A method and apparatus for detecting a melt pool type of laser printing

Abstract

This invention discloses a method and apparatus for detecting the type of molten pool in laser printing, comprising: acquiring an image of the molten pool captured by an image device when a laser head prints on a substrate in a calibrated printing direction; acquiring a laser beam angle signal captured by a laser beam angle detection component associated with the laser head; extracting features from the molten pool image to obtain molten pool reflection features, and extracting features from the laser beam angle signal to obtain laser beam angle features; and determining the type of the molten pool based on the molten pool reflection features, the laser beam angle features, and the printing direction. By acquiring the molten pool image and laser beam angle signal during the printing process, and accurately identifying the type of the molten pool based on the features extracted from the molten pool image and laser beam angle signal, automated detection of the molten pool is achieved, avoiding misjudgments caused by manual identification.

Description

Technical Field

[0001] This invention relates to the field of 3D printing technology, and in particular to a method and apparatus for detecting the molten pool type in laser printing. Background Technology

[0002] Direct energy deposition (DED), also known as 3D printing powder feeding technology, is an additive manufacturing method that plays a crucial role in the manufacture of components such as fuel nozzles and turbine blades within the aerospace industry. In current industrial applications, DED often involves layer-by-layer processing over long periods, with multiple cycles and high number of cycles. Therefore, ensuring the density of each printed layer is essential to avoid interlayer porosity. This makes real-time monitoring of the molten pool state crucial. If process parameters can be adjusted promptly when molten pool collapses or bulges occur, problems such as poor print quality and numerous porosity defects can be avoided, improving production efficiency and processing reliability.

[0003] In traditional molten pool condition detection, non-real-time monitoring methods such as cross-sectional quality monitoring or real-time monitoring methods based on visual monitoring or temperature sensors are often used. However, the above monitoring methods require human visual judgment or indirect judgment based on temperature curves to determine whether molten pool collapse has occurred. With the rapid development of optical information technology, there is an urgent need for a monitoring method that can directly reflect the degree of collapse. Summary of the Invention

[0004] This invention provides a method and apparatus for detecting the molten pool type in laser printing, so as to achieve accurate detection of the molten pool type.

[0005] According to a first aspect of the present invention, a method for detecting the molten pool type of laser printing is provided, the method comprising: acquiring an image of the molten pool captured by an image device when a laser head prints on a substrate in a calibrated printing direction;

[0006] Acquire the laser beam angle signal collected by the laser beam angle detection component associated with the laser head;

[0007] Feature extraction is performed on the image of the molten metal pool to obtain the reflection features of the molten pool, and feature extraction is performed on the laser beam angle signal to obtain the laser beam angle features;

[0008] The type of molten metal pool is determined based on the molten pool reflection characteristics, the laser beam angle characteristics, and the printing direction.

[0009] According to another aspect of the present invention, a laser printing molten pool type detection device is provided, the device comprising: a molten pool image acquisition module, used to acquire a molten pool image collected by an image device when the laser head prints on a substrate in a calibrated printing direction;

[0010] A laser beam angle signal acquisition module is used to acquire the laser beam angle signal collected by the laser beam angle detection component associated with the laser head;

[0011] The feature extraction module is used to extract features from the molten metal pool image to obtain the molten pool reflection features, and to extract features from the laser beam angle signal to obtain the laser beam angle features;

[0012] The molten pool type determination module is used to determine the type of the molten pool based on the molten pool reflection characteristics, the laser beam angle characteristics, and the printing direction.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: one or more processors;

[0014] Storage device for storing one or more programs.

[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any embodiment of the present invention.

[0016] According to another aspect of the present invention, a storage medium for computer-executable instructions is provided, on which a computer program is stored, which, when executed by a processor, implements the method described in any of the embodiments of the present invention.

[0017] The technical solution of the present invention acquires the image of the molten metal pool and the laser beam angle signal during the printing process, and accurately identifies the type of the molten metal pool based on the features extracted from the image of the molten metal pool and the laser beam angle signal, thereby realizing automated detection of the molten metal pool and avoiding misjudgment caused by manual identification.

[0018] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0020] Figure 1 This is a flowchart of a laser printing melt pool type detection method according to Embodiment 1 of the present invention;

[0021] Figure 2 This is a schematic diagram of the structure of the laser printing melt pool type detection system provided in Embodiment 1 of the present invention;

[0022] Figure 3 This is a flowchart of another laser printing melt pool type detection method provided in Embodiment 2 of the present invention;

[0023] Figure 4 This is a schematic diagram of a laser printing melt pool type detection device according to Embodiment 3 of the present invention;

[0024] Figure 5 This is a structural block diagram of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, apparatus, product, or terminal device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or terminal devices.

[0027] Example 1

[0028] Figure 1 This is a flowchart of a laser printing melt pool type detection method provided in Embodiment 1 of the present invention. This embodiment is applicable to the detection of the melt pool type during the laser printing process. The method can be executed by a laser printing melt pool type detection device, which can be implemented in hardware and / or software, and can be integrated into an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0029] S101: When the laser head prints on the substrate in the calibrated printing direction, it acquires an image of the molten metal pool captured by the image device.

[0030] Optionally, acquiring images of the molten metal pool captured by the image acquisition device includes: determining a pre-set acquisition frequency; acquiring images of the molten metal pool captured by the image acquisition device according to the acquisition frequency, wherein the image acquisition device includes an industrial camera.

[0031] Among them, such as Figure 2 The diagram shows a schematic of a laser printing molten pool type detection system. This system includes a laser head 1, a laser beam angle detection component 2, an image device 3, and a detection device 4. The detection device 4 is equipped with software such as an online image processing unit, a molten pool type identification unit, and a closed-loop control unit. This is merely an example and does not limit the hardware or software configured in the detection device. Specifically, the laser head in this embodiment uses a blue laser as the light source and performs 3D printing by feeding powder or filament. The heat generated by the blue laser melts the powder or filament to generate a liquid metal molten pool. The laser head specifically uses a coaxial or off-axis method for powder or filament feeding. The processing methods include surface cladding or direct forming. This is also merely an example and does not limit the specific forming method. Furthermore, the image device in this embodiment can be a color industrial camera to capture images of the molten metal pool across the entire visible light spectrum.

[0032] Specifically, in this embodiment, when detecting the type of molten pool, a color industrial camera is fixed to a work support in the working environment. The distance between the powder flow convergence point and the laser head is 12mm. This distance is used to adjust the lens for focusing. During focusing, the aperture is reduced as much as possible to increase the depth of field and ensure imaging quality. Then, the ratio of the image to the actual size is calibrated. The ratio of the image pixel value to the actual size of 1mm is 35:1. Of course, this embodiment is only an example and does not limit the distance or the calibrated ratio. During printing, the color industrial camera will capture images of the processing in real time, for example, at a capture frequency of 100fps.

[0033] S102, acquire the laser beam angle signal collected by the laser beam angle detection component associated with the laser head.

[0034] In this embodiment, because molten metal splashes during the laser input process in 3D printing, and the laser beam is incident perpendicularly, there is a high probability that the laser nozzle will be damaged by the splashes. Therefore, a certain angle deflection is performed to prevent splash damage to the laser nozzle. The laser beam angle detection component 2 is used to collect the laser beam angle signal. In this embodiment, the laser beam angle detection component can be an infrared laser sensor, which is fixed to the side of the laser head. In this embodiment, the laser beam angle detection component can be an angle displacement sensor or a tilt sensor. Of course, this embodiment is only for illustrative purposes and does not limit the specific type of laser beam angle detection component.

[0035] S103, feature extraction is performed on the image of the molten metal pool to obtain the reflection features of the molten pool, and feature extraction is performed on the laser beam angle signal to obtain the laser beam angle features.

[0036] Optionally, feature extraction is performed on the molten pool image to obtain molten pool reflection features, including: performing grayscale processing on the molten pool image to obtain a grayscale processed image, wherein the grayscale distribution range of the grayscale processed image is smaller than that of the molten pool image; filtering out the noise generated in the grayscale processed image due to the scattering effect of the laser beam and powder to obtain a denoised image; performing visible light filtering on the denoised image to obtain a filtered image containing the green light band, and performing visual feature extraction on the filtered image to obtain molten pool reflection features, wherein the molten pool reflection features include the incident angle of the molten pool surface and the reflection angle of the molten pool surface.

[0037] Optionally, feature extraction is performed on the laser beam angle signal to obtain laser beam angle features, including: obtaining a signal analysis method that matches the laser beam angle detection component; analyzing the laser beam angle signal according to the signal analysis method to obtain laser beam angle features, wherein the laser beam angle features include the deflection angle of the laser head when it is not perpendicularly incident.

[0038] Specifically, in this embodiment, after acquiring the image of the molten metal pool, preprocessing is performed. First, the molten metal pool image is subjected to grayscale processing, that is, the grayscale distribution range in the grayscale histogram of the molten metal pool image is reduced to at least 1 / 2 of the original to obtain a grayscale processed image. Then, the grayscale processed image is subjected to noise reduction processing to remove the interference caused by the scattering of the laser beam and powder. At the same time, powder splashes with a pixel value less than 3 are removed to obtain a noise-reduced image. Finally, the noise-reduced image is subjected to visible light filtering to obtain a filtered image of the green light band. Since the color industrial camera acquires a molten metal pool image of the entire visible light band, and the blue laser wavelength is about 400-500nm, after the laser interacts with the powder or filament, the powder or filament absorbs the blue laser energy and melts into shape. The reflected laser energy is absorbed and the wavelength becomes longer. The green light image filtering processing can filter out the lengthened wavelength and retain the green light band within 460-620nm. After obtaining a filtered image containing only the green light band by preprocessing the image, visual feature extraction can be performed on the filtered image to obtain the molten pool reflection features. Specifically, the optical feature that the green light reflectivity changes rapidly with the incident angle is utilized. The incident angle and reflection angle of the molten pool surface are calculated through the filtered image containing the green light band, thereby obtaining the molten pool reflection features in the filtered image. Of course, this embodiment is only an example and does not limit the specific content of the molten pool reflection features.

[0039] Furthermore, since the laser beam angle signal acquired by the laser beam angle detection component does not directly contain the deflection angle, it is necessary to obtain a signal analysis method that matches the laser beam angle detection component, and analyze the laser beam angle signal according to the analysis method to obtain the deflection angle of the laser head when it is not perpendicularly incident, and use the deflection angle of the laser head when it is not perpendicularly incident as the laser beam angle feature. Since the specific content of analyzing the signal to obtain the angle is not the focus of this application, it will not be described in detail in this embodiment.

[0040] S104. The type of molten metal pool is determined based on the molten pool reflection characteristics, laser beam angle characteristics, and printing direction.

[0041] Optionally, the type of molten metal pool is determined based on the reflection characteristics of the molten pool, the angle characteristics of the laser beam, and the printing direction, including: converting the deflection angle to obtain the first angle between the laser beam emitted by the laser head and the substrate; converting the incident angle and reflection angle of the molten pool surface to obtain the second angle between the molten surface and the substrate; and determining the type of molten metal pool based on the first angle, the second angle, and the printing direction.

[0042] Optionally, determining the type of molten metal pool based on the first included angle, the second included angle, and the printing direction includes: detecting sensitive signals at each detection point based on the first included angle and the second included angle in the printing direction; when a sensitive signal is detected in the printing direction, obtaining the new included angle direction formed by the first included angle and the second included angle, and determining a first type of molten metal pool based on the new included angle direction and the printing direction, wherein the first type includes a single-sided convex platform and a single-sided concave collapse; when two sensitive signals are detected in the printing direction, obtaining the new included angle direction formed by the first included angle and the second included angle each time a sensitive signal is detected, as well as the duration between the two sensitive signals, and determining a second type of molten metal pool based on the duration, the two new included angle directions, and the printing direction, wherein the second type includes a continuous convex platform, a convex platform, a concave pit, a continuous concave collapse, a hump, and a collapse.

[0043] Specifically, the printing direction specified in this embodiment can be from the left side of the substrate to the right side of the substrate. In addition, this embodiment will also specify a standard surface, i.e., the state of a standard horizontal molten pool, such as being parallel to the substrate. Furthermore, in this embodiment, the deflection angle in the laser beam angle feature will be converted into the first included angle a1 between the laser beam and the substrate, that is, the reference object will be changed from the laser beam to the substrate. At the same time, the incident angle and reflection angle of the molten pool surface in the molten pool reflection feature will be converted to obtain the second included angle a2 between the molten surface and the substrate, that is, the reference object will be changed from the molten pool to the substrate. Since the image device and the laser beam angle detection component acquire the image of the molten metal pool and the laser beam angle signal in real time, respectively, each detection point will contain a set of first included angles and second included angles. In this embodiment, the type of molten metal pool will be determined based on the first included angle, the second included angle and the printing direction of each detection point.

[0044] In a specific implementation, when |a1-a2|>110° is detected at each detection point in the printing direction, it is determined that a sensitive signal has appeared at that detection point. Under the movement of the calibrated printing direction, if only one sensitive signal is detected, and the opening direction of the new angle formed by |a1-a2| is the opposite direction of the printing direction, it is judged as a unilateral convex platform. If the opening direction of the new angle is the printing direction, it is judged as a unilateral concave collapse. The above-mentioned unilateral convex platform and unilateral concave collapse are regarded as the first type. If two sensitive signals appear during the scanning process, and the opening direction of the new angle is always opposite to the printing direction, it is considered a continuous upward convex platform. If two opening directions are in the printing direction, it is considered a continuous downward depression. If an opening direction is opposite to the printing direction for a period of time (the sensitive time is long and is a gradual process) and then the opening direction is in the printing direction, it is considered an upward convex platform. If an opening direction is in the printing direction for a period of time and then the opening direction is opposite to the printing direction, it is considered a downward depression. If an opening direction is opposite to the printing direction and then immediately the opening direction is in the printing direction, it is considered a hump. If an opening direction is in the printing direction and then immediately the opening direction is opposite to the printing direction, it is considered a collapse. The above-mentioned upward convex platform, upward convex platform, downward depression, continuous downward depression, hump, and collapse are considered as the second type. Of course, this embodiment is only an example and does not limit the type of molten metal pool.

[0045] For example, if two sensitive signals are detected, with the first sensitive signal occurring at a time of 2.1 seconds and the second sensitive signal occurring at a time of 1.7 seconds after 3.7 seconds, the angle between the laser beam and the molten pool plane is 117° when the first sensitive signal is detected, and the direction of the 117° angle is towards the printing direction. At the end of the first sensitive signal time of 2.1 seconds, the angle between the laser beam and the molten pool plane is approximately 109.8°. When the second sensitive signal is detected, the angle between the laser beam and the molten pool is 115°, and the direction of the angle is towards the printing direction. At the end of the second sensitive signal time of 1.7 seconds, the angle between the laser beam and the molten pool plane is 110°, which is identified as a continuous depression collapse. Of course, this embodiment only uses continuous depression collapse as an example for illustration. The identification principle for other types of molten pools is roughly the same, and will not be elaborated further in this embodiment.

[0046] The technical solution of the present invention acquires the image of the molten metal pool and the laser beam angle signal during the printing process, and accurately identifies the type of the molten metal pool based on the features extracted from the image of the molten metal pool and the laser beam angle signal, thereby realizing automated detection of the molten metal pool and avoiding misjudgment caused by manual identification.

[0047] Example 2

[0048] Figure 3This is a flowchart of another laser printing melt pool type detection method provided by an embodiment of the present invention. This embodiment is based on the above embodiment, and the method includes: obtaining an adjustment strategy matching the type, and adjusting the printing parameters of the laser head according to the adjustment strategy, such as... Figure 3 As shown, the method includes:

[0049] S201: When the laser head prints on the substrate in the calibrated printing direction, the image of the molten metal pool acquired by the image device is obtained.

[0050] Optionally, acquiring images of the molten metal pool captured by the image acquisition device includes: determining a pre-set acquisition frequency; acquiring images of the molten metal pool captured by the image acquisition device according to the acquisition frequency, wherein the image acquisition device includes an industrial camera.

[0051] S202, acquire the laser beam angle signal collected by the laser beam angle detection component associated with the laser head.

[0052] S203, feature extraction is performed on the image of the molten metal pool to obtain the reflection features of the molten pool, and feature extraction is performed on the laser beam angle signal to obtain the laser beam angle features.

[0053] Optionally, feature extraction is performed on the molten pool image to obtain molten pool reflection features, including: performing grayscale processing on the molten pool image to obtain a grayscale processed image, wherein the grayscale distribution range of the grayscale processed image is smaller than that of the molten pool image; filtering out the noise generated in the grayscale processed image due to the scattering effect of the laser beam and powder to obtain a denoised image; performing visible light filtering on the denoised image to obtain a filtered image containing the green light band, and performing visual feature extraction on the filtered image to obtain molten pool reflection features, wherein the molten pool reflection features include the incident angle of the molten pool surface and the reflection angle of the molten pool surface.

[0054] Optionally, feature extraction is performed on the laser beam angle signal to obtain laser beam angle features, including: obtaining a signal analysis method that matches the laser beam angle detection component; analyzing the laser beam angle signal according to the signal analysis method to obtain laser beam angle features, wherein the laser beam angle features include the deflection angle of the laser head when it is not perpendicularly incident.

[0055] S204. The type of molten metal pool is determined based on the molten pool reflection characteristics, laser beam angle characteristics, and printing direction.

[0056] Optionally, the type of molten metal pool is determined based on the reflection characteristics of the molten pool, the angle characteristics of the laser beam, and the printing direction, including: converting the deflection angle to obtain the first angle between the laser beam emitted by the laser head and the substrate; converting the incident angle and reflection angle of the molten pool surface to obtain the second angle between the molten surface and the substrate; and determining the type of molten metal pool based on the first angle, the second angle, and the printing direction.

[0057] Optionally, determining the type of molten metal pool based on the first included angle, the second included angle, and the printing direction includes: detecting sensitive signals at each detection point based on the first included angle and the second included angle in the printing direction; when a sensitive signal is detected in the printing direction, obtaining the new included angle direction formed by the first included angle and the second included angle, and determining a first type of molten metal pool based on the new included angle direction and the printing direction, wherein the first type includes a single-sided convex platform and a single-sided concave collapse; when two sensitive signals are detected in the printing direction, obtaining the new included angle direction formed by the first included angle and the second included angle each time a sensitive signal is detected, as well as the duration between the two sensitive signals, and determining a second type of molten metal pool based on the duration, the two new included angle directions, and the printing direction, wherein the second type includes a continuous convex platform, a convex platform, a concave pit, a continuous concave collapse, a hump, and a collapse.

[0058] S205, Obtain the adjustment strategy that matches the type, and adjust the printing parameters of the laser head according to the adjustment strategy.

[0059] Specifically, intermittent humps and depressions are caused by overheating and violent fluctuations in the molten pool; convex platforms are caused by excessive molten pool accumulation; and concave platforms are caused by insufficient filler material or insufficient melting energy, resulting in incomplete melting. Therefore, this embodiment employs different adjustment strategies for different molten pool types. For example, when a hump or depression is detected, the adjustment strategy is to reduce the laser power, increase the appropriate scanning speed, and reduce the protective gas flow rate; when a convex platform is detected, the adjustment strategy is to reduce the scanning speed, reduce the laser power, appropriately adjust the protective gas flow rate, and reduce the powder feeding gas flow rate; when a concave platform is detected, the adjustment strategy is to increase the scanning speed, increase the laser power, appropriately adjust the protective gas flow rate, and increase the powder feeding gas flow rate. Of course, this embodiment is merely illustrative and does not limit the specific adjustments to the printing parameters.

[0060] The technical solution of this invention acquires images of the molten metal pool and laser beam angle signals during the printing process, and accurately identifies the type of molten metal pool based on features extracted from these images and signals. This achieves automated detection of the molten metal pool, avoiding misjudgments caused by manual identification. Furthermore, printing process parameters are adjusted promptly based on the identified pool type to ensure a stable and high-quality molten metal pool shape, preventing any impact on processing quality.

[0061] Example 3

[0062] Figure 4 This is a schematic diagram of a laser printing melt pool type detection device provided in an embodiment of the present invention. Figure 4 As shown, the device includes: a metal molten pool image acquisition module 310, a laser beam angle signal acquisition module 320, a feature extraction module 330, and a molten pool type determination module 340.

[0063] The molten metal pool image acquisition module 310 is used to acquire the molten metal pool image collected by the image device when the laser head prints on the substrate in the calibrated printing direction.

[0064] The laser beam angle signal acquisition module 320 is used to acquire the laser beam angle signal collected by the laser beam angle detection component associated with the laser head;

[0065] The feature extraction module 330 is used to extract features from the molten pool image to obtain the molten pool reflection features, and to extract features from the laser beam angle signal to obtain the laser beam angle features.

[0066] The molten pool type determination module 340 is used to determine the type of molten metal pool based on the molten pool reflection characteristics, laser beam angle characteristics, and printing direction.

[0067] Optionally, a molten metal pool image acquisition module is used to determine a pre-set acquisition frequency;

[0068] Images of a molten metal pool are acquired by an image acquisition device at a specific acquisition frequency. The image acquisition device includes an industrial camera.

[0069] Optionally, the feature extraction module includes a molten pool reflection feature extraction unit, which is used to perform grayscale processing on the molten pool image to obtain a grayscale processed image, wherein the grayscale distribution range of the grayscale processed image is smaller than that of the molten pool image.

[0070] The noise generated by the scattering of the laser beam and powder in the grayscale image is filtered out to obtain a denoised image;

[0071] The denoised image is subjected to visible light filtering to obtain a filtered image containing the green light band, and the filtered image is subjected to visual feature extraction to obtain the molten pool reflection features, which include the incident angle of the molten pool surface and the reflection angle of the molten pool surface.

[0072] Optionally, the feature extraction module includes a laser beam angle feature extraction unit, used to obtain a signal parsing method that matches the laser beam angle detection component;

[0073] The laser beam angle signal is analyzed according to the signal analysis method to obtain the laser beam angle characteristics, which include the deflection angle of the laser head when it is not perpendicularly incident.

[0074] Optionally, a molten pool type determination module is used to convert the laser beam emitted by the laser head and the substrate according to the deflection angle.

[0075] The second angle between the molten surface and the substrate is obtained by converting the incident angle and the reflection angle of the molten pool surface.

[0076] The type of molten metal pool is determined based on the first included angle, the second included angle, and the printing direction.

[0077] Optionally, the melt pool type determination module is also used to detect sensitive signals in the printing direction based on the first included angle and the second included angle at each detection point;

[0078] When a sensitive signal is detected in the printing method, the direction of the new angle formed by the first angle and the second angle is obtained, and the first type of the molten metal pool is determined based on the new angle direction and the printing direction. The first type includes a unilateral convex platform and a unilateral concave collapse.

[0079] When it is determined that two sensitive signals are detected in the printing direction, the new angle direction formed by the first angle and the second angle at each time a sensitive signal is detected, as well as the duration between the two sensitive signals, are obtained. Based on the duration, the two new angle directions and the printing direction, the second type of molten metal pool is determined. The second type includes continuous convex platforms, convex platforms, concave pits, continuous concave collapses, humps and collapses.

[0080] Optionally, the device also includes a printing parameter adjustment module for obtaining an adjustment strategy that matches the type;

[0081] The printing parameters of the laser head were adjusted according to the adjustment strategy.

[0082] The laser printing melt pool type detection device provided in this embodiment of the invention can execute the laser printing melt pool type detection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0083] Example 4

[0084] Figure 5 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0085] The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the invention described and / or claimed herein.

[0086] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0087] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other electronic devices through computer networks such as the Internet and / or various telecommunications networks.

[0088] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the melt pool type detection method in laser printing.

[0089] That is, when the laser head prints on the substrate in the calibrated printing direction, it acquires the image of the molten metal pool captured by the imaging device;

[0090] Acquire the laser beam angle signal collected by the laser beam angle detection component associated with the laser head;

[0091] Feature extraction is performed on the image of the molten metal pool to obtain the reflection features of the molten pool, and feature extraction is performed on the laser beam angle signal to obtain the laser beam angle features;

[0092] The type of molten metal pool is determined based on the molten pool reflection characteristics, laser beam angle characteristics, and printing direction.

[0093] In some embodiments, the laser printing melt pool type detection method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the laser printing melt pool type detection method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the laser printing melt pool type detection method by any other suitable means (e.g., by means of firmware).

[0094] Various embodiments of the apparatuses and techniques described above herein can be implemented in digital electronic circuit devices, integrated circuit devices, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), device-on-a-chip (SoC) devices, complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable device including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage device, at least one input device, and at least one output device, and transmitting data and instructions to the storage device, the at least one input device, and the at least one output device.

[0095] The computer program used to implement the laser printing melt pool type detection method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other non-stop data migration device, such that when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0096] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution apparatus, device, or electronic device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage electronics, magnetic storage electronics, or any suitable combination thereof.

[0097] To provide interaction with a user, the devices and techniques described herein can be implemented on an electronic device having: a display device (e.g., a touchscreen) for displaying information to the user; and buttons through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0098] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0099] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for detecting the molten pool type in laser printing, characterized in that, The method includes: When the laser head prints on the substrate in the calibrated printing direction, it acquires an image of the molten metal pool captured by the imaging device. Acquire the laser beam angle signal collected by the laser beam angle detection component associated with the laser head; Feature extraction is performed on the image of the molten metal pool to obtain the reflection features of the molten pool, and feature extraction is performed on the laser beam angle signal to obtain the laser beam angle features; The type of molten metal pool is determined based on the molten pool reflection characteristics, the laser beam angle characteristics, and the printing direction.

2. The method according to claim 1, characterized in that, The image of the molten metal pool acquired by the image acquisition device includes: Determine the preset sampling frequency; The image acquisition device acquires images of the molten metal pool at the acquisition frequency, wherein the image acquisition device includes an industrial camera.

3. The method according to claim 1, characterized in that, The step of extracting features from the molten pool image to obtain molten pool reflection features includes: The image of the molten metal pool is subjected to grayscale processing to obtain a grayscale processed image, wherein the grayscale distribution range of the grayscale processed image is smaller than that of the molten metal pool image; The noise generated by the scattering of the laser beam and powder in the grayscale image is filtered out to obtain a denoised image; The denoised image is subjected to visible light filtering to obtain a filtered image containing the green light band, and the filtered image is subjected to visual feature extraction to obtain the molten pool reflection features, wherein the molten pool reflection features include the incident angle of the molten pool surface and the reflection angle of the molten pool surface.

4. The method according to claim 3, characterized in that, The step of extracting features from the laser beam angle signal to obtain laser beam angle features includes: Obtain the signal analysis method that matches the laser beam angle detection component; The laser beam angle signal is analyzed according to the signal analysis method to obtain the laser beam angle features, wherein the laser beam angle features include the deflection angle of the laser head when it is not perpendicularly incident.

5. The method according to claim 4, characterized in that, The process of determining the type of molten metal pool based on the molten pool reflection characteristics, the laser beam angle characteristics, and the printing direction includes: The first angle between the laser beam emitted by the laser head and the substrate is obtained by converting the deflection angle. The second angle between the molten surface and the substrate is obtained by converting the incident angle and the reflection angle of the molten pool surface. The type of the molten metal pool is determined based on the first included angle, the second included angle, and the printing direction.

6. The method according to claim 5, characterized in that, Determining the type of the molten metal pool based on the first included angle, the second included angle, and the printing direction includes: Sensitive signals are detected in the printing direction based on the first angle and the second angle at each detection point; When a sensitive signal is detected in the printing method, a new angle direction formed by the first angle and the second angle is obtained, and a first type of the molten metal pool is determined based on the new angle direction and the printing direction, wherein the first type includes a single-sided convex platform and a single-sided concave collapse. When it is determined that two sensitive signals are detected in the printing direction, the new angle direction formed by the first angle and the second angle at each time a sensitive signal is detected, as well as the duration between the two sensitive signals, are obtained. Based on the duration, the two new angle directions, and the printing direction, a second type of the molten metal pool is determined, wherein the second type includes a continuous convex platform, an convex platform, a concave pit, a continuous concave collapse, a hump, and a collapse.

7. The method according to claim 1, characterized in that, After determining the type of molten metal pool based on the molten pool reflection characteristics, the laser beam angle characteristics, and the printing direction, the method further includes: Obtain the adjustment strategy that matches the type; The printing parameters of the laser head are adjusted according to the adjustment strategy described above.

8. A laser printing melt pool type detection device, characterized in that, The device includes: The molten metal pool image acquisition module is used to acquire the molten metal pool image captured by the image acquisition device when the laser head prints on the substrate in the calibrated printing direction; A laser beam angle signal acquisition module is used to acquire the laser beam angle signal collected by the laser beam angle detection component associated with the laser head; The feature extraction module is used to extract features from the molten metal pool image to obtain the molten pool reflection features, and to extract features from the laser beam angle signal to obtain the laser beam angle features. The molten pool type determination module is used to determine the type of the molten pool based on the molten pool reflection characteristics, the laser beam angle characteristics, and the printing direction.

9. An electronic device, characterized in that, The electronic device includes: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-7.

10. A storage medium for computer-executable instructions, wherein a computer program is stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

Images