Metallographic measurement method and device, electronic equipment, storage medium and program

Abstract

Embodiments of the present application disclose a metallographic measurement method and device, electronic equipment, storage medium and program, wherein the method comprises: obtaining a molten pool ROI image of a target entity; performing region segmentation on the molten pool ROI image of the target entity to obtain a region segmentation result of the molten pool ROI image; and determining a weld forming parameter of the target entity according to a metallographic measurement priori logic and the region segmentation result of the molten pool ROI image. The technical solution of the embodiments of the present application can improve the processing efficiency and accuracy of metallographic measurement.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of metallographic testing technology, and in particular to a metallographic measurement method, apparatus, electronic device, storage medium and program. Background Technology

[0002] In the current stage of new energy production, in order to improve efficiency, optimize quality and control product consistency, laser welding has been widely used in the welding process of core components such as cell shells, module boxes and battery pack boxes.

[0003] To ensure that welding quality and parameters meet established standards, metallographic analysis of welded parts is required during daily production. This analysis process covers key steps such as cutting, mounting, grinding, polishing, etching, drying, microscopic imaging, and dimensional measurement. The measurement step requires manual selection of geometric features such as points, lines, and circles using specialized software to detect core indicators such as weld penetration and weld width. This process is labor-intensive and involves a high proportion of repetitive work. Summary of the Invention

[0004] This invention provides a metallographic measurement method, apparatus, electronic device, storage medium, and program that can improve the processing efficiency and accuracy of metallographic measurements.

[0005] According to one aspect of the present invention, a metallographic measurement method is provided, comprising: Obtain the Region of Interest (ROI) image of the melt pool of the target entity; The ROI image of the target entity is segmented to obtain the ROI image segmentation result. The weld formation parameters of the target entity are determined based on the metallographic measurement prior logic and the region segmentation results of the ROI image of the molten pool.

[0006] According to another aspect of the present invention, a metallographic measuring apparatus is provided, comprising: The ROI image acquisition module is used to acquire the ROI image of the target entity. The image region segmentation module is used to segment the ROI image of the target entity to obtain the region segmentation result of the ROI image. The weld formation parameter determination module is used to determine the weld formation parameters of the target entity based on the metallographic measurement prior logic and the region segmentation results of the ROI image of the molten pool.

[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the metallographic measurement method according to any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the metallographic measurement method according to any embodiment of the present invention.

[0009] According to another aspect of the present invention, a computer program product is also provided, comprising a computer program that, when executed by a processor, implements the metallographic measurement method according to any embodiment of the present invention.

[0010] This invention acquires a molten pool ROI image of a target entity and performs region segmentation on the ROI image to obtain the region segmentation result. Further, the weld formation parameters of the target entity are determined based on metallographic measurement prior logic and the region segmentation result of the ROI image. This solution addresses the accuracy shortcomings of existing metallographic measurement techniques caused by multiple interferences and unclear grayscale contrast, thereby improving the processing efficiency and accuracy of metallographic measurements.

[0011] 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

[0012] 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.

[0013] Figure 1 This is a flowchart of a metallographic measurement method provided in Embodiment 1 of the present invention; Figure 2 This is a flowchart of a metallographic measurement method provided in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of a metallographic measuring device provided in Embodiment 3 of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0014] 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.

[0015] It should be noted that the terms "target," "original," etc., used 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 embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises 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 apparatus.

[0016] Example 1 Figure 1 This is a flowchart of a metallographic measurement method provided in Embodiment 1 of the present invention. This embodiment is applicable to the automated measurement of weld formation parameters of a target entity based on images of the welded area of ​​the target entity. The method can be executed by a metallographic measurement device, which can be implemented in software and / or hardware, and is generally integrated into an electronic device. This electronic device can be a terminal device or a server device, as long as it can execute the metallographic measurement method. The present invention does not limit the specific type of electronic device. Correspondingly, as... Figure 1 As shown, the method includes the following operations: S110. Obtain the ROI image of the target entity's melt pool.

[0017] The target entity can be an entity that has undergone laser welding and is awaiting determination of weld formation parameters. For example, the target entity can be made of metallic or non-metallic materials; this embodiment of the invention does not limit the material type of the target entity. The ROI (Region of Interest) image of the weld pool can be the region of interest extracted from the original image acquired during laser welding or similar processes.

[0018] Metallographic analysis, also known as metallographic examination, is a specialized method for studying the macroscopic and microscopic structure of materials using a microscope. Macroscopic structure refers to the visual morphology of the components within a material as observed directly with a magnifying glass of 10x or less, or with the naked eye; microscopic structure primarily refers to the visual appearance of the components within a material under an optical microscope. Based on this, the entity to be subjected to metallographic measurement can be considered the target entity. Furthermore, when performing processing techniques such as laser welding on this target entity, the ROI (Region of Interest) image of the molten pool can be extracted from the acquired raw images.

[0019] S120. Perform region segmentation on the ROI image of the target entity to obtain the region segmentation result of the ROI image.

[0020] The region segmentation result of the ROI image can be the image output result obtained after performing region segmentation processing on the ROI image of the molten pool.

[0021] Accordingly, after obtaining the ROI image of the target entity's molten pool, the ROI image of the target entity can be processed by region segmentation. By segmenting regions such as the molten pool, shell, and weld, pixel-level contour information of each region can be obtained and used as the region segmentation result of the ROI image of the molten pool.

[0022] S130. Determine the weld formation parameters of the target entity based on the metallographic measurement prior logic and the region segmentation results of the ROI image of the molten pool.

[0023] The metallographic measurement prior logic can be pre-set rules and constraints for metallographic measurement. Weld formation parameters can be a series of quantitative indicators of the weld cross-sectional geometry during laser welding of the target entity, such as, but not limited to, penetration depth and weld width. This embodiment of the invention does not limit the specific type of weld formation parameters. Penetration depth can be the size of the molten pool region formed in the longitudinal direction of the target entity after laser welding. Weld width can be the size of the molten pool region formed in the transverse direction of the target entity after laser welding.

[0024] Correspondingly, after obtaining the region segmentation results of the ROI image of the molten pool, the relevant information of the weld formation parameters can be accurately located and extracted from the region segmentation results of the ROI image of the molten pool according to the metallographic measurement prior logic. Thus, the weld formation parameters of the target entity can be determined based on the relevant information of the weld formation parameters, providing reliable data support for subsequent welding quality assessment, process parameter adjustment and welding process optimization.

[0025] Therefore, the metallographic measurement method provided in this invention automatically measures weld formation parameters based on the ROI image of the molten pool and metallographic measurement prior logic. This automated measurement mode not only significantly reduces manual intervention and effectively avoids efficiency bottlenecks that may occur during manual operation, but also significantly improves the efficiency of metallographic measurement work, enabling rapid response to the inspection needs of large-scale welded workpieces. Simultaneously, its automated data processing flow can more accurately capture the subtle forming features of the weld, reducing the impact of human error on the measurement results and further improving the reliability and accuracy of metallographic measurement data. Furthermore, relying on standardized metallographic measurement prior logic, it can effectively reduce errors caused by subjective judgment differences during manual visual inspection, ensuring a high degree of consistency between measurement data and manual visual inspection in core judgment dimensions.

[0026] This invention acquires a molten pool ROI image of a target entity and performs region segmentation on the ROI image to obtain the region segmentation result. Further, the weld formation parameters of the target entity are determined based on metallographic measurement prior logic and the region segmentation result of the ROI image. This solution addresses the accuracy shortcomings of existing metallographic measurement techniques caused by multiple interferences and unclear grayscale contrast, thereby improving the processing efficiency and accuracy of metallographic measurements.

[0027] Example 2 Figure 2 This is a flowchart of a metallographic measurement method provided in Embodiment 2 of the present invention. This embodiment is a specific embodiment based on the above embodiment. In this embodiment, a specific optional implementation method is given for performing region segmentation on the ROI image of the molten pool of the target entity to obtain the region segmentation result of the ROI image of the molten pool, and for determining the weld formation parameters of the target entity based on the metallographic measurement prior logic and the region segmentation result of the ROI image of the molten pool. At the same time, optional implementation operations are also given before determining the weld formation parameters of the target entity based on the metallographic measurement prior logic and the region segmentation result of the ROI image of the molten pool. Correspondingly, such as Figure 2 As shown, the method in this embodiment may include: S210. Obtain the ROI image of the target entity's melt pool.

[0028] In an optional embodiment of the present invention, obtaining the ROI image of the target entity may include: obtaining a microscopic image of the target entity; performing ROI localization on the microscopic image of the target entity using a target detection model to determine the ROI image of the target entity; and determining the ROI image of the target entity based on a preset input size and the ROI image of the target entity when the ROI image of the target entity is determined to be less than or equal to a preset size threshold.

[0029] The microscopic image can be an image of the target entity to be measured using a microscope. The target detection model can be a model used to locate the molten pool in the microscopic image of the target entity. The molten pool size correlation data can be a set of geometric parameters of the molten pool formed by the high-temperature heat source during laser welding. For example, the molten pool size correlation data can include, but is not limited to, molten pool length, molten pool width, and molten pool area. This embodiment of the invention does not limit the specific content included in the molten pool size correlation data. The preset size threshold can be a pre-set threshold for the molten pool size. The preset input size can be a pre-set image input size for the target segmentation model.

[0030] Since metallographic analysis requires analyzing microscopic information, and the target entity is typically only a few millimeters in size, the pixel precision of the imaging and the accuracy of the metallographic measurement must be at the micrometer level. Therefore, in acquiring the molten pool ROI image of the target entity, a microscopic image of the target entity can first be obtained using a microscope. After acquiring the microscopic image, a target detection model can be used to locate the molten pool in the microscopic image of the target entity, outputting molten pool size correlation data. This method replaces the traditional positioning process, has stronger generalization ability, a shorter development cycle, and can automatically remove redundant areas around the molten pool, reducing the amount of data to be processed, thereby significantly improving the efficiency of metallographic measurement. In a specific example, the object detection model may include, but is not limited to, the YOLOV11 (You Only Look Once version 11) model, other versions of the YOLO series models, the SSD (Single Shot Multi-Box Detector) model, the Faster R-CNN (Faster Region-based Convolutional Neural Network) model, or the DETR (Detection Transformer) model, etc. The embodiments of the present invention do not limit the specific type of object detection model.

[0031] Furthermore, it can be determined whether the molten pool size correlation data of the located molten pool area meets the preset size threshold. If the molten pool size correlation data is less than or equal to the preset size threshold, the metallographic measurement process can be executed normally; if the molten pool size correlation data is greater than the preset size threshold, an abnormal alarm is displayed, and relevant personnel are notified for review. By judging the molten pool size correlation data, on the one hand, potential molten pool positioning abnormalities can be filtered out; on the other hand, downsampling and scaling operations on excessively large molten pool areas can be avoided, preventing the introduction of errors. At the same time, it can also screen for metallographic measurement abnormalities caused by abnormal process images.

[0032] Furthermore, when the melt pool size correlation data is less than or equal to a preset size threshold, the melt pool region that meets the requirements can be expanded according to the preset input size, so that the melt pool region that meets the requirements is input into the target segmentation model with the preset input size, thereby ensuring that the input image of the target segmentation model has not undergone downsampling operation, and thus ensuring the accuracy of the region segmentation result.

[0033] S220. Perform contrast enhancement and filtering processing on the ROI image of the target entity to obtain an enhanced ROI image.

[0034] Among them, the enhanced ROI image of the molten pool can be an image obtained by contrast enhancement and filtering of the ROI image of the molten pool.

[0035] Molten pool ROI images often suffer from low grayscale contrast and indistinct edge transitions. Therefore, after acquiring the molten pool ROI image of the target entity, grayscale contrast enhancement can be performed to improve the grayscale contrast between the molten pool region and the shell region, thereby improving the segmentation accuracy of the target segmentation model. Simultaneously, the molten pool ROI image can be filtered to obtain an enhanced molten pool ROI image. In a specific example, Gaussian filtering or bilateral filtering algorithms can be used to filter noise in the molten pool ROI image while preserving the boundaries between the molten pool, shell, and weld.

[0036] S230. Perform region segmentation processing on the molten pool ROI image and the enhanced molten pool ROI image respectively using the target segmentation model to obtain the original region segmentation result of the molten pool ROI image and the original region segmentation result of the enhanced molten pool ROI image.

[0037] The target segmentation model can be a model used for region segmentation processing of the molten pool ROI image and the enhanced molten pool ROI image. The original region segmentation result of the molten pool ROI image can be obtained by performing region segmentation processing on the molten pool ROI image. Similarly, the original region segmentation result of the enhanced molten pool ROI image can be obtained by performing region segmentation processing on the enhanced molten pool ROI image.

[0038] Accordingly, after obtaining the enhanced molten pool ROI image, region segmentation processing can be performed on both the molten pool ROI image and the enhanced molten pool ROI image to obtain the original region segmentation results of the molten pool ROI image and the enhanced molten pool ROI image, respectively. The above scheme can segment regions such as the molten pool, shell, and weld seam in the image, obtaining accurate pixel-level contour information for each region. In a specific example, the target segmentation model can include, but is not limited to, the Segformer (SEgmentation Generic Former) model, the Topformer (Token Pyramid VisionTransformer) model, or the PIDnet (Proportional-Integral-Derivative Network), etc. This embodiment of the invention does not limit the specific type of target segmentation model.

[0039] S240. Based on preset evaluation criteria, the original region segmentation result of the molten pool ROI image and the original region segmentation result of the enhanced molten pool ROI image are combined to determine the region segmentation result of the molten pool ROI image.

[0040] Among them, the preset evaluation criteria can be pre-set standards for evaluating the quality of image region segmentation results.

[0041] Accordingly, after obtaining the original region segmentation results of the molten pool ROI image and the original region segmentation results of the enhanced molten pool ROI image, the original region segmentation results of the molten pool ROI image and the original region segmentation results of the enhanced molten pool ROI image can be combined and judged according to the preset evaluation criteria, so as to select the region segmentation results with better quality and determine them as the final region segmentation results of the molten pool ROI image.

[0042] Specifically, the original region segmentation result of the molten pool ROI image is mainly adapted to cases where the original imaging quality is good, thus avoiding anomalies introduced by image enhancement operations; the original region segmentation result of the enhanced molten pool ROI image is mainly adapted to cases where poor imaging contrast leads to abnormal region segmentation. The above scheme, by combining the two original region segmentation results, can significantly reduce anomalies in region segmentation and improve the compatibility of the metallographic measurement method provided by this invention with imaging differences.

[0043] S250. Perform abnormal interference detection on the ROI image of the molten pool to determine the abnormal interference association information in the ROI image of the molten pool.

[0044] Among them, abnormal interference-related information can be abnormal conditions such as foreign objects, pits, scratches, and abrasions included in the ROI image of the molten pool.

[0045] In this embodiment of the invention, after acquiring the melt pool ROI image, anomaly detection can be performed on the melt pool ROI image using a target anomaly detection model to determine the anomaly category and location in the melt pool ROI image, as well as other anomaly interference correlation information. In a specific example, the target anomaly detection module may include, but is not limited to, the YoloV11 model, other versions of the Yolo series models, the SSD model, the Faster R-CNN model, or the DETR model, etc. This embodiment of the invention does not limit the specific type of target detection model.

[0046] S260. Determine the weld formation parameters of the target entity based on the metallographic measurement prior logic, the region segmentation results of the ROI image of the molten pool, and the abnormal interference association information.

[0047] Accordingly, after obtaining the region segmentation results and abnormal interference correlation information of the molten pool ROI image, the region segmentation results and abnormal interference correlation information of the molten pool ROI image can be analyzed and data extracted based on the metallographic measurement prior logic in order to determine the weld formation parameters of the target entity.

[0048] In an optional embodiment of the present invention, determining the weld formation parameters of the target entity based on the metallographic measurement prior logic, the region segmentation result of the molten pool ROI image, and the abnormal interference correlation information may include: performing anomaly removal on the region segmentation result of the molten pool ROI image based on the abnormal interference correlation information to obtain a corrected region segmentation result of the molten pool ROI image; determining weld formation measurement element information based on the metallographic measurement prior logic and the corrected region segmentation result of the molten pool ROI image; and determining the weld formation parameters of the target entity based on the weld formation measurement element information.

[0049] The corrected region segmentation result can be the region segmentation result after anomaly removal. The weld formation measurement element information can be the boundary and point information required to measure the weld formation parameters.

[0050] In this embodiment of the invention, during the process of determining the weld formation parameters of the target entity based on metallographic measurement prior logic, the region segmentation results of the molten pool ROI image, and abnormal interference correlation information, anomalies in the region segmentation results of the molten pool ROI image can first be removed based on the abnormal interference correlation information to obtain a corrected region segmentation result for the molten pool ROI image. It is understood that different types of anomalies require different removal rules. By removing anomalies from the region segmentation results of the molten pool ROI image, the interference of anomalies on the metallographic measurement results can be reduced, thereby reducing the overkill rate of automated metallographic measurement and improving the yield of this solution.

[0051] Furthermore, based on the metallographic measurement prior logic, the boundary and point information required for measuring weld formation parameters, i.e., weld formation measurement element information, can be extracted from the corrected region segmentation results of the molten pool ROI image. After obtaining the weld formation measurement element information, the weld formation parameters such as weld penetration and weld width of the target entity can be calculated using the weld formation measurement element information based on the metallographic measurement prior logic. The metallographic measurement prior logic can be determined based on the metallographic measurement industry standards ISO17639 or GB / T26955. In the above scheme, the metallographic measurement prior logic ensures the rationality and correctness of the metallographic measurement, the pixel-level contour information of the region segmentation results ensures the accuracy and precision of the weld formation measurement element information, and the abnormal interference correlation information provides a reference for eliminating interference during the metallographic measurement process. These three elements form a synergistic support from three dimensions: core logic, data accuracy, and interference elimination, comprehensively ensuring the accuracy of the measurement logic and data, ultimately achieving a high degree of consistency between automated metallographic measurement results and manual measurement data.

[0052] In a specific example, assuming the target entity is the welded part of a lithium battery cell top cover (to the casing) or a sealing pin (to the top cover's liquid injection hole), when calculating its weld formation parameters such as penetration depth and weld width, the target entity's welded sample can first undergo cross-sectional preparation, polishing, and etching treatment perpendicular to the weld axis to clearly reveal the interface between the base material and the weld fusion zone, thus obtaining the fusion line. Based on this, the set of boundary points between the base material's upper surface reference line L0 and the fusion line can be extracted from the metallographic image with the pixel-physical dimension calibration coefficient k completed. The penetration depth is the vertical distance from the lowest point of the fusion line to the reference line L0, and can be calculated based on the following formula: ; The weld width is the horizontal distance between the two intersection points of the weld line and the baseline L0. The weld width of the target entity can be calculated based on the following formula: ; in, For the melting depth of the target entity, This is the lowest point of the fusion line, i.e., the point with the largest Y-coordinate in the set of boundary points of the fusion line. Let L0 be the Y-coordinate of the reference line L0 on the upper surface of the base material. To calibrate the pixel-to-physical size factor, For the weld width of the target entity, The X-coordinate of the point where the fusion line intersects the baseline L0 to the right. The X-coordinate of the point where the fusion line intersects the baseline L0 on the left.

[0053] In an optional embodiment of the present invention, after determining the weld formation parameters of the target entity based on the metallographic measurement prior logic and the region segmentation result of the ROI image of the molten pool, the method may further include: performing a compliance judgment on the weld formation parameters of the target entity based on a preset weld formation size threshold; and determining that the compliance judgment result of the weld formation parameters of the target entity is compliant if it is determined that the weld formation parameters of the target entity are within the range of the preset weld formation size threshold.

[0054] The preset weld formation size threshold can be a pre-defined size threshold for weld formation parameters. The compliance judgment result of the weld formation parameters can be the result obtained by judging the compliance of the weld formation parameters' dimensions.

[0055] In this embodiment of the invention, after determining the weld formation parameters of the target entity based on the metallographic measurement prior logic and the region segmentation results of the molten pool ROI image, a preset weld formation size threshold and the weld formation parameters can be compared. If the weld formation parameter value is within the preset weld formation size threshold range, the target entity is determined to be compliant; if the weld formation parameter value is not within the preset weld formation size threshold range, the target entity is determined to be non-compliant. Furthermore, compliant measurement results can be allowed to proceed, while non-compliant measurement anomalies can be intercepted, thereby avoiding some anomalies caused by automated metallographic measurement and ensuring the accuracy and validity of the entire metallographic analysis measurement data.

[0056] Continuing with the example above, for the welded joint between the sealing pin and the top cover's injection hole, the weld penetration should be greater than or equal to half the thickness of the sealing pin, and less than or equal to the thickness of the sealing pin, to avoid welding through the injection hole. The weld width should be less than or equal to the diameter of the injection hole. For the welded joint between the lithium battery cell's top cover and the casing, the weld penetration should be greater than or equal to 80% of the casing thickness to meet the welding sealing strength requirements, and the weld width should match the designed weld width.

[0057] Optionally, after determining the weld formation parameters of the target entity based on the metallographic measurement prior logic and the region segmentation results of the molten pool ROI image, manual verification can be performed to address some over-scanning issues in automated metallographic measurement. Compliant metallographic measurement results can also be stored to facilitate subsequent data verification and information sharing.

[0058] This invention acquires a molten pool ROI image of a target entity and performs contrast enhancement and filtering on the molten pool ROI image to obtain an enhanced molten pool ROI image. After obtaining the enhanced molten pool ROI image, a target segmentation model is used to perform region segmentation processing on both the molten pool ROI image and the enhanced molten pool ROI image to obtain the original region segmentation results of the molten pool ROI image and the enhanced molten pool ROI image. Further, a composite judgment is made on the original region segmentation results of the molten pool ROI image and the enhanced molten pool ROI image according to preset evaluation criteria to determine the region segmentation result of the molten pool ROI image. Simultaneously, abnormal interference detection is performed on the molten pool ROI image to determine the abnormal interference correlation information. Further, the weld formation parameters of the target entity are determined based on metallographic measurement prior logic, the region segmentation results of the molten pool ROI image, and the abnormal interference correlation information. The above solution solves the accuracy shortcomings of existing metallographic measurement technology caused by multiple interferences and unclear grayscale contrast, and can improve the processing efficiency and accuracy of metallographic measurement.

[0059] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information in this technical solution comply with relevant laws and regulations and do not violate public order and good morals.

[0060] It should be noted that all information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data comply with the relevant laws, regulations and standards of the relevant regions.

[0061] It should be noted that any arrangement or combination of the technical features in the above embodiments also falls within the protection scope of this invention.

[0062] Example 3 Figure 3 This is a schematic diagram of a metallographic measuring device provided in Embodiment 3 of the present invention, as shown below. Figure 3 As shown, the device includes: a molten pool ROI image acquisition module 310, an image region segmentation module 320, and a weld formation parameter determination module 330, wherein: The ROI image acquisition module 310 is used to acquire the ROI image of the target entity.

[0063] The image region segmentation module 320 is used to perform region segmentation on the ROI image of the target entity to obtain the region segmentation result of the ROI image.

[0064] The weld formation parameter determination module 330 is used to determine the weld formation parameters of the target entity based on the metallographic measurement prior logic and the region segmentation results of the ROI image of the molten pool.

[0065] This invention acquires a molten pool ROI image of a target entity and performs region segmentation on the ROI image to obtain the region segmentation result. Further, the weld formation parameters of the target entity are determined based on metallographic measurement prior logic and the region segmentation result of the ROI image. This solution addresses the accuracy shortcomings of existing metallographic measurement techniques caused by multiple interferences and unclear grayscale contrast, thereby improving the processing efficiency and accuracy of metallographic measurements.

[0066] Optionally, the ROI image acquisition module 310 is specifically used to: acquire a microscopic image of the target entity; perform ROI localization on the microscopic image of the target entity using a target detection model to determine the ROI size association data of the target entity; and, if the ROI size association data of the target entity is determined to be less than or equal to a preset size threshold, determine the ROI image of the target entity based on a preset input size and the ROI size association data of the target entity.

[0067] Optionally, the image region segmentation module 320 is specifically used for: performing contrast enhancement and filtering processing on the ROI image of the target entity to obtain an enhanced ROI image; performing region segmentation processing on the ROI image and the enhanced ROI image respectively using a target segmentation model to obtain the original region segmentation result of the ROI image and the original region segmentation result of the enhanced ROI image; and performing a composite judgment on the original region segmentation result of the ROI image and the original region segmentation result of the enhanced ROI image according to a preset evaluation standard to determine the region segmentation result of the ROI image.

[0068] Optionally, the above-mentioned device may further include an abnormal interference detection module, used to: perform abnormal interference detection on the molten pool ROI image and determine abnormal interference correlation information in the molten pool ROI image. The weld formation parameter determination module 330 is specifically used to: determine the weld formation parameters of the target entity based on the metallographic measurement prior logic, the region segmentation result of the molten pool ROI image, and the abnormal interference correlation information.

[0069] Optionally, the weld formation parameter determination module 330 is further configured to: perform anomaly removal on the region segmentation result of the molten pool ROI image based on the abnormal interference association information to obtain the corrected region segmentation result of the molten pool ROI image; determine weld formation measurement element information based on the metallographic measurement prior logic and the corrected region segmentation result of the molten pool ROI image; and determine the weld formation parameters of the target entity based on the weld formation measurement element information.

[0070] Optionally, the above-mentioned device may further include a compliance judgment module, used to: judge the compliance of the weld formation parameters of the target entity according to a preset weld formation size threshold; and determine that the compliance judgment result of the weld formation parameters of the target entity is compliant if it is determined that the weld formation parameters of the target entity are within the range of the preset weld formation size threshold.

[0071] The metallographic measuring device described above can execute the metallographic measuring method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the metallographic measuring method provided in any embodiment of the present invention.

[0072] Since the metallographic measuring device described above is capable of executing the metallographic measuring method in the embodiments of the present invention, those skilled in the art can understand the specific implementation and various variations of the metallographic measuring device in this embodiment based on the metallographic measuring method described in the embodiments of the present invention. Therefore, how the metallographic measuring device implements the metallographic measuring method in the embodiments of the present invention will not be described in detail here. Any device used by those skilled in the art to implement the metallographic measuring method in the embodiments of the present invention falls within the scope of protection of this application.

[0073] Example 4 Figure 4 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, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing 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.

[0074] like Figure 4As 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.

[0075] 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 devices through computer networks such as the Internet and / or various telecommunications networks.

[0076] 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 metallographic measurement methods.

[0077] In some embodiments, the metallographic measurement method may 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 may 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 metallographic measurement method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the metallographic measurement method by any other suitable means (e.g., by means of firmware).

[0078] Optionally, the metallographic measurement method may include: acquiring a ROI image of the molten pool of the target entity; performing region segmentation on the ROI image of the molten pool of the target entity to obtain a region segmentation result of the ROI image; and determining the weld formation parameters of the target entity based on metallographic measurement prior logic and the region segmentation result of the ROI image.

[0079] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-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 system 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 system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0080] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0081] 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 system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or 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 fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0082] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides 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).

[0083] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0084] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0085] 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 no limitation is imposed herein.

[0086] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. 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 disclosure should be included within the scope of protection of this disclosure.

Claims

1. A metallographic measurement method, characterized in that, include: Obtain the Region of Interest (ROI) image of the melt pool of the target entity; The ROI image of the target entity is segmented to obtain the ROI image segmentation result. The weld formation parameters of the target entity are determined based on the metallographic measurement prior logic and the region segmentation results of the ROI image of the molten pool.

2. The method according to claim 1, characterized in that, The acquisition of the melt pool ROI image of the target entity includes: Obtain a microscopic image of the target entity; The target entity's microscopic image is used to locate the molten pool and determine the molten pool size correlation data of the target entity. If the melt pool size correlation data of the target entity is determined to be less than or equal to a preset size threshold, the melt pool ROI image of the target entity is determined according to the preset input size and the melt pool size correlation data of the target entity.

3. The method according to claim 1, characterized in that, The step of performing region segmentation on the ROI image of the target entity to obtain the region segmentation result of the ROI image includes: The ROI image of the target entity is subjected to contrast enhancement and filtering to obtain an enhanced ROI image. The ROI image of the molten pool and the enhanced ROI image of the molten pool are processed by the target segmentation model to obtain the original region segmentation results of the ROI image of the molten pool and the original region segmentation results of the enhanced ROI image of the molten pool. The original region segmentation result of the molten pool ROI image and the original region segmentation result of the enhanced molten pool ROI image are combined and judged according to the preset evaluation criteria to determine the region segmentation result of the molten pool ROI image.

4. The method according to claim 1, characterized in that, Before determining the weld formation parameters of the target entity based on the metallographic measurement prior logic and the region segmentation results of the molten pool ROI image, the method further includes: Anomaly interference detection is performed on the ROI image of the molten pool to determine the correlation information of the abnormal interference in the ROI image of the molten pool; The step of determining the weld formation parameters of the target entity based on metallographic measurement prior logic and the region segmentation results of the molten pool ROI image includes: The weld formation parameters of the target entity are determined based on the metallographic measurement prior logic, the region segmentation results of the ROI image of the molten pool, and the abnormal interference correlation information.

5. The method according to claim 4, characterized in that, The step of determining the weld formation parameters of the target entity based on metallographic measurement prior logic, the region segmentation results of the molten pool ROI image, and the abnormal interference correlation information includes: Based on the abnormal interference correlation information, the region segmentation results of the molten pool ROI image are subjected to abnormal removal to obtain the corrected region segmentation results of the molten pool ROI image. Based on the metallographic measurement prior logic and the corrected region segmentation results of the molten pool ROI image, the weld formation measurement element information is determined; The weld formation parameters of the target entity are determined based on the weld formation measurement element information.

6. The method according to claim 1, characterized in that, After determining the weld formation parameters of the target entity based on the metallographic measurement prior logic and the region segmentation results of the molten pool ROI image, the method further includes: The compliance of the weld formation parameters of the target entity is judged based on the preset weld formation size threshold. If the weld formation parameters of the target entity are determined to be within the preset weld formation size threshold range, the compliance judgment result of the weld formation parameters of the target entity is determined to be compliant.

7. A metallographic measuring device, characterized in that, include: The ROI image acquisition module is used to acquire the ROI image of the target entity. The image region segmentation module is used to segment the ROI image of the target entity to obtain the region segmentation result of the ROI image. The weld formation parameter determination module is used to determine the weld formation parameters of the target entity based on the metallographic measurement prior logic and the region segmentation results of the ROI image of the molten pool.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that is executed by the at least one processor to enable the at least one processor to perform the metallographic measurement method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the metallographic measurement method according to any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program / instruction, wherein the computer program / instruction, when executed by a processor, implements the metallographic measurement method according to any one of claims 1-6.

Images