Method, system and equipment for grading foreign matters on secondary side of steam generator and medium

Abstract

The invention provides a steam generator secondary side foreign matter grading method, system and device and a medium, and relates to the technical field of steam generator foreign matter management and evaluation.The method comprises the steps that an inspection video of a steam generator secondary side pipeline is obtained, and a foreign matter image is recognized from the inspection video; according to the foreign matter image, three-dimensional size data of the foreign matter and the found position of the foreign matter are generated, and whether the foreign matter causes pipeline abrasion or not is judged; according to the pipeline abrasion condition, the three-dimensional size data and / or the found position of the foreign matter, risk grade division is conducted on the foreign matter. Risk grades can be accurately divided, the evaluation time is remarkably shortened, and the nuclear power plant foreign matter management efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of foreign object management and assessment technology for steam generators, and in particular to a method, system, device and medium for classifying foreign objects on the secondary side of a steam generator. Background Technology

[0002] As a core piece of equipment in the nuclear island of a nuclear power plant, the steam generator plays a crucial role in the energy exchange between the primary and secondary loops. Its structural integrity and heat transfer performance directly impact the plant's safety and economic efficiency. Domestic and international operational experience shows that foreign matter accumulation on the secondary side of the steam generator has become a major defect type, and the frequent incidents in recent years highlight the urgency of foreign matter management. Foreign matter in the secondary flow field undergoes random vibrations due to turbulent excitation, leading to continuous friction and wear against the heat transfer tube walls. This process involves complex fluid-structure interaction effects and exhibits significant randomness. Traditional assessment methods require the construction of a three-dimensional fluid dynamics and fluid-structure interaction model based on specific assumptions. This process is complex, computationally resource-intensive, and time-consuming, making it difficult to meet the rapid decision-making needs of nuclear power plant overhaul windows. This results in delayed foreign matter handling, exacerbating the risk of heat transfer tube degradation and even rupture. Therefore, there is room for improvement in developing an efficient and reliable method for rapid classification and evaluation of foreign matter wear to guide timely on-site intervention. Summary of the Invention

[0003] This invention provides a method, system, device, and medium for classifying foreign matter on the secondary side of a steam generator, in order to solve the technical problem of the lack of an efficient and reliable method for rapid classification and evaluation of foreign matter wear in the prior art.

[0004] This invention provides a method for classifying foreign matter on the secondary side of a steam generator, comprising:

[0005] Obtain inspection video of the secondary side pipeline of the steam generator and identify foreign object images from the inspection video;

[0006] Based on the image of the foreign object, generate three-dimensional size data of the foreign object and the location where the foreign object was found, and determine whether the foreign object has caused pipe wear;

[0007] The risk level of the foreign object is classified based on the wear condition of the pipeline, the three-dimensional dimensional data, and / or the location where the foreign object is found.

[0008] In one embodiment of the present invention, the step of acquiring an inspection video of the secondary side piping of the steam generator and identifying foreign object images from the inspection video includes:

[0009] Acquire inspection video of the secondary side piping of the steam generator and split the inspection video into consecutive frame images;

[0010] Using a pre-trained object detection model, foreign object identification is performed on each frame of the split image, and after successful identification, the foreign object image is extracted from the corresponding frame image.

[0011] In one embodiment of the present invention, the steps of generating three-dimensional size data of the foreign object and the location where the foreign object was found based on the foreign object image, and determining whether the foreign object has caused pipe wear, include:

[0012] Based on multiple images of the foreign object, a minimum bounding cube of the foreign object is fitted and formed, and corresponding three-dimensional size data is generated according to the minimum bounding cube.

[0013] Based on the detection pipeline information corresponding to the inspection video where the foreign object image is located, the location where the foreign object was found is generated;

[0014] By using a pre-trained semantic segmentation model, the wear features of the pipeline in which the foreign object was found are identified in the frame images within a preset range before and after it, in order to determine whether the foreign object has caused pipeline wear.

[0015] In one embodiment of the present invention, the risk level of the foreign object is classified into Level 1, Level 2, and Level 3. The step of classifying the risk level of the foreign object based on the wear condition of the pipeline, the three-dimensional dimensional data, and / or the location where the foreign object was found includes:

[0016] When the foreign object has caused wear and tear on the pipeline, the risk level of the foreign object is identified as Level 1;

[0017] When the foreign object does not cause wear on the pipeline, the risk level of the foreign object is classified according to the three-dimensional dimensional data and / or the location where the foreign object was found.

[0018] In one embodiment of the present invention, the step of classifying the risk level of the foreign object based on the three-dimensional size data and / or the location where the foreign object was found includes:

[0019] The three-dimensional size data is compared with a preset foreign object classification size threshold, wherein the foreign object classification size threshold includes a first-level risk size and a second-level risk size.

[0020] When the three-dimensional dimension data is greater than or equal to the first-level risk dimension, the risk level of the foreign object is confirmed as first-level;

[0021] When the three-dimensional dimension data is greater than or equal to the secondary risk dimension and less than the primary risk dimension, the risk level of the foreign object is determined to be secondary.

[0022] When the three-dimensional size data is smaller than the secondary risk size, the risk level of the foreign object is determined to be level three.

[0023] In one embodiment of the present invention, the step of classifying the risk level of the foreign object based on the three-dimensional size data and / or the location where the foreign object was found includes:

[0024] Determine the lateral flow velocity in the secondary side pipeline corresponding to the location where the foreign object was discovered:

[0025] When the lateral flow velocity is greater than or equal to a preset first flow velocity threshold, the risk level of the foreign object is determined to be Level 1;

[0026] When the lateral flow velocity is greater than or equal to a preset second flow velocity threshold and less than the first flow velocity threshold, the risk level of the foreign object is determined to be level two.

[0027] When the lateral flow velocity is less than the second flow velocity threshold, the risk level of the foreign object is determined to be level three.

[0028] In one embodiment of the present invention, the step of classifying the risk level of the foreign object based on the three-dimensional size data and / or the location where the foreign object was found includes:

[0029] Obtain the dimensional and fluid parameters of the secondary side pipeline corresponding to the location where the foreign object was discovered;

[0030] Based on the dimensional parameters and fluid parameters of the secondary side pipeline and the three-dimensional dimensional parameters of the foreign object, a pipeline wear analysis model is established.

[0031] Finite element analysis was performed on the pipeline wear analysis model to generate the critical wear time. The critical wear time characterizes the time it takes for the wear degree of the secondary pipeline caused by the foreign object to reach the pipe blockage threshold.

[0032] The critical wear time is compared with the preset refueling cycle of the nuclear power plant, and the risk level of the foreign object is determined as level one, level two or level three based on the comparison results.

[0033] The present invention also provides a classification system for foreign matter on the secondary side of a steam generator, comprising:

[0034] The identification module is used to acquire inspection videos of the secondary side pipeline of the steam generator and identify foreign object images from the inspection videos;

[0035] The judgment module is used to generate three-dimensional size data of the foreign object and the location where the foreign object was found based on the foreign object image, and to determine whether the foreign object has caused pipe wear;

[0036] The classification module is used to classify the risk level of the foreign object based on the wear condition of the pipeline, the three-dimensional dimensional data, and / or the location where the foreign object was found.

[0037] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the method for classifying foreign matter on the secondary side of a steam generator as described in any of the preceding claims.

[0038] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method for classifying foreign matter on the secondary side of a steam generator as described in any of the preceding claims.

[0039] This invention offers the following advantages: Based on a comprehensive assessment of foreign object size, location, and wear condition, it can accurately classify risk levels, avoiding the time-consuming nature of traditional fluid dynamics analysis, significantly shortening assessment time, and improving the efficiency of foreign object management in nuclear power plants. Simultaneously, by quantifying critical wear time thresholds and defining risk areas, this invention reduces the risk of heat transfer tube wear leading to blockage, ensuring equipment integrity and the safe and economical operation of nuclear power plants. Attached Figure Description

[0040] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0041] In the attached diagram:

[0042] Figure 1 A schematic flowchart of a method for classifying foreign matter on the secondary side of a steam generator according to an embodiment of the present invention;

[0043] Figure 2 This is a block diagram of a classification system for foreign matter on the secondary side of a steam generator provided in one embodiment of the present invention;

[0044] Figure 3 This is a schematic diagram of the structure of an electronic device provided in one embodiment of the present invention. Detailed Implementation

[0045] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0046] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. The drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0047] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0048] This invention provides a method, system, device, and medium for classifying foreign objects on the secondary side of a steam generator. By constructing a standardized foreign object risk classification system and integrating key parameters and historical data, it enables real-time determination of risk levels, thereby guiding power plants to prioritize the handling of high-risk foreign objects, significantly shortening the assessment cycle, providing real-time technical support for operation and maintenance, and possessing greater engineering practical value. Detailed descriptions are provided below through specific embodiments.

[0049] Please see Figure 1 In one embodiment of the present invention, the method for classifying foreign matter on the secondary side of a steam generator may specifically include the following steps:

[0050] Step S100: Obtain an inspection video of the secondary side pipeline of the steam generator and identify foreign object images from the inspection video.

[0051] In one embodiment of the present invention, when performing step S100, specifically, the secondary side of the steam generator is a complex space composed of thousands of closely arranged heat transfer tubes. Typically, a video inspection is performed after chemical cleaning and hydraulic flushing of the secondary side. The tool used for performing the inspection is usually a high-definition camera mounted on a remotely operated vehicle (ROV) or a robotic arm. In this embodiment, step S100 may specifically include the following steps:

[0052] Step S110: Obtain the inspection video of the secondary side pipeline of the steam generator, and split the inspection video into continuous frame images.

[0053] In one embodiment of the present invention, when performing step S110, specifically, firstly, an inspection video of the secondary side piping of the steam generator is acquired using a high-definition camera. Then, the dynamic inspection video is converted into a series of static frame images with timestamps and camera pose information. Typically, a typical secondary side inspection may generate several hours of high-definition video; therefore, it can first be divided into multiple independent video segments according to the inspected piping, and then each video segment can be further divided to form a continuous frame image.

[0054] Step S120: Using a pre-trained target detection model, foreign object identification is performed on each frame of the split image, and after successful identification, the foreign object image is extracted from the corresponding frame image.

[0055] In one embodiment of the present invention, when executing step S120, specifically, after obtaining the frame image sequence, foreign object identification is performed using a target detection model. It is understood that the dataset formed by inspecting video segmentation is extremely large; therefore, the target detection model needs to meet both detection accuracy and extremely high detection speed. In this embodiment, the target detection model can adopt the YOLO (You Only Look Once) series of models. The YOLO series of models has excellent single-pass forward detection speed, suitable for quickly filtering massive amounts of frame images. The target detection model first rapidly and extensively filters out a few key frames from the massive data, and then leaves the computationally intensive task of precise analysis to these selected key frames. Through the above-mentioned hierarchical processing strategy, computational efficiency is greatly optimized while ensuring that no potential threats are missed.

[0056] In one embodiment of the present invention, a pre-trained target detection model is employed. Given that in a real nuclear power plant environment, the types, shapes, sizes, and locations of foreign objects vary greatly and occur with extremely low frequency, it is difficult to collect a large-scale and balanced real training dataset. The present invention constructs the required training set based on synthetic data generation technology. Specifically, a high-fidelity 3D virtual model of the secondary side tube bundle of the steam generator is first created. Then, a large number of training images are generated procedurally within this virtual model scene. These images include typical foreign objects such as bolts, wires, and welding slag, and their size, material, location, and orientation are randomized. Simultaneously, variations in underwater environment factors such as lighting, shadows, reflections, and water turbidity are simulated to ensure that the generated synthetic data covers various potential real-world operating conditions. By training on this highly diverse synthetic data, the target detection model can effectively overcome the problem of scarce real data, obtain strong generalization ability, and thus accurately identify foreign objects never seen in real-world scenarios.

[0057] In this embodiment, the trained object detection model analyzes each frame of the video one by one. Once a foreign object is identified, the model outputs a bounding box indicating its location. Subsequently, based on this bounding box, the foreign object image is extracted from the corresponding frame image, and relevant metadata such as timestamps and camera poses are obtained.

[0058] Step S200: Based on the foreign object image, generate the three-dimensional size data of the foreign object and the location where the foreign object was found, and determine whether the foreign object has caused pipe wear.

[0059] In one embodiment of the present invention, when performing step S200, specifically, the three-dimensional dimensions and precise location of the foreign object are extracted from the foreign object image, and it is determined whether it has caused physical damage to the surrounding environment. In this embodiment, step S200 may specifically include the following steps:

[0060] Step S210: Based on the images of the foreign object from multiple angles, fit and form the minimum circumscribed cube of the foreign object, and generate corresponding three-dimensional size data according to the minimum circumscribed cube.

[0061] In one embodiment of the present invention, when performing step S210, specifically, firstly, a set of clear images of the same foreign object is selected from the foreign object image sequence filtered in step S100. Based on the SfM (Structure from Motion) algorithm, feature points are detected and matched on this set of images. By analyzing the positional changes of these matching points in different images, the precise camera position and pose at the time of each photo is calculated in reverse, and a sparse three-dimensional point cloud composed of these feature points is generated. Next, based on the MVS (Multi-View Stereo) algorithm, pixel-level dense matching is performed according to the camera pose information, and triangulation is performed on each pixel between images to generate a high-precision three-dimensional point cloud model covering the surface of the foreign object. Finally, geometric analysis is performed on the generated three-dimensional point cloud, and a minimum bounding box that can completely enclose all point clouds is calculated and fitted. The length, width, and height dimensions of this cube are the three-dimensional size data of the foreign object.

[0062] Step S220: Generate the location where the foreign object was found based on the detection pipeline information corresponding to the inspection video where the foreign object image is located.

[0063] In one embodiment of the present invention, when performing step S220, specifically, during the foreign object inspection process, the detection device not only records video but also simultaneously records the specific pipe or area it is inspecting, i.e., the pipe information being inspected. This pipe information is associated with the video timestamp as metadata. For example, the log records that within a certain time period of the video, the camera is inspecting the pipe channel in row X and column Y. When the target detection model identifies a foreign object in a frame, it can use the timestamp of that frame to query and extract the corresponding pipe location information from the log. Based on this pipe location information, the location where the foreign object was found can be determined.

[0064] Step S230: Using a pre-trained semantic segmentation model, identify the wear features of the pipeline at the location where the foreign object was found and within a preset range before and after it, in order to determine whether the foreign object has caused pipeline wear.

[0065] In one embodiment of the present invention, when step S230 is executed, specifically, a pre-trained semantic segmentation model, such as a model based on the U-Net architecture, is used to identify wear features on a high-resolution image of the pipe at the location where the foreign object was found and the surface of the adjacent heat transfer pipe, and outputs a segmentation mask, where different colors represent different pixel categories. Finally, by checking whether there are areas marked as wear marks in the segmentation mask, and combining the analysis of multiple frames of images within a preset range before and after the location where the foreign object was found, it is determined whether the foreign object has caused pipe wear. This semantic segmentation model is specially trained and can identify specific pixel categories, such as normal pipe wall, corrosion spots, foreign object body, and wear marks (e.g., scratches, indentations, fretting wear areas, etc.).

[0066] Step S300: Based on the wear condition of the pipeline, the three-dimensional dimensional data, and / or the location where the foreign object was found, classify the risk level of the foreign object.

[0067] In one embodiment of the present invention, when step S300 is performed, the following steps may be included:

[0068] Step S310: When the foreign object has caused wear on the pipeline, the risk level of the foreign object is confirmed as Level 1.

[0069] In one embodiment of the present invention, when step S310 is executed, specifically, according to the judgment result of step S200, if the foreign object has caused actual and observable physical damage to the pipeline, then there is no need to further consider the size, location and other factors of the foreign object, and its risk level can be directly confirmed as level one.

[0070] Step S320: When the foreign object does not cause pipe wear, classify the risk level of the foreign object based on the three-dimensional size data and / or the location where the foreign object was found.

[0071] In one embodiment of the present invention, when step S320 is executed, specifically, when the foreign object does not cause visible wear, a rapid risk screening can be performed based on the key parameters of the foreign object, thereby quickly identifying high-risk objects.

[0072] In one embodiment of the present invention, risk classification can be performed on foreign objects based on their three-dimensional size data, which may specifically include the following steps:

[0073] Step S321: Compare the three-dimensional size data with a preset foreign object classification size threshold, wherein the foreign object classification size threshold includes a first-level risk size and a second-level risk size.

[0074] When the three-dimensional dimension data is greater than or equal to the first-level risk dimension, the risk level of the foreign object is confirmed as first-level;

[0075] When the three-dimensional dimension data is greater than or equal to the secondary risk dimension and less than the primary risk dimension, the risk level of the foreign object is determined to be secondary.

[0076] When the three-dimensional size data is smaller than the secondary risk size, the risk level of the foreign object is determined to be level three.

[0077] In one embodiment of the present invention, when step S321 is executed, specifically, the three-dimensional size data of the foreign object is compared with a preset foreign object classification size threshold. In this embodiment, the foreign object classification size threshold can be set based on the specific geometric parameters of the steam generator. For example, the foreign object classification size threshold may include a primary risk size and a secondary risk size. The primary risk size can be defined as a size larger than the minimum clearance of the pipeline. Any foreign object larger than this size has a very high probability of being stuck in the pipe, generating continuous, high-contact-force vibrations under the action of fluid, thereby leading to severe fretting wear. The secondary risk size can be set, for example, to 60% of the primary risk size. Although the foreign object corresponding to this size will not jam the pipeline, its size and mass are sufficient to cause non-negligible wear on the pipe wall during vibration.

[0078] In one embodiment of the present invention, risk classification can be performed based on the location where the foreign object is found and the flow field characteristics in the pipeline, which may specifically include the following steps:

[0079] Step S322: Determine the lateral flow velocity of the secondary side pipeline corresponding to the location where the foreign object was discovered.

[0080] When the lateral flow velocity is greater than or equal to a preset first flow velocity threshold, the risk level of the foreign object is determined to be Level 1;

[0081] When the lateral flow velocity is greater than or equal to a preset second flow velocity threshold and less than the first flow velocity threshold, the risk level of the foreign object is determined to be level two.

[0082] When the lateral flow velocity is less than the second flow velocity threshold, the risk level of the foreign object is determined to be level three.

[0083] In one embodiment of the present invention, when step S322 is executed, specifically, the lateral flow velocity at the location where the foreign object was found is queried from the thermal-hydraulic model database of the steam generator; that is, the flow velocity perpendicular to the tube bundle direction. This lateral flow velocity is then compared with a preset first flow velocity threshold and a second flow velocity threshold to classify the risk level. In a steam generator, lateral flow is the main driving force inducing tube bundle vibration and foreign object movement. The higher the lateral flow velocity, the greater the hydrodynamic force acting on the foreign object, which will cause the foreign object to vibrate at a higher frequency and with a larger amplitude, thereby significantly accelerating the wear rate between it and the tube wall. Therefore, a foreign object located in a high-velocity zone, even if small in size, has a much greater potential destructive force than the same foreign object located in a stagnant flow zone. In this embodiment, the first flow velocity threshold is set, for example, to 1.157 m / s, and the second flow velocity threshold is set, for example, to 0.583 m / s. When the lateral flow velocity is greater than or equal to the first flow velocity threshold, the risk level of the foreign object is confirmed as Level 1. When the lateral flow velocity is greater than or equal to the second velocity threshold and less than the first velocity threshold, the risk level of the foreign object is determined to be Level 2. When the lateral flow velocity is less than the second velocity threshold, the risk level of the foreign object is determined to be Level 3.

[0084] In one embodiment of the present invention, the risk classification of foreign objects can be predictively assessed based on finite element analysis (FEA), which may specifically include the following steps:

[0085] Step S323: Obtain the size data and fluid parameters of the secondary side pipeline corresponding to the location where the foreign object was found, and establish a pipeline wear analysis model based on the size data and fluid parameters of the secondary side pipeline and the three-dimensional size data of the foreign object.

[0086] In one embodiment of the present invention, when step S323 is executed, specifically, firstly, the size data and fluid parameters of the secondary side pipeline corresponding to the location where the foreign object was found, as well as the three-dimensional size data of the foreign object, are obtained, and based on the above data, a geometric model of the foreign object and the local tube bundle is constructed, namely, a pipeline wear analysis model.

[0087] Step S324: Perform finite element analysis on the pipeline wear analysis model to generate the critical wear time. The critical wear time characterizes the time it takes for the wear degree of the secondary pipeline caused by the foreign object to reach the pipe blockage threshold.

[0088] In one embodiment of the present invention, when executing step S324, specifically, pipe wear analysis is achieved by establishing a CFD-FEA coupled simulation framework. First, CFD (Computational Fluid Dynamics) simulation is performed. Based on the pipe wear analysis model of the foreign object and the tube bundle, and local fluid parameters, the transient fluid dynamics acting on the foreign object under specific operating conditions are calculated. Then, FEA (Finite Element Analysis) is conducted, applying the fluid dynamic load output by the CFD to the finite element model containing the foreign object and the heat transfer tube, simulating their vibration response, contact pressure, relative slip, and impact force.

[0089] Next, iterative calculations are performed based on Akard's wear law. Within a small time step, the instantaneous wear depth is calculated based on the normal pressure at the contact point and the slip distance, combined with the material hardness. After each time step, the surface geometry of the heat transfer tube is dynamically updated, and coupled calculations begin for the next time step, cyclically simulating the progressive wear process of the tube wall. The simulation continues until the cumulative wear depth reaches a preset tube blockage threshold; the total time elapsed at this point is the critical wear time. This time parameter quantifies the critical period for foreign objects to cause structural failure of the heat transfer tube, providing a direct basis for safety assessment.

[0090] Step S325: Compare the critical wear time with the preset nuclear power plant refueling cycle, and determine the risk level of the foreign object as Level 1, Level 2 or Level 3 based on the comparison result.

[0091] In one embodiment of the invention, when performing step S325, specifically, the refueling cycle of a nuclear power plant is the time interval between two planned outages for maintenance, typically 18 or 24 months, representing the window of opportunity for the next safe and planned maintenance of the steam generator. If the critical wear time is less than or equal to the refueling cycle, it means that the foreign object has a high probability of causing the heat transfer tubes to wear to the failure threshold before the next planned overhaul. Therefore, the foreign object will be identified as a Level 1 risk and must be removed as soon as possible. If the critical wear time is greater than the refueling cycle, it means that the foreign object is safe for the next operating cycle. Furthermore, the risk level can be further subdivided based on the length of time it exceeds the cycle. For example, a critical wear time between 1 and 3 refueling cycles can be defined as a Level 2 risk, requiring close monitoring and timely handling during future overhauls; if the critical wear time is much greater than several refueling cycles, it can be defined as a Level 3 risk, indicating that the likelihood of it posing a threat within the design life of the power plant is extremely low, and it can be safely retained.

[0092] Please see Figure 2The present invention also provides a classification system for foreign matter on the secondary side of a steam generator, which corresponds one-to-one with the classification methods in the above embodiments. This classification system for foreign matter on the secondary side of a steam generator may include an identification module 11, a judgment module 12, and a classification module 13. Detailed descriptions of each functional module are as follows.

[0093] The identification module 11 can be used to acquire inspection videos of the secondary side piping of the steam generator and identify foreign object images from the inspection videos. More specifically, the identification module 11 can acquire inspection videos of the secondary side piping of the steam generator and split the inspection videos into continuous frame images; using a pre-trained target detection model, it performs foreign object identification on each split frame image, and after successful identification, extracts the foreign object image from the corresponding frame image.

[0094] The judgment module 12 is used to generate the three-dimensional size data of the foreign object and the location where the foreign object was found based on the foreign object image, and to determine whether the foreign object has caused pipeline wear. Further, the judgment module 12 can be specifically used to fit a minimum bounding cube of the foreign object based on multiple foreign object images, and generate corresponding three-dimensional size data based on the minimum bounding cube; generate the location where the foreign object was found based on the detection pipeline information corresponding to the inspection video where the foreign object image is located; and use a pre-trained semantic segmentation model to identify the wear features of the pipeline at the location where the foreign object was found and within a preset range of frames before and after it, in order to determine whether the foreign object has caused pipeline wear.

[0095] The classification module 13 is used to classify the risk level of foreign objects based on the wear condition of the pipeline, three-dimensional dimensional data, and / or the location where the foreign object is found. Specifically, the classification module 13 can be used to classify the risk level of the foreign object as Level 1 when it has caused pipeline wear, and to classify the risk level of the foreign object based on three-dimensional dimensional data and / or the location where it is found when it has not caused pipeline wear.

[0096] Specific limitations regarding the classification system for foreign matter on the secondary side of the steam generator can be found in the limitations of the classification method above, and will not be repeated here. Each module in the aforementioned classification system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in hardware or independently of the processor in a computer device, or stored in software in the memory of a computer device, so that the processor can call and execute the corresponding operations of each module.

[0097] Embodiments of the present invention also provide an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by one or more processors, cause the electronic device to implement the classification method for secondary side foreign matter of a steam generator provided in the above embodiments.

[0098] Please see Figure 3 The electronic device 20 may include a memory 21, a processor 22 and a bus, and may also include a computer program, such as a grading program, stored in the memory 21 and run on the processor 22.

[0099] The memory 21 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 21 can be an internal storage unit of the electronic device 20, such as the portable hard drive of the electronic device 20. In other embodiments, the memory 21 can also be an external storage device of the electronic device 20, such as a plug-in portable hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc., equipped on the electronic device 20. Furthermore, the memory 21 can include both internal and external storage units of the electronic device 20. The memory 21 can be used not only to store application software and various types of data installed on the electronic device 20, such as hierarchical code, but also to temporarily store data that has been output or will be output.

[0100] In some embodiments, the processor 22 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits packaged with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 22 is the control unit of the electronic device 20, connecting various components of the electronic device 20 via various interfaces and lines. It executes programs or modules (such as hierarchical programs) stored in the memory 21 and calls data stored in the memory 21 to perform various functions and process data of the electronic device 20.

[0101] Processor 22 executes the operating system of electronic device 20 and various installed application programs. Processor 22 executes the application programs to implement the steps in the above-described method for classifying foreign matter on the secondary side of the steam generator.

[0102] For example, a computer program may be divided into one or more modules, one or more of which are stored in memory 21 and executed by processor 22 to complete this application. One or more modules may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in electronic device 20. For example, the computer program may be divided into an identification module 11, a judgment module 12, and a classification module 13.

[0103] The integrated unit implemented as a software functional module described above can be stored in a computer-readable storage medium, which can be non-volatile or volatile. The software functional module stored in the storage medium includes several instructions to cause a computer device (which may be a personal computer, computer equipment, or network device, etc.) or processor to perform some functions of the classification method for secondary-side foreign matter in the steam generator of the various embodiments of this application.

[0104] In summary, the classification method, system, equipment, and medium for foreign objects on the secondary side of a steam generator disclosed in this invention have the following beneficial effects: Based on a comprehensive judgment of the size, location, and wear state of the foreign object, this invention can accurately classify risk levels, avoiding the time-consuming nature of traditional fluid dynamics analysis, significantly shortening the assessment time, and improving the efficiency of foreign object management in nuclear power plants. Simultaneously, this invention can reduce the risk of pipe blockage caused by heat transfer tube wear by quantifying the critical wear time threshold and dividing risk areas, ensuring equipment integrity and the safe and economical operation of nuclear power plants. Therefore, this invention effectively overcomes the various shortcomings of existing technologies and has high industrial application value.

[0105] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A method for classifying foreign matter on the secondary side of a steam generator, characterized in that, include: Obtain inspection video of the secondary side pipeline of the steam generator and identify foreign object images from the inspection video; Based on the image of the foreign object, generate three-dimensional size data of the foreign object and the location where the foreign object was found, and determine whether the foreign object has caused pipe wear; The risk level of the foreign object is classified based on the wear condition of the pipeline, the three-dimensional dimensional data, and / or the location where the foreign object is found.

2. The method for classifying foreign matter on the secondary side of a steam generator according to claim 1, characterized in that, The step of acquiring inspection video of the secondary side piping of the steam generator and identifying foreign object images from the inspection video includes: Acquire inspection video of the secondary side piping of the steam generator and split the inspection video into consecutive frame images; Using a pre-trained object detection model, foreign object identification is performed on each frame of the split image, and after successful identification, the foreign object image is extracted from the corresponding frame image.

3. The method for classifying foreign matter on the secondary side of a steam generator according to claim 1, characterized in that, The steps of generating three-dimensional size data of the foreign object and the location where the foreign object was found based on the foreign object image, and determining whether the foreign object has caused pipe wear, include: Based on multiple images of the foreign object, a minimum bounding cube of the foreign object is fitted and formed, and corresponding three-dimensional size data is generated according to the minimum bounding cube. Based on the detection pipeline information corresponding to the inspection video where the foreign object image is located, the location where the foreign object was found is generated; By using a pre-trained semantic segmentation model, the wear features of the pipeline in which the foreign object was found are identified in the frame images within a preset range before and after it, in order to determine whether the foreign object has caused pipeline wear.

4. The method for classifying foreign matter on the secondary side of a steam generator according to claim 1, characterized in that, The risk level of the foreign object is classified into three levels: Level 1, Level 2, and Level 3. The step of classifying the risk level of the foreign object based on the wear condition of the pipeline, the three-dimensional dimensional data, and / or the location where the foreign object was found includes: When the foreign object has caused wear and tear on the pipeline, the risk level of the foreign object is identified as Level 1; When the foreign object does not cause wear on the pipeline, the risk level of the foreign object is classified according to the three-dimensional dimensional data and / or the location where the foreign object was found.

5. The method for classifying foreign matter on the secondary side of a steam generator according to claim 4, characterized in that, The step of classifying the risk level of the foreign object based on the three-dimensional size data and / or the location where the foreign object was found includes: The three-dimensional size data is compared with a preset foreign object classification size threshold, wherein the foreign object classification size threshold includes a first-level risk size and a second-level risk size. When the three-dimensional dimension data is greater than or equal to the first-level risk dimension, the risk level of the foreign object is confirmed as first-level; When the three-dimensional dimension data is greater than or equal to the secondary risk dimension and less than the primary risk dimension, the risk level of the foreign object is determined to be secondary. When the three-dimensional size data is smaller than the secondary risk size, the risk level of the foreign object is determined to be level three.

6. The method for classifying foreign matter on the secondary side of a steam generator according to claim 4, characterized in that, The step of classifying the risk level of the foreign object based on the three-dimensional size data and / or the location where the foreign object was found includes: Determine the lateral flow velocity in the secondary side pipeline corresponding to the location where the foreign object was discovered: When the lateral flow velocity is greater than or equal to a preset first flow velocity threshold, the risk level of the foreign object is determined to be Level 1; When the lateral flow velocity is greater than or equal to a preset second flow velocity threshold and less than the first flow velocity threshold, the risk level of the foreign object is determined to be level two. When the lateral flow velocity is less than the second flow velocity threshold, the risk level of the foreign object is determined to be level three.

7. The method for classifying foreign matter on the secondary side of a steam generator according to claim 4, characterized in that, The step of classifying the risk level of the foreign object based on the three-dimensional size data and / or the location where the foreign object was found includes: Obtain the dimensional and fluid parameters of the secondary side pipeline corresponding to the location where the foreign object was discovered; Based on the dimensional parameters and fluid parameters of the secondary side pipeline and the three-dimensional dimensional parameters of the foreign object, a pipeline wear analysis model is established. Finite element analysis was performed on the pipeline wear analysis model to generate the critical wear time. The critical wear time characterizes the time it takes for the wear degree of the secondary pipeline caused by the foreign object to reach the pipe blockage threshold. The critical wear time is compared with the preset refueling cycle of the nuclear power plant, and the risk level of the foreign object is determined as level one, level two or level three based on the comparison results.

8. A classification system for foreign matter on the secondary side of a steam generator, characterized in that, include: The identification module is used to acquire inspection videos of the secondary side pipeline of the steam generator and identify foreign object images from the inspection videos; The judgment module is used to generate three-dimensional size data of the foreign object and the location where the foreign object was found based on the foreign object image, and to determine whether the foreign object has caused pipe wear; The classification module is used to classify the risk level of the foreign object based on the wear condition of the pipeline, the three-dimensional dimensional data, and / or the location where the foreign object was found.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method for classifying foreign matter on the secondary side of a steam generator as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for classifying foreign matter on the secondary side of a steam generator as described in any one of claims 1 to 7.

Images