Image-assisted fluorescence spectrum detection method and system for additive manufacturing

Abstract

The invention provides an image-assisted fluorescence spectrum detection method and system for additive manufacturing, and the method comprises the following steps: obtaining a slice image of a to-be-detected additive manufacturing part, and carrying out the image preprocessing, thereby obtaining a standardized image containing a plurality of to-be-detected part contours; performing edge detection and contour recognition on the standardized image, extracting center coordinates and corresponding vertex coordinates of the contour of each part in an image coordinate system, and constructing an image coordinate set; acquiring a conversion proportionality coefficient between the image coordinate system and an actual physical coordinate system through a multi-point calibration method, establishing a linear mapping relation between the image coordinate system and the actual physical coordinate system, and converting the image coordinate set into an actual coordinate set; according to the center coordinates and the vertex coordinates of all the contours in the actual coordinate set and the size of the detection light spot, the detection path covering all the to-be-detected areas is generated through the path, full-process automation and intelligentization of element component detection in the additive manufacturing process are achieved, and the detection efficiency and reliability are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of spectral detection technology, and in particular to an image-assisted fluorescence spectral detection method for additively manufactured parts. Background Technology

[0002] With the rapid development of additive manufacturing technologies, such as selective laser melting and electron beam melting, the manufacturing of complex structural and functional integrated parts has become increasingly common. In order to ensure the structural reliability and functional stability of these parts, the material composition testing of additively manufactured parts after production is particularly critical. Fluorescence spectrometers, as commonly used elemental analysis tools, have the advantages of being non-destructive, fast, and highly sensitive, and are widely used in material characterization. However, they still face significant challenges in actual testing.

[0003] CN106626377B discloses an additive manufacturing method and apparatus for real-time detection of powder bed surface deformation. The method includes: controlling a ray to perform a grating scan on the powder bed surface to form grating lines; controlling an imaging device to image the grating lines and determining whether deformation exists based on the imaging results; stopping additive manufacturing when deformation exists in the grating lines and the deformation amount exceeds an allowable value; adjusting the ray energy based on the deformation amount when deformation exists in the grating lines and the deformation amount is less than or equal to the allowable value; adjusting the ray energy based on the deformation amount includes: lowering the ray energy when the deformation amount is positive; increasing the ray energy when the deformation amount is negative; melting the powder bed surface using the ray; and melting the powder bed surface using the ray before and / or after controlling the ray to perform the grating scan on the powder bed surface.

[0004] While the aforementioned existing technologies can achieve online monitoring of powder bed deformation, they rely on fixed-pattern grating scanning paths and lack path planning mechanisms, resulting in low detection efficiency and a large amount of redundant scanning. At the same time, the method does not involve a high-precision mapping relationship between image coordinates and physical coordinates, making it impossible to achieve accurate positioning of the detection location, thereby reducing the accuracy and efficiency of spectral detection of additive manufacturing parts. Summary of the Invention

[0005] In view of this, the present invention proposes an image-assisted fluorescence spectroscopy detection method and system for additively manufactured parts. By transforming the image coordinates and combining it with a honeycomb snake-wing path planning algorithm, redundant scanning paths are significantly reduced, detection efficiency is greatly improved, and full coverage detection without blind spots is ensured, thereby improving the accuracy and efficiency of spectral detection of additively manufactured parts.

[0006] The technical solution of the present invention is implemented as follows: In a first aspect, the present invention provides an image-assisted fluorescence spectroscopy detection method for additive manufacturing, comprising the following steps: S1. Obtain a slice image of the additive manufacturing part to be inspected and perform image preprocessing to obtain a standardized image containing the outlines of several parts to be inspected. S2, a pre-trained network model is used to perform edge detection and contour recognition on the standardized image, extract the center coordinates and corresponding vertex coordinates of each part contour in the image coordinate system, and construct an image coordinate set; S3. The transformation ratio coefficient between the image coordinate system and the actual physical coordinate system is obtained by multi-point calibration method, and a linear mapping relationship between the two is established. Based on the linear mapping relationship, the image coordinate set is converted into the actual coordinate set. S4. Based on the center coordinates, vertex coordinates, and detection spot size of each contour in the actual coordinate set, a honeycomb serpentine path arrangement algorithm is used to generate a detection path covering all areas to be detected, and the scan point coordinate file is output. S5 controls the motion system to read the scanning point coordinate file, drives the fluorescence spectrometer to move to each scanning point according to the detection path, and triggers spectral acquisition in sequence to complete the elemental composition detection.

[0007] Based on the above technical solutions, preferably, step S1 includes the following sub-steps: Obtain slice images of the additively manufactured part to be inspected; Based on the HSV color space model, an HSV threshold range corresponding to the positioning boundary color is set; a color segmentation algorithm is used to extract the positioning boundary region. The image within the positioning boundary area is cropped and adjusted to a preset standard size to obtain a standardized image containing the outlines of several parts to be inspected.

[0008] Based on the above technical solutions, preferably, the step S3 of obtaining the transformation ratio between the image coordinate system and the actual physical coordinate system through multi-point calibration includes the following sub-steps: Select multiple reference points distributed on the slice image and obtain their coordinates in the image coordinate system; Measure the actual coordinates of each reference point in the physical coordinate system; calculate the ratio of the corresponding distances of each reference point in the image coordinate system and the physical coordinate system to obtain multiple scaling factors; The least squares method is used to perform linear regression fitting on multiple scaling coefficients to obtain the final transformation scaling coefficients between the image coordinate system and the actual physical coordinate system.

[0009] Based on the above technical solutions, preferably, the step S3 of selecting multiple distributed reference points on the slice image includes: Copper foil is arranged around the edge of the printing substrate as a boundary reference point for spatial positioning on the slice image; The fluorescence spectrometer is controlled to scan its spot on the printed substrate; When the light spot crosses the edge of the copper foil, the copper element signal intensity undergoes a step change, and the peak value of the first derivative of the copper element signal is taken as the physical boundary of the printed substrate.

[0010] Based on the above technical solutions, preferably, the establishment of a linear mapping relationship between the two in step S3, and the conversion of the image coordinate set into the actual coordinate set based on the linear mapping relationship, includes the following sub-steps: obtaining the actual coordinates corresponding to the center point of the printed substrate in the physical coordinate system; calculating the physical coordinates after image coordinate conversion by multiplying the image coordinates with the final conversion ratio coefficient and adding it to the actual coordinates corresponding to the center point of the printed substrate in the physical coordinate system; and constructing the actual coordinate set based on the converted actual physical coordinates.

[0011] Based on the above technical solutions, preferably, step S4 includes the following sub-steps: Calculate the actual width and height of each part's outline based on the vertex coordinates, and compare the actual width and height with the spot size; If the actual width and height are both smaller than the spot size, the part outline is determined to be a small area, and the center point of the part outline is taken as the only scanning point. If the actual width and height are greater than the spot size, the part outline is determined to be a large area. The X-direction scanning step size is set to be equal to the spot diameter, and the Y-direction scanning step size is set to be equal to a preset ratio multiple of the spot diameter. Based on the center coordinates of the part's contour, and according to the X-direction scanning step size, Y-direction scanning step size, and the width and height of the part's contour image, the tangency between the light spot edge and the image boundary is used as a constraint condition. The light spot diameter is dynamically adjusted, and an initial rectangular scanning point array covering the part's contour is generated. The initial rectangular scanning point array is misaligned by adjusting the X coordinates of all scanning points in even or odd rows, shifting them in the X direction by a spot radius, so that the scanning points in adjacent rows are staggered in the X direction, forming a honeycomb distribution. All scan points are connected row by row to form a detection path, and the paths of adjacent rows are connected in opposite directions to form a serpentine reciprocating scan path.

[0012] Based on the above technical solution, preferably, step S4 further includes the following sub-steps: Calculate the distance between the rightmost column of scan points in the initial rectangular scan point array and the right boundary of the contour. If the distance is greater than 0, add a column of scan points to the right boundary. Calculate the distance between the bottom row of scan points in the initial rectangular scan point array and the bottom boundary of the contour. If the distance is greater than 0, add a row of scan points at the bottom boundary. Finally, a detection path covering all areas to be detected is generated.

[0013] Based on the above technical solutions, preferably, step S5 includes the following sub-steps: By integrating the fluorescence spectrometer into the motion control system, the motion control system is used to move the fluorescence spectrometer along three axes; The motion control system reads the coordinate file of the scanning points, drives the fluorescence spectrometer to move to each scanning point according to the detection path, and sends a trigger signal to the fluorescence spectrometer after positioning. After receiving the signal, the fluorescence spectrometer performs the elemental composition detection task at the current position. After the detection is completed, it returns a completion signal, and the motion system drives the fluorescence spectrometer to move to the next scanning point. This process is repeated until all scanning points are detected.

[0014] Secondly, the present invention also provides an image-assisted fluorescence spectroscopy detection system for additive manufacturing, which is implemented using an image-assisted fluorescence spectroscopy detection method for additive manufacturing. The system includes: The preprocessing module is used to acquire slice images of the additive manufacturing parts to be inspected and perform image preprocessing to obtain a standardized image containing the outlines of several parts to be inspected. The image processing module is used to perform edge detection and contour recognition on standardized images using a pre-trained network model, extract the center coordinates and corresponding vertex coordinates of each part contour in the image coordinate system, and construct an image coordinate set. The coordinate transformation module is used to obtain the transformation ratio coefficient between the image coordinate system and the actual physical coordinate system through multi-point calibration, establish a linear mapping relationship between the two, and transform the image coordinate set into the actual coordinate set based on the linear mapping relationship. The path planning module is used to generate a detection path covering all areas to be detected based on the center coordinates, vertex coordinates, and detection spot size of each contour in the actual coordinate set, using a honeycomb serpentine path arrangement algorithm, and outputs a scan point coordinate file. The motion control module is used to control the motion system to read the coordinate file of the scanning points, drive the fluorescence spectrometer to move to each scanning point according to the detection path, and trigger the spectral acquisition in sequence to complete the elemental composition detection.

[0015] Thirdly, the present invention also provides a computer-readable storage medium storing a program for an image-assisted fluorescence spectroscopy detection method for additive manufacturing, wherein the program, when executed, implements the image-assisted fluorescence spectroscopy detection method for additive manufacturing.

[0016] The image-assisted fluorescence spectroscopy detection method and system for additive manufacturing of the present invention have the following advantages over the prior art: (1) Automatic positioning of the detection area was achieved through intelligent image recognition and precise mapping of physical coordinates. Combined with the honeycomb serpentine path planning algorithm, an optimized detection path with full coverage and no blind spots was generated. Finally, through the closed-loop linkage between the motion control system and the spectral detector, the detection efficiency, accuracy and reliability were significantly improved. (2) By using multi-point calibration and least squares fitting algorithm, combined with the precise positioning technology of spectral signal of copper foil boundary, a high-precision and robust linear mapping relationship between image space and physical space was established, which solved the coordinate deviation problem caused by system cumulative error and mechanical backlash, and significantly improved the accuracy and repeatability of the entire detection system. (3) By using the size adaptive judgment mechanism and the honeycomb serpentine path planning algorithm, the global optimization and full coverage generation of the detection path are realized. Not only does the honeycomb staggered point layout effectively eliminate the two-dimensional detection blind spot, but the serpentine reciprocating connection also greatly reduces the idle time of the motion system. At the same time, the point supplementation strategy at the boundary ensures that no detection is missed. Thus, while significantly improving the detection efficiency, the integrity and reliability of the element composition analysis results are guaranteed. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the image-assisted fluorescence spectroscopy detection method for additive manufacturing according to the present invention; Figure 2 This is a slice image of the image-assisted fluorescence spectroscopy detection method for additive manufacturing according to the present invention; Figure 3 This is a schematic diagram of the three-axis motion system structure of the image-assisted fluorescence spectroscopy detection method for additive manufacturing according to the present invention; Figure 4 This is a schematic diagram of the image-assisted fluorescence spectroscopy detection system for additive manufacturing according to the present invention. Detailed Implementation

[0019] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0020] like Figure 1-3 As shown, in a first aspect, the present invention provides an image-assisted fluorescence spectroscopy detection method for additive manufacturing, comprising the following steps: S1. Obtain a slice image of the additive manufacturing part to be inspected and perform image preprocessing to obtain a standardized image containing the contours of several parts to be inspected.

[0021] It should be noted that in this embodiment, step S1 first performs the image acquisition and preprocessing steps. The purpose is to process the original slice image, which may contain redundant information, into a standardized image that only contains the effective detection area and has a uniform size, so as to lay the foundation for subsequent image recognition.

[0022] Step S1 includes the following sub-steps: Obtain slice images of the additively manufactured part to be inspected; It should be noted that the slice image comes from the slicing software used by the additive manufacturing equipment. Before or after the printing task begins, the system exports a two-dimensional slice image of the current printing layer from the slicing software. This image clearly shows all the areas on the printing layer where the metal powder will be melted and shaped, as well as the unoccupied substrate areas.

[0023] Based on the HSV color space model, an HSV threshold range corresponding to the positioning boundary color is set; a color segmentation algorithm is used to extract the positioning boundary region.

[0024] It should be noted that the preprocessing module first converts the sliced ​​image of the input RGB color model to the HSV color space. The HSV space is closer to the human eye's perception of color than the RGB space, and can separate color information, saturation information and brightness information. It has better robustness to changes in lighting and is more conducive to color-based segmentation. The system presets the HSV threshold range corresponding to the color of the positioning boundary. For example, if the boundary is red, the hue (H) range can be set to (0,10) and (170,180), the saturation (S) range to (100,255), and the brightness (V) range to (50,255). These thresholds can be used as input parameters to adapt to different color boundaries. The HSV image is thresholded using a color segmentation algorithm to generate a binary mask, where the white area represents the identified red boundary and the black area represents other parts. Then, morphological operations are used to fill the small holes, and the maximum contour is extracted by the contour search algorithm to obtain the required positioning boundary. The image within the positioning boundary area is cropped and adjusted to a preset standard size to obtain a standardized image containing the outlines of several parts to be inspected.

[0025] Based on the extracted positioning boundary contour, its minimum bounding rectangle is obtained. Using this rectangle as a reference, the system crops the original slice image, completely removing all redundant information outside the image and the red border itself, retaining only the core printing area image inside the border. This step ensures that subsequent processing focuses only on the effective part contour. The cropped image is uniformly scaled or interpolated to a preset standard size, eliminating image scale differences caused by different slicing software settings or export resolutions. This provides a calculation basis for the fixed ratio conversion between image coordinates and physical coordinates in subsequent steps, ensuring the consistency, repeatability, and accuracy of the system processing.

[0026] Understandably, through intelligent boundary recognition and image standardization processing based on the HSV color space, redundant information and scale differences in the original slice images are effectively eliminated, and standardized images with uniform size and containing only the outlines of effective parts are automatically extracted, laying a solid foundation for subsequent recognition and positioning, and significantly improving the automation, accuracy and consistency of the system processing.

[0027] S2 uses a pre-trained network model to perform edge detection and contour recognition on the standardized image, extracts the center coordinates and corresponding vertex coordinates of each part contour in the image coordinate system, and constructs an image coordinate set.

[0028] It should be noted that edge detection and contour recognition are performed on the standardized image using a pre-trained semantic segmentation network model. For regular rectangular contours, the four corner points are directly extracted; for irregular polygonal contours, a polygon approximation algorithm is used to obtain a sequence of key vertices that can characterize their shape features. These vertex coordinates define the shape and boundary of the part. Based on all the pixels of the contour or the vertex coordinates, its geometric center is calculated, and this center coordinate will be used as the representative position of the part contour in the image coordinate system. The center coordinates and corresponding vertex coordinates of all part contours extracted in the above steps are stored in the corresponding elements. All elements contained in each slice layer are stored as image coordinate subsets. The image coordinate subsets are saved according to the slice layer sequence to form an image coordinate set. This set completely describes the geometric information of all targets to be detected in the part printed by the current additive manufacturing.

[0029] Understandably, by introducing a pre-trained semantic segmentation network model, high-precision and automated recognition and feature extraction of part contours in standardized images are achieved, effectively overcoming the shortcomings of traditional image processing algorithms in adapting to complex and blurred edges. By calculating the coordinates of the geometric center and key vertices and constructing a structured set of image coordinates, a complete and accurate geometric information foundation is provided for subsequent coordinate mapping and path planning, significantly improving the intelligence level and recognition reliability of the detection system.

[0030] S3. The transformation ratio coefficient between the image coordinate system and the actual physical coordinate system is obtained by multi-point calibration method, and a linear mapping relationship between the two is established. Based on the linear mapping relationship, the image coordinate set is converted into the actual coordinate set.

[0031] Step S3, which describes obtaining the transformation ratio between the image coordinate system and the actual physical coordinate system using a multi-point calibration method, includes the following sub-steps: Select multiple reference points distributed on the slice image and obtain their coordinates in the image coordinate system; It should be noted that, on the standardized slice image obtained in step S1, n (n≥3) evenly distributed and easily identifiable reference points are manually or automatically selected. These reference points should cover the four corners and the central area of ​​the image to ensure the representativeness and global accuracy of the calibration. Image processing software or algorithms (such as click-to-select or corner detection) are used to accurately obtain the pixel coordinates of these n reference points in the image coordinate system. On the corresponding actual printed substrate, measuring equipment, such as an optical measuring instrument, laser displacement sensor, or encoder reading of a high-precision CNC platform, is used to measure the coordinates (X_r_i, Y_r_i) of the points corresponding to the above n reference points in the actual physical coordinate system.

[0032] Measure the actual coordinates of each reference point in the physical coordinate system; calculate the ratio of the corresponding distances of each reference point in the image coordinate system and the physical coordinate system to obtain multiple scaling factors; This includes: calculating the Euclidean distance between every two reference points (i, j) in the image coordinate system and the actual coordinate system; The distance calculation expression in the image coordinate system is:

[0033] In the formula, (X_i_i,Y_i_i) represents the image coordinates of the i-th reference point; (X_i_j,Y_i_j) represents the image coordinates of the j-th reference point; The distance calculation expression in the physical coordinate system is:

[0034] In the formula, (X_r_i,Y_r_i) represents the actual coordinates of the i-th reference point; (X_r_j,Y_r_j) represents the actual coordinates of the j-th reference point; The scaling factor produced by this pair of reference points is calculated using the following expression: k_ij = d_r_ij / d_i_ij; By combining different reference point pairs, C(n,2) scaling coefficients k_ij can be obtained.

[0035] The least squares method is used to perform linear regression fitting on multiple scaling coefficients to obtain the final transformation scaling coefficients between the image coordinate system and the actual physical coordinate system.

[0036] Since the image coordinates and the actual physical coordinates have a linear proportional relationship, a model is established. The model has no intercept because zero pixel distance corresponds to zero physical distance.

[0037] The least squares method is used to perform linear regression on all the above data points to solve for the optimal proportional coefficient k. The formula is:

[0038] In the formula, m is the number of all valid reference point pairs, m=C(n,2); The image distance between the i-th pair of points; Let be the actual distance between the i-th pair of points.

[0039] This method can resist the interference of random measurement errors, and in particular, it can reduce the overall deviation caused by the inaccuracy of individual point pairs, thus obtaining a more robust and accurate global scaling factor.

[0040] Step S3, which establishes a linear mapping relationship between the two and converts the image coordinate set into a physical coordinate set based on the linear mapping relationship, includes the following sub-steps: obtaining the actual coordinates of the center point of the printed substrate in the physical coordinate system; calculating the physical coordinates after image coordinate transformation by multiplying the image coordinates by the final transformation scaling factor and adding it to the actual coordinates of the center point of the printed substrate in the physical coordinate system; and constructing a physical coordinate set based on the transformed physical coordinates, expressed as:

[0041] In the formula, (X_c,Y_c) are the coordinates of the reference point in the physical coordinate system corresponding to the origin of the image coordinate system, which is the center point of the printed substrate, and (X_i,Y_i) are the image coordinates.

[0042] By applying the above mapping relationship, the image coordinate set constructed in step S2 is calculated in batches to finally obtain the actual physical coordinate set used to guide the movement of the fluorescence spectrometer; this realizes the accurate mapping from the virtual image space to the real physical world, laying a solid theoretical foundation for subsequent automated path planning and precise positioning detection.

[0043] Step S3, which involves selecting multiple distributed reference points on the slice image, includes: Copper foil is arranged around the edge of the printing substrate as a boundary reference point for spatial positioning on the slice image; It should be noted that, in order to achieve high-precision coordinate mapping, a stable and accurate actual physical coordinate system is first established. In this embodiment, the following method is adopted: a foil strip with high-contrast elements, preferably copper foil, is arranged around the edge of the printing substrate as a reference object for spatial positioning; the copper foil strip provides a clear and known physical boundary reference.

[0044] The fluorescence spectrometer is controlled to scan its spot on the printed substrate; It should be noted that the fluorescence spectrometer controls the spot of the light to perform fine scanning on the printed substrate area including the edge of the copper foil, and collects the characteristic X-ray fluorescence intensity signal of copper element in real time. When the light spot crosses the boundary between the copper foil and the substrate, the signal intensity of copper element will show a step change. By calculating the derivative of the signal curve, the peak point of its first derivative is the precise physical location of the copper foil boundary. When the light spot crosses the edge of the copper foil, the copper element signal intensity undergoes a step change, and the peak value of the first derivative of the copper element signal is taken as the physical boundary of the printed substrate.

[0045] It should be noted that by scanning and locating the boundary points on both sides of the substrate, and combining them with the actual design dimensions of the substrate, the precise coordinates (X_c, Y_c) of the geometric center point of the printed substrate in physical space can be calculated, and this point is defined as the origin of the entire actual physical coordinate system. This method effectively calibrates the cumulative error and mechanical backlash of the motion system itself, ensuring the accuracy and reproducibility of the coordinate system reference.

[0046] In addition, during the selection of reference points, specific markers on the copper foil boundary or feature points at known locations on the substrate are preferred.

[0047] It should be noted that by using multi-point calibration and least squares fitting algorithms, combined with precise positioning technology of spectral signals of copper foil boundaries, a high-precision and robust linear mapping relationship between image space and physical space was established. This solved the coordinate deviation problem caused by system cumulative error and mechanical backlash, laying a solid technical foundation for achieving fully automatic and highly reliable detection from virtual image recognition to precise positioning in physical space, and significantly improving the accuracy and repeatability of the entire detection system.

[0048] S4. Based on the center coordinates, vertex coordinates, and detection spot size of each contour in the actual coordinate set, a honeycomb serpentine path arrangement algorithm is used to generate a detection path covering all areas to be detected, and the scan point coordinate file is output.

[0049] It should be noted that, based on the actual physical coordinate set obtained in step S3 and the spot characteristics of the fluorescence spectrometer, this embodiment generates an efficient detection path without blind spots. This path planning method comprehensively considers detection efficiency and coverage integrity, and adopts an optimization strategy that combines honeycomb staggered point placement with serpentine reciprocating connection.

[0050] Step S4 includes the following sub-steps: Calculate the actual width and height of each part's outline based on the vertex coordinates, and compare the actual width and height with the spot size; If the actual width and height are both smaller than the spot size, the part outline is determined to be a small area, and the center point of the part outline is taken as the only scanning point. If the actual width and height are greater than the spot size, the part outline is determined to be a large area. The X-direction scanning step size is set to be equal to the spot diameter, and the Y-direction scanning step size is set to be equal to a preset ratio multiple of the spot diameter. It should be noted that each part contour in the actual coordinate set is traversed, and its actual width W and height H are calculated based on the vertex coordinates of the contour. If W ≤ spot diameter D and H ≤ spot diameter D, then the contour is determined to be a small-sized region. A single spot can completely cover it, and the system uses the geometric center point of the contour as its unique scanning point; If W > spot diameter D or H > spot diameter D, then the contour is determined to be a large area, and the subsequent path arrangement sub-step is entered to generate a scan point array; Based on the center coordinates of the part's contour, and according to the X-direction scanning step size, Y-direction scanning step size, and the width and height of the part's contour image, the tangency between the light spot edge and the image boundary is used as a constraint condition. The light spot diameter is dynamically adjusted, and an initial rectangular scanning point array covering the part's contour is generated. It should be noted that the X-direction scan step size dx = D; the Y-direction scan step size... Wherein, R is a preset scaling factor, which typically ranges from 0.5 to 0.9, preferably 0.75. This design is intended to create a certain overlap of light spots in the Y direction to ensure coverage. Based on the center coordinates of the contour, and according to its width W and height H, with the constraint that the edges of the light spots in the first and last rows / columns are tangent to the contour boundary, the required number of rows and columns is calculated, and an initial rectangular scan point array covering the region is generated.

[0051] The initial rectangular scanning point array is misaligned by adjusting the X coordinates of all scanning points in even or odd rows, shifting them in the X direction by a spot radius, so that the scanning points in adjacent rows are staggered in the X direction, forming a honeycomb distribution. All scan points are connected row by row to form a detection path, and the paths of adjacent rows are connected in opposite directions to form a serpentine reciprocating scan path.

[0052] It should be noted that, in order to improve the coverage uniformity of the two-dimensional plane and eliminate detection blind spots, the initial rectangular dot matrix is ​​optimized; the X coordinates of all scanning points in even or odd rows are adjusted so that they are offset by dx / 2 in the X direction; after this adjustment, the scanning points between adjacent rows are staggered in the X direction, thus forming a honeycomb distribution on the two-dimensional plane, making the coverage of the light spot in the Y direction more continuous, effectively avoiding the striped uncovered areas that may be generated by the traditional checkerboard dot layout. In order to maximize detection efficiency and reduce the round-trip time of the motion platform, a serpentine scanning method is used to connect all scanning points to form a detection path.

[0053] It should be noted that, to ensure complete coverage of the contour edge region, the system performs full coverage verification after generating the basic path to ensure that the generated scan path completely covers the entire target area without blind spots. Step S4 also includes the following sub-steps: Calculate the distance between the rightmost column of scan points in the initial rectangular scan point array and the right boundary of the contour. If the distance is greater than 0, add a column of scan points to the right boundary. Calculate the distance between the bottom row of scan points in the initial rectangular scan point array and the bottom boundary of the contour. If the distance is greater than 0, add a row of scan points at the bottom boundary. Finally, a detection path covering all areas to be detected is generated.

[0054] Understandably, by using a size-adaptive judgment mechanism and a honeycomb serpentine path planning algorithm, global optimization and full coverage generation of the detection path are achieved. Not only does the honeycomb staggered point layout effectively eliminate the two-dimensional detection blind spot, but the serpentine reciprocating connection also significantly reduces the idle time of the motion system. At the same time, the point supplementation strategy at the boundary ensures that no detection is missed. Thus, while significantly improving detection efficiency, the integrity and reliability of the element composition analysis results are guaranteed.

[0055] S5 controls the motion system to read the scanning point coordinate file, drives the fluorescence spectrometer to move to each scanning point according to the detection path, and triggers spectral acquisition in sequence to complete the elemental composition detection.

[0056] It should be noted that step S5 is the final execution stage to achieve full-process automation. This step transforms the digital detection path generated in the previous steps into the actual physical movement and detection action of the fluorescence spectrometer. Through the collaborative communication and linkage control between the subsystems, the elemental composition is finally collected.

[0057] Step S5 includes the following sub-steps: By integrating the fluorescence spectrometer into the motion control system, the motion control system is used to move the fluorescence spectrometer along three axes; Before starting the test, ensure that the three-axis motion system with integrated fluorescence spectrometer has completed the zeroing or origin positioning operation so that its current position is aligned with the origin (X_c, Y_c) of the physical coordinate system. The three-axis motion system consists of an XYZ slide table driven by a high-precision stepper motor or servo motor.

[0058] The motion control system reads the coordinate file of the scanning points, drives the fluorescence spectrometer to move to each scanning point according to the detection path, and sends a trigger signal to the fluorescence spectrometer after positioning. The motion control system reads the scan point coordinate file from the specified storage path, parses the file, and loads the physical coordinate sequence in it into memory in sequence to form a queue of detection points to be executed. After receiving the signal, the fluorescence spectrometer performs the elemental composition detection task at the current position. After the detection is completed, it returns a completion signal, and the motion system drives the fluorescence spectrometer to move to the next scanning point. This process is repeated until all scanning points are detected.

[0059] After the entire testing process is completed, the system automatically releases the pause state, resumes the printing program, and begins the construction of the next layer. Understandably, through the closed-loop linkage of the motion control system, fluorescence spectrometer, and central control module, a seamless conversion and precise execution of the digital testing path to the physical testing action is achieved. The high-precision three-axis positioning and synchronous triggering mechanism ensures the automatic acquisition of elemental composition data at each testing point, realizing a non-destructive, multi-point, fully automated testing process between printing layers, significantly improving the real-time performance and accuracy of process quality control.

[0060] like Figure 4 As shown, in a second aspect, the present invention also provides an image-assisted fluorescence spectroscopy detection system for additive manufacturing, which employs an image-assisted fluorescence spectroscopy detection method for additive manufacturing. The system includes: The preprocessing module is used to acquire slice images of the additive manufacturing parts to be inspected and perform image preprocessing to obtain a standardized image containing the outlines of several parts to be inspected. The image processing module is used to perform edge detection and contour recognition on standardized images using a pre-trained network model, extract the center coordinates and corresponding vertex coordinates of each part contour in the image coordinate system, and construct an image coordinate set. The coordinate transformation module is used to obtain the transformation ratio coefficient between the image coordinate system and the actual physical coordinate system through multi-point calibration, establish a linear mapping relationship between the two, and transform the image coordinate set into the actual coordinate set based on the linear mapping relationship. The path planning module is used to generate a detection path covering all areas to be detected based on the center coordinates, vertex coordinates, and detection spot size of each contour in the actual coordinate set, using a honeycomb serpentine path arrangement algorithm, and outputs a scan point coordinate file. The motion control module is used to control the motion system to read the coordinate file of the scanning points, drive the fluorescence spectrometer to move to each scanning point according to the detection path, and trigger the spectral acquisition in sequence to complete the elemental composition detection.

[0061] It should be noted that this system corresponds to the above-mentioned image-assisted fluorescence spectroscopy detection method for additive manufacturing. All implementation methods in the above method embodiments are applicable to the embodiments of this system and can achieve the same technical effect.

[0062] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0063] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the system and modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0064] In the embodiments provided by this invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0065] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0066] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0067] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0068] Furthermore, it should be noted that in the system and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent solutions of the present invention. Moreover, the steps performing the above series of processes can naturally be executed in the order described, but are not necessarily required to be executed in chronological order; some steps can be executed in parallel or independently of each other. Those skilled in the art will understand that all or any step or component of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or network of computing devices, in hardware, firmware, software, or a combination thereof. This is something that those skilled in the art can achieve by using their basic programming skills after reading the description of the present invention.

[0069] Therefore, the object of the present invention can also be achieved by running a program or a set of programs on any computing system. The computing system can be a known general-purpose system. Therefore, the object of the present invention can also be achieved simply by providing a program product containing program code implementing the method or apparatus. That is, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent to the present invention. Furthermore, the steps performing the above series of processes can naturally be performed in the order described, but are not necessarily required to be performed in chronological order. Some steps can be performed in parallel or independently of each other.

[0070] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An image-assisted fluorescence spectroscopy detection method for additive manufacturing, characterized in that, Includes the following steps: S1. Obtain a slice image of the additive manufacturing part to be inspected and perform image preprocessing to obtain a standardized image containing the outlines of several parts to be inspected. S2, a pre-trained network model is used to perform edge detection and contour recognition on the standardized image, extract the center coordinates and corresponding vertex coordinates of each part contour in the image coordinate system, and construct an image coordinate set; S3. The transformation ratio coefficient between the image coordinate system and the actual physical coordinate system is obtained by multi-point calibration method, and a linear mapping relationship between the two is established. Based on the linear mapping relationship, the image coordinate set is converted into the actual coordinate set. S4. Based on the center coordinates, vertex coordinates, and detection spot size of each contour in the actual coordinate set, a honeycomb serpentine path arrangement algorithm is used to generate a detection path covering all areas to be detected, and the scan point coordinate file is output. S5 controls the motion system to read the scanning point coordinate file, drives the fluorescence spectrometer to move to each scanning point according to the detection path, and triggers spectral acquisition in sequence to complete the elemental composition detection.

2. The image-assisted fluorescence spectroscopy detection method for additive manufacturing as described in claim 1, characterized in that, Step S1 includes the following sub-steps: Obtain slice images of the additively manufactured part to be inspected; Based on the HSV color space model, an HSV threshold range corresponding to the positioning boundary color is set; a color segmentation algorithm is used to extract the positioning boundary region. The image within the positioning boundary area is cropped and adjusted to a preset standard size to obtain a standardized image containing the outlines of several parts to be inspected.

3. The image-assisted fluorescence spectroscopy detection method for additive manufacturing as described in claim 1, characterized in that, Step S3, which describes obtaining the transformation ratio between the image coordinate system and the actual physical coordinate system using a multi-point calibration method, includes the following sub-steps: Select multiple reference points distributed on the slice image and obtain their coordinates in the image coordinate system; Measure the actual coordinates of each reference point in the physical coordinate system; calculate the ratio of the corresponding distances of each reference point in the image coordinate system and the physical coordinate system to obtain multiple scaling factors; The least squares method is used to perform linear regression fitting on multiple scaling coefficients to obtain the final transformation scaling coefficients between the image coordinate system and the actual physical coordinate system.

4. The image-assisted fluorescence spectroscopy detection method for additive manufacturing as described in claim 3, characterized in that: Step S3, which involves selecting multiple distributed reference points on the slice image, includes: Copper foil is arranged around the edge of the printing substrate as a boundary reference point for spatial positioning on the slice image; The fluorescence spectrometer is controlled to scan its spot on the printed substrate; When the light spot crosses the edge of the copper foil, the copper element signal intensity undergoes a step change, and the peak value of the first derivative of the copper element signal is taken as the physical boundary of the printed substrate.

5. The image-assisted fluorescence spectroscopy detection method for additive manufacturing as described in claim 4, characterized in that: The establishment of a linear mapping relationship between the two in step S3, and the conversion of the image coordinate set into the actual coordinate set based on the linear mapping relationship, includes the following sub-steps: obtaining the actual coordinates corresponding to the center point of the printed substrate in the physical coordinate system; calculating the physical coordinates after image coordinate conversion by multiplying the image coordinates with the final conversion scaling factor and adding it to the actual coordinates corresponding to the center point of the printed substrate in the physical coordinate system; and constructing the actual coordinate set based on the converted actual physical coordinates.

6. The image-assisted fluorescence spectroscopy detection method for additive manufacturing as described in claim 5, characterized in that, Step S4 includes the following sub-steps: Calculate the actual width and height of each part's outline based on the vertex coordinates, and compare the actual width and height with the spot size; If the actual width and height are both smaller than the spot size, the part outline is determined to be a small area, and the center point of the part outline is taken as the only scanning point. If the actual width and height are greater than the spot size, the part outline is determined to be a large area. The X-direction scanning step size is set to be equal to the spot diameter, and the Y-direction scanning step size is set to be equal to a preset ratio multiple of the spot diameter. Based on the center coordinates of the part's contour, and according to the X-direction scanning step size, Y-direction scanning step size, and the width and height of the part's contour image, the tangency between the light spot edge and the image boundary is used as a constraint condition. The light spot diameter is dynamically adjusted, and an initial rectangular scanning point array covering the part's contour is generated. The initial rectangular scanning point array is misaligned by adjusting the X coordinates of all scanning points in even or odd rows, shifting them in the X direction by a spot radius, so that the scanning points in adjacent rows are staggered in the X direction, forming a honeycomb distribution. All scan points are connected row by row to form a detection path, and the paths of adjacent rows are connected in opposite directions to form a serpentine reciprocating scan path.

7. The image-assisted fluorescence spectroscopy detection method for additive manufacturing as described in claim 6, characterized in that, Step S4 also includes the following sub-steps: Calculate the distance between the rightmost column of scan points in the initial rectangular scan point array and the right boundary of the contour. If the distance is greater than 0, add a column of scan points to the right boundary. Calculate the distance between the bottom row of scan points in the initial rectangular scan point array and the bottom boundary of the contour. If the distance is greater than 0, add a row of scan points at the bottom boundary. Finally, a detection path covering all areas to be detected is generated.

8. The image-assisted fluorescence spectroscopy detection method for additive manufacturing as described in claim 1, characterized in that, Step S5 includes the following sub-steps: By integrating the fluorescence spectrometer into the motion control system, the motion control system is used to move the fluorescence spectrometer along three axes; The motion control system reads the coordinate file of the scanning points, drives the fluorescence spectrometer to move to each scanning point according to the detection path, and sends a trigger signal to the fluorescence spectrometer after positioning. After receiving the signal, the fluorescence spectrometer performs the elemental composition detection task at the current position. After the detection is completed, it returns a completion signal, and the motion system drives the fluorescence spectrometer to move to the next scanning point. This process is repeated until all scanning points are detected.

9. An image-assisted fluorescence spectroscopy detection system for additive manufacturing, implemented using the image-assisted fluorescence spectroscopy detection method for additive manufacturing as described in any one of claims 1-8, characterized in that, The system includes: The preprocessing module is used to acquire slice images of the additive manufacturing parts to be inspected and perform image preprocessing to obtain a standardized image containing the outlines of several parts to be inspected. The image processing module is used to perform edge detection and contour recognition on standardized images using a pre-trained network model, extract the center coordinates and corresponding vertex coordinates of each part contour in the image coordinate system, and construct an image coordinate set. The coordinate transformation module is used to obtain the transformation ratio coefficient between the image coordinate system and the actual physical coordinate system through multi-point calibration, establish a linear mapping relationship between the two, and transform the image coordinate set into the actual coordinate set based on the linear mapping relationship. The path planning module is used to generate a detection path covering all areas to be detected based on the center coordinates, vertex coordinates, and detection spot size of each contour in the actual coordinate set, using a honeycomb serpentine path arrangement algorithm, and outputs a scan point coordinate file. The motion control module is used to control the motion system to read the coordinate file of the scanning points, drive the fluorescence spectrometer to move to each scanning point according to the detection path, and trigger the spectral acquisition in sequence to complete the elemental composition detection.

10. A computer-readable storage medium, characterized in that, The storage medium stores a program for an image-assisted fluorescence spectroscopy detection method for additive manufacturing, which, when executed, implements the image-assisted fluorescence spectroscopy detection method for additive manufacturing as described in any one of claims 1-8.

Images