Radioactive substance multi-point synchronous detection and identification method and system

By constructing a spatial adjacency matrix and using edge computing technology, multi-point radiation data can be collected and processed in real time, solving the problems of weak signal identification and leakage source location in traditional radioactive material monitoring systems, and achieving efficient and intelligent radioactive material detection and identification.

CN120705611AActive Publication Date: 2025-09-26ZHEJIANG JUNAN INSPECTION & TESTING TECH CO LTD

Patent Information

Application Number
CN202510753210.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-06
Publication Date
2025-09-26
Estimated Expiration
2045-06-06

AI Technical Summary

Technical Problem

Traditional radioactive material monitoring systems lack effective suppression of short-term fluctuations and electronic noise in the environment, are unable to accurately identify weak abnormal signals, and lack temporal trend modeling of historical data, resulting in false alarms or missed alarms. There is a lack of information fusion and spatial collaborative judgment between multi-node monitoring, making it difficult to achieve accurate positioning and response linkage of the location and intensity of radiation sources.

Method used

By collecting multi-point radiation data in real time for preprocessing, constructing a spatial adjacency matrix, estimating local spatial gradients, calculating the degree of anomaly, and conducting collaborative anomaly assessment, the location and intensity of the leakage source are inferred based on the total fitting error value, implementing graded early warning and multi-node cross-confirmation measures, and combining edge computing with cloud monitoring for data visualization analysis and event processing.

Benefits of technology

It achieves early identification and precise positioning of radioactive material leaks, reduces false alarms and missed alarms, improves detection credibility and response efficiency, and supports full-process closed-loop management and intelligent support.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120705611A_ABST
    Figure CN120705611A_ABST
Patent Text Reader

Abstract

The invention discloses a radioactive substance multi-point synchronous detection and identification method and system, and relates to the technical field of radioactive substance monitoring. Comprising the following steps: step 1, collecting multi-point radiation data in real time, and preprocessing and storing the data; step 2, constructing a spatial adjacency matrix, estimating a local spatial gradient, calculating an anomaly degree value, taking optimization measures, and performing collaborative anomaly evaluation on the monitoring nodes; 3, calculating a total fitting error value, reversely deducing a leakage source position and leakage intensity in real time, and taking corresponding measures in real time; 4, abnormal trend identification is carried out, an early warning judgment value is calculated, and graded early warning and multi-node cross confirmation measures are implemented; and 5, receiving and storing various types of data, carrying out visualized analysis on the data, and supporting event processing and feedback. The problems that due to the fact that some devices are good in shielding and have physical obstruction, trace leakage is difficult to detect by a single-point monitor, and the risk of long-term retention pollution exists are solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of radioactive material monitoring, and in particular to a method and system for multi-point synchronous detection and identification of radioactive materials. Background Art

[0002] In scenarios such as public safety, nuclear facility regulation, counterterrorism, and environmental monitoring, the illegal or accidental release of radioactive materials poses a serious threat to human health, ecosystems, and social stability. With the advancement of wireless communications, distributed sensing, and data analysis technologies, the construction of intelligent detection systems based on multi-node synchronous sensing, integrated judgment of abnormal trends, and traceability and location has become a trend.

[0003] For example, the invention patent with publication number CN108089218B discloses a radioactive monitoring system for entering and exiting the control area of ​​a nuclear power plant. The radioactive monitoring system is based on the following arrangement: a changing room and a dose management room are arranged in the sanitary passage, a non-radioactive work area is arranged outside the sanitary passage, and the sanitary passage leads to the radioactive control area; the changing room is arranged in the first area entered in the sanitary passage, and the dose management room is arranged after the changing room and at the boundary between the non-radioactive work area and the radioactive control area; a self-service wardrobe is provided in the changing room, and a self-service duty machine is provided in the dose management room. Both the self-service wardrobe and the self-service duty machine are equipped with a card reading area, connected to a universal Internet network, and interconnected with the nuclear power plant server system; before entering the changing room, staff must configure a dedicated personal dose intelligent terminal and must carry the terminal at all times when entering and exiting the sanitary passage or working in the control area and non-control area.

[0004] For example, the invention patent with publication number CN102713676B discloses anomaly detection of radioactive signatures. In this method, a target gamma-ray spectrum is obtained from a target, and a target data set is prepared based on the target gamma-ray spectrum. The data set includes a plurality of intensity values, each intensity value is associated with an energy bin, and the energy bin represents a gamma-ray energy or a gamma-ray energy range in the target gamma-ray spectrum. The target data set is then preprocessed and projected into a principal component space, which contains a preprocessed database projected into the principal component space. The distance between the projected preprocessed target data set and one or more clusters of the projected preprocessed database is then determined in the principal component space, and the distance is compared with a predetermined threshold distance to determine whether anomalous radioactive material is present in the target.

[0005] However, in the process of implementing the technical solutions of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems: On the one hand, traditional technologies lack effective suppression of short-term fluctuations and electronic noise in the environment, making them unable to accurately identify weak abnormal signals, which can easily lead to false alarms or missed reports. On the other hand, traditional systems lack temporal trend modeling of historical data and are unable to identify abnormal deviations based on periodic background changes. Furthermore, there is a lack of effective information fusion and spatial collaborative judgment mechanisms between multi-node monitoring, resulting in isolated detection and judgment and poor spatial consistency. Furthermore, traditional systems generally lack the ability to invert the location and intensity of radioactive sources, making it difficult to accurately locate and coordinate responses to leak sources in complex environments.

[0006] Therefore, in order to solve the above problems, there is an urgent need for a method and system for multi-point synchronous detection and identification of radioactive materials. Summary of the Invention

[0007] Technical problems solved In response to the shortcomings of the existing technology, the present invention provides a multi-point synchronous detection and identification method and system for radioactive materials, which solves the problem that trace leaks are difficult to be detected by single-point monitors due to the good shielding and physical barriers of equipment such as radioactive drug cold storage or shielded storage cabinets, and there is a risk of long-term contamination.

[0008] Technical Solution To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for multi-point synchronous detection and identification of radioactive materials, including: step one, real-time collection of multi-point radiation data, data preprocessing, and real-time storage of multi-point radiation data; step two, constructing a spatial adjacency matrix, estimating local spatial gradients, calculating abnormality levels, taking optimization measures in real time according to the abnormality levels, and performing collaborative abnormality assessment on monitoring nodes; step three, calculating a total fitting error value based on multi-point radiation data, inferring the leakage source location and leakage intensity in real time according to the total fitting error value, and taking corresponding measures in real time; step four, aggregating multi-point radiation data for real-time abnormal trend identification, calculating early warning judgment values, and implementing hierarchical early warning and multi-node cross-confirmation measures; step five, receiving and storing various types of data, performing visual analysis of the data, and supporting event processing and feedback.

[0009] Furthermore, the specific process of real-time collection of multi-point radiation data, data preprocessing, and real-time storage of multi-point radiation data is as follows: multiple high-sensitivity monitoring nodes are deployed in the radiation source storage area according to the site layout, potential leakage points and ventilation paths. Each monitoring node is equipped with a Geiger counter, a scintillation counter and a semiconductor detector, and a unique identification code is set for each monitoring node to collect multi-point radiation data in real time. The multi-point radiation data includes: the radiation dose rate and count rate data of the surrounding environment, as well as the three-dimensional coordinates and equipment parameters of each monitoring node; the real-time multi-point radiation data of each monitoring node is denoised using a moving average filter, the background dose is corrected, the stable baseline is eliminated, and standardization and normalization are performed; the multi-point radiation data is uploaded to the multi-point radiation database, and the multi-point radiation data is sent to the edge computing device through the message queue telemetry transmission protocol. If a network anomaly occurs, the monitoring node automatically caches the data and supports remote firmware upgrades and regular calibration.

[0010] Furthermore, a spatial adjacency matrix is ​​constructed, local spatial gradients are estimated, and the degree of anomaly is calculated. The specific process of taking real-time optimization measures based on the degree of anomaly is as follows: a spatial adjacency matrix is ​​constructed based on the three-dimensional coordinates recorded when each monitoring node is deployed; the Euclidean distance between all monitoring nodes is calculated. When the distance between any two monitoring nodes is less than three meters, they are considered neighbors, and the adjacency relationship between the two neighboring monitoring nodes is recorded; based on the spatial adjacency matrix, the gradient component in the three-dimensional direction is calculated using the difference in radiation dose rate and the difference in three-dimensional coordinates between the monitoring nodes; the gradient estimation method adopts a weighted difference form: the influence of each neighbor node on the monitoring node is weighted according to the inverse square of the distance, and the closer the distance, the greater the weight; the gradient result is updated once per second based on the current radiation dose rate, and it is determined whether there is a trend of increasing dose in a certain direction in a certain area; the historical radiation dose rate data of each monitoring node is subjected to sliding filtering processing, and a fixed window sliding average method is used to smooth out short-term fluctuations caused by electronic noise, environmental disturbances and individual transient events to obtain the filtered dose value at the current moment; a time period-based daily background model is established for each monitoring node: the same period of the past three consecutive days is used to calculate the gradient component in the three-dimensional direction; The corresponding historical filtered dose value is extracted, and a stable background mean is obtained by calculating the mean value as the normal state baseline of the monitoring node; and the standard deviation is calculated based on the filtered dose value of the same period in the past three consecutive days to obtain the background standard deviation; the filtered dose value of the i-th monitoring node at time t is obtained, and the background mean and background standard deviation of the i-th monitoring node at time t are obtained at the same time; the filtered dose value of the i-th monitoring node at time t is subtracted from the background mean and then divided by the sum of the background standard deviation and a constant 1 to obtain the standard deviation term, and the standard deviation term is subtracted from the abnormal threshold weight factor to obtain the abnormal degree of the i-th monitoring node at time t. degree value; perform a maximum function operation on the abnormality degree value: if the abnormality degree value is less than zero, the abnormality degree value is set to zero; if the abnormality degree value is not less than zero, the calculation result is the abnormality degree value; when the abnormality degree values ​​of multiple nodes in a certain area increase abnormally, shorten the sliding window, automatically send an on-site review prompt, and call the regional ventilation system to dilute potential radioactive substances in advance; if a node has a high abnormality degree value for a long time and the neighboring nodes do not respond, start the sensor self-diagnosis program; mark it as a "suspected false alarm" state, initiate remote self-calibration, automatically analyze historical performance and error trends, and automatically evaluate whether to replace the equipment.

[0011] Furthermore, the specific process of collaborative anomaly evaluation of monitoring nodes is as follows: obtain the anomaly degree values ​​of the i-th monitoring node and the j-th neighbor node at time t; obtain the spatial adjacency matrix, and filter the neighbor nodes of the spatial adjacency matrix to obtain the neighbor node set of the i-th monitoring node, and obtain the length of the neighbor node set to obtain the number of neighbor nodes; sum the anomaly degree values ​​of all neighbor nodes at time t based on the number of neighbor nodes, and then divide the sum by the number of neighbor nodes to obtain the neighborhood average anomaly value, multiply the neighborhood average anomaly value by the neighborhood fusion weight factor, and then add it to the anomaly degree value of the i-th monitoring node at time t to obtain the collaborative anomaly evaluation value; compare the collaborative anomaly evaluation value with the first and second level anomaly thresholds in real time. When the collaborative anomaly evaluation value is less than or equal to the first level anomaly threshold, it is considered that the radiation level is within the normal background fluctuation range, and routine monitoring is continued to keep the equipment and data normal. Collection, no intervention is required; when the collaborative anomaly assessment value is greater than the first-level anomaly threshold and less than or equal to the second-level anomaly threshold, it is considered that there is a trace leak or equipment anomaly, and the collaborative anomaly degree value will be uploaded to the background to start higher-frequency data collection; automatic monitoring of the abnormal monitoring node and the status and environmental parameters of the surrounding equipment. If it is confirmed that the anomaly is valid and is in a poorly ventilated and high-risk area, the ventilation system will be automatically started, local sound and light prompts will be issued, and protection warning instructions will be issued to the on-site area; when the collaborative anomaly assessment value is greater than the second-level anomaly threshold, it is considered that the radiation level is abnormal and there is a risk of leakage. The collaborative anomaly degree value will be uploaded to the background, the on-site emergency plan will be immediately started, and the suspected leakage area will be isolated; remote and on-site synchronous alarms will be issued, and abnormal prompts will be automatically pushed; portable high-precision detectors will be used for precise positioning and confirmation of the leak source; and cleaning and repair instructions will be pushed according to the degree of leakage, and the execution progress and feedback will be recorded at the same time.

[0012] Furthermore, the total fitting error value is calculated based on the multi-point radiation data, and the specific process of inferring the leakage source position and leakage intensity in real time based on the total fitting error value is as follows: obtain the three-dimensional coordinates of each monitoring node and the corresponding radiation dose rate, and perform abnormal point filtering according to the equipment parameters; construct a dose gradient field through spatial difference based on the three-dimensional coordinates and real-time radiation dose rate of the monitoring node, and select the monitoring node position with the largest radiation dose rate as the initial leakage source position according to the dose gradient field; according to the selected maximum radiation dose rate, the distance between the initial leakage source position and the current monitoring node, and infer the radiation dose rate of the leakage source position as the initial leakage intensity through the real-time radiation dose rate of the monitoring node; based on the information criterion and spatial clustering fusion algorithm, perform spatial clustering analysis on the abnormal degree values ​​of the radiation dose rates of all monitoring nodes, and preliminarily infer the number of potential source points by identifying the high radiation dose rate abnormal clustering areas, and under different hypothetical source numbers, combine the Bayesian information criterion algorithm to perform leakage source inversion positioning calculation analysis respectively, and select the source point number with the smallest Bayesian information criterion value as the current scenario The optimal total number of leakage sources is obtained; the total number of monitoring nodes is obtained by obtaining the number of detectors deployed; the three-dimensional coordinates of the i-th monitoring node and the radiation dose rate measured at the i-th monitoring node are obtained; the initial leakage source position and initial leakage intensity are obtained, the square of the Euclidean distance from the three-dimensional coordinates of the i-th monitoring node to the initial leakage source position is calculated and added with a constant one, and then the initial leakage intensity is divided by the sum to obtain the leakage source contribution value; based on the total number of leakage sources, the leakage source contribution values ​​of all leakage sources are accumulated to obtain the estimated dose value of the i-th monitoring node; the radiation dose rate of the i-th monitoring node is subtracted from the estimated dose value of the i-th monitoring node and then squared to obtain the squared error term; based on the total number of monitoring nodes, the squared error terms of all monitoring nodes are summed to obtain the initial total fitting error value of K leakage sources; based on the initial total fitting error value of the K leakage sources, the leakage source position and leakage intensity are adjusted using a nonlinear least squares optimization algorithm to gradually reduce the total fitting error value until the total fitting error value is less than the error threshold, and then the current k-th leakage source position and the leakage intensity of the k-th leakage source are obtained by reverse calculation.

[0013] Furthermore, the specific process of taking corresponding measures in real time is as follows: real-time comparison of the total fitting error value and the error threshold; when the total fitting error value is less than or equal to the error threshold, the leakage source positioning result is considered to be credible and directly used for rapid response and on-site disposal of the leakage source; the three-dimensional coordinate position of the leakage source and the leakage intensity as well as the total fitting error value are uploaded to the monitoring platform, and the leakage emergency plan module is triggered in real time; the risk level is automatically assigned, and regional sealing, ventilation, sound and light alarms and protection instructions are executed in conjunction, and the leakage evolution process is continuously and dynamically monitored; when the total fitting error value is greater than the error threshold, the leakage source positioning result is considered to be unreliable, and a "fitting failure" prompt is output, and a reminder to check data quality and equipment status is automatically pushed; check whether there are abnormal multi-point radiation data and monitoring sensor failures, perform data cleaning and equipment calibration; evaluate the existing monitoring node layout; recalculate the total fitting error value after adjustment until the total fitting error value meets the effective judgment.

[0014] Furthermore, multi-point radiation data is aggregated to identify real-time abnormal trends, and the specific process of calculating the early warning judgment value is as follows: the edge computing device periodically collects multi-point radiation data transmitted by each monitoring node at a high frequency, establishes a rolling cache, and saves at least one hour of historical multi-point radiation data; and the cached multi-point radiation data is strictly synchronized using a timestamp; obtains the radiation dose rate of the i-th monitoring node and the j-th neighbor node at time t, obtains the background mean of the i-th monitoring node and the j-th neighbor node, obtains the neighbor node set of the i-th monitoring node, and obtains the length of the neighbor node set of the i-th monitoring node to obtain the number of neighbor nodes; calculates the difference between the radiation dose rate of the i-th monitoring node and the background mean of the i-th monitoring node to obtain the normal deviation degree of the monitoring node; calculates the difference between the radiation dose rate of the j-th neighbor node and the background mean of the j-th neighbor node, and based on the number of neighbor nodes, sums all the differences, divides the sum by the number of neighbor nodes, and then multiplies it by the neighbor influence weight factor to obtain the neighbor influence term, and adds the neighbor influence term to the normal deviation degree to obtain the early warning judgment value.

[0015] Furthermore, the specific process for implementing graded warning and multi-node cross-verification measures is as follows: real-time comparison of the warning judgment value with the first- and second-level warning thresholds. When the warning judgment value is less than the first-level warning threshold, it is determined to be normal, and continuous monitoring and regular archiving are carried out without intervention. When the warning judgment value is greater than or equal to the first-level warning threshold and less than the second-level threshold, it is determined to be a slight dose increase, possibly affected by disturbance or initial leakage, and local audio and visual reminders are issued, the radiation dose rate change rate is recorded in real time, and monitoring of key areas is strengthened. When the warning judgment value is greater than or equal to the second-level threshold, it is determined to be a significant abnormality and suspected leakage source activity. The local buzzer and red light alarm are immediately activated to respond, the warning judgment value is uploaded, and mobile detection equipment is automatically dispatched to inspect the abnormal area. The detection data is returned in real time, and the leak source location and emergency response procedures are initiated. If a single node alarms but the neighboring nodes do not respond, the remote alarm will be delayed and marked as "pending confirmation". If the warning judgment values ​​of three or more neighboring nodes are simultaneously greater than the warning threshold and are spatially consistent, it will be upgraded to a "regional leak warning", and the leak source inversion location module will be automatically triggered to initiate positioning.

[0016] Furthermore, the specific process of receiving and storing various types of data, performing visual analysis of the data, and supporting event processing and feedback is as follows: the cloud server receives the monitoring node identification code, radiation dose rate, radiation dose rate change rate, positioning results and timestamp in real time, and stores them uniformly in the time series database; and performs visual analysis based on the multi-point radiation data of the monitoring node; supports multi-level alarms, and pushes notifications to relevant personnel through multiple channels such as SMS, email, and WeChat, supports event processing records and backtracking; introduces machine learning models for intelligent identification and risk assessment of leakage patterns, and automatically generates risk assessment reports on a regular basis.

[0017] The second aspect of the present invention provides a multi-point synchronous detection and identification system for radioactive materials, including: a multi-point synchronous monitoring module, a dose trend collaborative modeling module, a leakage source inversion positioning module, an edge computing and early warning module, and a cloud monitoring and analysis module; wherein the multi-point synchronous monitoring module is used to collect multi-point radiation data in real time, perform data preprocessing, and store the multi-point radiation data in real time; the dose trend collaborative modeling module is used to construct a spatial adjacency matrix, estimate the local spatial gradient, calculate the abnormality degree value, take optimization measures in real time according to the abnormality degree value, and perform collaborative abnormality evaluation on the monitoring nodes; the leakage source inversion positioning module is used to calculate the total fitting error value based on the multi-point radiation data, infer the leakage source position and leakage intensity in real time according to the total fitting error value, and take corresponding measures in real time; the edge computing and early warning module is used to collect multi-point radiation data for real-time abnormal trend identification, calculate the early warning judgment value, and implement hierarchical early warning and multi-node cross-confirmation measures; the cloud monitoring and analysis module is used to receive and store various types of data, perform data visualization analysis, and support event processing and feedback.

[0018] Beneficial effects The present invention has the following beneficial effects: (1) The present invention collects multi-point radiation data in real time and constructs a spatial adjacency matrix to estimate the local spatial gradient and calculate the abnormality value, thereby realizing the collaborative abnormality assessment of the monitoring nodes and timely discovering the potential radioactive leakage trend.

[0019] (2) The present invention constructs a dose gradient field by using multi-point radiation data. By optimizing the calculation of the total fitting error value, the leakage source location and leakage intensity can be inferred. It is also linked with the emergency response mechanism to improve the efficiency of handling leakage incidents.

[0020] (3) The present invention uses edge computing and early warning modules to enable the system to identify real-time abnormal trends, calculate early warning judgment values, and implement hierarchical early warning and multi-node cross-confirmation measures, significantly reducing false alarms and missed alarms and improving the credibility of alarms.

[0021] (4) The present invention can perform visual analysis, event processing and risk assessment on all data through the cloud monitoring and analysis module, identify leakage patterns through machine learning models, and automatically generate risk assessment reports, thus achieving full-process closed-loop management and intelligent support.

[0022] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 The present invention is a flow chart of a method for multi-point simultaneous detection and identification of radioactive materials; Figure 2 This is a structural diagram of a multi-point synchronous detection and identification system for radioactive materials; Figure 3 This is a comparison chart of collaborative anomaly assessment values. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0025] See also Figure 1-Figure 3The embodiment of the present invention provides a technical solution: a method and system for multi-point synchronous detection and identification of radioactive materials, including: step 1, real-time collection of multi-point radiation data, data preprocessing, and real-time storage of the multi-point radiation data; step 2, constructing a spatial adjacency matrix, estimating the local spatial gradient, calculating the abnormality degree value, taking optimization measures in real time according to the abnormality degree value, and performing collaborative abnormality assessment on the monitoring nodes; step 3, calculating the total fitting error value according to the multi-point radiation data, inferring the leakage source position and leakage intensity in real time according to the total fitting error value, and taking corresponding measures in real time; step 4, aggregating multi-point radiation data for real-time abnormal trend identification, calculating the early warning judgment value, and implementing hierarchical early warning and multi-node cross-confirmation measures; step 5, receiving and storing various types of data, performing visual analysis of the data, and supporting event processing and feedback.

[0026] Specifically, the specific process of real-time collection of multi-point radiation data, data preprocessing, and real-time storage of multi-point radiation data is as follows: multiple high-sensitivity monitoring nodes are deployed in the radioactive source storage area according to the site layout, potential leakage points and ventilation paths, which can significantly improve the spatial perception coverage capability of trace leakage signals and reduce the probability of missed detection; each monitoring node is equipped with a Geiger counter, a scintillation counter and a semiconductor detector, and a unique identification code is set for each monitoring node to ensure that the collected data has time accuracy and equipment traceability, and collect multi-point radiation data in real time. The multi-point radiation data includes: radiation dose rate and count rate data of the surrounding environment, as well as the three-dimensional coordinates and equipment parameters of each monitoring node; the real-time multi-point radiation data of each monitoring node is denoised using a moving average filter, the background dose is corrected, the stable baseline is eliminated, and standardization and normalization are performed; the multi-point radiation data is uploaded to the multi-point radiation database, and the multi-point radiation data is sent to the edge computing device through the message queue telemetry transmission protocol, which is conducive to the stability of the multi-node system and the coordination of edge decision-making. If a network anomaly occurs, the monitoring node automatically caches the data and supports remote firmware upgrades and regular calibration.

[0027] In this implementation plan, it has high spatial coverage and multi-modal detection capabilities, can stably collect and intelligently pre-process radiation data, and improve the accuracy of trace leak identification; at the same time, it has edge computing collaboration, network disconnection caching, remote maintenance and other mechanisms to achieve high-reliability data transmission throughout the entire process and automatic steady-state operation in abnormal scenarios.

[0028] Specifically, the specific process of constructing a spatial adjacency matrix, estimating the local spatial gradient, calculating the abnormality value, and taking optimization measures in real time according to the abnormality value is as follows: constructing a spatial adjacency matrix based on the three-dimensional coordinates recorded when each monitoring node is deployed, which can be used to construct a regional topology map, realize spatial correlation modeling and local cluster analysis; and calculating the Euclidean distance between all monitoring nodes. When the distance between any two monitoring nodes is less than three meters, they are determined to be neighbors, and the adjacency relationship between the two neighbor monitoring nodes is recorded, which helps to form a high-density sensitive area and improve the leakage trend positioning accuracy through spatial coupling analysis; according to the spatial adjacency matrix, the monitoring nodes are used to locate the leakage trend. The gradient component in the three-dimensional direction is calculated by the difference in radiation dose rate and three-dimensional coordinates between the monitoring nodes; the gradient estimation method adopts the weighted difference form: the influence of each neighbor node on the monitoring node is set according to the inverse square of the distance, and the closer the distance, the greater the weight; the gradient result is updated once per second according to the current radiation dose rate, and it is judged whether there is a trend of increasing dose in a certain direction in a certain area, which helps to achieve early identification of weak but continuous leakage; the historical radiation dose rate data of each monitoring node is subjected to sliding filtering processing, and the fixed window sliding average method is used to smooth out the short-term fluctuations caused by electronic noise, environmental disturbances and individual transient events, and the filtered value at the current moment is obtained. Wave dose value; establish a daily background model based on time period for each monitoring node: extract the corresponding historical filtered dose value from the same time period of the past three consecutive days, and obtain a stable background mean by calculating the average value as the normal state baseline of the monitoring node; and calculate the standard deviation based on the filtered dose value of the same time period of the past three consecutive days to obtain the background standard deviation; obtain the filtered dose value of the i-th monitoring node at time t, and at the same time obtain the background mean and background standard deviation of the i-th monitoring node at time t; use the filtered dose value of the i-th monitoring node at time t minus the background mean and then divide it by the sum of the background standard deviation and the constant 1 to obtain the standard deviation term, and use the standard deviation term to subtract the abnormal threshold weight The abnormality degree value of the i-th monitoring node at time t is obtained by factoring; the maximum function operation is performed on the abnormality degree value: if the abnormality degree value is less than zero, the abnormality degree value is set to zero; if the abnormality degree value is not less than zero, the calculation result is the abnormality degree value; when the abnormality degree values ​​of multiple consecutive nodes in a certain area increase abnormally, the sliding window is shortened, an on-site review prompt is automatically sent, and the regional ventilation system is called to dilute potential radioactive substances in advance; if a node has a high abnormality degree value for a long time and the neighboring nodes do not respond, the sensor self-diagnosis program is started; it is marked as a "suspected false alarm" state, remote self-calibration is initiated, historical performance and error trends are automatically analyzed, and the equipment is automatically evaluated for replacement.

[0029] The specific formula for the abnormality degree value is: ; Where, is the abnormality degree value, which indicates the abnormality degree of the radiation dose rate of the i-th monitoring node at time t relative to the stable background mean; is the filtered dose value of the i-th monitoring node at time t; is the background mean of the i-th monitoring node at time t; is the background standard deviation of the i-th monitoring node at time t; Represents the maximum function operation. If the abnormality value is less than zero, the abnormality value is set to zero. If the abnormality value is not less than zero, the calculation result is the abnormality value, ensuring that the abnormality value is not negative. For the anomaly threshold weight factor, based on the historical radiation dose rate data, a training set characterized by filtered dose value, background mean and background standard deviation is constructed. Through enumeration search and optimization algorithm, the anomaly threshold weight factor with the best anomaly detection performance in the training set is selected, ranging from 0.01 to 0.06.

[0030] In this implementation plan, the spatial adjacency matrix construction of multi-point radiation data, local spatial gradient estimation, calculation of anomaly degree values ​​and execution of real-time optimization measures are realized. It has the functions of sliding filtering processing, daily background model establishment, standard deviation item calculation, anomaly threshold judgment, regional review prompts, ventilation system call, sensor self-diagnosis and remote self-calibration, etc., which improve the accuracy of anomaly recognition and the level of intelligent system response.

[0031] Specifically, the specific process of collaborative anomaly evaluation of monitoring nodes is as follows: obtain the anomaly degree values ​​of the i-th monitoring node and the j-th neighbor node at time t; obtain the spatial adjacency matrix, and filter the neighbor nodes of the spatial adjacency matrix to obtain the neighbor node set of the i-th monitoring node, and obtain the length of the neighbor node set to obtain the number of neighbor nodes; sum the anomaly degree values ​​of all neighbor nodes at time t based on the number of neighbor nodes, and then divide the sum by the number of neighbor nodes to obtain the neighborhood average anomaly value, multiply the neighborhood average anomaly value by the neighborhood fusion weight factor and then add it to the anomaly degree value of the i-th monitoring node at time t to obtain the collaborative anomaly evaluation value, thereby enhancing the ability to identify group leakage signals; compare the collaborative anomaly evaluation value with the first and second level anomaly thresholds in real time to form a graded response mechanism, which helps to take different levels of disposal measures in a timely manner. When the collaborative anomaly evaluation value is less than or equal to the first level anomaly threshold, it is considered that the radiation level is within the normal background fluctuation range, and routine monitoring is continued to maintain normal equipment and data collection without intervention. ; When the collaborative anomaly assessment value is greater than the first-level anomaly threshold and less than or equal to the second-level anomaly threshold, it is considered that there is a trace leak or equipment anomaly, and the collaborative anomaly degree value will be uploaded to the background to start higher-frequency data collection; automatically monitor the status and environmental parameters of the abnormal monitoring nodes and surrounding equipment. If it is confirmed that the anomaly is valid and is in a poorly ventilated and high-risk area, the ventilation system will be automatically started, local sound and light prompts will be issued, and protection warning instructions will be issued to the on-site area; when the collaborative anomaly assessment value is greater than the second-level anomaly threshold, it is considered that the radiation level is abnormal and there is a risk of leakage. The collaborative anomaly degree value will be uploaded to the background, and the on-site emergency plan will be immediately activated to isolate the suspected leakage area; remote and on-site synchronous alarms, automatic push of abnormal prompts, realize multi-platform and multi-role linkage response, and improve the efficiency of abnormal information arrival; use portable high-precision detectors to carry out precise positioning and confirmation of the source of the leak; and push cleaning and repair instructions according to the degree of leakage, while recording the execution progress and feedback to complete the closed-loop management of the disposal task, which is conducive to post-evaluation and continuous optimization of the model.

[0032] The specific formula for the collaborative anomaly evaluation value is: ; Where, is the collaborative anomaly evaluation value of the i-th monitoring node at time t, which is used to determine whether there may be a local radioactive leakage; is the abnormality value of the i-th monitoring node at time t; is the set of neighbor nodes of the i-th monitoring node; is the number of neighbor nodes; is the abnormality value of the jth neighbor node at time t; is the neighborhood fusion weight factor. By analyzing historical multi-point radiation data, the radiation dose rate time series correlation coefficient between each monitoring node and its neighbors is calculated. The correlation between the abnormality degree value sequence of the i-th monitoring node and its j-th neighbor node is calculated. The neighborhood fusion weight factor is set to the weighted average of the correlation coefficients of the i-th monitoring node and its neighbors. It is obtained by comprehensive analysis using the statistical correlation analysis algorithm and ranges from 0 to 1.

[0033] The neighborhood fusion weight factor was set to 0.6. Different anomaly levels were calculated based on the different radiation dose rates of radioactive materials detected by different monitoring nodes. Different monitoring nodes also obtained different neighborhood average anomaly values ​​based on the number of neighboring nodes. When the neighborhood fusion weight factor was consistent, the collaborative anomaly assessment value of the monitoring node was calculated. Table 1 shows the collaborative anomaly assessment value data.

[0034] Table 1 Collaborative anomaly evaluation value data table Monitoring node number 1 0.01124 3 0.00014 0.01132 2 0.02852 2 0.00046 0.0288 3 0.02196 3 0.0105 0.02826 4 0.01796 3 0.008 0.02276 5 0.00468 3 0.00093 0.00524 like Figure 3 As shown in Table 1 and Table 2, the comparison chart of the collaborative abnormal evaluation value provided by this application example is shown in Table 1 and Table 2. Figure 3 It can be seen that when the neighborhood fusion weight factors are consistent, different monitoring nodes have different anomaly degree values, number of neighboring nodes, and average neighborhood anomaly values, and different collaborative anomaly evaluation values ​​are calculated, as well as the current anomaly degree value of each monitoring node and the degree of collaborative influence of its neighborhood.

[0035] In this implementation plan, the calculation and classification of collaborative anomaly assessment values ​​are realized, and it has the functions of neighborhood fusion, spatial consistency judgment, real-time threshold comparison, dynamic sampling and frequency modulation, equipment and environment linkage monitoring, automatic ventilation control, local sound and light prompts, early warning command issuance, emergency plan activation, leakage source confirmation, cleaning and repair command push and execution closed-loop recording, etc., to improve the system's recognition accuracy of abnormal events and the level of intelligent response.

[0036] Specifically, the total fitting error value is calculated based on multi-point radiation data, and the specific process of real-time reverse deduction of the leakage source position and leakage intensity based on the total fitting error value is as follows: obtain the three-dimensional coordinates of each monitoring node and the corresponding radiation dose rate, and perform abnormal point filtering according to the equipment parameters to eliminate interference data such as fault points and strong noise points to enhance the input quality; construct a dose gradient field through spatial difference based on the three-dimensional coordinates and real-time radiation dose rate of the monitoring node, reveal the dose change trend in space, and provide directional information for preliminary positioning; select the monitoring node position with the largest radiation dose rate as the initial leakage source position according to the dose gradient field; and select the monitoring node with the largest radiation dose rate according to the selected maximum radiation dose rate. The radiation dose rate, the distance between the initial leakage source location and the current monitoring node are calculated, and the radiation dose rate at the leakage source location is inferred from the real-time radiation dose rate of the monitoring node as the initial leakage intensity; based on the information criterion and spatial clustering fusion algorithm, the abnormal degree values ​​of the radiation dose rate of all monitoring nodes are spatially clustered to distinguish independent leakage events from local disturbance clusters, and adapt to multi-source scenarios; by identifying the abnormal aggregation area of ​​high radiation dose rate, the number of potential source points is preliminarily inferred, and under different hypothetical source numbers, the Bayesian information criterion algorithm is combined to perform leakage source inversion positioning calculation analysis, and the source point number with the smallest Bayesian information criterion value is selected as the current The optimal total number of leakage sources in the scenario; the total number of monitoring nodes is obtained by obtaining the number of detectors; the three-dimensional coordinates of the i-th monitoring node and the radiation dose rate measured at the i-th monitoring node are obtained; the initial leakage source position and initial leakage intensity are obtained, the square of the Euclidean distance from the three-dimensional coordinates of the i-th monitoring node to the initial leakage source position is calculated and added with a constant of one, and then the leakage source contribution value is obtained by dividing the sum by the initial leakage intensity. Based on the total number of leakage sources, the leakage source contribution values ​​of all leakage sources are accumulated to obtain the estimated dose value of the i-th monitoring node, and the radiation dose rate of the i-th monitoring node is subtracted from the estimated dose value of the i-th monitoring node. The squared error term is obtained by row squaring operation. The squared error term measures the deviation between the simulated value and the measured value and is the core goal of optimization convergence. Based on the total number of monitoring nodes, the squared error terms of all monitoring nodes are summed to obtain the initial total fitting error value of the K leakage sources. Based on the initial total fitting error value of the K leakage sources, the nonlinear least squares optimization algorithm is used to adjust the leakage source position and leakage intensity, gradually reducing the total fitting error value. Through iterative adjustment, the estimation result gradually approaches the true leakage source parameters to achieve global optimal approximation until the total fitting error value is less than the error threshold, and then the current k-th leakage source position and leakage intensity of the k-th leakage source are obtained by reverse deduction.

[0037] Among them, the specific formula of the total fitting error value is: ; Where, is the total fitting error value of K leakage sources, where are the three-dimensional coordinate points of the kth leakage source, is the leakage intensity of the kth leakage source, which is used to measure the error between the sum of the theoretical radiation doses calculated by all monitoring nodes and the actual measured radiation dose value; is the total number of leakage sources; is the total number of monitoring nodes; is the three-dimensional coordinate of the i-th monitoring node; is the radiation dose rate measured at the i-th monitoring node; is the kth leakage source location; is the leakage intensity of the kth leakage source.

[0038] In this implementation, the total fitting error value calculation based on multi-point radiation data and the real-time inverse calculation of the leakage source position and leakage intensity are realized. It has the functions of outlier filtering, dose gradient field construction, initial leakage source estimation, spatial clustering analysis, Bayesian information criterion judgment, nonlinear least squares optimization, and error dynamic convergence, which improves the leakage source positioning accuracy and intelligent adaptability in multi-source scenarios.

[0039] Specifically, the specific process of taking corresponding measures in real time is as follows: real-time comparison of the total fitting error value and the error threshold. When the total fitting error value is less than or equal to the error threshold, the leakage source positioning result is considered credible and directly used for rapid response and on-site disposal of the leakage source, which greatly shortens the time delay from source point identification to response execution and improves the overall disposal efficiency; the three-dimensional coordinate position of the leakage source and the leakage intensity as well as the total fitting error value are uploaded to the monitoring platform, and the leakage emergency plan module is triggered in real time to realize the automatic linkage mechanism driven by the identification results, supporting visual monitoring and closed-loop traceability of the entire process; automatically assigning risk levels, and linking the execution of regional sealing and ventilation , sound and light alarms and protection instructions, and continuously and dynamically monitor the evolution process of the leakage to ensure the continuity and integrity of the full life cycle management of the leakage incident; when the total fitting error value is greater than the error threshold, the leakage source positioning result is considered unreliable, and a "fitting failure" prompt is output, and a reminder to check the data quality and equipment status is automatically pushed; check whether there are abnormal multi-point radiation data and monitoring sensor failures, perform data cleaning and equipment calibration; evaluate the existing monitoring node layout; recalculate the total fitting error value after adjustment until the total fitting error value meets the effective judgment, realize the automatic closed-loop correction process, and enhance the system's adaptability to complex scenarios.

[0040] In this implementation plan, real-time comparison and credibility judgment of the total fitting error value and the error threshold are realized, and it has the functions of uploading leakage source positioning results, triggering the leakage emergency plan module, automatic allocation of risk level, regional sealing and ventilation sound and light alarm linkage, dynamic evolution monitoring, fitting failure prompt, data quality and equipment status reminder, data cleaning and equipment calibration, monitoring node layout evaluation and adjustment, error recalculation and other functions, which improve the reliability, closed-loop and intelligence level of the system leakage identification and response.

[0041] Specifically, the specific process of collecting multi-point radiation data to identify real-time abnormal trends and calculating the warning judgment value is as follows: the edge computing device periodically collects multi-point radiation data transmitted by each monitoring node at a high frequency, establishes a rolling cache, and saves at least one hour of historical multi-point radiation data to ensure the system's time-series perception of abnormal trends and support dynamic identification and tracking of minute-level changes; and strictly synchronizes the cached multi-point radiation data with timestamps to ensure that spatially heterogeneous data are comparable and fused within a unified time frame to avoid the superposition of misjudgment factors; obtains the radiation dose rate of the i-th monitoring node and the j-th neighbor node at time t, obtains the background mean of the i-th monitoring node and the j-th neighbor node, and obtains the neighbor node set of the i-th monitoring node. The length of the neighbor node set of the i-th monitoring node is obtained to obtain the number of neighbor nodes; the difference between the radiation dose rate of the i-th monitoring node and the background mean of the i-th monitoring node is calculated to obtain the normal deviation degree of the monitoring node, reflecting the abnormal amplitude of the current node relative to its historical normal state; the difference between the radiation dose rate of the j-th neighbor node and the background mean of the j-th neighbor node is calculated, and based on the number of neighbor nodes, all differences are summed up, the sum result is divided by the number of neighbor nodes and then multiplied by the neighbor influence weight factor to obtain the neighbor influence term, and the neighbor influence term is added to the normal deviation degree to obtain the warning judgment value, which comprehensively considers the local offset and spatial propagation trend and is the key decision indicator for triggering subsequent warning measures.

[0042] The specific formula for the early warning judgment value is: ; Where, is the warning judgment value of the i-th monitoring node at time t, which is used to evaluate the radiation anomaly degree of a monitoring node at the current moment; is the radiation dose rate of the i-th monitoring node at time t; is the background mean of the i-th monitoring node; is the set of neighbor nodes of the i-th monitoring node; is the number of neighbor nodes; is the radiation dose rate of the jth neighbor node at time t; is the background mean of the jth neighbor node; For the neighbor influence weight factor, a series of candidate neighbor influence weight factors are set based on the radiation dose rate of the monitoring node in multiple historical time periods, the corresponding background mean, the three-dimensional coordinates of the monitoring node, and whether a leakage has been recorded. Under each candidate neighbor influence weight factor, the early warning judgment value is calculated and compared with the known leakage events. The optimal neighbor influence weight factor is obtained through cross-validation statistical analysis, ranging from 0 to 1.

[0043] In this implementation plan, high-frequency collection and rolling caching of multi-point radiation data, strict synchronization of timestamps, extraction of neighbor node sets, calculation of normal deviation degree, calculation and fusion of neighbor influence items are realized to generate early warning judgment values. It has trend identification, spatial collaborative analysis and real-time early warning triggering functions, which improves the system's sensitivity to radiation anomaly trends and the timeliness of response.

[0044] Specifically, the specific process of implementing graded warning and multi-node cross-confirmation measures is as follows: real-time comparison of the warning judgment value with the first and second level warning thresholds. When the warning judgment value is less than the first level warning threshold, it is judged as no abnormality, continuous monitoring, and regular archiving without intervention. This state can maximize the reduction of false alarm interference and ensure the resource efficiency of system operation; when the warning judgment value is greater than or equal to the first level warning threshold and less than the second level threshold, it is judged as a slight dose increase, which may be affected by disturbances or initial leakage. Local sound and light reminders are issued, and the radiation dose rate change rate is recorded in real time. Strengthening monitoring of key areas is conducive to rapid response to potential leakage trends; when the warning judgment value is greater than or equal to the second level threshold, it is judged as obvious abnormality and suspected leakage. If there is any source activity, the local buzzer and red light alarm will be activated immediately to respond, the early warning judgment value will be uploaded, the mobile detection equipment will be automatically dispatched to check the abnormal area, and the detection data will be sent back in real time to start the leakage source positioning and emergency handling procedures; if a single node alarms but the neighboring nodes do not respond, the remote alarm will be delayed and marked as "pending confirmation", which effectively filters out isolated false alarms and prevents the system from frequently triggering the plan by mistake; if the early warning judgment values ​​of more than three neighboring nodes are greater than the early warning threshold at the same time and their distribution is consistent in space, it will be upgraded to a "regional leakage early warning", and the leakage source inversion positioning module will be automatically triggered to start positioning, realizing the fusion judgment of regional aggregation characteristics and spatial consistency, ensuring that the system has the ability to quickly perceive and locate large-scale leaks.

[0045] In this implementation plan, real-time comparison between the warning judgment value and the first and second level warning thresholds is achieved, and it has the functions of continuous monitoring and archiving, local sound and light reminders, radiation dose rate change records, enhanced monitoring of key areas, buzzer and red light response, warning value upload, mobile detection equipment scheduling, real-time data feedback, leakage source positioning and emergency processing, "pending confirmation" status marking, regional leakage warning identification and inversion positioning startup, etc., to improve the hierarchical disposal capability of the warning response and the level of spatial consistency judgment.

[0046] Specifically, the specific process of receiving and storing various types of data, performing visual analysis of the data, and supporting event processing and feedback is as follows: the cloud server receives the monitoring node identification code, radiation dose rate, radiation dose rate change rate, positioning results and timestamp in real time, and stores them uniformly in the time series database to ensure the real-time and integrity of historical trends and event tracing analysis; and performs visual analysis based on the multi-point radiation data of the monitoring node to enhance the user's intuitive understanding of the abnormal situation of the coordinated monitoring node, and assist the command personnel to accurately grasp the availability of the monitoring node; supports multi-level alarms, and pushes notifications to relevant personnel through multiple channels such as SMS, email, and WeChat, supports event processing records and backtracking, automatically archives alarm handling operations, response time and feedback content, and improves the closed-loop controllability of event management; introduces machine learning models for intelligent identification and risk assessment of leakage patterns, realizes automatic classification and judgment of different types of leakage, and automatically generates risk assessment reports on a regular basis.

[0047] In this implementation plan, unified storage of monitoring node identification codes, radiation dose rates, radiation dose rate change rates, positioning results and timestamps is achieved, with functions such as leakage source positioning heat map display, suspected leakage intensity and location visualization analysis, multi-level alarms, multi-channel push, event processing records and backtracking, leakage pattern intelligent identification, risk assessment and report generation, etc., to enhance data management, visual perception and intelligent decision-making capabilities.

[0048] Reference Figure 2 As shown, the second aspect of the present invention provides a multi-point synchronous detection and identification system for radioactive materials, which is applied to the above-mentioned multi-point synchronous detection and identification method for radioactive materials, including: a multi-point synchronous monitoring module, a dose trend collaborative modeling module, a leakage source inversion and positioning module, an edge computing and early warning module, and a cloud monitoring and analysis module; wherein the multi-point synchronous monitoring module is used to collect multi-point radiation data in real time, perform data preprocessing, and store the multi-point radiation data in real time; the dose trend collaborative modeling module is used to construct a spatial adjacency matrix, estimate local spatial gradients, calculate abnormality values, take optimization measures in real time based on the abnormality values, and perform collaborative abnormality assessment on monitoring nodes; the leakage source inversion and positioning module is used to calculate the total fitting error value based on the multi-point radiation data, infer the leakage source position and leakage intensity in real time based on the total fitting error value, and take corresponding measures in real time; the edge computing and early warning module is used to aggregate multi-point radiation data for real-time abnormal trend identification, calculate early warning judgment values, and implement hierarchical early warning and multi-node cross-confirmation measures; the cloud monitoring and analysis module is used to receive and store various types of data, perform data visualization analysis, and support event processing and feedback.

[0049] In this implementation plan, real-time collection, preprocessing and storage of multi-point radiation data are realized, and it has the functions of spatial adjacency matrix construction, local spatial gradient estimation, anomaly degree value calculation and collaborative evaluation, total fitting error value inversion of leakage source location and intensity, anomaly trend identification, warning judgment value calculation and graded warning, data visualization analysis and event processing feedback, etc., to enhance the system's multi-dimensional perception, intelligent diagnosis and response linkage capabilities for leakage events.

[0050] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0051] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to the specific embodiments described. Obviously, many modifications and variations are possible based on the content of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for multi-point synchronous detection and identification of radioactive substances, characterized in that: include: Step 1: real-time collection of multi-point radiation data, data preprocessing, and real-time storage of the multi-point radiation data; Step 2: Construct a spatial adjacency matrix, estimate the local spatial gradient, calculate the degree of anomaly, take optimization measures in real time based on the degree of anomaly, and conduct collaborative anomaly assessment on the monitoring nodes; Step 3: Calculate the total fitting error value based on the multi-point radiation data, reversely infer the leakage source location and leakage intensity in real time based on the total fitting error value, and take corresponding measures in real time; Step 4: Collect multi-point radiation data to identify real-time abnormal trends, calculate early warning judgment values, and implement hierarchical early warning and multi-node cross-confirmation measures; Step 5: Receive and store various types of data, perform visual analysis of the data, and support event processing and feedback.

2. The method for multi-point synchronous detection and identification of radioactive substances according to claim 1, characterized in that: The specific process of real-time acquisition of multi-point radiation data, data preprocessing, and real-time storage of the multi-point radiation data is as follows: Multiple highly sensitive monitoring nodes are deployed within the radioactive source storage area based on site layout, potential leakage points, and ventilation paths. Each monitoring node is equipped with a Geiger counter, scintillation counter, and semiconductor detector. Each monitoring node is assigned a unique identification code to collect multi-point radiation data in real time. This data includes the radiation dose rate and count rate data of the surrounding environment, as well as the three-dimensional coordinates and equipment parameters of each monitoring node. The real-time multi-point radiation data of each monitoring node is denoised using moving average filtering, background dose correction is performed, stable baselines are removed, and standardization and normalization are performed. Upload multi-point radiation data to the multi-point radiation database, and send the multi-point radiation data to the edge computing device through the message queue telemetry transmission protocol. If a network anomaly occurs, the monitoring node automatically caches the data and supports remote firmware upgrades and regular calibration.

3. The method for multi-point synchronous detection and identification of radioactive substances according to claim 1, characterized in that: The specific process of constructing a spatial adjacency matrix, estimating the local spatial gradient, calculating the abnormality value, and taking optimization measures in real time according to the abnormality value is as follows: Based on the three-dimensional coordinates recorded when each monitoring node was deployed, a spatial adjacency matrix was constructed. The Euclidean distance between all monitoring nodes was calculated. When the distance between any two monitoring nodes was less than three meters, they were considered neighbors and the adjacency relationship between the two neighboring monitoring nodes was recorded. Based on the spatial adjacency matrix, the gradient components in the three-dimensional direction are calculated using the differences in radiation dose rates and three-dimensional coordinates between monitoring nodes. The gradient estimation method uses a weighted difference method: the influence of each neighbor node on the monitoring node is weighted according to the inverse square of the distance, with the closer the distance, the greater the weight. The gradient results are updated once per second based on the current radiation dose rate, and it is determined whether there is a trend of increasing dose in a certain direction in a certain area. Sliding filtering is performed on the historical radiation dose rate data of each monitoring node, and a fixed window sliding average method is used to smooth out short-term fluctuations caused by electronic noise, environmental disturbances and individual transient events to obtain the filtered dose value at the current moment; A time-based daily background model is established for each monitoring node: the corresponding historical filtered dose values ​​are extracted from the same time period for the past three consecutive days, and a stable background mean is obtained by calculating the mean value, which serves as the normal state baseline of the monitoring node; The background standard deviation is obtained by calculating the standard deviation based on the filtered dose values ​​of the same period over the past three consecutive days; Obtain the filtered dose value of the i-th monitoring node at time t, and simultaneously obtain the background mean and background standard deviation of the i-th monitoring node at time t; subtract the background mean from the filtered dose value of the i-th monitoring node at time t and divide it by the sum of the background standard deviation and a constant of one to obtain the standard deviation term; subtract the abnormal threshold weight factor from the standard deviation term to obtain the abnormal degree value of the i-th monitoring node at time t; Perform the maximum function operation on the abnormality degree value: if the abnormality degree value is less than zero, the abnormality degree value is set to zero; if the abnormality degree value is not less than zero, the calculation result is the abnormality degree value; When the abnormality values ​​of multiple nodes in a certain area increase abnormally, the sliding window is shortened, an on-site review prompt is automatically sent, and the regional ventilation system is activated to dilute potential radioactive materials in advance; If a node has a high abnormality value for a long time and the neighboring nodes do not respond, the sensor self-diagnosis program is started; Mark the device as a "suspected false alarm" and initiate remote self-calibration to automatically analyze historical performance and error trends and assess whether to replace the device.

4. The method for multi-point synchronous detection and identification of radioactive substances according to claim 1, characterized in that: The specific process of performing collaborative anomaly assessment on monitoring nodes is as follows: Obtain the abnormality degree value of the i-th monitoring node and the j-th neighbor node at time t; obtain the spatial adjacency matrix, and filter the neighbor nodes of the spatial adjacency matrix to obtain the neighbor node set of the i-th monitoring node, and obtain the length of the neighbor node set to obtain the number of neighbor nodes; Based on the number of neighboring nodes, the anomaly degree values ​​of all neighboring nodes at time t are summed, and the summed result is divided by the number of neighboring nodes to obtain the neighborhood average anomaly value. The neighborhood average anomaly value is multiplied by the neighborhood fusion weight factor and then added to the anomaly degree value of the i-th monitoring node at time t to obtain the collaborative anomaly evaluation value; Compare the collaborative anomaly assessment value with the first and second level anomaly thresholds in real time. When the collaborative anomaly assessment value is less than or equal to the first level anomaly threshold, the radiation level is considered to be within the normal background fluctuation range. Continue routine monitoring, maintain normal equipment and data collection, and no intervention is required. When the collaborative anomaly assessment value is greater than the first-level anomaly threshold and less than or equal to the second-level anomaly threshold, it is considered that there is a trace leak or equipment anomaly, and the collaborative anomaly degree value is uploaded to the backend to start more frequent data collection; the abnormal monitoring node and the status of surrounding equipment and environmental parameters are automatically monitored. If it is confirmed that the anomaly is valid and is in a poorly ventilated or high-risk area, the ventilation system will be automatically started, local sound and light prompts will be issued, and protective warning instructions will be issued to the on-site area; When the collaborative anomaly assessment value is greater than the second-level anomaly threshold, the radiation level is considered abnormal and there is a risk of leakage. The collaborative anomaly degree value will be uploaded to the background, and the on-site emergency plan will be immediately activated to isolate the suspected leakage area; remote and on-site synchronous alarms will be issued, and abnormal prompts will be automatically pushed; portable high-precision detectors will be used for precise positioning and confirmation of the source of the leak; and cleaning and repair instructions will be pushed according to the degree of leakage, while the execution progress and feedback will be recorded.

5. The method for multi-point synchronous detection and identification of radioactive substances according to claim 1, characterized in that: The specific process of calculating the total fitting error value based on the multi-point radiation data and inferring the leakage source position and leakage intensity in real time based on the total fitting error value is as follows: The three-dimensional coordinates and corresponding radiation dose rate of each monitoring node are obtained, and outlier filtering is performed according to the equipment parameters. Based on the three-dimensional coordinates of the monitoring nodes and the real-time radiation dose rate, a dose gradient field is constructed through spatial differentiation. The monitoring node position with the largest radiation dose rate is selected as the initial leakage source position based on the dose gradient field. The radiation dose rate at the leakage source position is obtained as the initial leakage intensity based on the selected maximum radiation dose rate, the distance between the initial leakage source position and the current monitoring node, and the real-time radiation dose rate of the monitoring node. Based on the information criterion and spatial clustering fusion algorithm, a spatial clustering analysis was performed on the abnormal degree values ​​of the radiation dose rate of all monitoring nodes. By identifying the areas with abnormal high radiation dose rates, the number of potential source points was preliminarily estimated. Under different hypothetical numbers of sources, the Bayesian information criterion algorithm was combined to perform leakage source inversion and positioning calculations and analysis. The number of source points with the minimum Bayesian information criterion value was selected as the optimal total number of leakage sources in the current scenario. The total number of monitoring nodes is obtained by obtaining the number of detectors deployed; the three-dimensional coordinates of the i-th monitoring node and the radiation dose rate actually measured at the i-th monitoring node are obtained; the initial leakage source position and the initial leakage intensity are obtained, the square of the Euclidean distance from the three-dimensional coordinates of the i-th monitoring node to the initial leakage source position is calculated and a constant of one is added, and then the initial leakage intensity is divided by the sum to obtain the leakage source contribution value; based on the total number of leakage sources, the leakage source contribution values ​​of all leakage sources are accumulated to obtain the estimated dose value of the i-th monitoring node; the radiation dose rate of the i-th monitoring node is subtracted from the estimated dose value of the i-th monitoring node and then squared to obtain the squared error term; based on the total number of monitoring nodes, the squared error terms of all monitoring nodes are summed to obtain the initial total fitting error value of the K leakage sources; Based on the initial total fitting error value of K leakage sources, the nonlinear least squares optimization algorithm is used to adjust the leakage source position and leakage intensity, and gradually reduce the total fitting error value until the total fitting error value is less than the error threshold, and then reversely infer the current k-th leakage source position and leakage intensity of the k-th leakage source.

6. The method for multi-point synchronous detection and identification of radioactive substances according to claim 1, characterized in that: The specific process of taking corresponding measures in real time is as follows: The total fitting error value is compared with the error threshold in real time. When the total fitting error value is less than or equal to the error threshold, the leak source location result is considered reliable and directly used for rapid response and on-site disposal of the leak source. The three-dimensional coordinate position of the leak source, the leakage intensity, and the total fitting error value are uploaded to the monitoring platform, triggering the leak emergency plan module in real time. The risk level is automatically assigned, and regional lockdown, ventilation, sound and light alarms, and protective instructions are linked to be executed. The leak evolution process is continuously and dynamically monitored. When the total fitting error value is greater than the error threshold, the leak source location result is considered unreliable, a "fitting failed" prompt is output, and a reminder to check data quality and device status is automatically pushed; Check for abnormal multi-point radiation data and monitoring sensor failures, perform data cleaning and equipment calibration; and evaluate the layout of existing monitoring nodes; After adjustment, the total fitting error value is recalculated until the total fitting error value meets the effective judgment.

7. The method for multi-point synchronous detection and identification of radioactive substances according to claim 1, characterized in that: The specific process of collecting multi-point radiation data to identify real-time abnormal trends and calculate early warning judgment values ​​is as follows: The edge computing device periodically collects multi-point radiation data transmitted by each monitoring node at a high frequency, establishes a rolling cache, and saves at least one hour of historical multi-point radiation data; and strictly synchronizes the cached multi-point radiation data with a timestamp; Get the radiation dose rate of the i-th monitoring node and the j-th neighbor node at time t, get the background mean of the i-th monitoring node and the j-th neighbor node, get the neighbor node set of the i-th monitoring node, and get the length of the neighbor node set of the i-th monitoring node to get the number of neighbor nodes; The difference between the radiation dose rate of the i-th monitoring node and the background mean of the i-th monitoring node is calculated to obtain the normal deviation degree of the monitoring node; Calculate the difference between the radiation dose rate of the j-th neighbor node and the background mean of the j-th neighbor node, and sum all the differences based on the number of neighbor nodes. Divide the sum by the number of neighbor nodes and multiply it by the neighbor influence weight factor to obtain the neighbor influence term. Add the neighbor influence term and the degree of deviation from normal to obtain the warning judgment value.

8. The method for multi-point synchronous detection and identification of radioactive substances according to claim 1, characterized in that: The specific process of implementing the hierarchical early warning and multi-node cross-confirmation measures is as follows: Compare the warning judgment value with the first and second level warning thresholds in real time. When the warning judgment value is less than the first level warning threshold, it is determined to be normal, and continuous monitoring and regular archiving are performed without intervention. When the warning judgment value is greater than or equal to the first-level warning threshold and less than the second-level threshold, it is judged as a slight dose increase, which may be affected by disturbances or initial leakage. Local sound and light warnings are issued, the radiation dose rate change rate is recorded in real time, and key areas are monitored more closely; When the warning judgment value is greater than or equal to the second-level threshold, it is judged as a clear abnormality and suspected leakage source activity. The local buzzer and red light alarm light will be activated immediately to respond, the warning judgment value will be uploaded, and mobile detection equipment will be automatically dispatched to check the abnormal area. The detection data will be sent back in real time to start the leakage source location and emergency response procedures; If a single node alarms but the neighboring nodes do not respond, the remote alarm will be delayed and marked as "pending confirmation"; if the warning judgment values ​​of more than three neighboring nodes are simultaneously greater than the warning threshold and their distribution is consistent in space, it will be upgraded to a "regional leak warning", automatically triggering the leak source inversion positioning module to start positioning.

9. The method for multi-point synchronous detection and identification of radioactive substances according to claim 1, characterized in that: The specific process of receiving and storing various types of data, performing visual analysis of the data, and supporting event processing and feedback is as follows: The cloud server receives the monitoring node identification code, radiation dose rate, radiation dose rate change rate, positioning results and timestamp in real time and stores them in a time series database. It also performs visual analysis based on the multi-point radiation data of the monitoring node. Supports multi-level alarms and push notifications to relevant personnel via SMS, email, and WeChat, and supports event processing records and backtracking; Introduce machine learning models to intelligently identify leakage patterns and conduct risk assessments, and automatically generate risk assessment reports on a regular basis.

10. A radioactive material multi-point synchronous detection and identification system, characterized in that: include: Multi-point synchronous monitoring module, dose trend collaborative modeling module, leakage source inversion positioning module, edge computing and early warning module, and cloud monitoring and analysis module; The multi-point synchronous monitoring module is used to collect multi-point radiation data in real time, perform data preprocessing, and store the multi-point radiation data in real time; The dose trend collaborative modeling module is used to construct a spatial adjacency matrix, estimate local spatial gradients, calculate abnormality values, take optimization measures in real time based on the abnormality values, and perform collaborative abnormality assessments on monitoring nodes; The leakage source inversion positioning module is used to calculate the total fitting error value based on the multi-point radiation data, infer the leakage source position and leakage intensity in real time based on the total fitting error value, and take corresponding measures in real time; The edge computing and early warning module is used to collect multi-point radiation data to identify real-time abnormal trends, calculate early warning judgment values, and implement hierarchical early warning and multi-node cross-confirmation measures; The cloud monitoring and analysis module is used to receive and store various types of data, perform visual analysis of the data, and support event processing and feedback.

Citation Information

Patent Citations

  • Radiation therapy treatment plan optimization using machine learning

    CN114401768A

  • Radioactive source positioning method, radioactive source positioning instrument and control method

    CN115657102A

  • Method for judging radioactive direction source and measuring system

    CN117331022A

  • Nuclear radiation monitoring method and system for improving gamma dose rate prediction accuracy

    CN118760866A

  • High-voltage control cabinet with partial discharge detection device

    CN118801234A

Cited By

  • Real-time processing method for data missing value of regional radiation monitor

    CN121051597A

  • Mining dust concentration real-time monitoring and early warning system

    CN121164140A

  • Nuclear leakage rapid positioning method based on gridding aerosol online monitoring device

    CN121393957A

  • Data processing method and system based on radiation safety supervision platform

    CN121432504A

  • System and method for online measurement and feedback calibration of electron irradiation dose

    CN121477273A