A Real-time Monitoring System and Method for Air Pollution in Industrial Plant Areas

Abstract

This application provides a real-time air pollution monitoring system and method for industrial plants. The system clusters the emission inflection points of pollutant concentration curves at various monitoring points within the industrial plant into multiple abnormal emission events, thereby identifying pollution source monitoring points within the industrial plant. It calculates the angle between the pointing vector from the pollution source monitoring point to other monitoring points within the industrial plant and the wind direction vector, obtaining the vector angle of the pollution source monitoring point. Then, it determines the environmental impact confidence level of the pollution source monitoring point using the vector angle and the maximum pollutant concentration in each abnormal emission event. When the environmental impact confidence level is greater than the impact threshold within the industrial plant, the sampling frequency of the downwind monitoring point is optimized based on the distance between the pollution source monitoring point and the downwind monitoring point. Based on the above scheme, risk confidence assessment of pollution sources in industrial plant air pollution monitoring can be achieved, thereby improving the accuracy of capturing abnormal emission events.

Description

Technical Field

[0001] This application relates to the field of pollution monitoring technology, and more specifically, to a real-time monitoring system and method for air pollution in industrial plants. Background Technology

[0002] Air pollution in industrial areas mainly originates from fuel combustion, chemical reactions, and material emissions during production processes, resulting in pollutants such as sulfur dioxide, nitrogen oxides, volatile organic compounds, and particulate matter. These pollutants not only create localized high concentrations of pollution within the factory area but also spread with air currents, affecting air quality in surrounding regions and posing a threat to ecosystems and public health. Air pollution in industrial areas is characterized by concentrated pollution sources, high emission intensity, and complex pollutant types, and is influenced by both factory layout and meteorological conditions.

[0003] Traditional fixed-frequency monitoring in industrial air pollution monitoring suffers from significant response delays and path prediction blind spots due to its uniform sampling strategy. It fails to detect the dynamic characteristics of pollution diffusion, and when abnormal emissions occur, monitoring points outside the pollution path continue to generate invalid data, while those along the path may miss concentration peaks due to sampling intervals. Static monitoring networks struggle to construct real-time transport trajectories of pollutants under wind conditions, causing the system to trigger alarms only after pollutants reach downstream monitoring points. This not only delays the golden window for source tracing but also fails to provide early warnings for unaffected areas, leaving the monitoring system in a reactive state. Therefore, achieving risk confidence assessment of pollution sources in industrial air pollution monitoring to improve the accuracy of abnormal emission event detection has become a major challenge for the industry. Summary of the Invention

[0004] This application provides a real-time monitoring system and method for air pollution in industrial plants, which can realize risk confidence assessment of pollution sources in air pollution monitoring of industrial plants, thereby improving the accuracy of capturing abnormal emission events.

[0005] Firstly, this application provides a method for real-time monitoring of air pollution in industrial plant areas, including:

[0006] By deploying sensors at various monitoring points within the industrial plant area, pollutant concentration data within the industrial plant area are collected at an initial frequency.

[0007] The pollutant concentration curves of each monitoring point are extracted from the pollutant concentration data. The emission inflection points in each pollutant concentration curve are clustered into multiple abnormal emission events. Then, the pollution source monitoring points in the industrial plant area are screened out by the meteorological information of each abnormal emission event and the concentration gradient of each abnormal emission event.

[0008] Based on the meteorological information and pollutant concentration data of the industrial plant area at the current moment, the angle between the pointing vector of the pollution source monitoring point to other monitoring points in the industrial plant area and the wind direction vector is calculated to obtain the vector angle of the pollution source monitoring point. Then, the environmental impact confidence of the pollution source monitoring point is determined by the vector angle and the maximum pollutant concentration in each abnormal emission event.

[0009] When the confidence level of the environmental impact is greater than the impact threshold within the industrial plant area, the sampling frequency of the downwind monitoring point is optimized based on the distance between the pollution source monitoring point and the downwind monitoring point.

[0010] In some embodiments, extracting pollutant concentration curves for each monitoring point from the pollutant concentration data specifically includes:

[0011] The pollutant concentration data are interpolated and aligned using a unified time base to obtain the concentration sequence at equal time intervals at each monitoring point.

[0012] By connecting the various concentration sequences in chronological order, pollutant concentration curves for each monitoring point are constructed.

[0013] In some embodiments, clustering emission inflection points in various pollutant concentration curves into multiple anomalous emission events specifically includes:

[0014] The starting and ending inflection points are obtained from the concentration curves of each pollutant, thus obtaining the emission inflection point pairs in each pollutant concentration curve.

[0015] Multiple candidate anomaly segments were identified by aligning the concentration time intervals between the initial and final inflection points of each emission inflection point.

[0016] Spatiotemporal clustering was performed on all candidate anomaly segments to obtain multiple anomaly emission events.

[0017] In some embodiments, the selection of pollution source monitoring points within an industrial plant area based on meteorological information and concentration gradients of various abnormal emission events specifically includes:

[0018] For each abnormal emission event, the concentration centroid of the abnormal emission event is determined by the concentration gradient of the abnormal emission event;

[0019] Extract the dominant upwind direction of the abnormal emission event from the meteorological information of the abnormal emission event;

[0020] The pollution source points of abnormal emission events are screened out in the dominant upwind fan-shaped area of ​​the concentration center, thereby obtaining the pollution source points of each abnormal emission event;

[0021] Identify pollution source monitoring points within the industrial plant area by identifying all pollution source points.

[0022] In some embodiments, the angle between the pointing vector from the pollution source monitoring point to other monitoring points within the industrial plant area and the wind direction vector is calculated based on the meteorological information and pollutant concentration data of the industrial plant area at the current moment. Specifically, the angle between the vectors of the pollution source monitoring points includes:

[0023] Obtain the pointing vector from the pollution source monitoring point to other monitoring points within the industrial plant area from the pollutant concentration data at the current moment;

[0024] Obtain the wind direction vector from the meteorological information of the industrial plant area at the current moment;

[0025] Calculate the angle between each pointing vector and the wind direction vector, and then determine the vector angle of the pollution source monitoring point using all the angles.

[0026] In some embodiments, determining the environmental impact confidence level of the pollution source monitoring point by means of the vector angle and the maximum pollutant concentration in each abnormal emission event specifically includes:

[0027] The angle influence factor of the pollution source monitoring point is determined by the included vector angle;

[0028] The concentration influence factor of the pollution source monitoring point is determined by the maximum pollutant concentration at each abnormal emission event.

[0029] The environmental impact confidence level of the pollution source monitoring point is determined based on the included angle influence factor and the concentration influence factor.

[0030] In some embodiments, optimizing the sampling frequency of the downwind monitoring point based on the distance between the pollution source monitoring point and the downwind monitoring point specifically includes:

[0031] Obtain multiple downwind monitoring points from the pollution source monitoring points;

[0032] Establish frequency adjustment rules for downwind monitoring points;

[0033] The sampling frequency of the downwind monitoring points is adjusted according to the frequency adjustment rules based on the distance between the pollution source monitoring point and each downwind monitoring point.

[0034] Secondly, this application provides a real-time air pollution monitoring system for industrial plants, including a frequency optimization unit, wherein the frequency optimization unit includes:

[0035] The data acquisition module is used to collect pollutant concentration data in the industrial plant area at an initial frequency by using sensors deployed at various monitoring points within the industrial plant area.

[0036] The processing module is used to extract pollutant concentration curves of each monitoring point from the pollutant concentration data, cluster the emission inflection points in each pollutant concentration curve into multiple abnormal emission events, and then screen out the pollution source monitoring points in the industrial plant area through the meteorological information of each abnormal emission event and the concentration gradient of each abnormal emission event.

[0037] The processing module is also used to calculate the angle between the pointing vector of the pollution source monitoring point to other monitoring points in the industrial plant area and the wind direction vector based on the meteorological information and pollutant concentration data of the industrial plant area at the current moment, to obtain the vector angle of the pollution source monitoring point, and then determine the environmental impact confidence of the pollution source monitoring point through the vector angle and the maximum pollutant concentration in each abnormal emission event.

[0038] The execution module is used to optimize the sampling frequency of the downwind monitoring point based on the distance between the pollution source monitoring point and the downwind monitoring point when the confidence level of the environmental impact is greater than the impact threshold within the industrial plant area.

[0039] Thirdly, this application provides a computer device, which includes a memory and a processor. The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device performs the above-described method for real-time monitoring of air pollution in industrial plants.

[0040] Fourthly, this application provides a computer-readable storage medium storing instructions or code that, when executed on a computer, cause the computer to implement the aforementioned method for real-time monitoring of air pollution in industrial plant areas.

[0041] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0042] This application provides a real-time air pollution monitoring system and method for industrial plants. The system collects pollutant concentration data at an initial frequency using sensors deployed at various monitoring points within the industrial plant area. Pollutant concentration curves for each monitoring point are extracted from the data. Emission inflection points on these curves are clustered into multiple abnormal emission events. Pollution source monitoring points within the industrial plant area are then identified using meteorological information and concentration gradients from each abnormal emission event. The angle between the pointing vector from the pollution source monitoring point to other monitoring points within the industrial plant area and the wind direction vector is calculated based on the current meteorological information and pollutant concentration data. This yields the vector angle of the pollution source monitoring point. The environmental impact confidence level of the pollution source monitoring point is then determined using this vector angle and the maximum pollutant concentration from each abnormal emission event. When the environmental impact confidence level exceeds the impact threshold within the industrial plant area, the sampling frequency of the downwind monitoring point is optimized based on the distance between the pollution source monitoring point and the downwind monitoring point.

[0043] Therefore, in this application, when the environmental impact confidence level is greater than the impact threshold within the industrial plant area, the sampling frequency of the downwind monitoring point is optimized based on the distance between the pollution source monitoring point and the downwind monitoring point. First, determining the pollution source monitoring point allows for the identification of potential emission source locations with high correlation in both physical space and the event causal chain, thereby elevating discrete, superficial concentration alarm events into a complete pollution event chain with clear source tracing. Through spatial analysis that integrates meteorological information and concentration gradients, the relationship between the successive triggering of multiple monitoring points due to pollutant diffusion and the actual emission source is effectively identified. This overcomes the one-sidedness of traditional monitoring that only relies on a single monitoring point exceeding the concentration standard for alarms, and avoids the risk of misjudging affected points downstream of pollution as sources. By identifying the most probable source monitoring point for each abnormal emission event, instead of responding to alarms from individual sensors in isolation, a complete diffusion picture can be reconstructed, improving the accuracy of event tracing. Then, by determining the environmental impact confidence level, a dynamic assessment index can be obtained to quantitatively characterize the potential environmental hazard level of the pollution source monitoring point. This enables risk classification and prioritization of multiple pollution source monitoring points, driving adaptive optimization of monitoring resources. By comprehensively considering the historical static emission intensity of the pollution source and dynamic meteorological diffusion conditions, a multi-dimensional risk assessment problem is transformed into a quantitative confidence scalar. This approach addresses the challenge of effectively distinguishing between high-intensity emissions under unfavorable diffusion conditions and low-intensity emissions under highly efficient diffusion conditions using only absolute concentration values ​​or fixed rules in traditional monitoring. Based on this confidence index, it identifies pollution sources with a history of high emissions that are currently spreading downwind in sensitive areas, allowing for the priority allocation of monitoring resources. This transforms industrial air pollution monitoring into a highly efficient and predictive monitoring model focused on the highest-risk targets. In summary, this solution enables risk confidence assessment of pollution sources in industrial air pollution monitoring, thereby improving the accuracy of capturing abnormal emission events. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is an exemplary flowchart of a real-time monitoring method for air pollution in industrial plants, according to some embodiments of this application;

[0046] Figure 2 This is a flowchart illustrating the process of determining the confidence level of environmental impact according to some embodiments of this application;

[0047] Figure 3 This is a schematic diagram of the structure of a frequency optimization unit according to some embodiments of this application;

[0048] Figure 4 This is a schematic diagram of the structure of a computer device for implementing a real-time monitoring method for air pollution in industrial plants, according to some embodiments of this application. Detailed Implementation

[0049] To better understand the technical solution of this application, the technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0050] refer to Figure 1 The figure is an exemplary flowchart of a real-time monitoring method for air pollution in an industrial plant area according to some embodiments of this application. The real-time monitoring method for air pollution in an industrial plant area mainly includes the following steps:

[0051] In step 101, pollutant concentration data within the industrial plant area are collected at an initial frequency using sensors deployed at various monitoring points within the plant area.

[0052] It should be noted that, in this application, the pollutant concentration data is monitoring information that includes the pollutant type and its concentration quantification value. In specific implementation, continuous atmospheric pollutant concentration sensors are installed and calibrated at various monitoring points within the industrial plant area, and a unified initial frequency is configured for all sensors. This initial frequency serves as the reference sampling rate. Each sensor periodically (once every 5 seconds by default) measures the pollutant concentration at each sampling time point. The sensors at each monitoring point will continuously generate pollutant concentration readings with timestamps according to the timing instructions, and the set of all pollutant concentration readings within a specified time period (the most recent week by default) will be used as the pollutant concentration data within the industrial plant area.

[0053] In step 102, pollutant concentration curves for each monitoring point are extracted from the pollutant concentration data. The emission inflection points in each pollutant concentration curve are clustered into multiple abnormal emission events. Then, the pollution source monitoring points in the industrial plant area are screened out by the meteorological information of each abnormal emission event and the concentration gradient of each abnormal emission event.

[0054] In some embodiments, extracting pollutant concentration curves for each monitoring point from the pollutant concentration data can be achieved using the following steps:

[0055] The pollutant concentration data are interpolated and aligned using a unified time base to obtain the concentration sequence at equal time intervals at each monitoring point.

[0056] By connecting the various concentration sequences in chronological order, pollutant concentration curves for each monitoring point are constructed.

[0057] It should be noted that, in this application, the pollutant concentration curve is a graphical representation used to intuitively characterize the continuous change trend of pollutant concentration at different time points of a single monitoring point; the concentration sequence is an ordered set of pollutant concentration values ​​arranged in chronological order.

[0058] In practice, firstly, a common and unified time reference is set (default is once every 5 seconds). Using this reference time as the axis, a linear interpolation algorithm is used to calculate the concentration estimate at each standard time point for the pollutant concentration data. This generates a concentration sequence with equal time intervals that is strictly aligned in the time dimension for each monitoring point, thus obtaining the concentration sequence with equal time intervals for each monitoring point. Subsequently, for each monitoring point, the data points in the concentration sequence of the monitoring point are connected in chronological order in a Cartesian coordinate system. The connection result is used as the pollutant concentration curve for that monitoring point. The pollutant concentration curves for each monitoring point can be obtained in the above way.

[0059] In some embodiments, clustering emission inflection points in various pollutant concentration curves into multiple anomalous emission events can be achieved using the following steps:

[0060] The starting and ending inflection points are obtained from the concentration curves of each pollutant, thus obtaining the emission inflection point pairs in each pollutant concentration curve.

[0061] Multiple candidate anomaly segments were identified by aligning the concentration time intervals between the initial and final inflection points of each emission inflection point.

[0062] Spatiotemporal clustering was performed on all candidate anomaly segments to obtain multiple anomaly emission events.

[0063] It should be noted that, in this application, an abnormal emission event is a pollution diffusion process jointly represented by candidate abnormal segments that are related in time and space; an emission inflection point pair is the start and end time of a potential abnormal emission; and a candidate abnormal segment refers to a potential abnormal emission process to be confirmed.

[0064] In practice, firstly, for each pollutant concentration curve, the slope change value of the pollutant concentration curve at each standard time point is calculated. A concentration change rate threshold is preset based on historical experience. A positive value greater than the threshold is used as the starting inflection point indicating the beginning of an abnormal rise in concentration. A negative value greater than the threshold is used as the ending inflection point indicating the beginning of an abnormal decline after the concentration peak. These corresponding starting and ending inflection points are combined into emission inflection point pairs, thus obtaining the emission inflection point pairs in the pollutant concentration curve. The emission inflection point pairs in each pollutant concentration curve can be obtained through this method. First, inflection point pairs are established. Then, based on the positions of the start and end inflection points on the time axis in each emission inflection point pair, the corresponding concentration data segments within that time interval are extracted, thus identifying each data segment as a candidate anomaly segment, resulting in multiple candidate anomaly segments. Finally, using the start time of all candidate anomaly segments as the time coordinate and the geographical location of their respective monitoring points as the spatial coordinate, a density-based clustering algorithm is used to merge multiple candidate anomaly segments that are simultaneously clustered in time and space into the same emission group. Ultimately, each emission group obtained from clustering is treated as an independent anomaly emission event, thus yielding multiple anomaly emission events.

[0065] In some embodiments, the following steps can be used to screen out pollution source monitoring points within an industrial plant area based on meteorological information and concentration gradients of various abnormal emission events:

[0066] For each abnormal emission event, the concentration centroid of the abnormal emission event is determined by the concentration gradient of the abnormal emission event;

[0067] Extract the dominant upwind direction of the abnormal emission event from the meteorological information of the abnormal emission event;

[0068] The pollution source points of abnormal emission events are screened out in the dominant upwind fan-shaped area of ​​the concentration center, thereby obtaining the pollution source points of each abnormal emission event;

[0069] Identify pollution source monitoring points within the industrial plant area by identifying all pollution source points.

[0070] It should be noted that in this application, the pollution source monitoring point is a designated agent point of the pollution source in the monitoring network; the dominant upwind direction is the opposite direction of the source of the pollutant gas mass in each abnormal emission event; and the pollution source point is the actual geographical location within the plant area where the batch of pollutants was released in each abnormal emission event.

[0071] In specific implementation, firstly, for each abnormal emission event, the monitoring point with the highest concentration in the abnormal emission event is selected. Its geographical coordinates are used as a vector, and its corresponding pollutant concentration is used as a weight to calculate a weighted average, thus determining the calculated spatial coordinate point as the concentration centroid of the abnormal emission event. Next, historical wind direction data for the duration of the abnormal emission event is obtained from the meteorological information of the event. The average wind direction in the historical wind direction data for the duration of the abnormal emission event is calculated, and the opposite direction of this average wind direction is taken as the dominant upwind direction of the abnormal emission event. Then, with the concentration centroid as the vertex, a preset angle (default is...) is defined along the dominant upwind axis. A fan-shaped search area of ​​30° is used to select monitoring points within this fan-shaped area that have the highest concentration peak or the fastest concentration increase rate during this event. The actual geographical location of these monitoring points is then taken as the pollution source point of the abnormal emission event. The pollution source points of each abnormal emission event can be obtained through the above method. Finally, the set of all pollution source points after deduplication of coordinates is taken as the pollution source monitoring points within the industrial plant area. It should be noted that in this application, if there is only one pollution source monitoring point, the subsequent sampling frequency is adjusted for a single pollution source monitoring point; if there are multiple pollution source monitoring points, the same method is used to adjust the sampling frequency for each pollution source monitoring point.

[0072] In step 103, the angle between the pointing vector of the pollution source monitoring point to other monitoring points in the industrial plant area and the wind direction vector is calculated based on the meteorological information and pollutant concentration data of the industrial plant area at the current time. The vector angle of the pollution source monitoring point is obtained, and then the environmental impact confidence of the pollution source monitoring point is determined by the vector angle and the maximum pollutant concentration in each abnormal emission event.

[0073] In some embodiments, the angle between the pointing vector from the pollution source monitoring point to other monitoring points within the industrial plant area and the wind direction vector is calculated based on the meteorological information and pollutant concentration data of the industrial plant area at the current moment. The vector angle of the pollution source monitoring point can be obtained by the following steps:

[0074] Obtain the pointing vector from the pollution source monitoring point to other monitoring points within the industrial plant area from the pollutant concentration data at the current moment;

[0075] Obtain the wind direction vector from the meteorological information of the industrial plant area at the current moment;

[0076] Calculate the angle between each pointing vector and the wind direction vector, and then determine the vector angle of the pollution source monitoring point using all the angles.

[0077] It should be noted that in this application, the included vector angle represents the potential directional distribution of the pollution source's influence on all monitoring point locations under the current wind field conditions; the pointing vector represents the spatial direction from the pollution source to the target monitoring point; and the wind direction vector represents the direction of the wind at the current moment.

[0078] In practice, firstly, a unified Cartesian coordinate system is established, and the geographical coordinates of the pollution source monitoring point and all other monitoring points within the factory area are placed under this coordinate system. For each other monitoring point, a vector is calculated pointing from the coordinates of the pollution source monitoring point to the coordinates of that monitoring point, thus obtaining a set of pointing vectors. The pointing vectors from the pollution source monitoring point to other monitoring points within the industrial plant area can be obtained in this way. Then, wind direction data is read from the meteorological information of the industrial plant area at the current moment, and the wind direction (the direction from which the wind is coming) is converted into a unit vector pointing to the direction the wind is blowing under this unified coordinate system as the wind direction vector according to meteorological conventions. Finally, for each pointing vector, the angle between the pointing vector and the wind direction vector is calculated using the vector angle formula, which is the angle between the pointing vector and the wind direction vector. The angle between each pointing vector and the wind direction vector can be obtained in this way, and the set of all angles is taken as the vector angle of the pollution source monitoring point.

[0079] In some embodiments, the environmental impact confidence level of the pollution source monitoring point is determined by the vector angle and the maximum pollutant concentration in each abnormal emission event, with reference to... Figure 2 The diagram is a flowchart illustrating the process of determining the confidence level of environmental impact in some embodiments of this application. In this embodiment, determining the confidence level of environmental impact can be achieved using the following steps:

[0080] In step 1031, the angle influence factor of the pollution source monitoring point is determined by the vector angle;

[0081] In step 1032, the concentration influence factor of the pollution source monitoring point is determined by the maximum pollutant concentration at the pollution source monitoring point in each abnormal emission event;

[0082] In step 1033, the environmental impact confidence level of the pollution source monitoring point is determined based on the included angle influence factor and the concentration influence factor.

[0083] It should be noted that, in this application, the environmental impact confidence level is a quantitative assessment indicator used to ultimately determine the possibility that the pollution source monitoring point poses a pollution risk to the environment; the included angle influence factor is a quantitative numerical indicator used to characterize the degree of favorable influence of the pollution source monitoring point on the orientation of all other monitoring points in the industrial plant area under the current wind field conditions; and the concentration influence factor is a quantitative numerical indicator used to characterize the pollutant release intensity level of the pollution source monitoring point in historical abnormal emission events.

[0084] In practice, firstly, the included angles of all vectors from the pollution source monitoring points are read, and the arithmetic mean of the cosine values ​​of all included angles is calculated as the included angle influence factor of the pollution source monitoring point. Secondly, pollutant concentration data in each abnormal emission event associated with the pollution source monitoring point are retrieved, and the maximum pollutant concentration value appearing at the pollution source monitoring point is selected from each pollutant concentration data. The maximum pollutant concentration value is normalized using a preset background concentration value and a global maximum concentration value, and the normalized value is used as the concentration influence factor of the pollution source monitoring point. Finally, the weight coefficients of the included angle influence factor and the concentration influence factor are obtained from a preset weight configuration table, and the weighted included angle influence factor and the weighted concentration influence factor are summed, and the calculated weighted sum is used as the environmental impact confidence of the pollution source monitoring point.

[0085] In step 104, when the confidence level of the environmental impact is greater than the impact threshold within the industrial plant area, the sampling frequency of the downwind monitoring point is optimized based on the distance between the pollution source monitoring point and the downwind monitoring point.

[0086] It should be noted that in this application, when the environmental impact confidence level is greater than the impact threshold within the industrial plant area, the pollution source monitoring point simultaneously possesses high diffusion risk due to its location in a key downwind direction and high pollution potential due to its historical emission intensity. The possibility of it triggering a regional pollution event has reached the condition for intervention monitoring. Therefore, intervention measures must be taken to increase the monitoring frequency of the pollution source monitoring point and its downstream areas in order to capture more refined pollution diffusion dynamics, buy valuable time for accurate source tracing and emergency response, and ultimately prioritize the use of limited data resources on the highest-risk monitoring targets.

[0087] In some embodiments, optimizing the sampling frequency of the downwind monitoring point based on the distance between the pollution source monitoring point and the downwind monitoring point can be achieved through the following steps:

[0088] Obtain multiple downwind monitoring points from the pollution source monitoring points;

[0089] Establish frequency adjustment rules for downwind monitoring points;

[0090] The sampling frequency of the downwind monitoring points is adjusted according to the frequency adjustment rules based on the distance between the pollution source monitoring point and each downwind monitoring point.

[0091] It should be noted that, in this application, the downwind monitoring point is a monitoring point located on the pollutant diffusion path; the frequency adjustment rule is a logical rule that clearly defines the mathematical relationship between the distance parameter and the sampling frequency.

[0092] In practice, firstly, based on the current wind field data and the spatial location of the monitoring points, the angle between the vector pointing from the pollution source monitoring point to each other monitoring point within the factory area and the wind direction vector is calculated. All monitoring points with angles less than or equal to a preset threshold (default 30°) are selected as downwind monitoring points of the pollution source monitoring point, thus obtaining multiple downwind monitoring points of the pollution source monitoring point. Subsequently, a preset mathematical mapping model is used as the frequency adjustment rule. This frequency adjustment rule explicitly stipulates that the adjustment amount of the sampling frequency is inversely proportional to the distance between the pollution source monitoring point and the downwind monitoring point, i.e., the closer the distance, the greater the frequency increase. Finally, for each downwind monitoring point, the distance value between the downwind monitoring point and the pollution source monitoring point is read, and this distance value is substituted into the aforementioned frequency adjustment rule for calculation. The calculated new value is then used as the adjusted sampling frequency of the downwind monitoring point. Through the above method, the adjusted sampling frequency of each downwind monitoring point can be obtained.

[0093] Furthermore, in another aspect of this application, in some embodiments, this application provides a real-time monitoring system for air pollution in industrial plant areas, which includes a frequency optimization unit, referencing... Figure 3 The figure is a schematic diagram of the structure of a frequency optimization unit according to some embodiments of this application. The frequency optimization unit includes: a data acquisition module 201, a processing module 202, and an execution module 203, which are described below:

[0094] The acquisition module 201 in this application is mainly used to acquire pollutant concentration data in the industrial plant area at an initial frequency by using sensors deployed at various monitoring points in the industrial plant area.

[0095] Processing module 202, in this application, is used to extract pollutant concentration curves of each monitoring point from the pollutant concentration data, cluster the emission inflection points in each pollutant concentration curve into multiple abnormal emission events, and then screen out the pollution source monitoring points in the industrial plant area through the meteorological information of the industrial plant area in each abnormal emission event and the concentration gradient of each abnormal emission event.

[0096] It should be noted that the processing module 202 is also used to calculate the angle between the pointing vector of the pollution source monitoring point to other monitoring points in the industrial plant area and the wind direction vector based on the meteorological information and pollutant concentration data of the industrial plant area at the current time, to obtain the vector angle of the pollution source monitoring point, and then determine the environmental impact confidence of the pollution source monitoring point through the vector angle and the maximum pollutant concentration in each abnormal emission event.

[0097] The execution module 203 in this application is mainly used to optimize the sampling frequency of the downwind monitoring point based on the distance between the pollution source monitoring point and the downwind monitoring point when the environmental impact confidence level is greater than the impact threshold within the industrial plant area.

[0098] The foregoing has detailed examples of the real-time monitoring system and method for air pollution in industrial plants provided in the embodiments of this application. It is understood that the corresponding apparatus, in order to achieve the above functions, includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specified application, but such implementation should not be considered beyond the scope of this application.

[0099] In some embodiments, this application also provides a computer device, the computer device including a memory and a processor, the memory for storing a computer program, and the processor for calling and running the computer program from the memory, so that the computer device performs the above-described method for real-time monitoring of air pollution in industrial plants.

[0100] In some embodiments, reference Figure 4 The dashed lines in the figure indicate that the unit or module is optional. This figure is a structural schematic diagram of a computer device for implementing a real-time monitoring method for air pollution in industrial plants according to an embodiment of this application. The real-time monitoring method for air pollution in industrial plants described in the above embodiments can... Figure 4 The computer device shown is used to implement this, and the computer device includes at least one processor 301, a memory 302 and at least one communication unit 305. The computer device may be a terminal device, a server or a chip.

[0101] Processor 301 can be a general-purpose processor or a special-purpose processor. For example, processor 301 can be a central processing unit (CPU), which can be used to control computer devices, execute software programs, and process data from software programs. The computer device may also include a communication unit 305 for inputting (receiving) and outputting (transmitting) signals.

[0102] For example, the computer device may be a chip, and the communication unit 305 may be the input and / or output circuit of the chip, or the communication unit 305 may be the communication interface of the chip, which may be a component of a terminal device, network device or other device.

[0103] For example, the computer device may be a terminal device or a server, and the communication unit 305 may be a transceiver of the terminal device or the server, or the communication unit 305 may be a transceiver circuit of the terminal device or the server.

[0104] The computer device may include one or more memories 302 storing a program 304. The program 304 can be executed by a processor 301 to generate instructions 303, causing the processor 301 to execute the method described in the above method embodiments according to the instructions 303. Optionally, the memory 302 may also store data (such as a target audit model). Optionally, the processor 301 may also read data stored in the memory 302, which may be stored at the same storage address as the program 304, or it may be stored at a different storage address than the program 304.

[0105] The processor 301 and memory 302 can be configured separately or integrated together, for example, integrated on the system on chip (SOC) of the terminal device.

[0106] It should be understood that each step of the above method embodiment can be completed by hardware logic circuits or software instructions in the processor 301. The processor 301 can be a CPU, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, such as discrete gate, transistor logic devices, or discrete hardware components.

[0107] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0108] For example, in some embodiments, this application also provides a computer-readable storage medium storing instructions or code that, when executed on a computer, cause the computer to implement the above-described method for real-time monitoring of air pollution in industrial plants.

[0109] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0110] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for real-time monitoring of atmospheric pollution in an industrial plant, characterized in that, The method comprises the following steps: Collecting pollutant concentration data in the industrial plant at initial frequency through sensors arranged at each monitoring point in the industrial plant; Extracting pollutant concentration curves of each monitoring point from the pollutant concentration data, clustering emission inflection points in each pollutant concentration curve into multiple abnormal emission events, and further screening a pollution source monitoring point in the industrial plant through meteorological information of the industrial plant in each abnormal emission event and concentration gradient of each abnormal emission event; Calculating an included angle between a pointing vector of the pollution source monitoring point pointing to other monitoring points in the industrial plant and a wind direction vector according to meteorological information of the industrial plant at a current time and the pollutant concentration data, obtaining a vector included angle of the pollution source monitoring point, and further determining an environmental impact confidence of the pollution source monitoring point through the vector included angle and a maximum pollutant concentration in each abnormal emission event, wherein the environmental impact confidence is a quantitative evaluation index for finally judging a possibility of pollution risk of the pollution source monitoring point to the environment; When the environmental impact confidence is greater than an impact threshold in the industrial plant, optimizing and configuring a sampling frequency of a downwind monitoring point according to a distance between the pollution source monitoring point and the downwind monitoring point; Wherein, determining the environmental impact confidence of the pollution source monitoring point through the vector included angle and the maximum pollutant concentration in each abnormal emission event specifically comprises: Determining an included angle impact factor of the pollution source monitoring point through the vector included angle; Determining a concentration impact factor of the pollution source monitoring point through the maximum pollutant concentration of the pollution source monitoring point in each abnormal emission event; Determining the environmental impact confidence of the pollution source monitoring point according to the included angle impact factor and the concentration impact factor.

2. The method of claim 1, wherein, Extracting pollutant concentration curves of each monitoring point from the pollutant concentration data specifically comprises: Interpolating and aligning all data with a uniform time reference to obtain concentration sequences of each monitoring point at equal time intervals; Connecting each concentration sequence in time sequence to construct a pollutant concentration curve of each monitoring point.

3. The method of claim 1, wherein, Clustering emission inflection points in each pollutant concentration curve into multiple abnormal emission events specifically comprises: Obtaining a starting inflection point and an ending inflection point from each pollutant concentration curve, and further obtaining an emission inflection point pair in each pollutant concentration curve; Determining multiple candidate abnormal segments through a concentration time period between the starting inflection point and the ending inflection point in each emission inflection point pair; Performing time and space clustering on all candidate abnormal segments to obtain multiple abnormal emission events.

4. The method of claim 1, wherein, Screening a pollution source monitoring point in the industrial plant through meteorological information of the industrial plant in each abnormal emission event and a concentration gradient of each abnormal emission event specifically comprises: For each abnormal emission event, determining a concentration gravity center of the abnormal emission event through the concentration gradient of the abnormal emission event; Extracting a dominant upwind direction of the abnormal emission event from the meteorological information of the abnormal emission event; Screening a pollution source point of the abnormal emission event in a dominant upwind direction sector of the concentration gravity center, and further obtaining a pollution source point of each abnormal emission event; Determine the pollution source monitoring points in the industrial plant area through all pollution source points.

5. The method of claim 1, wherein, Calculate the angle between the pointing vector of the pollution source monitoring point pointing to other monitoring points in the industrial plant area and the wind direction vector according to the meteorological information and the pollutant concentration data of the industrial plant area at the current time, to obtain the vector angle of the pollution source monitoring point, and the vector angle specifically includes: Obtain the pointing vector of the pollution source monitoring point pointing to other monitoring points in the industrial plant area from the pollutant concentration data of the industrial plant area at the current time; Obtain the wind direction vector from the meteorological information of the industrial plant area at the current time; Calculate the angle between each pointing vector and the wind direction vector, and then determine the vector angle of the pollution source monitoring point through all the angles.

6. The method of claim 1, wherein, Optimally configure the sampling frequency of the downwind monitoring point according to the distance between the pollution source monitoring point and the downwind monitoring point, and the optimal configuration specifically includes: Obtain multiple downwind monitoring points of the pollution source monitoring point; Establish a frequency adjustment rule for the downwind monitoring points; Adjust the sampling frequency of the downwind monitoring point according to the distance between the pollution source monitoring point and each downwind monitoring point according to the frequency adjustment rule.

7. An industrial plant atmospheric pollution real-time monitoring system comprising a frequency optimization unit that uses the method of any one of claims 1 to 6 for industrial plant atmospheric pollution real-time monitoring, characterized in that, The frequency optimization unit includes: A collection module configured to collect pollutant concentration data in the industrial plant area at an initial frequency through sensors arranged at each monitoring point in the industrial plant area; A processing module configured to extract the pollutant concentration curve of each monitoring point from the pollutant concentration data, cluster the emission inflection points in each pollutant concentration curve into multiple abnormal emission events, and then screen out the pollution source monitoring point in the industrial plant area through the meteorological information of the industrial plant area in each abnormal emission event and the concentration gradient of each abnormal emission event; The processing module is further configured to calculate the angle between the pointing vector of the pollution source monitoring point pointing to other monitoring points in the industrial plant area and the wind direction vector according to the meteorological information and the pollutant concentration data of the industrial plant area at the current time, to obtain the vector angle of the pollution source monitoring point, and then determine the environmental impact confidence of the pollution source monitoring point through the vector angle and the maximum pollutant concentration in each abnormal emission event; An execution module configured to optimally configure the sampling frequency of the downwind monitoring point according to the distance between the pollution source monitoring point and the downwind monitoring point when the environmental impact confidence is greater than an impact threshold value in the industrial plant area.

8. A computer device, comprising: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the industrial plant area atmospheric pollution real-time monitoring method in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores instructions or codes, and when the instructions or codes run on the computer, the computer executes the industrial plant area atmospheric pollution real-time monitoring method in any one of claims 1 to 6.

Images