A radon concentration detection system and method

Abstract

This invention discloses a radon concentration detection system and method, belonging to the field of environmental monitoring technology. The system includes a radon collection device integrating environmental parameter monitoring functions, a radon sensor with temperature compensation, and advanced data processing and analysis software. The radon collection device collects radon samples from inside and outside urban buildings, while the environmental parameter monitoring function records the temperature and humidity of the sampling site in real time. The radon sensor with temperature compensation accurately measures radon concentration and automatically adjusts the calibration coefficient to eliminate the influence of temperature fluctuations. The data processing and analysis software is responsible for collecting, processing, and analyzing all data, ultimately outputting an accurate radon concentration report. This invention achieves accurate measurement of radon concentration in urban environments, free from interference from factors such as environmental humidity and temperature. By integrating environmental parameter monitoring functions and temperature compensation technology, the system significantly improves the accuracy and stability of measurements.

Description

Technical Field

[0001] This invention belongs to the field of environmental monitoring technology, specifically relating to a radon concentration detection system and method. Background Technology

[0002] Accurate detection of radon gas is of paramount importance in urban environmental monitoring. Radon is a colorless and odorless radioactive gas, and long-term exposure to high concentrations of radon increases the risk of lung cancer. Therefore, real-time monitoring of radon concentrations in different areas and buildings within a city is crucial for protecting public health, preventing occupational diseases, and assessing building safety performance.

[0003] Traditional radon detection methods primarily rely on passive samplers or active detectors. While these devices can reflect radon concentration to some extent, they often suffer from long detection cycles, limited accuracy, and poor real-time data delivery. Furthermore, traditional methods typically depend on manual on-site operation, which is not only inefficient but also makes it difficult to achieve continuous and efficient monitoring over large urban areas.

[0004] Radon concentration in urban environments is influenced by a variety of factors, such as soil type, building structure, ventilation conditions, and groundwater level. These factors make the distribution and concentration changes of radon highly complex and uncertain. Therefore, relying solely on traditional single-point detection methods is insufficient to comprehensively and accurately reflect the radon situation in urban environments. Summary of the Invention

[0005] This invention aims to address the shortcomings of existing technologies by proposing a radon concentration detection system and method. Combining advanced sensor technology, IoT communication technology, and data analysis algorithms, it aims to achieve real-time monitoring, efficient transmission, and intelligent analysis of radon concentrations in different urban areas. By constructing a distributed monitoring network and integrating dynamic monitoring of environmental factors, this system can provide more comprehensive, accurate, and timely radon detection data, offering strong support for urban environmental protection and public health monitoring.

[0006] To achieve the above objectives, the present invention provides the following solution: a radon concentration detection system, comprising:

[0007] Radon gas collection module, used to collect pure radon gas samples in urban environments;

[0008] The enrichment device is connected to the radon gas collection module and is used to enrich the radon gas sample to obtain an enriched sample.

[0009] The radon ionization chamber detector is connected to the enrichment device and is used to measure radon in the enriched sample based on ionization chamber technology to obtain radon detection results in the form of electrical signals.

[0010] The calibration and verification system is connected to the radon ionization chamber detector and is used to calibrate the radon detection results based on a standard radon source.

[0011] The temperature control system is connected to the calibration and verification system and has a built-in temperature and humidity sensor and control system to maintain a stable sampling environment.

[0012] The signal processing unit is connected to the calibration and verification system and is used to convert electrical signals into digital signals;

[0013] The cloud computing platform is connected to the signal processing unit and is used to receive the radon detection results and obtain the radon concentration based on the radon detection results;

[0014] The data analysis mobile platform and the cloud computing platform are used to generate a radon concentration distribution map based on the radon concentration.

[0015] The intelligent early warning system and the cloud computing platform are used to trigger an early warning mechanism based on a preset threshold and the radon concentration.

[0016] More preferably, the position and sampling time of the radon gas collection module are optimized to obtain the optimal sampling position and sampling time window.

[0017] More preferably, the calibration and verification system is based on a dynamic calibration method, which automatically adjusts the detection parameters according to environmental changes.

[0018] More preferably, the method by which the temperature control system maintains a stable sampling environment includes:

[0019] Calculate the difference between the current ambient temperature and the reference temperature: ΔT = T current -T base ;

[0020] Based on the differences, the measurement parameters are adjusted using a preset algorithm model: Sensitivity S adjusted =S base ×(1+k s ×ΔT), integration time t adjusted =t base ×(1+k t ×ΔT) n ), where S base Indicates the reference sensitivity; t base Indicates the reference integration time; k s The temperature compensation coefficient representing the integration time; k t The temperature compensation coefficient represents the integral time; n represents the exponential parameter for adjusting the integral time.

[0021] The adjusted parameters were calibrated over time to verify the effect, and then adjusted again based on feedback.

[0022] Measurements were performed using the adjusted parameters, and the results were transmitted to a mobile data analytics platform.

[0023] Identify the correlation patterns between temperature and measurement error, and optimize the algorithm.

[0024] More preferably, the method for obtaining radon concentration includes:

[0025] The input data is preprocessed to obtain radon concentration data. A multiple linear regression model is used to compensate for temperature and humidity in the radon concentration data. Then, an exponential weighted moving average algorithm is used for smoothing.

[0026] A radon concentration prediction model is constructed, and the radon concentration is obtained based on the prediction model.

[0027] More preferably, the intelligent early warning system also provides early warnings based on a radon exposure risk index;

[0028] Radon exposure risk index: RI = (C a ×t) / (RL);

[0029] In the formula: RI is the risk index; C a t represents the average radon concentration; t represents the exposure time; and RL represents the reference level.

[0030] The present invention also provides a method for detecting radon gas concentration, comprising the following steps:

[0031] Radon gas is collected in different areas of the city using a radon gas collection module;

[0032] The collected radon gas samples were tested to obtain radon concentration data;

[0033] Processing and analyzing the detection data;

[0034] A radon concentration distribution map is generated based on the processed data.

[0035] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0036] Environmental adaptability optimization: For complex urban environments (such as densely built-up areas and busy traffic areas), optimize sampling locations and sampling times to reduce environmental interference and improve detection accuracy.

[0037] Multi-parameter fusion analysis: Combining environmental parameters such as temperature, humidity, air pressure, and wind speed, and using multiple regression analysis or machine learning algorithms, the accuracy of radon concentration prediction models can be improved.

[0038] Dynamic calibration technology: Develop a dynamic calibration method based on online monitoring to automatically adjust detection parameters according to environmental changes, ensuring long-term stability and accuracy.

[0039] Intelligent route planning: For mobile detection systems, GIS and IoT technologies are used to intelligently plan detection routes to ensure efficient coverage of key urban monitoring areas.

[0040] User-friendly interface and data analysis tools: The system features an intuitive and easy-to-use user interface and provides visual data analysis reports, including radon concentration distribution maps, trend analysis, and abnormal event records, to facilitate management decision-making.

[0041] The radon detection system and method proposed in this invention can efficiently and accurately detect radon in urban environments, providing strong support for urban environmental protection, public health monitoring, and geological disaster early warning. Attached Figure Description

[0042] To more clearly illustrate the technical solution of the present invention, the drawings used in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a framework diagram of a radon concentration detection system according to an embodiment of the present invention. Detailed Implementation

[0044] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0046] Example 1:

[0047] like Figure 1 As shown, this embodiment provides a radon concentration detection system. The core of the system consists of four major modules: radon gas acquisition, ultra-sensitive sensing, data processing and communication, and remote monitoring. The precise layout and efficient interconnection form a city-wide monitoring network, realizing real-time monitoring of radon concentration and high-speed data transmission. Figure 1 The interaction between the acquisition module and the data processing unit was highlighted, emphasizing the built-in ultra-sensitive sensor and its protective structure to accurately capture radon signals; the data processing unit analyzes the data in real time and transmits it quickly to a remote platform to ensure accurate and timely data.

[0048] Specifically, the system includes:

[0049] The radon gas collection module is used to collect pure radon gas samples from the urban environment. Specifically, it employs a high-efficiency, low-noise air pump combined with a precision filter to ensure the collection of pure radon gas samples from the urban environment.

[0050] To improve the accuracy and reliability of the data, the collected raw data is preprocessed, including data cleaning, outlier removal, and data smoothing.

[0051] The data cleaning process employs a multi-stage verification mechanism to ensure data quality. Format verification: checks whether the data conforms to preset format specifications (such as timestamp format, numerical range, etc.); Integrity check: uses a hash checksum algorithm to verify the integrity of the data packets: checksum = Σ(data byte )mod 256; Device status association verification: Associate the data with the device status log and remove the data collected during the period of device abnormality.

[0052] An improved box plot method combined with a moving window technique was used for outlier removal. Specifically, the statistics within the sliding window (window size = 24 hours) were calculated: Q1 = 25th percentile; Q3 = 75th percentile; IQR = Q3 - Q1; outlier threshold = [Q1 - k * IQR, Q3 + k * IQR] (k = 1.5-3.0 adjustable). Continuous outliers were specially processed to avoid mistakenly deleting true peak data.

[0053] An adaptive Kalman filter algorithm is used for data smoothing.

[0054] Environmental parameter compensation: An extended temperature and humidity compensation model is adopted, with the addition of an air pressure compensation term.

[0055] R c =R m ×[1+α(T-T0)+β(H-H0)+γ(P-P0)];

[0056] Where: α and β represent temperature compensation coefficient and humidity compensation coefficient, respectively; γ is air pressure compensation coefficient (typical value 0.0005-0.0015 / hPa); P is actual air pressure (hPa), P0 is reference air pressure (1013.25hPa); T represents actual temperature; T0 represents reference temperature (25℃); H represents actual humidity (%), H0 is reference humidity (50%).

[0057] The enrichment device is connected to the radon gas collection module and uses highly efficient adsorption materials such as activated carbon or molecular sieves to enrich the radon gas sample, thereby obtaining an enriched sample and improving detection sensitivity.

[0058] The radon ionization chamber detector is connected to the enrichment device and is used to measure radon in the enriched sample based on ionization chamber technology to obtain radon detection results in the form of electrical signals.

[0059] The calibration and verification system is connected to the radon ionization chamber detector and has a built-in automatic calibration system that periodically calibrates using a standard radon source to ensure the accuracy and stability of radon detection results.

[0060] The temperature control system is connected to the calibration and verification system and has built-in temperature and humidity sensors and a control system to maintain a stable sampling environment and reduce the impact of external factors on radon detection results.

[0061] The signal processing unit is connected to the calibration and verification system and the radon ionization chamber detector, and includes signal amplification, filtering and analog-to-digital conversion circuits to convert the electrical signal output by the radon ionization chamber detector into a digital signal.

[0062] The cloud computing platform is connected to the signal processing unit and is used to receive the radon detection results and obtain the radon concentration based on the radon detection results;

[0063] The data analysis mobile platform and the cloud computing platform are used to generate a radon concentration distribution map based on the radon concentration.

[0064] The intelligent early warning system and the cloud computing platform are used to trigger an early warning mechanism based on a preset threshold and the radon concentration, and notify relevant personnel via SMS, email, or other means.

[0065] Further implementation involves employing more refined sampling strategies in complex urban environments, such as densely populated high-rise areas and busy traffic zones. Through simulation and field testing, the optimal sampling location and time window for the radon gas collection module are determined to reduce environmental noise and interference, thereby improving the accuracy of radon concentration detection. The optimal sampling location is selected through simulation (e.g., fluid dynamics models) and field testing, choosing points least affected by factors such as building layout, ventilation conditions, and traffic interference, such as areas far from pollution sources and with good ventilation. The optimal sampling time window avoids peak traffic periods or extreme weather times, selecting periods with higher radon concentration stability (e.g., nighttime or early morning). By combining real-time environmental data (e.g., temperature, humidity, wind speed) and IoT feedback, the sampling frequency or location is dynamically adjusted to reduce noise interference. Environmental parameters (air pressure, wind speed, etc.) are recorded simultaneously for subsequent data compensation and model optimization, further improving accuracy.

[0066] For mobile helium sampling modules, GIS (Geographic Information System) and IoT technologies are utilized, combined with heuristic search algorithms (such as A* or Dijkstra's algorithm) and reinforcement learning algorithms to intelligently plan detection paths. Heuristic search algorithms can quickly find near-optimal paths, while reinforcement learning algorithms optimize path selection through continuous trial and error, ensuring efficient coverage of key urban monitoring areas. Furthermore, real-time information such as traffic conditions and weather conditions is considered to dynamically adjust the detection path.

[0067] Further implementation involves employing advanced machine learning algorithms, such as random forests, support vector machines, or deep learning models, when combining environmental parameters like temperature, humidity, air pressure, and wind speed to predict radon concentration. These algorithms can handle nonlinear relationships and complex interaction effects, thereby improving the accuracy of the prediction model. Furthermore, new data is continuously collected, and incremental learning techniques are used to continuously optimize model performance.

[0068] Specifically, the input data is first preprocessed to obtain radon concentration data, and a multiple linear regression model is used to compensate for temperature and humidity in the radon concentration data; then, an exponentially weighted moving average algorithm is used for smoothing: S t =α1·X t +(1-α1)·S t-1 ; where: S t X is the smoothed value at time t; t Let be the measured value at time t; α1 is the smoothing factor (0 < α1 < 1, usually taken as 0.1-0.3). For multi-point monitoring data, a spatial distribution model is constructed using Kriging interpolation: in: Z(s) is the estimated value of position s0; i ) represents the position s i Observed values; λ i The weighting coefficients are determined using a variogram. Big data analytics and machine learning algorithms are employed to establish a radon concentration distribution model. Based on this model, the enriched samples are analyzed to obtain the radon concentration. Specific methods include: using Fourier transform to extract periodic features to obtain temporal features, and using spatial autocorrelation analysis to extract spatial features.

[0069] A spatiotemporal feature matrix (including historical concentrations, environmental parameters, geographic information, etc.) was constructed based on temporal and spatial characteristics, and PCA was used for dimensionality reduction to retain 95% of the variance. Bayesian optimization was used to adjust hyperparameters, and spatiotemporal cross-validation was performed. Model interpretation: SHAP values ​​were used to analyze feature importance.

[0070] The model architecture includes: a base model, a meta-model, and a stacked model; the specific architecture is as follows:

[0071] #Base Model

[0072] base_models = [

[0073] ('rf',RandomForestRegressor(n_estimators=100)),

[0074] ('gbrt',GradientBoostingRegressor()),

[0075] ('svr', SVR(kernel = 'rbf')) ]

[0077] #Metamodel

[0078] meta_model=LinearRegression()

[0079] #Stacking Model

[0080] stack_model=StackingRegressor(

[0081] estimators = base_models,

[0082] final_estimator = meta_model

[0083] cv=5 )

[0085] A further implementation involves the calibration and verification system being based on a dynamic calibration method, automatically adjusting detection parameters according to environmental changes. Specifically, when using a dynamic calibration method based on online monitoring, adaptive filtering algorithms, such as Kalman filters or particle filters, are introduced. These algorithms can automatically adjust detection parameters according to real-time environmental changes, ensuring the stability and accuracy of radon detection results. Simultaneously, calibration and verification are performed periodically using standard substances to ensure long-term operational reliability.

[0086] Further implementation involves a temperature control system that incorporates high-precision sensing elements and intelligent algorithms. These algorithms, designed based on machine learning or adaptive control principles, aim to improve the accuracy and stability of radon concentration measurements, particularly in environments with significant temperature fluctuations. By monitoring ambient temperature in real time and dynamically adjusting measurement parameters (such as sensitivity and integration time), the algorithm eliminates or minimizes the impact of temperature on the measurement results. Ambient temperature monitoring uses an environmental parameter monitoring module to acquire real-time ambient temperature data from the sampling site. This data is then transmitted as an input signal to the temperature control system. The ambient temperature data is filtered to remove noise and outliers. The trend and fluctuation range of ambient temperature are calculated to provide a basis for subsequent algorithm adjustments. Intelligent algorithm adjustment: Based on the ambient temperature data, the intelligent algorithm automatically calculates and adjusts the measurement parameters of the radon sensor. For example, when the ambient temperature rises, the algorithm may reduce the sensor's sensitivity or increase the integration time; conversely, when the ambient temperature falls, the algorithm may increase the sensor's sensitivity or shorten the integration time. Radon concentration measurement: Under the adjusted measurement parameters, the radon sensor accurately measures radon. Environmental parameters are used to correct the measurement data, further eliminating the influence of environmental factors on the measurement results. The corrected data undergoes comprehensive analysis, including trend analysis and outlier detection, to ultimately generate an accurate and reliable radon concentration report. Based on actual measurement results and user needs, the intelligent algorithm continuously learns and optimizes its adjustment strategies. The algorithm identifies patterns in the relationship between temperature and measurement error by analyzing historical data and measurement results, and adjusts future adjustment strategies accordingly.

[0087] Methods for maintaining a stable sampling environment in a temperature control system include: calculating the difference between the current ambient temperature and the reference temperature: ΔT = T current -T base Based on the differences, the measurement parameters are adjusted using a preset algorithm model: sensitivity S adjusted =S base ×(1+k s ×ΔT), integration time t adjusted =t base ×(1+k t ×ΔT) n ), where S base This indicates the reference sensitivity, which is the initial sensitivity value of the sensor at a standard temperature (e.g., 25°C); t base The reference integration time represents the initial signal integration time of the sensor at standard temperature; k s The temperature compensation coefficient, representing the sensitivity, is used to adjust the magnitude of sensitivity changes with temperature; k tThe temperature compensation coefficient represents the integration time, used to adjust the magnitude of the integration time change with temperature; n represents the exponential parameter for adjusting the integration time, used to nonlinearly correct the influence of temperature on the integration time; the adjusted parameters are time-calibrated to verify the effect and readjusted based on feedback; measurements are performed under the adjusted parameters, and the results are transmitted to the mobile data analysis platform; the correlation pattern between temperature and measurement error is identified, the algorithm is optimized, and the adjustment strategy is continuously optimized based on real-time measurement results and user needs.

[0088] A further implementation involves the intelligent early warning system also issuing warnings based on the radon exposure risk index.

[0089] Among them, the radon exposure risk index: RI = (C a ×t) / (RL); where: RI is the risk index; C a Average radon concentration (Bq / m³) 3 ); t is the exposure time (h); RL is the reference level (WHO recommends 100 Bq / m²). 3 ).

[0090] System maintenance and management include:

[0091] (1) Regular inspection and maintenance:

[0092] To ensure the continuous and efficient operation of the radon detection system, it is necessary to regularly inspect and maintain the key components of the system. This includes, but is not limited to, the radon detector, the data acquisition module, and the data analysis terminal. Regularly calibrating the detector sensitivity, cleaning surface contaminants, and checking the stability of data transmission lines can effectively guarantee the normal working condition of the system and improve detection accuracy and stability.

[0093] (2) Data backup and security:

[0094] Given the importance of radon detection data for environmental health assessment, the system must implement a strict data backup strategy. Regular backups of collected radon concentration data should be performed and stored on secure and reliable storage media to prevent data loss. Simultaneously, a data access control mechanism should be established to ensure data confidentiality and security. Regarding data recovery, a rapid response mechanism should be established to ensure rapid recovery in the event of accidental data loss or corruption, guaranteeing data continuity and integrity.

[0095] (3) System upgrade and optimization:

[0096] With advancements in technology and the continuous development of radon detection technology, the system requires regular upgrades and optimizations. This includes updating the radon detector firmware, optimizing data acquisition algorithms, and enhancing the intelligence level of the data analysis software. By introducing advanced radon concentration prediction models and data analysis techniques, the system's detection efficiency and accuracy can be improved. Simultaneously, the system configuration should be adjusted according to changes in the urban environment and actual needs to ensure the system can adapt to the complex and ever-changing urban environment and provide more accurate and reliable radon concentration monitoring services.

[0097] Example 2:

[0098] This embodiment provides a method for detecting radon gas concentration, including the following steps:

[0099] Radon gas is collected in different areas of the city using a radon gas collection module.

[0100] The radon monitoring equipment at each monitoring station is activated to begin real-time collection of radon concentration data. The equipment will continuously monitor according to the preset sampling frequency and duration. The collected raw data will be preprocessed, including data cleaning, outlier removal, and data smoothing, to improve the accuracy and reliability of the data.

[0101] The collected radon gas samples were tested to obtain radon concentration data.

[0102] By utilizing big data analytics and machine learning algorithms, the received data is analyzed in depth to establish a radon concentration distribution model. This model predicts radon concentration trends in different regions, providing a scientific basis for early warning issuance.

[0103] The radon concentration data was processed and analyzed.

[0104] When the radon concentration in a certain area exceeds the preset safety threshold, the data analysis platform will automatically trigger an early warning mechanism, issuing warning information to relevant departments and personnel via SMS, email, or app push notifications. Simultaneously, it will provide emergency response suggestions, guiding relevant departments and personnel to take necessary prevention and control measures.

[0105] A radon concentration distribution map is generated based on the processed data.

[0106] Based on the data analysis results, a detailed radon monitoring report is generated. The report includes the spatiotemporal distribution characteristics of radon concentration, the identification and assessment of abnormal areas, and an evaluation of the effectiveness of prevention and control measures. The report is presented to users through an interactive interface, and adjustments and optimizations are made based on user feedback.

[0107] When designing an intuitive and user-friendly interface, it provides visualized data analysis reports such as real-time radon concentration distribution maps, trend analysis charts, and abnormal event logs, enabling managers to quickly understand the data and make decisions. Simultaneously, it integrates data mining and statistical analysis tools, such as cluster analysis and association rule mining, to help users delve deeper into the patterns and regularities behind the data.

[0108] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made by those skilled in the art to the technical solutions of the present invention without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. A radon concentration detection system, characterized in that, include: Radon gas collection module, used to collect pure radon gas samples in urban environments; The enrichment device is connected to the radon gas collection module and is used to enrich the radon gas sample to obtain an enriched sample. The radon ionization chamber detector is connected to the enrichment device and is used to measure radon in the enriched sample based on ionization chamber technology to obtain radon detection results in the form of electrical signals. The calibration and verification system is connected to the radon ionization chamber detector and is used to calibrate the radon detection results based on a standard radon source. The temperature control system is connected to the calibration and verification system and has a built-in temperature and humidity sensor and control system for real-time monitoring of the temperature of the sampling environment and dynamic adjustment of measurement parameters. The signal processing unit is connected to the calibration and verification system and is used to convert electrical signals into digital signals; The cloud computing platform is connected to the signal processing unit and is used to receive the radon detection results and obtain the radon concentration based on the radon detection results; The data analysis mobile platform and the cloud computing platform are used to generate a radon concentration distribution map based on the radon concentration. The intelligent early warning system and the cloud computing platform are used to trigger an early warning mechanism based on a preset threshold and the radon concentration; The temperature control system dynamically adjusts the measurement parameters, including: Calculate the difference between the current ambient temperature and the reference temperature: ΔT = T current -T base ; Based on the differences, the measurement parameters are adjusted using a preset algorithm model: Sensitivity S adjusted =S base ×(1+k s ×ΔT), integration time t adjusted =t base ×(1+k t ×ΔT) n , among which, S base Indicates the reference sensitivity; t base Indicates the reference integration time; k s Temperature compensation coefficient representing sensitivity; k t The temperature compensation coefficient represents the integration time; n represents the exponential parameter for adjusting the integration time, used to nonlinearly correct the effect of temperature on the integration time. The adjusted parameters were calibrated over time to verify the effect, and then adjusted again based on feedback. Measurements were performed using the adjusted parameters, and the results were transmitted to a mobile data analytics platform. Identify the correlation patterns between temperature and measurement error, and optimize the algorithm.

2. The radon concentration detection system according to claim 1, characterized in that, Based on the urban environment, the location and sampling time of the radon gas collection module were optimized to obtain the optimal sampling location and sampling time window.

3. The radon concentration detection system according to claim 1, characterized in that, The calibration and verification system is based on a dynamic calibration method, which automatically adjusts the detection parameters according to environmental changes.

4. The radon concentration detection system according to claim 1, characterized in that, The intelligent early warning system also issues warnings based on the radon exposure risk index; Radon exposure risk index: RI=(C a ×t) / (RL); In the formula: RI is the risk index; C a t represents the average radon concentration; t represents the exposure time; and RL represents the reference level.

5. A method for detecting radon gas concentration, wherein the method uses the detection system according to any one of claims 1-4, characterized in that, Includes the following steps: Radon gas is collected in different areas of the city using a radon gas collection module; The collected radon gas samples were tested to obtain radon concentration data; Processing and analyzing the detection data; A radon concentration distribution map is generated based on the processed data.

Images