Nuclear radiation environment monitoring system based on unmanned aerial vehicle

Abstract

The invention discloses a nuclear radiation environment monitoring system based on an unmanned aerial vehicle, and relates to the technical field of nuclear radiation monitoring, an initialization unit is used for dividing a to-be-monitored area into a plurality of sub-areas, and setting a plurality of radiation dose monitoring points in the sub-areas; the parameter setting unit is used for setting flight parameters and an inspection path of the unmanned aerial vehicle based on the coordinate data of the radiation dose monitoring points, and converting radiation monitoring of the to-be-monitored area into radiation monitoring of the plurality of radiation dose monitoring points in the plurality of sub-areas; the monitoring unit is used for acquiring and processing radiation dose data of each radiation dose monitoring point to obtain a first processing result; the image unit is used for acquiring a real-time image and processing the real-time image and the original image to obtain a second processing result; and the parameter adjusting unit is used for adjusting the flight parameters and the inspection path of the unmanned aerial vehicle based on the first processing result and the second processing result. According to the invention, the accuracy and real-time performance of radiation monitoring data acquisition are improved, and the unmanned aerial vehicle can be ensured to work in a safe range.

Description

Technical Field

[0001] The present invention relates to the technical field of nuclear radiation monitoring, and in particular to a nuclear radiation environment monitoring system based on an unmanned aerial vehicle. Background Art

[0002] When a nuclear leakage accident occurs in a nuclear facility, it is of great significance to quickly enter the accident area to obtain the radiation distribution of the nuclear leakage and radioactive contamination site. When a major nuclear accident occurs, the accompanying serious damage to the roads makes it impossible for nuclear radiation detectors to accompany personnel to conduct radiation monitoring at the nuclear accident site. In order to overcome the problems of traditional nuclear emergency monitoring methods such as radiation damage to personnel, poor mobility and low efficiency, the method of monitoring the nuclear radiation environment through drones has been developed.

[0003] The principle of monitoring the nuclear radiation environment based on drones is: it mainly uses the ionization effect of particles released by radioactive substances to make air molecules produce ionizing radiation fields. The drone uses the radiation detectors it carries to collect and analyze radiation data for each area in turn according to the pre-set flight path and flight parameters, and transmits the data to the ground control system. The ground control system receives and processes the radiation data to determine whether there is a nuclear radiation leak in the target area.

[0004] However, the current monitoring of nuclear radiation environment based on drones has the following problems: drones collect environmental data according to the flight path and flight parameters set in advance. The principle is to collect environmental data in the shortest time and transmit it back to the ground control system. However, in the area where nuclear radiation actually occurs, the environmental factors are complex and changeable. Not only will the radiation source affect the work of the drone (affecting the accuracy of the drone's acquisition of monitoring data), but if the nuclear radiation is caused by a small-scale explosion, it will also form multiple obstacles (which will affect the flight of the drone) and multiple local shielding areas. Therefore, for monitoring nuclear radiation areas in complex environments, a nuclear radiation environment monitoring system based on drones is urgently needed, which can not only improve the accuracy and real-time nature of monitoring data acquisition, but also ensure that drones work in a safe environment as much as possible. Summary of the invention

[0005] In order to solve the above-mentioned deficiencies in the prior art, the present invention provides a nuclear radiation environment monitoring system based on a drone, the system comprising:

[0006] Initialization unit: acquiring multidimensional data and original image data of the area to be monitored, dividing the area to be monitored into a plurality of sub-areas based on the multidimensional data, each of which is provided with a plurality of radiation dose monitoring points, and recording the first coordinate data of each radiation dose monitoring point into a preset data table;

[0007] A parameter setting unit: based on the data in the preset data table, sets the first flight parameter of the UAV, and generates a first inspection path of the UAV using a first method;

[0008] Monitoring unit: the UAV collects and processes radiation dose data for each sub-area in turn based on the first flight parameter and the first inspection path to obtain a first processing result;

[0009] Image unit: the UAV obtains real-time image data of each sub-area during flight, and processes the real-time image data and the original image data to obtain a second processing result;

[0010] Parameter adjustment unit: Based on the first processing result, the first flight parameter is adjusted in real time; based on the second processing result, the first inspection path is adjusted in real time, and the UAV monitors the remaining area in the area to be monitored based on the adjusted first flight parameter and first inspection path.

[0011] The present invention is achieved through the following technical solutions:

[0012] Initialization unit: obtain multi-dimensional data (such as environmental monitoring data, spatial distribution data and trajectory data, etc.) and original image data (real images taken during normal operation) of the area to be monitored, divide the area to be monitored into multiple sub-areas through the multi-dimensional data, then set multiple radiation dose monitoring points in each sub-area, and record the first coordinate data of each radiation dose monitoring point to a preset data table, complete the radiation monitoring of the entire sub-area by collecting radiation dose data for all radiation dose monitoring points in a single sub-area, and complete the radiation monitoring of the entire area to be monitored by collecting radiation dose data for the radiation dose monitoring points in all sub-areas;

[0013] Parameter setting unit: The UAV completes the radiation monitoring of the entire area to be monitored by collecting the radiation dose data of all radiation dose monitoring points. Therefore, it is necessary to set the first flight parameters (such as speed, altitude, angle, etc.) of the UAV based on the coordinate data of all radiation dose monitoring points in the preset data table, and use the first method to generate the first inspection path of the UAV;

[0014] Monitoring unit: The UAV collects and processes radiation dose data of each sub-area in turn based on the set first flight parameters and the planned first inspection path to obtain a first processing result;

[0015] Image unit: When a nuclear leak occurs, it may be accompanied by a small-scale explosion, thereby forming a new obstacle. Therefore, it is necessary to obtain real-time image data and compare the real-time image data with the original image data to obtain a second processing result, and use the second processing result to determine whether a new obstacle is generated;

[0016] Parameter adjustment unit: The first processing result is to process the collected radiation dose data. In order to ensure that the UAV can take samples within a safe range, it is necessary to adjust the first flight parameter based on the first processing result; and the second processing result is to judge when a new obstacle is generated. In order to avoid the obstacle and ensure that the monitoring of all radiation dose monitoring points can be completed in the shortest time, it is necessary to adjust the first inspection path in real time. Finally, during the flight, the UAV continuously adjusts the flight parameters and inspection paths, which not only improves the accuracy and real-time nature of the monitoring data acquisition, but also ensures that the UAV works within a safe range as much as possible.

[0017] Based on the first processing result and the second processing result, adjusting the first flight parameter and the first inspection path in real time;

[0018] As an optional technical solution, based on the multi-dimensional data, dividing the area to be monitored into a plurality of sub-areas includes:

[0019] Collect multi-dimensional data in the area to be monitored, extract personnel trajectory data from the multi-dimensional data and generate trajectory information;

[0020] Extracting environmental monitoring data, spatial distribution data and nuclear equipment distribution data from the multidimensional data in sequence to obtain extraction results;

[0021] Based on the trajectory information and the extraction result, the area to be monitored is divided into a plurality of sub-areas.

[0022] As an optional technical solution, several radiation dose monitoring points are set up in each sub-area, including:

[0023] Acquire the nuclear equipment distribution data, radiation source type data and regional area data in any sub-region to obtain a first acquisition result;

[0024] Based on the first acquisition result, a first number of radiation dose monitoring points are arranged in the corresponding sub-area, and based on all the radiation dose monitoring points in the single sub-area, radiation monitoring coverage of the single sub-area is completed.

[0025] As an optional technical solution, the first method includes:

[0026] Extract the center point of each sub-area as a node, and record the second coordinate data of each node;

[0027] Constructing a grid diagram with longitude as the horizontal coordinate and latitude as the vertical coordinate, and adding all nodes to the grid diagram based on all second coordinate data;

[0028] Based on the trellis graph, a starting node and a target node are determined, and a Dijkstra algorithm is used to traverse all nodes in the trellis graph to obtain the shortest path from the starting node to the target node;

[0029] Based on the shortest path, the inspection order of the drone for all sub-areas is obtained, and the second method is used to plan the inspection path for each sub-area until all radiation dose monitoring points in the area to be monitored are covered.

[0030] As an optional technical solution, the second method includes:

[0031] Obtain any sub-area as a first sub-area, and based on the inspection sequence, obtain an adjacent inspection sub-area of ​​the first sub-area as a second sub-area;

[0032] Obtaining a radiation dose monitoring point in the first sub-region that is farthest from any radiation dose monitoring point in the second sub-region, and recording it as a starting monitoring point of the first sub-region;

[0033] Acquire a radiation dose monitoring point in the first sub-region that is closest to any radiation dose monitoring point in the second sub-region, and record it as a target monitoring point in the first sub-region;

[0034] Based on the starting node and the target node of the first sub-region, all radiation dose monitoring points in the first sub-region are traversed using the Dijkstra algorithm to obtain the shortest path from the starting monitoring point to the target monitoring point in the first sub-region.

[0035] As an optional technical solution, radiation dose data of each sub-region is collected and processed in turn, and a first processing result is obtained including:

[0036] Obtain any sub-region as the third sub-region, and obtain radiation dose data of all radiation dose monitoring points in the third sub-region, and put them into the first set;

[0037] A first-level determination is performed on all radiation dose data in the first set, specifically:

[0038] It is determined whether the corresponding radiation dose data exceeds the preset value. If not, no action is taken. If yes, a first formula is used to calculate the radiation dose percentage data in the corresponding radiation dose monitoring point. Based on the radiation dose percentage data, a first classification mark is made for all corresponding radiation dose monitoring points. The first formula includes:

[0039]

[0040] η% is the radiation dose percentage data of a single radiation dose monitoring point, μ i is the radiation dose data of a single radiation monitoring point, and A is the preset value;

[0041] Perform secondary determination on all radiation dose data in the first set, specifically:

[0042] Obtain all radiation dose monitoring points in the first set where the radiation dose data exceeds the preset value, and place them in the second set;

[0043] Acquire a radiation dose monitoring point corresponding to the maximum value of the radiation dose data in the second set, record it as a first radiation dose monitoring point, acquire radiation source type data and radiation dose data of the first radiation dose monitoring point, and obtain a second acquisition result;

[0044] Acquire all radiation dose monitoring points in the second set except the first radiation dose monitoring point, and record them as second radiation dose monitoring points;

[0045] Acquire the first coordinate data of all second radiation dose monitoring points, put them into a coordinate set, and obtain a third acquisition result;

[0046] Constructing a radiation diffusion model and training it, inputting the second acquisition result and the third acquisition result into the trained radiation diffusion model, and outputting a simulated radiation dose data curve graph of each second radiation dose monitoring point in the coordinate set changing with time;

[0047] Obtain a change curve graph of the radiation dose data of each second radiation dose monitoring point within a preset time period, and match the corresponding simulated radiation dose data curve graph based on the radiation dose data at the starting point of the change curve graph. If the match is successful, no action is taken. If the match fails, the corresponding second radiation dose monitoring point is marked as a second mark.

[0048] As an optional technical solution, based on the radiation dose percentage data, all corresponding radiation dose monitoring points are graded and marked, including:

[0049] Acquire historical data of the radiation dose percentage data within a preset time period, and divide the radiation dose percentage data into data intervals based on the historical data, and set a corresponding level for each data interval;

[0050] Obtaining radiation dose percentage data of any radiation dose monitoring point, recorded as first radiation dose percentage data;

[0051] Obtaining a data interval of the first radiation dose percentage data, recorded as a first data interval;

[0052] The level corresponding to the first data interval is obtained as the marking level of the corresponding radiation dose monitoring point.

[0053] As an optional technical solution, the real-time image data and the original image data are processed to obtain a second processing result, including:

[0054] Integrate and crop the original image data to obtain an original image of a single sub-region, which is recorded as a first original image;

[0055] Acquire the real-time image data of a single sub-region and perform integration and cropping processing to obtain a corresponding real-time image, which is recorded as a first real-time image;

[0056] Determine a plurality of feature points in the first real-time image, and based on all the feature points, obtain a corresponding region image in the first original image, recorded as a first region image;

[0057] The first real-time image is matched with the first regional image. If the match is successful, no action is taken. If the match fails, three-dimensional point cloud data of the area corresponding to the first regional image is obtained. Based on the three-dimensional point cloud data, obstacles in the area corresponding to the first regional image are modeled, and the A* algorithm is used to calculate the shortest path for the drone to pass through the obstacle.

[0058] As an optional technical solution, based on the first processing result and the second processing result, adjusting the first flight parameter and the first inspection path in real time includes:

[0059] Based on the first processing result, obtaining a classification level of any radiation dose monitoring point, adjusting the flight speed and the flight altitude in the first flight parameter based on the classification level, and transmitting the first coordinate data of all second radiation dose monitoring points passing through the second mark back to the ground control terminal;

[0060] Based on the second processing result, the shortest path for the drone to pass through the obstacle is obtained to obtain a fourth acquisition result, and based on the fourth acquisition result, the first inspection path is adjusted in real time.

[0061] One or more technical solutions provided by the present invention have at least the following technical effects or advantages:

[0062] The present invention discloses a nuclear radiation environment monitoring system based on an unmanned aerial vehicle. The entire area to be monitored is divided into multiple sub-areas by an initialization unit, and multiple radiation dose monitoring points are set in each sub-area; the flight parameters and inspection paths of the unmanned aerial vehicle are set based on the coordinate data of the radiation dose monitoring points by a parameter setting unit, and the radiation monitoring of the entire area to be monitored is converted into radiation monitoring of multiple radiation dose monitoring points in multiple sub-areas; the radiation dose data of each radiation dose monitoring point is collected and processed by a monitoring unit to obtain a first processing result; the real-time image is obtained by an image unit and processed with the original image to obtain a second processing result; finally, the flight parameters are adjusted in real time based on the first processing result by a parameter adjustment unit, and the inspection paths are adjusted in real time based on the second processing result. The present invention not only ensures that the unmanned aerial vehicle works within a safe range as much as possible, but also ensures the accuracy and real-time performance of radiation monitoring data collection.

[0063] The present invention discloses a first method for generating an inspection path of an unmanned aerial vehicle. The shortest path of the unmanned aerial vehicle is generated by repeatedly using the Dijkstra algorithm. Specifically, the center point of each sub-area is obtained, and all the center points are placed in a grid map marked with longitude and latitude. On the premise of determining a starting node and a target node, the Dijkstra algorithm is used to traverse all the center points to generate the shortest path from the starting node to the target node. Each center point corresponds to a single sub-area, so the shortest path from the starting node to the target node is the flight sequence of all the sub-areas. Based on the flight sequence, the Dijkstra algorithm is used to process all radiation dose monitoring points in a single sub-area, and a definition method for setting a starting monitoring point and a target monitoring point in a single sub-area is used. That is, the shortest path of the unmanned aerial vehicle passing through all the radiation dose monitoring points is generated by repeatedly using the Dijkstra algorithm as the first inspection path of the unmanned aerial vehicle.

[0064] The present invention performs primary and secondary judgments on all radiation dose data collected from a single sub-area, wherein the primary judgment calculates the radiation dose percentage data of a single radiation dose monitoring point through a first formula, and based on the radiation dose percentage data, grades and marks the corresponding radiation dose monitoring points; the secondary judgment is to obtain the radiation dose monitoring point corresponding to the maximum value of the radiation dose data in the single sub-area as the first radiation dose monitoring point, simulate the radiation diffusion of the radiation source corresponding to the first radiation dose monitoring point through the constructed radiation diffusion model, output the simulated radiation dose data curve graph of the remaining radiation dose monitoring points changing with time, obtain the change curve graph of the radiation dose data of the remaining radiation dose monitoring points within a preset time period, and match it with the corresponding simulated radiation dose data curve graph based on the starting point of the change curve graph, and judge whether there is a new radiation source in the partially shielded area at the remaining radiation dose monitoring points through the matching results.

[0065] The present invention collects real-time image data and original image data for processing to determine whether there are new obstacles in the preset area. If so, the corresponding three-dimensional point cloud data is obtained to model the obstacle, and then the A* algorithm is used to calculate the shortest path for the drone to pass through the obstacle, thereby optimizing and adjusting the drone's inspection path. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of the present invention, and do not constitute a limitation on the embodiments of the present invention;

[0067] Figure 1 It is a schematic diagram of the composition of a nuclear radiation environment monitoring system based on an unmanned aerial vehicle in the present invention. DETAILED DESCRIPTION

[0068] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0069] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those within the scope of this description. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0070] Example

[0071] Please refer to Figure 1 , Figure 1 The present invention is a schematic diagram of a nuclear radiation environment monitoring system based on an unmanned aerial vehicle, wherein the monitoring system comprises:

[0072] Initialization unit: acquiring multidimensional data and original image data of the area to be monitored, dividing the area to be monitored into a plurality of sub-areas based on the multidimensional data, each of which is provided with a plurality of radiation dose monitoring points, and recording the first coordinate data of each radiation dose monitoring point into a preset data table;

[0073] A parameter setting unit: based on the data in the preset data table, sets the first flight parameter of the UAV, and generates a first inspection path of the UAV using a first method;

[0074] Monitoring unit: the UAV collects and processes radiation dose data for each sub-area in turn based on the first flight parameter and the first inspection path to obtain a first processing result;

[0075] Image unit: the UAV obtains real-time image data of each sub-area during flight, and processes the real-time image data and the original image data to obtain a second processing result;

[0076] Parameter adjustment unit: Based on the first processing result and the second processing result, the first flight parameter and the first inspection path are adjusted in real time, and the UAV monitors the remaining area in the area to be monitored based on the adjusted first flight parameter and the first inspection path.

[0077] The specific embodiments of the present invention are as follows:

[0078] Initialization unit: obtain multidimensional data (such as environmental monitoring data, spatial distribution data and trajectory data, etc.) and original image data (such as aerial survey images, etc.) of the area to be monitored, divide the area to be monitored into multiple sub-areas through the multidimensional data, and set a number of radiation dose monitoring points in each sub-area, and record the first coordinate data of each radiation dose monitoring point to a preset data table. This embodiment provides a method for dividing the area to be monitored into sub-areas, specifically:

[0079] Collect multi-dimensional data in the area to be monitored, extract personnel trajectory data from the multi-dimensional data and generate trajectory information;

[0080] Extracting environmental monitoring data, spatial distribution data and nuclear equipment distribution data from the multidimensional data in sequence to obtain extraction results;

[0081] Based on the trajectory information and the extraction result, the area to be monitored is divided into a plurality of sub-areas.

[0082] Among them, by integrating the geographical characteristics (spatial distribution data), equipment characteristics (environmental monitoring data and nuclear equipment distribution data) and human characteristics (personnel trajectory data) of the area to be monitored, the entire area to be monitored is divided into sub-areas, which not only facilitates monitoring, but also can perform preliminary positioning in the shortest time when a radiation source leakage is detected, that is, determine the preliminary area of ​​the emitted radiation leakage.

[0083] This embodiment provides a method for setting a radiation dose monitoring point in each sub-area, specifically:

[0084] Acquire the nuclear equipment distribution data, radiation source type data and regional area data in any sub-region to obtain a first acquisition result;

[0085] Based on the first acquisition result, a first number of radiation dose monitoring points are arranged in the corresponding sub-area, and based on all the radiation dose monitoring points in the single sub-area, radiation monitoring coverage of the entire sub-area is completed.

[0086] Among them, by obtaining the nuclear equipment distribution data, radiation source type data and area data in each sub-area, the number of radiation dose monitoring points to be arranged in each sub-area is determined to ensure that the radiation monitoring coverage of a single sub-area is completed with the minimum number of radiation dose monitoring points.

[0087] Parameter setting unit: The UAV completes the radiation monitoring of the entire area to be monitored by collecting the radiation dose data of all radiation dose monitoring points. Therefore, it is necessary to set the first flight parameters (such as speed, altitude, angle, etc.) of the UAV based on the coordinate data of all radiation dose monitoring points in the preset data table, and use the first method to generate the first inspection path of the UAV;

[0088] The first method includes:

[0089] Extract the center point of each sub-area as a node, and record the second coordinate data of each node;

[0090] Constructing a grid diagram with longitude as the horizontal coordinate and latitude as the vertical coordinate, and adding all nodes to the grid diagram based on all second coordinate data;

[0091] Based on the trellis graph, a starting node and a target node are determined, and a Dijkstra algorithm is used to traverse all nodes in the trellis graph to obtain the shortest path from the starting node to the target node;

[0092] Based on the shortest path, the inspection order of the drone for all sub-areas is obtained, and the second method is used to plan the inspection path for each sub-area until all radiation dose monitoring points in the area to be monitored are covered.

[0093] The second method includes:

[0094] Obtain any sub-area as a first sub-area, and based on the inspection sequence, obtain an adjacent inspection sub-area of ​​the first sub-area as a second sub-area;

[0095] Obtaining a radiation dose monitoring point in the first sub-region that is farthest from any radiation dose monitoring point in the second sub-region, and recording it as a starting monitoring point of the first sub-region;

[0096] Acquire a radiation dose monitoring point in the first sub-region that is closest to any radiation dose monitoring point in the second sub-region, and record it as a target monitoring point in the first sub-region;

[0097] Based on the starting node and the target node of the first sub-region, all radiation dose monitoring points in the first sub-region are traversed using the Dijkstra algorithm to obtain the shortest path from the starting monitoring point to the target monitoring point in the first sub-region.

[0098] Among them, the core idea of ​​the Dijkstra algorithm is to adopt the strategy of the greedy algorithm under the premise of determining the starting point and the end point, and traverse the adjacent nodes of the vertex closest to the starting point and not visited each time until it is expanded to the end point. This embodiment uses the Dijkstra algorithm repeatedly. The first time it is used for all sub-areas to generate the flight order of all sub-areas, and then it is used for all radiation dose monitoring points in each sub-area to generate the flight path of all radiation dose monitoring points in a single sub-area. Based on the flight order of all sub-areas and the flight path of all radiation dose monitoring points in a single sub-area, the shortest path of the area to be monitored is generated as the first inspection path of the drone. It should be noted that the setting of the first flight parameter is set according to relevant industry standards and the safe working height of the drone. It is a relatively mature technology for technicians in this field, and this embodiment will not be specifically expanded.

[0099] Monitoring unit: The UAV collects and processes radiation dose data for each sub-area in turn based on the first flight parameter and the first inspection path to obtain a first processing result, which is specifically:

[0100] Obtain any sub-region as the third sub-region, and obtain radiation dose data of all radiation dose monitoring points in the third sub-region, and put them into the first set;

[0101] A first-level determination is performed on all radiation dose data in the first set, specifically:

[0102] It is determined whether the corresponding radiation dose data exceeds the preset value. If not, no action is taken. If yes, a first formula is used to calculate the radiation dose percentage data in the corresponding radiation dose monitoring point. Based on the radiation dose percentage data, a first classification mark is made for all corresponding radiation dose monitoring points. The first formula includes:

[0103]

[0104] η% is the radiation dose percentage data of a single radiation dose monitoring point, μ i is the radiation dose data of a single radiation monitoring point, and A is the preset value;

[0105] Perform secondary determination on all radiation dose data in the first set, specifically:

[0106] Obtain all radiation dose monitoring points in the first set where the radiation dose data exceeds the preset value, and place them in the second set;

[0107] Acquire a radiation dose monitoring point corresponding to the maximum value of the radiation dose data in the second set, record it as a first radiation dose monitoring point, acquire radiation source type data and radiation dose data of the first radiation dose monitoring point, and obtain a second acquisition result;

[0108] Acquire all radiation dose monitoring points in the second set except the first radiation dose monitoring point, and record them as second radiation dose monitoring points;

[0109] Acquire the first coordinate data of all second radiation dose monitoring points, put them into a coordinate set, and obtain a third acquisition result;

[0110] Constructing a radiation diffusion model and training it, inputting the second acquisition result and the third acquisition result into the trained radiation diffusion model, and outputting a simulated radiation dose data curve graph of each second radiation dose monitoring point in the coordinate set changing with time;

[0111] Obtain a change curve graph of the radiation dose data of each second radiation dose monitoring point within a preset time period, and match the corresponding simulated radiation dose data curve graph based on the radiation dose data at the starting point of the change curve graph. If the match is successful, no action is taken. If the match fails, the corresponding second radiation dose monitoring point is marked as a second mark.

[0112] Based on the radiation dose percentage data, all corresponding radiation dose monitoring points are graded and marked including:

[0113] Acquire historical data of the radiation dose percentage data within a preset time period, and divide the radiation dose percentage data into data intervals based on the historical data, and set a corresponding level for each data interval;

[0114] Obtaining radiation dose percentage data of any radiation dose monitoring point, recorded as first radiation dose percentage data;

[0115] Obtaining a data interval of the first radiation dose percentage data, recorded as a first data interval;

[0116] The level corresponding to the first data interval is obtained as the marking level of the corresponding radiation dose monitoring point.

[0117] Among them, this embodiment provides a secondary determination of all radiation dose data in a single sub-area, the primary determination is for the radiation dose data of a single radiation dose monitoring point, and the secondary determination is for the radiation dose data of all radiation dose monitoring points.

[0118] The specific first-level judgment is: calculate the radiation dose percentage data of each radiation dose monitoring point through the first formula, and based on the radiation dose percentage data, grade and mark the corresponding radiation dose monitoring points. The larger the radiation dose percentage data, the higher the corresponding marking level, indicating that the radiation dose of the corresponding radiation dose monitoring point is higher, so the flight parameters of the corresponding UAV need to be adjusted.

[0119] The specific secondary judgment is: by obtaining the radiation dose monitoring point corresponding to the maximum value of the radiation dose data in a single sub-area as the first radiation dose monitoring point, the radiation diffusion of the radiation source corresponding to the first radiation dose monitoring point is simulated through the constructed radiation diffusion model, and the simulated radiation dose data curve graph of the remaining radiation dose monitoring points changing with time is output, and the change curve graph of the radiation dose data of the remaining radiation dose monitoring points within the preset time period is obtained, and based on the starting point of the change curve graph, it is matched with the corresponding simulated radiation dose data curve graph. If the match is successful, it means that there is a new radiation source at the corresponding radiation dose monitoring point, but due to the existence of a local shielding area, the radiation dose data collected by the radiation dose monitoring point is lower than the actual value. Such radiation dose monitoring points need to be marked for the second time, and the marking results are transmitted back to the ground control terminal to facilitate the monitoring personnel to take follow-up measures, such as using drones for secondary collection of such radiation dose monitoring points.

[0120] Image unit: During the flight, the UAV obtains real-time image data of each sub-area, and processes the real-time image data and the original image data to obtain a second processing result, which is specifically:

[0121] Integrate and crop the original image data to obtain an original image of a single sub-region, which is recorded as a first original image;

[0122] Acquire the real-time image data of a single sub-region and perform integration and cropping processing to obtain a corresponding real-time image, which is recorded as a first real-time image;

[0123] Determine a plurality of feature points in the first real-time image, and based on all the feature points, obtain a corresponding region image in the first original image, recorded as a first region image;

[0124] The first real-time image is matched with the first regional image. If the match is successful, no action is taken. If the match fails, three-dimensional point cloud data of the area corresponding to the first regional image is obtained. Based on the three-dimensional point cloud data, obstacles in the area corresponding to the first regional image are modeled, and the A* algorithm is used to calculate the shortest path for the drone to pass through the obstacle.

[0125] Among them, the A* algorithm is an efficient path finding algorithm that can find the shortest path from the starting point to the end point in a scene with obstacles. This embodiment collects real-time image data and original image data for processing to determine whether there are new obstacles in the preset area. If so, the corresponding three-dimensional point cloud data is obtained, the obstacle is modeled, and then the A* algorithm is used to calculate the shortest path for the drone to pass through the obstacle, thereby optimizing and adjusting the inspection path of the drone.

[0126] Parameter adjustment unit: Based on the first processing result, the first flight parameter is adjusted in real time; based on the second processing result, the first inspection path is adjusted in real time, and the UAV monitors the remaining area in the area to be monitored based on the adjusted first flight parameter and first inspection path.

[0127] Based on the first processing result and the second processing result, adjusting the first flight parameter and the first inspection path in real time includes:

[0128] Based on the first processing result, obtaining a classification level of any radiation dose monitoring point, adjusting the flight speed and the flight altitude in the first flight parameter based on the classification level, and transmitting the first coordinate data of all second radiation dose monitoring points passing through the second mark back to the ground control terminal;

[0129] Based on the second processing result, the shortest path for the drone to pass through the obstacle is obtained to obtain a fourth acquisition result, and based on the fourth acquisition result, the first inspection path is adjusted in real time.

[0130] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0131] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A nuclear radiation environment monitoring system based on drones, characterized in that: The monitoring system comprises: Initialization unit: acquiring multidimensional data and original image data of the area to be monitored, dividing the area to be monitored into a plurality of sub-areas based on the multidimensional data, each of which is provided with a plurality of radiation dose monitoring points, and recording the first coordinate data of each radiation dose monitoring point into a preset data table; A parameter setting unit: based on the data in the preset data table, sets the first flight parameter of the UAV, and generates a first inspection path of the UAV using a first method; Monitoring unit: the UAV collects and processes radiation dose data for each sub-area in turn based on the first flight parameter and the first inspection path to obtain a first processing result; Image unit: the UAV obtains real-time image data of each sub-area during flight, and processes the real-time image data and the original image data to obtain a second processing result; Parameter adjustment unit: Based on the first processing result, the first flight parameter is adjusted in real time; based on the second processing result, the first inspection path is adjusted in real time, and the UAV monitors the remaining area in the area to be monitored based on the adjusted first flight parameter and first inspection path.

2. The nuclear radiation environment monitoring system based on drone according to claim 1 is characterized in that: Based on the multidimensional data, dividing the area to be monitored into a plurality of sub-areas comprises: Collect multi-dimensional data in the area to be monitored, extract personnel trajectory data from the multi-dimensional data and generate trajectory information; Extracting environmental monitoring data, spatial distribution data and nuclear equipment distribution data from the multidimensional data in sequence to obtain extraction results; Based on the trajectory information and the extraction result, the area to be monitored is divided into a plurality of sub-areas.

3. The nuclear radiation environment monitoring system based on drone according to claim 2 is characterized in that: Several radiation dose monitoring points are set up in each sub-area, including: Acquire the nuclear equipment distribution data, radiation source type data and regional area data in any sub-region to obtain a first acquisition result; Based on the first acquisition result, a first number of radiation dose monitoring points are arranged in the corresponding sub-area, and based on all the radiation dose monitoring points in the single sub-area, radiation monitoring coverage of the single sub-area is completed.

4. The nuclear radiation environment monitoring system based on drone according to claim 1 is characterized in that: The first method comprises: Extract the center point of each sub-area as a node, and record the second coordinate data of each node; Constructing a grid diagram with longitude as the horizontal coordinate and latitude as the vertical coordinate, and adding all nodes to the grid diagram based on all second coordinate data; Based on the trellis graph, a starting node and a target node are determined, and a Dijkstra algorithm is used to traverse all nodes in the trellis graph to obtain the shortest path from the starting node to the target node; Based on the shortest path, the inspection order of the drone for all sub-areas is obtained, and the second method is used to plan the inspection path for each sub-area until all radiation dose monitoring points in the area to be monitored are covered.

5. The nuclear radiation environment monitoring system based on drone according to claim 4 is characterized in that: The second method comprises: Obtain any sub-area as a first sub-area, and based on the inspection sequence, obtain an adjacent inspection sub-area of ​​the first sub-area as a second sub-area; Obtaining a radiation dose monitoring point in the first sub-region that is farthest from any radiation dose monitoring point in the second sub-region, and recording it as a starting monitoring point of the first sub-region; Acquire a radiation dose monitoring point in the first sub-region that is closest to any radiation dose monitoring point in the second sub-region, and record it as a target monitoring point in the first sub-region; Based on the starting node and the target node of the first sub-region, all radiation dose monitoring points in the first sub-region are traversed using the Dijkstra algorithm to obtain the shortest path from the starting monitoring point to the target monitoring point in the first sub-region.

6. The nuclear radiation environment monitoring system based on drone according to claim 1 is characterized in that: Collecting and processing radiation dose data for each sub-region in turn, and obtaining a first processing result including: Obtain any sub-region as the third sub-region, and obtain radiation dose data of all radiation dose monitoring points in the third sub-region, and put them into the first set; A first-level determination is performed on all radiation dose data in the first set, specifically: It is determined whether the corresponding radiation dose data exceeds the preset value. If not, no action is taken. If yes, a first formula is used to calculate the radiation dose percentage data in the corresponding radiation dose monitoring point. Based on the radiation dose percentage data, a first classification mark is made for all corresponding radiation dose monitoring points. The first formula includes: η% is the radiation dose percentage data of a single radiation dose monitoring point, μ i is the radiation dose data of a single radiation monitoring point, and A is the preset value; Perform secondary determination on all radiation dose data in the first set, specifically: Obtain all radiation dose monitoring points in the first set where the radiation dose data exceeds the preset value, and place them in the second set; Acquire a radiation dose monitoring point corresponding to the maximum value of the radiation dose data in the second set, record it as a first radiation dose monitoring point, acquire radiation source type data and radiation dose data of the first radiation dose monitoring point, and obtain a second acquisition result; Acquire all radiation dose monitoring points in the second set except the first radiation dose monitoring point, and record them as second radiation dose monitoring points; Acquire the first coordinate data of all second radiation dose monitoring points, put them into a coordinate set, and obtain a third acquisition result; Constructing a radiation diffusion model and training it, inputting the second acquisition result and the third acquisition result into the trained radiation diffusion model, and outputting a simulated radiation dose data curve graph of each second radiation dose monitoring point in the coordinate set changing with time; Obtain a change curve graph of the radiation dose data of each second radiation dose monitoring point within a preset time period, and match the corresponding simulated radiation dose data curve graph based on the radiation dose data at the starting point of the change curve graph. If the match is successful, no action is taken. If the match fails, the corresponding second radiation dose monitoring point is marked as a second mark.

7. The nuclear radiation environment monitoring system based on drone according to claim 6 is characterized in that: Based on the radiation dose percentage data, all corresponding radiation dose monitoring points are graded and marked including: Acquire historical data of the radiation dose percentage data within a preset time period, and divide the radiation dose percentage data into data intervals based on the historical data, and set a corresponding level for each data interval; Obtaining radiation dose percentage data of any radiation dose monitoring point, recorded as first radiation dose percentage data; Obtaining a data interval of the first radiation dose percentage data, recorded as a first data interval; The level corresponding to the first data interval is obtained as the marking level of the corresponding radiation dose monitoring point.

8. The nuclear radiation environment monitoring system based on drone according to claim 6 is characterized in that: Processing the real-time image data and the original image data to obtain a second processing result includes: Integrate and crop the original image data to obtain an original image of a single sub-region, which is recorded as a first original image; Acquire the real-time image data of a single sub-region and perform integration and cropping processing to obtain a corresponding real-time image, which is recorded as a first real-time image; Determine a plurality of feature points in the first real-time image, and based on all the feature points, obtain a corresponding region image in the first original image, recorded as a first region image; The first real-time image is matched with the first regional image. If the match is successful, no action is taken. If the match fails, three-dimensional point cloud data of the area corresponding to the first regional image is obtained. Based on the three-dimensional point cloud data, obstacles in the area corresponding to the first regional image are modeled, and the A* algorithm is used to calculate the shortest path for the drone to pass through the obstacle.

9. The nuclear radiation environment monitoring system based on drone according to claim 8, characterized in that: Based on the first processing result and the second processing result, adjusting the first flight parameter and the first inspection path in real time includes: Based on the first processing result, obtaining a classification level of any radiation dose monitoring point, adjusting the flight speed and the flight altitude in the first flight parameter based on the classification level, and transmitting the first coordinate data of all second radiation dose monitoring points passing through the second mark back to the ground control terminal; Based on the second processing result, the shortest path for the drone to pass through the obstacle is obtained to obtain a fourth acquisition result, and based on the fourth acquisition result, the first inspection path is adjusted in real time.

Images