Intelligent Tracing Method for Hazardous Chemical Leakage Driven by Meteorology

Abstract

A meteorologically-driven intelligent tracing method for hazardous chemical leakage, belonging to the technical field of hazardous chemical leakage detection. The method includes: deploying micro-meteorological 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 structured parameter table of meteorology-concentration. Assimilating the structured parameter table into the lattice Boltzmann CFD model to recalculate the structured parameter table and output a grid-based concentration distribution. Extracting the boundaries of the over-standard areas from the grid-based concentration distribution to generate a list of high-risk area boundaries. Generating a visualization layer on the GIS platform based on the list of high-risk area boundaries and triggering warning information. Among them, the boundary of the over-standard area is the area where the meteorological and concentration data in the grid-based concentration distribution exceed the set threshold. This method can locate the leakage source in the first time after the leakage of hazardous chemicals, improving the efficiency and accuracy of leakage source location.

Description

Technical Field

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

[0002] In modern chemical industrial parks, high-value-added products such as PTA (purified terephthalic acid), superabsorbent resin (SAP), EVA, ethylene oxide and its derivatives, acrylonitrile, methyl methacrylate (MMA), etc. coexist with oil refining and petrochemical products (such as para-xylene 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. widely used in the production process are all 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 factory area and its surrounding areas, posing a safety hazard. In recent years, with the increasing demand for intelligent transformation of large chemical industrial parks, higher requirements have been put forward for real-time, accurate monitoring and tracing technologies for 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, and loading and unloading terminals has become the core problem in ensuring production safety and environmental risk control.

[0003] Currently, the leakage monitoring of hazardous chemicals in chemical industrial parks mainly relies on the following means: Fixed gas sensor network: Gas detectors with limited installation points are arranged near key pipelines, valves and storage tanks to collect concentrations in real time and link with the SCADA system for alarm; Video monitoring and manual inspection: Regular inspection trolleys are used for on-site inspection, and manual judgment of visible leakage characteristics (such as vapor clouds, droplets); UAV / mobile platform patrol: UAVs equipped with spectrometers or lidar are used for regular / event-triggered patrols of high-risk areas; Multi-system linkage: Sensor alarms, video images and GIS maps are initially superimposed and handed over to the emergency command center for manual decision-making on evacuation or valve closure.

[0004] Although the above technologies can provide leakage warnings to a certain extent, there are problems such as low update frequency, insufficient spatial resolution, visual disconnection and excessive manual intervention. The fixed sensors are sparsely distributed and cannot cover all pipelines. The diffusion model relying on meteorological station data is difficult to reflect sudden wind shear. Video and concentration data are often displayed separately, and the efficiency of emergency judgment is low. 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 an intelligent tracing method for hazardous chemical leakage driven by meteorology.

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

[0007] The first aspect of the present invention discloses an intelligent tracing method for hazardous chemical leakage driven by meteorology, and the method includes:

[0008] Deploy micro meteorological stations and gas sensor arrays at fixed intervals within the monitoring area to obtain meteorological and concentration data streams;

[0009] Clean and structure the meteorological and concentration data streams to generate a structured parameter table of meteorology-concentration;

[0010] Assimilate the structured parameter table into the lattice Boltzmann CFD model to recalculate the structured parameter table and output a grid concentration distribution;

[0011] Extract the boundary of the exceeding-standard area from the grid concentration distribution to generate a list of high-risk area boundaries;

[0012] Generate a visualization layer on the GIS platform based on the list of high-risk area boundaries and trigger a warning message;

[0013] Wherein, the boundary of the exceeding-standard area is the area where the meteorological and concentration data in the grid concentration distribution exceed the set threshold.

[0014] Further, the micro meteorological station includes a micro wind speed and direction meter for monitoring the wind speed and direction data in the monitoring area;

[0015] The step of deploying micro meteorological stations and gas sensor arrays at fixed intervals within the monitoring area to obtain meteorological and concentration data streams includes:

[0016] Obtain the boundary coordinates of the monitoring area and determine the monitoring starting reference point coordinates based on the boundary coordinates;

[0017] Generate the installation coordinates of the micro meteorological stations and gas sensors according to the boundary coordinates, fixed interval and monitoring starting reference point coordinates, and integrate the installation coordinates into a grid coordinate set;

[0018] Deploy a micro wind speed and direction meter and a gas sensor at each installation coordinate in the grid coordinate set to obtain a list of installed nodes;

[0019] Connect each node in the node list to the data aggregation server by LoRa, configure the NTP protocol, and calibrate the micro wind speed and direction meter and gas sensor to perform network synchronization for each node;

[0020] The micro wind speed and direction meter and gas sensor 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;

[0021] Summarize and package the wind speed and direction data and the gas concentration data and send them to the data aggregation server to obtain the meteorological and concentration data stream.

[0022] Further, cleaning and structuring the meteorological and concentration data stream to generate a structured parameter table of meteorology-concentration, including:

[0023] Verify each data record in the meteorological and concentration data stream to mark abnormal data and obtain a preliminary data set after verification; 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 wind speed and direction sensor, and the wind direction data value and the gas concentration value are both within the preset range;

[0024] Replace the abnormal data by weighted average interpolation and clean the preliminary data set to obtain a standardized and aligned unified data set;

[0025] Integrate the meteorological and concentration data from different sources in the unified data set into a unified format to generate the structured parameter table.

[0026] Further, assimilate the structured parameter table into the lattice Boltzmann CFD model to recalculate the structured parameter table and output the grid concentration distribution, including:

[0027] Input the structured parameter table into the lattice Boltzmann CFD model, extract the coordinates of the center of each grid in the monitoring area, and determine the concentration data corresponding to the center of each grid from the structured parameter table;

[0028] Construct an initial concentration distribution function field according to the coordinates and concentration data of the center of each grid according to the weights of the D2Q9 model;

[0029] Based on the initial concentration distribution function field, call 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;

[0030] Obtain the wind speed components of each discrete direction and grid point in the post-collision distribution function field and the unit displacement components in the corresponding direction of the D2Q9 model;

[0031] Push the post-collision distribution function field along the corresponding direction of the D2Q9 model to the adjacent grid points based on the wind speed components and the unit displacement components to obtain an updated distribution function field;

[0032] Sum the distributions in all directions for each grid point in the updated distribution function field to obtain the grid concentration distribution.

[0033] Further, extracting the boundary of the exceeded standard area from the grid concentration distribution to generate a list of high-risk area boundaries includes:

[0034] Obtain the leakage product type identifier, and screen all grid points in the grid concentration distribution according to the set reference threshold and type factor in the leakage product type identifier to obtain a set of exceeded standard grid points;

[0035] Process the set of exceeded standard grid points on a two-dimensional grid through an eight-neighborhood connectivity algorithm to mark each connected component;

[0036] 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;

[0037] Apply the Moore tracing and contour extraction algorithms on the binary mask of each sub-region in the list of connected sub-regions to generate a closed boundary along the periphery of each sub-region to obtain a list of boundary point sequences;

[0038] Process each closed boundary in the list of boundary point sequences through the Douglas-Peucker simplification algorithm to remove the redundant vertices in the list of boundary point sequences and output a list of simplified boundaries;

[0039] Calculate the maximum concentration value, area, and minimum enclosing range in each sub-region in the list of simplified boundaries, and integrate them to generate the list of high-risk area boundaries.

[0040] Further, generating a visualization layer on the GIS platform based on the list of high-risk area boundaries and triggering a warning message includes:

[0041] Encapsulate each boundary sequence in the list of high-risk area boundaries as a vector feature, and attach attribute fields to each vector feature to generate a GIS feature set; wherein, the attribute fields include chemical type, set threshold, and maximum concentration;

[0042] Construct a vector layer in the GIS platform and load the GIS feature set in the vector layer to perform a visualization operation on the high-risk area boundary in the vector layer to generate the visualization layer.

[0043] Further, generating a visualization layer on the GIS platform based on the list of high-risk area boundaries and triggering a warning message further includes:

[0044] Construct an indicator function for each sub-region in the list of high-risk area boundaries according to the concentration threshold and area threshold set by the safety specification;

[0045] When the concentration threshold does not exceed the maximum concentration in the GIS feature set or the area threshold does not exceed the specified area in the GIS feature set, the value of the indicator function is the first numerical value; otherwise, the value of the indicator function is the second numerical value.

[0046] Package the sub-regions in the high-risk area boundary list for which the value of the indicator function is the first numerical value into an alarm element list.

[0047] Further, the generating a visualization layer on the GIS platform based on the high-risk area boundary list and triggering a warning message further includes:

[0048] Identify the high-risk area boundary based on the alarm element list and generate an alarm target area.

[0049] Send the alarm target area to the command terminal. After receiving the alarm target area, the command terminal highlights it on the visualization layer and simultaneously pops up an alarm panel; the alarm panel is used to display the warning message.

[0050] A second aspect of the present invention discloses a terminal, including a processor and a storage medium; characterized in that:

[0051] The storage medium is used to store instructions;

[0052] The processor is used to operate according to the instructions to execute the steps of the method described in the first aspect.

[0053] A third aspect of the present invention discloses a computer-readable storage medium, on which a computer program is stored, characterized in that when the program is executed by a processor, it implements the steps of the method described in the first aspect.

[0054] The beneficial effects of the present invention are that, compared with the prior art, the present invention has the following advantages:

[0055] (1) By assimilating the structured parameter table (including wind speed, wind direction, and concentration data) collected at high frequency into the lattice Boltzmann CFD model, the present invention realizes the dynamic recalculation of the structured parameter table and outputs a high-precision grid concentration distribution. Different from the traditional scheme 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 the external force term, so that "convection-driven + diffusion relaxation" is deeply coupled during the simulation process, and the cloud mass can accurately shift and deform according to the real wind field at each time step. On this basis, more accurate monitoring of hazardous chemical leaks in each grid corresponding to the monitoring area can locate the leak source in the first time after the hazardous chemical leak, improving the efficiency and accuracy of leak source location, and further reflecting the safety concept of putting people first, avoiding unnecessary injury incidents that may be caused by manual exploration due to uncertain leakage situations.

[0056] (2)By generating a visualization layer of the high-risk area boundary list on the GIS platform, visualizing it, and triggering warning information, the present invention can timely display the accurate location of the leakage source to relevant personnel through the visualization layer, saving the exploration time for solving the leakage source and improving the timeliness of solving the leakage source. Description of the Drawings

[0057] Figure 1 It is a schematic flow chart of a meteorological-driven intelligent tracing method for hazardous chemical leakage provided by the present invention. Detailed Embodiments

[0058] The following further describes the present application with reference to the drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and cannot be used to limit the protection scope of the present application.

[0059] As Figure 1 shown, in one embodiment, a meteorological-driven intelligent tracing method for hazardous chemical leakage includes the following steps:

[0060] Step S110, deploy a micro meteorological station and a gas sensor array at a fixed interval within the monitoring area to obtain meteorological and concentration data streams.

[0061] It should be noted that the micro meteorological station includes a micro wind speed and direction sensor for monitoring wind speed and direction data within the monitoring area.

[0062] In some embodiments, for the meteorological-driven intelligent tracing method for hazardous chemical leakage provided by the present invention, step S110 specifically includes the following steps:

[0063] Step S111, obtain the boundary coordinates of the monitoring area and determine the monitoring starting reference point coordinates based on the boundary coordinates.

[0064] Step S112, generate the installation coordinates of the micro meteorological station and the gas sensor according to the boundary coordinates, the fixed interval, and the monitoring starting reference point coordinates, and integrate the installation coordinates into a grid coordinate set.

[0065] Step S113, deploy a micro wind speed and direction sensor and a gas sensor at each installation coordinate in the grid coordinate set to obtain a list of installed nodes.

[0066] Step S114, use LoRa to connect each node in the node list to the data aggregation server, configure the NTP protocol, and calibrate the micro wind speed and direction sensor and the gas sensor to synchronize the network for each node.

[0067] Step S115: The micro wind speed and direction sensors 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.

[0068] Step S116: The wind speed and direction data and gas concentration data are summarized and packaged and sent to the data aggregation server to obtain the meteorological and concentration data stream.

[0069] In a specific embodiment, the intelligent tracing method for hazardous chemical leakage driven by meteorology provided by the present invention includes steps 1 to 5:

[0070] Step 1: Deployment and data collection of the micro meteorological station and gas sensor array.

[0071] Specifically, deploy the micro meteorological station and gas sensor array with a spacing of 200 m, and collect the wind speed, wind direction and concentration data every 10 s. By obtaining high-frequency environment and concentration information, a multi-point data basis is provided for positioning.

[0072] It includes the following steps:

[0073] Step 1.1: Determination of the regional boundary and reference point.

[0074] Specifically, the coordinates of the southwest corner of the monitoring area are (x0, y0), which are obtained by reading the boundary value from the GIS base map, used to clarify the grid generation benchmark, and ensure the consistency of subsequent position calculations.

[0075] Step 1.2: Calculation of grid point coordinates.

[0076] Specifically, according to the following expression:

[0077] ;

[0078] where is the grid spacing, and the grid point satisfies , where i and j are non-negative integers, , are the maximum values of the monitoring area boundary coordinates. The maximum index is determined by rounding down the actual range to generate the complete sensor installation coordinates, ensuring no blind area in the area coverage, and obtaining the grid coordinate set.

[0079] Step 1.3: Physical installation of sensor nodes.

[0080] Specifically, install the micro wind speed and direction sensors and gas sensors at each coordinate in the grid coordinate set, with an installation height of 2 m ± 0.1 m, and at the same time equipped with a rain cover and a fixed bracket. By deploying multiple-point sensing devices on the ground, hardware guarantee is provided for data collection.

[0081] Step 1.4, Network construction and clock synchronization.

[0082] Specifically, LoRa / Wi-Fi / Ethernet nodes are used to access the data aggregation server, the NTP protocol is configured, the clock deviation is < 50 ms, and zero point and range calibration are performed on each sensor to eliminate timing and range drift and ensure reliable data synchronization of each node.

[0083] Step 1.5, Timed acquisition and data reporting.

[0084] Specifically, set the sampling period T = 10 s, and at each moment, trigger to read the wind speed v and wind direction of each node, the gas concentration c, summarize and package them and send them to the server, and construct the basic data stream required for subsequent assimilation and simulation by continuously producing high-frequency, multi-point environment and concentration data.

[0085] Step S120, Clean and structure the meteorological and concentration data streams to generate a structured parameter table of meteorology-concentration.

[0086] In some embodiments, for the intelligent tracing method of hazardous chemical leakage driven by meteorology provided by the present invention, step S120 specifically includes the following steps:

[0087] Step S121, Check each data record in the meteorological and concentration data streams to mark abnormal data and obtain a preliminary data set after verification; 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.

[0088] Step S122, Replace the abnormal data by weighted average interpolation and clean the preliminary data set to obtain a standardized and aligned unified data set.

[0089] Step S123, Integrate the meteorological and concentration data from different sources in the unified data set into a unified format to generate a structured parameter table.

[0090] In a specific embodiment, for the intelligent tracing method of hazardous chemical leakage driven by meteorology provided by the present invention, step 2, Clean and structure the collected data to generate a meteorology-concentration parameter table in a unified format to eliminate abnormal readings and unify the format for subsequent model assimilation.

[0091] It includes the following steps:

[0092] Step 2.1, Data reception and preliminary verification.

[0093] 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.

[0094] Step 2.2, outlier identification and interpolation.

[0095] 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.

[0096] Step 2.3, unit normalization and time alignment.

[0097] 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.

[0098] Step 2.4, structured parameter table generation.

[0099] Specific, structured parameter table As shown below:

[0100] ;

[0101] in, is a vector of length 4, They are wind speed, wind direction and concentration, which are output by the sensor; Seconds level timestamp.

[0102] By integrating multi-source data into a unified format, it is convenient for subsequent CFD models to be directly called.

[0103] 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;

[0104] 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:

[0105] Step S131: Input the structured parameter table into the lattice Boltzmann CFD model, extract the coordinates of the center of each grid within the monitoring area, and determine the corresponding concentration data for the center of each grid from the structured parameter table.

[0106] Step S132: Construct the initial concentration distribution function field according to the weights of the D2Q9 model, based on the coordinates and concentration data of the center of each grid.

[0107] Step S133: Based on the initial concentration distribution function field, call 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.

[0108] Step S134: Obtain the wind speed components at each discrete direction and grid point in the post-collision distribution function field and the unit displacement components in the corresponding directions of the D2Q9 model.

[0109] Step S135: Push the post-collision distribution function field along the corresponding directions in the D2Q9 model to adjacent grid points based on the wind speed components and unit displacement components to obtain the updated distribution function field.

[0110] Step S136: Sum the distributions in all directions for each grid point in the updated distribution function field to obtain the grid-based concentration distribution.

[0111] In a specific embodiment, for the intelligent tracing method of hazardous chemical leakage driven by meteorology provided by the present invention, in step 3, assimilate the structured parameter table into the lattice Boltzmann CFD model, recalculate and output the grid-based concentration distribution.

[0112] Specifically, assimilate the structured parameter table into the lattice Boltzmann CFD model every 10 s, recalculate and output the grid-based concentration distribution, and simulate the diffusion pattern of the cloud mass in real time, without relying on low-frequency weather stations.

[0113] It includes the following steps:

[0114] Step 3.1: Initialize the distribution function.

[0115] Specifically, take the center of each grid in the monitoring area , obtain the corresponding concentration at this point from the structured parameter vector P , and calculate according to the weights of the D2Q9 model (constant, ):

[0116] ;

[0117] The obtained array That is, it is the initial value for collision and flow calculations. Through this calculation, the macroscopic concentration information is mapped to the microscopic distribution function field, providing a basis for subsequent collision and flow operations.

[0118] Step 3.2, collision (relaxation) operation.

[0119] Specifically, calculate the relaxation time , for each direction i and each grid point , apply the BKG operator for relaxation:

[0120] ;

[0121] ;

[0122] ;

[0123] ;

[0124] Among them, is the distribution function field after collision, is the equilibrium distribution, calculated based on the local concentration and the wind speed field.

[0125] It can be understood that since Step 3 is continuously and real-time calculated, therefore, the functions and are essentially the same in nature. The only difference is that real-time associated with needs to be collected. The selection of the relaxation time depends on the characteristics of the hazardous chemicals, usually selected between 0.6 and 1.0. The heavier the gas, the larger the value.

[0126] ;

[0127] It can be understood that the collision operation makes the concentration distribution gradually tend to local equilibrium by simulating molecular collisions and diffusion tendencies. That is to say, it only changes the shape of the distribution function (amplitude adjustment), but does not change the position of the particles in space.

[0128] Step 3.3, flow (migration) operation.

[0129] Specifically, for each discrete direction index i = 0,..., 8 and each grid point , read the velocity component in this direction , among which, is the unit displacement component (constant) in the i-th direction in the D2Q9 model, and push the distribution function field after collision along this direction to the adjacent grid point:

[0130] ;

[0131] Among them, is the value of the output function field at the new time and new position. is the time change between the new time and the original time. Repeat the above process for all grid points and directions. At the grid boundary, if the target position exceeds the domain, "rebound" or "mirror" boundary processing is adopted to ensure mass conservation.

[0132] It can be understood that the flow (migration) operation realizes the macroscopic convection and diffusion process of particles by migrating the post - collision distribution along each discrete velocity direction in space, and is the key driving force for the generation of the concentration cloud. That is to say, it redistributes the particle distribution in space, realizes the diffusion and migration of the cloud in the region, and provides a new initial field for the next round of collision operation.

[0133] Step 3.4, Macroscopic concentration extraction and output.

[0134] Specifically, for each grid point Summing up all the direction distributions, the concentration field of the grid - based concentration distribution vector can be obtained, which can be directly used for the extraction of high - risk areas.

[0135] Step S140, Extract the boundary of the exceeded - standard area from the grid - based concentration distribution to generate a list of high - risk area boundaries.

[0136] Among them, the boundary of the exceeded - standard area is the area where the meteorological and concentration data in the grid - based concentration distribution exceed the set threshold.

[0137] In some embodiments, for the meteorological - driven intelligent tracer method for hazardous chemical leakage provided by the present invention, step S140 specifically includes the following steps:

[0138] Step S141, Obtain the leakage product type identifier, and screen all grid points in the grid - based concentration distribution according to the set reference threshold and type factor in the leakage product type identifier to obtain a set of exceeded - standard grid points.

[0139] Step S142, Process the set of exceeded - standard grid points on the two - dimensional grid through an eight - neighborhood connectivity algorithm to mark each connected component.

[0140] Step S143, 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.

[0141] Step S144, Apply the Moore tracing and contour extraction algorithm on the binary mask of each sub - region in the list of connected sub - regions to generate a closed boundary along the periphery of each sub - region to obtain a list of boundary point sequences.

[0142] Step S145: Process each closed boundary in the list of boundary point sequences through the Douglas-Peucker simplification algorithm to remove redundant vertices in the list of boundary point sequences, and output the simplified boundary list.

[0143] Step S146: Calculate the maximum concentration value, area, and minimum bounding range in each sub-region in the simplified boundary list, and integrate them to generate the high-risk area boundary list.

[0144] In a specific embodiment, for the intelligent tracing method of hazardous chemical leakage driven by meteorology provided by the present invention, in step 4, extract the boundary of the exceeded standard area from the concentration distribution, generate the high-risk area boundary list, clarify the range of the high-concentration area, and provide a spatial basis for personnel deployment.

[0145] It includes the following steps:

[0146] Step 4.1: Set the chemical type threshold and screen the exceeded standard grids.

[0147] Specifically, set the benchmark threshold according to the type of the leaked product , and multiply it by the type factor :

[0148] ;

[0149] Among them, if it is a light gas (such as ethylene), ; if it is a heavy gas (such as ethylene oxide and its derivatives), ; if it is a liquid-phase vapor (such as acrylonitrile), . For all grid points , if , then add it to the set S of exceeded standard grid points, and output:

[0150] ;

[0151] Among them, is the concentration distribution of the grid point .

[0152] The present invention adjusts the concentration threshold according to the volatility and toxicity of different chemicals, which can ensure that fewer high-risk areas are selected, without missing reports or over-expansion.

[0153] Step 4.2: Connected domain labeling and region grouping.

[0154] Specifically, apply the eight-neighborhood connectivity algorithm to the set S of exceeded standard grid points on the two-dimensional grid to label each connected component, group the grid points with the same connectivity identifier into a unified sub-region, and then output all sub-region sets, ensuring that each sub-region contains at least one grid point, and clustering the scattered exceeded standard grid points into several blocks, which is convenient for independently extracting the boundary for each region subsequently.

[0155] Step 4.3, Region boundary extraction.

[0156] Specifically, for each sub-region, apply the Moore tracing or contour extraction algorithm on its binary mask to generate a closed boundary along the periphery of the region and arrange it in order to obtain a list of boundary point sequences, which serves as the contour of the original high-risk area and can accurately depict the spatial shape of each high-risk area, supporting visualization and path planning.

[0157] Step 4.4, Boundary smoothing and simplification.

[0158] Specifically, apply the Douglas-Peucker simplification algorithm to each boundary point in the list of boundary point sequences. The tolerance is related to the chemical type: light gas , heavy gas , liquid-phase vapor . This tolerance is used to remove redundant vertices, maintain the contour shape, output the simplified list of boundary point sequences, reduce the data volume and rendering overhead, and at the same time retain the key geometric features, facilitating mobile terminals or AR superposition.

[0159] Step 4.5, Generation of the high-risk area boundary list.

[0160] Specifically, calculate the maximum concentration value, area, and minimum enclosing circle for each boundary point in the simplified list of boundary point sequences, and package attributes such as the coordinate sequence, chemical type, amplitude, maximum concentration, and area of the region to generate the final high-risk area boundary list.

[0161] Step S150, Generate a visualization layer on the GIS platform based on the high-risk area boundary list and trigger warning information.

[0162] In some embodiments, for the meteorologically-driven intelligent tracing method for hazardous chemical leaks provided by the present invention, step S150 specifically includes the following steps:

[0163] Step S151, Package each boundary sequence in the high-risk area boundary list as a vector feature, and attach attribute fields to each vector feature to generate a GIS feature set; among them, the attribute fields include chemical type, set threshold, and maximum concentration.

[0164] Step S152, Construct a vector layer in the GIS platform and load the GIS feature set in the vector layer to perform visualization operations on the high-risk area boundary in the vector layer to generate a visualization layer.

[0165] In some embodiments, for the meteorologically-driven intelligent tracing method for hazardous chemical leaks provided by the present invention, step S150 specifically further includes the following steps:

[0166] Step S153, construct an indicator function for each sub-region in the high-risk area boundary list according to the concentration threshold and area threshold set by the safety specification.

[0167] Step S154, when the concentration threshold does not exceed the maximum concentration in the GIS feature set or the area threshold does not exceed the specified area in the GIS feature set, the value of the indicator function is the first numerical value; otherwise, the value of the indicator function is the second numerical value.

[0168] Step S155, pack the sub-regions in the high-risk area boundary list with the value of the indicator function being the first numerical value into an alarm element list.

[0169] In some embodiments, for the meteorological-driven intelligent tracing method for hazardous chemical leakage provided by the present invention, step S150 specifically further includes the following steps:

[0170] Step S156, identify the high-risk area boundary based on the alarm element list and generate an alarm target area.

[0171] Step S157, send the alarm target area to the command terminal. After receiving the alarm target area, the command terminal highlights it on the visualization layer and simultaneously pops up an alarm panel; the alarm panel is used to display warning information.

[0172] In a specific embodiment, for the meteorological-driven intelligent tracing method for hazardous chemical leakage provided by the present invention, in step 5, visualize the high-risk area boundary in the GIS platform or the command terminal and automatically trigger an alarm, realizing a closed-loop from detection to positioning and then to response, and completing the detection and positioning of the leakage source within seconds.

[0173] It includes the following steps:

[0174] Step 5.1, data import and element generation.

[0175] Specifically, encapsulate each boundary point sequence in the high-risk area boundary list into a vector element, append attribute fields (chemical type, threshold, maximum concentration, etc.), generate a GeoJSON or Shapefile format set, and obtain a GIS feature set.

[0176] Step 5.2, layer rendering and style definition.

[0177] Specifically, create a new vector layer in the GIS platform, load the GIS feature set, apply a semi-transparent red fill and thick border description to the high-risk area, use a flashing yellow marker for the leakage source point, set the layer order to ensure that the high-risk area is on the top layer, and visually highlight the high-risk area and the source point position through colors and styles, enabling relevant personnel to quickly identify the risk area.

[0178] Step 5.3, early warning condition assessment.

[0179] Specifically, set the concentration threshold (such as 150 ppm) and the area threshold (such as 500 ㎡), and calculate the indicator function for each area:

[0180] ;

[0181] Among them, and are the corresponding maximum concentration and area in the set of high-risk area elements respectively. Package all high-risk areas into an alarm element list, automatically identify serious risk areas based on this alarm element list, generate accurate alarm targets, and avoid delays in manual screening.

[0182] Step 5.4, Alarm display and distribution.

[0183] Specifically, the command terminal receives the alarm elements obtained in step 5.3 and blinks the corresponding area on the map. At the same time, an alarm panel pops up, and pushes the alarm message (including area ID, threshold type, and coordinate range) to the mobile terminal APP, LED display board, and in-vehicle terminal in JSON format, and generates an emergency work order. It realizes "seeing the picture means alarm" and multi-channel distribution, ensures that the command center and on-site personnel can quickly learn and respond, and completes the intelligent tracing of high-risk areas.

[0184] The present disclosure can be a system, a method, and / or a computer program product. The computer program product may include a computer-readable storage medium having thereon computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0185] A computer-readable storage medium can be a tangible device that can hold and store instructions for use 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 foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium 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 disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanically encoded device such as a punched card or raised structures in grooves having instructions stored thereon, and any suitable combination of the foregoing. The computer-readable storage medium as used herein is not construed to be an instantaneous signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0186] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to various computing / processing devices, 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 may include a copper transmission cable, an optical fiber transmission, a wireless transmission, a router, a firewall, a switch, a gateway computer, and / or an edge server. A 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 a computer-readable storage medium in each computing / processing device.

[0187] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine - related 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 the "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, executed as a stand - alone software package, partially on the user's computer and 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, alternatively, may be connected to an external computer (e.g., through the Internet using an Internet service provider). In some embodiments, by using the state information of the computer - readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field - programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer - readable program instructions to implement various aspects of the present disclosure.

[0188] Aspects of the present disclosure are described herein with reference to the flowchart and / or block diagram of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowchart and / or block diagram, and the combinations of blocks in the flowchart and / or block diagram, can be implemented by computer - readable program instructions.

[0189] 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 apparatus to produce a machine such that the instructions, when executed by the processor of the computer or other programmable data - processing apparatus, result in an apparatus that implements the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer - readable program instructions can also be stored in a computer - readable storage medium, which causes a computer, a programmable data - processing apparatus, and / or other devices to operate in a particular manner. Thus, the computer - readable medium storing the instructions includes a manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0190] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, causing a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process such that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in one or more boxes of the flowchart and / or block diagram.

[0191] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two consecutive blocks may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block of the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or acts, or by a combination of dedicated hardware and computer instructions.

[0192] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific embodiments of the present invention, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered by the protection scope of the claims of the present invention.

Claims

1. An intelligent tracing method for hazardous chemical leakage driven by meteorology, characterized in that The method includes: Deploying micro-meteorological 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 structured parameter table of meteorology-concentration; Assimilating the structured parameter table into a lattice Boltzmann CFD model to recalculate the structured parameter table and output a grid-based concentration distribution; Extracting the boundaries of the over-standard areas from the grid-based concentration distribution to generate a list of high-risk area boundaries; Generating a visualization layer on a GIS platform based on the list of high-risk area boundaries and triggering a warning message; Wherein, the boundaries of the over-standard areas are the areas in the grid-based concentration distribution where the meteorological and concentration data exceed the set threshold; The extracting the boundaries of the over-standard areas from the grid-based concentration distribution to generate a list of high-risk area boundaries includes: Obtaining the leakage product type identifier, and screening all grid points in the grid-based concentration distribution according to the set reference threshold and type factor in the leakage product type identifier to obtain a set of over-standard grid points; Processing the set of over-standard grid points on a two-dimensional grid through an eight-neighborhood connectivity algorithm to mark each connected component; Dividing the grid points corresponding to the connected components with the same connection identifier into the same sub-region to obtain a list of connected sub-regions; Applying the Moore tracing and contour extraction algorithms on the binary mask of each sub-region in the list of connected sub-regions to generate a closed boundary along the periphery of each sub-region to obtain a list of boundary point sequences; Processing each closed boundary in the list of boundary point sequences through the Douglas-Peucker simplification algorithm to remove the redundant vertices in the list of boundary point sequences and output a list of simplified boundaries; Calculating the maximum concentration value, area, and minimum bounding range in each sub-region in the list of simplified boundaries, and integrating them to generate the list of high-risk area boundaries; Each sub-region contains at least one grid point.

2. The meteorological-driven intelligent tracing method for hazardous chemical leakage according to claim 1, wherein The micro-meteorological station includes a micro wind speed and direction sensor for monitoring the wind speed and direction data within the monitoring area; The deploying micro-meteorological stations and gas sensor arrays at fixed intervals within the monitoring area to obtain meteorological and concentration data streams includes: Obtaining the boundary coordinates of the monitoring area and determining the monitoring starting reference point coordinates based on the boundary coordinates; Generating the installation coordinates of the micro-meteorological stations and gas sensors according to the boundary coordinates, fixed interval, and monitoring starting reference point coordinates, and integrating the installation coordinates into a set of grid coordinates; Deploying a micro wind speed and direction sensor and a gas sensor at each installation coordinate in the set of grid coordinates to obtain a list of installed nodes; Connecting each node in the list of nodes to a data aggregation server using LoRa and configuring the NTP protocol to calibrate the micro wind speed and direction sensor and the gas sensor to perform network synchronization for each node; Collecting the wind speed and direction data and gas concentration data of each node through the micro wind speed and direction sensor and gas sensor corresponding to each node after network synchronization according to a preset sampling period; Summarize and package the wind speed and direction data and gas concentration data and send them to the data aggregation server to obtain the meteorological and concentration data stream.

3. The intelligent tracing method for hazardous chemical leakage driven by meteorology according to claim 2, characterized in that Clean and structure the meteorological and concentration data stream to generate a structured parameter table of meteorology-concentration, including: Verify each data record in the meteorological and concentration data stream to mark abnormal data and obtain a preliminary data set after verification; 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 wind speed and direction sensor, and the wind direction data value and gas concentration value are both within the preset range; Replace the abnormal data using weighted average interpolation and clean the preliminary data set to obtain a standardized and aligned unified data set; Integrate the meteorological and concentration data from different sources in the unified data set into a unified format to generate the structured parameter table.

4. The intelligent tracing method for hazardous chemical leakage driven by meteorology according to claim 3, wherein Assimilate the structured parameter table into the lattice Boltzmann CFD model to recalculate the structured parameter table and output the grid concentration distribution, including: Input the structured parameter table into the lattice Boltzmann CFD model, extract the coordinates of the center of each grid in the monitoring area, and determine the concentration data corresponding to the center of each grid from the structured parameter table; Construct an initial concentration distribution function field according to the weights of the D2Q9 model based on the coordinates and concentration data of the center of each grid; Based on the initial concentration distribution function field, call the BGK operator relaxation algorithm to process each direction and each grid point to simulate molecular collision and diffusion tendency and obtain the post-collision distribution function field; Obtain the wind speed components of each discrete direction and grid point in the post-collision distribution function field and the unit displacement components in the corresponding direction in the D2Q9 model; Push the post-collision distribution function field along the corresponding direction in the D2Q9 model to adjacent grid points based on the wind speed components and unit displacement components to obtain an updated distribution function field; Sum the distributions in all directions for each grid point in the updated distribution function field to obtain the grid concentration distribution.

5. The meteorological-driven intelligent tracing method for hazardous chemical leakage according to claim 4, characterized in that Generate a visualization layer on the GIS platform based on the list of high-risk area boundaries and trigger a warning message, including: Package each boundary sequence in the list of high-risk area boundaries as a vector feature and attach attribute fields to each vector feature to generate a GIS feature set; wherein, the attribute fields include chemical type, set threshold, and maximum concentration; Construct a vector layer on the GIS platform and load the GIS feature set in the vector layer to perform visualization operations on the high-risk area boundaries in the vector layer to generate the visualization layer.

6. The meteorological-driven intelligent tracing method for hazardous chemical leakage according to claim 5, wherein Generate a visualization layer on the GIS platform based on the list of high-risk area boundaries and trigger a warning message, further including: Construct an indicator function for each sub-region in the list of high-risk area boundaries according to the concentration threshold and area threshold set by the safety specifications; When the concentration threshold does not exceed the maximum concentration in the GIS element set or the area threshold does not exceed the specified area in the GIS element set, the value of the indicator function is the first numerical value; otherwise, the value of the indicator function is the second numerical value. Pack the sub-regions in the high-risk area boundary list whose indicator function values are the first numerical value into an alarm element list.

7. The meteorological-driven intelligent tracing method for hazardous chemical leakage according to claim 6, wherein The generating a visualization layer based on the high-risk area boundary list in the GIS platform and triggering a warning message further includes: Identifying the high-risk area boundary based on the alarm element list and generating an alarm target area. Sending the alarm target area to a command terminal, and after receiving the alarm target area, the command terminal highlights it in the visualization layer and simultaneously pops up an alarm panel; the alarm panel is used to display the warning message.

8. A terminal, comprising a processor and a storage medium; characterized in that: 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 according to any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method according to any one of claims 1-7.

Images