Welding seam defect identification method and device based on X-ray welding seam image

Abstract

The embodiment of the invention provides a weld defect identification method and device based on an X-ray weld image. When weld defect identification is carried out, image area analysis is carried out on an X-ray weld image at a pipeline weld to obtain image area characteristics of the X-ray weld image, and the obtained image area characteristics comprise area composition, area position, area brightness, area density and area shape. And then, providing the image region features of the X-ray welding seam image to a welding seam defect identification model to carry out welding seam defect identification. According to the welding seam defect identification method, the welding seam defect identification model is used for performing welding seam defect identification based on the image area characteristics such as the area position, the area brightness, the area density and the area shape of the X-ray welding seam image, and the efficiency and the precision of welding seam defect identification can be improved.

Description

Technical Field

[0001] The embodiments of this specification generally relate to the field of chemical production, and more particularly to a method and device for identifying weld defects based on X-ray weld images at pipeline welds. Background Art

[0002] In an integrated chemical production system, a large number of metal equipment need to be deployed, and pipelines need to be laid between the metal equipment for connection. The laid pipelines can be as long as 1,500 kilometers, for example. Therefore, multiple pipelines need to be welded together to achieve this, and welding is also required between the pipelines and the connected metal equipment. If there are defects in the welds at the welding point, it will cause chemical production risks such as leakage of chemical raw materials. Summary of the invention

[0003] In view of the above, the embodiments of this specification provide a method and device for weld defect recognition based on X-ray weld images. By using the weld defect recognition method, the efficiency and accuracy of weld defect recognition can be improved by using a weld defect recognition model to perform weld defect recognition based on image area features such as area position, area brightness, area density and area shape of the X-ray weld image.

[0004] According to one aspect of an embodiment of the present specification, a weld defect recognition method based on an X-ray weld image is provided, comprising: performing image region analysis on an X-ray weld image at a pipe weld to obtain image region features of the X-ray weld image, wherein the image region features include region position, region brightness, region density, and region shape; and providing the image region features of the X-ray weld image to a weld defect recognition model to perform weld defect recognition.

[0005] Optionally, in an example of the above aspect, providing the image area features of the X-ray weld image to a weld defect recognition model for weld defect recognition may include: providing the image area features of the X-ray weld image to a defect feature generation layer of the weld defect recognition model to generate a defect feature representation of the X-ray weld image; and providing the defect feature representation of the X-ray weld image to a defect classification layer of the weld defect recognition model for weld defect recognition.

[0006] Optionally, in an example of the above aspect, the X-ray weld image includes a 360-degree weld chain image formed by splicing multiple scanned film images at different angles at the pipeline weld.

[0007] Optionally, in an example of the above aspect, the training data set of the weld defect recognition model includes a training data set constructed based on an actual X-ray weld image at a pipeline weld and an enhanced X-ray weld image obtained by performing data enhancement on the actual X-ray weld image, and the data enhancement includes at least one of image rotation, image translation, image scaling, and filter-based image filtering.

[0008] Optionally, in an example of the above aspect, before performing image region analysis on the X-ray weld image at the pipeline weld, the weld defect identification method may further include: determining whether the X-ray weld image at the pipeline weld has been identified based on weld shape parameters according to an identified X-ray weld image library, wherein the weld shape parameters include weld overlay pitch and weld arc. In response to the X-ray weld image not being identified, performing image region analysis on the X-ray weld image at the pipeline weld.

[0009] Optionally, in an example of the above aspect, based on the weld shape parameters, determining whether the X-ray weld image at the pipeline weld has been identified according to the identified X-ray weld image library may include: acquiring the weld shape parameters of the X-ray weld image; and based on the acquired weld shape parameters, determining whether the X-ray weld image has been identified according to the identified X-ray weld image library.

[0010] Optionally, in an example of the above aspect, based on the weld shape parameters, determining whether the X-ray weld image at the pipeline weld has been identified according to the identified X-ray weld image library may include: providing the X-ray weld image and the identified X-ray weld images in the identified X-ray weld image library to a weld image similarity determination model to determine whether the X-ray weld image has been identified, and the weld image similarity determination model is pre-trained using the weld shape parameters as model features.

[0011] Optionally, in an example of the above aspect, the training data set of the weld image similarity determination model includes a training data set constructed based on an actual X-ray weld image at a pipeline weld and an enhanced X-ray weld image obtained by performing data enhancement on the actual X-ray weld image, and the data enhancement includes at least one of image rotation, image translation, image scaling, and filter-based image filtering.

[0012] Optionally, in an example of the above aspect, the weld defect identification method may further include: generating a weld defect identification report based on the weld defect identification result.

[0013] According to another aspect of an embodiment of the present specification, a weld defect identification device based on an X-ray weld image is provided, comprising: an image area analysis unit, configured to perform image area analysis on an X-ray weld image at a pipe weld to obtain image area features of the X-ray weld image, wherein the image area features include area position, area brightness, area density and area shape; and a weld defect identification unit, configured to provide the image area features of the X-ray weld image to a weld defect identification model for weld defect identification.

[0014] Optionally, in an example of the above aspect, the weld defect identification device may also include: an image recognition determination unit, configured to determine whether the X-ray weld image has been recognized based on weld shape parameters and a library of recognized X-ray weld images before performing image area analysis on the X-ray weld image, wherein the weld shape parameters include weld surfacing pitch and weld curvature. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] A further understanding of the nature and advantages of the content of this specification may be achieved by referring to the following drawings. In the drawings, similar components or features may have the same reference numerals.

[0016] Figure 1 An exemplary block diagram of a weld defect identification system according to an embodiment of the present specification is shown.

[0017] Figure 2 An example schematic diagram of an X-ray weld image according to an embodiment of the present specification is shown.

[0018] Figure 3 An example schematic diagram of an X-ray weld image formed by stitching together multiple X-ray film images according to an embodiment of the present specification is shown.

[0019] Figure 4A-Figure 4O An example schematic diagram of a defective X-ray weld image according to an embodiment of the present specification is shown.

[0020] Figure 5 An example schematic diagram of a weld defect recognition model according to an embodiment of the present specification is shown.

[0021] Figure 6 An exemplary flow chart of a weld defect identification method according to an embodiment of the present specification is shown.

[0022] Figure 7 An exemplary flowchart of a process for determining whether a weld image is recognized or not according to an embodiment of the present specification is shown.

[0023] Figure 8An example block diagram of a weld defect identification device according to an embodiment of the present specification is shown.

[0024] Fig. 9 An example schematic diagram of a weld defect identification device implemented based on a computer system according to an embodiment of the present specification is shown. DETAILED DESCRIPTION

[0025] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that the discussion of these embodiments is only to enable those skilled in the art to better understand and implement the subject matter described herein, and is not a limitation of the scope of protection, applicability or examples set forth in the claims. The functions and arrangements of the elements discussed can be changed without departing from the scope of protection of the contents of this specification. Various examples can omit, replace or add various processes or components as needed. For example, the described method can be performed in an order different from the described order, and various steps can be added, omitted or combined. In addition, the features described relative to some examples can also be combined in other examples.

[0026] As used herein, the term "including" and its variations represent open terms, meaning "including but not limited to". The term "based on" means "based at least in part on". The terms "one embodiment" and "an embodiment" mean "at least one embodiment". The term "another embodiment" means "at least one other embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other definitions may be included below, whether explicit or implicit. Unless the context clearly indicates otherwise, the definition of a term is consistent throughout the specification.

[0027] Figure 1 An example block diagram of a weld defect identification system 100 according to an embodiment of the present specification is shown.

[0028] like Figure 1 As shown, the weld defect recognition system 100 includes a weld image acquisition device 110, a weld image recognition library 120, a weld defect recognition model training device 130, a weld defect recognition model storage device 140, and a weld defect recognition device 150. The weld image acquisition device 110, the weld image recognition library 120, the weld defect recognition model training device 130, the weld defect recognition model storage device 140, and the weld defect recognition device 150 can be communicatively connected via a network 160. In some embodiments, some or all of the components in the weld image acquisition device 110, the weld image recognition library 120, the weld defect recognition model training device 130, the weld defect recognition model storage device 140, and the weld defect recognition device 150 can communicate directly without communicating through the network 160.

[0029] In some embodiments, the network 160 may be any one or more of a wired network or a wireless network. Examples of the network 160 may include, but are not limited to, a cable network, an optical fiber network, a telecommunications network, an enterprise intranet, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigZee network (ZigZee), near field communication (NFC), a bus within a device, a line within a device, etc., or any combination thereof.

[0030] The weld image acquisition device 110 is used to acquire an X-ray weld image at the weld of the pipeline to be inspected for weld defects. A pipeline weld refers to a joint formed when two cast or forged metals are connected together to form a pipeline. The formed pipeline weld is usually a circular weld. In view of the complexity of the pipeline welding site, welding must be performed manually by welders. Due to the constant changes in the welder's posture during welding and the uniqueness of the geographical and temporal space where each weld is welded, each weld has a unique weld shape, such as a unique weld wave. The weld shape parameters of the pipeline weld may include, for example, weld edge shape parameters, such as weldment overlaying gap and weldment radian. The weldment overlaying pitch is used to refer to the overlapping distance between two adjacent overlaying welds. The size of the weldment overlaying weld pitch has a significant effect on the flatness of the overlaying layer surface, the uniformity of the chemical composition of the overlaying layer, and the dilution rate of the parent metal. The smaller the weldment overlaying pitch, the higher the pipeline welding quality. The arc of a weldment is used to refer to the radius of curvature formed by the surface of the weldment. Figure 2 An example schematic diagram of an X-ray weld image according to an embodiment of the present specification is shown. In addition, the weld shape parameters may also include weld height, weld width, and weld surface corrugation concave-convexity.

[0031] In some embodiments, the weld image acquisition device 110 can be implemented as an X-ray scanner. When acquiring an X-ray weld image, the pipeline weld is scanned at a given angle (e.g., 0°, 120°, or 240°) to obtain an X-ray weld image (scanned film image) at the pipeline weld. Due to the limitations of the X-ray radiation source used for X-ray scanning, the X-ray weld image obtained each time is only a partial weld of the pipeline weld. In some embodiments, scanning can be performed at multiple different angles to obtain multiple scanned film images, and then the obtained multiple scanned film images are spliced ​​into a 360-degree weld chain image, thereby obtaining a complete X-ray weld image. In some embodiments, a 360-degree digitized weld chain image can be formed by splicing multiple scanned film images at different angles at the pipeline weld and performing digital twinning as an X-ray weld image at the pipeline weld. Figure 3 An example schematic diagram of an X-ray weld image formed by stitching together multiple X-ray film images according to an embodiment of the present specification is shown.

[0032] The X-ray weld image acquired by the weld image acquisition device 110 is provided to the weld defect recognition device 150. After receiving the X-ray weld image, the weld defect recognition device 150 performs image area analysis on the X-ray weld image to obtain the image area features of the X-ray weld image, and then provides the image area features to the weld defect recognition model to perform weld defect recognition. The weld defect recognition process of the weld defect recognition device 150 will be described in detail later in conjunction with the accompanying drawings. In some embodiments, the weld image acquisition device 110 may also have an image preprocessing function, such as an image denoising function. The weld image acquisition device 110 may perform image denoising on the acquired original X-ray weld image, thereby improving the image quality of the X-ray weld image, and provide the X-ray weld image after image denoising to the weld defect recognition device 150 for weld defect recognition, thereby improving the accuracy of weld defect recognition.

[0033] The X-ray weld image that has completed the weld defect identification can be stored in the weld image library 120 for use by the weld defect identification device 150 to perform repeated identification and appraisal of the weld image. In some embodiments, the original X-ray weld image or the X-ray weld image after image preprocessing can be stored in the weld image library 120. In some embodiments, the image feature representation (Embedding) obtained after the original X-ray weld image or the X-ray weld image after image preprocessing is extracted from the image feature can be stored in the weld image library 120. The image feature representation can also be called an image feature vector representation.

[0034] The weld defect recognition model used by the weld defect recognition device 150 may include, for example, a machine learning model and a deep learning model. The machine learning model may include a supervised learning model. Examples of supervised learning models may include, for example, a linear regression model, a logistic regression model, a decision tree, a support vector machine, a BP neural network, a random forest, etc. Examples of deep learning models may include, for example, a convolutional neural network (CNN), a recurrent neural network (RNN), a long short-term memory network (LSTM), etc. In some embodiments, the weld defect recognition model is implemented as a multi-classification model for realizing multi-defect category recognition.

[0035] Figures 4A-4O An example schematic diagram of a defective X-ray weld image according to an embodiment of the present specification is shown.

[0036] Figure 4A An example schematic diagram of an X-ray weld image with a cold lap defect according to an embodiment of the present specification is shown. A cold lap defect is a weld defect that occurs when the flux metal is not properly fused with the base metal or the previously fully welded material. Under cold lap, the arc of the weld fails to fully melt the base metal, so that a small amount of molten flux metal flows into the base metal and cannot achieve sufficient bonding. If a cold lap defect occurs, an irregular weld shape and an area containing inclusions in the weld will appear in the X-ray weld image. Since the area density of the area containing inclusions is different from the area density of the surrounding area, for example, the area density of the area containing inclusions is usually higher than the area density of the surrounding area, the cold lap defect can be judged based on the area density. As can be seen from the above, when there is an area with irregular edges, discontinuous lines or a grayscale difference with the surrounding area in the weld image, a cold lap defect will occur, so that image area features such as area shape and area density can be used to characterize the cold lap defect.

[0037] Figure 4BAn example schematic diagram of an X-ray weld image with a porosity defect according to an embodiment of the present specification is shown. Porosity defects are weld defects caused by gas entrapment in solid metals. On an X-ray weld image, pores can take on a variety of shapes, but typically appear as dark round or irregular spots or spots that are individual, clustered, or in rows. Sometimes, pores can be elongated and may appear to have tails. This is the result of gas trying to escape while the metal is still in a liquid state, called wormhole pores. All pores are voids in the material, and their area density (e.g., radiographic density) will be higher than the surrounding area. As can be seen from the above, image area features such as area shape, area brightness, and area density can be used to characterize porosity defects.

[0038] Figure 4C An example schematic diagram of an X-ray weld image with a Cluster Porosity defect according to an embodiment of the present specification is shown. A Cluster Porosity defect is a weld defect that occurs when the electrode of the flux is contaminated with moisture. Moisture turns into gas when heated and is trapped in the weld during the welding process. Cluster Porosity looks like regular pores in an X-ray weld image, but is tightly grouped together. As can be seen from the above, a Cluster Porosity defect occurs when there are high-density and tightly distributed dark spots in the weld image, and the shape and size uniformity of the spots, so that the Cluster Porosity defect can be characterized using image area features such as area shape, area brightness, and area density.

[0039] Figure 4D An example schematic diagram of an X-ray weld image with a slag inclusion defect according to an embodiment of the present specification is shown. Slag inclusion is a non-metallic solid material sandwiched in the weld metal or between the weld and the parent material. In the X-ray weld image, if there is a dark jagged asymmetric shape in or along the weld area, it indicates the presence of slag inclusion, so that image area features such as area shape, area position, and area density can be used to characterize the slag inclusion defect.

[0040] Figure 4EAn example schematic diagram of an X-ray weld image with an Incomplete Penetration / Lack of Penetration defect according to an embodiment of the present specification is shown. An incomplete penetration defect is a weld defect that occurs when the weld metal fails to penetrate the joint. When an incomplete penetration defect occurs, there is a lack of permeability, which leads to a natural stress concentration, so that cracks may propagate therefrom. If an incomplete penetration defect exists, a dark area will appear in the X-ray weld image, and the edges of the dark area are clear and straight, and run down along the pad or root surface in the center of the weldment, so that the image area features such as area shape, area brightness, area position, and area density can be used to characterize the incomplete penetration defect.

[0041] Figure 4F An example schematic diagram of an X-ray weld image with an incomplete fusion defect according to an embodiment of the present specification is shown. An incomplete fusion defect is a defect that occurs when the flux metal cannot be properly fused with the base metal. If an incomplete fusion defect occurs, one or more dark lines along the weld preparation area or the weld connection area and toward the weld direction will appear on the X-ray weld image, so that image area features such as area shape, area brightness, and area position can be used to characterize the incomplete fusion defect.

[0042] Figure 4G An example schematic diagram of an X-ray weld image with an internal concavity (Internal Concavity / SuckBack) defect according to an embodiment of the present specification is shown. An internal concavity (suckback) defect refers to a weld defect that occurs when the weld metal contracts and is pulled into the weld root when cooling. If an internal concavity defect occurs, similar to a lack of penetration defect, a straight line with irregular edges will appear on the X-ray weld image, and the straight line is usually wide at the center of the weld image, so that the internal concavity defect can be characterized using image area features such as area shape and area position.

[0043] Figure 4H An example schematic diagram of an X-ray weld image with an external / crown undercut defect according to an embodiment of the present specification is shown. External undercut is the erosion of the base metal near the crown of the weld. If an external undercut defect occurs, a dark irregular line along the outer edge of the weld area appears in the X-ray weld image, so that the external undercut defect can be characterized using image area features such as area shape, area position, and area brightness.

[0044] Fig. 4IAn example schematic diagram of an X-ray weld image with an offset (Offset / Mismatch) defect according to an embodiment of the present specification is shown. A mismatch defect is a weld defect that occurs when two parts welded together are not properly aligned. If a mismatch defect occurs, the X-ray weld image will show an obvious difference in density between the two pieces, a dark straight line formed by the staggered position, inconsistent thickness of the weld area, etc. The difference in density is due to the difference in material thickness. The dark straight line is caused by the failure of the weld metal to fuse with the pad area. As can be seen from the above description, image area features such as area shape, area brightness, and area density can be used to characterize the mismatch defect.

[0045] Figure 4J An example schematic diagram of an X-ray weld image with an inadequate weld reinforcement defect according to an embodiment of the present specification is shown. An inadequate weld reinforcement defect refers to an area in the weld where the thickness of the deposited weld metal is less than the thickness of the base material. If an inadequate weld reinforcement defect occurs, a weld area with a higher (darker) image density than the image density of the surrounding base material, an area with a weld metal thickness significantly less than the base material thickness, and a flat or concave weld top profile will appear in the X-ray weld image, so that image area features such as area density and area shape can be used to characterize the inadequate weld reinforcement defect.

[0046] Figure 4K An example schematic diagram of an X-ray weld image with an Excess Weld Reinforcement defect according to an embodiment of the present specification is shown. An Excess Weld Reinforcement defect refers to an area where the weld metal added to the weld exceeds the area specified in the engineering drawings and specifications. If an Excess Weld Reinforcement defect occurs, a weld area with a lower local density, a prominent weld contour, and a weld metal thickness that significantly exceeds the base material thickness will appear in the X-ray weld image, so that the Excess Weld Reinforcement defect can be characterized using image area features such as area density and area shape.

[0047] Figure 4L An example schematic diagram of an X-ray weld image with a crack defect according to an embodiment of the present specification is shown. A crack defect can be detected in an X-ray weld image only when the crack propagates in the thickness variation direction parallel to the X-ray beam. Crack defects appear in the X-ray weld image as jagged weak irregular lines, thin and long weak dark lines, and "tails" extending from slag inclusions or porosity defects, so that image area features such as area shape and area brightness can be used to characterize crack defects.

[0048] Figure 4MAn example schematic diagram of an X-ray weld image with a tungsten inclusion defect according to an embodiment of the present specification is shown. A tungsten inclusion defect is a weld defect in which tungsten is trapped in the weld due to the use of an incorrect welding process. Tungsten inclusion defects usually occur when welding using a TIG welding process. From a radiological point of view, tungsten is denser than aluminum or steel, so that tungsten appears as a lighter density area in the X-ray weld image, and has a clear outline, usually with irregular or rounded edges, which can be clearly distinguished from the surrounding weld metal, so that image area features such as area shape and area density can be used to characterize tungsten inclusion defects.

[0049] Figure 4N An example schematic diagram of an X-ray weld image with oxygen inclusion defects according to an embodiment of the present specification is shown. Oxygen inclusions are usually visible on the surface of the welded material (especially aluminum). The density of oxygen inclusions is usually lower than that of the surrounding materials, so they appear as dark and irregularly shaped discontinuities in the X-ray weld image. These areas appear as discontinuities with lower density on the image, so that image area features such as area shape, area density, and area brightness can be used to characterize oxygen inclusion defects.

[0050] Fig.4O An example schematic diagram of an X-ray weld image with a burn-through defect according to an embodiment of the present specification is shown. A burn-through defect occurs when too much heat causes too much weld metal to penetrate the weld area. If a burn-through defect occurs, a black spot surrounded by a light-colored spherical area (icicle) appears in the X-ray weld image, so that image area features such as area shape, area brightness, etc. can be used to characterize the burn-through defect.

[0051] From the above image analysis of defective X-ray weld images, it can be seen that if there are weld defects in the X-ray weld image, regional partitions will appear in the X-ray weld image and there will be abnormal areas in the partitioned areas, for example, abnormal regional shapes, abnormal regional brightness, abnormal regional density, etc. Therefore, when performing weld defect recognition on X-ray weld images, image region features of X-ray weld images can be selected as model features of the weld defect recognition model for model training, and after completing the weld defect recognition model training, image region analysis is performed on the X-ray weld image of the pipeline weld to obtain image region features, and the image region features are provided to the weld defect recognition model for weld defect recognition.

[0052] In some embodiments, the image region features used may include, for example, region position, region brightness, region density, and region shape. Region composition refers to how many regions the X-ray weld image consists of. Region position refers to the coordinate position information of each region. Region brightness refers to the brightness value of the region. Region density refers to the density value of the region, for example, radiographic density. Region shape may be, for example, the shape of the region edge, for example, irregular lines, circular spots, etc. In some embodiments, image region features may also include region composition, that is, how many regions the X-ray weld image consists of.

[0053] Figure 5 FIG. 5 shows an example schematic diagram of a weld defect recognition model 500 according to an embodiment of the present specification. Figure 5 As shown, the weld defect recognition model 500 includes a defect feature generation layer 510 and a defect classification layer 520 .

[0054] The defect feature generation layer 510 is used to generate a defect feature representation of the X-ray weld image based on the image region features obtained by performing image region analysis on the input X-ray weld image. The image region features of the X-ray weld image may include region position, region brightness, region density, and region shape. In some embodiments, the feature extraction layer 410 may be implemented using a convolutional neural network, and the generated defect feature representation is represented as a defect feature vector having a specific dimension, for example, a 20-dimensional defect feature vector. When generating the defect feature representation, the image region features of the X-ray weld image may be quantized, and the quantized image region features may be provided to the convolutional neural network to generate a defect feature vector.

[0055] The defect classification layer 520 is used to classify weld defects based on the defect feature representation of the X-ray weld image, thereby outputting the weld defect category to complete the weld defect identification. In some embodiments, the defect classification layer 520 can be implemented using a fully connected layer (Full Connect). In some embodiments, the defect classification layer 520 can implement multi-classification recognition, and the output result is each defect classification and the corresponding probability (confidence).

[0056] The weld defect recognition model training device 130 can pre-train a weld defect recognition model using a training data set, and store the trained weld defect recognition model in the weld defect recognition model storage device 140 for use by the weld defect recognition device 150. In some embodiments, the weld defect recognition model trained by the weld defect recognition model training device 130 can be directly deployed in the weld defect recognition device 150 without the weld defect recognition model storage device 140.

[0057] In some embodiments, the training data set used in the training of the weld defect recognition model can be constructed based on the actual X-ray weld image at the pipe weld. In some embodiments, in order to expand the data scale of the training data set and increase the data diversity, in addition to using the actual X-ray weld image at the pipe weld to construct the training data set, the actual X-ray weld image can also be data enhanced to obtain an enhanced X-ray weld image, and an enhanced data set can be constructed based on the enhanced X-ray weld image to serve as the training data set to perform data enhancement on the training data set. The data enhancement performed on the actual X-ray weld image can, for example, include at least one of image rotation, image translation, image scaling, and filter-based image filtering.

[0058] After the weld defect recognition model is trained, the weld defect recognition device 150 can use the trained weld defect recognition model to perform weld defect recognition based on the X-ray weld image acquired by the weld image acquisition device 110 .

[0059] Figure 6 An example flow chart of a weld defect identification method 600 according to an embodiment of the present specification is shown.

[0060] like Figure 6 As shown, after acquiring the X-ray weld image at the pipeline weld, at 610, based on the weld shape parameters, the X-ray weld image at the pipeline weld is identified according to the identified X-ray weld image library, and the weld shape parameters include the weldment surfacing pitch and the weldment curvature.

[0061] In some embodiments, the acquired X-ray weld image may be an X-ray weld film image acquired by scanning at a given angle by a weld image acquisition device. Due to the limitations of the X-ray radiation source used for X-ray scanning, the X-ray weld image is only a partial weld of the pipeline weld. In some embodiments, the acquired X-ray weld image may be a 360-degree weld chain image formed by splicing multiple scanned film images at different angles at the pipeline weld, for example, a 360-degree digitized weld chain image formed by splicing multiple scanned film images at different angles at the pipeline weld and performing digital twinning. In this case, since the acquired X-ray weld image is a complete weld image of the pipeline weld, it is possible to prevent the X-ray weld image at pipeline B from being counterfeited by splicing X-ray weld images acquired by scanning at different angles at pipeline A.

[0062] In some embodiments, a weld image similarity determination model may be pre-trained. For example, a weld image similarity determination model may be pre-trained using weld shape parameters as model features. After the weld image similarity determination model is trained, the X-ray weld image and the identified X-ray weld image in the identified X-ray weld image library are provided to the weld image similarity determination model to determine whether the X-ray weld image has been identified. For example, the weld image similarity determination model may be used to determine the similarity between the X-ray weld image and the identified X-ray weld image, and if there is an identified X-ray weld image with a similarity greater than a predetermined threshold, the X-ray weld image provided to the weld defect identification device is considered to have been identified.

[0063] In some examples, the training data set of the weld image similarity determination model may include a training data set constructed based on an actual X-ray weld image at a pipe weld. In some examples, the training data set of the weld image similarity determination model may include a training data set constructed based on an actual X-ray weld image at a pipe weld and an enhanced X-ray weld image obtained by performing data enhancement on the actual X-ray weld image. The data enhancement performed on the actual X-ray weld image may, for example, include at least one of image rotation, image translation, image scaling, and filter-based image filtering. According to the above-mentioned model training method, since the training data set used for model training includes a training data set that has undergone data enhancement processing such as image rotation, image translation, and image scaling, if the X-ray weld image provided to the weld image similarity determination model is obtained by performing data enhancement processing such as image rotation, image translation, and image scaling on the identified X-ray weld image, then the weld image similarity determination model can still be used to determine that the image is similar to the identified X-ray weld image, thereby improving the weld image similarity determination model's ability to identify new X-ray weld images that are counterfeited by performing data enhancement processing on the identified X-ray weld image, avoiding repeated identification of the identified weld image, and thereby improving the efficiency of weld defect recognition.

[0064] Figure 7 An exemplary flow chart of a process 700 for determining whether a weld image is recognized or not according to an embodiment of the present specification is shown.

[0065] like Figure 7 As shown, at 710, the weld shape parameters of the X-ray weld image to be identified are obtained.

[0066] At 720, based on the acquired weld shape parameters, it is determined whether the X-ray weld image has been identified according to the identified X-ray weld image library. For example, the weld shape parameters of the X-ray weld image to be identified can be compared with the weld shape parameters of each identified X-ray weld image in the identified X-ray weld image library. If it is determined based on the comparison result of the weld shape parameters that the similarity between the two X-ray weld images exceeds a predetermined threshold, it is considered that there is an identified X-ray weld image similar to the X-ray weld image to be identified, thereby determining that the X-ray weld image to be identified has been identified.

[0067] In some embodiments, the identified X-ray weld image library stores the original image data of the identified X-ray weld image. In some examples, the identified X-ray weld image library may also store digital twin image data obtained by digital twinning the original image data. In this case, the acquired weld shape parameters are the actual shape parameters of the X-ray weld image. For example, a computer image recognition algorithm may be used to perform weld shape recognition on the X-ray weld image, thereby obtaining the weld shape parameters of the X-ray weld image to be identified.

[0068] In some embodiments, the identified X-ray weld image library stores weld shape feature vectors obtained based on weld shape parameters of the identified X-ray weld images. In this case, when obtaining the weld shape parameters of the X-ray weld image to be identified, the X-ray weld image to be identified can be provided to a weld shape feature vector extraction model to obtain the weld shape feature vector of the X-ray weld image to be identified. Subsequently, the weld image similarity is determined based on the weld shape feature vector.

[0069] In some embodiments, significant shape feature extraction may be performed on the X-ray weld image to extract a portion of the X-ray weld image having significant shape features from the X-ray weld image. Subsequently, the identifiability of the X-ray weld image is determined based on the extracted portion of the X-ray weld image.

[0070] In some embodiments, a global feature comparison can be performed on the X-ray weld image to determine the image similarity with the identified X-ray weld image. In some embodiments, a local feature comparison can also be performed on the X-ray weld image to determine the image similarity with the identified X-ray weld image, for example, the image similarity is determined based on a weld image cutout segment cutout at a given angle.

[0071] In some embodiments, the X-ray weld image library may store the identified X-ray weld images and the 360-degree complete weld digital twin image chain formed by stitching the various weld images. In this case, the X-ray weld image and the identified X-ray weld images in the identified X-ray weld image library and the 360-degree complete weld digital twin image chain formed by stitching the various weld images may be provided to the weld image similarity determination model to determine whether the X-ray weld image has been identified or is part of a 360-degree complete weld.

[0072] Back to Figure 6 After obtaining the identification determination result as above, at 620, it is determined whether the X-ray weld image at the pipeline weld has been identified according to the identification determination result of 610. In response to the X-ray weld image at the pipeline weld having been identified, at 630, feedback information is returned that the X-ray weld image at the pipeline weld has completed defect identification.

[0073] In response to the X-ray weld image at the pipeline weld not being recognized, at 640, image region analysis is performed on the X-ray weld image at the pipeline weld to obtain image region features of the X-ray weld image, wherein the obtained image region features include region composition, region position, region brightness, region density, and region shape. Subsequently, at 650, the image region features of the X-ray weld image are provided to a weld defect recognition model to perform weld defect recognition.

[0074] Optionally, after the weld defect is identified using the weld defect recognition model, a weld defect recognition report can be generated based on the weld defect recognition result. The generated weld defect recognition report can include the location information of the pipeline weld, whether there is a weld defect, and the weld defect category information. The weld defect recognition report can be notified to the user in the form of text, audio and / or video.

[0075] It should be noted that in other alternative embodiments, the process of determining whether the weld image is recognized or not shown in 610 may not be included.

[0076] By utilizing the above-mentioned weld defect recognition method, the efficiency and accuracy of weld defect recognition can be improved by using a weld defect recognition model to perform weld defect recognition based on image area features such as area position, area brightness, area density and area shape of the X-ray weld image.

[0077] By utilizing the above-mentioned weld defect recognition method, by identifying the identified weld image based on the uniqueness of the weld shape, it is possible to avoid repeated recognition of the identified weld image, thereby improving the efficiency of weld defect recognition, while preventing the occurrence of weld image falsification and improving the reliability of weld defect recognition.

[0078] By utilizing the above-mentioned weld defect recognition method, a training data set constructed by using actual X-ray weld images based on pipeline welds and enhanced X-ray weld images obtained by data enhancement of the actual X-ray weld images is used when training the weld image similarity determination model, so that when the X-ray weld image provided to the weld image similarity determination model is obtained by performing data enhancement processing such as image rotation, image translation, image scaling and filter-based image filtering on the identified X-ray weld image, the weld image similarity determination model can still be used to determine that it is similar to the identified X-ray weld image, thereby improving the weld image similarity determination model's ability to identify new X-ray weld images that are counterfeited by performing data enhancement processing on the identified X-ray weld images, avoiding repeated recognition of the identified weld images, and thereby improving the efficiency of weld defect recognition.

[0079] Figure 8 FIG. 8 is a block diagram showing an example of a weld defect identification device 800 according to an embodiment of the present specification. Figure 8 As shown, the weld defect identification device 800 includes a weld image recognition or non-recognition determination unit 810, an image area analysis unit 820 and a weld defect identification unit 830.

[0080] The weld image recognition determination unit 810 is configured to determine whether the X-ray weld image at the pipe weld has been recognized based on the weld shape parameters and the recognized X-ray weld image library, wherein the weld shape parameters include the weld overlay pitch and the weld arc. The operation of the weld image recognition determination unit 810 can refer to the above reference Figure 6 610 and Figure 7 Describes the operation.

[0081] The image region analysis unit 820 is configured to perform image region analysis on the X-ray weld image at the pipe weld to obtain image region features of the X-ray weld image. The obtained image region features include region position, region brightness, region density and region shape. The operation of the image region analysis unit 820 can refer to the above reference Figure 6 The operation of 640 is described.

[0082] The weld defect recognition unit 830 is configured to provide the image region features of the X-ray weld image to the weld defect recognition model to perform weld defect recognition. The operation of the weld defect recognition unit 830 can refer to the above reference Figure 6 The operation of 650 is described.

[0083] It should be noted that in other alternative embodiments, the weld defect identification device 800 may also not include the weld image recognition determination unit 810.

[0084] As above Figures 1 to 8 The weld defect recognition method and weld defect recognition device according to the embodiments of the present specification are described. The weld defect recognition device can be implemented by hardware, software or a combination of hardware and software.

[0085] Fig. 9 FIG. 1 shows an example schematic diagram of a weld defect identification device 900 implemented based on a computer system according to an embodiment of the present specification. Fig. 9 As shown, the weld defect identification device 900 may include at least one processor 910, a memory (e.g., a non-volatile memory) 920, a memory 930, and a communication interface 940, and the at least one processor 910, the memory 920, the memory 930, and the communication interface 940 are connected together via a bus 960. At least one processor 910 executes at least one computer-readable instruction stored or encoded in the memory (i.e., the above-mentioned element implemented in the form of software).

[0086] In one embodiment, computer executable instructions are stored in a memory, which when executed cause at least one processor 910 to: perform image region analysis on an X-ray weld image at a pipeline weld to obtain image region features of the X-ray weld image, wherein the obtained image region features include region position, region brightness, region density, and region shape; and provide the image region features of the X-ray weld image to a weld defect recognition model to perform weld defect recognition.

[0087] It should be understood that the computer executable instructions stored in the memory, when executed, cause at least one processor 910 to perform the above combined operations in various embodiments of the present specification. Figure 1-Figure 8 Describes the various operations and functions.

[0088] According to one embodiment, a program product such as a machine-readable medium (e.g., a non-transitory machine-readable medium) is provided. The machine-readable medium may have instructions (i.e., the above-mentioned elements implemented in the form of software), which, when executed by a machine, causes the machine to perform the above-mentioned combination of various embodiments of this specification. Figure 1-Figure 8 Specifically, a system or device equipped with a readable storage medium may be provided, on which a software program code implementing the functions of any of the above-mentioned embodiments is stored, and a computer or processor of the system or device reads and executes the instructions stored in the readable storage medium.

[0089] In this case, the program code itself read from the machine-readable medium can realize the function of any one of the above-mentioned embodiments, and thus the machine-readable code and the machine-readable storage medium storing the machine-readable code constitute a part of the present invention.

[0090] Examples of readable storage media include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD-RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer or a cloud via a communication network.

[0091] According to one embodiment, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the processor performs the above combination of the various embodiments of this specification. Figure 1-Figure 8 Describes the various operations and functions.

[0092] Those skilled in the art should understand that the various embodiments disclosed above can be modified and altered in various ways without departing from the essence of the invention. Therefore, the protection scope of the present invention should be defined by the appended claims.

[0093] It should be noted that not all steps and units in the above-mentioned processes and system structure diagrams are necessary, and some steps or units can be ignored according to actual needs. The execution order of each step is not fixed and can be determined as needed. The device structure described in the above-mentioned embodiments can be a physical structure or a logical structure, that is, some units may be implemented by the same physical entity, or some units may be implemented by multiple physical entities, or some components in multiple independent devices may be implemented together.

[0094] In the above embodiments, the hardware unit or module can be realized by mechanical or electrical means. For example, a hardware unit, module or processor can include permanent dedicated circuit or logic (such as special processor, FPGA or ASIC) to complete the corresponding operation. The hardware unit or processor can also include programmable logic or circuit (such as general-purpose processor or other programmable processor), which can be temporarily set by software to complete the corresponding operation. Specific implementation (mechanical method or dedicated permanent circuit or temporary circuit) can be determined based on cost and time consideration.

[0095] The specific embodiments described above in conjunction with the accompanying drawings describe exemplary embodiments, but do not represent all embodiments that can be implemented or fall within the scope of protection of the claims. The term "exemplary" used throughout this specification means "used as an example, instance or illustration" and does not mean "preferred" or "having advantages" over other embodiments. For the purpose of providing an understanding of the described technology, the specific embodiments include specific details. However, these technologies can be implemented without these specific details. In some instances, in order to avoid making the concepts of the described embodiments difficult to understand, well-known structures and devices are shown in block diagram form.

[0096] The above description of the present disclosure is provided to enable any person of ordinary skill in the art to implement or use the present disclosure. Various modifications to the present disclosure will be apparent to those of ordinary skill in the art, and the general principles defined herein may be applied to other variations without departing from the scope of protection of the present disclosure. Therefore, the present disclosure is not limited to the examples and designs described herein, but is consistent with the widest range of principles and novel features disclosed herein.

Claims

1. A weld defect recognition method based on X-ray weld images, include: Performing image region analysis on the X-ray weld image at the pipeline weld to obtain image region features of the X-ray weld image, wherein the image region features include region position, region brightness, region density, and region shape; and The image area features of the X-ray weld image are provided to a weld defect recognition model to perform weld defect recognition.

2. The weld defect identification method according to claim 1, in, Providing the image region features of the X-ray weld image to a weld defect recognition model to perform weld defect recognition includes: Providing the image region features of the X-ray weld image to the defect feature generation layer of the weld defect recognition model to generate a defect feature representation of the X-ray weld image; and The defect feature representation of the X-ray weld image is provided to the defect classification layer of the weld defect recognition model to perform weld defect recognition.

3. The weld defect identification method according to claim 1, in, The X-ray weld image includes a 360-degree weld chain image formed by splicing a plurality of scanned film images at different angles at the pipeline weld.

4. The weld defect identification method according to claim 1, in, The training data set of the weld defect recognition model includes a training data set constructed based on an actual X-ray weld image at a pipeline weld and an enhanced X-ray weld image obtained by performing data enhancement on the actual X-ray weld image, wherein the data enhancement includes at least one of image rotation, image translation, image scaling, and filter-based image filtering.

5. The weld defect identification method according to claim 1, in, Before performing image region analysis on the X-ray weld image at the pipeline weld, the weld defect identification method further includes: Based on the weld shape parameters, determining whether the X-ray weld image at the pipeline weld has been identified according to the identified X-ray weld image library, wherein the weld shape parameters include weld overlay pitch and weld arc, In response to the X-ray weld image not being recognized, image region analysis is performed on the X-ray weld image at the pipeline weld.

6. The weld defect identification method according to claim 5, in, Based on the weld shape parameters, determining whether the X-ray weld image at the pipeline weld has been identified according to the identified X-ray weld image library includes: Acquiring weld shape parameters of the X-ray weld image; and Based on the acquired weld shape parameters, it is determined whether the X-ray weld image has been recognized according to a library of recognized X-ray weld images.

7. The weld defect identification method according to claim 5, in, Based on the weld shape parameters, determining whether the X-ray weld image at the pipeline weld has been identified according to the identified X-ray weld image library includes: The X-ray weld image and the identified X-ray weld images in the identified X-ray weld image library are provided to a weld image similarity determination model to determine whether the X-ray weld image has been identified, and the weld image similarity determination model is pre-trained using the weld shape parameters as model features.

8. The weld defect identification method according to claim 7, in, The training data set of the weld image similarity determination model includes a training data set constructed based on an actual X-ray weld image at a pipeline weld and an enhanced X-ray weld image obtained by performing data enhancement on the actual X-ray weld image, wherein the data enhancement includes at least one of image rotation, image translation, image scaling, and filter-based image filtering.

9. The weld defect identification method according to claim 1, further comprising: include: Based on the weld defect identification results, a weld defect identification report is generated.

10. A weld defect recognition device based on X-ray weld images, include: An image region analysis unit is configured to perform image region analysis on the X-ray weld image at the pipeline weld to obtain image region features of the X-ray weld image, wherein the image region features include region position, region brightness, region density and region shape; as well as The weld defect recognition unit is configured to provide the image area features of the X-ray weld image to the weld defect recognition model to perform weld defect recognition.

11. The weld defect identification device according to claim 10, further comprising: include: The image recognition determination unit is configured to determine whether the X-ray weld image has been recognized based on weld shape parameters and a library of recognized X-ray weld images before performing image area analysis on the X-ray weld image, wherein the weld shape parameters include weld overlay pitch and weld curvature.

Images