; the pores of the aluminum alloy casting are defect graded according to the overall defect severity score to determine the defect grading result.

[0047] Based on the three-dimensional reconstruction model of the aluminum alloy casting, the overall volume is discretely analyzed, the casting volume is divided into multiple three-dimensional space grid elements by using uniform meshing method, each element has a fixed volume size, such as 100 μm × 100 μm × 100 μm. Then, the pore multi-level defect array is mapped to the three-dimensional space grid element, and the pore defects in each grid element are counted respectively to obtain the total number of pore defects. At the same time, the equivalent circle diameters of all pores in the grid element are extracted using the mapping result, and are arranged in descending order, and the first-order pore diameter is selected as the maximum equivalent diameter of the element. On this basis, the defect impact analysis is carried out by comprehensively considering the total number of pore defects and the maximum equivalent diameter to construct the defect impact factor F, which can be calculated by the formula F = αN + βd max , wherein N is the total number of pore defects of the element, d maxThe maximum equivalent diameter, and a and β are weight factors, which are empirically set according to the application scenario of the casting.

[0048] The local defect severity index of each grid cell is calculated by weighting according to the defect influence factor. The weighting method can set weights based on the sensitivity of the functional area, for example, the weight of the key stress area is higher, and the weight of the non-key area is lower. The local defect severity indexes of all grid cells are weighted and summarized to obtain the overall defect severity score of the aluminum alloy casting.

[0049] According to the overall defect severity score and the preset grading threshold interval, the porosity defects of the aluminum alloy casting are divided into different grades. For example: a score less than or equal to 0.2 is determined as level one (slight defect), 0.2-0.5 is determined as level two (moderate defect), 0.5-0.8 is determined as level three (serious defect), and greater than or equal to 0.8 is determined as level four (scrap).

[0050] Further, the local defect severity indexes of the plurality of grid cells are obtained to evaluate the aluminum alloy casting and obtain the overall defect severity score, the method comprising:

[0051] The plurality of grid cells are traversed to obtain a plurality of regional risk levels according to the function; the plurality of grid cells are assigned weights according to the plurality of regional risk levels to determine the weight coefficients of the plurality of grid cells; the plurality of grid cells are analyzed for local defects based on the weight coefficients of the plurality of grid cells combined with the local defect severity indexes of the plurality of grid cells to obtain weighted contribution values of the plurality of grid cells; and the aluminum alloy casting is evaluated according to the weighted contribution values to obtain the overall defect severity score.

[0052] Preferably, the plurality of grid cells are traversed, and the aluminum alloy casting is functionally divided according to its structural characteristics, for example, the bearing area, the connecting area, and the non-key area are respectively marked as different functional areas. Combined with the preset importance weight coefficients of the functional areas (such as the weight coefficient of the bearing area is 1.0, the weight coefficient of the connecting area is 0.7, and the weight coefficient of the non-key area is 0.3), each grid cell is given a regional risk level. Then, the grid cells are assigned weights according to the regional risk levels to obtain the weight coefficients of the grid cells, wherein the weight coefficients can be assigned in a linear or hierarchical manner, for example, the weight of the high-risk area is larger, and the weight of the low-risk area is smaller. On this basis, the local defect severity index of each grid cell is multiplied by its weight coefficient to obtain the weighted contribution value of the grid cell. Finally, the weighted contribution values of all grid cells are accumulated and normalized to obtain the overall defect severity score of the aluminum alloy casting.

[0053] Weighted contribution value: wherein, a weighted contribution value for the i-th grid cell, a weight coefficient, a local defect severity index.

[0054] a global defect severity score of the aluminum alloy casting, wherein S is the global defect severity score, and the value range is between [0, 1].

[0055] According to the defect grading result, the quality of the aluminum alloy casting is rated, and the automatic sorting is performed according to the quality level.

[0056] The global defect severity score is compared with the preset quality rating standard, for example, the casting with a score in the range of 0~0.2 is determined as A (excellent), the score in the range of 0.2~0.5 is determined as B (usable), the score in the range of 0.5~0.8 is determined as C (defective), and the score in the range of 0.8~1 is determined as D (scrap). Thus, the quality rating level of each casting is obtained.

[0057] On this basis, the aluminum alloy casting is automatically sorted according to the quality rating level. Specifically, an automatic transmission device is arranged on the production line, and the detection result is bound to the corresponding casting by using a bar code or an RFID identifier; when the casting enters the sorting station, the control system triggers the actuator (such as a pneumatic push rod, a mechanical arm or a sorting baffle) according to the rating result, and guides the castings of different ratings to corresponding collection channels or material frames. For example, the A-grade castings enter the qualified product channel, the B-grade castings enter the repairable area, the C-grade castings enter the defective area, and the D-grade castings enter the scrap recycling area, so as to realize the automatic sorting corresponding to the quality level.

[0058] In summary, the embodiments of the present application have at least the following technical effects:

[0059] Firstly, the aluminum alloy casting is scanned by multi-angle imaging to obtain a sequence of tomographic images. Then, the sequence of tomographic images is enhanced, the initial feature information of the porosity defect is extracted for segmentation and recognition, the porosity defect distribution information is obtained for morphological analysis, and the porosity morphological defect parameters are obtained. Then, the data is verified in two directions according to the porosity defect distribution information combined with the porosity morphological defect parameters, a multi-level defect array of porosity is constructed for grade division, and the defect grading result is determined. Finally, the quality of the aluminum alloy casting is rated according to the defect grading result, and the automatic sorting is performed according to the quality level. The technical problems of low detection precision of porosity defects of aluminum alloy castings, difficulty in effective grading evaluation, inaccurate quality control and insufficient sorting efficiency in the prior art are solved, and the technical effects of improving the detection precision and the sorting efficiency are achieved.

[0060] Embodiment two, based on the same inventive concept as the aluminum alloy casting porosity defect grading detection method in the foregoing embodiments, such as Figure 2As shown, the application provides a system for grading detection of porosity defects of aluminum alloy castings, wherein the system comprises:

[0061] The image acquisition module 11 performs multi-angle imaging scanning of the aluminum alloy casting to obtain a sequence of tomographic images; the analysis module 12 performs image enhancement on the sequence of tomographic images, extracts initial feature information of porosity defects for segmentation and identification, obtains porosity defect distribution information for morphological analysis, and obtains porosity morphological defect parameters; the grade division module 13 performs data bidirectional verification according to the porosity defect distribution information combined with the porosity morphological defect parameters, constructs a multi-level defect array of porosity for grade division, and determines the defect grading result; the casting sorting module 14 performs quality rating of the aluminum alloy casting according to the defect grading result, and automatically sorts according to the quality level.

[0062] Further, the image acquisition module 11 is used to perform the following method:

[0063] A two-dimensional plane coordinate system of the aluminum alloy casting is constructed, key point analysis is performed on the two-dimensional plane coordinate system to determine a plurality of effective imaging field points; a center point cluster is determined according to the plurality of effective imaging field points to determine an effective field center; the aluminum alloy casting is scanned according to the effective field center combined with the plurality of effective imaging field points to construct an initial two-dimensional projection image; the initial two-dimensional projection image is step-rotated scanned according to the effective field center to obtain a multi-angle image acquisition sequence; and cross-sectional image reconstruction is performed on the aluminum alloy casting according to the multi-angle image acquisition sequence to construct the sequence of tomographic images.

[0064] Further, the analysis module 12 is used to perform the following method:

[0065] Non-local mean filtering is performed on the sequence of tomographic images to extract a plurality of image edge structures; contrast enhancement is performed on the sequence of tomographic images according to the plurality of image edge structures to generate a set of contrast-enhanced images; initial feature screening is performed on the sequence of tomographic images combined with historical porosity defect images based on the set of contrast-enhanced images to determine initial feature information of porosity defects; boundary identification is performed based on the initial feature information of porosity defects to determine a porosity region boundary; segmentation and identification are performed according to the porosity region boundary to determine a plurality of porosity regions for porosity traversal recording to obtain porosity defect distribution information.

[0066] Further, the analysis module 12 is used to perform the following method:

[0067] The local neighborhood gray scale analysis is performed according to the initial feature information of the pore defect, a segmentation threshold is determined, the fault image sequence is segmented according to the segmentation threshold, a binary image is generated for pore recognition, and a plurality of suspected pore regions are determined; the plurality of suspected pore regions are subjected to connectedness determination, and the connected suspected pore regions are taken as seed points; the gray scale gradient of the surrounding pixels is extracted with the seed points as the center for region growing, and the pore region boundary is determined.

[0068] Further, the analysis module 12 is configured to perform the following method:

[0069] The area calculation is performed on the plurality of pore regions, a plurality of region pixel area data are determined, the pixel conversion is performed based on the pore region boundary, a plurality of total boundary pixel numbers are obtained, the plurality of region pixel area data and the plurality of total boundary pixel numbers are converted according to a spatial calibration coefficient, actual physical area and actual physical perimeter are obtained, and the actual physical area is combined with the actual physical perimeter to calculate the equivalent circle diameter of the pore, and the pore morphology defect parameter is obtained.

[0070] Further, the grade division module 13 is configured to perform the following method:

[0071] The pore position coordinates are determined based on the pore defect distribution information, the first verification rule based on the pore morphology defect parameter and the second verification rule based on the pore defect distribution information are established, the pore defect distribution information is combined with the pore morphology defect parameter for bidirectional cross verification, S1: the deviation analysis is performed based on the equivalent circle diameter of the pore to determine the deviation parameter, the first verification rule is used for verification, and the first verification result is determined; S2: the distribution calculation is performed based on the pore spatial position coordinates to determine the spatial distribution density, the second verification rule is used for verification, and the second verification result is determined; the bidirectional verification judgment is performed based on the first verification result and the second verification result, and the pore multi-grade defect array is constructed according to the judgment result.

[0072] Further, the grade division module 13 is configured to perform the following method:

[0073] When the first verification result and the second verification result both pass the bidirectional verification, it is determined that the pore defect distribution information and the pore morphology defect parameter are valid data, then: S1: a plurality of pore size grades are divided according to the numerical range of the equivalent circle diameter of the pore; S2: a plurality of pore density grades are divided according to the region analysis of the aluminum alloy casting based on the pore spatial position coordinates; S3: the plurality of pore size grades and the plurality of pore density grades are associated and mapped to construct the pore multi-grade defect array.

[0074] Further, the grade division module 13 is configured to perform the following method:

[0075] Based on volume discretization analysis of the aluminum alloy casting, a three-dimensional space grid unit is constructed; the pore multi-level defect array is mapped to the three-dimensional space grid unit for pore defect quantity statistics, and the total number of pore defects of multiple grid units is obtained; the pore multi-level defect array is mapped to the three-dimensional space grid unit for pore size analysis, and the pore equivalent circle diameters of multiple grid units are processed in descending order, and the first-order pore equivalent circle diameter is extracted as the maximum equivalent diameter; the defect influence factor is generated according to the total number of pore defects of multiple grid units and the maximum equivalent diameter; the multiple grid units in the three-dimensional space grid unit are calculated according to the defect influence factor, and the local defect severity index of multiple grid units is obtained to evaluate the aluminum alloy casting, and the overall defect severity score is obtained; the pores of the aluminum alloy casting are classified according to the overall defect severity score, and the defect classification result is determined.

[0076] Further, the grade division module 13 is configured to perform the following method:

[0077] The multiple grid units are traversed according to the function to obtain multiple regional risk levels; the weight coefficients of multiple grid units are determined according to the multiple regional risk levels; the local defect analysis of multiple grid units is performed based on the weight coefficients of multiple grid units combined with the local defect severity index of multiple grid units, and the weighted contribution value of multiple grid units is obtained; the aluminum alloy casting is evaluated according to the weighted contribution value, and the overall defect severity score is obtained.

[0078] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The above describes a specific embodiment of the present application. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or may be advantageous.

[0079] The above only describes the preferred embodiments of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0080] The specification and drawings are, of course, to be regarded in an illustrative rather than a restrictive sense. It is to be understood that any such modifications, variations, combinations or equivalents that fall within the scope of the application are intended to be embraced herein.

Claims

1. A method for classifying and detecting porosity defects in aluminum alloy castings, characterized in that, The method includes: Multi-angle imaging scanning of aluminum alloy castings was performed to obtain tomographic image sequences; Image enhancement is performed on the tomographic image sequence, initial feature information of pore defects is extracted for segmentation and recognition, distribution information of pore defects is obtained for morphological analysis, and morphological defect parameters of pores are obtained. Based on the porosity defect distribution information and the porosity morphology defect parameters, bidirectional data verification is performed to construct a multi-level porosity defect array for classification and to determine the defect classification results. The aluminum alloy castings are graded according to the defect classification results, and automatically sorted according to the quality level. The method for constructing a multi-level porosity defect array by performing bidirectional data verification based on the porosity defect distribution information and the porosity morphology defect parameters includes: Based on the porosity defect distribution information, the location of the pores is identified, and the spatial coordinates of the pores are determined. Establish a first verification rule based on the pore morphology defect parameters and a second verification rule based on the pore defect distribution information, and perform bidirectional cross-validation on the pore defect distribution information in conjunction with the pore morphology defect parameters: S1: Based on the equivalent circle diameter of the pores, perform deviation analysis to determine the deviation parameters, verify them according to the first verification rule, and determine the first verification result; S2: Based on the spatial coordinates of the pores, perform distribution calculations to determine the spatial distribution density, verify according to the second verification rule, and determine the second verification result; Based on the first verification result and the second verification result, a bidirectional verification judgment is performed, and the multi-level pore defect array is constructed according to the judgment result. The method includes: When both the first verification result and the second verification result pass bidirectional verification, the porosity defect distribution information and the porosity morphology defect parameters are determined to be valid data. S1: Set a numerical range based on the equivalent circle diameter of the pores, and divide multiple pore size levels according to the numerical range; S2: Based on the spatial coordinates of the pores, perform regional analysis on the aluminum alloy casting to determine the key areas and divide them into multiple pore density levels; S3: Associate and map the multiple pore size levels with the multiple pore density levels to construct the multi-level pore defect array; The method for constructing a multi-level array of pore defects for classification and determining the defect classification results includes: Based on the volume discretization analysis of aluminum alloy castings, a three-dimensional spatial mesh element is constructed. The porosity multi-level defect array is mapped to the three-dimensional spatial grid cell to count the number of porosity defects, and the total number of porosity defects in multiple grid cells is obtained. The multi-level defect array of pores is mapped to the three-dimensional spatial grid cell for pore size analysis. The equivalent circle diameter of the pores in multiple grid cells is sorted in descending order, and the equivalent circle diameter of the first-order pore is extracted as the maximum equivalent diameter. Based on the total number of pore defects in multiple grid cells and the maximum equivalent diameter, a defect impact analysis is performed to generate a defect impact factor. The local defect severity index of the multiple grid cells in the three-dimensional spatial grid cell is obtained by weighting the defect impact factor according to the defect influence factor, and the aluminum alloy casting is evaluated to obtain the overall defect severity score. Based on the overall defect severity score, the porosity of the aluminum alloy casting is classified into defects, and the defect classification results are determined. To evaluate aluminum alloy castings, the local defect severity index of multiple mesh elements is obtained to obtain an overall defect severity score. The method includes: By traversing the multiple grid cells and labeling the regional risks according to their functions, multiple regional risk levels are obtained; The weights of the multiple grid cells are assigned according to the risk levels of the multiple regions, and the weight coefficients of the multiple grid cells are determined. Based on the weighting coefficients of multiple grid cells and the local defect severity index of multiple grid cells, local defect analysis is performed on multiple grid cells to obtain the weighted contribution value of multiple grid cells; The aluminum alloy casting is evaluated based on the weighted contribution value to obtain the overall defect severity score.

2. The method for graded detection of porosity defects in aluminum alloy castings as described in claim 1, characterized in that, Multi-angle imaging scanning of aluminum alloy castings to obtain tomographic image sequences, the method includes: A two-dimensional plane coordinate system for aluminum alloy castings is constructed, and key point analysis is performed by traversing the two-dimensional plane coordinate system to determine multiple effective imaging field points; Based on the multiple effective imaging field-of-view points, cluster the center points to determine the effective field-of-view center; The aluminum alloy casting is scanned according to the effective field of view center and the multiple effective imaging field of view points to construct an initial two-dimensional projection image; The initial two-dimensional projection image is scanned by step rotation along the effective field of view center to obtain a multi-angle image acquisition sequence; The cross-sectional images of the aluminum alloy casting are reconstructed according to the multi-angle image acquisition sequence to construct the tomographic image sequence.

3. The method for graded detection of porosity defects in aluminum alloy castings as described in claim 1, characterized in that, The method includes performing image enhancement on the tomographic image sequence, extracting initial feature information of pore defects for segmentation and identification, and obtaining pore defect distribution information. The tomographic image sequence is traversed and nonlocal mean filtering is performed to extract multiple image edge structures; The tomographic image sequence is contrast-enhanced according to the multiple image edge structures to generate a contrast-enhanced image set. Based on the contrast-enhanced image set, the tomographic image sequence is combined with historical porosity defect images to perform initial feature screening and determine the initial feature information of porosity defects. Boundary identification is performed based on the initial feature information of the pore defects to determine the boundary of the pore region. The pore regions are segmented and identified according to their boundaries. Multiple pore regions are identified and pore traversal records are made to obtain pore defect distribution information.

4. The method for graded detection of porosity defects in aluminum alloy castings as described in claim 3, characterized in that, Boundary identification based on the initial feature information of the pore defects to determine the boundary of the pore region includes the following method: Local neighborhood grayscale analysis is performed based on the initial feature information of the porosity defects to determine the segmentation threshold; The tomographic image sequence is segmented according to the segmentation threshold to generate a binarized image for stomatal identification, thereby identifying multiple suspected stomatal regions. Connectivity determination is performed on the multiple suspected stomatal regions, and the connected suspected stomatal regions are used as seed points; Using the seed point as the center, the grayscale gradient of the surrounding pixels is extracted for region growth to determine the boundary of the pore region.

5. The method for graded detection of porosity defects in aluminum alloy castings as described in claim 3, characterized in that, Methods include: obtaining morphological analysis of porosity defect distribution information to obtain porosity morphological defect parameters; and other methods. The area of ​​the multiple pore regions is calculated by traversing them to determine the pixel area data of the multiple regions. Pixel conversion is performed based on the boundary of the pore region to obtain the total number of boundary pixels. The pixel area data of the multiple regions and the total number of the multiple boundary pixels are converted according to the spatial calibration coefficient to obtain the actual physical area and the actual physical perimeter. Based on the actual physical area and the actual physical perimeter, the morphological analysis of the pores is performed to calculate the equivalent circle diameter of the pores, thereby obtaining the pore morphological defect parameters.

6. A grading and detection system for porosity defects in aluminum alloy castings, characterized in that, The system is used to implement the graded detection method for porosity defects in aluminum alloy castings according to any one of claims 1-5, the system comprising: Image acquisition module: Performs multi-angle imaging scans on aluminum alloy castings to acquire tomographic image sequences; Analysis module: performs image enhancement on the tomographic image sequence, extracts initial feature information of pore defects for segmentation and recognition, obtains pore defect distribution information for morphological analysis, and obtains pore morphological defect parameters; Grading module: Based on the porosity defect distribution information and the porosity morphology defect parameters, the data is verified bidirectionally to construct a multi-level porosity defect array for grading and to determine the defect grading result; Casting sorting module: Based on the defect classification results, aluminum alloy castings are graded for quality and automatically sorted according to the quality level.

Images