Dynamic compensation laser power calibration method and system

Abstract

The invention provides a dynamic compensation laser power calibration method and system, and the method comprises the steps: enabling the laser rated power to be increased according to a fixed step length according to the type of a powder material, and collecting the infrared heat radiation image data of a power point of each step length; extracting an effective area and calculating heat radiation intensity data; extracting features of splashing areas of the infrared thermal radiation images and identifying and marking the splashing areas; judging whether the splash area coverage rate is smaller than a threshold value or not, and if yes, replacing the data of the current splash frame with the thermal radiation intensity data of the previous effective frame; obtaining thermal radiation intensity standard continuous data corresponding to each powder material; fitting is carried out according to the thermal radiation intensity standard continuous data corresponding to each powder material and the laser power, and the optimal power point of the power value corresponding to each powder material is obtained; according to the method, the laser power of powder of different materials can be calibrated, errors are avoided, optical signal interference caused by powder splashing is eliminated, and therefore the laser power calibration effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of powder bed fusion in 3D printing, and particularly to a laser power calibration method and system with dynamic compensation. Background Art

[0002] In 3D printing, the power of the laser beam plays a crucial role. Especially in additive manufacturing (AM) technologies such as selective laser sintering (SLS) and selective laser melting (SLM), the laser beam, as an energy source, directly affects the melting, solidification, and printing accuracy of materials; in 3D printing, the power of the laser beam is a key control parameter that affects multiple aspects such as the melting of materials, printing speed, accuracy, and the performance of the final object; by precisely controlling the laser power, the printing process can be effectively optimized to ensure the quality, strength, and details of the printed object, while improving production efficiency; therefore, reasonably adjusting the laser power and coordinating it with other printing parameters is the core of high-quality additive manufacturing.

[0003] A laser device power automatic calibration system and method with the publication number CN117154537A. The automatic calibration system includes: a laser device and a power identification unit; an automatic calibration function module is provided inside the laser device; after the laser device outputs laser, the power identification unit identifies the power value of the laser output by the laser device and sends it to the laser device; after the laser device receives the power value feedback from the power identification unit, the automatic calibration function module calibrates the output power based on the relationship between the output power, the working temperature of the laser, and the output current.

[0004] Currently, laser devices in the 3D printing industry are power-calibrated at the factory. However, due to the influence of factors such as the use, storage, and installation and operation environment of the laser device, there is a certain error between the power of the laser beam reaching the material surface and the actual set power. In order to reduce the error, it is necessary to calibrate the power of each output laser when the laser is installed on the printing device. However, traditional laser power calibration uses the same power calibration data for different material powders, resulting in errors and being not applicable to high-precision devices. Moreover, the optical signal interference caused by powder splashing has not been effectively eliminated, thus reducing the effect of laser power calibration. Summary of the Invention

[0005] In view of this, the present invention proposes a laser power calibration method and system with dynamic compensation, which can calibrate the laser power of different material powders, avoid errors, be applicable to high-precision devices, and eliminate the optical signal interference caused by powder splashing, thereby improving the effect of laser power calibration.

[0006] The technical solution of the present invention is realized as follows: In the first aspect, the present invention provides a laser power calibration method with dynamic compensation, and the method includes the following steps:

[0007] S1. According to the type of powder material, increase the laser rated power in fixed steps, and sequentially collect the infrared thermal radiation image data corresponding to each power point of the steps.

[0008] S2. Preprocess each infrared thermal radiation image data, extract the effective region and calculate the thermal radiation intensity data.

[0009] S3. Process each infrared thermal radiation image data using a spatter detection algorithm, extract the spatter region features and identify and mark the spatter regions.

[0010] S4. Preset a spatter region coverage rate threshold. According to each infrared thermal radiation image data, judge whether the spatter region coverage rate is less than the threshold. If it is less, use the thermal radiation intensity data of the previous valid frame to replace the data of the current spatter frame; otherwise, trigger the laser to pause and re-spread the powder for collection to obtain the standard continuous thermal radiation intensity data corresponding to each powder material.

[0011] S5. Fit according to the standard continuous thermal radiation intensity data corresponding to each powder material and the laser power, and obtain the optimal power point of the power value corresponding to each powder material according to the fitting result.

[0012] Based on the above technical solutions, preferably, in step S1, the operation of increasing the laser rated power in fixed steps according to the type of powder material and sequentially collecting the infrared thermal radiation image data corresponding to each power point of the steps includes:

[0013] Perform separate laser power calibration according to different types of powder materials.

[0014] Start the rated power of the laser from 10% and gradually increase it to 100% rated power, and increase it sequentially in fixed steps.

[0015] Irradiate continuously for a fixed duration at each power point of the steps, and wait for an interval duration before scanning and collecting the next power point.

[0016] During the continuous period of each power point of the steps, use an image acquisition device equipped with a corresponding infrared band-pass filter to collect multiple frames of infrared thermal radiation image data.

[0017] Based on the above technical solutions, preferably, in step S2, the operation of preprocessing each infrared thermal radiation image data, extracting the effective region and calculating the thermal radiation intensity data includes the following sub-steps:

[0018] S21. Perform Gaussian filtering on each infrared thermal radiation image data, perform binary processing on the filtered image using a segmentation algorithm, extract the largest connected region, and expand outward along the boundary of the largest connected region to obtain the effective region.

[0019] S22. Collect the infrared background image in the state without laser irradiation, and calculate the thermal radiation intensity data of the effective area according to the infrared background image and the infrared thermal radiation image data. The expression is:

[0020] I t = ∑(x,y)∈ROI [I c (x,y) - I b (x,y)] × T(λ)

[0021] In the formula, I t represents the thermal radiation intensity in the effective area, ∑(x,y)∈ROI represents traversing and summing all pixel points in the effective area, I c (x,y) represents the intensity value at the pixel point (x,y) in the effective area in the current infrared thermal radiation image, I b (x,y) represents the intensity value at the pixel point (x,y) at the corresponding position in the infrared background image, I c (x,y) - I b (x,y) represents the net thermal signal after removing the background noise; T(λ) represents the wavelength correction coefficient.

[0022] Based on the above technical solution, preferably, in step S21, the filtered image is binarized by using a segmentation algorithm to extract the largest connected region, including the following sub-steps:

[0023] S211. Obtain the infrared thermal radiation image data after Gaussian filtering, and binarize the filtered image to obtain a grayscale image;

[0024] S212. Count the number of pixels at each gray level in the grayscale image, and calculate the probability distribution at each gray level. The expression is:

[0025] p(i) = g(i) / n

[0026] In the formula, p(i) represents the probability distribution value at each gray level, g(i) represents the number of pixels at the gray level i, and n represents the total number of pixels;

[0027] S213. Preset an array of segmentation thresholds, and segment the grayscale image into a background class and a foreground class according to each segmentation threshold, and calculate the pixel proportion and average gray value of the background class and the foreground class respectively. Among them,

[0028] The expression for the pixel proportion of the background class is:

[0029]

[0030] In the formula, t is the segmentation threshold;

[0031] The average gray value expression of the background class is:

[0032]

[0033] The pixel proportion expression of the foreground class is:

[0034] w1 = 1 - w0;

[0035] The average gray value expression of the foreground class is:

[0036]

[0037] S214. Calculate the between-class variance σ according to the pixel proportion and average gray value of the background class and foreground class corresponding to each segmentation threshold, and obtain the maximum between-class variance value σ max , and use it as the optimal segmentation threshold T to segment the grayscale image corresponding to each infrared thermal radiation image, and the expression for extracting the largest connected region is:

[0038] σ 2 = w0 × w1 × (μ0 - μ1) 2 .

[0039] On the basis of the above technical solutions, preferably, in step S3, the splash detection algorithm is used to process the data of each infrared thermal radiation image, extract the splash area features and identify and mark the splash area, including the following sub-steps:

[0040] S31. Perform Gaussian filtering on the data of each infrared thermal radiation image to obtain a Gaussian filtered image;

[0041] S32. Obtain two consecutive frames of Gaussian filtered images corresponding to the same type of powder material, and perform pixel-by-pixel difference on the two consecutive frames of Gaussian filtered images to obtain a difference image, and the expression is:

[0042] D(x,y) = |I j+1 (x,y) - I j (x,y)|

[0043] In the formula, D(x,y) is the difference image, and I j (x,y) and I j+1 (x,y) are consecutive Gaussian filtered images;

[0044] S34. Perform threshold segmentation on the difference image according to the optimal segmentation threshold to generate a binary image B(x,y). Among them, if D(x,y) > T, then B(x,y) = 255, indicating that the pixel belongs to the moving area; if D(x,y) ≤ T, then B(x,y) = 0, indicating that the pixel belongs to the background area;

[0045] S34. Perform morphological operations on the binary image to obtain a binary enhanced image;

[0046] S35. Extract the connected regions in the binary enhanced image and mark the splash regions based on feature screening;

[0047] S36. In the corresponding infrared thermal radiation image, frame and highlight the splash regions.

[0048] Based on the above technical solutions, preferably, the step of extracting the connected regions in the binary enhanced image and marking the splash regions based on feature screening in step S35 includes the following sub-steps:

[0049] S351. Traverse each pixel in the binary image. If the pixel value is 255, check its 8-neighborhood pixels. If there are no marked pixels in the 8-neighborhood pixels, mark this pixel as a new connected region. If there are marked pixels in the 8-neighborhood pixels, mark this pixel as the connected region with the same minimum pixel value as in its 8-neighborhood, to obtain each connected region in the binary enhanced image;

[0050] S352. For each connected region, calculate the total number of internal pixels;

[0051] S353. Preset the connected region pixel threshold range. Compare the total number of internal pixels of each connected region with the boundary values of the connected region pixel threshold range to obtain the regions where the total number of internal pixels of the connected regions is between the connected region pixel threshold range, to obtain the first candidate splash regions;

[0052] S354. For each first candidate splash region, calculate the width and height of its circumscribed rectangle to obtain the aspect ratio of each first candidate splash region;

[0053] S355. Preset the connected region aspect ratio threshold range. Compare the aspect ratio of each first candidate splash region with the boundary values of the connected region aspect ratio threshold range to obtain the regions where the aspect ratio of the first candidate splash regions is between the connected region aspect ratio threshold range, to obtain the second candidate splash regions;

[0054] S356. For each second candidate splash region, calculate the average value of its internal difference image, and select a local window around the second candidate splash region according to it, calculate the difference mean and difference standard deviation of its local region, and calculate the local dynamic threshold according to the difference mean and difference standard deviation of the local region. The expression is:

[0055] T l =μ l +k l ×σ l

[0056] In the formula, Tl is the local dynamic threshold, μ l is the differential mean value of the local area, σ3 is the differential standard deviation of the local area, and k1 is an empirical coefficient;

[0057] S357. Compare the average value of the internal differential image of the second candidate splash area with the local dynamic threshold, obtain the area where the average value of the internal differential image of the second candidate splash area is greater than the local dynamic threshold, and obtain the final splash area.

[0058] Based on the above technical solutions, preferably, for the preset splash area coverage rate threshold in step S4, according to the infrared thermal radiation image data of each powder material, judge whether the splash area coverage rate is less than the threshold. If it is less than, use the thermal radiation intensity data of the previous valid frame to replace the data of the current splash frame; otherwise, trigger the laser to pause and re-powder for acquisition to obtain the standard continuous data of the thermal radiation intensity corresponding to each powder material, including the following sub-steps:

[0059] S41. Use the splash detection algorithm to detect the splash area in the infrared thermal radiation image data of each power point in real time, and record the time point and duration of the splash occurrence;

[0060] S42. When a splash area is detected, calculate the area of each splash area to obtain the total splash area, and calculate the splash area coverage rate according to the ratio of the total splash area to the total image area;

[0061] S43. Preset the splash area coverage rate threshold, judge whether the splash area coverage rate is less than the splash area coverage rate threshold. If it is less than, use the thermal radiation intensity data of the previous valid frame before the splash to replace the data of the current splash frame during each frame of the splash duration. Otherwise, trigger the laser to pause and re-powder for acquisition to obtain the standard continuous data of the thermal radiation intensity corresponding to each powder material.

[0062] Based on the above technical solutions, preferably, for the fitting according to the standard continuous data of the thermal radiation intensity corresponding to each powder material and the laser power in step S5, and obtaining the optimal power point of the power value corresponding to each powder material according to the fitting result, including the following sub-steps:

[0063] S51. Fit according to the standard continuous data of the thermal radiation intensity corresponding to each powder material and the laser power at the corresponding points to obtain a thermal radiation intensity fitting model, and the expression is:

[0064] I t = aP 2 + bP + c

[0065] In the formula, I tis the thermal radiation intensity value, a is the contribution intensity of the square of the laser power to the thermal accumulation, b is the contribution intensity of the linear term of the laser power to the thermal accumulation, P is the output power of the laser, and c is the basic thermal accumulation;

[0066] S52. According to the thermal radiation intensity fitting model, obtain the point with the largest change rate of the thermal radiation intensity value with respect to the change in laser power, and obtain the optimal power point corresponding to the power value of each powder material. The expression is:

[0067] P opt = ArgMaxP(dP / dI t )

[0068] In the formula, P opt is the optimal power point, and dP / dI t is the change rate of the thermal radiation intensity;

[0069] Associate each powder material with the optimal power point corresponding to the corresponding power value, and store it in the powder power calibration database for laser power calibration.

[0070] In a second aspect, the present invention also provides a laser power calibration system with dynamic compensation, which is implemented by using the laser power calibration method with dynamic compensation. The system includes:

[0071] An acquisition module, which is used to increase the rated laser power in a fixed step according to the type of powder material, and sequentially acquire the infrared thermal radiation image data corresponding to each step power point;

[0072] A data processing and conversion module, which is used to preprocess each infrared thermal radiation image data, extract the effective area and calculate the thermal radiation intensity data;

[0073] A spatter area extraction module, which is used to process each infrared thermal radiation image data by using a spatter detection algorithm, extract the spatter area characteristics and identify and mark the spatter area;

[0074] A data optimization module, which is used to preset a spatter area coverage threshold. According to each infrared thermal radiation image data, judge whether the spatter area coverage is less than the threshold. If it is less than, use the thermal radiation intensity data of the previous valid frame to replace the data of the current spatter frame; otherwise, trigger the laser to pause and re-powder and collect to obtain the standard continuous thermal radiation intensity data corresponding to each powder material;

[0075] A model construction module, which is used to fit according to the standard continuous thermal radiation intensity data corresponding to each powder material and the laser power, and obtain the optimal power point corresponding to the power value of each powder material according to the fitting result.

[0076] In a third aspect, the present invention also provides a computer-readable storage medium, on which a program for the dynamic compensation laser power calibration method is stored. When the program for the dynamic compensation laser power calibration method is executed, the dynamic compensation laser power calibration method is implemented.

[0077] The dynamic compensation laser power calibration method and system of the present invention have the following beneficial effects compared with the prior art:

[0078] (1) By gradually increasing the laser rated power and collecting infrared thermal radiation image data at each step power point, preprocessing the image data to extract the effective area and calculate the thermal radiation intensity, using the splash detection algorithm to identify and mark the splash area, presetting the splash area coverage threshold to dynamically compensate for the influence of splash on the thermal radiation intensity data, ensuring the acquisition of accurate and continuous thermal radiation intensity standard data, and finally obtaining the optimal power point of the corresponding power value for each powder material by fitting the relationship between the thermal radiation intensity and the laser power, it can not only be applicable to different powders for calibration, but also eliminate the optical signal interference caused by powder splash, thereby improving the accuracy and reliability of laser power calibration;

[0079] (2) Through differential detection, threshold segmentation and morphological operations, the splash area can be accurately extracted. Feature screening further improves the detection accuracy and reduces false detection and missed detection; Gaussian filtering and morphological operations can effectively suppress noise and improve the robustness of the algorithm. The adaptive threshold method and feature screening can adapt to different scenarios and image features, improving the generality of the algorithm;

[0080] (3) Through connected region marking, area screening, shape screening and intensity screening, the splash area can be accurately extracted. The multi-step screening mechanism effectively reduces false detection and missed detection and improves the detection accuracy. The use of local dynamic thresholds and empirical coefficients improves the adaptability of the algorithm and can cope with different scenarios and image features. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0082] Figure 1 It is a flowchart of the dynamic compensation laser power calibration method of the present invention;

[0083] Figure 2 It is a principle block diagram of the synchronization control unit of the dynamic compensation laser power calibration method of the present invention;

[0084] Figure 3 The infrared thermal radiation intensity image of the laser power calibration method with dynamic compensation of the present invention;

[0085] Figure 4 The infrared thermal radiation grayscale image after Gaussian filtering of the laser power calibration method with dynamic compensation of the present invention

[0086] Figure 5 The schematic diagram of the laser output power calibration data of the first embodiment of the laser power calibration method with dynamic compensation of the present invention;

[0087] Figure 6 The schematic diagram of the laser output power calibration data of the second embodiment of the laser power calibration method with dynamic compensation of the present invention. Detailed implementation manners

[0088] Next, in combination with the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than 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 efforts shall fall within the protection scope of the present invention.

[0089] As Figure 1 shown, in the first aspect, the present invention provides a laser power calibration method with dynamic compensation, and the method includes the following steps:

[0090] S1. According to the type of powder material, increase the rated power of the laser in a fixed step, and sequentially collect the infrared thermal radiation image data corresponding to each step power point.

[0091] Among them, step S1 includes:

[0092] Perform separate laser power calibration according to different types of powder materials;

[0093] Start the rated power of the laser from 10%, gradually increase it to 100% of the rated power, and increase it sequentially in a fixed step;

[0094] Irradiate for a fixed duration at each step power point, and wait for an interval duration before scanning and collecting the next power point;

[0095] During the duration of each step power point, use an image acquisition device equipped with a corresponding infrared band-pass filter to collect multiple frames of infrared thermal radiation image data.

[0096] It should be noted that according to the physical properties of the powder, it can be classified into metal powder, ceramic powder, etc. For each type of powder material, the laser power is calibrated independently to ensure the accuracy and uniqueness of the collected data. This laser device includes a powder box, and the powder box has N independent cavities. Different types of powder materials are stored in each independent cavity. And the laser device is internally equipped with a powder pushing mechanism driven by a stepping motor. The powder box is pushed to move on the guide rail through the powder pushing mechanism, and the corresponding independent cavity is moved to the laser processing area, so that different types of powder processing can be switched.

[0097] Moreover, 10% of the rated power of the laser is set as the initial power, and the laser power is gradually increased step by step at a fixed step of 10% until the rated power of 100% is reached. At each power point, the laser continuously irradiates for a fixed duration of 10 ms to ensure that the powder is fully heated. After the irradiation ends, wait for a fixed duration of 50 ms for thermal relaxation to stabilize the system and avoid the influence of heat accumulation on the data of the next power point.

[0098] As Figure 2 shown, in addition, a high-sensitivity infrared thermal imaging camera CCD or CMOS sensor with a frame rate ≥ 1000 fps is used, equipped with a detachable infrared band-pass filter. Among them, the central wavelength matches the laser wavelength, such as 1064 nm, and the bandwidth is ±20 nm, filtering infrared radiation of specific wavelengths to improve the image quality; during the duration of each power point, 100 frames of infrared thermal radiation image data are continuously collected to obtain stable thermal distribution information, and the collected image data is associated with information such as the corresponding laser power, powder material, and collection time for subsequent analysis.

[0099] It can be understood that it also includes a synchronous control unit, which is used to make the laser, camera, and powder box achieve millisecond-level timing synchronization through PLC or FPGA, ensure the precise synchronization of the power change of the laser and the start time of the image acquisition device, avoid data deviation, and conduct experiments in a dark room or with shading measures to reduce the influence of environmental infrared radiation on the image, and avoid strong air currents in the experimental area to prevent powder movement or heat dissipation from affecting the thermal distribution.

[0100] S2. Preprocess each infrared thermal radiation image data, extract the effective area and calculate the thermal radiation intensity data.

[0101] As Figure 3 and Figure 4 shown, step S2 includes the following sub-steps:

[0102] S21. Perform Gaussian filtering on each infrared thermal radiation image data, and perform binarization processing on the filtered image using a segmentation algorithm, extract the largest connected region, and expand outward along the boundary of the largest connected region to obtain the effective area;

[0103] S22. Collect the infrared background image in the state without laser irradiation, and calculate the thermal radiation intensity data of the effective area according to the infrared background image and the infrared thermal radiation image data. The expression is as follows:

[0104] I t = ∑(x,y)∈ROI [I c (x,y) - I b (x,y)] × T(λ)

[0105] In the formula, I t represents the thermal radiation intensity within the effective area, ∑(x,y)∈ROI represents the sum of all pixel points within the effective area after traversing, I c (x,y) represents the intensity value at the pixel point (x,y) in the current infrared thermal radiation image within the effective area, I b (x,y) represents the intensity value at the pixel point (x,y) at the corresponding position in the infrared background image, I c (x,y) - I b (x,y) represents the net thermal signal after removing the background noise; T(λ) represents the wavelength correction coefficient.

[0106] It should be noted that the Gaussian filter is used to perform convolution operations on each frame of the infrared thermal radiation image. Select an appropriate Gaussian kernel size and standard deviation, adjust according to the image resolution and noise level, convert the image into a binary image to facilitate the extraction of connected regions, identify the largest connected region in the image, which corresponds to the main region of laser action, calculate the area of each connected region, select the connected region with the largest area as the target region, and expand 5px outward along the boundary of the largest connected region to avoid edge effects and obtain the effective area.

[0107] The step of performing binary processing on the filtered image by using the segmentation algorithm in step S21 to extract the largest connected region includes the following sub-steps:

[0108] S211. Obtain the infrared thermal radiation image data after Gaussian filtering, and perform binary processing on the filtered image to obtain a grayscale image;

[0109] S212. Count the number of pixels at each gray level in the grayscale image, and calculate the probability distribution of each gray level. The expression is as follows:

[0110] p(i) = g(i) / n

[0111] In the formula, p(i) represents the probability distribution value of each gray level, g(i) represents the number of pixels at the gray level i, and n represents the total number of pixels;

[0112] S213. A preset segmentation threshold array is used to segment the grayscale image into a background class and a foreground class according to each segmentation threshold, and the pixel proportion and average grayscale value of the background class and the foreground class are calculated respectively. Among them,

[0113] The expression for the pixel proportion of the background class is:

[0114]

[0115] In the formula, t is the segmentation threshold;

[0116] The expression for the average grayscale value of the background class is:

[0117]

[0118] The expression for the pixel proportion of the foreground class is:

[0119] w1 = 1 - w0;

[0120] The expression for the average grayscale value of the foreground class is:

[0121]

[0122] S214. According to the pixel proportion and average grayscale value of the background class and the foreground class corresponding to each segmentation threshold, calculate the between-class variance σ, and obtain the maximum between-class variance value σ max , and use it as the optimal segmentation threshold T to segment the grayscale image corresponding to each infrared thermal radiation image, and extract the largest connected region. The expression is:

[0123] σ 2 = w0 × w1 × (μ0 - μ1) 2 .

[0124] It should be noted that the largest connected region can be effectively extracted from the infrared thermal radiation image, providing an accurate effective region for subsequent thermal radiation intensity calculation. The application of the between-class variance method improves the accuracy and robustness of the binarization process, ensuring the effectiveness and integrity of the extracted region.

[0125] S3. Use the splash detection algorithm to process the data of each infrared thermal radiation image, extract the splash region features and identify and mark the splash region;

[0126] The steps in S3 include the following sub-steps:

[0127] S31. Perform Gaussian filtering on the data of each infrared thermal radiation image to obtain a Gaussian filtered image;

[0128] S32. Obtain two consecutive frames of Gaussian filtered images corresponding to the same type of powder material, and perform pixel-by-pixel difference on the two consecutive frames of Gaussian filtered images to obtain a difference image. The expression is:

[0129] D(x,y) = |I j+1 (x,y) - I j (x,y)|

[0130] Wherein, D(x,y) is the difference image, and I j (x,y) and I j+1 (x,y) are consecutive Gaussian filtered images;

[0131] S34. Perform threshold segmentation on the difference image according to the optimal segmentation threshold to generate a binary image B(x,y). Wherein, if D(x,y) > T, then B(x,y) = 255, indicating that the pixel belongs to the moving region; if D(x,y) ≤ T, then B(x,y) = 0, indicating that the pixel belongs to the background region;

[0132] S34. Perform morphological operations on the binary image to obtain a binary enhanced image;

[0133] S35. Extract the connected regions in the binary enhanced image and mark the splash regions based on feature screening;

[0134] S36. Frame and highlight the splash regions in the corresponding infrared thermal radiation image.

[0135] It should be noted that Gaussian filtering is performed on each frame of the infrared thermal radiation image to obtain a Gaussian filtered image. An appropriate Gaussian kernel size and standard deviation are selected and adjusted according to the image resolution and noise level. The filtered image is smoother, reducing the influence of noise on the differential result; two consecutive frames of Gaussian filtered images corresponding to the same type of powder material are obtained, and pixel-by-pixel difference is performed on the two consecutive frames of images to obtain a difference image. In the difference image, the splash area will show obvious pixel value changes between consecutive frames. In the difference image, the splash area appears as a highlighted area, and the background area appears as a low-brightness or zero-value area; threshold segmentation is performed on the difference image according to the optimal segmentation threshold T to generate a binary image. Threshold segmentation can distinguish the splash area from the areas of minor changes or noise in the difference image. In the binary image, the splash area is white 255 and the background area is black 0, which is convenient for subsequent processing; morphological operations are performed on the binary image to eliminate noise and holes, including opening operation and closing operation. The opening operation first erodes and then dilates to eliminate isolated noise points. The closing operation first dilates and then erodes to fill small holes and connect adjacent areas. The binary enhanced image after morphological operations is clearer, the splash area is more complete, and the noise is effectively suppressed; the connected component labeling algorithm is used to label all connected components in the binary image, and the connected components with too small area are removed. These areas may be noise. Further shape feature screening is performed according to the aspect ratio of the shape features of the splash area. Considering the motion intensity of the splash area, motion feature screening is performed by combining the analysis of multi-frame information. The extracted connected components more accurately reflect the splash area, reducing false detection and missed detection; the selected splash area is mapped back to the original infrared thermal radiation image, and the splash area is framed and highlighted in different colors or brightness in the image. In the original infrared thermal radiation image, the splash area is clearly marked, which is convenient for observing and analyzing the splash phenomenon.

[0136] In this embodiment, through differential detection, threshold segmentation, and morphological operations, the splash area can be accurately extracted. Feature screening further improves the accuracy of detection, reducing false detection and missed detection; Gaussian filtering and morphological operations can effectively suppress noise and improve the robustness of the algorithm. The adaptive threshold method and feature screening can adapt to different scenarios and image features, improving the generality of the algorithm.

[0137] The step of extracting the connected components in the binary enhanced image and marking the splash area based on feature screening in step S35 includes the following sub-steps:

[0138] S351, traverse each pixel in the binary image. If the pixel value is 255, check its 8-neighborhood pixels. If there are no marked pixels in the 8-neighborhood pixels, mark this pixel as a new connected component. If there are marked pixels in the 8-neighborhood pixels, mark this pixel as the connected component with the same minimum pixel value as that in its 8-neighborhood, to obtain each connected component in the binary enhanced image;

[0139] S352. For each connected region, calculate the total number of internal pixels thereof;

[0140] S353. Preset a connected region pixel threshold range. Compare the total number of internal pixels of each connected region with the boundary values of the connected region pixel threshold range to obtain the regions where the total number of internal pixels of the connected regions is between the connected region pixel threshold ranges, and obtain the first candidate splash regions;

[0141] S354. For each first candidate splash region, calculate the width and height of its circumscribed rectangle to obtain the aspect ratio of each first candidate splash region;

[0142] S355. Preset a connected region aspect ratio threshold range. Compare the aspect ratio of each first candidate splash region with the boundary values of the connected region aspect ratio threshold range to obtain the regions where the aspect ratio of the first candidate splash regions is between the connected region aspect ratio threshold ranges, and obtain the second candidate splash regions;

[0143] S356. For each second candidate splash region, calculate the average value of its internal difference image, and select a local window around the second candidate splash region to calculate the difference mean and difference standard deviation of its local region. Calculate the local dynamic threshold according to the difference mean and difference standard deviation of the local region. The expression is:

[0144] T l = μ l + k l × σ l

[0145] In the formula, T l is the local dynamic threshold, μ l is the difference mean of the local region, σ3 is the difference standard deviation of the local region, and k1 is an empirical coefficient;

[0146] S357. Compare the average value of the internal difference image of the second candidate splash region with the local dynamic threshold to obtain the regions where the average value of the internal difference image of the second candidate splash region is greater than the local dynamic threshold, and obtain the final splash regions.

[0147] It should be noted that by traversing pixels and checking neighborhoods, the moving regions in the binary image are marked as connected regions, ensuring that each connected region has a unique identifier for subsequent processing. The splash regions usually have a certain area, and noise regions can be removed through area screening. The preset pixel threshold range can adapt to different scenarios and image features. The splash regions usually have specific shape features, and misdetected regions can be further removed through aspect ratio screening. The preset aspect ratio threshold range can improve the detection accuracy. The local dynamic threshold can consider the differential features of local regions and improve the adaptability of threshold segmentation. The empirical coefficient k1 can be adjusted according to the actual situation to optimize the threshold segmentation effect. The splash regions usually have a relatively high differential intensity, and misdetected regions can be further removed through intensity screening. The local dynamic threshold ensures the accuracy of screening.

[0148] It can be understood that through connected region marking, area screening, shape screening, and intensity screening, the splash regions can be accurately extracted. The multi-step screening mechanism effectively reduces misdetection and missed detection and improves the detection accuracy. The use of local dynamic threshold and empirical coefficient improves the adaptability of the algorithm and can handle different scenarios and image features.

[0149] Specifically, the pixel threshold range of the connected region in this embodiment is 10px 2 <Area < 1000px 2 ; the aspect ratio threshold range of the connected region is 1:3 < Aspect ratio < 3:1.

[0150] S4. Preset the splash region coverage rate threshold. According to the infrared thermal radiation image data of each power point, determine whether the splash region coverage rate is less than the threshold. If it is less than, use the thermal radiation intensity data of the previous valid frame to replace the data of the current splash frame; otherwise, trigger the laser to pause and re-powder for collection to obtain the standard continuous thermal radiation intensity data corresponding to each powder material.

[0151] Step S4 includes the following sub-steps:

[0152] S41. Use the splash detection algorithm to detect the splash regions in the infrared thermal radiation image data of each power point in real time, and record the time points and durations of splash occurrences.

[0153] S42. When splash regions are detected, calculate the areas of the splash regions to obtain the total splash region area, and calculate the splash region coverage rate according to the ratio of the total splash region area to the total image area.

[0154] S43. Preset the threshold of the spatter area coverage rate, and determine whether the spatter area coverage rate is less than the threshold of the spatter coverage area rate. If it is less than, for each frame during the spatter duration, use the thermal radiation intensity data of the pre-spatter valid frame to replace the data of the current spatter frame. Otherwise, trigger the laser to pause and re-powder collection to obtain the standard continuous data of the thermal radiation intensity corresponding to each powder material.

[0155] It should be noted that through threshold judgment and data correction, the influence of spatter on the thermal radiation intensity data is reduced, and the accuracy of the data is improved. When the spatter area coverage rate is small, the data of the pre-order valid frame is used for replacement, maintaining the continuity of the data, which is helpful for the coherence and consistency of the data during subsequent analysis. The laser pause and re-powder mechanism ensure the stability and reliability of the system when the spatter is severe.

[0156] S5. Fit according to the standard continuous data of the thermal radiation intensity corresponding to each powder material and the laser power, and obtain the optimal power point of the power value corresponding to each powder material according to the fitting result.

[0157] Step S5 includes the following sub-steps:

[0158] S51. Fit according to the standard continuous data of the thermal radiation intensity corresponding to each powder material and the laser power at the corresponding point to obtain the thermal radiation intensity fitting model, and the expression is:

[0159] I t =aP 2 +bP+c

[0160] In the formula, I t is the thermal radiation intensity value, a is the contribution intensity of the square of the laser power to the heat accumulation, b is the contribution intensity of the linear term of the laser power to the heat accumulation, P is the output power of the laser, and c is the basic heat accumulation;

[0161] S52. According to the thermal radiation intensity fitting model, obtain the point with the largest change rate of the thermal radiation intensity value with respect to the change of the laser power, and obtain the optimal power point of the power value corresponding to each powder material. The expression is:

[0162] P opt =ArgMaxP(dP / dI t )

[0163] In the formula, P opt is the optimal power point, and dP / dI t is the change rate of the thermal radiation intensity;

[0164] Associate each powder material with the optimal power point corresponding to the corresponding power value, and store it in the powder power calibration database for laser power calibration.

[0165] Such asFigure 5 Calibration data of the laser output power of 316L powder for the SLM250 device in Example 1; Figure 6 Calibration data of the laser output power of Ti6Al4V powder for the SLM250 device in Example 2.

[0166] It should be noted that the optimal power point corresponds to the point where the change rate of the laser power with respect to the change in the thermal radiation intensity value is the largest. That is, at this point, a small change in the laser power will result in a significant change in the thermal radiation intensity. By solving the point with the largest change rate, the optimal power point can be obtained, providing a basis for laser power calibration; a mathematical relationship between the thermal radiation intensity and the laser power is established through polynomial fitting to obtain a fitting model of the thermal radiation intensity. The fitting model can better describe the non-linear relationship between the thermal radiation intensity and the laser power. The optimal power point corresponds to the point where the change rate of the laser power with respect to the change in the thermal radiation intensity value is the largest. By solving the point with the largest change rate, the optimal power point can be obtained, improving the accuracy and reliability of laser power calibration.

[0167] In a second aspect, the present invention also provides a laser power calibration system with dynamic compensation, which is implemented by using the laser power calibration method with dynamic compensation. The system includes:

[0168] An acquisition module, configured to increase the laser rated power in a fixed step according to the type of powder material, and sequentially acquire infrared thermal radiation image data corresponding to each step power point;

[0169] A data processing and conversion module, configured to preprocess each infrared thermal radiation image data, extract the effective region and calculate the thermal radiation intensity data;

[0170] A spatter region extraction module, configured to process each infrared thermal radiation image data by using a spatter detection algorithm, extract spatter region features and identify and mark the spatter regions;

[0171] A data optimization module, configured to preset a spatter region coverage threshold, and determine whether the spatter region coverage is less than the threshold according to each infrared thermal radiation image data. If it is less than, the thermal radiation intensity data of the previous valid frame is used to replace the data of the current spatter frame; otherwise, the laser is paused and powder spreading is restarted for acquisition to obtain standard continuous thermal radiation intensity data corresponding to each powder material;

[0172] A model construction module, configured to perform fitting according to the standard continuous thermal radiation intensity data corresponding to each powder material and the laser power, and obtain the optimal power point of the power value corresponding to each powder material according to the fitting result.

[0173] It should be noted that this system corresponds to the above laser power calibration method with dynamic compensation. All implementation manners in the above method embodiments are applicable to the embodiments of this system and can also achieve the same technical effects.

[0174] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0175] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems and modules described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0176] In the embodiments provided by the present 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 example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical or other forms.

[0177] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0178] In addition, the functional units in the various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0179] When the above-mentioned functions are implemented in the form of 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 the present invention, in essence, or the part that contributes to the prior art or a part of this 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 for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0180] In addition, it should be noted that in the systems and methods of the present invention, obviously, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of the present invention. And, the steps of performing the above series of processes can naturally be executed in chronological order according to the described order, but it is not necessary to execute them in chronological order. Some steps can be executed in parallel or independently of each other. For those of ordinary skill in the art, it can be understood that all or any steps or components of the methods and devices of the present invention can be implemented in any computing device (including processors, storage media, etc.) or in a network of computing devices in the form of hardware, firmware, software, or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0181] 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 well-known general system. Therefore, the object of the present invention can also be achieved only by providing a program product containing program codes for implementing the method or device. That is to say, 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 well-known storage medium or any storage medium developed in the future. It should also be noted that in the devices and methods of the present invention, obviously, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of the present invention. And, the steps of performing the above series of processes can naturally be executed in chronological order according to the described order, but it is not necessary to execute them in chronological order. Some steps can be executed in parallel or independently of each other.

[0182] The above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A dynamic compensation-based laser power calibration method, characterized in that: The method includes the following steps: S1. According to the type of powder material, increase the laser rated power in a fixed step, and sequentially collect the infrared thermal radiation image data corresponding to each step power point; S2. Preprocess each infrared thermal radiation image data, extract the effective area and calculate the thermal radiation intensity data; S3. Use a splash detection algorithm to process each infrared thermal radiation image data, extract the splash area features and identify and mark the splash area; S4. Preset a splash area coverage threshold. According to each infrared thermal radiation image data, judge whether the splash area coverage is less than the threshold. If it is less, use the thermal radiation intensity data of the previous valid frame to replace the data of the current splash frame; otherwise, trigger the laser to pause and re-powder and collect to obtain the standard continuous thermal radiation intensity data corresponding to each powder material; S5. Fit according to the standard continuous thermal radiation intensity data and the laser power corresponding to each powder material, and obtain the optimal power point of the power value corresponding to each powder material according to the fitting result.

2. The dynamic compensation-based laser power calibration method according to claim 1, wherein, In step S1, the step of increasing the laser rated power in a fixed step according to the type of powder material and sequentially collecting the infrared thermal radiation image data corresponding to each step power point includes: Perform separate laser power calibration according to different types of powder materials; Start the rated power of the laser from 10% and gradually increase it to 100% rated power, and increase it sequentially in a fixed step; Continuously irradiate for a fixed duration at each step power point, and wait for an interval duration before scanning and collecting the next power point; During the duration of each step power point, use an image acquisition device equipped with a corresponding infrared band-pass filter to collect multiple frames of infrared thermal radiation image data.

3. The dynamic compensation-based laser power calibration method according to claim 1, wherein In step S2, the sub-steps of preprocessing each infrared thermal radiation image data, extracting the effective area and calculating the thermal radiation intensity data include: S21. Perform Gaussian filtering on each infrared thermal radiation image data, and use a segmentation algorithm to perform binary processing on the filtered image, extract the largest connected area, and expand outward along the boundary of the largest connected area to obtain the effective area; S22. Collect an infrared background image in the state of no laser irradiation, and calculate the thermal radiation intensity data of the effective area according to the infrared background image and the infrared thermal radiation image data. The expression is: I t = ∑(x,y)∈ROI [I c (x,y) - I b (x,y)] × T(λ) Wherein, I t represents the thermal radiation intensity within the effective region, ∑(x,y)∈ROI represents the summation by traversing all pixel points within the effective region, and I c (x,y) represents the intensity value at the pixel point (x,y) within the effective region in the current infrared thermal radiation image, and I b (x,y) represents the intensity value at the pixel point (x,y) at the corresponding position in the infrared background image, and I c (x,y) - I b (x,y) represents the net thermal signal after removing background noise; T(λ) represents the wavelength correction coefficient.

4. The dynamic compensation-based laser power calibration method according to claim 3, characterized in that, In step S21, the sub-steps of using a segmentation algorithm to perform binary processing on the filtered image and extracting the largest connected area include: S211. Obtain the infrared thermal radiation image data after Gaussian filtering, and perform binary processing on the filtered image to obtain a grayscale image; S212. Count the number of pixels of each gray level in the grayscale image, and calculate the probability distribution of each gray level. The expression is: p(i) = g(i) / n In the formula, p(i) represents the probability distribution value of each gray level, g(i) represents the number of pixels with gray level i, and n represents the total number of pixels; S213. Preset a segmentation threshold array, segment the grayscale image into a background class and a foreground class according to each segmentation threshold respectively, and calculate the pixel proportion and average gray value of the background class and the foreground class respectively. Among them, The expression for the pixel proportion of the background class is: where t is the segmentation threshold; The expression for the average gray value of the background class is: The expression for the pixel proportion of the foreground class is: w1 = 1 - w0; The expression for the average gray value of the foreground class is: S214. Calculate the between-class variance σ based on the pixel proportion and average gray value of the background class and foreground class corresponding to each segmentation threshold, and obtain the maximum between-class variance value σ max , and use it as the optimal segmentation threshold T to segment the grayscale image corresponding to each infrared thermal radiation image, and extract the largest connected region. The expression is as follows: σ 2 = w0 × w1 × (μ0 - μ1) 2 .

5. The dynamic compensation-based laser power calibration method according to claim 4, characterized in that, In step S3, the splash detection algorithm is used to process each infrared thermal radiation image data, extract the splash area features and identify and mark the splash area, including the following sub-steps: S31, Perform Gaussian filtering on each infrared thermal radiation image data to obtain a Gaussian filtered image; S32, Obtain two consecutive frames of Gaussian filtered images corresponding to the same type of powder material, and perform pixel-by-pixel difference on the two consecutive frames of Gaussian filtered images to obtain a difference image, and the expression is: D(x,y) = |I j+1 (x,y) - I j (x,y)| where D(x, y) is the difference image, and I j (x, y) and I j+1 (x, y) are consecutive Gaussian filtered images; S34, Perform threshold segmentation on the difference image according to the optimal segmentation threshold to generate a binary image B(x, y). Among them, if D(x, y) > T, then B(x, y) = 255, indicating that the pixel belongs to the motion area; if D(x, y) ≤ T, then B(x, y) = 0, indicating that the pixel belongs to the background area; S34, Perform morphological operations on the binary image to obtain a binary enhanced image; S35, Extract the connected regions in the binary enhanced image and mark the splash area based on feature screening; S36, Frame and highlight the splash area in the corresponding infrared thermal radiation image.

6. The dynamic compensation-based laser power calibration method according to claim 5, wherein, In step S35, the connected regions in the binary enhanced image are extracted and the splash area is marked based on feature screening, including the following sub-steps: S351, Traverse each pixel in the binary image. If the pixel value is 255, check its 8-neighborhood pixels. If there are no marked pixels in the 8-neighborhood pixels, mark the pixel as a new connected region. If there are marked pixels in the 8-neighborhood pixels, mark the pixel as the connected region with the same minimum pixel value as its 8-neighborhood to obtain each connected region in the binary enhanced image; S352, For each connected region, calculate the total number of internal pixels; S353, Preset the connected region pixel threshold range. Compare the total number of internal pixels of each connected region with the boundary values of the connected region pixel threshold range to obtain the region where the total number of internal pixels of the connected region is within the connected region pixel threshold range, and obtain the first candidate splash area; S354, For the first candidate splash area, calculate the width and height of its circumscribed rectangle to obtain the aspect ratio of each first candidate splash area; S355, Preset the connected region aspect ratio threshold range. Compare the aspect ratio of each first candidate splash area with the boundary values of the connected region aspect ratio threshold range to obtain the region where the aspect ratio of the first candidate splash area is within the connected region aspect ratio threshold range, and obtain the second candidate splash area; S356, For each second candidate splash area, calculate the average value of its internal difference image, and select a local window around the second candidate splash area, calculate the differential mean and differential standard deviation of its local area, and calculate the local dynamic threshold according to the differential mean and differential standard deviation of the local area, and the expression is: T l = μ l + k l × σ l Wherein, T l is the local dynamic threshold, μ l is the differential mean of the local area, σ3 is the differential standard deviation of the local area, and k1 is an empirical coefficient; S357. Compare the average value of the internal differential image of the second candidate spatter area with the local dynamic threshold, and obtain the area where the average value of the internal differential image of the second candidate spatter area is greater than the local dynamic threshold, thereby obtaining the final spatter area.

7. The dynamic compensation-based laser power calibration method according to claim 1, wherein In step S4, for the preset spatter area coverage rate threshold, based on the infrared thermal radiation image data of each frame, determine whether the spatter area coverage rate is less than the threshold. If it is less than the threshold, use the thermal radiation intensity data of the previous valid frame to replace the data of the current spatter frame; otherwise, trigger the laser to pause and re-powder for collection to obtain the standard continuous thermal radiation intensity data corresponding to each powder material. This includes the following sub-steps: S41. Use the spatter detection algorithm to detect the spatter area in the infrared thermal radiation image data of each power point in real time, and record the time point and duration of spatter occurrence. S42. When a spatter area is detected, calculate the area of each spatter area to obtain the total spatter area, and calculate the spatter area coverage rate based on the ratio of the total spatter area to the total image area. S43. Preset the spatter area coverage rate threshold, and determine whether the spatter area coverage rate is less than the spatter area coverage rate threshold. If it is less than the threshold, for each frame during the spatter duration, use the thermal radiation intensity data of the previous valid frame before spatter to replace the data of the current spatter frame; otherwise, trigger the laser to pause and re-powder for collection to obtain the standard continuous thermal radiation intensity data corresponding to each powder material.

8. The dynamic compensation-based laser power calibration method according to claim 7, wherein, In step S5, the fitting based on the standard continuous thermal radiation intensity data corresponding to each powder material and the laser power, and obtaining the optimal power point corresponding to the power value of each powder material according to the fitting result, includes the following sub-steps: S51. Fit the standard continuous thermal radiation intensity data corresponding to each powder material and the laser power at the corresponding points to obtain a thermal radiation intensity fitting model, and the expression is: I t = aP 2 + bP + c Where, I t is the thermal radiation intensity value, a is the contribution intensity of the square of the laser power to the thermal accumulation, b is the contribution intensity of the linear term of the laser power to the thermal accumulation, P is the output power of the laser, and c is the basic thermal accumulation; S52. According to the thermal radiation intensity fitting model, obtain the point where the change rate of the thermal radiation intensity value with respect to the change in laser power is the largest, and obtain the optimal power point corresponding to the power value of each powder material. The expression is: P opt = ArgMaxP(dP / dI t ) Where P opt is the optimal power point, and dP / dI t is the change rate of the thermal radiation intensity; Associate each powder material with the optimal power point corresponding to the corresponding power value, and store it in the powder power calibration database for laser power calibration.

9. A laser power calibration system with dynamic compensation, which is implemented by using the dynamic compensation laser power calibration method according to any one of claims 1 to 8, characterized in that, The system includes: An acquisition module, which is used to increase the laser rated power in a fixed step according to the powder material type, and sequentially acquire the infrared thermal radiation image data corresponding to each step power point. A data processing and conversion module, which is used to preprocess the infrared thermal radiation image data of each frame, extract the effective area and calculate the thermal radiation intensity data. A spatter area extraction module, which is used to process the infrared thermal radiation image data of each frame by using the spatter detection algorithm, extract the spatter area characteristics and identify and mark the spatter area. A data optimization module, which is used to preset the spatter area coverage rate threshold, and based on the infrared thermal radiation image data of each frame, determine whether the spatter area coverage rate is less than the threshold. If it is less than the threshold, use the thermal radiation intensity data of the previous valid frame to replace the data of the current spatter frame; otherwise, trigger the laser to pause and re-powder for collection to obtain the standard continuous thermal radiation intensity data corresponding to each powder material. A model construction module, which is used to perform fitting based on the continuous data of the thermal radiation intensity standard corresponding to each powder material and the laser power, and obtain the optimal power point of the power value corresponding to each powder material according to the fitting result.

10. A computer-readable storage medium, characterized in that, A program of a dynamic compensation laser power calibration method is stored on the storage medium, and when the program of the dynamic compensation laser power calibration method is executed, the dynamic compensation laser power calibration method according to any one of claims 1 to 8 is implemented.

Images