Nuclear-biochemical automatic monitoring system and monitoring method

Abstract

The invention discloses a nuclear-biochemical automatic monitoring system and a monitoring method, and relates to the technical field of chemical detection, the nuclear-biochemical automatic monitoring system comprises an environment probe combination, a data processing unit, an indication particle distribution device and an alarm unit; according to the invention, a dynamic balance model is constructed through the environment probe and the data processing unit, so that complex environment interference can be effectively dealt with, signals can be accurately distinguished, and the detection accuracy and reliability are improved; the indicating particle spreading device solves the problem of malicious disguise article detection by utilizing the interaction of materials; a low-cost environmental probe combination is adopted, so that the cost is reduced and the reliability is ensured; the data processing unit processes gas concentration data by combining a moving average method with a Kalman filtering algorithm, and performs classified counting on microorganisms through a deep learning image recognition technology; multiple technologies cooperate to construct a comprehensive detection mechanism, strategies can be flexibly adjusted, maintenance optimization and technology fusion are facilitated, and safety detection of industries such as postal service and the like is powerfully guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of chemical detection, and in particular to a nuclear, biological and chemical automatic monitoring system and a monitoring method. Background Art

[0002] In the field of nuclear, biological and chemical detection technology, in complex environments such as public transportation hubs and postal sorting centers with dense crowds and numerous items, the existing detection technology has many problems that need to be solved in practical applications.

[0003] In terms of interference in complex environments, existing conventional detection technologies have serious deficiencies in distinguishing signals generated by normal objects, background radiation and other interference from real nuclear, biological, chemical and explosive hazardous materials signals. For example, in postal sorting centers, the signal characteristics generated by daily electronic devices and some packaging materials made of special materials are very similar to the signals of nuclear, biological and chemical substances, which can easily lead to misjudgment of detection results. Traditional methods of improving detection sensitivity not only fail to effectively solve this problem, but also increase the probability of misjudgment; and conventional signal filtering methods, under the existing technical framework, often remove valid signals while filtering out interference signals. This is mainly because most existing detection technologies only analyze signals based on a single dimension, such as only focusing on conventional features such as signal strength and frequency, and lack comprehensive consideration of multi-dimensional information such as the source of items and transportation trajectories, making it difficult to build an accurate and effective interference identification and elimination model.

[0004] For the detection of malicious disguised items, the existing detection methods based on conventional material properties are inadequate. For example, when radioactive materials are wrapped in a new type of material with thermal and chemical stability similar to ordinary plastics, such disguised items are very similar to normal items in appearance, physical properties and chemical properties, and existing detection technologies are difficult to detect the dangerous items hidden in them. This is because the existing detection technology fails to fully explore the potential interactions between materials and only relies on the detection of the conventional properties of the material itself, which cannot break through the layers of disguised items.

[0005] In the field of microbial community detection, traditional image recognition methods have difficulty accurately classifying and counting microorganisms with diverse morphologies and complex characteristics. This shows that in the monitoring of microbial communities in complex environments, existing technologies cannot efficiently and accurately obtain microbial-related information, making it difficult to fully play the role of microbial communities, an important environmental indicator, in the detection system, and it is difficult to effectively judge whether the environment is affected by nuclear, biological and chemical substances through changes in microbial communities.

[0006] In summary, existing nuclear, biological and chemical detection technologies have exposed obvious deficiencies in interference response in complex environments, detection of malicious disguised items, data processing, and microbial community detection. These problems have seriously affected the accuracy and reliability of nuclear, biological and chemical detection. A new detection system and method are urgently needed to solve the above problems in order to meet the strict requirements of nuclear, biological and chemical detection in complex scenarios.

[0007] In view of this, a nuclear, biological and chemical automatic monitoring system and a monitoring method are provided to overcome the above problems. Summary of the invention

[0008] The object of the present invention is to provide a nuclear, biological and chemical automatic monitoring system and monitoring method to solve the problems raised in the above background technology.

[0009] In order to solve the above technical problems, the present invention provides a nuclear, biological and chemical automatic monitoring system, comprising: Environmental probe combination: deployed in the detection area to monitor environmental parameters in real time; the environmental probe combination includes gas composition sensors and microbial community monitoring devices. The microbial community monitoring device uses a culture dish with a preset culture medium; Data processing unit: connected to the environmental probe combination, used to collect data monitored by the environmental probe combination, build an environmental dynamic balance model, and compare the real-time monitoring data with the model; Indicator particle dispersing device: used to disperse indicator particles in the detection area; when the indicator particles come into contact with materials that may be used to disguise nuclear, biological and chemical items, obvious and observable phenomena will occur; Alarm unit: connected with the data processing unit and the indicating particle dispersion device.

[0010] Furthermore, the gas composition sensor is based on the metal oxide semiconductor principle and is a low-cost sensor used to detect concentration changes of common gas components including but not limited to oxygen, carbon dioxide, and volatile organic compounds; the expression of its gas concentration detection function is:

[0011] in, Considering the temperature and humidity Gas concentration after the impact. is the current ambient temperature, Calibrate the temperature of the sensor, is the temperature influence coefficient; is the current ambient humidity, Calibrate humidity for the sensor, is the humidity influence coefficient.

[0012] Furthermore, the microbial community monitoring device uses a culture dish with automatic moisturizing and temperature regulation functions; the bottom of the culture dish is made of transparent material and has tiny air holes on the edge; the culture medium uses peptone, beef extract, and yeast extract as main nutrients, with sodium chloride and agar added, and trace elements and specific growth factors are added according to the local microbial distribution characteristics.

[0013] Furthermore, the indicator particle dispersing device includes a high-precision spray device arranged on the package conveyor belt and a special coating arranged on the ground and walls of the package stacking area; the high-precision spray device uses microcomputer control technology to evenly spray a solution containing indicator particles on the surface of the package when the package passes, and the special coating also contains indicator particles.

[0014] Furthermore, the data processing unit applies a moving average method combined with a Kalman filter algorithm to the gas concentration data to calculate the optimal estimated values ​​of the gas concentrations including but not limited to oxygen, carbon dioxide, and VOCs in different time periods; and classifies and counts the types and quantities of microorganisms through image recognition technology based on deep learning.

[0015] Furthermore, the alarm unit includes a first-level alarm and a second-level alarm; the first-level alarm is triggered when the data processing unit determines that the environmental parameters are abnormal, and the second-level alarm is triggered when the indicator particles detect an abnormality.

[0016] A nuclear, biological and chemical automatic monitoring method comprises the following steps: Step 1: Set up an environmental probe assembly in the detection area to monitor environmental parameters in real time, covering gas composition and microbial communities; Step 2: Use the data processing unit to collect the data monitored by the environmental probe combination, establish an environmental dynamic balance model, and compare the real-time monitoring data with the environmental dynamic balance model; if the environmental parameters exceed the normal fluctuation range, it is determined that there may be dangerous goods; Step 3: Spread indicator particles in the detection area through the indicator particle spreading device; when the indicator particles interact with materials that may be used to disguise nuclear, biological and chemical items to produce obvious phenomena, it is determined that there are malicious disguised items; Step 4: When it is determined that there may be dangerous items or malicious disguised items, the alarm unit is triggered to sound an alarm.

[0017] Furthermore, in step 1, when the gas composition sensor detects the gas concentration, the influence of temperature and humidity on the sensor performance is considered, and the formula is used:

[0018] Calculate the gas concentration.

[0019] Furthermore, in step two, the data processing unit processes the gas concentration data using a moving average method combined with a Kalman filter algorithm, and classifies and counts the types and quantities of microorganisms using an image recognition technology based on deep learning.

[0020] Compared with the prior art, the present invention has the following beneficial effects: 1. Improve detection accuracy and reliability: Dealing with complex environmental interference: Real-time monitoring of environmental parameters, including gas composition and microbial communities, is performed through a combination of environmental probes. A dynamic balance model of the environment is constructed using a data processing unit, and the real-time monitoring data is compared with it. It can effectively distinguish between normal environmental fluctuations and anomalies caused by dangerous goods. Compared with the existing technology that only analyzes signals based on a single dimension, this multi-dimensional comprehensive consideration method can accurately identify dangerous goods signals, avoid misjudgments caused by environmental factors and interference from ordinary items, and significantly improve detection accuracy and reliability.

[0021] Identifying malicious disguised items: The indicator particle dispersing device uses special interactions between materials. When the indicator particles come into contact with materials that may be used to disguise nuclear, biological and chemical items, obvious and observable phenomena will occur. For example, for camouflage materials containing special fluorocarbon groups, the prepared indicator particles will show obvious color changes when reacting with them, which solves the problem that the existing technology is difficult to detect malicious disguised items and improves the success rate of detecting such dangerous items.

[0022] 2. Reduce testing costs: Environmental probe combination is low cost: The environmental probe combination uses low-cost gas composition sensors based on the principle of metal oxide semiconductors, and the culture medium components of the microbial community monitoring device are common and easy to obtain, which reduces the hardware cost of the detection system as a whole. At the same time, these low-cost devices are sensitive to small changes in the environment, ensuring the reliability of detection and providing the possibility for large-scale application.

[0023] 3. Improve data processing capabilities: Gas concentration data processing: The data processing unit applies the moving average method combined with the Kalman filter algorithm to the gas concentration data. Compared with the traditional moving average method, it can effectively remove the sensor data noise caused by electromagnetic interference and airflow fluctuations generated by electrical equipment and ventilation systems in complex environments such as postal sorting centers, and calculate the optimal estimate of gas concentration in different time periods, thereby improving the accuracy and stability of the data and providing reliable support for determining the normal fluctuation range of gas concentration.

[0024] Analysis of microbial species and quantity: Using deep learning-based image recognition technology and convolutional neural networks to classify and count microbial species and quantities, the traditional image recognition method is difficult to accurately process microbial images with diverse morphologies and complex features. Through training with a large number of annotated microbial image data sets, the model recognition accuracy can reach more than 95%, providing accurate data for the analysis of microbial community changes and improving the environmental dynamic balance model.

[0025] 4. Optimize microbial community detection: Accurately obtain microbial information: The microbial community monitoring device uses a culture dish with automatic moisturizing and temperature regulation functions to simulate a stable and suitable microbial growth environment to ensure accurate monitoring of the dynamic changes of the microbial community. The high-definition camera regularly shoots the culture dish with a transparent bottom, combined with deep learning-based image recognition technology, it can efficiently and accurately obtain relevant information such as the type and quantity of microorganisms, so that the microbial community, an important environmental indicator, can play a full role in the detection system.

[0026] Assist in judging the impact on the environment: Use the stability of the microbial community to assist in judging whether the environment is affected by nuclear, biological and chemical substances. Because interference factors generally cannot change the ecological balance of the microbial community, while nuclear, biological and chemical substances can cause significant changes. When investigating disguised nuclear substances, signs of the presence of nuclear substances can be discovered in a timely manner by monitoring abnormal growth of microbial communities (reduction in number, change in species, etc.).

[0027] 5. Establish a comprehensive collaborative testing mechanism: Multiple technologies cooperate: Environmental dynamic balance monitoring, indicator particle detection based on material interaction, detection based on packaging material characteristics, detection based on secondary changes in microbial communities, and detection based on package surface charge distribution. Environmental dynamic balance monitoring narrows the scope of suspicious areas from a macroscopic perspective, and other technologies accurately identify suspicious items from different microscopic angles, building a comprehensive and efficient collaborative detection mechanism to further improve the accuracy, reliability and efficiency of detection.

[0028] Flexible adjustment of detection strategies: In actual applications, this collaborative detection mechanism can flexibly adjust detection strategies according to real-time changes in the environment. When transporting a large number of electronic devices, the weight of each detection technology is automatically adjusted to strengthen the detection method with less interference; when responding to a large-scale influenza epidemic, the detection function of specific viruses can be added in the microbial detection link. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 The present invention is a schematic diagram of a nuclear, biological and chemical automatic monitoring system and monitoring method. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0031] See also Figure 1 , the present invention provides a technical solution: See also Figure 1 As shown, an embodiment of a nuclear, biological and chemical automatic monitoring system and monitoring method: 1. Background and Scene Large postal sorting centers need to handle a large number of parcels, luggage and goods from different regions every day, with frequent personnel movement and huge goods turnover. According to statistics, the sorting center handles hundreds of thousands of parcels per day and has more than a thousand internal staff. Affected by factors such as the type of goods and ventilation conditions, the temperature fluctuation range in different areas is 20-30℃, and the humidity fluctuation range is 40%-60%. This complex environment makes it difficult for conventional detection technology to effectively deal with the detection problems of interference and malicious disguised items.

[0032] By collecting and analyzing actual operational data from multiple large sorting centers in the postal industry, we found that the growth in business volume and the frequent flow of people and goods have greatly increased the complexity of the environment. In similar complex scenarios, the previous detection technology had a false detection rate of up to 20% (this value was obtained through statistical analysis of actual detection data from multiple large sorting centers in the postal industry for one year. During the statistical period, all samples that were detected as "dangerous goods" were strictly checked twice to determine the number of normal items that were actually normal. After calculation, the number of normal items that were falsely detected accounted for 20% of the total number of detected items, thus determining the false detection rate to be 20%. The basis for the inference is that the detection environment of large sorting centers is complex and representative, and long-term multi-center data collection can more comprehensively reflect the false detection of conventional detection technology in actual operation), and the missed detection rate was as high as 15% (obtained through simulated dangerous goods mixing experiments in multiple large sorting centers. In the simulation experiment, a certain number of known dangerous goods were mixed into the normal parcel flow, and the detection of the detection system was observed. After the experiment, the number of dangerous goods that were not detected was counted, and it was calculated that the number of dangerous goods that were not detected accounted for 15% of the total number of dangerous goods that were actually mixed in, thus determining the missed detection rate to be 15%. The simulation experiment restores the real scene as much as possible, and can effectively evaluate the missed detection of dangerous goods by the detection technology), which cannot meet the safety detection needs.

[0033] 2. Implementation of the principle of environmental dynamic balance 1. Environmental probe settings Gas composition sensor An "environmental probe assembly" is set up every 5 meters in key areas such as the conveyor belts and parcel stacking areas of the postal sorting center. The gas composition sensor uses a low-cost sensor based on the principle of metal oxide semiconductors. The sensor can keenly capture the concentration changes of common gas components such as oxygen, carbon dioxide, and volatile organic compounds (VOCs).

[0034] Working principle and formula: When gas adsorbs and reacts with the surface of metal oxide, it will cause the conductivity to change. The traditional formula for detecting gas concentration is: (1) ( is the gas concentration, is the sensor characteristic constant, is the conductivity change).

[0035] However, in the actual complex environment of the postal sorting center, factors such as temperature and humidity will significantly affect the performance of the sensor. Considering these factors, the formula is obtained: (2) in, Considering the temperature and humidity Gas concentration after the impact. is the current ambient temperature, Calibrate the temperature of the sensor, is the temperature influence coefficient; is the current ambient humidity, Calibrate humidity for the sensor, is the humidity influence coefficient. Through a large number of experimental measurements, in the environment of this postal sorting center, for the detection of carbon dioxide gas, the value range is [0.001-0.003] and the value range is [0.002-0.005]. These coefficients are obtained by fitting the experimental data using the least squares method based on the characteristics of different gases and different sensors.

[0036] Experimental studies have shown that changes in temperature and humidity will change the physical and chemical properties of metal oxide semiconductors, thereby affecting their adsorption and reaction processes to gases, and significantly interfering with the linear relationship between conductivity changes and gas concentrations. Through multiple sets of gas concentration detection experiments under different temperature and humidity conditions, combined with data analysis methods, the influence of temperature and humidity on the detection results was determined, and the above formula was derived.

[0037] The resulting formula takes into account the key interference factors in the actual environment, can calculate the gas concentration more accurately, improve the accuracy of environmental dynamic balance monitoring, and reduce the risk of misjudgment caused by environmental factors. For solving the problem of interference in complex environments, this formula can ensure the reliability of gas concentration detection data and avoid misjudgment caused by similar interference signals caused by temperature and humidity fluctuations. At the same time, when investigating disguised nuclear materials, accurate gas concentration data can help determine whether the environment has broken the dynamic balance due to the presence of nuclear materials. If nuclear materials change the ionization balance of the surrounding air, it may cause subtle changes in the gas composition. This formula ensures the accuracy of the detection of these changes and provides a reliable basis for subsequent judgments.

[0038] Microbial community monitoring device The microbial community monitoring device uses a specially designed culture dish with automatic moisturizing and temperature regulation functions. The bottom of the culture dish is made of transparent material, which is convenient for regular shooting with a high-definition camera. Tiny air holes are designed on the edge to ensure that the microorganisms have a certain gas exchange with the external environment and prevent contamination from external impurities. The culture medium uses peptone, beef extract, and yeast extract as the main nutrients, and adds appropriate amounts of sodium chloride, agar, etc., and adds trace elements and specific growth factors according to the local microbial distribution characteristics. For example, to promote the growth of lactic acid bacteria, add appropriate amounts of glucose and calcium carbonate; for halophilic bacteria, appropriately increase the sodium chloride content. Common local microorganisms include Bacillus subtilis, Escherichia coli, lactic acid bacteria, and molds such as Penicillium and Aspergillus.

[0039] Microbial growth is extremely sensitive to environmental conditions, and stable temperature and humidity are the basis for ensuring the normal growth and reproduction of microorganisms. The transparent bottom facilitates the use of machine vision technology to collect and analyze microbial images. The air vent design is based on the balance between microbial aerobic respiration and prevention of contamination by foreign bacteria. The composition and additives of the culture medium are determined through in-depth biochemical analysis of the metabolic characteristics and nutritional requirements of local microorganisms, and common microbial species are obtained through comprehensive analysis of local environmental microbial samples using high-throughput sequencing technology.

[0040] Simulate a stable and suitable environment for microbial growth to ensure that the dynamic changes of microbial communities can be accurately monitored, introduce biological indicators for environmental dynamic balance monitoring, and enhance the sensitivity of the detection system to environmental changes. When dealing with complex environmental disturbances, the stability of microbial communities can be used as an important basis for judging whether the environment is normal. Interference factors are generally difficult to change the ecological balance of microbial communities in the entire region, while nuclear, biological and chemical substances may cause significant changes in microbial communities. For the investigation of disguised nuclear materials, since nuclear radiation may damage the DNA of microorganisms, leading to abnormal growth of microbial communities, such as a decrease in quantity and a change in species, these abnormalities can be discovered in a timely manner through real-time monitoring of microbial communities, thereby locking in the area where suspicious items are located.

[0041] 2. Establishment of the environmental dynamic balance model Data Collection Under the condition that the sorting center is operating normally and there are no dangerous goods present, data is collected from each environmental probe combination for one week.

[0042] The time span of one week can cover various periods of daily operations of the sorting center, including business peaks and troughs, as well as environmental conditions under different weather conditions, ensuring that the collected data can fully reflect the environmental characteristics under normal operating conditions and is fully representative. It provides a sufficient and comprehensive data basis for subsequent data processing and model building, ensuring that the model can accurately depict the range of normal environmental parameters. This is crucial for efficient interference elimination. By establishing an accurate normal environment model, small fluctuations in environmental parameters can be clearly distinguished from abnormal changes caused by dangerous goods, avoiding misjudgments due to natural fluctuations in the environment. When investigating disguised nuclear materials, the model provides a benchmark for judging whether the environment is in a normal equilibrium state. Once the environmental parameters are found to deviate from the range of this model, it can be preliminarily determined that there are suspicious items, which will provide a direction for further testing.

[0043] Data processing Gas concentration data processing: For gas concentration data, the improved moving average method combined with the Kalman filter algorithm is used to calculate the optimal estimated values ​​of oxygen, carbon dioxide, VOCs and other gas concentrations in different time periods. The traditional moving average method formula is: (3) is the time window length of the moving average.

[0044] In the complex and ever-changing environment of the postal sorting center, the data noise is large, and the simple moving average method cannot effectively remove the noise interference. After the Kalman filter algorithm is introduced, its state equation is: (4) The measurement equation is: (5) in, for The state vector at time t (here, the estimated gas concentration), is the state transfer matrix, is the control input matrix, is the control vector (can be set to 0 in this scenario), is the process noise, for The measured value at the moment (i.e. the gas concentration value measured by the sensor), is the observation matrix, is the measurement noise. Through iterative calculation, a more accurate gas concentration estimate can be obtained.

[0045] There are various electrical equipment and ventilation systems in the postal sorting center, which will generate electromagnetic interference, airflow fluctuations, etc., resulting in noise in the sensor data. As an optimal linear estimation algorithm, the Kalman filter algorithm can integrate the dynamic information of the system with the measurement data, effectively filter out noise, and improve the accuracy and stability of the data. By simulating and analyzing the actual collected data, comparing the traditional moving average method with the algorithm after the introduction of the Kalman filter, the results show that the improved algorithm can effectively reduce the data noise variance by 30%; this is obtained by simulating and analyzing the actual collected gas concentration data. The gas concentration data collected over a period of time are processed using the traditional moving average method and the improved moving average method combined with the Kalman filter algorithm. By calculating the noise variance of the data processed by the two algorithms, it is found that the noise variance of the data processed by the improved algorithm is reduced by 30% compared with the traditional algorithm. The specific calculation process is to first use the traditional moving average method to process the data and calculate its noise variance. , and then use the improved algorithm to process the same data and calculate the noise variance , according to the formula The result shows that the ratio of reducing data noise variance is 30%. The algorithm comparison based on the actual collected data can truly reflect the difference between the two algorithms in processing data noise.

[0046] The resulting data processing method can process gas concentration data more accurately, effectively remove noise interference, provide more reliable data support for determining the normal fluctuation range of gas concentration, and improve the accuracy and reliability of the environmental dynamic balance model. This helps to accurately identify real dangerous goods signals in complex environments and avoid misjudgment of similar dangerous goods signals due to noise interference. When investigating disguised nuclear materials, accurate data processing can promptly detect abnormal changes in gas concentration caused by the presence of nuclear materials, providing strong data support for determining whether there are disguised nuclear materials.

[0047] Analysis of microbial species and quantity: For the species and quantity of microorganisms, the microorganisms in the culture dish are classified and counted through deep learning-based image recognition technology. A convolutional neural network (CNN) model is used, and its network structure includes multiple convolutional layers, pooling layers, and fully connected layers. During the training process, a large number of annotated microbial image data sets are used for training, and the loss function uses the cross entropy loss function: (6) in, is the sample size, is the number of microbial categories, For sample Belongs to category The true label (0 or 1), Predict samples for the model Belongs to category The network parameters are adjusted through the back propagation algorithm so that the model can accurately identify different types of microorganisms and count their numbers. The number of each microorganism at different time points is counted, and its proportion in the total number of microorganisms is calculated. For example, after a large amount of statistical analysis of data, it is determined that the number of Bacillus subtilis accounts for [20%-30%] of the total number of microorganisms, and the number fluctuates between ±5%; the number of Escherichia coli accounts for [10%-20%], and the fluctuation range is between ±3%. These data are based on data collected by a combination of multiple environmental probes at different time periods and locations, and are obtained using statistical methods such as hypothesis testing and regression analysis.

[0048] Microorganisms are diverse in morphology and complex in features, and traditional image recognition methods are difficult to accurately classify and count. Deep learning convolutional neural networks have shown excellent performance in the field of image recognition and can automatically extract features of microbial images. The cross entropy loss function can effectively measure the difference between the model's predicted value and the true value in classification problems. The model parameters are continuously optimized through the back propagation algorithm to improve the recognition accuracy of the model. Experimental verification shows that the recognition accuracy of the CNN model for common microorganisms in this area can reach more than 95%, which is verified by a large number of experiments. Image samples of common microorganisms in this area were collected to construct a data set containing 5,000 samples, of which 4,000 samples were used to train the CNN model and 1,000 samples were used for testing. During the test, the number of microbial samples correctly identified by the model was recorded. After testing, the number of samples correctly identified by the model was more than 950. According to the formula (number of correctly identified samples / total number of test samples) × 100%, the recognition accuracy can reach more than 95%. The inference is based on a large number of representative sample tests, which can more accurately reflect the recognition ability of the model in practical applications.

[0049] Image recognition technology based on deep learning can efficiently and accurately classify and count microorganisms, provide precise data for the analysis of microbial community changes, help to more accurately determine the normal fluctuation range of microbial-related parameters, and improve the environmental dynamic balance model. This makes it possible to effectively eliminate interference caused by ordinary items based on the stability of the microbial community in complex environments, and accurately judge whether the environment is affected by nuclear, biological and chemical substances. For the investigation of disguised nuclear materials, accurate microbial community data can help discover abnormal microbial growth caused by nuclear radiation. Even if the surface of the disguised nuclear material is no different from that of normal items, it is difficult to completely cover up the impact on the microbial community, thereby achieving effective investigation of suspicious items.

[0050] (III) Testing process In daily operations, environmental probes continuously monitor environmental parameters in real time and transmit data to the central processing unit. The central processing unit quickly compares the real-time data with the environmental dynamic balance model. If one or more parameters exceed the normal fluctuation range, such as the carbon dioxide concentration suddenly rises to more than 500ppm, and at the same time the proportion of Bacillus subtilis drops below 10%, the system will immediately determine that there may be dangerous goods in the area. At this time, the system automatically marks the packages in the area and nearby, and issues a level 1 alarm.

[0051] The entry of dangerous goods will disrupt the original ecological and chemical balance of the environment. Through a large number of experiments and actual case analysis, it is found that the presence of nuclear, biological, chemical and explosive dangerous goods often causes significant deviations from the normal range of parameters such as environmental gas composition and microbial communities. The thresholds set according to the established environmental dynamic balance model can effectively identify these abnormal changes.

[0052] Quickly and accurately lock suspicious areas, provide clear directions for subsequent precise detection, greatly improve detection efficiency, and reduce the potential harm time of dangerous goods in the sorting center. When dealing with complex environmental interference, this detection process based on environmental dynamic balance can quickly eliminate the interference caused by normal environmental fluctuations and focus detection on areas where dangerous goods may actually exist. For the investigation of disguised nuclear materials, once abnormal environmental parameters are found, the packages that may be disguised in the area can be paid special attention, and further investigation can be carried out in combination with subsequent detection methods, which greatly improves the pertinence and efficiency of the investigation.

[0053] 3. Implementation of camouflage identification based on material interaction 1. Preparation of indicator particles For similar plastic materials that may be used to disguise radioactive materials, it was found that they contain special fluorocarbon groups. Based on this, a kind of indicator particles with silica as the core and modified with organic molecules that have specific reactions to fluorocarbon groups on the surface were prepared. Silica nanoparticles were evenly dispersed in anhydrous ethanol to form a stable suspension, and 3-aminopropyltrimethoxysilane was added to react for several hours at 50°C under stirring conditions, so that the organic molecules were modified on the silica surface through chemical bonding. After multiple washings and centrifugal separations, the unreacted organic compounds were removed to obtain pure indicator particles.

[0054] Inference basis Advanced analytical techniques such as Fourier transform infrared spectroscopy (FT-IR) and nuclear magnetic resonance spectroscopy (NMR) were used to deeply analyze the camouflage material and determine the special fluorocarbon group structure. According to the principles of organic synthetic chemistry, under specific temperature and stirring conditions, the amino group in 3-aminopropyltrimethoxysilane can undergo a condensation reaction with the hydroxyl group on the surface of silica to form a stable chemical bond. At the same time, the organic group at the other end can undergo a specific chemical reaction with the fluorocarbon group to ensure the specificity and stability of the indicator particles.

[0055] The successful preparation of indicator particles with high specificity for camouflage materials provides a key material basis for subsequent camouflage identification and significantly improves the detection ability of malicious camouflage items. This is of great significance for solving the detection dilemma of malicious camouflage items. Even if the disguised items are close to normal items in physical and chemical properties, as long as they contain specific chemical groups used for camouflage, the indicator particles can react specifically with them and intuitively display abnormalities, thereby achieving accurate identification of camouflaged nuclear materials and making up for the shortcomings of conventional detection methods in detecting camouflaged items.

[0056] 2. Indicator particle dispersion A high-precision spray device is installed on the parcel conveyor belt of the postal sorting center. Using microcomputer control technology, a solution containing indicator particles is evenly sprayed on the surface of the parcel when the parcel passes. The solvent is volatile ethyl acetate, which evaporates quickly after spraying, so that the indicator particles are firmly attached to the surface of the parcel. At the same time, a layer of special paint containing indicator particles is applied on the ground and walls of the parcel stacking area.

[0057] The microcomputer control technology is based on a programmable logic controller (PLC). The spray time, spray volume and spray angle of the spray device are precisely controlled through a preset program to ensure that the solution is evenly sprayed on the package surface. Ethyl acetate has the characteristics of low boiling point and high volatility. It can evaporate in a short time, allowing the indicator particles to adhere tightly to the package surface. The special coating formula has been repeatedly optimized through experiments, and nano-level dispersion technology is used to ensure that the indicator particles are evenly dispersed in the coating. The film layer formed after the coating dries has good adhesion and air permeability, ensuring that the indicator particles can effectively contact the package surface.

[0058] The indicator particles can be widely and evenly contacted with the package, greatly improving the probability of disguise identification and ensuring that malicious disguised items can be discovered in time. This helps to increase the chance of contact with disguised nuclear materials in complex environments and solve the problem that disguised items are difficult to detect by conventional means. Whether the disguised items are hidden in a large number of packages or in a package stacking area, the indicator particles can cover them as much as possible, improving the success rate of detecting disguised nuclear materials, and it is low-cost and easy to apply on a large scale.

[0059] (III) Process of camouflage identification When there is a camouflage material containing fluorocarbon groups on the surface of the package to which the indicator particles are attached, the amino groups on the surface of the indicator particles react chemically with the fluorocarbon groups to generate a product with a distinct color (such as red). During daily inspections, staff can visually detect packages with color changes with the naked eye. At the same time, high-definition cameras are installed at key locations in the sorting center to monitor color changes on the surface of packages in real time using image recognition technology. Once a package with abnormal color is found, the system immediately issues a secondary alarm.

[0060] According to the organic chemical reaction mechanism, the reaction between amino groups and fluorocarbon groups will cause electron cloud rearrangement, producing products with specific absorption spectra, thus showing obvious color changes. The high-definition camera collects the surface image of the package, and uses the image recognition algorithm based on color feature extraction to calculate the color histogram, hue saturation value (HSV) and other characteristic parameters of the image, and compares them with the color characteristics of normal packages. Once an abnormality is found, an alarm is triggered immediately.

[0061] It provides an intuitive and efficient way to identify disguised items without the need for complex instrument analysis. It combines manual inspection with automatic image recognition technology to greatly improve detection efficiency and accuracy, and effectively reduce the risk of missed detection of dangerous items. In complex environments, this intuitive detection method can quickly detect disguised nuclear materials and avoid detection failures caused by environmental interference due to reliance on complex instruments. At the same time, for nuclear materials that look the same as normal items after disguise, the chemical reaction of the indicator particles can reveal their flaws. Through the dual protection of manual inspection and automatic image recognition, it ensures that suspicious items will not be missed, further improving the ability to detect disguised nuclear materials.

[0062] 4. Disguise Detection 1. Testing based on packaging material characteristics Special induction pads are set on the floor of the parcel stacking area. The induction pads are made of materials that have adsorption to specific packaging materials, such as fluorinated polymer packaging materials commonly used for nuclear material camouflage. Special induction pads are set on the floor of the parcel stacking area. The induction pads are made of materials that have adsorption to specific packaging materials, such as porous silica gel materials with surface modification of polyethylene glycol (PEG) for fluorinated polymer packaging materials commonly used for nuclear material camouflage. When the parcel is placed on the induction pad, if the packaging material contains the target component, it will be adsorbed to the induction pad. By measuring the change in adsorption force between the induction pad and the parcel, the formula is used: (7) For the change of adsorption force, is the adsorption coefficient. Through experimental determination, the adsorption coefficient for this type of material is between 0.5-0.8 (determined through a series of adsorption experiments. In the experiment, a porous silica gel material with surface modification of polyethylene glycol (PEG) was placed in an environment of fluorine-containing polymer packaging materials with different concentrations, and the adsorption force between the two was measured. According to the relationship between the adsorption force and the concentration of the packaging material, the adsorption coefficient under different conditions was calculated using the formula F=k×m (F is the adsorption force, k is the adsorption coefficient, and m is the change in mass of the sensing pad caused by adsorption). After many experiments, it was determined that the adsorption coefficient is between 0.5-0.8. The basis for the inference is that the adsorption coefficient range of the material for fluorine-containing polymer packaging materials can be accurately obtained through direct experimental measurement and calculation with relevant formulas). The change in the mass of the sensor pad caused by adsorption is combined with the preset threshold to determine whether it is suspicious. When the adsorption force exceeds a certain threshold, it indicates that the packaging material of the package may have been specially processed for nuclear material disguise, and the system marks it as a suspicious package.

[0063] The adsorption between different materials is based on the principle of intermolecular forces. By analyzing the commonly used camouflage packaging materials for nuclear substances, materials with strong adsorption are selected to make sensing pads. Experimental studies have shown that porous silica gel materials modified with PEG have a significant adsorption effect on fluorinated polymer packaging materials, and there is a certain correlation between the adsorption force and the content of the target component in the packaging material.

[0064] Starting from the characteristics of packaging materials, a simple adsorption principle is used to achieve preliminary screening of suspicious packages. This has unique advantages in solving interference problems in complex environments. It does not rely on complex signal analysis, and can effectively avoid signal interference caused by other items only through the physical property of adsorption. When investigating disguised nuclear substances, the package may be made of special materials, which can quickly lock in those packages that use specific suspicious packaging materials. Even if the disguised nuclear substances are well disguised in other aspects, the characteristics of the packaging materials are difficult to completely cover up, which greatly improves the pertinence and efficiency of the investigation and reduces the cost of detection.

[0065] 2. Detection of secondary changes in microbial communities When the package passes through the conveyor belt, in addition to spraying indicator particles, a special microbial activator is also sprayed. This activator can promote the growth and reproduction of microorganisms on the surface of the package, but for microbial communities affected by nuclear radiation, their growth response will be different from that of normal microbial communities. Under the action of the activator, the growth rate of normal microbial communities will show exponential growth within a certain period of time. For example, under the action of the activator, the growth rate of Escherichia coli conforms to the formula: (8) Among them is The number of microorganisms at a given moment, is the initial number of microorganisms, is the growth rate constant (experimentally determined to be between 0.05 and 0.08 for E. coli in this environment) (obtained through a simulation experiment in the postal sorting center environment. In the experiment, a certain amount of E. coli samples were placed in an environment similar to that of the sorting center, and microbial activators were added to measure the changes in the number of E. coli at regular intervals. According to the formula ; for The number of microorganisms at a given moment, is the initial number of microorganisms, is the growth rate constant, The k value is calculated by fitting and analyzing the number of E. coli measured at different time points. After many experiments, it is determined that the growth rate constant of E. coli in this environment is between 0.05-0.08. The inference is based on the simulation experiment of the actual environment and the analysis of the microbial growth data, which can accurately obtain the growth rate constant range of E. coli in this environment). For time. Microbial communities affected by nuclear radiation may have their DNA and other genetic materials damaged, so their growth rate will be significantly lower than normal, or even inhibited. By comparing the growth of microorganisms on the surfaces of different packages after the activator is applied, it can be determined whether the package is suspicious. If the growth rate of microorganisms on the surface of a package is significantly lower than the normal range, the system will mark it as a suspicious package for further inspection.

[0066] Microorganisms are extremely sensitive to radiation. Nuclear radiation can damage the DNA and other genetic materials of microorganisms, thus seriously affecting their normal growth and reproduction process. The mechanism of action of microbial activators is to provide additional nutrients and create a suitable growth environment, thereby accelerating the growth of microorganisms. Through a large number of experiments conducted in normal environments and simulated nuclear radiation environments, the growth of microorganisms after the action of activators was compared, and the difference in growth rates between the two was clarified.

[0067] This method cleverly utilizes the sensitivity of microorganisms to nuclear radiation and the promotion of microbial growth by activators, and provides an innovative detection method from the unique perspective of secondary changes in microbial communities. In a complex environment, it is difficult for other interfering factors to have an impact on the growth rate of microbial communities similar to that of nuclear radiation, which greatly reduces the possibility of misjudgment due to environmental interference. For the detection of disguised nuclear materials, even if the nuclear material is carefully disguised, the impact of radiation on microorganisms is difficult to be completely concealed. By closely observing the growth of microorganisms, it is possible to effectively discover packages that appear normal but actually hide nuclear materials. Moreover, this method is easy to operate and low in cost, opening up a new and effective way for investigation.

[0068] 3. Detection based on charge distribution on the package surface An electrostatic induction device is installed on the package conveyor belt. The device consists of a series of electrostatic induction probes, which can accurately detect the charge distribution on the package surface. The presence of nuclear materials may interfere with the charge distribution of surrounding materials, resulting in abnormal charge distribution on the package surface. During the transmission process, the surface charge distribution of normal packages is relatively uniform and conforms to certain statistical laws. Through the collection and in-depth analysis of a large amount of normal package surface charge distribution data, a charge distribution model for normal packages is established. When it is detected that the surface charge distribution of a package is significantly different from the normal model, such as when the local charge density is too high or too low, the system marks it as a suspicious package. For example, by calculating the charge density of different areas on the package surface: (9) for The charge density at the coordinates, is the charge on the region, is the area of ​​the region and is compared with the normal range. If the charge density of a certain area exceeds the normal range by 20%, the package is judged to be suspicious (derived through the collection and analysis of a large number of normal package surface charge distribution data. After collecting enough normal package surface charge distribution data, the average value μ and standard deviation σ of the normal charge density are calculated, and the charge density exceeding μ+20%×σ is judged to be abnormal. Through the analysis of a large amount of historical data, it is found that when the charge density exceeds the normal range by 20%, the probability that the package is related to dangerous goods increases significantly. The basis for inference is based on the statistical analysis of a large amount of normal package data to determine a reasonable threshold to effectively identify suspicious packages).

[0069] Nuclear materials are radioactive and will cause ionization of surrounding materials, thereby changing the charge distribution of surrounding materials. Electrostatic induction devices can keenly detect changes in charge distribution on the surface of objects. By detecting and analyzing a large number of normal packages, an accurate normal charge distribution model can be established, thereby effectively identifying suspicious packages with abnormal charge distribution.

[0070] This detection method starts from the unique perspective of charge distribution and uses a simple electrostatic induction principle to achieve efficient detection of suspicious packages. In complex environments, this method is not interfered by conventional signals from other items and only makes judgments based on the characteristic of charge distribution. For the investigation of disguised nuclear materials, even if the disguise is extremely sophisticated, the impact of nuclear materials on the surrounding charge distribution still exists. By comparing with the normal charge distribution model, abnormal situations can be quickly discovered and efficient detection of suspicious packages can be achieved. This method has high detection efficiency and accuracy, and the equipment cost is relatively low, providing strong technical support for solving detection problems in complex environments.

[0071] Summarize: The above-mentioned detection technologies cooperate with each other to build a comprehensive and efficient collaborative detection mechanism. Environmental dynamic balance monitoring lays a solid foundation for the entire detection system from a macro level. Through real-time monitoring of environmental parameters, it can quickly narrow the scope of suspicious areas and effectively eliminate interference caused by natural environmental fluctuations and ordinary objects. Various technologies such as indicator particle detection based on material interactions, detection based on packaging material characteristics, detection using secondary changes in microbial communities, and detection based on package surface charge distribution can accurately identify suspicious items from different microscopic perspectives.

[0072] When dealing with interference problems in complex environments, the coordinated operation of multiple detection technologies enables the detection system to conduct comprehensive analysis and judgment from multiple dimensions, effectively avoiding misjudgments caused by interference factors in a single detection method. In response to the detection dilemma of malicious disguised items, each detection technology is carefully designed to target possible flaws in disguised nuclear materials, complementing and verifying each other, greatly improving the success rate of detecting disguised nuclear materials. This collaborative detection mechanism not only significantly improves detection efficiency and reduces detection costs, but also further enhances the accuracy and reliability of detection, providing a solid and powerful guarantee for security detection work in complex places such as postal sorting centers.

[0073] In actual applications, this collaborative detection mechanism can flexibly adjust the detection strategy according to real-time changes in the environment. For example, when encountering special cargo transportation periods, such as when transporting a large number of electronic devices, since the electronic devices themselves may cause certain interference to some detection technologies, the system can automatically adjust the weights of each detection technology at this time, and strengthen the detection methods that are less affected by interference, such as environmental dynamic balance and microbial community monitoring, to ensure the accuracy of the detection work. At the same time, in response to large-scale influenza epidemics, in order to prevent the spread of viruses through packages, the detection function of specific viruses can be added to the microbial detection link, and the potential risk of virus transmission can be discovered in a timely manner by monitoring virus-related indicators in the microbial community.

[0074] In addition, the maintenance and optimization of this collaborative detection mechanism is also crucial. Regularly calibrate and maintain hardware equipment such as environmental probes, sensor pads, and electrostatic induction devices to ensure their stable performance. At the same time, use big data analysis technology to deeply mine the long-term accumulated detection data, and continuously optimize the parameter settings and threshold settings of each detection technology to adapt to the ever-changing environment and camouflage methods. For example, by analyzing the detection data of different seasons and different sources of goods, it is found that packages in certain areas may cause natural fluctuations in microbial communities due to environmental factors in certain seasons, thereby adjusting the corresponding microbial detection thresholds to avoid misjudgment.

[0075] With the continuous advancement of science and technology, the mechanism can also easily integrate new detection technologies and methods. For example, if a material detection method based on quantum sensing technology appears in the future, it can be integrated into the existing detection system to further enhance the detection capabilities of disguised nuclear materials and other dangerous goods. In addition, through data sharing and experience exchange with other postal sorting centers, it continuously improves its own detection mechanism to continuously safeguard the safe and stable development of the postal industry.

[0076] Application expansion and future prospects 1. Cross-domain application ideas This collaborative detection mechanism is not only applicable to postal sorting centers, but its concepts and some technologies can also be extended to other fields. In the baggage security check at the airport, it also faces the challenge of detecting complex environments and potentially dangerous goods. We can learn from the idea of ​​dynamic environmental balance monitoring to conduct real-time monitoring of environmental parameters such as air quality, temperature and humidity in key areas such as airport waiting halls and baggage handling areas, and establish an environmental model. Once abnormal fluctuations occur in environmental parameters, it may indicate that dangerous goods have affected the environmental balance, thereby triggering a targeted detection process. In port cargo inspections, methods based on packaging material characteristics and microbial community detection can also play an important role. Many imported and exported goods are packaged in a variety of ways. By setting up similar sensing pads in the cargo stacking area to detect special packaging materials, and using microbial detection technology to monitor changes in microbial communities on the surface of the cargo, contraband or contaminated items hidden in the cargo can be effectively discovered.

[0077] 2. Intelligent and automated upgrade direction In the future, this collaborative detection mechanism will develop towards a higher level of intelligence and automation. On the one hand, the deep learning algorithm of artificial intelligence is introduced to conduct in-depth fusion analysis of multi-source detection data. It can not only quickly identify known dangerous goods characteristics and environmental abnormal patterns, but also discover potential dangerous goods threat patterns through learning a large amount of historical data and real-time data, and realize early warning of unknown dangers. On the other hand, the automated operation process will be further improved. For example, when the detection system finds a suspicious package, it automatically guides the robotic arm or mobile robot to accurately grab the suspicious package and transfer it to a special isolation detection area for more in-depth detection and analysis, reducing manual intervention and reducing the risk of staff contact with dangerous goods.

[0078] 3. Integration Trend with Emerging Technologies With the continuous development of emerging technologies such as 5G, the Internet of Things, and blockchain, the collaborative detection mechanism will be deeply integrated with them. The high-speed and low-latency characteristics of 5G technology can realize real-time and fast transmission of detection data, ensuring that the central processing unit can obtain data from each detection device in a timely manner and respond quickly. Internet of Things technology can connect all detection equipment into a huge network to achieve intelligent linkage and information sharing between devices. Blockchain technology can be used to ensure the security and non-tamperability of detection data, ensure the credibility of detection results, and provide reliable data support for subsequent legal issues that may be involved. For example, in cross-border postal transportation, postal departments of various countries can share detection data through blockchain technology to achieve full-process safe traceability of cross-border packages.

Claims

1. A nuclear, biological and chemical automatic monitoring system, characterized in that: include: Environmental probe combination: deployed in the detection area to monitor environmental parameters in real time; The environmental probe portfolio includes gas composition sensors and microbial community monitoring devices, the latter of which uses culture dishes and is pre-set with culture media; Data processing unit: connected to the environmental probe combination, used to collect data monitored by the environmental probe combination, build an environmental dynamic balance model, and compare the real-time monitoring data with the model; Indicator particle scattering device: used to scatter indicator particles in the detection area; When the indicator particles come into contact with materials that may be used to disguise NBC agents, a clearly observable phenomenon will occur; Alarm unit: connected with the data processing unit and the particle dispersion indicating device, the alarm unit includes a first-level alarm and a second-level alarm.

2. The nuclear, biological and chemical automatic monitoring system according to claim 1, characterized in that: The gas composition sensor is based on the principle of metal oxide semiconductor and is a low-cost sensor used to detect the concentration changes of common gas components including but not limited to oxygen, carbon dioxide, and volatile organic compounds. The expression of its gas concentration detection function is: in, Considering the temperature and humidity The gas concentration after the impact, is the current ambient temperature, Calibrate the temperature of the sensor, is the temperature influence coefficient; is the current ambient humidity, Calibrate humidity for the sensor, is the humidity influence coefficient.

3. The nuclear, biological and chemical automatic monitoring system according to claim 1, characterized in that: The microbial community monitoring device uses a culture dish with automatic moisturizing and temperature regulation functions; the bottom of the culture dish is made of transparent material and has tiny air holes on the edge; the culture medium uses peptone, beef extract, and yeast extract as the main nutrients, with sodium chloride and agar added, and trace elements and specific growth factors added according to the local microbial distribution characteristics.

4. The nuclear, biological and chemical automatic monitoring system according to claim 1, characterized in that: The indicator particle dispersing device includes a high-precision spray device installed on the package conveyor belt and a special coating installed on the ground and walls of the package stacking area; the high-precision spray device uses microcomputer control technology to evenly spray a solution containing indicator particles on the surface of the package when the package passes. The special coating also contains indicator particles.

5. The nuclear, biological and chemical automatic monitoring system according to claim 1, characterized in that: The data processing unit uses the moving average method combined with the Kalman filter algorithm to calculate the optimal estimated values ​​of gas concentrations including but not limited to oxygen, carbon dioxide, and VOCs in different time periods; and classifies and counts the types and quantities of microorganisms through image recognition technology based on deep learning.

6. The nuclear, biological and chemical automatic monitoring system according to claim 1, characterized in that: When the data processing unit determines that the environmental parameters are abnormal, a first-level alarm is triggered, and when the indicator particles detect an abnormality, a second-level alarm is triggered.

7. A nuclear, biological and chemical automatic monitoring method, characterized in that: The following steps are involved: Step 1: Set up an environmental probe assembly in the detection area to monitor environmental parameters in real time, covering gas composition and microbial communities; Step 2: Use the data processing unit to collect the data monitored by the environmental probe combination, establish an environmental dynamic balance model, and compare the real-time monitoring data with the environmental dynamic balance model; if the environmental parameters exceed the normal fluctuation range, it is determined that there may be dangerous goods; Step 3: Spreading indicator particles in the detection area through the indicator particle spreading device; When the indicator particles interact with materials that may be used to disguise nuclear, biological and chemical items and produce obvious phenomena, it is determined that malicious disguised items exist; Step 4: When it is determined that there may be dangerous items or malicious disguised items, the alarm unit is triggered to sound an alarm.

8. A nuclear, biological and chemical automatic monitoring method as claimed in claim 7, characterized in that: In step 1, when the gas composition sensor detects the gas concentration, the influence of temperature and humidity on the sensor performance is considered and the formula is used: Calculate the gas concentration.

9. The nuclear, biological and chemical automatic monitoring method according to claim 7, characterized in that: In step two, the data processing unit processes the gas concentration data using a moving average method combined with a Kalman filter algorithm, and classifies and counts the types and quantities of microorganisms using deep learning-based image recognition technology.

Images