Regional radiation monitoring method, device and equipment based on distributed environmental radiation monitor and storage medium

Abstract

The invention discloses a regional radiation monitoring method, device and equipment based on distributed environmental radiation monitors and a storage medium, and the method comprises the steps: laying a plurality of distributed radiation monitors in a to-be-monitored region, and collecting the radiation data in real time; performing multi-stage filtering on the radiation data through wavelet transform and a Kalman filter to obtain filtered radiation data; performing data fusion and correction on the filtered radiation data to obtain corrected radiation data; performing prediction according to the corrected radiation data to obtain radiation intensity distribution data; the radiation prediction map is generated based on the radiation data and the radiation intensity distribution data so as to realize regional radiation monitoring, the accuracy and reliability of the radiation data are improved by optimizing the layout of the distributed radiation monitors, so that the radiation intensity distribution data are accurately predicted according to the radiation data, and then the dynamic radiation prediction map is generated. Regional radiation monitoring is realized, and the efficiency and precision of regional radiation monitoring can be effectively improved.

Description

Technical Field

[0001] The present application relates to the field of radiation monitoring technology, and in particular to a method, apparatus, device and storage medium for regional radiation monitoring based on a distributed environmental radiation monitor. Background Art

[0002] Radiation monitoring is crucial in many areas, including nuclear power plants, radioactive material storage, environmental protection, and public safety. Traditional radiation monitoring typically relies on a small number of fixed-location monitoring stations to obtain data. This approach has limitations, particularly when the monitoring area is large or the radiation sources are unevenly distributed. This makes it difficult to accurately reflect the radiation situation across the entire area, resulting in data gaps or inaccuracies. In short, traditional radiation monitoring methods often struggle to cope with complex and changing radiation environments. This is especially true when radiation sources are widely distributed and frequently changing. Traditional fixed-point monitoring methods are not only inefficient but also struggle to achieve comprehensive coverage of the entire monitoring area. Summary of the Invention

[0003] The main purpose of this application is to provide a regional radiation monitoring method, device, equipment and storage medium based on a distributed environmental radiation monitor, aiming to solve the technical problem that the traditional fixed-point monitoring method is not only inefficient but also difficult to achieve comprehensive coverage of the entire monitoring area.

[0004] To achieve the above objectives, the present application proposes a regional radiation monitoring method based on a distributed environmental radiation monitor, the regional radiation monitoring method based on a distributed environmental radiation monitor comprising: Deploy a plurality of distributed radiation monitors in the area to be monitored, and collect radiation data in real time through each of the distributed radiation monitors; Performing multi-stage filtering on the radiation data through wavelet transform and Kalman filter to obtain filtered radiation data; performing data fusion and correction on the filtered radiation data to obtain corrected radiation data; Performing radiation distribution prediction based on the corrected radiation data to obtain radiation intensity distribution data; A radiation prediction map is generated based on the radiation data and the radiation intensity distribution data to achieve regional radiation monitoring.

[0005] In one embodiment, the method of deploying a plurality of distributed radiation monitors in the area to be monitored and collecting radiation data in real time through each of the distributed radiation monitors includes: Initializing a population, wherein each individual in the population represents an initial radiation monitor deployment plan, and the initial radiation monitor deployment plan includes the location and quantity of each distributed radiation monitor; Calculating the fitness value of each individual according to a preset fitness function, wherein the fitness function is determined based on the coverage and overlap of the distributed radiation monitors and environmental factors of the area to be monitored, wherein the environmental factors of the area to be monitored include at least terrain factors, wind direction factors, and environmental shielding factors; Selecting the individual with the highest fitness value as the parent generation according to the fitness value, and generating offspring through genetic operations; generating a new population according to the parent generation and the offspring generation; Iteratively executing the steps of calculating the fitness value of each individual according to a preset fitness function, selecting the individual with the highest fitness value as the parent according to the fitness value, and generating offspring through genetic operations until a preset iteration termination condition is met to obtain a target population; Select the individual with the highest fitness value in the target population as the optimal layout plan; Distributed radiation monitors are deployed in the area to be monitored according to the optimal deployment plan, and radiation data is collected in real time through each of the distributed radiation monitors.

[0006] In one embodiment, the multi-stage filtering of the radiation data using wavelet transform and Kalman filter to obtain filtered radiation data includes: Performing wavelet transform on the radiation data to obtain radiation data components in different frequency bands; The radiation data components of each frequency band are filtered by a Kalman filter to obtain the filtered radiation data components of each frequency band; The radiation data components after filtering in each frequency band are reconstructed to obtain filtered radiation data.

[0007] In one embodiment, performing data fusion and correction on the filtered radiation data to obtain corrected radiation data includes: Performing spatiotemporal correlation analysis on the filtered radiation data collected by each distributed radiation monitor to obtain the spatiotemporal relationship between the filtered radiation data; Constructing a deep learning network, wherein the deep learning network includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer; Using the filtered radiation data collected by each distributed radiation monitor and the corresponding spatiotemporal relationship as input data of the input layer; Extracting features from the input data through the convolution layer, and performing dimensionality reduction processing on the extracted features through the pooling layer to obtain features after dimensionality reduction; Inputting the reduced-dimensional features into the fully connected layer for classification or regression processing, and outputting preliminary fused data through the output layer; Learning the preliminary fusion data through a long short-term memory network to predict the change trend of the radiation data; The preliminary fusion data is corrected according to the predicted change trend to obtain corrected radiation data.

[0008] In one embodiment, performing radiation distribution prediction based on the corrected radiation data to obtain radiation intensity distribution data includes: The corrected radiation data is simulated and analyzed by a radiation diffusion model based on CFD and wind simulation to obtain radiation diffusion trends and intensity distribution characteristics; Obtain historical and real-time weather data; Predicting radiation propagation using a radiation propagation prediction model based on the corrected radiation data, the historical meteorological data, and the real-time meteorological data to obtain radiation propagation trend and intensity distribution prediction results; Radiation intensity distribution data is obtained based on the radiation diffusion trend and intensity distribution characteristics and the radiation propagation trend and intensity distribution prediction results.

[0009] In one embodiment, the radiation diffusion model based on CFD and wind simulation is used to simulate and analyze the corrected radiation data to obtain radiation diffusion trends and intensity distribution characteristics, including: Obtain environmental data and wind data of the area to be monitored; Constructing a fluid dynamics model, and performing a radiation diffusion simulation based on the environmental data and the corrected radiation data using the fluid dynamics model to obtain a radiation diffusion trend; Simulating the influence of wind on the radiation diffusion process using a wind simulation algorithm based on the wind data to obtain wind influence simulation results, wherein the wind influence simulation results include the wind carrying of radiation materials, changes in diffusion direction, and changes in intensity distribution; The radiation intensity distribution characteristics under the influence of wind are obtained based on the radiation diffusion trend and wind influence simulation results.

[0010] In one embodiment, the radiation propagation prediction model is used to predict radiation propagation based on the corrected radiation data, the historical meteorological data, and the real-time meteorological data to obtain radiation propagation trend and intensity distribution prediction results, including: Constructing a radiation propagation prediction model, wherein the radiation propagation prediction model is constructed based on a support vector machine and a deep learning network; Extracting radiation propagation features based on the corrected radiation data, historical meteorological data, and real-time meteorological data using the radiation propagation prediction model to obtain extracted radiation propagation features; Inputting the extracted radiation propagation features into the support vector machine for classification processing to obtain a radiation propagation trend prediction result, wherein the radiation propagation trend prediction result includes a predicted propagation path, speed, and range of the radiation material; The radiation propagation trend prediction results and the real-time meteorological data are input into the deep learning network for deep learning processing to obtain radiation intensity distribution prediction results. The intensity distribution prediction results include the predicted radiation intensity distribution of different areas. The deep learning processing includes feature fusion, multi-layer perceptron processing and regression prediction.

[0011] In addition, to achieve the above-mentioned purpose, the present application also proposes a regional radiation monitoring device based on a distributed environmental radiation monitor, the regional radiation monitoring device based on a distributed environmental radiation monitor comprising: A collection module is used to deploy multiple distributed radiation monitors in the area to be monitored and collect radiation data in real time through each of the distributed radiation monitors; A filtering module, configured to perform multi-stage filtering on the radiation data through wavelet transform and Kalman filter to obtain filtered radiation data; A correction module, configured to perform data fusion and correction on the filtered radiation data to obtain corrected radiation data; A prediction module, configured to perform radiation distribution prediction based on the corrected radiation data to obtain radiation intensity distribution data; A generation module is used to generate a radiation prediction map based on the radiation data and the radiation intensity distribution data to achieve regional radiation monitoring.

[0012] In addition, to achieve the above-mentioned purpose, the present application also proposes a regional radiation monitoring device based on a distributed environmental radiation monitor, the device including: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the regional radiation monitoring method based on a distributed environmental radiation monitor as described above.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the regional radiation monitoring method based on the distributed environmental radiation monitor as described above are implemented.

[0014] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the regional radiation monitoring method based on distributed environmental radiation monitors as described above.

[0015] One or more technical solutions proposed in this application are to deploy multiple distributed radiation monitors in the area to be monitored, and collect radiation data in real time through each of the distributed radiation monitors; perform multi-stage filtering on the radiation data through wavelet transform and Kalman filter to obtain filtered radiation data; perform data fusion and correction on the filtered radiation data to obtain corrected radiation data; perform radiation distribution prediction based on the corrected radiation data to obtain radiation intensity distribution data; generate a radiation prediction map based on the radiation data and the radiation intensity distribution data to achieve regional radiation monitoring. In the above manner, by optimizing the deployment of distributed radiation monitors, the accuracy and reliability of radiation data are improved, thereby accurately predicting radiation intensity distribution data based on radiation data, and then generating a dynamic radiation prediction map to achieve regional radiation monitoring, which can effectively improve the efficiency and accuracy of regional radiation monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1 A flowchart of the first embodiment of the regional radiation monitoring method based on a distributed environmental radiation monitor is provided in this application; Figure 2 A schematic diagram of the structure of a detector provided in an embodiment of the regional radiation monitoring method based on a distributed environmental radiation monitor of the present application; Figure 3 A flow chart of the second embodiment of the regional radiation monitoring method based on a distributed environmental radiation monitor is provided for this application; Figure 4 This is a schematic diagram of the module structure of a regional radiation monitoring device based on a distributed environmental radiation monitor according to an embodiment of the present application; Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the regional radiation monitoring device based on the distributed environmental radiation monitor in the embodiment of the present application.

[0019] Description of Figure Numbers: First hollow aluminum cylinder 1, second hollow aluminum cylinder 2, end cover 3; Gluing 4, welding 5.

[0020] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0022] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of the embodiment of the present application is: deploy multiple distributed radiation monitors in the area to be monitored, and collect radiation data in real time through each of the distributed radiation monitors; perform multi-stage filtering on the radiation data through wavelet transform and Kalman filter to obtain filtered radiation data; perform data fusion and correction on the filtered radiation data to obtain corrected radiation data; perform radiation distribution prediction based on the corrected radiation data to obtain radiation intensity distribution data; generate a radiation prediction map based on the radiation data and the radiation intensity distribution data to realize regional radiation monitoring.

[0024] Traditional radiation monitoring methods often seem powerless when faced with complex and changing radiation environments, especially in scenarios where radiation sources are widely distributed and change frequently. Traditional fixed-point monitoring methods are not only inefficient but also difficult to achieve full coverage of the entire monitoring area.

[0025] This application provides a solution that improves the accuracy and reliability of radiation data by optimizing the layout of distributed radiation monitors, thereby accurately predicting radiation intensity distribution data based on radiation data, and then generating a dynamic radiation prediction map to achieve regional radiation monitoring, which can effectively improve the efficiency and accuracy of regional radiation monitoring.

[0026] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication, and program execution capabilities, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of implementing the aforementioned functions, or a regional radiation monitoring device based on a distributed environmental radiation monitor. This embodiment and the following embodiments will be described below using a regional radiation monitoring device based on a distributed environmental radiation monitor as an example.

[0027] Based on this, the embodiment of the present application provides a regional radiation monitoring method based on a distributed environmental radiation monitor, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the regional radiation monitoring method based on distributed environmental radiation monitors of the present application.

[0028] In this embodiment, the regional radiation monitoring method based on the distributed environmental radiation monitor includes steps S10 to S50: Step S10: deploying a plurality of distributed radiation monitors in the area to be monitored, and collecting radiation data in real time through each of the distributed radiation monitors.

[0029] It should be noted that the "surveillance area" refers to the specific geographic area where radiation monitoring is required. This range may vary depending on the application scenario, such as the vicinity of a nuclear power plant, near industrial radiation sources, or in an urban environment. When deploying distributed radiation monitors, it is necessary to comprehensively consider the size, shape, topography, location of potential radiation sources, and environmental factors of the monitored area to ensure that the monitors can fully and accurately cover the entire monitored area and collect reliable radiation data in real time.

[0030] Distributed radiation monitors (DRMs) are devices specifically designed to monitor radiation levels in an environment. These monitors are typically equipped with highly sensitive radiation sensors that can accurately capture weak radiation signals in the environment and convert them into digital data for analysis and processing. A DRM consists of three parts: a detector, an external enclosure, and a bracket. The detector is the core component of the monitor, responsible for collecting real-time radiation data. The external enclosure protects the detector from external interference and damage, while also providing the necessary power supply and communication interface. The bracket secures the detector in its designated position, ensuring stability and accuracy during monitoring.

[0031] like Figure 2 As shown, Figure 2 Figure 3 is a schematic diagram of the detector structure. The detector cylinder consists of two standard hollow aluminum cylinders (i.e., a first hollow aluminum cylinder 1 and a second hollow aluminum cylinder 2) and an end cap 3. The first hollow aluminum cylinder 1 and the second hollow aluminum cylinder 2 are fastened by gluing 4 and welding 5. This ensures that the thickness of the aluminum cylinder is as small as possible (2mm) to reduce the attenuation of low-energy rays and ensures the structural strength of the connection between the two hollow aluminum cylinders. In addition, choosing standard aluminum cylinder profiles can effectively save costs.

[0032] In practice, a genetic algorithm can be used to optimize the number and placement of distributed radiation monitors. As an optimization search algorithm that simulates natural selection and genetic mechanisms, the genetic algorithm can effectively find near-optimal solutions in complex search spaces, ultimately yielding an optimized distributed radiation monitor placement plan. Based on this plan, multiple distributed radiation monitors are rationally deployed within the monitored area to ensure comprehensive radiation data collection and improve its accuracy and reliability. During the placement process, factors such as the monitor's orientation and height must also be considered to minimize environmental interference with radiation data collection. Once deployed, each distributed radiation monitor begins collecting radiation data in real time.

[0033] In a feasible implementation, step S10 may include steps A11 to A17: Step A11: Initialize a population, wherein each individual in the population represents an initial radiation monitor deployment plan, and the initial radiation monitor deployment plan includes the location and quantity of each distributed radiation monitor.

[0034] It should be noted that the radiation monitor deployment plan includes the location and number of distributed radiation monitors. These parameters jointly determine the radiation data collection effect and the coverage of the monitoring area.

[0035] It is understood that the initial radiation monitor placement plan is randomly generated to provide a starting point for the subsequent optimization process. When initializing the population, the size of the population can be set, that is, the number of initial radiation monitor placement plans included, as well as the range or constraints of the number of radiation monitors and location parameters in each placement plan.

[0036] Step A12: Calculate the fitness value of each individual according to a preset fitness function, wherein the fitness function is determined based on the coverage range and overlap of the distributed radiation monitors and the environmental factors of the area to be monitored, and the environmental factors of the area to be monitored include at least terrain factors, wind direction factors, and environmental shielding factors.

[0037] It's important to note that the fitness function is a key metric for evaluating the quality of each initial radiation monitor deployment plan. It comprehensively considers the coverage and overlap of distributed radiation monitors, as well as environmental factors in the monitored area. By calculating the fitness value of each deployment plan, we can assess its performance in achieving comprehensive and accurate radiation monitoring.

[0038] The design of the fitness function must fully consider the characteristics of the monitored area and the monitoring requirements. For example, in a scenario where radiation sources are widely distributed and change frequently, the fitness function should focus on the coverage and overlap of the monitoring instruments to ensure that there are no blind spots in the entire monitoring area and that data redundancy is appropriate. At the same time, the impact of terrain factors, wind direction factors, and environmental shielding factors on radiation data collection must also be considered to further improve data accuracy and reliability. The fitness function formula is: in, represents the contribution of coverage to fitness, Indicates the effect of overlap on fitness. The smaller the overlap, the better. 、 、 Respectively represent the effects of terrain, wind direction and environmental shielding factors on fitness, is the coverage of the i-th radiation monitor, is the total area of ​​the area to be monitored, n is the number of monitors deployed, is the terrain influence coefficient, is the wind direction influence coefficient, is the environmental blocking coefficient.

[0039] It's worth noting that the coverage of a monitor refers to the geographic area that each distributed radiation monitor can monitor. The larger the coverage, the stronger the monitor's monitoring capability and the higher the degree of coverage of the monitored area. During specific assessments, Geographic Information System (GIS) technology can be used to accurately calculate and visualize the coverage of each monitor, providing an intuitive understanding of each monitor's monitoring capabilities and the effectiveness of its layout. Overlap refers to the degree of overlap between the monitoring areas of different monitors. While a moderate degree of overlap ensures data redundancy and reliability, excessive overlap can lead to resource waste and increased data processing complexity. Therefore, when optimizing the deployment of distributed radiation monitors, a comprehensive balance between coverage and overlap is necessary to ensure maximum monitoring efficiency and accuracy.

[0040] Environmental factors in the monitored area include topography, wind direction, and environmental shielding. Topography, such as mountains, hills, and plains, can affect the propagation path and speed of radioactive materials. Wind direction refers to the direction and intensity of wind, which can affect the direction and range of radiation diffusion. Environmental shielding involves natural and man-made obstacles such as buildings and vegetation, which can block or weaken the spread of radioactive materials. These environmental factors need to be taken into account when designing the fitness function to more accurately evaluate the advantages and disadvantages of different radiation monitor deployment plans. Specifically, geographic information systems (GIS) and meteorological data can be used to model and analyze factors such as topography and wind direction, thereby adjusting the weights and parameters of the fitness function.

[0041] In practice, simulation technology can be used to evaluate and compare different radiation monitor deployment plans. Using computer simulation software, the radiation distribution within the monitored area and the monitors' data collection performance can be simulated, allowing for intuitive visualization and quantitative analysis of the advantages and disadvantages of different deployment plans. This approach not only significantly improves the efficiency and accuracy of the optimization process but also reduces the trial-and-error and time costs associated with actual deployment.

[0042] Step A13: Select the individual with the highest fitness value as the parent generation according to the fitness value, and generate offspring through genetic operations.

[0043] It's important to note that genetic operations include two basic operations: crossover and mutation. Crossover involves swapping some genes from a parent to produce a new offspring. Mutation involves randomly changing one or more values ​​in the offspring's genes to increase population diversity. These two operations can produce offspring with new characteristics.

[0044] It is understandable that, based on their fitness values, several individuals with the highest fitness values ​​can be directly selected as parents. These parents demonstrate good performance in the distributed radiation monitor deployment plan, with high coverage and low overlap, while also fully considering environmental factors in the monitored area. Then, through a crossover operation, the superior genes of these parent individuals are combined to generate new offspring individuals. Crossover can be performed using single-point, two-point, or multi-point crossover methods, depending on the complexity of the problem and the optimization goal. During the crossover process, it is necessary to ensure that the offspring individuals retain the superior genes of the parents while also exhibiting a certain degree of novelty to increase population diversity. Furthermore, through a mutation operation, one or more values ​​in the genes of the offspring individuals are randomly altered to introduce new genetic features, further increasing population diversity and preventing the algorithm from falling into local optimal solutions. The probability of mutation operations is typically low to ensure algorithm stability and convergence.

[0045] Step A14: Generate a new population based on the parent generation and the child generation.

[0046] It's important to note that the new population incorporates both the superior genes of the parent generation and the new characteristics of the offspring, providing more possibilities for subsequent evolution. Through continuous iterations of the genetic algorithm, the individuals in the population will gradually approach the optimal solution, resulting in the optimal deployment plan for distributed radiation monitors.

[0047] Step A15: Iteratively execute the steps of calculating the fitness value of each individual according to the preset fitness function, selecting the individual with the highest fitness value as the parent according to the fitness value, and generating offspring through genetic operations until the preset iteration termination condition is met to obtain the target population.

[0048] Step A16: Select the individual with the highest fitness value in the target population as the optimal layout plan.

[0049] It should be noted that the preset iteration termination conditions can be reaching a preset maximum number of iterations or the change in fitness values ​​of individuals across multiple generations being less than a preset threshold. When either of these conditions is met, the algorithm is considered to have converged to a near-optimal solution, and the iteration process is terminated. The individuals with the highest fitness values ​​from the target population are selected as the optimal deployment plan. This plan will serve as the basis for the actual deployment of distributed radiation monitors in subsequent steps to ensure comprehensive radiation data collection and full coverage of the monitoring area.

[0050] Step A17: Distributed radiation monitors are deployed in the area to be monitored according to the optimal deployment plan, and radiation data is collected in real time through each of the distributed radiation monitors.

[0051] It should be noted that the optimal deployment plan is the number and location of distributed radiation monitors optimized by a genetic algorithm. This plan comprehensively considers the coverage and overlap of the radiation monitors, as well as the environmental factors of the monitored area, ensuring the comprehensive and accurate collection of radiation data.

[0052] In specific implementation, distributed radiation monitors can be reasonably deployed in the area to be monitored according to the optimal deployment plan, and each monitor can be started to collect real-time data.

[0053] Step S20: performing multi-stage filtering on the radiation data through wavelet transform and Kalman filter to obtain filtered radiation data.

[0054] It should be noted that the radiation data may be affected by various noises and interferences during the collection process, resulting in a decrease in data quality. In order to improve the accuracy and reliability of the data, this embodiment uses wavelet transform and Kalman filter to perform multi-stage filtering on the radiation data. Wavelet transform is an effective signal processing technology that can decompose the signal into different frequency components and analyze them simultaneously in the time domain and frequency domain. Through wavelet transform, useful information in the radiation data can be extracted while removing high-frequency noise and interference. The Kalman filter is a recursive estimation algorithm that can recursively calculate the optimal estimate at the current moment based on the estimate at the previous moment and the observed value at the current moment in the presence of noise and uncertainty. On the basis of wavelet transform, the radiation data is further smoothed and filtered using the Kalman filter to obtain more accurate and reliable radiation data.

[0055] In a feasible implementation, step S20 may include: performing a wavelet transform on the radiation data to obtain radiation data components of different frequency bands; filtering the radiation data components of each frequency band through a Kalman filter to obtain filtered radiation data components of each frequency band; and reconstructing the filtered radiation data components of each frequency band to obtain filtered radiation data.

[0056] It should be noted that through wavelet transform, radiation data can be decomposed into data components in multiple frequency bands, each component containing signal components of different frequencies. In this way, targeted filtering processing can be performed based on the signal characteristics of different frequency bands. Specifically, components in high-frequency bands may mainly contain noise and interference information, while components in low-frequency bands are more likely to contain useful radiation signals. Therefore, when performing Kalman filtering on the radiation data components in each frequency band, different filtering parameters and models can be set according to actual conditions to adapt to the characteristics of signals in different frequency bands. Ultimately, the radiation data components after filtering in each frequency band are reconstructed to obtain radiation data that has undergone multi-stage filtering. This method combines the advantages of wavelet transform and Kalman filter, can more effectively remove noise and interference, and improve the accuracy and reliability of radiation data.

[0057] Step S30: performing data fusion and correction on the filtered radiation data to obtain corrected radiation data.

[0058] It should be noted that in a distributed radiation monitoring system, the radiation data collected by individual monitors may contain discrepancies or redundancy. To improve the overall data quality and reliability, this data needs to be fused and corrected. Data fusion involves the integrated processing of data from different monitors to obtain more comprehensive and accurate information. During the data fusion process, factors such as the geographic location, measurement accuracy, and environmental factors of each monitor can be considered. Data fusion can fully leverage the strengths of each monitor, offset the shortcomings of a single monitor, and improve the overall accuracy and reliability of the data. Data correction is also a crucial task. Due to various reasons, such as instrument failure and environmental interference, collected radiation data may contain errors or anomalies. Therefore, data correction is necessary to eliminate or reduce these errors. Data correction can be performed using a variety of methods, such as correction based on historical data and correction based on physical models. Data correction can further improve data accuracy and reliability.

[0059] In specific implementations, filtered radiation data can be fused and corrected using deep learning networks and long short-term memory (LSTM) networks. Deep learning networks possess powerful feature extraction and pattern recognition capabilities, enabling them to automatically learn useful features and information from large amounts of data. LSTM networks are a special type of recurrent neural network that can capture long-term dependencies in time series data. During data fusion and correction, deep learning networks can be used to extract features and comprehensively analyze radiation data from different monitors to obtain more comprehensive and accurate information. Furthermore, LSTM networks can be used to model and predict time series radiation data, further correcting errors and anomalies in the data. Specifically, filtered radiation data can be input into the deep learning network. Through multi-layer neural network processing and feature extraction, data features for each monitor are obtained. The LSTM network then performs time series analysis and prediction on these features to capture long-term trends and cyclical changes in the data. Based on this, data fusion and correction can be performed by incorporating information such as the geographic location, measurement accuracy, and environmental factors of each monitor to produce corrected radiation data.

[0060] In a feasible embodiment, step S30 may include: performing spatiotemporal correlation analysis on the filtered radiation data collected by each distributed radiation monitor to obtain the spatiotemporal relationship between each filtered radiation data; constructing a deep learning network, wherein the deep learning network includes an input layer, a convolution layer, a pooling layer, a fully connected layer and an output layer; using the filtered radiation data collected by each distributed radiation monitor and the corresponding spatiotemporal relationship as input data of the input layer; performing feature extraction on the input data through the convolution layer, and performing dimensionality reduction processing on the extracted features through the pooling layer to obtain reduced dimensionality features; inputting the reduced dimensionality features into the fully connected layer for classification or regression processing, and outputting preliminary fused data through the output layer; learning the preliminary fused data through a long short-term memory network to predict the changing trend of the radiation data; and correcting the preliminary fused data according to the predicted changing trend to obtain corrected radiation data.

[0061] It should be noted that spatiotemporal correlation analysis involves correlating and analyzing radiation data collected by different distributed radiation monitors in both time and space. This analysis considers the temporal and spatial characteristics of radiation data, as well as their interactions. By analyzing the changing trends and spatial distribution patterns of data at different points in time, it is possible to reveal the distribution and movement patterns of radiation sources, as well as the impact of environmental factors on radiation propagation. Specifically, a geographic information system (GIS) and time series analysis techniques can be used to perform spatiotemporal correlation analysis on radiation data collected by different monitors. By analyzing the time lags and spatial correlations between the data, it is possible to derive spatiotemporal relationships between the individual data sets, such as trends between adjacent monitors and fluctuations in data over different time periods.

[0062] It's understandable that building a deep learning network can be achieved using deep learning frameworks such as TensorFlow or PyTorch. These frameworks provide a wealth of tools and library functions to facilitate the efficient construction, training, and evaluation of deep learning models. When building a deep learning network, the input layer receives filtered radiation data and its corresponding spatiotemporal relationships from distributed radiation monitors. After preprocessing, this data is input to the convolutional layer for feature extraction. The convolutional layer slides multiple convolution kernels over the input data to extract local features. The pooling layer downsamples the feature maps output by the convolutional layer, reducing the data dimension while retaining important features and improving the model's generalization capabilities. The fully connected layer receives the feature vectors output by the pooling layer and performs classification or regression processing to initially fuse the data from different monitors. The output layer then outputs this initially fused data.

[0063] Based on the initial data fusion, the Long Short-Term Memory (LSTM) network further learns the time series characteristics of the data. By capturing long-term dependencies in the data, the LSTM can predict the changing trends of radiation data. This predictive capability is crucial for correcting errors and anomalies in the data. Based on the changing trends predicted by the LSTM, the initial fused data can be corrected to obtain more accurate and reliable radiation data. This approach combines the advantages of deep learning networks and LSTM to more effectively fuse and correct radiation data from different monitors, improving the overall quality and reliability of the data.

[0064] Step S40: performing radiation distribution prediction based on the corrected radiation data to obtain radiation intensity distribution data.

[0065] It should be noted that radiation distribution prediction refers to the use of mathematical models or machine learning algorithms to predict the distribution of radiation intensity over a period of time based on corrected radiation data. Radiation distribution prediction can help us understand the possible locations of radiation sources, the changing trends of radiation intensity, and potential risk areas.

[0066] In practice, radiation distribution prediction can be achieved using a variety of methods, including those based on physical models and statistical learning. Physical modeling methods typically use mathematical models based on the physical laws of radiation propagation and environmental factors. This approach considers the influence of factors such as the characteristics of the radiation source, the properties of the propagation medium, and topography on radiation distribution, resulting in high prediction accuracy. However, physical modeling methods typically require significant computing resources and time, and the model establishment and optimization process is complex. In contrast, statistical learning methods are more flexible and efficient. By learning and analyzing historical radiation data, they automatically extract features and patterns from the data and build a predictive model. This approach is not only capable of processing large datasets but also adapts to the radiation distribution prediction needs of different regions and scenarios.

[0067] It is worth mentioning that machine learning algorithms such as support vector machines (SVM), random forests, and neural networks can be used to predict radiation distribution. These algorithms can learn the relationship between radiation intensity and various factors from a large amount of data and automatically adjust model parameters to improve prediction accuracy. Step S50: generating a radiation prediction map based on the radiation data and the radiation intensity distribution data to achieve regional radiation monitoring.

[0068] It should be noted that radiation prediction maps are intuitive, visual tools that clearly display the distribution and changing trends of radiation intensity. When generating radiation prediction maps, corrected radiation data and radiation intensity distribution data are used as input, and processed and plotted using a Geographic Information System (GIS) or related visualization tools. The maps provide a visual representation of radiation intensity in different regions, potential risk areas, and the possible locations of radiation sources, enabling regional radiation monitoring. Furthermore, radiation prediction maps can be dynamically updated and adjusted based on actual needs to ensure their accuracy and practicality.

[0069] In practice, radiation prediction maps can be generated and visualized based on a Geographic Information System (GIS) platform, such as ArcGIS or QGIS. First, the corrected radiation data and radiation intensity distribution data are imported into the GIS platform as the underlying data for the map. Then, using the mapping tools and visualization features provided by the GIS platform, the data is displayed on the map using different colors, symbols, or legends to visually demonstrate the distribution and changing trends of radiation intensity. Furthermore, elements such as labels, legends, and scales can be added to the map as needed to improve its readability and practicality. Once generated, the radiation prediction map can be used for regional radiation monitoring. By regularly updating the map data, changes in radiation intensity can be monitored in real time, allowing the timely identification of potential risk areas and the possible locations of radiation sources. Furthermore, the map data can be correlated and analyzed with other relevant information, such as meteorological data and environmental monitoring data, to provide a more comprehensive understanding of the factors influencing radiation distribution and changing trends, thereby ensuring regional radiation safety.

[0070] This embodiment provides a regional radiation monitoring method based on distributed environmental radiation monitors, wherein a plurality of distributed radiation monitors are deployed in the area to be monitored, and radiation data is collected in real time by each of the distributed radiation monitors; the radiation data is subjected to multi-stage filtering by wavelet transform and Kalman filter to obtain filtered radiation data; data fusion and correction are performed on the filtered radiation data to obtain corrected radiation data; radiation distribution is predicted based on the corrected radiation data to obtain radiation intensity distribution data; a radiation prediction map is generated based on the radiation data and the radiation intensity distribution data to achieve regional radiation monitoring. In the above manner, by optimizing the layout of distributed radiation monitors, the accuracy and reliability of radiation data are improved, thereby accurately predicting radiation intensity distribution data based on radiation data, and then generating a dynamic radiation prediction map to achieve regional radiation monitoring, which can effectively improve the efficiency and accuracy of regional radiation monitoring.

[0071] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 3 , step S40 includes steps S401 to S404: Step S401: simulating and analyzing the corrected radiation data using a radiation diffusion model based on CFD and wind simulation to obtain radiation diffusion trends and intensity distribution characteristics.

[0072] It should be noted that the radiation diffusion model based on computational fluid dynamics (CFD) and wind simulation combines the principles of fluid mechanics with numerical calculation methods to simulate the diffusion of radioactive substances in the environment. By inputting corrected radiation data, the model can simulate the diffusion of radioactive substances under different wind speeds, wind directions, and terrain conditions, thereby determining the radiation diffusion trend and intensity distribution characteristics. This simulation analysis helps to deepen the understanding of the propagation patterns of radioactive substances and provides strong support for subsequent radiation distribution predictions.

[0073] In practice, professional CFD software, such as ANSYS Fluent or OpenFOAM, can be used to build radiation diffusion models and perform simulation analysis. These software programs offer a rich set of physical models and numerical algorithms, enabling accurate simulation of the diffusion of radiation in complex environments. Furthermore, wind simulation technology can be incorporated to consider the effects of varying wind speeds and directions on radiation diffusion, further improving the accuracy and reliability of simulation analysis.

[0074] In a feasible embodiment, step S401 may include: obtaining environmental data and wind data of the area to be monitored; constructing a fluid dynamics model, and performing radiation diffusion simulation based on the environmental data and the corrected radiation data through the fluid dynamics model to obtain a radiation diffusion trend; simulating the influence of wind during the radiation diffusion process through a wind simulation algorithm based on the wind data to obtain a wind influence simulation result, wherein the wind influence simulation result includes the wind carrying of radiation substances, changes in diffusion direction, and changes in intensity distribution; and obtaining radiation intensity distribution characteristics under the influence of wind based on the radiation diffusion trend and the wind influence simulation result.

[0075] It's important to note that environmental data for the monitored area refers to information such as topography, landforms, and building distribution, all of which have a certain impact on the radiation diffusion process. By acquiring accurate environmental data, we can more realistically simulate the diffusion of radioactive substances within the monitored area. Wind data, on the other hand, refers to parameters such as wind speed and direction within the monitored area, which have a significant impact on the radiation diffusion process. By acquiring real-time wind data and combining it with a wind simulation algorithm, we can simulate the diffusion of radioactive substances under different wind speeds and directions, thereby characterizing the radiation intensity distribution under wind influence.

[0076] Understandably, when constructing a fluid dynamics model, factors such as the physical properties of the radiation, environmental parameters, and boundary conditions must be considered. Through appropriate model setup and parameter adjustment, the diffusion trend of radiation within the monitored area can be simulated. Furthermore, incorporating a wind simulation algorithm, the impact of wind on the radiation diffusion process can be further analyzed, revealing the radiation intensity distribution characteristics under wind influence. These characteristics, including information on the diffusion range, diffusion velocity, and intensity distribution of the radiation, provide a crucial basis for subsequent radiation distribution predictions.

[0077] In practice, fluid dynamics models can be constructed using CFD software, such as ANSYS Fluent. This software can perform various fluid dynamics simulations, including radiation diffusion simulations. It provides a rich set of physical models and numerical algorithms, enabling accurate simulation of the diffusion of radioactive substances in complex environments. It also supports user-defined model parameters and boundary conditions to meet specific simulation requirements. OpenFOAM, another popular open-source CFD software, offers high flexibility and scalability, allowing users to customize models and optimize algorithms based on their needs. When constructing a fluid dynamics model, appropriate model settings and parameter adjustments are necessary based on factors such as the environmental data of the monitored area, the physical properties of the radioactive substances, and boundary conditions. By adjusting model parameters such as fluid density, viscosity, and radioactive substance concentration, radiation diffusion can be simulated under different conditions, resulting in more accurate radiation diffusion trends and intensity distribution characteristics. After obtaining simulation results for radiation diffusion trends and wind impacts, these results need to be analyzed and processed. Visualization tools can be used to present simulation results in graphical or animated form, providing a more intuitive understanding of the radiation diffusion process and wind impacts.

[0078] Step S402: Acquire historical meteorological data and real-time meteorological data.

[0079] It should be noted that historical meteorological data refers to meteorological information recorded over a period of time, including parameters such as temperature, humidity, wind speed, wind direction, and air pressure. This data is crucial for analyzing the historical trends and patterns of radiation diffusion. By acquiring and analyzing historical meteorological data, we can understand the characteristics and influencing factors of radiation diffusion under different meteorological conditions. Real-time meteorological data refers to meteorological information at the current moment or in the near future. This data is crucial for real-time monitoring and prediction of radiation diffusion processes.

[0080] It is understandable that by obtaining real-time meteorological data, we can timely grasp the current meteorological conditions, such as wind speed, wind direction, etc., so as to more accurately predict the diffusion trend and intensity distribution of radioactive materials.

[0081] In practice, historical and real-time meteorological data can be obtained through meteorological monitoring stations, satellite remote sensing, numerical weather forecasts, and other sources. This data is typically presented as a time series and can be extracted, cleaned, and organized using data analysis and processing tools. After obtaining historical and real-time meteorological data, these data can be correlated and analyzed with corrected radiation data. By considering the impact of meteorological factors on radiation diffusion, the accuracy and reliability of radiation distribution predictions can be further improved. For example, in conditions of high wind speeds, radiation may spread rapidly to distant areas; whereas, in conditions of low wind speeds or the presence of obstacles, the diffusion of radiation may be limited. By analyzing historical and real-time meteorological data, we can understand the characteristics and patterns of radiation diffusion under different meteorological conditions, thereby providing a more accurate basis for radiation distribution predictions.

[0082] Step S403: predicting radiation propagation based on the corrected radiation data, the historical meteorological data and the real-time meteorological data using a radiation propagation prediction model to obtain radiation propagation trend and intensity distribution prediction results.

[0083] It's important to note that the radiation propagation prediction model combines physics principles, statistical methods, and machine learning algorithms to comprehensively consider the impact of multiple factors on radiation propagation. By inputting corrected radiation data, historical meteorological data, and real-time meteorological data, the model can simulate and predict the propagation trends and intensity distribution of radioactive materials at different temporal and spatial scales.

[0084] In practice, radiation propagation prediction models can employ a variety of techniques and methods, including those based on physical models, statistical learning, and machine learning. Physical modeling methods typically employ mathematical models based on the physical laws of radiation propagation and environmental factors, offering high accuracy but computationally complex and time-consuming. Statistical learning methods are more flexible and efficient, automatically extracting features and patterns from historical data through analysis and analysis, and establishing a prediction model. Machine learning algorithms, such as support vector machines and neural networks, can learn the relationships between radiation propagation and various factors from large datasets and automatically adjust model parameters to improve prediction accuracy. By integrating the strengths of multiple prediction methods and techniques, radiation propagation prediction models can more accurately predict the propagation trends and intensity distribution of radioactive materials, providing strong support for regional radiation monitoring.

[0085] In a feasible embodiment, step S403 may include: constructing a radiation propagation prediction model, wherein the radiation propagation prediction model is constructed based on a support vector machine and a deep learning network; extracting radiation propagation features according to the corrected radiation data, historical meteorological data and real-time meteorological data through the radiation propagation prediction model to obtain extracted radiation propagation features; inputting the extracted radiation propagation features into the support vector machine for classification processing to obtain radiation propagation trend prediction results, wherein the radiation propagation trend prediction results include the predicted propagation path, speed and range of the radiation material; inputting the radiation propagation trend prediction results and the real-time meteorological data into the deep learning network for deep learning processing to obtain radiation intensity distribution prediction results, wherein the intensity distribution prediction results include the predicted radiation intensity distribution of different regions, and the deep learning processing includes feature fusion, multi-layer perceptron processing and regression prediction.

[0086] It should be noted that in this embodiment, the radiation propagation prediction model is constructed based on support vector machines and deep learning networks, combining the advantages of the two algorithms to improve the accuracy and reliability of the prediction. Support vector machine (SVM) is a classification algorithm based on supervised learning. It classifies samples by finding the optimal hyperplane that can separate samples of different categories. In radiation propagation prediction, SVM can be used to extract key features of radiation propagation and make preliminary predictions on the propagation trends of radiation materials. Deep learning networks, especially convolutional neural networks (CNN) and recurrent neural networks (RNN), have powerful feature extraction and pattern recognition capabilities and can learn complex nonlinear relationships from large-scale data sets. In radiation propagation prediction, deep learning networks can be used to further fuse and extract radiation propagation features and make detailed predictions of radiation intensity distribution based on these features.

[0087] In practice, programming languages ​​such as Python can be used in conjunction with machine learning frameworks such as Scikit-learn, TensorFlow, or PyTorch to build and train radiation propagation prediction models. First, a training dataset must be prepared, including corrected radiation data, historical meteorological data, and real-time meteorological data. Next, appropriate feature extraction methods and model architectures should be selected based on the data characteristics and prediction objectives. For example, CNNs can be used for image feature extraction, while RNNs can be used for time series prediction. During model training, model parameters such as the learning rate and batch size must be continuously optimized to improve predictive performance and generalization. Finally, the model should be evaluated and fine-tuned through methods such as cross-validation to ensure accuracy and reliability.

[0088] It can be understood that radiation propagation characteristics refer to the key factors affecting radiation propagation, mainly including the type of radiation material (such as radioactive gas, particulate matter, etc.), the speed and path of radiation propagation (affected by wind speed, terrain, air pressure, etc.), environmental factors (such as wind speed, temperature, humidity, etc.), etc.

[0089] It's worth noting that radiation propagation features are input into a support vector machine (SVM) for classification processing to predict radiation propagation trends. The core goal of the SVM is to find an optimal hyperplane based on the feature distribution to classify the data into different categories (such as different propagation paths or speed ranges). The SVM finds the optimal hyperplane by optimizing the following objectives: The constraints are: in, is the normal vector of the hyperplane, is the bias, is the label of the sample (category of radiation propagation trend), is the input feature vector.

[0090] It's worth noting that the SVM output (radiation propagation trend forecast) and real-time meteorological data are fed into a deep learning network for further processing to predict the radiation intensity distribution in different areas. Deep learning models typically use a multi-layer perceptron (MLP), which consists of multiple layers of neurons and is capable of effective nonlinear mapping. The MLP inputs include the SVM prediction results (radiation propagation trend) and real-time meteorological data.

[0091] When performing deep learning, feature fusion is first required to fuse the prediction results of the SVM and the meteorological data into a comprehensive feature vector. Then, the fused feature vector is input into the multi-layer perceptron. The MLP performs nonlinear transformation of the features through multiple hidden layers and outputs the radiation intensity distribution prediction. Assuming that the network structure has L hidden layers, each layer in the network uses an activation function for nonlinear transformation. The goal of the output layer is to perform regression prediction to predict the radiation intensity distribution in different areas. Assuming the output is y intensity , represents the radiation intensity in different areas. The regression loss function is usually evaluated using the mean square error (MSE), as follows: Where L is the loss function, is the total sample size, is the true radiation intensity of the i-th sample, is the predicted radiation intensity of the i-th sample.

[0092] Step S404: obtaining radiation intensity distribution data according to the radiation diffusion trend and intensity distribution characteristics and the radiation propagation trend and intensity distribution prediction results.

[0093] It's important to note that radiation intensity distribution data is the result of a combination of radiation diffusion simulation, wind impact analysis, and radiation propagation prediction. This data not only reflects the diffusion trend and intensity distribution of radioactive materials in the current environment but also predicts the likely propagation paths and intensity changes of radioactive materials over the next period of time. By acquiring and analyzing radiation intensity distribution data, we can provide a timely understanding of the radiation status of the monitored area.

[0094] In a specific implementation, the radiation diffusion trend and intensity distribution characteristics are fused with the radiation propagation trend and intensity distribution prediction results to obtain a fused radiation intensity distribution characteristic. This fused radiation intensity distribution characteristic is then spatially interpolated and time-series analyzed to obtain spatially and temporally continuous radiation intensity distribution data. This radiation intensity distribution data is then formatted and standardized for subsequent data storage, transmission, and analysis. This step allows for comprehensive and accurate radiation intensity distribution data to be obtained, providing strong data support for regional radiation monitoring.

[0095] It is worth noting that radiation intensity distribution data can be presented in a variety of forms, such as numerical tables, two-dimensional or three-dimensional graphs, and animated simulations, which are not specifically limited in this embodiment. Numerical tables provide detailed radiation intensity data, facilitating quantitative analysis and comparison; two-dimensional or three-dimensional graphs can intuitively display the diffusion range and intensity distribution of radioactive substances, helping to quickly identify high-risk areas; and animated simulations can dynamically display the diffusion process of radioactive substances.

[0096] In this embodiment, the corrected radiation data is simulated and analyzed using a radiation diffusion model based on CFD and wind simulation to obtain radiation diffusion trends and intensity distribution characteristics; historical meteorological data and real-time meteorological data are obtained; radiation propagation is predicted based on the corrected radiation data, the historical meteorological data, and the real-time meteorological data using a radiation propagation prediction model to obtain radiation propagation trend and intensity distribution prediction results; and radiation intensity distribution data is obtained based on the radiation diffusion trend and intensity distribution characteristics and the radiation propagation trend and intensity distribution prediction results. In the above manner, by introducing a radiation diffusion model based on CFD and wind simulation and a radiation propagation prediction model combined with a support vector machine and a deep learning network, a more accurate radiation propagation prediction can be achieved, effectively improving the accuracy of the radiation intensity distribution prediction.

[0097] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the regional radiation monitoring method based on distributed environmental radiation monitors in the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0098] This application also provides a regional radiation monitoring device based on a distributed environmental radiation monitor, please refer to Figure 4 , the regional radiation monitoring device based on the distributed environmental radiation monitor includes: The acquisition module 10 is used to deploy a plurality of distributed radiation monitors in the area to be monitored, and to collect radiation data in real time through each of the distributed radiation monitors.

[0099] The filtering module 20 is configured to perform multi-stage filtering on the radiation data through wavelet transform and Kalman filter to obtain filtered radiation data.

[0100] The correction module 30 is used to perform data fusion and correction on the filtered radiation data to obtain corrected radiation data.

[0101] The prediction module 40 is configured to perform radiation distribution prediction based on the corrected radiation data to obtain radiation intensity distribution data.

[0102] The generating module 50 is configured to generate a radiation prediction map based on the radiation data and the radiation intensity distribution data to implement regional radiation monitoring.

[0103] The regional radiation monitoring device based on a distributed environmental radiation monitor provided in this application, which utilizes the regional radiation monitoring method based on a distributed environmental radiation monitor in the above-mentioned embodiments, can resolve the technical issues that traditional fixed-point monitoring methods are not only inefficient but also difficult to achieve comprehensive coverage of the entire monitoring area. Compared with the prior art, the beneficial effects of the regional radiation monitoring device based on a distributed environmental radiation monitor provided in this application are the same as those of the regional radiation monitoring method based on a distributed environmental radiation monitor provided in the above-mentioned embodiments. Other technical features of the regional radiation monitoring device based on a distributed environmental radiation monitor are the same as those disclosed in the above-mentioned embodiments and are not further described here.

[0104] The present application provides a regional radiation monitoring device based on a distributed environmental radiation monitor. The regional radiation monitoring device based on the distributed environmental radiation monitor includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the regional radiation monitoring method based on the distributed environmental radiation monitor in the above-mentioned embodiment one.

[0105] Reference below Figure 5 , which shows a schematic structural diagram of a regional radiation monitoring device based on a distributed environmental radiation monitor suitable for implementing an embodiment of the present application. The regional radiation monitoring device based on a distributed environmental radiation monitor in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (e.g., vehicle-mounted navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The regional radiation monitoring device based on the distributed environmental radiation monitor is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0106] like Figure 5 As shown, the regional radiation monitoring device based on the distributed environmental radiation monitor may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in ROM (Read Only Memory) 1002 or programs loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the regional radiation monitoring device based on the distributed environmental radiation monitor. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input device 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output device 1008 including, for example, an LCD (Liquid Crystal Display), speaker, vibrator, etc.; storage device 1003 including, for example, a magnetic tape, hard disk, etc.; and communication device 1009. Communication device 1009 can allow the regional radiation monitoring device based on the distributed environmental radiation monitor to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a regional radiation monitoring device based on the distributed environmental radiation monitor with various systems, it should be understood that implementation or presence of all the illustrated systems is not required. More or fewer systems may alternatively be implemented or present.

[0107] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0108] The regional radiation monitoring device based on a distributed environmental radiation monitor provided in this application utilizes the regional radiation monitoring method based on a distributed environmental radiation monitor in the above-mentioned embodiment, thereby resolving the technical issues that traditional fixed-point monitoring methods are not only inefficient but also difficult to achieve comprehensive coverage of the entire monitoring area. Compared with the prior art, the beneficial effects of the regional radiation monitoring device based on a distributed environmental radiation monitor provided in this application are the same as those of the regional radiation monitoring method based on a distributed environmental radiation monitor provided in the above-mentioned embodiment. Other technical features of the regional radiation monitoring device based on a distributed environmental radiation monitor are the same as those disclosed in the above-mentioned embodiment and are not further described here.

[0109] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0110] 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 this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0111] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, and the computer-readable program instructions are used to execute the regional radiation monitoring method based on the distributed environmental radiation monitor in the above embodiment.

[0112] The computer-readable storage medium provided herein may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory or Flash memory), optical fiber, CD-ROM (CD-Read Only Memory), optical storage device, magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including, but not limited to, wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0113] The computer-readable storage medium may be included in the regional radiation monitoring device based on the distributed environmental radiation monitor; or may exist independently without being assembled into the regional radiation monitoring device based on the distributed environmental radiation monitor.

[0114] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the regional radiation monitoring device based on the distributed environmental radiation monitor, the regional radiation monitoring device based on the distributed environmental radiation monitor: deploys multiple distributed radiation monitors in the area to be monitored, and collects radiation data in real time through each of the distributed radiation monitors; performs multi-stage filtering on the radiation data through wavelet transform and Kalman filter to obtain filtered radiation data; performs data fusion and correction on the filtered radiation data to obtain corrected radiation data; performs radiation distribution prediction based on the corrected radiation data to obtain radiation intensity distribution data; and generates a radiation prediction map based on the radiation data and the radiation intensity distribution data to realize regional radiation monitoring.

[0115] The computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a LAN (Local Area Network) or a WAN (Wide Area Network), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0116] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0117] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0118] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned regional radiation monitoring method based on distributed environmental radiation monitors. This computer-readable storage medium addresses the technical issues of traditional fixed-point monitoring methods, which are not only inefficient but also difficult to achieve comprehensive coverage of the entire monitoring area. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are similar to those of the regional radiation monitoring method based on distributed environmental radiation monitors provided in the aforementioned embodiments, and are not further elaborated here.

[0119] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the regional radiation monitoring method based on the distributed environmental radiation monitor as described above.

[0120] The computer program product provided in this application can address the technical issues of traditional fixed-point monitoring methods, which are not only inefficient but also difficult to achieve comprehensive coverage of the entire monitoring area. Compared to the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the regional radiation monitoring method based on distributed environmental radiation monitors provided in the above-mentioned embodiments, and are not further elaborated here.

[0121] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A regional radiation monitoring method based on a distributed environmental radiation monitor, characterized in that: The method comprises: Deploy a plurality of distributed radiation monitors in the area to be monitored, and collect radiation data in real time through each of the distributed radiation monitors; Performing multi-stage filtering on the radiation data through wavelet transform and Kalman filter to obtain filtered radiation data; performing data fusion and correction on the filtered radiation data to obtain corrected radiation data; Performing radiation distribution prediction based on the corrected radiation data to obtain radiation intensity distribution data; A radiation prediction map is generated based on the radiation data and the radiation intensity distribution data to achieve regional radiation monitoring.

2. The method according to claim 1, wherein The method of deploying a plurality of distributed radiation monitors in the area to be monitored and collecting radiation data in real time through each of the distributed radiation monitors includes: Initializing a population, wherein each individual in the population represents an initial radiation monitor deployment plan, and the initial radiation monitor deployment plan includes the location and quantity of each distributed radiation monitor; Calculating the fitness value of each individual according to a preset fitness function, wherein the fitness function is determined based on the coverage and overlap of the distributed radiation monitors and environmental factors of the area to be monitored, wherein the environmental factors of the area to be monitored include at least terrain factors, wind direction factors, and environmental shielding factors; Selecting the individual with the highest fitness value as the parent generation according to the fitness value, and generating offspring through genetic operations; generating a new population according to the parent generation and the offspring generation; Iteratively executing the steps of calculating the fitness value of each individual according to a preset fitness function, selecting the individual with the highest fitness value as the parent according to the fitness value, and generating offspring through genetic operations until a preset iteration termination condition is met to obtain a target population; Select the individual with the highest fitness value in the target population as the optimal layout plan; Distributed radiation monitors are deployed in the area to be monitored according to the optimal deployment plan, and radiation data is collected in real time through each of the distributed radiation monitors.

3. The method according to claim 1, wherein The multi-stage filtering of the radiation data by wavelet transform and Kalman filter to obtain filtered radiation data includes: Performing wavelet transform on the radiation data to obtain radiation data components in different frequency bands; The radiation data components of each frequency band are filtered by a Kalman filter to obtain the filtered radiation data components of each frequency band; The radiation data components after filtering in each frequency band are reconstructed to obtain filtered radiation data.

4. The method according to claim 1, wherein The performing data fusion and correction on the filtered radiation data to obtain corrected radiation data includes: Performing spatiotemporal correlation analysis on the filtered radiation data collected by each distributed radiation monitor to obtain the spatiotemporal relationship between the filtered radiation data; Constructing a deep learning network, wherein the deep learning network includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer; Using the filtered radiation data collected by each distributed radiation monitor and the corresponding spatiotemporal relationship as input data of the input layer; Extracting features from the input data through the convolution layer, and performing dimensionality reduction processing on the extracted features through the pooling layer to obtain features after dimensionality reduction; Inputting the reduced-dimensional features into the fully connected layer for classification or regression processing, and outputting preliminary fused data through the output layer; Learning the preliminary fusion data through a long short-term memory network to predict the change trend of the radiation data; The preliminary fusion data is corrected according to the predicted change trend to obtain corrected radiation data.

5. The method according to claim 1, wherein The step of performing radiation distribution prediction based on the corrected radiation data to obtain radiation intensity distribution data includes: The corrected radiation data is simulated and analyzed by a radiation diffusion model based on CFD and wind simulation to obtain radiation diffusion trends and intensity distribution characteristics; Obtain historical and real-time weather data; Predicting radiation propagation using a radiation propagation prediction model based on the corrected radiation data, the historical meteorological data, and the real-time meteorological data to obtain radiation propagation trend and intensity distribution prediction results; Radiation intensity distribution data is obtained based on the radiation diffusion trend and intensity distribution characteristics and the radiation propagation trend and intensity distribution prediction results.

6. The method according to claim 5, wherein The radiation diffusion model based on CFD and wind simulation is used to simulate and analyze the corrected radiation data to obtain radiation diffusion trends and intensity distribution characteristics, including: Obtain environmental data and wind data of the area to be monitored; Constructing a fluid dynamics model, and performing a radiation diffusion simulation based on the environmental data and the corrected radiation data using the fluid dynamics model to obtain a radiation diffusion trend; Simulating the influence of wind on the radiation diffusion process using a wind simulation algorithm based on the wind data to obtain wind influence simulation results, wherein the wind influence simulation results include the wind carrying of radiation materials, changes in diffusion direction, and changes in intensity distribution; The radiation intensity distribution characteristics under the influence of wind are obtained based on the radiation diffusion trend and wind influence simulation results.

7. The method according to claim 5, wherein The radiation propagation prediction model predicts radiation propagation based on the corrected radiation data, the historical meteorological data, and the real-time meteorological data to obtain radiation propagation trend and intensity distribution prediction results, including: Constructing a radiation propagation prediction model, wherein the radiation propagation prediction model is constructed based on a support vector machine and a deep learning network; Extracting radiation propagation features based on the corrected radiation data, historical meteorological data, and real-time meteorological data using the radiation propagation prediction model to obtain extracted radiation propagation features; Inputting the extracted radiation propagation features into the support vector machine for classification processing to obtain a radiation propagation trend prediction result, wherein the radiation propagation trend prediction result includes a predicted propagation path, speed, and range of the radiation material; The radiation propagation trend prediction results and the real-time meteorological data are input into the deep learning network for deep learning processing to obtain radiation intensity distribution prediction results. The intensity distribution prediction results include the predicted radiation intensity distribution of different areas. The deep learning processing includes feature fusion, multi-layer perceptron processing and regression prediction.

8. A regional radiation monitoring device based on a distributed environmental radiation monitor, characterized in that: The regional radiation monitoring device based on the distributed environmental radiation monitor includes: A collection module is used to deploy multiple distributed radiation monitors in the area to be monitored and collect radiation data in real time through each of the distributed radiation monitors; A filtering module, configured to perform multi-stage filtering on the radiation data through wavelet transform and Kalman filter to obtain filtered radiation data; A correction module, configured to perform data fusion and correction on the filtered radiation data to obtain corrected radiation data; A prediction module, configured to perform radiation distribution prediction based on the corrected radiation data to obtain radiation intensity distribution data; A generation module is used to generate a radiation prediction map based on the radiation data and the radiation intensity distribution data to achieve regional radiation monitoring.

9. A regional radiation monitoring device based on a distributed environmental radiation monitor, characterized in that: The regional radiation monitoring device based on a distributed environmental radiation monitor includes: a memory, a processor, and a regional radiation monitoring program based on a distributed environmental radiation monitor stored in the memory and executable on the processor. The regional radiation monitoring program based on a distributed environmental radiation monitor is configured to implement the regional radiation monitoring method based on a distributed environmental radiation monitor as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a regional radiation monitoring program based on a distributed environmental radiation monitor. When the regional radiation monitoring program based on a distributed environmental radiation monitor is executed by a processor, the regional radiation monitoring method based on a distributed environmental radiation monitor according to any one of claims 1 to 7 is implemented.

Images