Meteorological-driven intelligent tracing method for dangerous chemical leakage

Abstract

A meteorological-driven intelligent tracing method for leakage of hazardous chemical substances belongs to the technical field of hazardous chemical substance leakage detection, and comprises the following steps: deploying miniature meteorological stations and gas sensor arrays in a monitoring area according to a fixed interval to obtain meteorological and concentration data streams; and cleaning and structuring the meteorological and concentration data flow to generate a meteorological-concentration structured parameter table. And assimilating the structured parameter table to a lattice Boltzmann CFD model to recalculate the structured parameter table and output a gridding concentration distribution. And extracting out-of-standard region boundaries from the gridding concentration distribution, and generating a high-risk region boundary list. And generating a visual layer on a GIS platform based on the high-risk region boundary list, and triggering early warning information. Wherein the boundary of the exceeding region is a region in which the meteorological and concentration data in the gridding concentration distribution exceed a set threshold value. According to the method, the leakage source can be positioned at the first time after the hazardous chemical substance leaks, and the leakage source positioning efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of hazardous chemical leakage detection, and more specifically, relates to a weather-driven intelligent tracing method for hazardous chemical leakage. Background Art

[0002] In modern chemical parks, high value-added products such as PTA (purified terephthalic acid), super absorbent resin (SAP), EVA, ethylene oxide and its derivatives, acrylonitrile, methyl methacrylate (MMA) coexist with refining and petrochemical products (paraxylene PX, ethylene, MTO, PDH, etc.), forming a large industrial cluster covering petrochemicals, fine chemicals and polymer materials. Acetic acid, crude oil, refined oil, PX, ethylene, acrylonitrile, ethylene oxide, etc., which are widely used in the production process, are highly toxic, flammable, explosive or corrosive hazardous chemicals. Once the pipeline leaks or the storage tank is damaged, a high-concentration harmful cloud will quickly form in the plant and its surroundings, causing safety hazards. In recent years, the growth in demand for intelligent transformation of large chemical parks has put forward higher requirements for real-time and accurate monitoring and tracing technology of leakage accidents. How to quickly identify the location of the leakage source and dynamically track the gas diffusion range in complex scenarios such as pipeline corridors, storage tank areas, loading and unloading docks has become a core problem to ensure production safety and environmental risk control.

[0003] At present, the monitoring of hazardous chemical leaks in chemical parks mainly relies on the following means: fixed gas sensor network: gas detectors are deployed at limited locations near key pipelines, valves and storage tanks to collect concentrations in real time and link alarms with the SCADA system; video monitoring and manual inspections: regular inspection vehicles are used for on-site inspections, and visual features of leaks (such as vapor clouds and droplets) are manually determined; drone / mobile platform inspections: drones equipped with spectrometers or lidar are used for regular / event-triggered inspections of high-risk areas; multi-system linkage: sensor alarms, video images and GIS maps are preliminarily superimposed, and the emergency command center makes manual decisions on evacuation or valve closing.

[0004] Although the above technologies can provide leak warnings to a certain extent, they still have problems such as low update frequency, insufficient spatial resolution, disconnected visualization, and much manual intervention. Fixed sensors are sparsely located and cannot cover all pipelines. Diffusion models that rely on weather station data are difficult to reflect sudden wind shears. Video and concentration data are often displayed separately, and emergency assessment is inefficient. Summary of the invention

[0005] In order to solve the deficiencies in the prior art, the purpose of the present invention is to solve the above-mentioned defects and further propose a weather-driven intelligent tracing method for hazardous chemical leakage.

[0006] The present invention adopts the following technical solution.

[0007] The first aspect of the present invention discloses a weather-driven intelligent tracing method for hazardous chemical leakage, the method comprising: Deploy micro-weather stations and gas sensor arrays at fixed intervals within the monitoring area to obtain meteorological and concentration data streams; Cleaning and structuring the meteorological and concentration data streams to generate a meteorological-concentration structured parameter table; Assimilating the structured parameter table into a lattice Boltzmann CFD model to recalculate the structured parameter table and output a gridded concentration distribution; Extracting the boundaries of the exceeding-standard areas from the gridded concentration distribution to generate a list of boundaries of high-risk areas; Generate a visualization layer on the GIS platform based on the high-risk area boundary list and trigger warning information; Among them, the boundary of the exceeding-standard area is the area where the meteorological and concentration data in the gridded concentration distribution exceed the set threshold.

[0008] Furthermore, the micro-meteorological station includes a micro-wind speed and direction instrument for monitoring wind speed and direction data in the monitoring area; The micro-meteorological stations and gas sensor arrays are deployed at fixed intervals within the monitoring area to obtain meteorological and concentration data streams, including: Acquire the boundary coordinates of the monitoring area, and determine the coordinates of the monitoring starting reference point based on the boundary coordinates; Generating the installation coordinates of the micro weather station and the gas sensor according to the boundary coordinates, the fixed spacing, and the coordinates of the monitoring starting reference point, and integrating the installation coordinates into a grid coordinate set; Deploy a micro anemometer and a gas sensor at each installation coordinate in the grid coordinate set to obtain a list of nodes that have been installed; Each node in the node list is connected to a data aggregation server using LoRa, and the NTP protocol is configured to calibrate the micro anemometer and the gas sensor to synchronize the network of each node; The micro wind speed and direction instruments and gas sensors corresponding to each node after network synchronization collect wind speed and direction data and gas concentration data of each node according to the preset sampling period; The wind speed and direction data and the gas concentration data are aggregated, packaged and sent to the data aggregation server to obtain the meteorological and concentration data stream.

[0009] Furthermore, the meteorological and concentration data streams are cleaned and structured to generate a structured parameter table of meteorological-concentration, including: Verify each data record in the meteorological and concentration data stream to mark abnormal data and obtain a verified preliminary data set; wherein the time interval error between adjacent data records in the preliminary data set does not exceed the set time interval, the wind speed data value does not exceed the range of the micro anemometer, and the wind direction data value and the gas concentration value are both within a preset range; Using weighted average interpolation to replace the abnormal data, and cleaning the preliminary data set to obtain a standardized and aligned unified data set; The meteorological and concentration data from different sources in the unified data set are integrated into a unified format to generate the structured parameter table.

[0010] Further, assimilating the structured parameter table into a lattice Boltzmann CFD model to recalculate the structured parameter table and output a gridded concentration distribution includes: Inputting the structured parameter table into the lattice Boltzmann CFD model, extracting the coordinates of each grid center in the monitoring area, and determining the concentration data corresponding to each grid center from the structured parameter table; According to the weight of the D2Q9 model, the initial concentration distribution function field is constructed based on the coordinates and concentration data of each grid center; Based on the initial concentration distribution function field, calling the BGK operator relaxation algorithm to process each direction and each grid point to simulate the molecular collision and diffusion tendency, and obtain the post-collision distribution function field; Obtain the wind speed component of each discrete direction and grid point in the post-collision distribution function field and the unit displacement component in the corresponding direction in the D2Q9 model; Pushing the post-collision distribution function field to adjacent grid points along the corresponding direction in the D2Q9 model based on the wind speed component and the unit displacement component to obtain an updated distribution function field; The distribution of each grid point in the updated distribution function field is summed in all directions to obtain the gridded concentration distribution.

[0011] Furthermore, extracting the boundaries of the areas exceeding the standard from the gridded concentration distribution and generating a list of boundaries of high-risk areas includes: Obtaining a leaked product type identifier, and screening all grid points in the gridded concentration distribution according to a set reference threshold and type factor in the leaked product type identifier to obtain a set of grid points exceeding the standard; Processing the set of excess grid points on a two-dimensional grid by an eight-neighborhood connectivity algorithm to mark each connected component; Divide the grid points corresponding to the connected components with the same connectivity identifier into the same sub-region to obtain a list of connected sub-regions; Applying Moore's tracing and contour extraction algorithms on the binary mask of each sub-region in the list of connected sub-regions to generate closed boundaries along the periphery of each sub-region to obtain a list of boundary point sequences; Processing each closed boundary in the boundary point sequence list by using the Douglas-Peucker simplification algorithm to remove redundant vertices in the boundary point sequence list, and outputting a simplified boundary list; The maximum concentration value, area and minimum enclosing range of each sub-region in the simplified boundary list are calculated, and integrated to generate the high-risk area boundary list.

[0012] Furthermore, generating a visualization layer on a GIS platform based on the high-risk area boundary list and triggering early warning information includes: Encapsulating each boundary sequence in the high-risk area boundary list as a vector element, and adding an attribute field to each vector element to generate a GIS element set; wherein the attribute field includes the chemical type, the set threshold, and the maximum concentration; A vector layer is constructed in the GIS platform, and the GIS element set is loaded in the vector layer, so as to perform visualization operation on the boundary of the high-risk area in the vector layer to generate the visualization layer.

[0013] Furthermore, the generating of a visualization layer on a GIS platform based on the high-risk area boundary list and triggering of early warning information also includes: Constructing an indicator function for each sub-area in the high-risk area boundary list according to a concentration threshold and an area threshold set by safety regulations; When the concentration threshold does not exceed the maximum concentration value in the GIS element set or the area threshold does not exceed the standard area in the GIS element set, the value of the indicator function is the first value, otherwise the value of the indicator function is the second value; The sub-areas in the high-risk area boundary list whose values ​​of the indicator function are the first value are packaged into an alarm element list.

[0014] Furthermore, the generating of a visualization layer on a GIS platform based on the high-risk area boundary list and triggering of early warning information also includes: Identify the high-risk area boundary based on the alarm element list and generate an alarm target area; The alarm target area is sent to the command terminal. After receiving the alarm target area, the command terminal highlights it on the visualization layer and pops up an alarm panel; the alarm panel is used to display the alarm information.

[0015] A second aspect of the present invention discloses a terminal, including a processor and a storage medium; the characteristics are: The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of the method described in the first aspect.

[0016] The third aspect of the present invention discloses a computer-readable storage medium having a computer program stored thereon, characterized in that when the program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0017] The beneficial effects of the present invention are that, compared with the prior art, the present invention has the following advantages: (1) The present invention assimilates the high-frequency collected structured parameter table (including wind speed, wind direction and concentration data) into the lattice Boltzmann CFD model, realizing the dynamic recalculation of the structured parameter table and outputting high-precision gridded concentration distribution. Unlike the traditional solution based only on fixed meteorological parameters, the present invention cleverly embeds the real-time measured wind speed and wind direction directly into the equilibrium distribution function and external force terms, so that the "convection drive + diffusion relaxation" is deeply coupled in the simulation process, and the cloud can accurately shift and deform according to the real wind field in each time step. On this basis, each grid corresponds to the monitoring area for more accurate monitoring of hazardous chemical leaks, and can locate the leak source as soon as possible after the leak of hazardous chemicals, thereby improving the efficiency and accuracy of leak source positioning, thereby embodying the people-oriented safety concept, avoiding the need for manual exploration due to uncertain leaks, which may lead to unnecessary injury incidents.

[0018] (2) The present invention generates a visualization layer on the GIS platform to visualize the boundary list of high-risk areas and triggers early warning information at the same time. The precise location of the leakage source can be displayed to relevant personnel through the visualization layer in a timely manner, thus saving time for exploring the leakage source and improving the timeliness of solving the leakage source. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 The present invention provides a flow chart of a weather-driven intelligent tracing method for leaking hazardous chemicals. DETAILED DESCRIPTION

[0020] The present application is further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present application.

[0021] like Figure 1 As shown, in one embodiment, a weather-driven intelligent tracing method for hazardous chemical leakage includes the following steps: Step S110, deploying micro-weather stations and gas sensor arrays at fixed intervals in the monitoring area to obtain meteorological and concentration data streams.

[0022] It should be noted that the micro-meteorological station includes a micro-wind speed and direction meter, which is used to monitor the wind speed and direction data in the monitoring area.

[0023] In some embodiments, the weather-driven intelligent tracing method for hazardous chemical leakage provided by the present invention, step S110 specifically includes the following steps: Step S111, obtaining the boundary coordinates of the monitoring area, and determining the coordinates of the monitoring start reference point based on the boundary coordinates.

[0024] Step S112, generating the installation coordinates of the micro weather station and the gas sensor according to the boundary coordinates, the fixed spacing and the coordinates of the monitoring starting reference point, and integrating the installation coordinates into a grid coordinate set.

[0025] Step S113, deploying a micro anemometer and a gas sensor at each installation coordinate in the grid coordinate set to obtain a list of nodes that have been installed.

[0026] Step S114, using LoRa to connect each node in the node list to the data aggregation server, and configure the NTP protocol to calibrate the micro anemometer and gas sensor to synchronize the network of each node.

[0027] Step S115, the micro-wind speed and direction instruments and gas sensors corresponding to each node after network synchronization collect the wind speed and direction data and gas concentration data of each node according to a preset sampling period.

[0028] Step S116, the wind speed and direction data and the gas concentration data are aggregated and packaged and sent to a data aggregation server to obtain a meteorological and concentration data stream.

[0029] In a specific embodiment, the weather-driven intelligent tracing method for hazardous chemical leakage provided by the present invention includes steps 1 to 5: Step 1: Deployment and data collection of micro-weather stations and gas sensor arrays.

[0030] Specifically, micro-meteorological stations and gas sensor arrays are deployed at intervals of 200m to collect wind speed, wind direction and concentration data every 10s. By acquiring high-frequency environment and concentration information, a multi-point data basis is provided for positioning.

[0031] The following steps are involved: Step 1.1, determine the region boundaries and reference points.

[0032] Specifically, the coordinates of the southwest corner of the monitoring area are (x 0 ,y 0 ), which is obtained by reading the boundary value from the GIS base map and is used to clarify the grid generation benchmark to ensure the consistency of subsequent position calculations.

[0033] Step 1.2, grid point coordinate calculation.

[0034] Specifically, according to the following expression: ;

[0035] in, is the grid spacing, grid points satisfy , where i and j are non-negative integers, , To monitor the maximum value of the boundary coordinates of the area, the maximum index is determined by rounding down the actual range, and the complete sensor installation coordinates are generated to ensure that the area is covered without blind spots, and a grid coordinate set is obtained.

[0036] Step 1.3, sensor node physical installation.

[0037] Specifically, a micro anemometer and a gas sensor are installed at each coordinate in the grid coordinate set at a height of 2m±0.1m. A rain cover and a fixed bracket are also provided. Multi-point sensing equipment is deployed on the ground to provide hardware support for data collection.

[0038] Step 1.4: Network establishment and clock synchronization.

[0039] Specifically, LoRa / Wi-Fi / Ethernet nodes are used to access the data aggregation server, the NTP protocol is configured, the clock deviation is <50ms, and zero point and range calibration is performed on each sensor to eliminate timing and range drift and ensure reliable data synchronization of each node.

[0040] Step 1.5: Regular data collection and reporting.

[0041] Specifically, let the sampling period T = 10s, and trigger the reading of wind speed v and wind direction at each node at every moment. , gas concentration c, and send them to the server in a package. By continuously producing high-frequency, multi-point environmental and concentration data, the basic data stream required for subsequent assimilation and simulation is constructed.

[0042] Step S120, cleaning and structuring the meteorological and concentration data streams to generate a meteorological-concentration structured parameter table.

[0043] In some embodiments, the weather-driven intelligent tracing method for hazardous chemical leakage provided by the present invention, step S120 specifically includes the following steps: Step S121, verify each data record in the meteorological and concentration data stream to mark abnormal data and obtain a verified preliminary data set; wherein the time interval error between adjacent data records in the preliminary data set does not exceed the set time interval, the wind speed data value does not exceed the range of the micro anemometer, and the wind direction data value and the gas concentration value are both within the preset range.

[0044] Step S122, using weighted average interpolation to replace abnormal data and clean the preliminary data set to obtain a standardized and aligned unified data set.

[0045] Step S123, integrating the meteorological and concentration data from different sources in the unified data set into a unified format to generate a structured parameter table.

[0046] In a specific embodiment, the weather-driven intelligent tracing method for hazardous chemical leaks provided by the present invention, step 2, cleans and structures the collected data to generate a weather-concentration parameter table in a unified format to eliminate abnormal readings and unify the format to facilitate subsequent model assimilation.

[0047] The following steps are involved: Step 2.1: Data reception and preliminary verification.

[0048] Specifically, check the continuity of timestamps for each data record in the collected data stream (the time interval between adjacent records should be 10s±0.1s), the wind speed value v does not exceed the sensor range [0,40], and the wind direction angle value The data are within [0,360°) and the concentration value c is in [0,10000]ppm. The out-of-range or missing entries are considered abnormal data and will be removed to provide a reliable basis for subsequent processing.

[0049] Step 2.2, outlier identification and interpolation.

[0050] Specifically, for the records marked as abnormal data in step 2.2, the weighted average interpolation of the two valid readings before and after is adopted. If there are more than three consecutive missing data, the historical average value of the same site during the same period is used to replace them, so as to eliminate the gaps caused by occasional jitter and short-term packet loss and ensure the continuity of the time series.

[0051] Step 2.3, unit normalization and time alignment.

[0052] Specifically, confirm that all wind speed units are unified as m / s, wind directions retain integer degrees, all timestamps are rounded to seconds, concentration units are unified as ppm, and the ±0.5s error due to clock drift is corrected in the local gateway to eliminate abnormal data caused by different equipment ranges and clock deviations, form comparable and synchronizable inputs, and obtain a standardized and aligned unified data set.

[0053] Step 2.4, structured parameter table generation.

[0054] Specific, structured parameter table As shown below: ;

[0055] in, is a vector of length 4, They are wind speed, wind direction and concentration, which are output by the sensor; Seconds level timestamp.

[0056] By integrating multi-source data into a unified format, it is convenient for subsequent CFD models to be directly called.

[0057] Step S130, assimilating the structured parameter table into the lattice Boltzmann CFD model to recalculate the structured parameter table and output a gridded concentration distribution; In some embodiments, the weather-driven intelligent tracing method for hazardous chemical leakage provided by the present invention, step S130 specifically includes the following steps: Step S131, input the structured parameter table into the lattice Boltzmann CFD model, extract the coordinates of each grid center in the monitoring area, and determine the concentration data corresponding to each grid center from the structured parameter table.

[0058] Step S132, constructing an initial concentration distribution function field according to the weights of the D2Q9 model and the coordinates and concentration data of each grid center.

[0059] Step S133, based on the initial concentration distribution function field, calling the BGK operator relaxation algorithm to process each direction and each grid point to simulate the molecular collision and diffusion tendency, and obtain the post-collision distribution function field.

[0060] Step S134, obtaining the wind speed component of each discrete direction and grid point in the post-collision distribution function field and the unit displacement component in the corresponding direction in the D2Q9 model.

[0061] Step S135, based on the wind speed component and the unit displacement component, the post-collision distribution function field is pushed to the adjacent grid points along the corresponding direction in the D2Q9 model to obtain an updated distribution function field.

[0062] Step S136, summing the distribution in all directions for each grid point in the updated distribution function field to obtain a gridded concentration distribution.

[0063] In a specific embodiment, the weather-driven intelligent tracing method for hazardous chemical leakage provided by the present invention, step 3, assimilates the structured parameter table into the lattice Boltzmann CFD model, recalculates and outputs the gridded concentration distribution.

[0064] Specifically, the structured parameter table is assimilated into the lattice Boltzmann CFD model every 10 seconds, and the gridded concentration distribution is recalculated and output to simulate the cloud diffusion morphology in real time, no longer relying on low-frequency weather stations.

[0065] The following steps are involved: Step 3.1, distribution function initialization.

[0066] Specifically, take each grid center of the monitoring area , obtain the concentration corresponding to the point from the structured parameter vector P , according to the weights of the D2Q9 model (constant, )calculate: ;

[0067] The resulting array That is, it is the initial value of the collision and flow calculation. Through this calculation, the macroscopic concentration information is mapped into the microscopic distribution function field, providing a basis for subsequent collision and flow operations.

[0068] Step 3.2, collision (relaxation) operation.

[0069] Specifically, calculate the relaxation time , for each direction i and each grid point , apply the BKG operator relaxation: ; ; ; ;

[0070] in, is the distribution function field after collision, For balanced distribution, according to the local concentration Calculated with wind speed field.

[0071] It is understandable that since step 3 is continuously calculated in real time, the function and They are essentially the same, the only difference is that they need to collect real-time Related The selection of relaxation time depends on the characteristics of the hazardous chemicals and is usually between 0.6 and 1.0. The heavier the gas, the larger the value.

[0072] ; It can be understood that the collision operation simulates the molecular collision and diffusion tendency, so that the concentration distribution gradually tends to local equilibrium. In other words, it only changes the shape of the distribution function (amplitude adjustment), but does not change the position of the particles in space.

[0073] Step 3.3, flow (migration) operation.

[0074] Specifically, for each discrete direction index i=0,...,8 and each grid point , read the velocity component in this direction ,in, is the unit displacement component (constant) in the i-th direction in the D2Q9 model, and pushes the post-collision distribution function field to the adjacent grid points along this direction: ;

[0075] in, That is, the value of the output function field at the new time and new position, The time between the new moment and the original moment is changed. The above process is repeated for all grid points and directions. At the grid boundary, if the target position exceeds the definition domain, a “bounce” or “mirror” boundary treatment is used to ensure mass conservation.

[0076] It is understandable that the flow (migration) operation is the key driving force for the formation of concentration clouds by migrating the distribution after collision along each discrete velocity direction in space, realizing the macroscopic convection and diffusion process of particles. In other words, it redistributes the particle distribution in space, realizes the diffusion and migration of clouds in the region, and provides a new initial field for the next round of collision operation.

[0077] Step 3.4, macro concentration extraction and output.

[0078] Specifically, for each grid point By summing up the distributions in all directions, we can get the concentration field of the gridded concentration distribution vector, which can be directly used to extract high-risk areas.

[0079] Step S140, extracting the boundaries of the areas exceeding the standard from the gridded concentration distribution and generating a list of boundaries of high-risk areas.

[0080] Among them, the boundary of the exceeded area is the area where the meteorological and concentration data in the gridded concentration distribution exceed the set threshold.

[0081] In some embodiments, the weather-driven intelligent tracing method for hazardous chemical leakage provided by the present invention, step S140 specifically includes the following steps: Step S141, obtaining the leakage product type identification, and screening all grid points in the gridded concentration distribution according to the set reference threshold and type factor in the leakage product type identification to obtain a set of grid points exceeding the standard.

[0082] Step S142, processing the set of grid points exceeding the standard by using an eight-neighborhood connectivity algorithm on the two-dimensional grid to mark each connected component.

[0083] Step S143, dividing the grid points corresponding to the connected components with the same connectivity identifier into the same sub-region to obtain a connected sub-region list.

[0084] Step S144, applying Moore's tracing and contour extraction algorithms to the binary mask of each sub-region in the connected sub-region list to generate closed boundaries along the periphery of each sub-region to obtain a boundary point sequence list.

[0085] Step S145 , processing each closed boundary in the boundary point sequence list by using the Douglas-Peucker simplification algorithm to remove redundant vertices in the boundary point sequence list, and outputting a simplified boundary list.

[0086] Step S146, calculating the maximum concentration value, area and minimum enclosing range of each sub-region in the simplified boundary list, and integrating them to generate a high-risk area boundary list.

[0087] In a specific embodiment, the weather-driven intelligent tracing method for hazardous chemical leaks provided by the present invention, step 4, extracts the boundary of the exceeding standard area from the concentration distribution, generates a list of high-risk area boundaries, clarifies the scope of the high-concentration area, and provides a spatial basis for personnel deployment.

[0088] The following steps are involved: Step 4.1, setting chemical type thresholds and screening for excessive levels.

[0089] Specifically, the benchmark threshold is set according to the type of leaked product. , and the type factor Multiplication: ;

[0090] Among them, if light gas (such as ethylene), ; If heavy gases (such as ethylene oxide and its derivatives), ; If the liquid vapor (such as acrylonitrile), For all grid points ,like , then add it to the set of grid points that exceed the standard S, and output: ;

[0091] in, is the grid point concentration distribution.

[0092] The present invention adjusts the concentration threshold according to the volatility and toxicity of different chemicals, which can ensure that high-risk areas are less selected and neither missed nor over-expanded.

[0093] Step 4.2: Connected domain labeling and region grouping.

[0094] Specifically, the eight-neighborhood connectivity algorithm is applied to the set S of excessive grid points on a two-dimensional grid to mark each connected component, and the grid points with the same connectivity identifier are grouped into a unified sub-region, and then all sub-region sets are output to ensure that each sub-region contains at least one grid point. The scattered excessive grid points are clustered into several blocks to facilitate the subsequent independent boundary extraction of each region.

[0095] Step 4.3: region boundary extraction.

[0096] Specifically, for each sub-region, Moore tracing or contour extraction algorithm is applied on its binary mask to generate a closed boundary along the periphery of the region. The points are arranged in order to obtain a list of boundary point sequences. This list serves as the original high-risk area contour, which can more accurately depict the spatial shape of each high-risk area and support visualization and path planning.

[0097] Step 4.4, boundary smoothing and simplification.

[0098] Specifically, the Douglas-Peucker simplification algorithm is applied to each boundary point in the boundary point sequence list, with a tolerance of Related to chemical type: Light gas , heavy gas , liquid vapor This tolerance is used to remove redundant vertices, maintain the contour shape, and output a simplified list of boundary point sequences, which reduces the amount of data and rendering overhead while retaining key geometric features for easy mobile terminal or AR overlay.

[0099] Step 4.5, generate a high-risk area boundary list.

[0100] Specifically, the maximum concentration value, area and minimum enclosing circle of each boundary point in the simplified boundary point sequence list are calculated, and the attributes such as coordinate sequence, chemical type, amplitude, maximum concentration and regional area are packaged to generate the final high-risk area boundary list.

[0101] Step S150, generating a visualization layer on the GIS platform based on the high-risk area boundary list, and triggering warning information.

[0102] In some embodiments, the weather-driven intelligent tracing method for hazardous chemical leakage provided by the present invention, step S150 specifically includes the following steps: Step S151, encapsulate each boundary sequence in the high-risk area boundary list into a vector element, and add an attribute field to each vector element to generate a GIS element set; wherein the attribute field includes the chemical type, the set threshold and the maximum concentration.

[0103] Step S152, constructing a vector layer in the GIS platform, and loading a GIS feature set in the vector layer, so as to visualize the boundary of the high-risk area in the vector layer and generate a visualization layer.

[0104] In some embodiments, the weather-driven intelligent tracing method for hazardous chemical leakage provided by the present invention, step S150 specifically further includes the following steps: Step S153: construct an indicator function for each sub-area in the high-risk area boundary list according to the concentration threshold and area threshold set by the safety specification.

[0105] Step S154, when the concentration threshold does not exceed the maximum concentration value in the GIS element set or the area threshold does not exceed the standard area in the GIS element set, the value of the indicator function is the first value, otherwise the value of the indicator function is the second value.

[0106] Step S155: Pack the sub-areas whose indicator function value is the first value in the high-risk area boundary list into an alarm element list.

[0107] In some embodiments, the weather-driven intelligent tracing method for hazardous chemical leakage provided by the present invention, step S150 specifically further includes the following steps: Step S156, identifying the high-risk area boundary based on the alarm element list and generating an alarm target area.

[0108] Step S157, the alarm target area is sent to the command terminal. After receiving the alarm target area, the command terminal highlights it on the visualization layer and pops up an alarm panel; the alarm panel is used to display the alarm information.

[0109] In a specific embodiment, the weather-driven intelligent tracing method for hazardous chemical leaks provided by the present invention, step 5, visualizes the boundary of the high-risk area in the GIS platform or command terminal, and automatically triggers an early warning, realizing a closed loop from detection to positioning to response, and completing the detection and positioning of the leakage source within seconds.

[0110] The following steps are involved: Step 5.1, data import and feature generation.

[0111] Specifically, each boundary point sequence in the high-risk area boundary list is encapsulated as a vector feature, and attribute fields (chemical type, threshold, maximum concentration, etc.) are attached to generate a GeoJSON or Shapefile format collection to obtain a GIS feature collection.

[0112] Step 5.2, layer rendering and style definition.

[0113] Specifically, a new vector layer is created in the GIS platform, a GIS feature set is loaded, semi-transparent red fill and thick edge drawing are applied to high-risk areas, flashing yellow marks are used for leakage sources, and the layer order is set to ensure that high-risk areas are at the top layer. The high-risk areas and source locations are intuitively highlighted through color and style, so that relevant personnel can quickly identify risk areas.

[0114] Step 5.3, early warning condition evaluation.

[0115] Specifically, the concentration threshold is set according to safety regulations. (such as 150ppm) and area threshold (such as 500㎡), calculate the indicator function for each area: ;

[0116] in, , They are the corresponding maximum concentration and area in the high-risk area element set. The high-risk areas are packaged into an alarm element list to automatically identify serious risk areas based on the alarm element list, generate accurate alarm targets, and avoid manual screening delays.

[0117] Step 5.4, alarm display and distribution.

[0118] Specifically, the command terminal receives the alarm elements obtained in step 5.3 and flashes the corresponding area on the map. At the same time, the alarm panel pops up, pushes the alarm message (including the area ID, threshold type, and coordinate range) to the mobile terminal APP, LED billboard, and vehicle terminal in JSON format, and generates an emergency work order. This realizes "alarm as soon as you see the picture" and multi-channel distribution, ensuring that the command center and on-site personnel can quickly learn and respond, and complete the intelligent tracing of high-risk areas.

[0119] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0120] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples (a non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the above. The computer-readable storage medium used herein is not to be interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0121] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0122] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, JAVA, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect through the Internet). In some embodiments, by using the state information of the computer-readable program instructions to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit may execute the computer-readable program instructions, thereby implementing various aspects of the present disclosure.

[0123] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0124] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0125] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0126] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A weather-driven intelligent tracing method for hazardous chemical leakage, characterized in that: The method comprises: Deploy micro-weather stations and gas sensor arrays at fixed intervals within the monitoring area to obtain meteorological and concentration data streams; Cleaning and structuring the meteorological and concentration data streams to generate a meteorological-concentration structured parameter table; Assimilating the structured parameter table into a lattice Boltzmann CFD model to recalculate the structured parameter table and output a gridded concentration distribution; Extracting the boundaries of the exceeding-standard areas from the gridded concentration distribution to generate a list of boundaries of high-risk areas; Generate a visualization layer on the GIS platform based on the high-risk area boundary list and trigger warning information; Among them, the boundary of the exceeding-standard area is the area where the meteorological and concentration data in the gridded concentration distribution exceed the set threshold.

2. The weather-driven intelligent tracing method for hazardous chemical leakage according to claim 1 is characterized in that: The micro-meteorological station includes a micro-wind speed and direction instrument for monitoring wind speed and direction data in the monitoring area; The micro-meteorological stations and gas sensor arrays are deployed at fixed intervals within the monitoring area to obtain meteorological and concentration data streams, including: Acquire the boundary coordinates of the monitoring area, and determine the coordinates of the monitoring starting reference point based on the boundary coordinates; Generating the installation coordinates of the micro weather station and the gas sensor according to the boundary coordinates, the fixed spacing, and the coordinates of the monitoring starting reference point, and integrating the installation coordinates into a grid coordinate set; Deploy a micro anemometer and a gas sensor at each installation coordinate in the grid coordinate set to obtain a list of nodes that have been installed; Each node in the node list is connected to a data aggregation server using LoRa, and the NTP protocol is configured to calibrate the micro anemometer and the gas sensor to synchronize the network of each node; The micro wind speed and direction instruments and gas sensors corresponding to each node after network synchronization collect wind speed and direction data and gas concentration data of each node according to the preset sampling period; The wind speed and direction data and the gas concentration data are aggregated, packaged and sent to the data aggregation server to obtain the meteorological and concentration data stream.

3. The weather-driven intelligent tracing method for hazardous chemical leakage according to claim 2 is characterized in that: The step of cleaning and structuring the meteorological and concentration data streams to generate a structured parameter table of meteorological and concentration data includes: Verify each data record in the meteorological and concentration data stream to mark abnormal data and obtain a verified preliminary data set; wherein the time interval error between adjacent data records in the preliminary data set does not exceed the set time interval, the wind speed data value does not exceed the range of the micro anemometer, and the wind direction data value and the gas concentration value are both within a preset range; Using weighted average interpolation to replace the abnormal data, and cleaning the preliminary data set to obtain a standardized and aligned unified data set; The meteorological and concentration data from different sources in the unified data set are integrated into a unified format to generate the structured parameter table.

4. The weather-driven intelligent tracing method for hazardous chemical leakage according to claim 3 is characterized in that: Assimilating the structured parameter table into a lattice Boltzmann CFD model to recalculate the structured parameter table and output a gridded concentration distribution includes: Inputting the structured parameter table into the lattice Boltzmann CFD model, extracting the coordinates of each grid center in the monitoring area, and determining the concentration data corresponding to each grid center from the structured parameter table; According to the weight of the D2Q9 model, the initial concentration distribution function field is constructed based on the coordinates and concentration data of each grid center; Based on the initial concentration distribution function field, calling the BGK operator relaxation algorithm to process each direction and each grid point to simulate the molecular collision and diffusion tendency, and obtain the post-collision distribution function field; Obtain the wind speed component of each discrete direction and grid point in the post-collision distribution function field and the unit displacement component in the corresponding direction in the D2Q9 model; Pushing the post-collision distribution function field to adjacent grid points along the corresponding direction in the D2Q9 model based on the wind speed component and the unit displacement component to obtain an updated distribution function field; The distribution of each grid point in the updated distribution function field is summed in all directions to obtain the gridded concentration distribution.

5. The weather-driven intelligent tracing method for hazardous chemical leakage according to claim 4 is characterized in that: The step of extracting the boundaries of the exceeding-standard areas from the gridded concentration distribution and generating a list of boundaries of high-risk areas includes: Obtaining a leaked product type identifier, and screening all grid points in the gridded concentration distribution according to a set reference threshold and type factor in the leaked product type identifier to obtain a set of grid points exceeding the standard; Processing the set of excess grid points on a two-dimensional grid by an eight-neighborhood connectivity algorithm to mark each connected component; Divide the grid points corresponding to the connected components with the same connectivity identifier into the same sub-region to obtain a list of connected sub-regions; Applying Moore's tracing and contour extraction algorithms on the binary mask of each sub-region in the list of connected sub-regions to generate closed boundaries along the periphery of each sub-region to obtain a list of boundary point sequences; Processing each closed boundary in the boundary point sequence list by using the Douglas-Peucker simplification algorithm to remove redundant vertices in the boundary point sequence list, and outputting a simplified boundary list; The maximum concentration value, area and minimum enclosing range of each sub-region in the simplified boundary list are calculated, and integrated to generate the high-risk area boundary list.

6. The weather-driven intelligent tracing method for hazardous chemical leakage according to claim 5 is characterized in that: The generating of a visualization layer on the GIS platform based on the high-risk area boundary list and triggering of early warning information includes: Encapsulating each boundary sequence in the high-risk area boundary list as a vector element, and adding an attribute field to each vector element to generate a GIS element set; wherein the attribute field includes the chemical type, the set threshold, and the maximum concentration; A vector layer is constructed in the GIS platform, and the GIS element set is loaded in the vector layer, so as to perform visualization operation on the boundary of the high-risk area in the vector layer to generate the visualization layer.

7. The weather-driven intelligent tracing method for hazardous chemical leakage according to claim 6 is characterized in that: The generating of a visualization layer on a GIS platform based on the high-risk area boundary list and triggering of early warning information also includes: Constructing an indicator function for each sub-area in the high-risk area boundary list according to a concentration threshold and an area threshold set by safety regulations; When the concentration threshold does not exceed the maximum concentration value in the GIS element set or the area threshold does not exceed the standard area in the GIS element set, the value of the indicator function is the first value, otherwise the value of the indicator function is the second value; The sub-areas in the high-risk area boundary list whose values ​​of the indicator function are the first value are packaged into an alarm element list.

8. The weather-driven intelligent tracing method for hazardous chemical leakage according to claim 7 is characterized in that: The generating of a visualization layer on a GIS platform based on the high-risk area boundary list and triggering of early warning information also includes: Identify the high-risk area boundary based on the alarm element list and generate an alarm target area; The alarm target area is sent to the command terminal. After receiving the alarm target area, the command terminal highlights it on the visualization layer and pops up an alarm panel; the alarm panel is used to display the alarm information.

9. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1-8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images