Radiographic inspection isolation boundary safety monitoring method and device

Abstract

The present invention discloses a method and device for monitoring the safety of radiographic inspection isolation boundaries, which relates to the technical field of radiographic inspection. The method comprises: generating a distributed sensor node network based on a set of nodes deployed in a regional monitoring network, monitoring and acquiring information on changes in node radiation intensity to identify anomalies and obtain radiation intensity anomaly feature information; performing a radiation safety integrated assessment on the radiation intensity anomaly feature information of each sensor node based on a central controller to obtain a radiation safety assessment coefficient; and triggering a safety warning mechanism to issue a radiation safety warning for the radiographic inspection isolation boundary if the radiation safety assessment coefficient is lower than a preset safety threshold. This method achieves continuous and comprehensive monitoring of the radiographic inspection isolation boundary through a distributed sensor network, improves the monitoring response speed, and enables timely discovery and handling of safety hazards. The method is applicable to the safety requirements of various radiographic inspection scenarios, ensuring the safety of the radiographic inspection process.

Description

Technical Field

[0001] The present invention relates to the technical field of radiographic flaw detection, and in particular to a method and device for safety monitoring of radiographic flaw detection isolation boundaries. Background Art

[0002] Radiographic flaw detection technology, a key nondestructive testing method, leverages the penetrating and absorption properties of radiation to detect defects and foreign matter within materials. It is widely used in aerospace, nuclear power, petrochemical, and other fields. However, the radiation generated during radiographic flaw detection poses potential hazards to humans and the environment, necessitating strict control over the leakage and spread of radiation. However, existing methods for monitoring the safety of radiographic flaw detection isolation boundaries, which mostly rely on manual inspections and fixed monitoring points, suffer from slow response speeds and low monitoring accuracy, making them unable to meet the safety requirements of modern radiographic flaw detection technology. Summary of the Invention

[0003] This application solves the technical problems of the existing radiographic inspection isolation boundary safety monitoring method, which has slow response speed and low monitoring accuracy, and is difficult to meet the safety requirements of modern radiographic inspection technology, by providing a radiographic inspection isolation boundary safety monitoring method and device. It achieves continuous and comprehensive monitoring of radiographic inspection isolation boundaries through a distributed sensor network, improves the monitoring response speed, so as to timely discover and deal with safety hazards, and is applicable to the safety requirements of various radiographic inspection scenarios, ensuring the safety of the radiographic inspection process.

[0004] In view of the above problems, the present invention provides a method and device for monitoring the safety of an isolation boundary of a radiographic inspection system.

[0005] In a first aspect, the present application provides a method for safety monitoring of a radiographic flaw detection isolation boundary, the method comprising: S1: obtaining spatial distribution area information and flaw detection demand information of a radiographic flaw detection isolation boundary, performing a monitoring network deployment analysis on the spatial distribution area information and flaw detection demand information, and determining a set of regional monitoring network deployment nodes; S2: generating a distributed sensor node network based on the set of regional monitoring network deployment nodes, wherein each sensor node in the distributed sensor node network includes a radiation detector, a data processing unit, and a communication module; S3: obtaining node radiation intensity change information through monitoring by the radiation detector, performing anomaly identification on the node radiation intensity change information based on the data processing unit, obtaining radiation intensity anomaly feature information, and transmitting the radiation intensity anomaly feature information to a central controller through the communication module; S4: performing a radiation safety integrated assessment on the radiation intensity anomaly feature information of each sensor node based on the central controller to obtain a radiation safety assessment coefficient; if the radiation safety assessment coefficient is lower than a preset safety threshold, triggering a safety warning mechanism, and performing a radiation safety warning for the radiographic flaw detection isolation boundary based on the safety warning mechanism.

[0006] On the other hand, the present application also provides a device for monitoring the safety of a radiographic inspection isolation boundary, the device comprising: a monitoring network deployment analysis module for obtaining spatial distribution area information and inspection demand information of the radiographic inspection isolation boundary, performing a monitoring network deployment analysis on the spatial distribution area information and inspection demand information, and determining a set of regional monitoring network deployment nodes; a sensor node network generation module for generating a distributed sensor node network based on the set of regional monitoring network deployment nodes, wherein each sensor node in the distributed sensor node network includes a radiographic detector, a data processing unit, and a communication module; a radiation abnormality feature acquisition module for obtaining node radiation intensity change information through monitoring by the radiographic detector, performing abnormality identification on the node radiation intensity change information based on the data processing unit, obtaining radiation intensity abnormality feature information, and transmitting the radiation intensity abnormality feature information to a central controller through the communication module; and a radiation safety warning module for performing a radiation safety integrated assessment on the radiation intensity abnormality feature information of each sensor node based on the central controller to obtain a radiation safety assessment coefficient. If the radiation safety assessment coefficient is lower than a preset safety threshold, a safety warning mechanism is triggered, and a radiation safety warning is issued for the radiographic inspection isolation boundary based on the safety warning mechanism.

[0007] In a third aspect, the present application provides an electronic device comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program implements the steps of any one of the above methods when executed by the processor.

[0008] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps in any one of the above methods when executed by a processor.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] By analyzing the spatial distribution area information and inspection requirements of the radiographic inspection isolation boundary through monitoring network deployment, a set of regional monitoring network deployment nodes is determined to generate a distributed sensor node network. Each sensor node in the distributed sensor node network includes a radiation detector, a data processing unit, and a communication module. The radiation detector monitors and obtains radiation intensity change information at the node. The data processing unit identifies anomalies in the radiation intensity change information at the node, and obtains radiation intensity anomaly feature information, which is transmitted to a central controller via the communication module. A radiation safety integrated assessment is then performed on the radiation intensity anomaly feature information of each sensor node to obtain a radiation safety assessment coefficient. If the radiation safety assessment coefficient is lower than a preset safety threshold, a safety warning mechanism is triggered to issue a radiation safety warning for the radiographic inspection isolation boundary. This technical solution achieves continuous and comprehensive monitoring of the radiographic inspection isolation boundary through a distributed sensor network, improves monitoring response speed, facilitates timely detection and resolution of safety hazards, and is applicable to the safety requirements of various radiographic inspection scenarios, ensuring the safety of the radiographic inspection process.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A flow chart of the radiographic inspection isolation boundary safety monitoring method for this application;

[0013] Figure 2 A schematic diagram of a process for determining a set of nodes to be deployed in a regional monitoring network in the radiographic flaw detection isolation boundary security monitoring method of this application;

[0014] Figure 3 This is a schematic diagram of the structure of the radiographic inspection isolation boundary safety monitoring device for this application;

[0015] Figure 4 This is a schematic diagram of the structure of an exemplary electronic device of this application.

[0016] Explanation of the accompanying drawings: monitoring network deployment analysis module 11, sensor node network generation module 12, radiation anomaly feature acquisition module 13, radiation safety warning module 14, bus 1110, processor 1120, transceiver 1130, bus interface 1140, memory 1150, operating device 1151, application 1152 and user interface 1160. DETAILED DESCRIPTION

[0017] In the description of this application, those skilled in the art should know that this application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, this application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software. In addition, in some embodiments, this application can also be implemented in the form of a computer program product in one or more computer-readable storage media, wherein the computer-readable storage medium contains computer program code.

[0018] The computer-readable storage medium may be any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor devices, apparatuses or components, or any combination thereof. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memory, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination thereof. In this application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution device, apparatus, or component.

[0019] This application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0020] It should be understood that each block in the flowchart and / or block diagram, as well as combinations of blocks in the flowchart and / or block diagram, can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine. These computer-readable program instructions are executed by the computer or other programmable data processing device to produce a device that implements the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0021] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to operate in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product that implements the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0022] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process that implements the functions / operations specified by the blocks in the flowchart and / or block diagram.

[0023] The present application is described below in conjunction with the accompanying drawings.

[0024] Example 1

[0025] like Figure 1 As shown, the present application provides a method for monitoring the safety of an isolation boundary of a radiographic inspection, the method comprising:

[0026] Step S1: obtaining spatial distribution area information and detection requirement information of the radiographic detection isolation boundary, performing monitoring network deployment analysis on the spatial distribution area information and the detection requirement information, and determining a regional monitoring network deployment node set;

[0027] like Figure 2 As shown, further, the regional monitoring network deployment node set is determined in S1, and the steps of this application also include:

[0028] S11: performing monitoring feature analysis on the flaw detection requirement information to determine flaw detection monitoring requirement features, wherein the flaw detection monitoring requirement features include ray type features, ray intensity thresholds, and flaw detection accuracy requirements;

[0029] S12: Associating sensor parameters based on the ray type characteristics, ray intensity threshold, and flaw detection accuracy requirements to obtain flaw detection associated sensor requirement parameter information;

[0030] S13: performing boundary monitoring coverage analysis on the spatial distribution area information to obtain a boundary area coverage level, and determining boundary monitoring sensor deployment parameter information based on the boundary area coverage level;

[0031] S14: Deploy monitoring network nodes for the radiographic flaw detection isolation boundary based on the flaw detection associated sensor requirement parameter information and the boundary monitoring sensor deployment parameter information, and determine the regional monitoring network deployment node set.

[0032] Specifically, in order to achieve continuous and comprehensive monitoring of the radiographic flaw detection isolation boundary, the spatial distribution area information of the radiographic flaw detection isolation boundary, including spatial layout, obstacle distribution, etc., is first obtained through the radiographic flaw detection management system; the flaw detection demand information, that is, the demand target of radiographic flaw detection is clarified to help determine the monitoring sensor type and performance requirements. Furthermore, a monitoring network deployment analysis is performed on the spatial distribution area information and the flaw detection demand information. First, the flaw detection demand information is analyzed for boundary safety monitoring characteristics to determine the flaw detection monitoring demand characteristics. The flaw detection monitoring demand characteristics specifically include ray type characteristics, ray intensity thresholds, and flaw detection accuracy requirements. Sensor parameter association is performed based on the ray type characteristics, ray intensity thresholds, and flaw detection accuracy requirements to obtain flaw detection associated sensor demand parameter information. The flaw detection associated sensor demand parameter information matches the flaw detection monitoring demand characteristics, including sensor application parameters such as monitoring sensor type, sensor monitoring threshold, and sensor test accuracy, to ensure that sensor monitoring is applicable to radiographic flaw detection scenarios.

[0033] Then, a boundary monitoring coverage analysis is performed on the spatial distribution area information, that is, a comprehensive monitoring coverage analysis is performed according to the size of the spatial area layout to obtain the boundary area coverage level. The boundary area coverage level is the monitoring density level required to cover each boundary spatial area. Based on the boundary area coverage level, the boundary monitoring sensor deployment parameter information is determined. The boundary monitoring sensor deployment parameter information includes parameter information such as sensor deployment location and quantity, which matches the boundary area coverage level. The larger the coverage level, the higher the required monitoring density level, and the denser the corresponding deployment quantity and location, to ensure comprehensive monitoring coverage of the boundary area. Based on the flaw detection-related sensor requirement parameter information and the boundary monitoring sensor deployment parameter information, the monitoring network nodes of the radiographic flaw detection isolation boundary are evenly deployed to determine the regional monitoring network deployment node set. The regional monitoring network deployment node set is used to perform comprehensive real-time monitoring of the radiographic flaw detection isolation boundary. The accuracy of the deployment parameters of the radiographic flaw detection isolation boundary sensor monitoring is improved to ensure continuous and comprehensive monitoring of the boundary security.

[0034] Step S2: generating a distributed sensor node network based on the regional monitoring network deployment node set, wherein each sensor node in the distributed sensor node network includes a ray detector, a data processing unit and a communication module;

[0035] Specifically, a distributed sensor network is employed. Sensor nodes are deployed around the radiographic inspection isolation boundary according to the regional monitoring network deployment node set, generating a distributed sensor node network and forming a continuous sensor monitoring network. Each sensor node in the distributed sensor node network includes a radiographic detector, which can be a mobile, high-sensitivity radiographic detector to facilitate real-time inspections and focus on monitoring specific areas, ensuring effective monitoring of low-dose radiation and improving monitoring effectiveness. A data processing unit can be a low-power, high-performance microprocessor. A communication module can utilize wireless communication technology to achieve real-time communication with a central controller. The distributed sensor node network also enables simultaneous inspection tasks at multiple inspection sites, enabling monitoring of different inspection sites through node networking. This ensures comprehensive and real-time border security monitoring, thereby improving the efficiency of security monitoring data processing.

[0036] Step S3: monitoring and acquiring node ray intensity change information through the ray detector, performing abnormality identification on the node ray intensity change information based on the data processing unit to obtain ray intensity abnormality feature information, and transmitting the ray intensity abnormality feature information to the central controller through the communication module;

[0037] Furthermore, the step of obtaining the node ray intensity change information in S3 further includes:

[0038] S31: performing radiation level analysis on the sensor node area to obtain radiation level information of the node area, and dividing the sensor node area based on the radiation level information of the node area to obtain a set of node radiation division areas;

[0039] S32: Setting radiation level-monitoring frequency mapping rules according to radiation safety monitoring requirements;

[0040] S33: Map and match the node radiation division area sets in sequence based on the radiation level-monitoring frequency mapping rule to generate a node radiation area monitoring frequency set;

[0041] S34: Performing radiation graded monitoring on the sensor node area according to the monitoring frequency set of the node radiation area by the radiation detector to obtain the radiation intensity change information of the node.

[0042] Furthermore, in step S31, the node area radiation level information is obtained, and the steps of this application further include:

[0043] Based on the abnormal ray intensity characteristic information, the occurrence area and occurrence intensity of the sensor node area are counted to obtain the node radiation area frequency and the node radiation intensity frequency;

[0044] Performing radiation criticality analysis on the node radiation area frequency and the node radiation intensity frequency to obtain a node radiation criticality allocation factor;

[0045] The node radiation area frequency and the node radiation intensity frequency are weightedly fused based on the node radiation criticality allocation factor to determine the node area radiation level information.

[0046] Specifically, the radiation dose of each sensor node environment is monitored through the radiation detector. To ensure radiation monitoring accuracy, a radiation level analysis is performed on specific radiation areas within the sensor node area, achieving node area hierarchical monitoring. First, based on historical radiation monitoring data, namely the radiation intensity anomaly characteristic information, the radiation occurrence area and radiation occurrence intensity statistics of the sensor node area are calculated to obtain the node radiation area frequency and node radiation intensity frequency corresponding to each specific radiation area. Then, based on expert subjective experience, a radiation criticality analysis is performed on the node radiation area frequency and node radiation intensity frequency to obtain a node radiation criticality allocation factor. The node radiation criticality allocation factor is the weighted distribution information of the node radiation area frequency and node radiation intensity frequency. A greater criticality indicates a greater decision weight for the radiation factor. Based on the node radiation criticality allocation factor, the node radiation area frequency and node radiation intensity frequency are weighted and fused, and the weighted calculation result is determined as the node area radiation level information for each specific radiation area.

[0047] Based on the radiation level information of the node area, the sensor node area is divided, and the node area is divided and integrated according to the radiation level to obtain an integrated node radiation division area set. Then, according to the experience of radiation safety monitoring requirements, a radiation level-monitoring frequency mapping rule is set, and the radiation level-monitoring frequency mapping rule reflects the mapping relationship between the radiation level area and the corresponding monitoring frequency. Based on the radiation level-monitoring frequency mapping rule, the node radiation division area set is mapped and matched in turn to generate a node radiation area monitoring frequency set corresponding to each radiation level area. Through the radiation detector, according to the node radiation area monitoring frequency set, the sensor node area is subjected to radiation frequency graded monitoring to ensure that the node area with a larger radiation level is monitored in focus, and the corresponding node radiation intensity change information is obtained to indicate the radiation dose information of the sensor node.

[0048] The data processing unit identifies anomalies in the node's radiation intensity change information, sets a radiation intensity safety threshold based on the safety standards for radiographic inspection isolation boundaries, and rapidly compares and identifies intensity data exceeding the threshold for anomalies, obtaining radiation intensity anomaly signature information, including the intensity level and location of the anomaly. This anomaly signature information, obtained by each sensor node through monitoring and identification, is transmitted to a central controller via the communication module. The central controller then quickly and efficiently processes and analyzes the radiation data. This distributed network of sensor nodes enables radiation safety monitoring and identification of radiographic inspection isolation boundaries, improving the comprehensiveness of radiation monitoring and response speed, thereby ensuring efficient radiation anomaly identification.

[0049] Step S4: Based on the central controller, a radiation safety integrated assessment is performed on the abnormal radiation intensity characteristic information of each sensor node to obtain a radiation safety assessment coefficient. If the radiation safety assessment coefficient is lower than a preset safety threshold, a safety warning mechanism is triggered, and a radiation safety warning is performed on the radiation inspection isolation boundary based on the safety warning mechanism.

[0050] Furthermore, in the step S4, the radiation safety assessment coefficient is obtained, and the steps of this application further include:

[0051] S41: Acquire a radiographic flaw detection monitoring data set, perform anomaly labeling on the radiographic flaw detection monitoring data set, and obtain a radiographic anomaly feature label data set;

[0052] S42: Perform support vector machine classification training based on the radiation anomaly feature label dataset to construct a radiation anomaly recognition semi-model;

[0053] S43: performing label supervision training on the radiation anomaly feature label dataset based on a recurrent neural network structure to generate a radiation safety level semi-model;

[0054] S44: Merging and fusing the radiation anomaly identification half-model and the radiation safety level half-model to obtain a radiation safety assessment model for configuring the central controller, and obtaining the radiation safety assessment coefficient based on the output of the radiation safety assessment model.

[0055] Furthermore, the steps of constructing the data transmission reward function in this application also include:

[0056] Determine the radiation linkage warning mode according to the safety warning mechanism;

[0057] Using the difference between the radiation safety assessment coefficient and the baseline safety threshold coefficient as the radiation safety optimization coefficient;

[0058] Construct ray boundary security operation and maintenance space according to ray boundary security operation and maintenance strategy;

[0059] Based on the radiation safety optimization coefficient, a strategy matching analysis is performed in the radiation boundary safety operation and maintenance space, and boundary safety operation and maintenance strategy parameters are output. Then, safety warning operation and maintenance of the radiation flaw detection isolation boundary are performed through the radiation linkage warning method and the boundary safety operation and maintenance strategy parameters.

[0060] Furthermore, the application steps also include:

[0061] Verifying the evaluation effect of the radiation safety assessment model, extracting model parameters based on the verification results, and determining model weights and model biases;

[0062] Define a model loss function to perform gradient calculation on the model weights and model biases to obtain model parameter gradient calculation information;

[0063] The model parameters are iteratively updated and configured based on the model parameter gradient calculation information through the back propagation algorithm to obtain a radiation safety optimization assessment model.

[0064] Specifically, based on the central controller, a radiation safety integrated assessment is performed on the radiation intensity abnormality characteristic information of each sensor node. First, a radiographic flaw detection monitoring data set is acquired through big data technology. The radiographic flaw detection monitoring data set is the historical radiation monitoring data of the radiographic flaw detection isolation boundary. The abnormal data in the radiographic flaw detection monitoring data set is labeled according to the radiographic flaw detection isolation boundary safety standard, including whether it is an abnormal data label, a radiation abnormality level label, and a corresponding radiation safety level label, to obtain a labeled radiation abnormality feature label data set. Support vector machine classification training is performed based on the radiation abnormality feature label data set. The support vector machine is used to perform abnormal data classification training on the radiation abnormality feature label data set according to whether it is an abnormal data label until a preset classification accuracy rate is reached, thereby obtaining a radiation abnormality recognition semi-model. The radiation abnormality recognition semi-model is used to quickly identify radiation abnormality data.

[0065] Based on the recurrent neural network structure, the abnormal data in the radiation anomaly feature label data set is identified and supervised for training, and the radiation anomaly feature label data set is trained for safety level assessment according to the time series through the radiation safety level label until the model converges to generate the corresponding radiation safety level half-model, and the radiation safety level half-model is used to perform radiation safety level assessment on the radiation intensity anomaly feature. The radiation anomaly identification half-model and the radiation safety level half-model are merged and fused to obtain a radiation safety assessment model and configure the central controller. Based on the radiation safety assessment model, the radiation intensity anomaly feature information of each sensor node is subjected to radiation safety integrated identification and assessment, and the radiation safety level assessment result of each sensor node is output. The radiation safety level assessment results can be weighted averaged to obtain the calculated output result as the radiation safety assessment coefficient, thereby improving the efficiency of boundary safety assessment.

[0066] To ensure the accuracy of the radiation safety assessment model, the model is verified using a validation set to obtain the corresponding model assessment accuracy. If the validation result indicates that the model assessment accuracy does not meet the standard, model parameters are extracted based on the validation result. If the model needs to be optimized, the existing training model parameters are extracted and determined, including model weights, i.e., the weight values ​​connecting different layers in the neural network; and model biases, i.e., the bias values ​​of each neuron in the neural network. The model loss function is then defined, and the mean square error loss function can be preferably used to perform gradient calculations on the model weights and model biases. That is, the partial derivatives of each model parameter are calculated using the model loss function, and the model parameter gradient calculation information can be obtained through the chain rule.

[0067] The model parameters are then iteratively updated based on the model parameter gradient calculation information through the back-propagation algorithm. A model learning rate can be added to the update process to control the parameter update step size. The model parameter update steps are repeated to gradually optimize the model parameters. The value of the loss function is reduced by iteratively adjusting the model parameters to minimize the value of the loss function. The model optimization parameter information is then iteratively updated to obtain the model parameters. Based on the model optimization parameter information, the model parameters of the radiation safety assessment model are configured to obtain the optimized radiation safety optimization assessment model. This makes the model assessment results more accurate, improves the model accuracy and generalization ability, and thus improves the accuracy of the radiation safety assessment.

[0068] If the radiation safety assessment coefficient is lower than the preset safety threshold, it indicates that the radiation dose exceeds the preset safety value, triggering the safety warning mechanism, which is used to provide remote and timely warnings for radiation safety. According to the safety warning mechanism, the applicable radiation linkage warning method is determined. The radiation linkage warning method can be customized according to actual needs, such as setting different alarm levels and alarm methods to meet the safety needs in different scenarios, for example, by using sound and light alarms, SMS notifications, etc. to remind relevant personnel to handle the situation. The difference between the radiation safety assessment coefficient and the baseline safety threshold coefficient is then used as the radiation safety optimization coefficient, and the radiation safety optimization coefficient is the target radiation optimization degree. The radiation boundary safety operation and maintenance strategy is obtained through the radiation boundary safety operation and maintenance experience, and the radiation boundary safety operation and maintenance strategy is a set of boundary radiation emergency response processing methods.

[0069] According to the radiation boundary safety operation and maintenance strategy, a radiation boundary safety operation and maintenance space is constructed. The radiation boundary safety operation and maintenance space includes historical radiation safety optimization coefficients, safety operation and maintenance strategy parameters, and corresponding operation and maintenance effect data, which serve as the optimization range of the isolation boundary safety operation and maintenance strategy. Based on the radiation safety optimization coefficient, strategy matching is performed in the radiation boundary safety operation and maintenance space to obtain a set of matching safety operation and maintenance strategy parameters, and then a comparison and analysis of the operation and maintenance effects is performed on them, and the parameter with the best operation and maintenance effect is output as the boundary safety operation and maintenance strategy parameter. Safety warning operation and maintenance are performed on the radiation flaw detection isolation boundary through the radiation linkage warning method and the boundary safety operation and maintenance strategy parameters. The monitoring and operation response speed is improved so that safety hazards can be discovered and handled in a timely manner, thereby ensuring the safety of the radiation flaw detection process.

[0070] In summary, the radiographic inspection isolation boundary safety monitoring method provided in this application has the following technical effects:

[0071] By analyzing the spatial distribution area information and inspection requirements of the radiographic inspection isolation boundary through monitoring network deployment, a set of regional monitoring network deployment nodes is determined to generate a distributed sensor node network. Each sensor node in the distributed sensor node network includes a radiation detector, a data processing unit, and a communication module. The radiation detector monitors and obtains radiation intensity change information at the node. The data processing unit identifies anomalies in the radiation intensity change information at the node, and obtains radiation intensity anomaly feature information, which is transmitted to a central controller via the communication module. A radiation safety integrated assessment is then performed on the radiation intensity anomaly feature information of each sensor node to obtain a radiation safety assessment coefficient. If the radiation safety assessment coefficient is lower than a preset safety threshold, a safety warning mechanism is triggered to issue a radiation safety warning for the radiographic inspection isolation boundary. This technical solution achieves continuous and comprehensive monitoring of the radiographic inspection isolation boundary through a distributed sensor network, improves monitoring response speed, facilitates timely detection and resolution of safety hazards, and is applicable to the safety requirements of various radiographic inspection scenarios, ensuring the safety of the radiographic inspection process.

[0072] Example 2

[0073] Based on the same inventive concept as the radiographic flaw detection isolation boundary safety monitoring method in the aforementioned embodiment, the present invention also provides a radiographic flaw detection isolation boundary safety monitoring device, such as Figure 3 As shown, the device includes:

[0074] The monitoring network deployment analysis module 11 is used to obtain the spatial distribution area information of the radiographic inspection isolation boundary and the inspection demand information, perform monitoring network deployment analysis on the spatial distribution area information and the inspection demand information, and determine the regional monitoring network deployment node set;

[0075] A sensor node network generation module 12 is configured to generate a distributed sensor node network based on the set of nodes deployed in the regional monitoring network, wherein each sensor node in the distributed sensor node network includes a ray detector, a data processing unit, and a communication module;

[0076] a ray abnormality feature acquisition module 13, configured to acquire node ray intensity change information through monitoring by the ray detector, perform abnormality identification on the node ray intensity change information based on the data processing unit, obtain ray intensity abnormality feature information, and transmit the ray intensity abnormality feature information to the central controller through the communication module;

[0077] The radiation safety warning module 14 is used to perform a radiation safety integrated assessment on the abnormal radiation intensity characteristic information of each sensor node based on the central controller to obtain a radiation safety assessment coefficient. If the radiation safety assessment coefficient is lower than a preset safety threshold, a safety warning mechanism is triggered, and a radiation safety warning is issued for the radiation detection isolation boundary based on the safety warning mechanism.

[0078] Furthermore, the monitoring network deployment analysis module 11 is also used to:

[0079] Performing monitoring feature analysis on the flaw detection requirement information to determine flaw detection monitoring requirement features, wherein the flaw detection monitoring requirement features include ray type features, ray intensity thresholds, and flaw detection accuracy requirements;

[0080] Associating sensor parameters based on the ray type characteristics, ray intensity threshold, and flaw detection accuracy requirements to obtain flaw detection associated sensor requirement parameter information;

[0081] Performing boundary monitoring coverage analysis on the spatial distribution area information to obtain a boundary area coverage level, and determining boundary monitoring sensor deployment parameter information based on the boundary area coverage level;

[0082] Based on the detection-related sensor requirement parameter information and the boundary monitoring sensor deployment parameter information, monitoring network nodes are deployed on the radiation detection isolation boundary to determine the regional monitoring network deployment node set.

[0083] Furthermore, the radiation anomaly feature acquisition module 13 is further configured to:

[0084] Performing radiation level analysis on the sensor node area to obtain radiation level information of the node area, and dividing the sensor node area based on the radiation level information of the node area to obtain a set of node radiation division areas;

[0085] Set radiation level-monitoring frequency mapping rules according to radiation safety monitoring requirements;

[0086] Based on the radiation level-monitoring frequency mapping rule, the node radiation division area set is mapped and matched in sequence to generate a node radiation area monitoring frequency set;

[0087] The ray detector performs ray graded monitoring on the sensor node area according to the monitoring frequency set of the node radiation area to obtain the ray intensity change information of the node.

[0088] Furthermore, the radiation anomaly feature acquisition module 13 is further configured to:

[0089] Based on the abnormal ray intensity characteristic information, the occurrence area and occurrence intensity of the sensor node area are counted to obtain the node radiation area frequency and the node radiation intensity frequency;

[0090] Performing radiation criticality analysis on the node radiation area frequency and the node radiation intensity frequency to obtain a node radiation criticality allocation factor;

[0091] The node radiation area frequency and the node radiation intensity frequency are weightedly fused based on the node radiation criticality allocation factor to determine the node area radiation level information.

[0092] Furthermore, the radiation safety warning module 14 is also used to:

[0093] Acquiring a radiographic flaw detection monitoring data set, performing anomaly labeling on the radiographic flaw detection monitoring data set, and obtaining a radiographic anomaly feature label data set;

[0094] Perform support vector machine classification training based on the radiation anomaly feature label data set to build a radiation anomaly recognition semi-model;

[0095] Based on a recurrent neural network structure, the radiation anomaly feature label dataset is subjected to label supervision training to generate a radiation safety degree semi-model;

[0096] The radiation anomaly identification half-model and the radiation safety degree half-model are merged and fused to obtain a radiation safety assessment model for configuring the central controller, and the radiation safety assessment coefficient is obtained based on the output of the radiation safety assessment model.

[0097] Furthermore, the radiation safety warning module 14 is also used to:

[0098] Determine the radiation linkage warning mode according to the safety warning mechanism;

[0099] Using the difference between the radiation safety assessment coefficient and the baseline safety threshold coefficient as the radiation safety optimization coefficient;

[0100] Construct ray boundary security operation and maintenance space according to ray boundary security operation and maintenance strategy;

[0101] Based on the radiation safety optimization coefficient, a strategy matching analysis is performed in the radiation boundary safety operation and maintenance space, and boundary safety operation and maintenance strategy parameters are output. Then, safety warning operation and maintenance of the radiation flaw detection isolation boundary are performed through the radiation linkage warning method and the boundary safety operation and maintenance strategy parameters.

[0102] Furthermore, the radiation safety warning module 14 is also used to:

[0103] Verifying the evaluation effect of the radiation safety assessment model, extracting model parameters based on the verification results, and determining model weights and model biases;

[0104] Define a model loss function to perform gradient calculation on the model weights and model biases to obtain model parameter gradient calculation information;

[0105] The model parameters are iteratively updated and configured based on the model parameter gradient calculation information through the back propagation algorithm to obtain a radiation safety optimization assessment model.

[0106] The foregoing Figure 1 The various variations and specific examples of the radiographic flaw detection isolation boundary safety monitoring method in Example 1 are also applicable to the radiographic flaw detection isolation boundary safety monitoring device of this embodiment. Through the above detailed description of the radiographic flaw detection isolation boundary safety monitoring method, those skilled in the art can clearly understand the implementation method of the radiographic flaw detection isolation boundary safety monitoring device of this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0107] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and run on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, the various processes of the above-mentioned method embodiment for controlling output data are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0108] Exemplary electronic devices

[0109] For details, see Figure 4 As shown, the present application also provides an electronic device, which includes a bus 1110 , a processor 1120 , a transceiver 1130 , a bus interface 1140 , a memory 1150 and a user interface 1160 .

[0110] In the present application, the electronic device further includes: a computer program stored in the memory 1150 and executable on the processor 1120, and when the computer program is executed by the processor 1120, each process of the above-mentioned method embodiment for controlling output data is implemented.

[0111] The transceiver 1130 is configured to receive and send data under the control of the processor 1120 .

[0112] In the present application, a bus architecture (represented by bus 1110 ) may include any number of interconnected buses and bridges, and bus 1110 connects various circuits including one or more processors represented by processor 1120 and memory represented by memory 1150 .

[0113] Bus 1110 represents one or more of any of several types of bus structures, including a memory bus and memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. By way of example and not limitation, such architectures include an Industry Standard Architecture bus, a Micro Channel Architecture bus, an expansion bus, a Video Electronics Standards Association bus, and a Peripheral Component Interconnect bus.

[0114] The processor 1120 can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiment can be completed by an integrated logic circuit of the hardware in the processor or instructions in the form of software. The above-mentioned processors include: general-purpose processors, central processing units, network processors, digital signal processors, application-specific integrated circuits, field programmable gate arrays, complex programmable logic devices, programmable logic arrays, microcontrollers or other programmable logic devices, discrete gates, transistor logic devices, discrete hardware components. The various methods, steps and logic block diagrams disclosed in this application can be implemented or executed. For example, the processor can be a single-core processor or a multi-core processor, and the processor can be integrated into a single chip or located on multiple different chips.

[0115] Processor 1120 can be a microprocessor or any conventional processor. The method steps disclosed herein can be performed directly by a hardware decoding processor, or by a combination of hardware and software modules within the decoding processor. The software modules can be located in a readable storage medium known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, or registers. The readable storage medium is located in a memory, and the processor reads the information in the memory and, in conjunction with its hardware, performs the steps of the method described above.

[0116] The bus 1110 may also connect various other circuits, such as peripheral devices, voltage regulators, or power management circuits. The bus interface 1140 provides an interface between the bus 1110 and the transceiver 1130. These are all well known in the art and are therefore not further described in this application.

[0117] The transceiver 1130 can be a single component or multiple components, such as multiple receivers and transmitters, providing a means for communicating with various other devices over a transmission medium. For example, the transceiver 1130 receives external data from other devices and transmits data processed by the processor 1120 to other devices. Depending on the nature of the computer device, a user interface 1160 may also be provided, such as a touch screen, physical keyboard, display, mouse, speaker, microphone, trackball, joystick, or stylus.

[0118] It should be understood that in the present application, the memory 1150 may further include a memory remotely located relative to the processor 1120, and these remotely located memories may be connected to the server via a network. One or more portions of the aforementioned network may be an ad hoc network, an intranet, an extranet, a virtual private network, a local area network, a wireless local area network, a wide area network, a wireless wide area network, a metropolitan area network, the Internet, a public switched telephone network, a plain old telephone service network, a cellular telephone network, a wireless network, a wireless fidelity network, or a combination of two or more of the aforementioned networks. For example, the cellular telephone network and the wireless network may be a global mobile communications device, a code division multiple access device, a global interoperability for microwave access device, a general packet radio service device, a wideband code division multiple access device, a long term evolution device, an LTE frequency division duplex device, an LTE time division duplex device, an advanced long term evolution device, a universal mobile communications device, an enhanced mobile broadband device, a massive machine type communication device, an ultra-reliable low latency communication device, etc.

[0119] It should be understood that the memory 1150 in the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory includes: read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, or flash memory.

[0120] Volatile memory includes random access memory (RAM), which serves as an external cache memory. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate SDRAM, enhanced SDRAM, synchronous linked dynamic random access memory (SRAM), and direct memory bus (DMA) random access memory (DMA). Memory 1150 of the electronic device described herein includes, but is not limited to, the aforementioned and any other suitable types of memory.

[0121] In the present application, the memory 1150 stores the following elements of the operating device 1151 and the application 1152 : executable modules, data structures, or subsets thereof, or extended sets thereof.

[0122] Specifically, operating device 1151 includes various device programs, such as a framework layer, a core library layer, and a driver layer, for implementing various basic services and handling hardware-based tasks. Application programs 1152 include various applications, such as a media player and a browser, for implementing various application services. Programs implementing the methods of the present application may be included in application programs 1152. Application programs 1152 include applets, objects, components, logic, data structures, and other computer-executable instructions that perform specific tasks or implement specific abstract data types.

[0123] In addition, the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned method embodiment for controlling output data are implemented and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0124] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A radiographic inspection isolation boundary safety monitoring method, characterized in that: The method comprises: S1: obtaining spatial distribution area information of the radiographic inspection isolation boundary and inspection demand information, performing monitoring network deployment analysis on the spatial distribution area information and inspection demand information, and determining a regional monitoring network deployment node set; S2: generating a distributed sensor node network based on the regional monitoring network deployment node set, wherein each sensor node in the distributed sensor node network includes a ray detector, a data processing unit and a communication module; S3: Acquire node ray intensity change information through the ray detector, perform abnormality identification on the node ray intensity change information based on the data processing unit to obtain ray intensity abnormality feature information, and transmit the ray intensity abnormality feature information to the central controller through the communication module; S4: performing a radiation safety integrated assessment on the abnormal radiation intensity characteristic information of each sensor node based on the central controller to obtain a radiation safety assessment coefficient. If the radiation safety assessment coefficient is lower than a preset safety threshold, a safety warning mechanism is triggered, and a radiation safety warning is issued for the radiation detection isolation boundary based on the safety warning mechanism. Get node ray intensity change information, including: S31: performing radiation level analysis on the sensor node area to obtain radiation level information of the node area, and dividing the sensor node area based on the radiation level information of the node area to obtain a set of node radiation division areas; S32: Setting a radiation level-monitoring frequency mapping rule according to radiation safety monitoring requirements, wherein the mapping rule reflects a mapping relationship between radiation level areas and corresponding monitoring frequencies; S33: Map and match the node radiation division area sets in sequence based on the radiation level-monitoring frequency mapping rule to generate a node radiation area monitoring frequency set; S34: performing radiation graded monitoring of the sensor node area according to the monitoring frequency set of the node radiation area by the radiation detector to obtain the radiation intensity change information of the node; Obtain node area radiation level information, including: Based on the abnormal ray intensity characteristic information, the occurrence area and occurrence intensity of the sensor node area are counted to obtain the node radiation area frequency and the node radiation intensity frequency; Performing radiation criticality analysis on the node radiation area frequency and the node radiation intensity frequency to obtain a node radiation criticality allocation factor; The node radiation area frequency and the node radiation intensity frequency are weightedly fused based on the node radiation criticality allocation factor to determine the node area radiation level information. The node radiation criticality allocation factor is the weight allocation information of the node radiation area frequency and the node radiation intensity frequency.

2. The method according to claim 1, wherein The step S1 determines a set of nodes for deploying a regional monitoring network, including: S11: performing monitoring feature analysis on the flaw detection requirement information to determine flaw detection monitoring requirement features, wherein the flaw detection monitoring requirement features include ray type features, ray intensity thresholds, and flaw detection accuracy requirements; S12: Associating sensor parameters based on the ray type characteristics, ray intensity threshold, and flaw detection accuracy requirements to obtain flaw detection associated sensor requirement parameter information; S13: performing boundary monitoring coverage analysis on the spatial distribution area information to obtain a boundary area coverage level, and determining boundary monitoring sensor deployment parameter information based on the boundary area coverage level; S14: Deploy monitoring network nodes for the radiographic flaw detection isolation boundary based on the flaw detection associated sensor requirement parameter information and the boundary monitoring sensor deployment parameter information, and determine the regional monitoring network deployment node set.

3. The method according to claim 1, wherein The radiation safety assessment coefficient obtained in S4 includes: S41: Acquire a radiographic flaw detection monitoring data set, perform anomaly labeling on the radiographic flaw detection monitoring data set, and obtain a radiographic anomaly feature label data set; S42: performing support vector machine classification training based on the radiation anomaly feature label dataset, performing abnormal data classification training on the radiation anomaly feature label dataset by the support vector machine according to whether the dataset is an abnormal data label, until a preset classification accuracy is achieved, thereby obtaining a radiation anomaly recognition semi-model, wherein the radiation anomaly recognition semi-model is used to quickly identify radiation anomaly data; S43: performing identification supervision training on abnormal data in the radiation abnormality feature label dataset based on a recurrent neural network structure, and performing safety level assessment training on the radiation abnormality feature label dataset according to a time series using radiation safety level labels, until the model converges to generate a corresponding radiation safety level half-model, and the radiation safety level half-model is used to perform radiation safety level assessment on the radiation intensity abnormality features; S44: Merging and fusing the radiation anomaly identification half-model and the radiation safety level half-model to obtain a radiation safety assessment model for configuring the central controller, and obtaining the radiation safety assessment coefficient based on the output of the radiation safety assessment model.

4. The method according to claim 1, wherein The method comprises: Determine the radiation linkage warning mode according to the safety warning mechanism; Using the difference between the radiation safety assessment coefficient and the baseline safety threshold coefficient as the radiation safety optimization coefficient; Construct ray boundary security operation and maintenance space according to ray boundary security operation and maintenance strategy; Based on the radiation safety optimization coefficient, a strategy matching analysis is performed in the radiation boundary safety operation and maintenance space, and boundary safety operation and maintenance strategy parameters are output. Then, safety warning operation and maintenance of the radiation flaw detection isolation boundary are performed through the radiation linkage warning method and the boundary safety operation and maintenance strategy parameters.

5. The method according to claim 3, wherein The method comprises: Verifying the evaluation effect of the radiation safety assessment model, extracting model parameters based on the verification results, and determining model weights and model biases; Define a model loss function to perform gradient calculation on the model weights and model biases to obtain model parameter gradient calculation information; The model parameters are iteratively updated and configured based on the model parameter gradient calculation information through the back propagation algorithm to obtain a radiation safety optimization assessment model.

6. A radiographic inspection isolation boundary safety monitoring device, based on the method according to any one of claims 1 to 5, characterized in that: The device comprises: A monitoring network deployment analysis module is used to obtain spatial distribution area information of the radiographic inspection isolation boundary and inspection demand information, perform monitoring network deployment analysis on the spatial distribution area information and inspection demand information, and determine a regional monitoring network deployment node set; A sensor node network generation module, configured to generate a distributed sensor node network based on the set of nodes deployed in the regional monitoring network, wherein each sensor node in the distributed sensor node network includes a ray detector, a data processing unit, and a communication module; a ray abnormality feature acquisition module, configured to acquire node ray intensity change information through the ray detector, perform abnormality identification on the node ray intensity change information based on the data processing unit, obtain ray intensity abnormality feature information, and transmit the ray intensity abnormality feature information to the central controller through the communication module; The radiation safety warning module is used to perform a radiation safety integrated assessment on the abnormal radiation intensity characteristic information of each sensor node based on the central controller to obtain a radiation safety assessment coefficient. If the radiation safety assessment coefficient is lower than a preset safety threshold, a safety warning mechanism is triggered, and a radiation safety warning is issued for the radiation inspection isolation boundary based on the safety warning mechanism.

7. An electronic device comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps of the radiographic inspection isolation boundary safety monitoring method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the radiographic flaw detection isolation boundary safety monitoring method according to any one of claims 1 to 5 are implemented.

Images