Intelligent response trapping device for atmospheric mercury

Abstract

The invention relates to the technical field of atmospheric mercury monitoring, in particular to an atmospheric mercury intelligent response trapping device which comprises a trapping module used for monitoring mercury concentration and environmental information of a preset area and sending a monitoring result to a storage module; the purification module is used for carrying out purification treatment on the mercury-containing gas; the storage module is used for storing mercury concentration and environment information; the analysis module is used for predicting the mercury pollution change trend by adopting a machine learning algorithm according to the historical monitoring result and the current monitoring result of the preset area, and generating a prediction result; and the control module is also used for adjusting the working state of the purification module for purifying the mercury-containing gas according to the prediction result. According to the scheme, the mercury concentration in the atmosphere can be monitored and purified, the purification module can be automatically adjusted in advance according to the change of the mercury concentration, and the purification effect is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of atmospheric mercury monitoring, and specifically provides an intelligent response capture device for atmospheric mercury. Background Art

[0002] Mercury (Hg) is a heavy metal naturally present on the earth, with high toxicity and bioaccumulation. It can enter the environment through various channels, including natural processes such as volcanic eruptions and forest fires, as well as human activities such as coal combustion, metal smelting, and chemical production. When mercury is released into the atmosphere, it can exist in the form of gaseous elemental mercury (GEM), particulate-bound mercury (PHg), or reactive mercury compounds (such as Hg 2+ ) and can be transported over long distances globally, eventually settling into land and water bodies, posing a potential threat to ecosystems and human health. The hazards of mercury Mercury and its compounds are extremely harmful to human health, especially to the nervous system, kidneys, and other organs. Long-term exposure to low concentrations of mercury in the environment may cause chronic poisoning symptoms, while short-term high-dose exposure may trigger acute poisoning. In addition, mercury can accumulate through the food chain, accumulating in fish and other aquatic organisms, thereby affecting the people who consume these organisms. Therefore, accurately monitoring the mercury concentration in the atmosphere is crucial for assessing its environmental impact and taking effective prevention and control measures.

[0003] Monitoring the mercury concentration in the atmosphere mainly relies on mercury sensors. Although single monitoring can timely remind people to evacuate when the mercury concentration exceeds the standard, it cannot directly control the mercury concentration. If air purification devices are directly set up for purification, a large number of air purification devices need to be set up, and it is impossible to reasonably manage a large number of air purification devices, especially the air purification devices in different regions cannot be targeted for management and adjustment. As the mercury concentration in the atmosphere changes and is adjusted one by one, there will be a lag, affecting the air purification effect.

[0004] Therefore, there is an urgent need for an intelligent response capture device for atmospheric mercury, which can monitor the mercury concentration in the atmosphere, purify it, and can automatically adjust the purification module in advance according to the change of mercury concentration to ensure the purification effect. Summary of the Invention

[0005] The present invention aims to provide an intelligent response capture device for atmospheric mercury, which can monitor the mercury concentration in the atmosphere, purify it, and can automatically adjust the purification module in advance according to the change of mercury concentration to ensure the purification effect.

[0006] The present invention provides the following basic solution: an intelligent response capture device for atmospheric mercury, comprising: a capture module, a purification module, a storage module, and an analysis module;

[0007] A capture module, which is used to monitor the mercury concentration and environmental information in a preset area and send the monitoring results to a storage module;

[0008] A purification module, which is used to purify the mercury-containing gas;

[0009] A storage module, which is used to store the mercury concentration and environmental information;

[0010] An analysis module, which is used to predict the change trend of mercury pollution and generate a prediction result by using a machine learning algorithm according to the historical and current monitoring results in a preset area;

[0011] It is also used to adjust the working state of the purification module for purifying the mercury-containing gas according to the prediction result.

[0012] Furthermore, the capture module includes: a monitoring grid;

[0013] Monitoring nodes are set at several preset positions in the preset area to form a monitoring grid, and the mercury concentration and environmental information in each preset position area are monitored. A mercury sensor and a weather station are set in the monitoring nodes; the environmental information includes, but is not limited to: temperature, humidity and wind speed.

[0014] Furthermore, an edge computing sub-module is also set in the monitoring node, which is used to preprocess the mercury concentration and environmental information collected by the sensor and the weather station, and upload the processed and summarized mercury concentration and environmental information to the storage module.

[0015] Furthermore, the purification module includes: a gas purification device set in the monitoring node, which is used to purify the mercury-containing gas.

[0016] Furthermore, the machine learning algorithm adopts an LSTM model, and the historical and current mercury concentration, temperature, humidity and wind speed are input, and the mercury concentration in a preset future time period is output.

[0017] Furthermore, the LSTM model includes: an input layer, an LSTM layer, a Dropout layer, a fully connected layer, and an output layer; the input layer is connected to the LSTM layer, each LSTM layer is connected to a Dropout layer, the last Dropout layer is connected to the fully connected layer, and the fully connected layer is connected to the output layer;

[0018] The input of the input layer is a three-dimensional tensor, and its shape is (number of samples, time step, number of features); each sample represents a time window and contains data (mercury concentration, temperature, humidity and wind speed) at multiple historical time points; the time step represents the number of data at historical time points contained in each sample; the number of features is all variables used for prediction, including: mercury concentration, temperature, humidity and wind speed.

[0019] Further, adjusting the working state of the purification module for purifying mercury-containing gas according to the prediction result, including:

[0020] Adjusting the working state of the purification module for purifying mercury-containing gas according to the predicted mercury concentration in a preset future time period, where the working state includes: air flow rate and replacement frequency of the adsorbent.

[0021] Further, if the mercury concentration in the preset future time period increases, the air flow rate is reduced and the replacement frequency of the adsorbent is increased;

[0022] If the mercury concentration in the preset future time period decreases, the air flow rate is increased and the replacement frequency of the adsorbent is reduced.

[0023] Further, it further includes: a verification module;

[0024] The verification module is used to determine whether there is an abnormality in the monitoring result. If so, it generates monitoring node abnormality information and pushes it to the management terminal of the operation and maintenance personnel, and at the same time, issues an early warning for the monitoring node abnormality.

[0025] Further, the determination of whether there is an abnormality in the monitoring result includes:

[0026] Analyzing the relationship between the monitoring nodes according to the geographical relationship and distance between the monitoring nodes at preset positions in the preset area, and constructing a relationship topology network between the monitoring nodes;

[0027] For the monitoring results collected by each monitoring node, according to the relationship topology network, it is judged whether the monitoring results conform to the relationship. If so, it is determined that the monitoring result is correct. If not, it is determined that the monitoring result is abnormal.

[0028] Beneficial effects: First, in this solution, a capture module is set to monitor the mercury concentration and environmental information in the preset area, and the specific quantity and position can be set according to actual needs, so as to realize the mercury concentration monitoring and environmental monitoring in the preset area. The monitoring results are sent to the storage module for storage, which is convenient for traceability and convenient for calling; at the same time, a purification module is also set to purify the mercury-containing gas;

[0029] Secondly, by setting an analysis module to adopt a machine learning algorithm according to the historical monitoring results and current monitoring results in the preset area, predict the mercury pollution change trend, generate a prediction result, so as to predict the mercury pollution change trend in a future period of time, that is, the mercury concentration change, based on the known monitoring results;

[0030] Finally, based on the prediction results, the analysis module also adjusts the working state of the purification module for purifying mercury-containing gas, so that the purification module in the preset area can automatically adjust its working state according to the change of mercury concentration, ensuring the purification effect without hysteresis and being able to make adjustments in advance, making the current working state adapt to the current environment and ensuring the purification effect.

[0031] In summary, it can monitor the mercury concentration in the atmosphere, purify it, and automatically adjust the purification module in advance according to the change of mercury concentration to ensure the purification effect. Brief Description of the Drawings

[0032] Figure 1 It is a logic block diagram of an embodiment of an intelligent mercury-responsive capture device for the atmosphere of the present invention;

[0033] Figure 2 It is a schematic diagram of a relationship topology network in an embodiment of an intelligent mercury-responsive capture device for the atmosphere of the present invention. Detailed Description of the Invention

[0034] The following is a more detailed description through specific embodiments:

[0035] Embodiment 1

[0036] This embodiment is basically as shown in the attached Figure 1 : An intelligent mercury-responsive capture device for the atmosphere, comprising: a capture module, a purification module, a storage module, and an analysis module;

[0037] The capture module is used to monitor the mercury concentration and environmental information in the preset area and send the monitoring results (i.e., mercury concentration and environmental information) to the storage module;

[0038] Specifically, monitoring nodes are set at several preset positions in the preset area to form a monitoring grid to monitor the mercury concentration and environmental information in the areas of each preset position. Among them, mercury sensors and weather stations are set in the monitoring nodes; the environmental information includes, but is not limited to: temperature, humidity, and wind speed;

[0039] An edge computing sub-module is also set in each monitoring node to preprocess the mercury concentration and environmental information collected by the sensors and the weather station, reduce the data transmission volume, and upload the processed and summarized mercury concentration and environmental information to the storage module;

[0040] Among them, the preprocessing includes: data cleaning and normalization processing;

[0041] Among them, data cleaning is to clean missing values, outliers, or incorrect data points to ensure data quality;

[0042] Normalization processing is to scale the data values to the same scale, which helps to accelerate the convergence of the model.

[0043] Purification module, used for purifying mercury-containing gas;

[0044] Specifically, a gas purification device is also provided in the monitoring node for purifying mercury-containing gas; the purification intensity of the gas purification device when purifying mercury-containing gas is affected by the gas flow rate and the adsorbent;

[0045] The lower the gas flow rate flowing through the gas purification device, the more time the adsorbent will have to contact mercury, thereby improving the purification intensity. On the contrary, the higher the gas flow rate, the shorter the contact time between the adsorbent and mercury, and the lower the purification intensity;

[0046] Within a certain temperature range, the higher the temperature, the better the adsorption effect of the adsorbent, because the molecular motion intensifies, making it easier for mercury molecules to approach and enter the surface or pores of the adsorbent, thereby improving the purification intensity. However, if the temperature is too high, it may also affect the lifespan of the adsorbent or cause other problems, such as secondary release pollution;

[0047] The type and replacement frequency of the adsorbent will also affect the purification intensity. Adsorbents with higher performance have better adsorption effects and can enhance the purification intensity. Different types of adsorbents have different affinities for mercury; the higher the replacement frequency of the adsorbent, the better the adsorption effect, because a large amount of mercury adsorbed on the surface of the adsorbent after use will affect the adsorption effect.

[0048] Storage module, used for storing mercury concentration and environmental information; in this embodiment, cloud storage is used for data storage, which is convenient for early data summary storage and later call and analysis;

[0049] Analysis module, used for predicting the change trend of mercury pollution and generating a prediction result by using a machine learning algorithm based on the historical monitoring results and current monitoring results of a preset area;

[0050] Among them, the machine learning algorithm uses an LSTM model, which inputs historical and current mercury concentrations, temperatures, humidities, and wind speeds, and outputs the mercury concentration in a preset future time period;

[0051] The LSTM model includes: an input layer, an LSTM layer, a Dropout layer, a fully connected layer, and an output layer; in this embodiment, one input layer, a fully connected layer, and an output layer are provided, and several LSTM layers and Dropout layers; the input layer is connected to the LSTM layer, each LSTM layer is connected to a Dropout layer, the last Dropout layer is connected to the fully connected layer, and the fully connected layer is connected to the output layer;

[0052] The input to the input layer is a three-dimensional tensor with a shape of (number of samples, number of time steps, number of features); each sample represents a time window that contains data (mercury concentration, temperature, humidity, and wind speed) at multiple historical time points; the number of time steps represents the number of data points at historical time points contained in each sample; the number of features are all the variables used for prediction, which are mercury concentration, temperature, humidity, and wind speed in this embodiment; specifically, the input shape is (number of samples, 60, 4), each sample contains data at 60 historical time points, and each time point has 4 features (mercury concentration, temperature, humidity, and wind speed). If the time series constructed from historical monitoring results is [(t1, Hg1, T1, H1, V1), (t2, Hg2, T2, H2, V2),..., (tn, Hgn, Tn, Hn, Vn)], then the data input at one time is from (t1, Hg1, T1, H1, V1) to (t60, Hg60, T60, H60, V60).

[0053] In this embodiment, the number of LSTM layers is 5, each layer is set to 60 units, each LSTM layer is connected to a Dropout layer, the Dropout layer is connected to the next LSTM layer, and the LSTM layer returns a sequence for the next layer to continue processing the time series information. The last LSTM layer does not return a sequence. Among them, the Dropout layer is used to reduce the complexity of the model and prevent overfitting. The Dropout layer randomly discards a part of the neurons, thereby enhancing the generalization ability of the model.

[0054] The fully connected layer is used for final prediction, and the output dimension is R, corresponding to the mercury concentration at R future time points. In this embodiment, R is taken as 10, and the output layer is set with 10 nodes to output the predicted mercury concentration at the next 10 time points.

[0055] Using historical monitoring results, a training set and a test set are constructed, the LSTM model is trained, and it is tested whether the trained LSTM model meets the preset requirements. If so, the trained LSTM model is called for prediction. If not, the parameters in the LSTM are optimized.

[0056] The analysis module is further configured to adjust the working state of the purification module for purifying the mercury-containing gas according to the prediction result.

[0057] Specifically, according to the predicted mercury concentration in a preset future time period, the working state of the purification module for purifying mercury-containing gas is adjusted, where the working state includes: the air flow rate and the replacement frequency of the adsorbent; although the indicators of the working efficiency of the purification module also include temperature and the type of adsorbent, the temperature is greatly affected by the outside world, and the adsorbent has been installed, and it is troublesome to replace the type of adsorbent. It is not possible to replace the adsorbent at any time due to changes in mercury concentration. Therefore, in this solution, the working state of the purification module is mainly adjusted by adjusting the air flow rate of the gas passing through the purification device and the replacement frequency of the adsorbent;

[0058] If the mercury concentration in the preset future time period increases, the air flow rate is reduced and the replacement frequency of the adsorbent is increased; specifically, for each increase in the preset concentration value, the air flow rate of the preset air flow velocity value is reduced, and the replacement time interval of the adsorbent in the preset time period is reduced; where the preset concentration value, the preset air flow velocity value, and the preset time period are set according to requirements, and the air flow rate and the replacement frequency of the adsorbent are set with corresponding minimum and maximum thresholds, and the air flow rate and the replacement frequency of the adsorbent cannot exceed the range of the combination of the corresponding minimum and maximum thresholds to prevent excessive adjustment and cause the purification module to stop working or be overloaded;

[0059] If the mercury concentration in the preset future time period decreases, the air flow rate is increased and the replacement frequency of the adsorbent is reduced; specifically, for each decrease in the preset concentration value, the air flow rate of the preset air flow velocity value is increased, and the replacement time interval of the adsorbent in the preset time period is increased. In addition, other embodiments also include: judging whether the mercury concentration in the preset future time period does not belong to the preset mercury concentration range. If so, an analysis of the increase or decrease in the mercury concentration in the preset future time period is performed, and then the working state of the purification module for purifying mercury-containing gas is adjusted. If not, the working state of the purification module for purifying mercury-containing gas is not adjusted to avoid increasing the adjustment workload.

[0060] Embodiment 2

[0061] This embodiment is basically the same as the above embodiment, the difference is that: it further includes: a verification module;

[0062] The verification module is used to judge whether the monitoring result is abnormal. If so, a monitoring node abnormal information is generated and pushed to the management terminal of the operation and maintenance personnel, and at the same time, an abnormal warning of the monitoring node is also carried out;

[0063] Specifically, based on the geographical relationships and distances between the monitoring nodes at preset positions in the preset area, analyze the relationships between the monitoring nodes and construct a relationship topology network for the monitoring nodes, where the relationship topology network is a directed node graph; taking a simple example of multiple rooms, there are rooms A, B, C, and D. A chemical device is installed in room A, which will generate mercury. Rooms A, B, and C are connected in sequence, and monitoring nodes are set in each room. The mercury concentrations in rooms A, B, and C are related, while the mercury concentration in room D has nothing to do with the other three rooms. According to the distance from the position of the chemical device that generates mercury, theoretically, the mercury concentrations in rooms A, B, and C should decrease in sequence. Therefore, the relationship between the monitoring nodes analyzed is the monitored mercury concentration, A > B > C. In the directed node graph, the nodes represent the rooms, the vector direction represents the flow direction (here it is mercury gas), and the weight of the vector can represent the relationship between the nodes, as Figure 2 shown; the same applies to temperature, humidity, and wind speed. For example, the temperature is lower in places with higher altitudes, and the wind speed is greater in the narrowest part of the canyon wind, etc.;

[0064] For the monitoring results collected by each monitoring node, according to the relationship topology network, determine whether the monitoring results conform to the relationship. If so, determine that the monitoring results are correct; if not, determine that the monitoring results are abnormal. For the monitoring nodes with abnormal monitoring results, generate monitoring node abnormal information and push it to the management terminal of the operation and maintenance personnel. At the same time, an abnormal warning for the monitoring node is also issued. If the mercury concentration in room B is greater than that in room A, then it is determined that the monitoring node in room B is abnormal, generate monitoring node abnormal information, and push it to the management terminal of the operation and maintenance personnel. At the same time, an abnormal warning for the monitoring node is also issued, which is convenient for the operation and maintenance personnel to check and repair in time, prevent problems from occurring when the subsequent analysis module adjusts the working state of the purification module, and ensure the normal and accurate operation of the entire device.

[0065] Embodiment III

[0066] This embodiment is basically the same as the above embodiment, the difference is that: the analysis module is further configured to adjust the working state of the purification module for purifying the mercury-containing gas according to the prediction result, specifically including:

[0067] The analysis module, according to the prediction result, adopts an optimization model to generate an optimal working state plan for the purification module to purify the mercury-containing gas, and according to the optimal working state plan, generate adjustment information for the adjusted working state and send it to the purification module;

[0068] The purification module adjusts the working state of purifying the mercury-containing gas according to the adjustment information.

[0069] Among them, according to the prediction result, adopting an optimization model to generate an optimal working state plan for the purification module to purify the mercury-containing gas includes:

[0070] It is determined that the mercury concentration in the preset future preset time period does not belong to the preset mercury concentration range. If so, an optimization model is used to generate an optimal working state plan for the purification module to purify the mercury-containing gas, including:

[0071] S1. Determine whether the mercury concentration in the preset future time period increases or decreases. If it increases, several working state plans with reduced air flow velocity, increased adsorbent replacement frequency, and executed at a preset time point are randomly generated relative to the current working state; if it decreases, several working state plans with increased air flow velocity, decreased adsorbent replacement frequency, and executed at a preset time point are randomly generated relative to the current working state; the generated working state plans are combined into an initial population.

[0072] S2. Construct a fitness evaluation function.

[0073] The fitness evaluation function is a comprehensive evaluation function used to evaluate the change in the working state and the cost change, representing the adjustment difficulty and cost:

[0074] S = a×|u - u'| + b×|f - f'| + dΔc

[0075] where S is the value of the comprehensive evaluation function, u is the air flow velocity of the working state being executed, u' is the gas flow of the individual plan, f is the adsorbent replacement frequency of the working state being executed, f' is the adsorbent replacement frequency of the individual plan, Δc is the cost change amount, and a, b, d are adjustment coefficients.

[0076] S3. According to the fitness evaluation function, perform iterative optimization on the initial population to generate an optimal working state plan for the purification module to purify the mercury-containing gas. The specific process is as follows:

[0077] S301. Initialize the iteration number r = 1.

[0078] S302. According to the fitness function, calculate the fitness function value of each individual plan in the initial population, and perform the first sorting from small to large according to the fitness function value.

[0079] S303. According to the first sorting result, obtain the first k individual plans, and use a machine learning algorithm to preset whether the mercury concentration in the preset future time period belongs to the preset mercury concentration range after the working state plan executed at the preset time point of the individual plan. If so, retain the individual plan; if not, reject the individual plan, and extract the first individual plan among the unselected individual plans in the sorting result; in this embodiment, the machine learning algorithm also uses the LSTM model.

[0080] S304. Perform crossover and mutation on the obtained k individual solutions to form a number of new individual solutions, calculate the fitness function values of the new individual solutions, and perform a second sorting from small to large together with the individual solutions according to the fitness function values;

[0081] S305. Determine whether the current iteration number r is equal to the preset iteration number R. If so, execute S306; if not, then r = r + 1, update the individual solutions of the initial population to the second sorting result, and execute S302. If the second sorting result is used as the first sorting result in S302, then S303 can be directly executed; thus, the excellent genes of the parent generation are retained to ensure that the subsequent iterative purification can proceed in a more optimal direction;

[0082] S306. Obtain the first individual solution of the sorting result as the optimal working state solution and output it;

[0083] Generate adjustment information for adjusting the working state according to the output optimal working state solution and send it to the purification module for adjustment. Thus, compared with adjusting by a fixed value, it can better adapt to the change of mercury concentration, perform more accurate adjustment, and during the iterative optimization process, the excellent parent generation is retained to ensure that the subsequent iterative purification can proceed in a more optimal direction, improve the optimization efficiency, and avoid local optimality.

[0084] The above are only the embodiments of the present invention. Specific structures and characteristics and other common knowledge in the art are not described in detail here. Those of ordinary skill in the art know all the common technical knowledge in the technical field to which the invention belongs before the application date or the priority date, can know all the existing technologies in this field, and have the ability to apply the conventional experimental means before this date. Those of ordinary skill in the art can, under the inspiration given in this application, combine their own abilities to improve and implement this solution. Some typical well-known structures or well-known methods should not become obstacles for those of ordinary skill in the art to implement this application. It should be noted that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can still be made, and these should also be regarded as the protection scope of the present invention, which will not affect the implementation effect of the present invention and the practicality of the patent. The protection scope required by this application should be based on the content of its claims, and the specific implementation manners and the like recorded in the specification can be used to interpret the content of the claims.

Claims

1. An intelligent response mercury capture device for the atmosphere, characterized in that, Including: A capture module, a purification module, a storage module, and an analysis module; The capture module is used to monitor the mercury concentration and environmental information in a preset area and send the monitoring results to the storage module; The purification module is used to purify the mercury-containing gas; The storage module is used to store the mercury concentration and environmental information; The analysis module is used to predict the changing trend of mercury pollution and generate a prediction result by using a machine learning algorithm based on the historical and current monitoring results in the preset area; It is also used to adjust the working state of the purification module for purifying the mercury-containing gas according to the prediction result.

2. The intelligent mercury-responsive trapping device for atmospheric mercury according to claim 1, wherein The capture module includes: a monitoring grid; Monitoring nodes are set at several preset positions in the preset area to form a monitoring grid, and the mercury concentration and environmental information in the areas of each preset position are monitored. A mercury sensor and a weather station are set in the monitoring nodes; the environmental information includes, but is not limited to: temperature, humidity, and wind speed.

3. The atmospheric mercury intelligent response capture device according to claim 2, characterized in that, An edge computing sub-module is also set in the monitoring node, which is used to preprocess the mercury concentration and environmental information collected by the sensor and the weather station and upload the processed and summarized mercury concentration and environmental information to the storage module.

4. The atmospheric mercury intelligent response capture device according to claim 2, characterized in that, The purification module includes: a gas purification device set in the monitoring node, which is used to purify the mercury-containing gas.

5. The atmospheric mercury intelligent response capture device according to claim 2, characterized in that, The machine learning algorithm uses an LSTM model, inputs the historical and current mercury concentration, temperature, humidity, and wind speed, and outputs the mercury concentration in a preset future time period.

6. The atmospheric mercury intelligent response capture device according to claim 5, characterized in that, The LSTM model includes: an input layer, an LSTM layer, a Dropout layer, a fully connected layer, and an output layer; the input layer is connected to the LSTM layer, each LSTM layer is connected to a Dropout layer, the last Dropout layer is connected to the fully connected layer, and the fully connected layer is connected to the output layer; What the input layer inputs is a three-dimensional tensor, and its shape is (number of samples, time steps, number of features); each sample represents a time window and contains data (mercury concentration, temperature, humidity, and wind speed) at multiple historical time points; the time steps represent the number of data at historical time points contained in each sample; the number of features is all variables used for prediction, including: mercury concentration, temperature, humidity, and wind speed.

7. The atmospheric mercury intelligent response capture device according to claim 1, characterized in that, Adjusting the working state of the purification module for purifying the mercury-containing gas according to the prediction result includes: Adjusting the working state of the purification module for purifying the mercury-containing gas according to the predicted mercury concentration in the preset future time period, where the working state includes: air flow rate and replacement frequency of the adsorbent.

8. The intelligent mercury-responsive capture device for atmospheric mercury according to claim 7, wherein If the mercury concentration in the preset future time period increases, the air flow rate is reduced and the replacement frequency of the adsorbent is increased; If the mercury concentration in the preset future time period decreases, the air flow rate is increased and the replacement frequency of the adsorbent is reduced.

9. The atmospheric mercury intelligent response capture device according to claim 1, wherein, It also includes: A verification module; The verification module is used to judge whether there is an abnormality in the monitoring result. If so, it generates monitoring node abnormality information and pushes it to the management terminal of the operation and maintenance personnel, and at the same time, it also gives an early warning of the monitoring node abnormality.

10. The atmospheric mercury intelligent response capture device according to claim 9, characterized in that, Judging whether there is an abnormality in the monitoring result includes: Analyzing the relationship between the monitoring nodes according to the geographical relationship and distance between the monitoring nodes at the preset positions in the preset area, and constructing a relationship topology network between the monitoring nodes; For the monitoring results collected by each monitoring node, according to the relationship topology network, determine whether the monitoring results conform to the relationship. If so, determine that the monitoring results are correct; if not, determine that the monitoring results are abnormal.

Images