Nuclear power plant spent fuel pool foreign matter falling detection method and system

Abstract

The invention relates to the technical field of nuclear power plant safety operation and maintenance, in particular to a nuclear power plant spent fuel pool foreign matter falling detection method and system. The method comprises the following steps: obtaining a detection result when the nuclear power plant spent fuel pool foreign matter falls off; sending out an alarm signal according to the detection result; based on the alarm signal, marking a foreign matter position in the detection image to obtain foreign matter position information; and according to the alarm signal and the foreign matter position information, foreign matter fishing operation is carried out. According to the invention, through high-precision dynamic monitoring and intelligent analysis, small foreign matter falling can be found in real time and accurate positioning can be realized, so that the safety and efficiency of pool monitoring can be greatly improved; by introducing an infrared thermal imaging technology, efficient monitoring can still be kept under different illumination conditions; and through a deep learning image recognition algorithm, the detection of the tiny foreign matters is more accurate, so that the safety guarantee level of the spent fuel pool of the nuclear power plant is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of safe operation and maintenance of nuclear power plants, and in particular to a method and system for detecting the falling of foreign objects into a spent fuel pool of a nuclear power plant. Background Art

[0002] The spent fuel pool is a key facility in a nuclear power plant for storing and cooling spent fuel assemblies, damaged fuel assemblies, and for underwater operations. Ensuring its safety is crucial to the normal operation of the nuclear power plant. Especially in the case of a complex and changeable pool environment, the falling of foreign objects can easily lead to unforeseen accidents, thus affecting the safety of the pool. Therefore, preventing foreign objects from falling into the spent fuel pool and promptly discovering their potential risks are the core links in ensuring the safety of spent fuel.

[0003] In the prior art, the detection of foreign objects is usually achieved by manual inspection or traditional video surveillance. Among them, the manual inspection method relies on the experience and real-time response of the staff, and is easily affected by environmental changes and human omissions; while the traditional video surveillance method is limited to static image analysis and cannot effectively cope with complex dynamic changes, especially in the detection of tiny foreign objects in the pool. The accuracy is low, resulting in hidden dangers that cannot be discovered in time. Both of the above methods cannot meet the high requirements of modern nuclear power plants for detection accuracy and real-time performance. Therefore, it is urgent to propose a method that can efficiently and accurately detect the fall of foreign objects in the spent fuel pool.

[0004] At present, there is not much research on the detection of foreign objects falling into spent fuel pools of nuclear power plants, and there is no specific method for detecting foreign objects falling into spent fuel pools of nuclear power plants. Summary of the invention

[0005] In view of the defects in the prior art, the present invention provides a method and system for detecting foreign objects falling into a spent fuel pool of a nuclear power plant.

[0006] In the first aspect, the present invention provides a method for detecting the falling of foreign objects in a spent fuel pool of a nuclear power plant, comprising the following steps: obtaining the detection result when a foreign object falls into the spent fuel pool of a nuclear power plant; issuing an alarm signal according to the detection result; marking the position of the foreign object in the detection image based on the alarm signal to obtain the position information of the foreign object; and performing the foreign object salvage operation through the alarm signal and the foreign object position information. The present invention monitors the dynamic changes of the spent fuel pool of a nuclear power plant in real time and accurately to ensure that once a foreign object falls into the pool, an alarm signal can be triggered immediately, effectively preventing the potential safety threats caused by foreign objects to the spent fuel pool; by marking the position of the foreign object in the image, the foreign object position information is accurately obtained, providing strong support for the subsequent foreign object salvage operation, greatly improving the salvage efficiency and accuracy; by combining the alarm signal and the foreign object position information, the safety risks that may be caused by the retention of foreign objects in the pool are avoided, and the normal operation of the spent fuel pool of the nuclear power plant is guaranteed.

[0007] Optionally, the detection result of foreign objects falling into the spent fuel pool of a nuclear power plant is obtained by: based on infrared thermal imaging technology, event camera and high-speed camera fusion technology, edge processing technology and cyclic visual transformation technology, the dynamic changes of the spent fuel pool of the nuclear power plant are captured in real time, and foreign objects are identified to obtain the detection result when the foreign objects fall. The present invention uses infrared thermal imaging technology to capture the temperature changes in the pool in real time, quickly respond to the thermal effects generated when foreign objects fall, and effectively improve the sensitivity of foreign object detection; through the fusion technology of event camera and high-speed camera, the dynamic changes of the pool are recorded at an ultra-high frame rate, and the moment of foreign objects falling is accurately captured to ensure the accuracy and reliability of the detection results; through edge processing technology and cyclic visual transformation technology, the characteristics of foreign objects in the pool are intelligently identified and extracted, and foreign objects and backgrounds are effectively distinguished, further improving the accuracy of foreign object detection.

[0008] Optionally, the sensitivity of the event camera is set to 1 cubic centimeter, the resolution of the image captured by the high-speed camera is not less than 1080P, the edge processing technology is used to pre-process the detection image, and the cyclic visual transformation technology identifies the location, size and type of foreign matter through a deep learning image recognition algorithm. The present invention uses a highly sensitive event camera to accurately capture the fall of tiny foreign objects in the pool to ensure that there are no omissions; a high-resolution high-speed camera is used to obtain a relatively clear image of the foreign object features, providing a solid foundation for subsequent image analysis; the detection image is pre-processed by edge processing technology, and combined with the deep learning image recognition algorithm in the cyclic visual transformation technology, the location, size and type of foreign matter are intelligently and accurately identified, which greatly improves the intelligence level and recognition accuracy of foreign object detection and provides strong support for the safety management of nuclear power plants.

[0009] Optionally, the temperature sensitivity of the infrared thermal imaging technology is 0.05°C. The present invention uses infrared thermal imaging technology with a temperature sensitivity of 0.05°C to keenly capture the tiny temperature changes caused when a foreign object falls into a pool, and can respond in time even if the foreign object is small in size or falls at a fast speed, effectively avoiding missed detection; the infrared thermal imaging technology is also conducive to intuitively analyzing the thermal interaction between the foreign object and the pool environment, providing a key basis for subsequent foreign object identification and salvage.

[0010] In a second aspect, the present invention provides a nuclear power plant spent fuel pool foreign body drop detection system, comprising an input device, a processor, an output device and a memory; the input device comprises a detection device, the detection device is installed above the spent fuel pool, and integrates event camera and high-speed camera fusion technology, edge processing technology and cyclic visual transformation technology; the processor comprises an image processing module and a control module, the image processing module is connected to the detection device, and is used to receive the image captured by the detection device and mark the foreign body position in the image; the control module is connected to the alarm module and the image processing module, and is used to receive the alarm signal and the alarm signal emitted by the detection device. The image processed by the image processing module, and control instructions are generated according to the processed image, and the control instructions include starting the foreign body salvage equipment, adjusting the position and operation direction of the salvage tool; the output device includes an alarm module, and the alarm module is connected to the detection device, which is used to receive the alarm signal issued by the detection device and issue an audible and visual alarm; the input device, the processor, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, the processor is configured to call the program instructions, and the system uses the method for detecting the fall of foreign objects in the spent fuel pool of a nuclear power plant. The detection system provided by the present invention realizes accurate and real-time detection of the fall of foreign objects in the spent fuel pool by integrating event camera and high-speed camera fusion technology, edge processing technology and cyclic visual transformation technology. First, the system quickly captures and marks the location of foreign objects, effectively improving the accuracy and efficiency of foreign object identification and reducing the cost and difficulty of manual monitoring. Secondly, the processor realizes image processing and the sound and light alarm of the alarm module, which can respond to the foreign object falling event immediately and ensure that the staff can take countermeasures quickly, thereby effectively preventing the impact of foreign objects on the spent fuel pool and the safe operation of the nuclear power plant. Finally, the system generates control instructions based on the image processing results, automatically starts the foreign object salvage equipment and adjusts the position and operation direction of the salvage tool, realizing the automation and intelligence of foreign object handling, and further improving the safety and operation efficiency of nuclear power plants.

[0011] Optionally, the image processing module is also used to output the specific size, shape and falling trajectory of the foreign object. The image processing module provided by the present invention provides important data support for subsequent foreign object processing by outputting the specific size of the foreign object; by identifying and outputting the shape characteristics of the foreign object, the nature and source of the foreign object are judged, which is conducive to a more intuitive understanding of the morphology of the foreign object, and then taking corresponding treatment measures; by tracking and outputting the falling trajectory of the foreign object, it is conducive to understanding the movement state of the foreign object in a specific time period, providing a strong basis for preventing the occurrence of safety accidents.

[0012] Optionally, the detection device has the function of 24-hour continuous monitoring and maintaining efficient monitoring under different lighting environments. The detection device provided by the present invention has the function of 24-hour continuous monitoring, ensuring that the monitoring area is always in a monitored state, effectively preventing the safety hazards caused by monitoring blind spots and time differences; the device can still maintain efficient monitoring under different lighting environments, whether it is strong light, weak light or no light environment, it can ensure the clarity and accuracy of the monitoring picture, greatly improving the reliability and practicality of monitoring.

[0013] Optionally, the detection device uses infrared thermal imaging technology to assist in detecting foreign objects. The detection device provided by the present invention has achieved the following effects by introducing infrared thermal imaging technology: first, it can penetrate obstructions such as smoke and dust and directly detect the thermal radiation of the object, thereby achieving effective detection of foreign objects that are hidden or difficult to directly observe, and improving the accuracy and comprehensiveness of detection; second, it is sensitive to changes in ambient temperature and can quickly capture the temperature difference between the foreign object and the surrounding environment, and even small temperature changes can be accurately captured, further enhancing the sensitivity of foreign object detection; third, it is independent of visible light and can still maintain efficient detection capabilities at night or under low light conditions, ensuring that all-weather foreign object detection needs are met, and providing strong technical support for safety monitoring and fault warning.

[0014] Optionally, the alarm module includes an audible and visual alarm device, which is used to emit an alarm signal of a buzzer and a flashing LED indicator after detecting a foreign object falling. The alarm module provided by the present invention integrates an audible and visual alarm device, which has the following effects: First, the emission of the buzzer can immediately attract the attention of the surrounding personnel, whether in a noisy environment or a quiet place, the alarm information can be quickly transmitted to ensure that the relevant personnel perceive the abnormal situation at the first time and take timely countermeasures; second, the flashing of the LED indicator provides an intuitive visual alarm signal, which can clearly indicate the location of the alarm source even in poor visibility or at night, which is convenient for quickly locating and handling foreign object falling events; third, the audible and visual dual alarm mechanism enhances the reliability and effectiveness of the alarm, reduces the risk of missed reports or false reports that may be caused by a single alarm method, and provides a solid guarantee for improving the overall safety monitoring level and emergency response capabilities.

[0015] Optionally, the functions of the control module also include: recording the data information of each salvage process and uploading the data information to a cloud database; automatically optimizing the salvage strategy based on the historical records of multiple salvage tasks. The control module provided by the present invention realizes the centralized storage and management of data by recording the data information of each salvage process and uploading it to a cloud database, which is convenient for subsequent data analysis and tracing, and provides strong support for the quality control and efficiency improvement of salvage operations; based on the historical records of multiple salvage tasks, the salvage strategy is automatically analyzed and optimized, and the salvage parameters are intelligently adjusted according to different scenarios and conditions, effectively improving the accuracy and efficiency of salvage operations.

[0016] Compared with the prior art, the beneficial effects of the present invention include: first, by integrating event camera and high-speed camera fusion technology, edge processing technology and cyclic visual transformation technology, the falling of tiny foreign objects in the spent fuel pool can be accurately identified and captured, especially foreign objects with a volume of only 1 cubic centimeter, and high-precision foreign object detection can be performed within a range of 5 meters, greatly improving the accuracy and efficiency of detection; second, by introducing infrared thermal imaging technology, efficient monitoring can still be maintained under different lighting conditions; third, the use of deep learning image recognition algorithm makes the detection of tiny foreign objects more accurate; fourth, an alarm signal can be quickly issued at the moment of detecting the falling of foreign objects, and the position, size and trajectory of foreign objects in the image can be accurately obtained, effectively avoiding the potential risks caused by foreign objects to the pool; fifth, the detection system has a simple structure, high integration, easy installation and debugging, and greatly reduces the operation and maintenance costs and the need for manual intervention; sixth, through real-time monitoring and instant alarm functions, potential safety hazards are automatically detected and responded to, avoiding safety accidents caused by human omissions or delayed responses. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of a method for detecting foreign matter falling into a spent fuel pool of a nuclear power plant according to an embodiment of the present invention; Figure 2 It is a distribution diagram of the detection device installed on the pole according to an embodiment of the present invention; Figure 3 A schematic diagram of the distribution of the detection device installed on the wall according to an embodiment of the present invention; Figure 4 The figure is a schematic diagram of the structure of a foreign object falling detection system for a spent fuel pool in a nuclear power plant according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described herein are only for illustration and are not intended to limit the present invention. In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is obvious to those of ordinary skill in the art that these specific details do not need to be adopted to implement the present invention. In other examples, in order to avoid confusing the present invention, known circuits, software or methods are not specifically described.

[0019] Throughout the specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment of the present invention. Therefore, the phrases "in one embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily all refer to the same embodiment or example. In addition, particular features, structures, or characteristics may be combined in one or more embodiments or examples in any suitable combination and / or subcombination. In addition, it should be understood by those of ordinary skill in the art that the figures provided herein are for illustrative purposes and that the figures are not necessarily drawn to scale.

[0020] See also Figure 1 The embodiment of the present invention provides a method for detecting foreign matter falling into a spent fuel pool in a nuclear power plant, the method comprising the following steps: S1. Obtain the detection results of foreign objects falling into the spent fuel pool of a nuclear power plant.

[0021] In one embodiment, a detection device is installed above a spent fuel pool in a nuclear power plant to capture dynamic changes in the pool and identify foreign objects falling therein, thereby obtaining detection results when foreign objects fall.

[0022] Specifically, the detection device is based on infrared thermal imaging technology, event camera and high-speed camera fusion technology, edge processing technology and cyclic visual transformation technology to capture the dynamic changes of the spent fuel pool of the nuclear power plant in real time and identify foreign objects. Among them, the event camera and high-speed camera fusion technology uses event cameras and high-speed cameras, and the cyclic visual transformation technology uses cyclic visual transformers (RVT, Recurrent Vision Transformers). The temperature sensitivity of infrared thermal imaging technology is 0.05℃, and it can still maintain efficient monitoring under different lighting conditions. The sensitivity of the event camera is set to 1 cubic centimeter, which can capture the dynamic changes of tiny objects in a very short time and has extremely high temporal resolution; the high-speed camera is used to provide high-resolution images, and its image resolution is not less than 1080P, ensuring that the position and size of foreign objects can be clearly presented during the rapid fall of foreign objects; edge processing technology is used to pre-process images, remove noise, enhance image quality, and improve the accuracy of subsequent deep learning models; the cyclic visual transformer analyzes the captured images through deep learning algorithms to identify the type, location and size of foreign objects, ensuring that tiny foreign objects can also be discovered and marked in time.

[0023] Furthermore, when a foreign object falls, the detection device can accurately capture the trajectory change of the foreign object, thereby obtaining the detection result when a foreign object falls. Due to the use of event cameras, the detection device can perform efficient monitoring under different lighting conditions, ensuring safe monitoring of the pool without blind spots for 24 hours.

[0024] It should be noted that the detection device can be installed in two ways: pole installation and wall installation. Figure 2 As shown, the wall is installed as Figure 3 As shown. Figure 2 and Figure 3 It can be seen that by installing the detection device in different installation methods, the dynamic changes of the pool can be captured in different areas.

[0025] S2. According to the detection result, an alarm signal is issued.

[0026] In one embodiment, based on the detection result obtained in step S1, an alarm signal is immediately issued.

[0027] The implementation effects of this embodiment are as follows: First, through high-precision dynamic monitoring technology and intelligent analysis, the moment of foreign object falling is quickly captured, and an alarm signal is immediately issued, effectively shortening the time interval from detection to response, so that relevant personnel can understand the abnormal situation at the first time and take corresponding measures to eliminate safety hazards, thereby ensuring the safe operation of the water pool; second, the issuance of the alarm signal improves the efficiency of emergency response, can quickly attract the attention of surrounding personnel, and guide them to quickly locate the specific location of the foreign object falling, which not only helps to reduce false alarms and missed alarms, but also enables relevant personnel to quickly arrive at the scene and carry out necessary salvage and processing work, thereby improving the efficiency of emergency response.

[0028] S3. Based on the warning signal, the position of the foreign object in the detected image is marked to obtain the foreign object position information.

[0029] In one embodiment, when an alarm signal is received, the detected image is immediately analyzed in depth, and the specific location of the foreign object in the image is accurately identified and marked through advanced image processing technology.

[0030] Furthermore, detailed foreign body location information is generated for subsequent processing and analysis.

[0031] The implementation effect of this embodiment is as follows: the triggering of the alarm signal means that the foreign object has been successfully detected and the abnormal event has been located in real time. Subsequently, through intelligent analysis and image processing technology, the precise location information of the foreign object can be quickly extracted from the detection image. This information not only provides intuitive visual guidance for relevant personnel, enabling them to quickly locate and handle foreign objects, but also greatly improves the efficiency and accuracy of salvage operations. At the same time, the recording of foreign object location information also provides valuable data support for subsequent data analysis and optimization of salvage strategies, which helps to further improve the safety monitoring level of spent fuel pools in nuclear power plants.

[0032] S4. Perform foreign object salvage operations based on the alarm signal and the foreign object location information.

[0033] In one embodiment, whether the foreign object constitutes a safety hazard is determined by using the alarm signal and the foreign object location information.

[0034] Furthermore, when there is a potential safety hazard, the operator is notified through sound and light alarms, remote notifications, etc. to take corresponding measures to perform foreign body salvage operations.

[0035] The implementation effect of this embodiment is as follows: the immediate triggering of the alarm signal ensures that relevant personnel can respond quickly, and the accurate provision of foreign body location information greatly shortens the time to locate foreign bodies, so that salvage operations can be carried out quickly and accurately. This not only effectively prevents the potential threat of foreign bodies to the safe operation of spent fuel pools in nuclear power plants, but also significantly improves the efficiency and safety of salvage operations. At the same time, the salvage operation based on the alarm signal and foreign body location information also realizes real-time recording and analysis of data, providing strong data support for subsequent safety monitoring and optimization of salvage strategies, and further enhancing the intelligence and automation level of the overall detection system.

[0036] See also Figure 4 , Figure 4 The present invention is a schematic diagram of the structure of a system for detecting foreign objects falling into a spent fuel pool in a nuclear power plant in an embodiment of the present invention. The system includes an input device, a processor, an output device and a memory, wherein the input device, the processor, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, the processor is configured to call the program instructions, and the system uses the method for detecting foreign objects falling into a spent fuel pool in a nuclear power plant.

[0037] In this embodiment, the input device includes a detection device, which is installed above the spent fuel pool to ensure that the dynamic range of the entire pool can be covered and the situation in the pool can be monitored in real time. The detection device includes an event camera and high-speed camera fusion module, an edge processing module and an RVT module, which are used to capture the falling of foreign objects in the pool in real time.

[0038] The event camera captures object changes in real time through high-speed sensors, with extremely high temporal resolution. For each frame, the event camera records the change time and the changed pixel position, and outputs an event stream. The event camera has a sampling interval of 0.1 milliseconds, which can capture the fall of at least 1 cubic centimeter of foreign objects.

[0039] For the calculation process, specifically, assume that the event flow is ,in is the position of the changed pixel, is the timestamp of when the event occurred.

[0040] Furthermore, for each frame of the image, the instantaneous speed of the object's motion is extracted according to the temporal characteristics of the event stream. The instantaneous speed satisfies the following expression: in, is the instantaneous speed, is the displacement of the foreign body, is the time interval.

[0041] The high-speed camera provides high-resolution images, ensuring that every detail in the pool is clearly displayed during the dynamic process. The image resolution is 1080P, and the continuous frame images captured by the camera can accurately capture the location and movement trajectory of foreign objects.

[0042] The edge processing module is responsible for preprocessing operations such as denoising and enhancing image contrast on the captured images. Its purpose is to reduce image noise through image filters, improve image quality, and ensure the detection accuracy of the subsequent deep learning model. It should be noted that the edge processing module dynamically adjusts the denoising algorithm according to image noise and environmental conditions to ensure the real-time and accuracy of image processing.

[0043] Specifically, a Gaussian blur filter is applied to the image, and the expression of the Gaussian module filter is as follows: in, is the Gaussian blur filter function, is the standard deviation of the Gaussian kernel, is the pixel coordinate.

[0044] The RVT module uses the temporal information in the image sequence and combines it with a deep learning algorithm to analyze the dynamic changes of the image and predict the trajectory, type and location of foreign objects. It models the spatial relationship and temporal changes in the image through the self-attention mechanism of the Transformer.

[0045] For the calculation process, specifically, the image data and the corresponding time series are input, and the attention weight of each frame of the image is calculated through the self-attention mechanism. The attention weight satisfies the following expression: in, Indicates The attention weight of the frame image, represents a time series, and Respectively represent and query vector, and Respectively represent and A key vector that captures the relationship between different locations in the image. , Indicates the image frame number.

[0046] Furthermore, all frames are weighted summed to obtain the final feature representation.

[0047] Furthermore, the processed images are subjected to deep learning analysis through the RVT module. The RVT module uses a convolutional neural network (CNN) to extract features from images and a recurrent neural network (RNN) to model image sequences and predict the trajectory of foreign objects.

[0048] Specifically, CNN is used to extract image features such as color, shape, and texture. The extracted features are obtained through a series of convolutional layers in the following form: in, Indicates the extracted image features, Indicates image features.

[0049] Furthermore, RNN is used to model the time series data and calculate the motion trajectory of the object, which satisfies the following expression: in, Represents the trajectory of an object. Indicates the extracted image features, Indicates The time series corresponding to the image features.

[0050] The output device comprises an alarm module, and the alarm module is connected to the detection device.

[0051] For the alarm module, specifically, when the system detects a foreign object falling, it compares the real-time detection image with the preset threshold in the alarm module to determine whether the foreign object poses a safety hazard. If there is a safety hazard, the operator is notified through sound and light alarms, remote notifications, etc. to take corresponding measures.

[0052] Regarding the comparison process, specifically, the expression for comparing the real-time detection image with the threshold value preset in the alarm module is as follows: in, Indicates the detection value, Indicates the preset threshold value, Indicates the alarm value, which has the following meanings: When the alarm value is 1, it means that the detection value is greater than or equal to the threshold, triggering an alarm; When the alarm value is 0, it means that the detection value is less than the threshold and no alarm is triggered.

[0053] The processor includes an image processing module and a control module; The image processing module is connected to the detection device, and is used to receive the image captured by the detection device and mark the position of the foreign body in the image.

[0054] The control module is connected to the alarm module and the image processing module, and is used for receiving the alarm signal and the foreign body position information in the image, and controlling the foreign body salvage work.

[0055] Specifically, when the alarm is triggered, the control module marks the location of the foreign object according to the image and generates a salvage instruction to control the movement trajectory of the salvage equipment. The control instruction includes the salvage angle and equipment startup information, which is calculated by the control module and sent to the operator.

[0056] Furthermore, after each salvage operation, the control module will automatically record the salvage details and upload them to the cloud database for subsequent analysis and optimization. The recorded details satisfy the following expression: in, A dataset representing a record, Indicates the salvage time. Indicates the location of foreign matter. Indicates the device status.

[0057] In summary, the present invention provides a method for detecting the fall of foreign objects in a spent fuel pool of a nuclear power plant. Through high-precision dynamic monitoring and intelligent analysis, the fall of tiny foreign objects can be detected in real time and accurately located, thereby greatly improving the safety and efficiency of pool monitoring. By introducing infrared thermal imaging technology, efficient monitoring can still be maintained under different lighting conditions. Through deep learning image recognition algorithms, the detection of tiny foreign objects is made more accurate, thereby significantly improving the safety level of spent fuel pools in nuclear power plants.

[0058] The invention provides a foreign body drop detection system for spent fuel pools in nuclear power plants, which has the following effects: 1. High-precision detection. By integrating event camera and high-speed camera technology, combined with the RVT module, it is possible to accurately identify and capture the fall of tiny foreign objects in the spent fuel pool, especially foreign objects with a volume of only 1 cubic centimeter. Compared with traditional visual monitoring and manual detection methods, the present invention can perform high-precision foreign object detection within a range of 5 meters, greatly improving the accuracy and efficiency of detection. The high temporal resolution of the event camera and the high-definition image of the high-speed camera, combined with the analytical capabilities of the deep learning algorithm, enable timely and accurate detection of tiny foreign objects even in complex dynamic environments.

[0059] 2. Timely warning and accurate marking. It can quickly send out an alarm signal when a foreign object is detected falling, and accurately mark the location, size and trajectory of the foreign object in the captured image, providing real-time guidance for on-site operators. The alarm module ensures that operators can receive the alarm and take corresponding countermeasures in the shortest time through sound and light alarms and remote network notifications. This function effectively avoids the potential risks caused by foreign objects to the water pool, especially for small foreign objects that are difficult to detect manually, which can effectively reduce safety hazards and ensure the safe operation of nuclear power plants.

[0060] 3. Simple structure, easy to install and maintain. The detection device has a simple structure, high integration, and is easy to install and debug. Compared with the traditional complex detection system, the system of the present invention is not only easy to install, but also has good scalability and is suitable for spent fuel pools of nuclear power plants of various sizes. The maintenance work is simple. The operator only needs to regularly check the operating status of the equipment and update the software to ensure the long-term stable operation of the system, which greatly reduces the operation and maintenance costs and the need for manual intervention.

[0061] 4. Efficient and safe operation and maintenance support. Through real-time monitoring and instant alarm functions, potential safety hazards are automatically detected and responded to, avoiding safety accidents that may be caused by human negligence or delayed response. During operation, through automation and intelligent management, the operation and maintenance efficiency of nuclear power plants is significantly improved, while reducing dependence on manual operations, thereby reducing the risk of human errors. By discovering and handling foreign object falling incidents in advance, the long-term safe and stable operation of the spent fuel pool is guaranteed, providing reliable safety protection for nuclear power plants.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A method for detecting foreign matter falling into a spent fuel pool in a nuclear power plant, characterized in that: The method comprises the following steps: Obtain detection results when foreign objects fall into spent fuel pools at nuclear power plants; issuing an alarm signal according to the detection result; Based on the warning signal, the position of the foreign object in the detected image is marked to obtain the foreign object position information; The foreign object salvaging operation is performed based on the alarm signal and the foreign object position information.

2. A method for detecting foreign matter falling into a spent fuel pool of a nuclear power plant according to claim 1, characterized in that: The detection result of obtaining the foreign matter falling into the spent fuel pool of the nuclear power plant includes: Based on infrared thermal imaging technology, event camera and high-speed camera fusion technology, edge processing technology and cyclic visual transformation technology, the dynamic changes of the spent fuel pool of the nuclear power plant can be captured in real time, foreign objects can be identified, and the detection results when the foreign objects fall can be obtained.

3. A method for detecting foreign matter falling into a spent fuel pool of a nuclear power plant according to claim 2, characterized in that: The sensitivity of the event camera is set to 1 cubic centimeter, the image resolution captured by the high-speed camera is not less than 1080P, the edge processing technology is used to pre-process the detection image, and the cyclic visual transformation technology identifies the position, size and type of foreign objects through a deep learning image recognition algorithm.

4. A method for detecting foreign matter falling into a spent fuel pool of a nuclear power plant according to claim 2, characterized in that: The temperature sensitivity of the infrared thermal imaging technology is 0.05°C.

5. A system for detecting foreign objects falling into a spent fuel pool in a nuclear power plant, the system using a method for detecting foreign objects falling into a spent fuel pool in a nuclear power plant according to any one of claims 1 to 4, characterized in that: The system includes an input device, a processor, an output device, and a memory; The input device includes a detection device, which is installed above the spent fuel pool and integrates event camera and high-speed camera fusion technology, edge processing technology and cyclic visual transformation technology; The processor includes an image processing module and a control module. The image processing module is connected to the detection device and is used to receive the image captured by the detection device and mark the position of the foreign body in the image. The control module is connected to the alarm module and the image processing module and is used to receive the alarm signal sent by the detection device and the image processed by the image processing module, and generate control instructions according to the processed image, and the control instructions include starting the foreign body salvage equipment, adjusting the position and operation direction of the salvage tool; The output device comprises an alarm module, which is connected to the detection device and is used to receive the alarm signal sent by the detection device and send out an audible and visual alarm; The input device, the processor, the output device and the memory are connected to each other, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions.

6. A nuclear power plant spent fuel pool foreign body drop detection system according to claim 5, characterized in that: The image processing module is also used to output the specific size, shape and falling trajectory of the foreign object.

7. A nuclear power plant spent fuel pool foreign body drop detection system according to claim 5, characterized in that: The detection device has the function of 24-hour continuous monitoring and maintaining efficient monitoring under different lighting environments.

8. A nuclear power plant spent fuel pool foreign body drop detection system according to claim 7, characterized in that: The detection device uses infrared thermal imaging technology to assist in detecting foreign matter.

9. A nuclear power plant spent fuel pool foreign body drop detection system according to claim 5, characterized in that: The alarm module includes an audible and visual alarm device, which is used to emit a buzzing sound and a flashing LED indicator light alarm signal after detecting a foreign object falling.

10. A nuclear power plant spent fuel pool foreign body drop detection system according to claim 5, characterized in that: The functions of the control module also include: Record the data information of each salvage process and upload the data information to the cloud database; Automatically optimize salvage strategies based on historical records of multiple salvage missions.

Images