An indoor radon gas intelligent monitoring system and method

Abstract

This invention provides an intelligent indoor radon monitoring system and method, relating to the field of radon monitoring technology. The system includes: deploying a multi-sensor fusion monitoring network in the room to be monitored, based on spatial grid division and multi-factor priority evaluation results; dynamically adapting the sampling frequency through the monitoring network, and simultaneously collecting radon concentration data, temperature data, humidity data, and airflow velocity data based on the determined sampling frequency; preprocessing and compensating for environmental multi-factor coupling on the collected radon concentration data, temperature data, humidity data, and airflow velocity data to obtain corrected, accurate radon concentration data; and executing multi-level early warning decisions based on the comparison results between the corrected, accurate radon concentration data and a preset threshold.

Description

Technical Field

[0001] This invention relates to the field of radon monitoring technology, specifically an indoor intelligent radon monitoring system and method. Background Technology

[0002] Radon, a colorless and odorless naturally occurring radioactive gas, is a significant source of indoor air pollution. Long-term exposure to high concentrations of radon has been identified as a major contributing factor to lung cancer. Therefore, effective and accurate monitoring and early warning of indoor radon concentrations are crucial for protecting public health.

[0003] Currently, indoor radon monitoring mainly relies on fixed or portable monitoring equipment. These methods typically have the following limitations: In terms of sensor deployment, there is a reliance on experience or simple uniform distribution, which fails to fully consider actual factors such as the heterogeneity of indoor spaces, the release characteristics of building materials, furniture placement and ventilation conditions. This results in insufficient representativeness of monitoring points, which may lead to the omission of local high-risk areas or the creation of resource redundancy.

[0004] In terms of data acquisition and processing, most systems use a fixed sampling frequency, which makes it difficult to balance real-time monitoring with system energy consumption. At the same time, the measurements of radon sensors are easily affected by environmental factors such as temperature, humidity, and airflow speed. Existing technologies often only perform simple linear compensation or ignore such effects, resulting in poor accuracy of monitoring data and affecting subsequent judgments.

[0005] In terms of early warning mechanisms, a single static threshold comparison method is commonly used, triggering an alarm when the concentration exceeds a set threshold. This method is too simplistic, unable to distinguish between short-term fluctuations and long-term risks, insensitive to slowly accumulating increases in concentration, prone to false alarms or missed alarms, and lacks the ability to spatially locate the source of risk, making it difficult to provide effective response guidance.

[0006] Therefore, an intelligent indoor radon monitoring system and method are provided, which can solve the problems of low radon monitoring accuracy caused by poor sensor deployment, poor environmental interference suppression, and low effectiveness of early warning mechanisms in the existing technology, and greatly improve the intelligent and accurate monitoring of indoor radon. Summary of the Invention

[0007] To address the aforementioned technical problems, the present invention aims to provide an intelligent indoor radon monitoring system and method, which can solve the problems of low radon monitoring accuracy caused by poor sensor deployment, poor environmental interference suppression, and low effectiveness of early warning mechanisms in the prior art, and greatly improve the intelligent and accurate monitoring of indoor radon.

[0008] To achieve the above objectives, the present invention provides the following technical solution: an intelligent indoor radon gas monitoring method, the method comprising: In the room to be monitored, a multi-sensor fusion monitoring network is deployed based on the spatial grid division and multi-factor priority evaluation results; Through the monitoring network, the sampling frequency is dynamically adapted, and based on the determined sampling frequency, radon concentration data, temperature data, humidity data and airflow velocity data are collected synchronously. The collected radon concentration data, temperature data, humidity data, and airflow velocity data are preprocessed and coupled with environmental multi-factor compensation to obtain accurate radon concentration data after correction. Based on the comparison between the corrected radon concentration data and the preset threshold, a multi-level early warning decision is made.

[0009] Preferably, the deployment of a multi-sensor fusion monitoring network in the room to be monitored, based on spatial grid division and multi-factor priority evaluation results, includes: Based on the room to be monitored, determine the spatial dimensions inside the room, and determine the reference dimensions based on the longest side length; Based on the reference dimensions, the space inside the room to be monitored is uniformly divided into multiple non-overlapping cubic monitoring units, and each cubic monitoring unit is assigned a unique number. Based on each cube monitoring unit, calculate the three-dimensional coordinates of the center point, the occupancy rate of the internal items, and the radon gas generation probability coefficient corresponding to the cube monitoring unit. Based on the three-dimensional coordinates of the center point of each cube monitoring unit, the item occupancy rate, and the radon gas generation probability coefficient, the corresponding deployment priority is calculated based on a preset priority evaluation model. Candidate deployment units are selected based on the deployment priority, and redundancy is removed from the candidate deployment units according to the unit spacing to obtain the final set of sensor installation points. At each point in the final sensor location set, a radon concentration sensor, a temperature and humidity sensor, and an airflow velocity sensor are respectively arranged to form a sensor monitoring network.

[0010] Preferably, the calculation of the three-dimensional coordinates of the center point, the occupancy rate of internal items, and the radon gas generation probability coefficient corresponding to each cube monitoring unit includes: Based on the three-dimensional environmental model of the room to be monitored, the geometric center coordinates of each cube monitoring unit are obtained, and the geometric center coordinates are determined as the three-dimensional coordinates of the center point; Identify all objects within each cube monitoring unit, determine the horizontal projected area of ​​the items within the unit, and obtain the item occupancy rate based on the reference dimensions; Identify the types of building materials within each cubic monitoring unit, determine the radon release risk weights for each type of material, and calculate the volume percentage of high-risk materials within the unit. Based on the floor location of the cube monitoring unit, as well as the radon release risk weight and volume ratio, the corresponding radon generation probability coefficient is determined.

[0011] Preferably, the step of preprocessing the collected data and coupling compensation with multiple environmental factors to obtain the corrected accurate radon concentration data includes: The synchronously collected radon concentration data, temperature data, humidity data, and airflow velocity data are preprocessed by timestamp alignment, outlier removal, and noise filtering to obtain an effective data sequence. Based on the temperature data, relative humidity data, and airflow velocity data in the effective data sequence, the corresponding temperature influence factor, humidity influence factor, airflow velocity influence factor, and interaction influence coefficient are determined, and the preliminary corrected radon concentration data is calculated through a multi-factor coupling correction formula. Based on a preset dynamic deviation calibration model, the initially corrected radon concentration data is compensated to obtain accurate radon concentration data.

[0012] Preferably, the sampling frequency dynamically adapted through the monitoring network is: After each sampling is completed, the latest acquired radon concentration data is added in real time to a fixed-length analysis sliding window, and the oldest data in the window is removed to form the current radon concentration data analysis sequence. Based on the radon concentration data analysis sequence within a specific analysis sliding window at this time, a composite judgment parameter for triggering cycle switching is calculated. The composite judgment parameter includes the trend consistency coefficient within the window, the significance of changes at the near end point, and the concentration range ratio within the window. The trend consistency coefficient within the window, the significance of changes at the near end, and the concentration range ratio within the window are input into a preset trigger decision function, which outputs the corresponding Boolean value. If the Boolean value is true, the frequency switching operation is performed; otherwise, the current sampling frequency is maintained, and the system waits for the next sampling moment.

[0013] Preferably, the frequency switching operation is as follows: Based on the precise radon concentration data at the current moment, as well as the precise radon concentration data at the previous moment and the moment before that, the concentration change characteristic parameters corresponding to the current moment are calculated. The concentration change characteristic parameters are the first-order rate of change, the second-order rate of change, and the concentration fluctuation coefficient. The frequency adjustment weight value is obtained by weighting and summing the first-order rate of change, the second-order rate of change, the concentration fluctuation coefficient, and their respective weight coefficients. Based on the frequency adjustment weight value and multiple preset weight thresholds, the sampling frequency of the next sampling point is dynamically adapted in multiple gradients to determine the adjusted sampling frequency. Based on the adjusted sampling frequency, the timing for starting the next sampling is calculated based on the sampling interval.

[0014] Preferably, the step of performing multi-level early warning decisions based on the comparison results between the corrected accurate radon concentration data and the preset threshold includes: Obtain accurate radon concentration data from all sensor locations at the current moment, calculate the average value in the indoor space to be monitored as the current indoor average concentration, and identify the maximum value in the space. The maximum spatial value is compared with the preset radon concentration threshold. If the maximum spatial value is greater than or equal to the radon concentration threshold of the first dynamic multiple coefficient, a first-level real-time warning is immediately triggered. Conversely, a two-level early warning strategy based on dynamic risk scores is constructed to dynamically adjust the first dynamic multiplier coefficient; Based on the dynamically adjusted first dynamic multiple coefficient, the preset second dynamic multiple coefficient, and the radon concentration threshold, the risk score is accumulated for the current monitoring period. When the cumulative risk score over N consecutive monitoring periods exceeds the preset score threshold, a secondary trend warning is triggered.

[0015] A second aspect of the present invention also provides an indoor radon intelligent monitoring system, comprising: The module is deployed in the room to be monitored, and a multi-sensor fusion monitoring network is deployed based on the spatial grid division and multi-factor priority evaluation results. The acquisition module, through the monitoring network, dynamically adapts the sampling frequency and, based on the determined sampling frequency, synchronously acquires radon concentration data, temperature data, humidity data, and airflow velocity data. The correction module preprocesses the collected radon concentration data, temperature data, humidity data, and airflow velocity data and performs multi-factor environmental compensation to obtain accurate radon concentration data after correction. The early warning module performs multi-level early warning decisions based on the comparison results between the corrected accurate radon concentration data and the preset threshold.

[0016] Compared with the prior art, the beneficial effects of the present invention are: This solution abandons the traditional experience-based or uniform deployment approach. By gridding the indoor space and prioritizing the placement of sensor points based on the center point location, object occupancy rate, and radon generation probability coefficient of each grid unit, it achieves scientific and intelligent selection and optimized layout of sensor locations. This method can accurately cover high-risk areas with a minimal number of sensors, significantly reducing hardware deployment costs while ensuring monitoring representativeness and improving the monitoring network's ability to locate potential pollution sources.

[0017] This solution analyzes the trend consistency, significance of changes, and fluctuation range of radon concentration data, dynamically triggering and adjusting the sampling frequency to achieve an adaptive sensing mode of steady-state low-frequency sampling and transient high-frequency capture. This reduces system power consumption and data redundancy while ensuring rapid response to sudden concentration changes. Secondly, in the data correction stage, in addition to conventional preprocessing, it innovatively couples and models multiple environmental parameters such as temperature, humidity, and airflow velocity, calculating a comprehensive influencing factor to compensate for the original concentration data, and introducing a dynamic deviation calibration model for secondary correction. This effectively eliminates the interference caused by environmental fluctuations on sensor readings, significantly improving the accuracy, stability, and reliability of radon concentration monitoring data, providing a high-quality data foundation for subsequent early warning decisions.

[0018] This solution departs from the traditional, simple single-threshold alarm model, constructing a multi-level early warning system consisting of a primary immediate warning and a secondary trend warning. The warning multiplier (such as the first dynamic multiplier coefficient) is not a fixed value but is adjusted in real time based on historical concentration trends and environmental conditions, making the warning threshold more closely match the actual risk level and reducing false alarms caused by short-term environmental fluctuations. By constructing a dynamic risk integral model, it quantifies and accumulates concentrations that are persistently high but have not reached the emergency threshold, and introduces a decay factor to simulate the natural dissipation of risk. This mechanism can effectively identify and warn of slowly accumulating, long-term potential health risks, compensating for the shortcomings of instantaneous threshold comparisons. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0020] Figure 1 This is a schematic diagram of a smart indoor radon monitoring method.

[0021] Figure 2 This is a schematic diagram of an indoor radon intelligent monitoring system. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be described in detail below. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other implementation methods obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0023] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0024] Example 1 like Figure 1 As shown in the figure, this embodiment discloses an intelligent indoor radon gas monitoring method, the method comprising: In the room to be monitored, a multi-sensor fusion monitoring network is deployed based on the spatial grid division and multi-factor priority evaluation results; It should be noted that, within the monitoring room, the multi-sensor fusion monitoring network deployed based on spatial grid division and multi-factor priority evaluation results includes: The spatial boundary of the room to be monitored is accurately located, and the reference size for cutting the cube is determined based on the longest side length of the room. ; According to the reference dimensions The monitoring chamber is uniformly divided into several non-overlapping cubic monitoring units, each with a side length of 1. Each cube monitoring unit is uniquely numbered (1, 2, 3, ..., n, where n is the total number of cube monitoring units). For each cube monitoring unit, calculate the three-dimensional coordinates of the center point of each cube monitoring unit. ,in Let be the coordinates of the midpoint of the unit along the interior length direction. Let be the coordinates of the midpoint of the unit along the width of the interior space. The coordinates of the midpoint of the unit along the indoor height direction (default) Take half the height from the indoor floor to the ceiling, which is the core height area for human activity. The horizontal projected area of ​​items (furniture, appliances, storage, etc.) within the unit is obtained using laser scanning or image recognition technology. Calculate the item occupancy rate ; For each cubic monitoring unit, a radon generation probability assessment is conducted. Specifically, the types of building materials within the unit are identified, and each material is assigned a radon release risk weight. The volume percentage of high-risk materials within the unit is also calculated; the definition of high-risk materials is freely set by the operator. A floor correction factor is also assigned based on the unit's floor location. The corresponding radon generation probability coefficient is determined based on the radon release risk weight, the volume percentage of high-risk materials, and the floor correction factor. .

[0025] Based on the three-dimensional coordinates of the center point of each cube monitoring unit, the item occupancy rate, and the radon gas generation probability coefficient, the deployment priority of each cube monitoring unit is determined based on a preset cube monitoring unit deployment priority evaluation model. The cube monitoring unit deployment priority evaluation model is as follows: In the formula, For the rationality of the center point location, , , These are the corresponding weight values.

[0026] Based on a preset priority threshold, cube monitoring units with a deployment priority greater than the preset priority threshold are selected as candidate deployment units. The preset priority threshold is related to the number of cube monitoring units and the final candidate deployment units.

[0027] Calculate the straight-line distance between the center points of any two candidate deployment units. If the straight-line distance is less than a preset distance threshold, the deployment unit with lower priority is eliminated. The center points of the remaining candidate deployment units are the final set of sensor placement points. Radon concentration sensors, temperature and humidity sensors, and airflow velocity sensors are synchronously deployed at each point, with the sensor detection surface facing the center of the unit. The installation height should be as consistent as possible with the Z coordinate of the center point. If they are inconsistent, reasonable settings are made based on the objects within the unit to form a fully covered and highly targeted sensor monitoring network.

[0028] Through the monitoring network, the sampling frequency is dynamically adapted, and based on the determined sampling frequency, radon concentration data, temperature data, humidity data and airflow velocity data are collected synchronously. It should be noted that the sampling frequency dynamically adapted through the monitoring network is: After each sampling is completed, the latest acquired radon concentration data is added in real time to a fixed-length analysis sliding window, and the oldest data in the window is removed to form the current radon concentration data analysis sequence. Based on the radon concentration data analysis sequence within a specific analysis sliding window at this time, a composite judgment parameter for triggering cycle switching is calculated. The composite judgment parameter includes the trend consistency coefficient within the window, the significance of changes at the near end point, and the concentration range ratio within the window. The trend consistency coefficient within the window, the significance of changes at the near end, and the concentration range ratio within the window are input into a preset trigger decision function, which outputs the corresponding Boolean value. If the Boolean value is true, the frequency switching operation is performed; otherwise, the current sampling frequency is maintained, and the system waits for the next sampling moment.

[0029] When the determination result indicates the need to perform a frequency switching operation, based on the precise radon concentration data at the current moment, and the precise radon concentration data at the previous and the moment before that, the concentration change characteristic parameters corresponding to the current moment are calculated. These concentration change characteristic parameters include the first-order rate of change, the second-order rate of change, and the concentration fluctuation coefficient. In this embodiment, the first-order rate of change... The calculation is as follows: , This provides precise data on radon concentration at the current moment. This is the precise radon concentration data from the previous moment. For the previous sampling interval, a positive value of the first-order rate of change indicates an increase in concentration, while a negative value indicates a decrease in concentration; the larger the absolute value, the more drastic the change. The second-order rate of change... The calculation is as follows: Concentration fluctuation coefficient The calculation formula is: , for The corresponding precise radon concentration data, This represents the average radon concentration over approximately k sliding windows. Current radon monitoring technologies often rely on a single parameter (such as a concentration threshold or a single rate of change), which fails to comprehensively characterize the dynamic features of the concentration: using only the first-order rate of change is susceptible to noise interference, using only the concentration value cannot capture the trend of change, and using only the fluctuation coefficient is insufficient to identify sudden changes. This solution creatively combines three types of parameters—first-order rate of change, second-order rate of change, and concentration fluctuation coefficient—to construct a three-dimensional evaluation system, achieving multi-dimensional verification and comprehensive monitoring. This represents a fundamental improvement over the traditional single-parameter evaluation model.

[0030] The frequency adjustment weight value is obtained by weighting and summing the first-order rate of change, the second-order rate of change, the concentration fluctuation coefficient, and their respective weight coefficients. Weight values ​​adjusted based on frequency and multiple preset weight thresholds , ; Perform multi-gradient dynamic adaptation on the sampling frequency of the next sampling point: For example, when At this point, the situation is determined to be a low-risk, stable state, and the sampling frequency is adjusted to the first sampling frequency. when If the condition is determined to be a normal stable state, the sampling frequency will be adjusted to the second sampling frequency. when If the current condition is determined to be a mild fluctuation state, the sampling frequency will be adjusted to the third sampling frequency. when If a high-risk mutation state is identified at this point, the sampling frequency is adjusted to the fourth sampling frequency. The first, second, third, and fourth sampling frequencies increase progressively. In this embodiment, the first, second, third, and fourth sampling frequencies are dynamically adjustable, unlike the fixed or manually set frequencies used in existing technologies. Specifically, the second sampling frequency... As the computational anchor point for the entire system, the formula is derived from the core parameters of the monitoring scenario rather than through subjective pre-setting. ,in The basic sampling interval is determined by one-third of the minimum length of the specific analysis sliding window. This specific analysis sliding window is a fixed-length window used to store radon concentration data after each sampling, and it triggers the sampling frequency switching decision. The first sampling frequency is the low-risk range, determined using the logic of baseline frequency reduction calibration, as shown in the formula: In the formula This is the low-stage frequency reduction factor, typically a constant, ranging from 0.2 to 0.5. The concentration fluctuation coefficient is dynamically adjusted within a low-risk range, where the low-risk range is the monitoring interval where the radon concentration change meets the low-risk determination criteria; the lower the fluctuation coefficient... The closer the value is to 0.2, the lower the sampling frequency during the low-risk, stable phase, addressing the pain point of oversampling in low-risk areas in existing technologies, while ensuring that the data is sufficient to reflect slow changing trends. The third sampling frequency is for mild fluctuations, employing a "gradual amplification of the base benchmark" logic, as shown in the formula. , This is the temperature-dependent increase coefficient, typically ranging from 1.0 to 2.0. The risk evolution rate is dynamically adjusted within a moderate fluctuation range, which is a monitoring range where radon concentration changes are at a medium risk and the fluctuation amplitude is relatively small. The evolution rate is correlated with the concentration change trend; the higher the evolution rate, the more obvious the concentration change trend. The closer to version 2.0, the more precisely it matches the characteristics of gradually escalating risks, avoiding excessive frequency increases that could lead to waste, while still capturing the patterns of gentle fluctuations. The fourth sampling frequency is for high-risk levels, employing a "coupling factor exponential amplification" logic, as shown in the formula: , It is not a fixed value, but rather a value coupled with the second-order rate of change and concentration fluctuation coefficient within the high-risk mutation range. The high-risk mutation range refers to the monitoring range where radon concentration changes drastically and the risk level is relatively high. , , These are the corresponding weight values. All frequency calculations are incorporated into scenario-based calibration rules, with coefficients fine-tuned based on the rate of change of the monitored object and process constraints (such as upper limits on sampling frequency and contamination risks in the fermentation system). For example, in a rapidly changing scenario, the coefficients are increased. Up to version 3.0~5.0.

[0031] Based on the adjusted sampling frequency, the timing for starting the next sampling is calculated based on the sampling interval.

[0032] The collected radon concentration data, temperature data, humidity data, and airflow velocity data are preprocessed and coupled with environmental multi-factor compensation to obtain accurate radon concentration data after correction. It should be noted that the preprocessing of the collected data and the coupling compensation of multiple environmental factors to obtain the corrected accurate radon concentration data include: The synchronously collected radon concentration data, temperature data, humidity data, and airflow velocity data are preprocessed by timestamp alignment, outlier removal, and noise filtering to obtain an effective data sequence. Based on the temperature data, relative humidity data, and airflow velocity data in the effective data sequence, the corresponding temperature influence factor, humidity influence factor, airflow velocity influence factor, and interaction influence coefficient are determined, and the preliminary corrected radon concentration data is calculated through a multi-factor coupling correction formula. Based on a preset dynamic deviation calibration model, the initially corrected radon concentration data is compensated to obtain accurate radon concentration data.

[0033] In this embodiment, the synchronously collected radon concentration data, temperature and humidity data, and airflow velocity data are first preprocessed. Specifically, the raw radon concentration data, temperature data, relative humidity data, and airflow velocity data are first timestamped, and outliers exceeding the device's measurement range are removed. The criteria remove random noise to obtain an effective data sequence.

[0034] An environmental impact factor database is constructed, including temperature impact factors, humidity impact factors, and airflow velocity impact factors. In this embodiment, the temperature impact factor is calculated as follows: In the formula For actual measured temperature, For standard reference temperature, , These are the corresponding temperature segment critical thresholds. , , The corresponding temperature influence coefficients are all positive. The humidity influence factor is calculated as follows: In the formula, RH is the measured relative humidity. Standard reference humidity; , Humidity segmentation critical threshold ( (Critical value for condensation). , , Humidity influence coefficient. Airflow velocity influence factor. The calculation formula is In the formula, To measure the airflow velocity, Standard reference airflow velocity; , The critical threshold for segmented airflow velocity. This is the diffusion saturation threshold; , , This refers to the airflow influence coefficient. In this embodiment, standard reference values ​​and segmented critical thresholds are set for the three environmental factors of temperature, humidity, and airflow velocity. The corresponding influence factors are calculated using correction coefficients for different intervals. A piecewise function is used to distinguish different environmental intervals (such as temperatures below / between / above the critical value), avoiding the problem that a single coefficient cannot adapt to complex environments and improving the accuracy of data correction.

[0035] Based on temperature influence factors Humidity influencing factors and airflow velocity influencing factors and preset interaction coefficients Establish a multi-factor coupling correction formula: The corresponding preliminary corrected radon concentration data were calculated. , This is the raw data of the collected radon concentration.

[0036] Accurate radon concentration data were obtained based on dynamic deviation calibration. And limited When the calculation result is negative, take... =0.

[0037] Among them, a deviation compensation function is established based on the sensor's factory calibration data and historical monitoring data. In detail, based on the raw radon concentration data, as well as the normalized temperature data, relative humidity data, and airflow velocity data, and the corresponding calibration data for each data point, a weighted sum is performed to obtain the corresponding... .

[0038] In another embodiment, a radon correction factor is used. Correction of raw radon concentration data In detail, a multi-factor coupled correction model is constructed and optimized using a BP neural network model. This model includes an input layer, an output layer, and hidden layers. The preprocessed radon concentration data, temperature data, relative humidity data, and airflow velocity data are used as input layer data, consisting of four nodes. The output layer contains the radon correction coefficient and has one node. The number of hidden layer nodes is calculated using the following formula: Where m is the number of hidden layer nodes and n is the number of input layer nodes. The number of output layer nodes is denoted by 'a', which is a coefficient. In this embodiment, a = 4, so the number of hidden layer nodes is 7.

[0039] Based on the comparison between the corrected radon concentration data and the preset threshold, a multi-level early warning decision is made.

[0040] It should be noted that the multi-level early warning decision-making based on the comparison results between the corrected radon concentration data and the preset threshold includes: Obtain accurate radon concentration data from all sensor locations at the current moment, and calculate the average value within the monitored indoor space as the current indoor average concentration. And identify the maximum spatial value within it. ; Maximum space Compared with the preset radon concentration threshold If the maximum spatial concentration is greater than or equal to the radon concentration threshold of the first dynamic multiple coefficient, a first-level immediate warning will be triggered immediately. Conversely, a two-level early warning strategy based on dynamic risk scores is constructed to dynamically adjust the first dynamic multiplier coefficient; Based on the dynamically adjusted first dynamic multiple coefficient, the preset second dynamic multiple coefficient, and the radon concentration threshold, the risk score is accumulated for the current monitoring period. When the cumulative risk score over N consecutive monitoring periods exceeds the preset score threshold, a secondary trend warning is triggered.

[0041] In detail, the maximum spatial concentration is compared with the preset radon concentration threshold: like This immediately triggers a Level 1 real-time warning. The first dynamic multiplier coefficient is used to indicate that the first-level immediate warning is to immediately activate the highest level warning and force the indoor ventilation system to start.

[0042] Conversely, a two-level early warning strategy based on dynamic risk scores is constructed, specifically as follows: Based on historical data of radon concentration thresholds within a preset time period, the corresponding trend slope and standard deviation of fluctuation are calculated, and then expressed using the formula... The first dynamic multiplier coefficient is dynamically adjusted, where The current comprehensive environmental factors are calculated by coupling temperature, humidity, and airflow velocity. A second dynamic multiplier coefficient less than K1 is also set. .

[0043] Then, risk points are accumulated: like Then, the cumulative risk score for the current monitoring period will be calculated. ; like ,and Then, the cumulative risk score for the current monitoring period will be calculated. ;in ; In other cases, the risk score remains unchanged or decreases slowly.

[0044] The secondary trend warning initiates the location verification process: analysis The system uses recent data trends and environmental data from the sensor location and adjacent locations to verify whether the anomaly is localized and persistent. Once the verification is successful, a medium-level alarm is triggered, and a risk area location prompt and suggested ventilation recommendations are provided.

[0045] like Figure 2 As shown, this embodiment discloses an indoor radon intelligent monitoring system, including: The module is deployed in the room to be monitored, and a multi-sensor fusion monitoring network is deployed based on the spatial grid division and multi-factor priority evaluation results. The acquisition module, through the monitoring network, dynamically adapts the sampling frequency and, based on the determined sampling frequency, synchronously acquires radon concentration data, temperature data, humidity data, and airflow velocity data. The correction module preprocesses the collected radon concentration data, temperature data, humidity data, and airflow velocity data and performs multi-factor environmental compensation to obtain accurate radon concentration data after correction. The early warning module performs multi-level early warning decisions based on the comparison results between the corrected accurate radon concentration data and the preset threshold.

[0046] Optionally, in this embodiment, those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0047] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0048] If the integrated units in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in the aforementioned computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause one or more electronic devices to execute all or part of the steps of the methods described in the various embodiments of this application.

[0049] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0050] In the several embodiments provided in this application, it should be understood that the disclosed application can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of units or modules may be electrical or other forms.

[0051] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0052] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0053] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for intelligent indoor radon monitoring, characterized in that, The method includes: In the room to be monitored, a multi-sensor fusion monitoring network is deployed based on the spatial grid division and multi-factor priority evaluation results; Through the monitoring network, the sampling frequency is dynamically adapted, and based on the determined sampling frequency, radon concentration data, temperature data, humidity data and airflow velocity data are collected synchronously. The collected radon concentration data, temperature data, humidity data, and airflow velocity data are preprocessed and coupled with environmental multi-factor compensation to obtain accurate radon concentration data after correction. Based on the comparison between the corrected radon concentration data and the preset threshold, a multi-level early warning decision is made.

2. The indoor radon intelligent monitoring method according to claim 1, characterized in that, The monitoring network deployed in the indoor monitoring room, based on spatial grid division and multi-factor priority evaluation results, includes: Based on the room to be monitored, determine the spatial dimensions inside the room, and determine the reference dimensions based on the longest side length; Based on the reference dimensions, the space inside the room to be monitored is uniformly divided into multiple non-overlapping cubic monitoring units, and each cubic monitoring unit is assigned a unique number. Based on each cube monitoring unit, calculate the three-dimensional coordinates of the center point, the occupancy rate of the internal items, and the radon gas generation probability coefficient corresponding to the cube monitoring unit. Based on the three-dimensional coordinates of the center point of each cube monitoring unit, the item occupancy rate, and the radon gas generation probability coefficient, the corresponding deployment priority is calculated based on a preset priority evaluation model. Candidate deployment units are selected based on the deployment priority, and redundancy is removed from the candidate deployment units according to the unit spacing to obtain the final set of sensor installation points. At each point in the final sensor location set, a radon concentration sensor, a temperature and humidity sensor, and an airflow velocity sensor are respectively arranged to form a sensor monitoring network.

3. The indoor radon intelligent monitoring method according to claim 2, characterized in that, The calculation of the three-dimensional coordinates of the center point, the occupancy rate of internal items, and the radon gas generation probability coefficient for each cube-shaped monitoring unit includes: Based on the three-dimensional environmental model of the room to be monitored, the geometric center coordinates of each cube monitoring unit are obtained, and the geometric center coordinates are determined as the three-dimensional coordinates of the center point; Identify all objects within each cube monitoring unit, determine the horizontal projected area of ​​the items within the unit, and obtain the item occupancy rate based on the reference dimensions; Identify the types of building materials within each cubic monitoring unit, determine the radon release risk weights for each type of material, and calculate the volume percentage of high-risk materials within the unit. Based on the floor location of the cube monitoring unit, as well as the radon release risk weight and volume ratio, the corresponding radon generation probability coefficient is determined.

4. The indoor radon intelligent monitoring method according to claim 3, characterized in that, The process of preprocessing the collected data and coupling compensation with multiple environmental factors to obtain accurate radon concentration data after correction includes: The synchronously collected radon concentration data, temperature data, humidity data, and airflow velocity data are preprocessed by timestamp alignment, outlier removal, and noise filtering to obtain an effective data sequence. Based on the temperature data, relative humidity data, and airflow velocity data in the effective data sequence, the corresponding temperature influence factor, humidity influence factor, airflow velocity influence factor, and interaction influence coefficient are determined, and the preliminary corrected radon concentration data is calculated through a multi-factor coupling correction formula. Based on a preset dynamic deviation calibration model, the initially corrected radon concentration data is compensated to obtain accurate radon concentration data.

5. The indoor radon intelligent monitoring method according to claim 4, characterized in that, The sampling frequency dynamically adapted through the monitoring network is: After each sampling is completed, the latest acquired radon concentration data is added in real time to a fixed-length analysis sliding window, and the oldest data in the window is removed to form the current radon concentration data analysis sequence. Based on the radon concentration data analysis sequence within a specific analysis sliding window at this time, a composite judgment parameter for triggering cycle switching is calculated. The composite judgment parameter includes the trend consistency coefficient within the window, the significance of changes at the near end point, and the concentration range ratio within the window. The trend consistency coefficient within the window, the significance of changes at the near end, and the concentration range ratio within the window are input into a preset trigger decision function, which outputs the corresponding Boolean value. If the Boolean value is true, the frequency switching operation is performed; otherwise, the current sampling frequency is maintained, and the system waits for the next sampling moment.

6. The indoor radon intelligent monitoring method according to claim 5, characterized in that, The frequency switching operation is as follows: Based on the precise radon concentration data at the current moment, as well as the precise radon concentration data at the previous moment and the moment before that, the concentration change characteristic parameters corresponding to the current moment are calculated. The concentration change characteristic parameters are the first-order rate of change, the second-order rate of change, and the concentration fluctuation coefficient. The frequency adjustment weight value is obtained by weighting and summing the first-order rate of change, the second-order rate of change, the concentration fluctuation coefficient, and their respective weight coefficients. Based on the frequency adjustment weight value and multiple preset weight thresholds, the sampling frequency of the next sampling point is dynamically adapted in multiple gradients to determine the adjusted sampling frequency. Based on the adjusted sampling frequency, the timing for starting the next sampling is calculated based on the sampling interval.

7. The indoor radon intelligent monitoring method according to claim 6, characterized in that, The multi-level early warning decision-making based on the comparison results between the corrected radon concentration data and the preset threshold includes: Obtain accurate radon concentration data from all sensor locations at the current moment, calculate the average value in the indoor space to be monitored as the current indoor average concentration, and identify the maximum value in the space. The maximum spatial value is compared with the preset radon concentration threshold. If the maximum spatial value is greater than or equal to the radon concentration threshold of the first dynamic multiple coefficient, a first-level real-time warning is immediately triggered. Conversely, a two-level early warning strategy based on dynamic risk scores is constructed to dynamically adjust the first dynamic multiplier coefficient; Based on the dynamically adjusted first dynamic multiple coefficient, the preset second dynamic multiple coefficient, and the radon concentration threshold, the risk score is accumulated for the current monitoring period. When the cumulative risk score over N consecutive monitoring periods exceeds the preset score threshold, a secondary trend warning is triggered.

8. An indoor radon intelligent monitoring system, implementing the indoor radon intelligent monitoring method according to any one of claims 1 to 7, characterized in that, include: The module is deployed in the room to be monitored, and a multi-sensor fusion monitoring network is deployed based on the spatial grid division and multi-factor priority evaluation results. The acquisition module, through the monitoring network, dynamically adapts the sampling frequency and, based on the determined sampling frequency, synchronously acquires radon concentration data, temperature data, humidity data, and airflow velocity data. The correction module preprocesses the collected radon concentration data, temperature data, humidity data, and airflow velocity data and performs multi-factor environmental compensation to obtain accurate radon concentration data after correction. The early warning module performs multi-level early warning decisions based on the comparison results between the corrected accurate radon concentration data and the preset threshold.

Images