Galvanized alloyed product pulverization detection method and related equipment

Abstract

The invention discloses a zinc-plated alloyed product pulverization detection method and related equipment, and relates to the technical field of metallurgical machinery and automation control, the method comprises the following steps: based on a detection instruction, controlling an image acquisition device to carry out image acquisition on a zinc-plated alloyed sample plate at a preset detection position to obtain initial image data; performing image optimization processing on the initial image data to obtain target image data; performing feature analysis on the target image data based on a deep learning model to identify a pulverization area in the zinc plating alloying sample plate, and extracting width features of the pulverization area; and based on the width characteristics, according to a preset pulverization width threshold range, determining a pulverization grade corresponding to the pulverization region. Edges are cut and blocked in the galvanizing production process through the visual system, the production quality of the galvanized outer plate is improved by researching countermeasures, and safety and reliability are achieved.

Description

Technical Field

[0001] The present application relates to the field of metallurgical machinery and automation control technology, and in particular to a method for detecting powdering of zinc alloyed products and related equipment. Background Art

[0002] In the production process of cold-rolled galvannealed steel strip products, the detection of alloy powdering width is a key link in quality control. The traditional method relies on manual operation. The galvannealed steel sample needs to be transferred to the inspection table. The operator measures the width of the powdering area visually or with simple tools, and determines the corresponding powdering level based on experience. However, manual measurement is inefficient and cannot meet the real-time detection requirements of high-speed continuous production lines. In addition, the manual measurement results are greatly affected by the subjective judgment of the operator. Different personnel are prone to deviations in the definition standards of the powdering boundary, resulting in poor consistency in quality evaluation. At the same time, the detection data relies on manual recording and transmission, which carries the risk of missed detection and misrecording. It cannot be efficiently linked with the production line control system, making it difficult to achieve dynamic optimization of process parameters.

[0003] Therefore, how to realize the powdering detection of zinc alloy products without relying on manual labor has become a technical problem that needs to be solved urgently. Summary of the Invention

[0004] The Summary of the Invention introduces a series of simplified concepts that will be further described in the Detailed Description of the Invention. The Summary of the Invention of this application is not intended to limit the key features and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0005] This application specifically includes the following aspects:

[0006] In a first aspect, the present application proposes a method for detecting powdering of a zinc alloyed product, comprising:

[0007] Based on the detection instruction, the image acquisition device is controlled to acquire an image of the galvannealed sample at a preset detection position to obtain initial image data;

[0008] Performing image optimization processing on the initial image data to obtain target image data;

[0009] Performing feature analysis on the target image data based on a deep learning model to identify a powdered area in the zinc alloyed plate and extracting a width feature of the powdered area;

[0010] Based on the width feature and a preset threshold range of the chalking width, a chalking level corresponding to the chalking area is determined.

[0011] In a feasible embodiment, the image acquisition device includes an industrial camera and a red light source; wherein, the red light source is used to enhance the contrast of the powdered area, and the shooting angle of the industrial camera is perpendicular to the surface of the galvannealed sample.

[0012] In a feasible implementation manner, performing image optimization processing on the initial image data to obtain target image data includes:

[0013] Performing denoising on the initial image data by using a Gaussian filtering algorithm;

[0014] Performing brightness correction on the image data after the denoising process using a histogram equalization technique;

[0015] The boundary of the chalking area in the brightness-corrected image data is enhanced based on an edge enhancement algorithm to obtain the target image data.

[0016] In one feasible implementation, the deep learning model adopts an encoder and decoder architecture based on a multi-head self-attention mechanism, where:

[0017] The encoder performs global context feature extraction on the target image data to generate a feature map including the chalked area;

[0018] The decoder decodes the feature map based on the global context features through a masked attention mechanism and a multi-scale feature fusion technique, and predicts the boundary of the chalking area to output a width feature of the chalking area.

[0019] In a feasible implementation manner, determining the powdering level corresponding to the powdering area based on the width feature and according to a preset powdering width threshold range includes:

[0020] The case where the width feature is less than or equal to the first width threshold is classified as a first powdering level, wherein the first powdering level is used to indicate that the anti-powdering performance of the zinc alloyed plate meets the excellent standard;

[0021] The case where the width feature is greater than the first width threshold and less than or equal to the second width threshold is classified as a second powdering level, wherein the second powdering level is used to indicate that the anti-powdering performance of the zinc alloy plate meets the qualified standard;

[0022] The case where the width feature is greater than the second width threshold and less than or equal to the third width threshold is classified as a third powdering level, and the third powdering level is used to indicate that the anti-powdering performance of the zinc alloy plate needs process adjustment;

[0023] The case where the width feature is greater than the third width threshold is classified into a fourth powdering level, and the fourth powdering level is used to indicate that the anti-powdering performance of the zinc alloy plate does not meet the production requirements.

[0024] In a feasible embodiment, the process adjustment includes adjusting at least one of the temperature, pressure or alloying time of the zinc alloying process in the production line.

[0025] In a feasible embodiment, the method for detecting powdering of zinc alloyed products further includes:

[0026] Scanning the QR code on the zinc alloying sample to obtain identification information, and associating the powdering level with the identification information and storing it in a database;

[0027] The powdering level and the identification information are pushed to a display terminal.

[0028] In a second aspect, the present application proposes a zinc alloy coating product powdering detection system, which is applied to the zinc alloy coating product powdering detection method described in any one of the above embodiments, comprising:

[0029] An image acquisition module is used to control the image acquisition device to acquire images of the galvannealed sample at a preset detection position based on the detection instruction to obtain initial image data;

[0030] An image processing module, configured to perform image optimization processing on the initial image data to obtain target image data;

[0031] a feature extraction module, configured to perform feature analysis on the target image data based on a deep learning model to identify a powdered area in the zinc alloyed plate and extract a width feature of the powdered area;

[0032] The powdering detection module is configured to determine the powdering level corresponding to the powdering area based on the width feature and a preset powdering width threshold range.

[0033] In a third aspect, an electronic device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement the steps of any one of the methods for detecting powdering of zinc-alloyed products according to the first aspect when executing the computer program stored in the memory.

[0034] In a fourth aspect, the present application further proposes a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods for detecting powdering of zinc-alloyed products in the first aspect.

[0035] In summary, the proposed method for detecting powdering of galvanized alloy products utilizes a visual automation technology and high-precision real-time detection technology to improve production efficiency and product quality. This application utilizes a visual system to detect edge trimming and blocking during the galvanizing production process, and studies countermeasures to improve the production quality of galvanized exterior sheets, ensuring safety and reliability.

[0036] The powdering detection method for zinc alloyed products proposed in this application, and other advantages, objectives and features of this application will be partially reflected in the following description, and will also be understood by technicians in this field through research and practice of this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present description. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0038] Figure 1 A schematic diagram of the process of detecting powdering of a zinc alloyed product provided in an embodiment of the present application;

[0039] Figure 2 A schematic diagram of the functional modules of a zinc alloy coating product powdering detection system provided in an embodiment of the present application;

[0040] Figure 3 A schematic diagram of the structure of an electronic device for detecting powdering of a zinc alloyed product provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] In order to better understand the technical solutions provided by the embodiments of this specification, the technical solutions of the embodiments of this specification are described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0042] In this article, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also include elements inherent to such process, method, article or equipment. In the absence of further restrictions, the elements defined by the statement "comprising a ..." do not exclude the presence of other identical elements in the process, method, article or equipment comprising the elements. The term "two or more" includes two or more than two cases.

[0043] See also Figure 1 , which is a schematic diagram of the process of a powdering detection method for a zinc alloyed product provided in an embodiment of the present application, which may specifically include:

[0044] S110 , based on the detection instruction, controlling the image acquisition device to acquire an image of the galvannealed sample at a preset detection position to obtain initial image data.

[0045] For example, the operator places the stamped galvannealed sample on the powdering test table. When the operator issues a test command (such as clicking the "Start" button of the control system), the control system will automatically turn on the auxiliary test light and control the image acquisition device (such as a high-definition industrial camera) to take a picture of the galvannealed sample at a pre-set test position to obtain initial image data for subsequent analysis.

[0046] S120: Perform image optimization processing on the initial image data to obtain target image data.

[0047] For example, the initial image data collected may contain noise, uneven brightness, and other issues that affect subsequent analysis. Therefore, image optimization processing, such as image denoising, smoothing filtering, and lens shading correction, is required to improve image quality and obtain target image data that is more suitable for analysis.

[0048] S130. Perform feature analysis on the target image data based on the deep learning model to identify the powdered area in the galvannealed sample and extract the width feature of the powdered area.

[0049] For example, the powerful feature learning and analysis capabilities of the deep learning model are used to process the optimized target image data, identify the area where powdering occurs in the galvannealed sample, and extract the width feature of the powdering area, which is the key data for judging the degree of powdering.

[0050] S140 : Based on the width feature and according to a preset chalking width threshold range, determine a chalking level corresponding to the chalking area.

[0051] Exemplarily, a powdering width threshold range corresponding to different powdering widths is pre-set, and the width characteristics of the extracted powdering area are compared with the preset powdering width threshold range to determine the powdering level corresponding to the powdering area of ​​the galvannealed sample.

[0052] In some examples, the image acquisition device includes an industrial camera and a red light source; wherein the red light source is used to enhance the contrast of the powdered area, and the shooting angle of the industrial camera is perpendicular to the surface of the zinc alloy plate.

[0053] For example, high-resolution industrial cameras can capture clear, detailed initial image data, meeting the image quality requirements for subsequent analysis. Comparing imaging with different light sources, a red light source is selected to best highlight the features of the powdered areas. The initial image data must also be uniformly bright to avoid the impact of shadows and reflections on the recognition results. Specifically, using a red light source can enhance the contrast between powdered and non-powdered areas in the target image data, facilitating subsequent identification and analysis of the powdered areas. A vertical shooting angle effectively avoids glare caused by light reflections, ensuring uniform brightness in the captured initial image data and minimizing the impact of shadows and reflections on the recognition results.

[0054] In some examples, performing image optimization processing on initial image data to obtain target image data includes:

[0055] The initial image data is denoised using the Gaussian filtering algorithm;

[0056] The histogram equalization technology is used to perform brightness correction on the denoised image data;

[0057] The boundary of the chalky area in the brightness-corrected image data is enhanced based on the edge enhancement algorithm to obtain the target image data.

[0058] For example, the Gaussian filtering algorithm is a commonly used image denoising method, which can effectively reduce noise and detail interference in the image, make the image smoother, and provide a better foundation for subsequent processing; the histogram equalization technology can adjust the brightness distribution of the image, make the brightness of the image more uniform, enhance the contrast of the image, improve the visual effect of the image, and facilitate the subsequent identification of the powdered area; the edge enhancement algorithm can highlight the boundary of the powdered area, making the boundary between the powdered area and the non-powdered area clearer, which helps the subsequent deep learning model to more accurately identify the powdered area and extract its width features.

[0059] In some examples, deep learning models use an encoder-decoder architecture based on a multi-head self-attention mechanism, where:

[0060] The encoder extracts global context features from the target image data and generates a feature map containing the chalked area;

[0061] Based on the global context features, the decoder decodes the feature map through the masked attention mechanism and multi-scale feature fusion technology, and predicts the boundary of the chalking area to output the width feature of the chalking area.

[0062] For example, the algorithmic core of the deep learning model is a multi-head self-attention mechanism (Transformer) encoder-decoder architecture. The multi-head self-attention mechanism enables the deep learning model to focus on information at different locations when processing target image data, improving the deep learning model's ability to capture image features. The encoder analyzes the target image data, extracts the global context features of the target image data, and converts them into a feature map containing the powdered area, providing a basis for the decoder's work. The decoder uses the global context features output by the encoder, combined with the masked attention mechanism and multi-scale feature fusion technology, to decode the feature map. The masked attention mechanism can enable the deep learning model to segment targets of different scales, thereby more accurately predicting the boundaries of the powdered area and ultimately outputting the width features of the powdered area.

[0063] Furthermore, in related object detection methods, anchor boxes are pre-defined, which can lead to redundant and unnecessary computation. The powdering detection algorithm improves anchor box generation and selection by introducing denoising techniques. Specifically, during training, ground-truth bounding boxes with noise are divided into valid and invalid components, which are then predicted separately. This helps the deep learning model learn to distinguish between true objects and noise and remove redundant predicted boxes. This technique reliably detects powdering bands, effectively ensuring that powdering region segmentation is performed at the correct location. The masked attention mechanism restricts cross-attention to the predicted mask region, allowing the model to focus on extracting local features relevant to the specific task. This mechanism helps deep learning models handle objects of varying scales and shapes more efficiently and accurately. This technique also improves the model's segmentation accuracy for powdering. To improve the deep learning model's ability to segment objects of varying scales, the powdering detection algorithm employs multi-scale feature fusion. This is achieved by upsampling or downsampling feature maps at different scales and concatenating or adding them in the channel dimension. By combining feature maps at different scales, the model can better capture detailed information in the image, thereby improving segmentation accuracy. In the process of training deep learning models, quantizers and a series of regularization techniques (such as weight decay and gradient clipping) are used to accelerate deep learning model training and prevent overfitting.

[0064] In some examples, based on the width feature and according to a preset chalking width threshold range, determining the chalking level corresponding to the chalking area includes:

[0065] The case where the width feature is less than or equal to the first width threshold is classified into a first powdering level, and the first powdering level is used to indicate that the anti-powdering performance of the zinc alloyed sample meets the excellent standard;

[0066] The case where the width feature is greater than the first width threshold and less than or equal to the second width threshold is classified as a second powdering level, and the second powdering level is used to indicate that the anti-powdering performance of the zinc alloy plate meets the qualified standard;

[0067] The case where the width feature is greater than the second width threshold and less than or equal to the third width threshold is classified as the third powdering level. The third powdering level is used to indicate that the anti-powdering performance of the zinc alloy plate requires process adjustment.

[0068] The case where the width feature is greater than the third width threshold is classified into a fourth powdering level, and the fourth powdering level is used to indicate that the anti-powdering performance of the galvannealed alloy sample does not meet the production requirements.

[0069] For example, when the width characteristic of the powdered area is less than or equal to the first width threshold, it indicates that the powdering degree of the zinc alloy plate is very low and its anti-powdering performance reaches the excellent standard. When the width characteristic is greater than the first width threshold and less than or equal to the second width threshold, the width of the powdered area increases, but is still within a certain range, and the anti-powdering performance of the zinc alloy plate meets the qualified standard. When the width characteristic is greater than the second width threshold and less than or equal to the third width threshold, the width of the powdered area increases further, indicating that the anti-powdering performance of the zinc alloy plate is poor and the process in the production line needs to be adjusted to improve the anti-powdering performance of the zinc alloy plate. When the width characteristic is greater than the third width threshold, it indicates that the powdering degree of the zinc alloy plate is serious and its anti-powdering performance does not meet the production requirements.

[0070] In some examples, the process adjustment includes adjusting at least one of the temperature, pressure, or alloying time of a zinc alloying step in the production line.

[0071] For example, when the powdering resistance of a zinc alloy plated sample is at the third powdering level and process adjustments are required, the powdering resistance of the zinc alloy plated sample can be improved by adjusting one or more of the temperature, pressure, or alloying time of the zinc alloying process. For example, appropriately increasing the temperature may promote the alloying reaction and enhance the powdering resistance of the coating; adjusting the pressure can affect the microstructure of the coating; and changing the alloying time can also affect the performance of the coating.

[0072] In some examples, the method for detecting powdering of a zinc alloy coating product further includes:

[0073] Scan the QR code on the zinc alloying sample to obtain identification information, and associate the powdering level with the identification information and store it in the database;

[0074] Push the powdering level and identification information to the display terminal.

[0075] For example, by scanning the QR code on the galvannealed sample, identification information such as the sample roll number can be obtained. This identification information is then associated with the detected powdering level and stored in a database for easy query and management. The powdering level and identification information are then pushed to a display terminal for personnel to review and confirm. After confirmation by the personnel, the control system generates target determination data based on the results and uploads it to the big data platform for subsequent determination systems to monitor and analyze the entire production process.

[0076] The technical solution of this application is further described in detail below through specific embodiments.

[0077] Step 1: Manually place the stamped galvanized alloy sample on the powdering test table.

[0078] Step 2. Click the "Start" button of the system, and the inspection table will automatically run to the specified position. The system will automatically turn on the auxiliary inspection light and control the high-definition industrial camera to take pictures of the inspection position.

[0079] Step 3: After the system captures the sample image, it identifies the width of the sample powdering and determines the powdering grade based on the width of the powdering area. Coating powdering is divided into six grades: grades 0 and 1 indicate good powdering resistance, grade 2 indicates acceptable powdering resistance, grade 3 indicates poor powdering resistance, and grades 4 and above indicate extremely poor powdering resistance.

[0080] Step 4: Identify the sample volume number (QR code) to match it with the sample test result and record it in the database.

[0081] Step 5: Push the powdering results of the test to the display screen of the testing agency for review and confirmation. The confirmed results are transmitted to the big data platform for subsequent judgment system use.

[0082] It should be noted that the above embodiments are only the best examples and are not intended to limit the implementation of the present application.

[0083] Furthermore, the present application also proposes a zinc alloy product powdering detection system, which is applied to any of the above zinc alloy product powdering detection methods, specifically as follows: Figure 2 FIG. 1 is a functional module diagram of a zinc alloy product powdering detection system proposed in this application, including:

[0084] The image acquisition module 21 is used to control the image acquisition device to acquire images of the galvannealed sample at a preset detection position based on the detection instruction to obtain initial image data;

[0085] The image processing module 22 is used to perform image optimization processing on the initial image data to obtain target image data;

[0086] A feature extraction module 23 is used to perform feature analysis on the target image data based on a deep learning model to identify the powdered area in the zinc alloyed plate and extract the width feature of the powdered area;

[0087] The powdering detection module 24 is configured to determine the powdering level corresponding to the powdering area based on the width feature and a preset powdering width threshold range.

[0088] Exemplarily, the image acquisition module 21 receives a detection instruction and controls an image acquisition device (such as a high-resolution industrial camera and a red light source) to capture an image of the sample at a preset position to obtain initial image data. The image processing module 22 processes the collected initial image data and optimizes the image using a Gaussian filter algorithm, histogram equalization technology, and an edge enhancement algorithm to obtain target image data. The feature extraction module 23 uses a deep learning model based on an encoder and decoder architecture with a multi-head self-attention mechanism to perform feature analysis on the target image data, identify the powdered area, and extract its width features. The powdering detection module 24 determines the powdering level corresponding to the powdered area based on the extracted width features of the powdered area and the powdering level classification method.

[0089] Furthermore, the zinc alloy product powdering detection system is divided into a human-computer interface, an interface service, and an algorithm service. The human-computer interface displays the powdering sample detection results and images of the zinc alloy sample. The interface service interacts with the powdering actuator and controls the algorithm service to perform algorithm testing and feedback. The algorithm service receives the powdering sample images from the interface service, performs algorithm testing, and provides feedback to the human-computer interface. Furthermore, to ensure higher accuracy and robustness of the core detection algorithm, a deep learning model must be trained and optimized. This training process requires a large amount of annotated data, including labels for powdered and non-powdered areas of the powdered sample. By continuously adjusting model parameters and learning strategies, the recognition performance of the deep learning model can be improved. Optimization techniques, such as regularization and ensemble learning, can also be used to further enhance the model's generalization and stability. Post-processing is the final step in the powdering recognition process, primarily focusing on further processing and optimizing the recognition results of the deep learning model. At this stage, the recognition results can be smoothed and false positives removed to improve accuracy and reliability. Furthermore, the recognition results can be displayed to the user in a visual format for easy review and analysis.

[0090] like Figure 3 As shown, an embodiment of the present application further provides an electronic device 300, including a processor 310, a memory 320, and a computer program 321 stored in the memory 320 and executable on the processor. When the processor 310 executes the computer program 321, the steps of any of the above-mentioned methods for detecting powdering of zinc-plated alloyed products are implemented.

[0091] Since the electronic device introduced in this embodiment is a device used to implement a method for detecting powdering of a zinc-alloyed product in an embodiment of the present application, based on the method introduced in the embodiment of the present application, technical personnel in this field can understand the specific implementation of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application will not be introduced in detail here. As long as the equipment used by technical personnel in this field to implement the method in the embodiment of the present application falls within the scope of protection of this application.

[0092] In the specific implementation process, the computer program 321 can be implemented when executed by the processor Figure 1 Any implementation manner in the corresponding embodiments.

[0093] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0094] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-readable program code.

[0095] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0096] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0097] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0098] An embodiment of the present application further provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes the process of the method for detecting powdering of zinc alloyed products.

[0099] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)).

[0100] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0101] In the several embodiments provided in this application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0102] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0103] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0104] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0105] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

[0106] Although the preferred embodiments of this specification have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of this specification.

[0107] Obviously, those skilled in the art may make various changes and modifications to this specification without departing from the spirit and scope of this specification. Thus, if such changes and modifications fall within the scope of the claims of this specification and their equivalents, this specification is intended to include such changes and modifications.

Claims

1. A method for detecting powdering of zinc alloyed products, characterized in that: include: Based on the detection instruction, the image acquisition device is controlled to acquire an image of the galvannealed sample at a preset detection position to obtain initial image data; Performing image optimization processing on the initial image data to obtain target image data; Performing feature analysis on the target image data based on a deep learning model to identify a powdered area in the zinc alloyed plate and extracting a width feature of the powdered area; Based on the width feature and a preset threshold range of the chalking width, a chalking level corresponding to the chalking area is determined.

2. The method for detecting powdering of a zinc alloyed product according to claim 1, wherein: The image acquisition device includes an industrial camera and a red light source; wherein the red light source is used to enhance the contrast of the powdered area, and the shooting angle of the industrial camera is perpendicular to the surface of the galvannealed sample.

3. The method for detecting powdering of a zinc alloyed product according to claim 1, wherein: The performing image optimization processing on the initial image data to obtain target image data includes: Performing denoising on the initial image data by using a Gaussian filtering algorithm; Performing brightness correction on the image data after the denoising process using a histogram equalization technique; The boundary of the chalking area in the brightness-corrected image data is enhanced based on an edge enhancement algorithm to obtain the target image data.

4. The method for detecting powdering of a zinc alloyed product according to claim 1, wherein: The deep learning model adopts an encoder and decoder architecture based on a multi-head self-attention mechanism, where: The encoder performs global context feature extraction on the target image data to generate a feature map including the chalked area; The decoder decodes the feature map based on the global context features through a masked attention mechanism and a multi-scale feature fusion technique, and predicts the boundary of the chalking area to output a width feature of the chalking area.

5. The method for detecting powdering of a zinc alloyed product according to claim 1, wherein: The determining of the powdering level corresponding to the powdering area based on the width feature and according to a preset powdering width threshold range includes: The case where the width feature is less than or equal to the first width threshold is classified as a first powdering level, wherein the first powdering level is used to indicate that the anti-powdering performance of the zinc alloyed plate meets the excellent standard; The case where the width feature is greater than the first width threshold and less than or equal to the second width threshold is classified as a second powdering level, wherein the second powdering level is used to indicate that the anti-powdering performance of the zinc alloy plate meets the qualified standard; The case where the width feature is greater than the second width threshold and less than or equal to the third width threshold is classified as a third powdering level, and the third powdering level is used to indicate that the anti-powdering performance of the zinc alloy plate needs process adjustment; The case where the width feature is greater than the third width threshold is classified into a fourth powdering level, and the fourth powdering level is used to indicate that the anti-powdering performance of the zinc alloy plate does not meet the production requirements.

6. The method for detecting powdering of a zinc alloyed product according to claim 5, wherein: The process adjustment includes adjusting at least one of the temperature, pressure or alloying time of the zinc alloying process in the production line.

7. The method for detecting powdering of a zinc alloyed product according to claim 1, wherein: Also includes: Scanning the QR code on the zinc alloying sample to obtain identification information, and associating the powdering level with the identification information and storing it in a database; The powdering level and the identification information are pushed to a display terminal.

8. A zinc alloy coating product powdering detection system, applied to the zinc alloy coating product powdering detection method according to any one of claims 1 to 7, characterized in that: include: An image acquisition module is used to control the image acquisition device to acquire images of the galvannealed sample at a preset detection position based on the detection instruction to obtain initial image data; An image processing module, configured to perform image optimization processing on the initial image data to obtain target image data; a feature extraction module, configured to perform feature analysis on the target image data based on a deep learning model to identify a powdered area in the zinc alloyed plate and extract a width feature of the powdered area; The powdering detection module is configured to determine the powdering level corresponding to the powdering area based on the width feature and a preset powdering width threshold range.

9. An electronic device comprising: A memory and a processor, wherein the processor is configured to implement the steps of the method for detecting powdering of a zinc alloyed product according to any one of claims 1 to 7 when executing a computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for detecting powdering of a zinc alloyed product according to any one of claims 1 to 7 are implemented.

Images