Laser cladding powder mixing quality monitoring method, system and equipment and storage medium
By using image processing and circular fitting techniques, the CRes-Net network model was employed to monitor the particle size of laser cladding powder, solving the problem of powder quality monitoring and ensuring coating quality and uniformity.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-05
- Publication Date
- 2026-03-10
AI Technical Summary
Existing technologies make it difficult to quickly and reliably monitor the quality of laser cladding powder, which affects the coating quality.
By acquiring images of the powder surface after laser cladding, image processing and circular fitting are performed. The CRes-Net network model is used to extract particle feature maps, determine powder particle size information, and monitor powder mixing quality.
It enables rapid and reliable monitoring of powder quality after laser cladding, ensuring coating quality and improving the uniformity of powder distribution and compaction.
Smart Images
Figure CN121639552A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of deep learning, and in particular to a laser cladding powder mixing quality monitoring method, system, device and storage medium. BACKGROUND
[0002] Laser cladding, also known as laser coating or laser coating, is a new surface modification technology. It adds cladding materials on the surface of the substrate, uses high-energy-density laser beams to quickly melt alloys of different compositions and properties with the substrate surface layer, and forms an alloy layer with completely different compositions and properties on the substrate surface. Laser cladding is a process that can significantly improve the wear resistance, corrosion resistance, heat resistance, oxidation resistance and electrical properties of the substrate surface, thereby achieving the purpose of surface modification or repair, meeting the requirements for specific properties of the material surface, and saving a large amount of valuable elements. Compared with traditional surfacing, spraying, electroplating and vapor deposition, laser cladding has high energy density of laser beam, fast heating speed, small thermal influence on the substrate, and small deformation of the workpiece; the laser cladding layer is firmly combined with the substrate, has dense structure, few micro defects, and fine cladding layer structure, and excellent performance; excellent materials can be used to modify the surface of the substrate, the material consumption is small, and the performance price ratio is excellent; the size and position of the laser cladding layer can be accurately controlled, and the beam aiming can be used to melt the areas that are difficult to access. In recent years, laser cladding technology has developed rapidly and become a frontier in the field of material surface engineering.
[0003] The cladding material is added in the form of powder, wire and plate, among which the powder form is most commonly used. The main process flow of pre-positioned laser cladding is: substrate cladding surface pretreatment - pre-positioned cladding material - preheating - laser melting - post-heating treatment. Due to the nature of the selective laser melting process, the parts constructed are prone to defects. The quality of the powder has a significant impact on the quality of the cladding layer. From the processing point of view, the size distribution, bulk density, flowability and sphericity of the powder particles themselves have a significant impact on the macro-morphology and microstructure of the coating. At the same time, ensuring that the powder bed has appropriate powder distribution and compaction is also the key to improving the quality of the coating.
[0004] Therefore, there is an urgent need to provide a technical solution to solve the above problems. SUMMARY
[0005] To solve the above technical problems, the present application provides a laser cladding powder mixing quality monitoring method, system, device and storage medium.
[0006] In a first aspect, the present application provides a laser cladding powder mixing quality monitoring method, and the technical scheme of the method is as follows:
[0007] An original image of a powder surface of a substrate to be detected after laser cladding is acquired, and the original image is processed to obtain a target image containing all particles of the powder surface;
[0008] A local image of any particle in the target image is subjected to circular fitting, and powder particle size information of the particle is obtained according to the circular local image after fitting, until powder particle size information of each particle is obtained.
[0009] The laser cladding powder mixing quality monitoring method has the following beneficial effects:
[0010] The method can quickly and reliably monitor the powder quality of the substrate surface after laser cladding, thereby ensuring the quality of the laser cladding coating.
[0011] Based on the above scheme, the laser cladding powder mixing quality monitoring method can be further improved as follows.
[0012] In an optional manner, the image processing manner includes image gray processing, image noise processing, image enhancement processing and boundary detection processing.
[0013] In an optional manner, the boundary detection processing step includes:
[0014] An overall feature map of the input image is extracted, and a core network model is used to acquire a core region feature map containing all particles of the powder surface in the overall feature map.
[0015] The overall feature map and the core region feature map are fused by using a CRes-Net network model to obtain a fusion feature map and determine the fusion feature map as the target image.
[0016] In an optional manner, the method further includes:
[0017] According to the powder particle size information of each particle, the powder mixing quality of the substrate surface to be detected is determined, wherein the powder mixing quality is determined by powder particle size distribution, average powder particle size and powder particle size standard deviation.
[0018] In a second aspect, the application provides a laser cladding powder mixing quality monitoring system, and the technical scheme of the system is as follows:
[0019] The system includes a processing module and a monitoring module.
[0020] The processing module is used to acquire an original image of a powder surface of a substrate to be detected after laser cladding, and the original image is processed to obtain a target image containing all particles of the powder surface.
[0021] The monitoring module is configured to perform circle fitting on a local image in which any particle in the target image is located, and obtain powder particle size information of the particle according to the fitted circle local image of the particle, until powder particle size information of each particle is obtained.
[0022] The laser cladding powder mixing quality monitoring system has the following advantages:
[0023] The system can quickly and reliably monitor the powder quality of the substrate surface after laser cladding, thereby ensuring the quality of the laser cladding coating.
[0024] Based on the above-mentioned scheme, the laser cladding powder mixing quality monitoring system can be further improved as follows.
[0025] In an optional manner, the image processing manner comprises image gray processing, image noise processing, image enhancement processing and boundary detection processing.
[0026] In an optional manner, the boundary detection processing comprises:
[0027] Extract the overall feature map of the input image, and use the core network model to obtain the core region feature map of all particles containing the powder surface in the overall feature map;
[0028] The CRes-Net network model is used to fuse the overall feature map and the core region feature map to obtain a fusion feature map and determine the target image.
[0029] In an optional manner, the system further comprises an analysis module, and the analysis module is configured to:
[0030] According to the powder particle size information of each particle, the powder mixing quality of the surface of the to-be-detected substrate is determined, and the powder mixing quality is determined by powder particle size distribution, average powder particle size and powder particle size standard deviation.
[0031] In a third aspect, the technical scheme of the electronic device of the present application is as follows:
[0032] The electronic device comprises a memory, a processor and a program stored in the memory and running on the processor, and the processor implements the steps of the laser cladding powder mixing quality monitoring method of the present application when executing the program.
[0033] In a fourth aspect, the technical scheme of the computer readable storage medium provided by the present application is as follows:
[0034] The instructions are stored in a computer readable storage medium, and when the computer readable storage medium reads the instructions, the computer readable storage medium executes the steps of the laser cladding powder mixing quality monitoring method of the present application.
[0035] The above description is only a summary of the technical solutions of the present application. In order to make the technical means of the present application more clearly understood, the present application can be implemented according to the content of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application are described below. BRIEF DESCRIPTION OF DRAWINGS
[0036] The accompanying drawings are included to provide a further understanding of the present application, and are incorporated herein and constitute a part of the detailed description. It should be noted that in the accompanying drawings, the same or similar components are denoted by the same reference numerals. In the drawings:
[0037] Figure 1 A flowchart of an embodiment of a laser cladding powder mixing quality monitoring method of the present application;
[0038] Figure 2 A schematic diagram of the principle of an image acquisition device;
[0039] Figure 3 A schematic diagram of an original image;
[0040] Figure 4 A schematic diagram of a convolutional neural network for boundary detection;
[0041] Figure 5 A structural schematic diagram of an embodiment of a laser cladding powder mixing quality monitoring system of the present application;
[0042] Figure 6 A structural schematic diagram of an embodiment of an electronic device of the present application. DETAILED DESCRIPTION
[0043] Exemplary embodiments of the present application will be described in detail with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein.
[0044] Figure 1This diagram illustrates a flowchart of an embodiment of a laser cladding powder mixing quality monitoring method provided by the present invention. This method can be executed by electronic devices such as terminal devices or servers. The terminal device can be any fixed or mobile terminal, such as user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, vehicle-mounted device, or wearable device. The server can be a single server or a server cluster consisting of multiple servers. Any electronic device can implement the laser cladding powder mixing quality monitoring method by having its processor call computer-readable instructions stored in its memory. Figure 1 As shown, it includes the following steps:
[0045] S1. Obtain the original image of the powder surface of the substrate to be tested after laser cladding, and perform image processing on the original image to obtain a target image containing all particles on the powder surface.
[0046] In this embodiment, the substrate to be tested is the substrate that has undergone laser cladding and requires monitoring of powder surface mixing quality. The type of substrate can be selected according to actual conditions and is not limited here. Image processing methods include, but are not limited to: image grayscale processing, image noise reduction, image enhancement processing, and boundary detection processing. In this embodiment, the following is used: Figure 2 The electron microscope image real-time acquisition system (camera), laser generator, and powder bed shown acquire raw images. For example... Figure 3 As shown, the surface of the powder after laser cladding contains multiple particles.
[0047] It should be noted that the order of the various processing steps in the image processing method is not restricted. In this embodiment, the default image processing order is: image grayscale processing → image noise processing → image enhancement processing → boundary detection processing. Specifically:
[0048] 1) The original image is processed into grayscale to obtain the first intermediate image. During grayscale processing, the R, G, and B components of the pixel value of each point in the original image are unified, transforming it from three-channel data into single-channel data. This reduces the amount of information contained in the original image, thereby improving detection efficiency. Common methods for image grayscale processing include the channel component method, the maximum value method, and the weighted average method. These methods use different weighting factors when calculating pixel grayscale values. For example, taking the weighted average method as an example, its expression is: Gray(i,j)=R(i,j)*0.299+G(i,j)*0.578+B(i,j)*0.114; R(i,j) is the pixel value of the R channel of pixel (i,j) in the original image, G(i,j) is the pixel value of the G channel of pixel (i,j) in the original image, B(i,j) is the pixel value of the B channel of pixel (i,j) in the original image, and Gray(i,j) is the pixel value of pixel (i,j) in the first intermediate image.
[0049] 2) Perform image noise processing on the first intermediate image to obtain the second intermediate image. During image noise processing, a Gaussian filtering algorithm is used. To better preserve the overall grayscale distribution characteristics of the image, the Gaussian filtering algorithm assigns different weights to pixels at different locations in the image; typically, pixels in the center have higher weights, while pixels farther from the center have lower weights. Its expression is: (x,y) represents the number of pixels in the first intermediate image, σ represents the standard deviation of the first intermediate image, L represents the size of the Gaussian filter template, and G(x,y) represents the number of pixels in the second intermediate image.
[0050] 3) Image enhancement processing is performed on the second intermediate image to obtain the third intermediate image. During image enhancement, histogram equalization is used to enhance image contrast. Histogram equalization ensures a uniform histogram distribution in the second intermediate image, improving its contrast. Non-linear grayscale stretching is applied to the second intermediate image to redistribute the grayscale values of all pixels, ensuring that the number of pixels for each grayscale level remains essentially the same in the second intermediate image.
[0051] 4) Perform boundary detection processing on the third intermediate image to obtain a target image containing all particles on the powder surface. For example... Figure 4As shown, in the boundary detection process, firstly, the CRes-Net basic network, using CRes-Net+FPN as the model, extracts the overall feature map of the third intermediate image. Then, the overall feature map is mapped to the representation spaces of three different regions (overall region, core region, and edge region) to obtain the feature representation of particle information in each region, resulting in the core region feature map. Using the CRes-Net network model, the overall feature map and the core region feature map are fused to obtain a fused feature map, which is then used as the target image. By fusing the overall feature map and the core region feature map, the core image region containing the particle image can be obtained, achieving higher accuracy compared to directly obtaining it from the overall feature map.
[0052] S2. Perform circular fitting on the local image of any particle in the target image, and obtain the powder particle size information of the particle based on the fitted circular local image of the particle, until the powder particle size information of each particle is obtained.
[0053] Some particles may have incomplete shapes, appearing approximately circular. Therefore, a circular fitting is performed on the local image of the particle to obtain a circular local image. The circular fitting process is as follows: based on geometric and grayscale features, cluster analysis is performed on the edge points of the local image of any particle to find the possible center position. The radius is estimated based on the center position, and the optimal circular model (circular local image) is fitted to determine the powder particle size information of the particle.
[0054] In one alternative approach, it also includes:
[0055] S3. Determine the powder mixing quality on the surface of the substrate to be tested based on the powder particle size information of each particle.
[0056] The powder mixing quality is determined by the powder particle size distribution, average powder particle size, and standard deviation of powder particle size, thus obtaining the powder uniformity and particle size distribution during the laser cladding process.
[0057] The technical solution of this embodiment can quickly and reliably monitor the powder quality on the surface of the substrate after laser cladding, thereby ensuring the quality of the laser cladding coating.
[0058] Figure 5 A schematic diagram of an embodiment of a laser cladding powder mixing quality monitoring system 200 provided by the present invention is shown. Figure 5 As shown, the system 200 includes: a processing module 210 and a monitoring module 220;
[0059] The processing module 210 is used to: acquire the original image of the powder surface of the substrate to be tested after laser cladding, and perform image processing on the original image to obtain a target image containing all particles on the powder surface;
[0060] The monitoring module 220 is used to: perform circular fitting on the local image of any particle in the target image, and obtain the powder particle size information of the particle based on the circular local image of the particle after fitting, until the powder particle size information of each particle is obtained.
[0061] In one alternative approach, the image processing methods include: image grayscale processing, image noise reduction, image enhancement processing, and boundary detection processing.
[0062] In one alternative approach, the boundary detection process includes the following steps:
[0063] Extract the overall feature map of the input image, and use the core network model to obtain the core region feature map containing all particles on the powder surface in the overall feature map;
[0064] Using the CRes-Net network model, the overall feature map and the core region feature map are fused to obtain a fused feature map, which is then identified as the target image.
[0065] In an alternative embodiment, it further includes: an analysis module; the analysis module is used for:
[0066] The powder mixing quality on the surface of the substrate to be tested is determined based on the powder particle size information of each particle; wherein the powder mixing quality is determined by the powder particle size distribution, the average powder particle size, and the standard deviation of the powder particle size.
[0067] The technical solution of this embodiment can quickly and reliably monitor the powder quality on the surface of the substrate after laser cladding, thereby ensuring the quality of the laser cladding coating.
[0068] The parameters and steps for each module in the laser cladding powder mixing quality monitoring system 200 described above to achieve their respective functions can be found in the parameters and steps in the embodiments of the laser cladding powder mixing quality monitoring method described above, and will not be repeated here.
[0069] like Figure 6 As shown, an electronic device 300 according to an embodiment of the present invention includes a processor 320 coupled to a memory 310. The memory 310 stores at least one computer program 330, which is loaded and executed by the processor 320 to enable the electronic device 300 to implement any of the above-mentioned laser cladding powder mixing quality monitoring methods. Specifically:
[0070] The electronic device 300 can vary considerably due to differences in configuration or performance. It may include one or more processors 320 (Central Processing Units, CPUs) and one or more memories 310. The one or more memories 310 store at least one computer program 330, which is loaded and executed by the one or more processors 320 to enable the electronic device 300 to implement any of the laser cladding powder mixing quality monitoring methods provided in the above embodiments. Of course, the electronic device 300 may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The electronic device 300 may also include other components for implementing device functions, which will not be elaborated upon here.
[0071] An embodiment of the present invention provides a computer-readable storage medium storing at least one computer program, which is loaded and executed by a processor to enable a computer to implement any of the above-described laser cladding powder mixing quality monitoring methods.
[0072] Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc.
[0073] In an exemplary embodiment, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform any of the laser cladding powder mixing quality monitoring methods described above.
[0074] It should be noted that the terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and represent a limitation on a specific order or sequence. Where appropriate, the order of use for similar objects can be interchanged so that the embodiments of this application described herein can be implemented in an order other than that shown or described.
[0075] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this disclosure can be specifically implemented in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, this invention can also be implemented as a computer program product in one or more computer-readable media containing computer-readable program code.
[0076] Any combination of one or more computer-readable media can be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, 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 device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
[0077] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.
Claims
1. A method of monitoring the quality of a mixture of laser cladding powders, characterized in that, The method comprises the following steps: An original image of a powder surface of a substrate to be detected after laser cladding is acquired, and image processing is performed on the original image to obtain a target image containing all particles on the powder surface; A local image of any particle in the target image is subjected to circular fitting, and powder particle size information of the particle is obtained according to the circular local image after fitting, until powder particle size information of each particle is obtained.
2. The method of claim 1, wherein, The image processing mode comprises image gray processing, image noise processing, image enhancement processing and boundary detection processing.
3. The method of claim 2, wherein: The steps of the boundary detection processing comprise: An overall feature map of an input image is extracted, and a core area feature map containing all particles on the powder surface in the overall feature map is acquired by using a core network model; The overall feature map and the core area feature map are fused by using a CRes-Net network model to obtain a fusion feature map and determine the fusion feature map as the target image.
4. The method of claim 1 to 3, wherein The method further comprises the following steps: The powder mixing quality of the surface of the substrate to be detected is determined according to the powder particle size information of each particle, wherein the powder mixing quality is determined by powder particle size distribution, average powder particle size and powder particle size standard deviation.
5. A laser cladding powder mix quality monitoring system, characterized by, The method comprises the following steps: A processing module and a monitoring module are provided; The processing module is configured to acquire an original image of a powder surface of a substrate to be detected after laser cladding, and perform image processing on the original image to obtain a target image containing all particles on the powder surface; The monitoring module is configured to perform circular fitting on a local image of any particle in the target image, and obtain powder particle size information of the particle according to the circular local image after fitting, until powder particle size information of each particle is obtained.
6. The laser cladding powder blend quality monitoring system of claim 5, wherein, The image processing mode comprises image gray processing, image noise processing, image enhancement processing and boundary detection processing.
7. The laser cladding powder mix quality monitoring system of claim 6, wherein, The steps of the boundary detection processing comprise: An overall feature map of an input image is extracted, and a core area feature map containing all particles on the powder surface in the overall feature map is acquired by using a core network model; The overall feature map and the core area feature map are fused by using a CRes-Net network model to obtain a fusion feature map and determine the fusion feature map as the target image.
8. The laser cladding powder mix quality monitoring system of any one of claims 5 to 7, wherein, The method further comprises the following steps: An analysis module is provided, and the analysis module is configured to: The powder mixing quality of the surface of the substrate to be detected is determined according to the powder particle size information of each particle, wherein the powder mixing quality is determined by powder particle size distribution, average powder particle size and powder particle size standard deviation.
9. An electronic device, comprising: The electronic device comprises a processor and a memory, the memory stores at least one computer program, the at least one computer program is loaded and executed by the processor, so that the electronic device implements the laser cladding powder mixing quality monitoring method according to any one of claims 1 to 4.
10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores at least one computer program, the at least one computer program is loaded and executed by the processor, so that the computer readable storage medium implements the laser cladding powder mixing quality monitoring method according to any one of claims 1 to 4.