Safety risk management and control system for chemical industry park

Abstract

The invention discloses a safety risk management and control system for a chemical industry park, particularly relates to the technical field of risk diffusion prediction, and is used for solving the problem that in the prior art, an emergency instruction and a risk propagation path are dynamically mismatched, and cross-regional chain reaction cannot be cooperatively blocked. Environmental parameters and equipment state data are obtained through a data acquisition module, and a fluid correction module extracts a continuous coherent bar code of turbulent vortex to generate a path correction coefficient; the coupling modeling module is combined with a multi-physics field coupling equation to generate dynamic space-time propagation parameters, and the path prediction module predicts a diffusion direction and an influence area according to vector superposition of the parameters and a three-dimensional topological map; the instruction optimization module adjusts the priority and the trigger range of a control instruction, and the execution control module organizes emergency equipment to block a diffusion path according to a preset logic; through dynamic modeling and path matching optimization, time-space cooperation of emergency response and control execution is realized, and the accident diffusion risk of the chemical industry park is significantly reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of risk diffusion prediction, and more specifically, to a safety risk control system for chemical industrial parks. Background Art

[0002] In the safety risk control of chemical industrial parks, the existing technology usually realizes risk monitoring and emergency response by deploying sensor networks, alarm systems, and automation control devices. Among them, the alarm system is used to identify abnormal states (such as gas leakage, temperature overrun), and the control system executes operations according to preset rules (such as closing valves, starting sprinklers). However, the above systems often operate independently, and the generation of alarm information and control instructions mainly depends on local data (such as the status of a single device or fixed area thresholds), without fully considering the dynamic propagation characteristics of risk events in the time and space dimensions. For example, the spread path of a fire or leakage is affected by real-time environmental parameters (such as wind direction, equipment layout), and the existing solutions lack the collaborative analysis of spatial topological relationships and temporal evolution.

[0003] Due to the independent processing of alarm, control, and spatial data by the existing technology, the ability to respond collaboratively to the cross-regional spatio-temporal propagation of risk events is insufficient, specifically manifested as: the emergency instructions (such as isolation, fire extinguishing) do not match the dynamic changes in the risk diffusion path, and the chain reaction cannot be effectively blocked, thus increasing the severity of the accident consequences. This problem is particularly prominent in scenarios involving large-scale parks, complex equipment layouts, or variable meteorological conditions. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the existing technology, embodiments of the present invention provide a safety risk control system for chemical industrial parks to solve the problems raised in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solutions: A safety risk control system for chemical industrial parks, including the following modules: A data acquisition module for obtaining real-time environmental parameters and equipment status data of multiple monitoring points in the chemical industrial park; A fluid correction module for extracting the persistent homology barcode of turbulent vortices through computational fluid dynamics according to the real-time environmental parameters and equipment status data, and generating a path correction coefficient by combining the resonance frequency matching degree between the equipment layout and the microclimate vortices; A coupled modeling module for generating dynamic spatio-temporal propagation parameters through a multi-physics field coupling equation based on the path correction coefficient and the risk diffusion rate in the time dimension; A path prediction module for predicting the diffusion direction and affected area of a risk event according to the vector superposition result of the dynamic spatio-temporal propagation parameters and the three-dimensional topological map of the chemical industrial park; An instruction optimization module, which is used to adjust the priority and trigger range of the automation control instruction based on the diffusion direction and the influence area, and generate a dynamic control instruction set that matches the risk diffusion path; An execution control module, which is used to execute the dynamic control instruction set and control the emergency equipment in the target area to block the risk diffusion path according to the preset logic.

[0006] In a preferred embodiment, real-time environmental parameters and equipment status data of multiple monitoring points in the chemical industrial park are obtained, including: Collect temperature data, gas concentration data, and wind speed data in the real-time environmental parameters through temperature sensors, gas concentration sensors, and wind speed sensors; Collect pipeline pressure data and valve opening data in the equipment status data through pressure sensors and valve opening sensors; Calculate the current risk level in real time according to the temperature data, gas concentration data, and wind speed data, and dynamically adjust the data collection frequency based on the current risk level.

[0007] In a preferred embodiment, according to the real-time environmental parameters and equipment status data, the persistent homology barcode of the turbulent vortex is extracted by computational fluid dynamics, and the path correction coefficient is generated by combining the resonance frequency matching degree between the equipment layout and the microclimate vortex, including: Perform dynamic filtering on the wind speed and wind direction data in the real-time environmental parameters to separate the persistent wind speed component and the instantaneous pulsation component representing the macroscopic flow field trend; Based on the persistent wind speed component, construct a three-dimensional transient flow field model by computational fluid dynamics and extract the persistent homology barcode of the turbulent vortex in the flow field; Synchronously perform spatial Fourier transform on the equipment layout coordinates in the equipment status data to identify the energy concentration area of the equipment layout at the dominant frequency of the microclimate vortex; Calculate the resonance coupling strength between the vortex energy diffusion path and the equipment layout according to the topological evolution characteristics of the persistent homology barcode and the spectral distribution of the energy concentration area, and generate the path correction coefficient.

[0008] In a preferred embodiment, the persistent homology barcode is generated by quantifying the topological evolution characteristics of the topological connectivity of the vortex boundary within a preset time window.

[0009] In a preferred embodiment, based on the path correction coefficient and the risk diffusion rate in the time dimension, dynamic spatio-temporal propagation parameters are generated through a multi-physical field coupling equation, including: Normalize the path correction coefficient to generate a correction weight factor; Perform time series weighting on the risk diffusion rate in the time dimension to generate a time decay coefficient, and the weighting is dynamically adjusted based on the decay trend of the historical accident diffusion rate. Establish a multi - physical - field coupling equation. The multi - physical - field coupling equation takes the modified weight factor as the spatial correction term and the time decay coefficient as the time correction term, and combines the fluid mechanics diffusion equation and the equipment layout resistance equation for simultaneous solution; By iteratively solving the multi - physical - field coupling equation, output dynamic spatio - temporal propagation parameters, which include the risk diffusion direction vector, the propagation rate gradient, and the spatial energy density distribution.

[0010] In a preferred embodiment, according to the vector superposition result of the dynamic spatio - temporal propagation parameters and the 3D topological map of the chemical industrial park, predict the diffusion direction and the affected area of the risk event, including: Superpose the risk diffusion direction vector in the dynamic spatio - temporal propagation parameters with the geographical coordinates in the 3D topological map of the chemical industrial park to generate a superposed risk propagation path vector field; Based on the superposed risk propagation path vector field, perform dynamic grid division on the chemical industrial park; Calculate the spatial change rate of the risk diffusion rate within the grid according to the propagation rate gradient, and combine the fluid viscosity and the equipment layout resistance equation to generate the risk diffusion priority coefficient for each grid; Based on the risk diffusion priority coefficient and the preset diffusion threshold, mark the continuous grid area where the risk diffusion priority coefficient exceeds the preset diffusion threshold as the affected area, and output the spatial coordinate set of the diffusion direction and the affected area.

[0011] In a preferred embodiment, the grid resolution in the dynamic grid division of the chemical industrial park is adjusted according to the spatial energy density distribution, and the grid side length in the high - energy - density area is smaller than that in the low - energy - density area.

[0012] In a preferred embodiment, based on the diffusion direction and the affected area, adjust the priority and the trigger range of the automatic control instructions to generate a dynamic control instruction set that matches the risk diffusion path, including: According to the spatial coordinate set of the affected area and the risk diffusion direction vector, establish a control instruction priority mapping table, and the level of the control instructions in the priority mapping table is dynamically adjusted according to the spatial energy density distribution and the risk diffusion priority coefficient; Based on the dynamic control instruction set and the topological relationship of the equipment layout in the chemical industrial park, adjust the trigger range of the automatic control instructions, and the trigger range covers the equipment coordinates in the affected area and its adjacent grids where the risk diffusion priority coefficient exceeds the preset diffusion threshold; According to the real - time diffusion rate and the equipment operation status data, mark the emergency control instructions that need to be executed immediately in the priority mapping table to generate a dynamic control instruction set; Verify the logical consistency of the dynamic control instruction set through the spatial matching degree between the risk diffusion path vector field and the device topology relationship, and eliminate the instructions conflicting with the diffusion path.

[0013] In a preferred embodiment, execute the dynamic control instruction set to control the emergency devices in the target area to block the risk diffusion path according to the preset logic, including: Sort the control instructions in the dynamic control instruction set according to the priority level from high to low, and send control instructions to the emergency devices in the target area step by step. The control instructions include device operation types and execution parameters; Based on the spatial matching degree between the chemical industrial park device topology relationship and the risk diffusion path vector field, execute the control instructions consistent with the diffusion path direction in the same priority level in parallel; Collect the execution status data of the emergency devices, and adjust the priority level of the unexecuted instructions according to the deviation value between the execution status data and the preset response logic; Verify the effectiveness of the executed control instructions through the feedback data of the real-time risk diffusion rate and the device execution status. If the diffusion rate does not drop to the safety threshold, trigger redundant control instructions.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. Through the continuous homology analysis integrating environmental parameters, device layout, and fluid mechanics, extract the topological evolution characteristics of fluid vortices and generate path correction coefficients, solving the defect that traditional static scene modeling ignores the dynamic coupling of microclimate, enabling the risk diffusion path prediction to accurately reflect the resonance effect between device layout and gas diffusion, and improving the physical authenticity and reliability of the prediction results; at the same time, introduce multi-physical field coupling equations in the process of generating dynamic spatio-temporal propagation parameters, use the path correction coefficient as a spatial non-uniformity correction term, and dynamically adjust the time weight in combination with the historical attenuation trend to form a composite transmission model covering spatio-temporal dimensions, avoiding the problem of deviating from the actual propagation path caused by traditional single-dimensional prediction.

[0015] 2. Through the real-time vector superposition of the risk diffusion path and the device topology map and the generation of dynamic control instructions, achieve the multi-factor matching of instructions and diffusion directions; based on the two-way feedback of the priority mapping table and the device execution status, adjust the spatial coverage range and execution order of instruction triggering to ensure the synchronous evolution of emergency response actions and the risk propagation process, effectively blocking the chain reaction between regions; at the same time, design a redundant instruction triggering mechanism, dynamically supplement the emergency control strategy through real-time diffusion rate feedback, and improve the fault tolerance ability of the system to sudden diffusion surges in complex scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic structural diagram of the chemical industrial park safety risk control system of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0018] Embodiment: Figure 1 The structural schematic diagram of the safety risk control system for chemical industrial parks of the present invention is given. The safety risk control system for chemical industrial parks includes the following modules: A data acquisition module for obtaining real-time environmental parameters and equipment status data of multiple monitoring points in the chemical industrial park; A fluid correction module for extracting the persistent homology barcode of turbulent vortices through computational fluid dynamics according to the real-time environmental parameters and equipment status data, and generating a path correction coefficient by combining the resonance frequency matching degree between the equipment layout and the microclimate vortices; A coupled modeling module for generating dynamic spatio-temporal propagation parameters through a multi-physics field coupling equation based on the path correction coefficient and the risk diffusion rate in the time dimension; A path prediction module for predicting the diffusion direction and influence area of risk events according to the vector superposition result of the dynamic spatio-temporal propagation parameters and the three-dimensional topological map of the chemical industrial park; An instruction optimization module for adjusting the priority and trigger range of the automated control instructions based on the diffusion direction and influence area, and generating a dynamic control instruction set matching the risk diffusion path; An execution control module for executing the dynamic control instruction set and controlling the emergency equipment in the target area to block the risk diffusion path according to the preset logic.

[0019] Obtaining the real-time environmental parameters and equipment status data of multiple monitoring points in the chemical industrial park is specifically implemented as follows: According to the equipment distribution density, process risk level, and historical accident data, divide the monitoring point deployment area in the chemical industrial park, and deploy temperature sensors, gas concentration sensors, and wind speed sensors.

[0020] The temperature sensor selects a probe type that is corrosion-resistant and has a response speed meeting the process requirements, and the installation position is comprehensively determined with reference to the surface heat conduction characteristics of the equipment and the surrounding ventilation conditions.

[0021] The gas concentration sensor selects a corresponding sensitive element according to the type of target gas to be detected, and is installed at the joints of equipment with a high leakage probability or at the bottom of the enclosed space.

[0022] The installation position of the wind speed sensor avoids the building or equipment shielding area, and preferably selects the highest point or open area in the park.

[0023] All sensors are connected to the data collector through an industrial bus protocol. The data collector configures filtering parameters according to the sensor type, uses a moving average filtering algorithm for temperature data to eliminate noise, and dynamically adjusts the length of the filtering window according to the fluctuation frequency of the ambient temperature. When the detected value of the gas concentration data is close to the upper limit of the range, it automatically switches to the high-precision acquisition mode, and cross-checks the data validity through the spare sensing channel. The wind speed data uses a dynamic filtering algorithm to separate the instantaneous gust and the sustained wind speed components.

[0024] The installation position of the pressure sensor is selected according to the hydrodynamic characteristics. For example, at the pipe elbow, the pump outlet, and the straight pipe section upstream of the valve, and the lengths of the front and rear straight pipe sections that meet the requirements of stable fluid flow are reserved. The valve opening sensor is mechanically coaxially connected to the actuator and uses non-contact measurement technology. The pressure sensor and the valve opening sensor communicate with the distributed system through an industrial control protocol, and the data refresh cycle is set synchronously with the device control cycle. The setting logic of the preset threshold is as follows: The pipeline pressure threshold is comprehensively calculated based on the device design pressure, material fatigue coefficient, and safety margin. For example, the first-level warning threshold is dynamically adjusted according to the ratio of the design pressure to the safety factor. The preset value of the valve opening is set according to the standard operating parameters in the process flow diagram, and the tolerance range is calculated based on the valve repeat positioning accuracy and the actuator error tolerance.

[0025] When calculating the current risk level in real time, the temperature data, gas concentration data, and wind speed data are normalized. For example, the temperature data is based on the temperature tolerated by the device material and the process allowable fluctuation range. The normalized parameters are linearly weighted according to the preset weights, and the weight distribution principle is determined according to the causal contribution degree of each parameter in the historical accident data. The weighted calculation result is mapped to a risk level value, and the risk level interval is divided in combination with the risk tolerance standard in the process safety specification. For example, there are four intervals: low risk, medium risk, high risk, and extremely high risk. The data acquisition frequency is dynamically adjusted based on the real-time risk level value. For example, the basic sampling frequency is maintained in the low-risk interval, and exponential incremental sampling is enabled and the redundant sensing channel is activated in the high-risk interval.

[0026] In data verification and exception handling, the abnormal determination of temperature data is achieved through the analysis of the differences between adjacent sensor data, and the difference threshold is calculated according to the sensor accuracy and the ambient thermal inertia characteristics. When the gas concentration data is abnormal, it automatically switches to the spare sensor and starts the manual calibration process. The validity of the wind speed data is determined through the consistency check of adjacent sensors and the trend correlation analysis. If it is abnormal, the wind speed field is reconstructed based on the spatial interpolation algorithm.

[0027] According to the real-time environmental parameters and equipment status data, the persistent homology barcode of the turbulent vortex is extracted through computational fluid dynamics, and the path correction coefficient is generated by combining the resonance frequency matching degree between the equipment layout and the microclimate vortex. The specific implementation is as follows: When performing dynamic filtering on wind speed and wind direction data in real-time environmental parameters, a sliding window filtering algorithm based on time series analysis is adopted to decompose the original wind speed and wind direction data into a persistent wind speed component representing the macroscopic flow field trend and an instantaneous pulsation component. The window length of the sliding window filtering algorithm is dynamically adjusted according to the statistical characteristics of the wind speed data. The specific adjustment method is as follows: Calculate the standard deviation of the wind speed data within a preset time period. When the standard deviation exceeds the set threshold, shorten the window length to capture high-frequency pulsation components; otherwise, extend the window length to enhance the low-frequency trend extraction ability. The determination method of the set threshold is as follows: Based on the statistical distribution of historical wind speed data, take the mean plus twice the standard deviation as the trigger threshold for high-frequency components, and the mean minus one standard deviation as the switching threshold for low-frequency components. For example, when the historical wind speed mean in a certain area is 3 m / s and the standard deviation is 1 m / s, the high-frequency trigger threshold is 5 m / s, and the low-frequency switching threshold is 2 m / s. The separated persistent wind speed component is used to construct a flow field model, and the instantaneous pulsation component detects abnormal fluctuation events through short-time Fourier transform and marks the timestamps.

[0028] When constructing a three-dimensional transient flow field model based on the persistent wind speed component, the finite volume method in computational fluid dynamics is used to divide the grid of the chemical industrial park. The grid resolution is set hierarchically according to the equipment layout density and terrain complexity. The specific rules are as follows: High-resolution grids are used in the surrounding areas of high-risk equipment such as storage tanks and reactors, and the grid side length does not exceed 1 / 10 of the equipment diameter; Low-resolution grids are used in open areas, and the grid side length does not exceed 1 / 5 of the equipment spacing. The inlet boundary conditions of the flow field model are set according to the direction and magnitude of the real-time wind speed component, and the outlet boundary conditions are dynamically adjusted according to the pressure gradient and terrain resistance coefficient. The flow field distribution is simulated by solving the transient Navier-Stokes equations, and the persistent homology barcode of the turbulent vortices in the flow field is extracted. The generation method of the persistent homology barcode is as follows: Perform eigenvalue decomposition on the velocity gradient tensor of the simulated flow field to identify the vortex core region. The determination condition for the vortex core is that the imaginary part of the eigenvalue is greater than zero and the vorticity amplitude exceeds three times the average vorticity of the flow field; Based on the principle of topological connectivity, analyze the evolution characteristics of the vortex boundary within a preset time window, including vortex merger, splitting, and dissipation events, and encode the spatio-temporal evolution trajectory of the vortex into a barcode sequence containing the life cycle, spatial scale, and energy intensity. For example, in a simulation with a time window of 60 seconds, a certain vortex lasts for 45 seconds from generation to extinction, and the corresponding barcode line segment length is 45 seconds, and the color depth of the line segment represents the vortex energy intensity.

[0029] When performing a spatial Fourier transform on the device layout coordinates in the device status data, first convert the device layout coordinates into two-dimensional spatial grid data with the grid size consistent with the resolution of the flow field model to ensure data alignment. The specific conversion method is as follows: discretize the device coordinates according to the grid size, and count the device density (number of devices per unit area) in each grid to form a device density distribution matrix. Perform a discrete Fourier transform on the device density distribution matrix to obtain the spatial frequency spectrum distribution of the device layout. The method for identifying the energy concentration region at the dominant frequency of the microclimate vortex is as follows: extract the frequency components in the spectrum whose energy amplitude exceeds a set multiple of the average energy level, and the set multiple is determined according to the statistical distribution of device resonance events in historical accident data. For example, when the energy amplitude of the device layout spectrum in a certain area at a frequency of 0.1 Hz is 2.5 times the average level and the proportion of this frequency in historical resonance accidents exceeds 70%, determine that the spatial region corresponding to this frequency is the energy concentration region.

[0030] When calculating the resonance coupling strength based on the topological evolution characteristics of the persistent homology barcode and the frequency spectrum distribution of the energy concentration region, first map the vortex energy diffusion paths in the barcode sequence to the spatial grid of the device layout, and calculate the overlapping area between each vortex path and the energy concentration region. The calculation method of the overlapping area is as follows: count the number of grids covered by the vortex path within the energy concentration region, and the weight of each grid is set according to its spectrum energy amplitude. The weight assignment rule is: for every time the spectrum energy amplitude exceeds the average level by one time, the grid weight increases by 0.2. For example, if the spectrum energy amplitude of a certain grid is 3 times the average level, its weight is 1.0 + 0.2×2 = 1.4. The resonance coupling strength is quantified by the ratio of the weighted overlapping area to the total vortex energy, and the total vortex energy is the sum of the products of the barcode segment length and the color depth. The finally generated path correction coefficient is the normalized result of the resonance coupling strength and the preset reference value, and the reference value is set according to the average diffusion rate in the non-resonance coupling scenario in historical data. The specific method is as follows: take the average diffusion rate in the past year when there are no device resonance events as the reference value, and when the deviation between the real-time diffusion rate and the reference value exceeds 20%, the path correction coefficient is linearly adjusted according to the deviation ratio. For example, when the reference value is 2 meters per second and the real-time diffusion rate is 2.4 meters per second, the path correction coefficient is adjusted to 1.2.

[0031] The continuous and pulsating components of wind speed are separated by dynamic filtering to ensure the stability of flow field modeling; based on computational fluid dynamics, a transient flow field model is constructed and continuous coherent barcodes are extracted to quantify the vortex evolution characteristics, breaking through the limitations of traditional steady-state flow field analysis; the spatial Fourier transform of the equipment layout is simultaneously performed to identify energy concentration areas, revealing the resonant coupling mechanism between equipment and microclimate. Compared with the defects of isolated processing of fluid, equipment and meteorological data in existing technologies, the diffusion path is dynamically corrected through multi-physical field coupling (fluid topology + equipment spectrum), significantly improving the prediction accuracy; the topological data analysis is associated with the equipment layout spectrum to solve the problem that traditional models ignore time and space coordination. For example, the interactive effect of the vortex energy diffusion path and equipment resonance can warn high-risk areas in advance, so that the control instructions can accurately match the real-time risk situation, reduce emergency response delays and resource waste, and thus achieve more reliable safety management and control in complex meteorological and equipment layout scenarios.

[0032] Based on the path correction coefficient and the risk diffusion rate in the time dimension, dynamic spatiotemporal propagation parameters are generated through multi-physics field coupling equations. The specific implementation is as follows: The path correction factor Perform normalization to generate a modified weight factor , specifically using the extreme value normalization method: ;in, It represents the maximum value of the path correction coefficient under typical working conditions without equipment resonance coupling in historical data. It is determined by counting the peak values ​​of different seasonal scenarios in at least one complete annual cycle. For example, in the high temperature and high humidity scenario in summer, the viscosity of the fluid is reduced. Increased, low temperature and dry scene in winter due to increased fluid resistance reduce; It indicates the minimum value in the data of the same period. The extreme value screening needs to exclude sensor failure or extremely abnormal data (such as typhoon weather); is the normalized modified weight factor, which ranges from [0,1] and is used to quantify the impact of equipment layout on the spatial heterogeneity of fluid diffusion. For example, a park determined by analyzing three years of historical data 2.5 (summer), is 0.5 (winter), when real time When 1.8, , indicating that the current space correction strength is 65% of the maximum value.

[0033] Risk diffusion rate in the time dimension Perform time series weighting processing to generate time decay coefficients , the specific logic is: Fitting an exponential decay model based on historical accident data: ,in, is the initial diffusion rate, and the historical accident triggering time is extracted ( ) is determined by the mean diffusion rate; is the decay rate constant, which is obtained by fitting the historical decay curve by the least square method; is the steady-state offset, which is taken from the baseline rate of the risk-free diffusion scenario. For example, in a chlorine gas leak accident, the fitting result is 2.2 m / s, 0.05, is 0.3 m / s, indicating that the diffusion rate decays exponentially with time to a stable value of 0.3 m / s; Calculate diffusion rate in real time With the fitted value If the relative error exceeds the preset threshold (e.g. 20%), the For example, when is 2.6 m / s and When the speed is 1.5 m / s, the deviation is (2.6−1.5) / 1.5=73%, triggering Decrease by 30% to suppress the over-correction of equipment resistance due to diffusion acceleration.

[0034] When establishing the multi-physics field coupling equation, the modified fluid mechanics diffusion equation and the equipment layout resistance equation are combined: Construct the fluid diffusion equation based on Fick's law: ;in For risk substance concentration, real-time monitoring is performed through gas sensors deployed in chemical parks (e.g. electrochemical sensors to detect chlorine concentration); is the effective diffusion coefficient, which is determined by querying the fluid property table. For example, the effective diffusion coefficient of chlorine in air is 1.2×10 -5 m2 / s; As a spatial correction term, it is used to characterize the local blocking or enhancing effect of equipment layout on the diffusion path; represents the gradient operator, which is used to calculate spatial derivatives; Construct the equipment resistance equation based on Darcy's law: ,in The equipment layout resistance is in Newton / square meter, which is output by a resistance sensor or a fluid mechanics simulation model; The viscosity of the fluid is obtained by matching the real-time temperature with the physical property parameter library (for example, the viscosity of air decreases as the temperature increases); As a time correction term, it is used to characterize the dynamic weakening or strengthening effect of the historical decay trend on the current resistance; Represents the flow field velocity in meters per second, which comes from the flow field model output; Represents spatial coordinates, with the unit of meters, consistent with the grid division of the chemical industrial park's Geographic Information System (GIS).

[0035] By iteratively solving the multi-physics field coupling equations, dynamic spatio-temporal propagation parameters are output, specifically including the following steps: The spatial correction term and the time correction term are decoupled using the method of separation of variables, and the concentration distribution is updated separately and the equipment resistance , where is the time step, set to 0.1 seconds according to the CFL condition to avoid numerical divergence; represents the number of iterations, with an initial value set to 0, and the maximum number of iterations set to 50 according to the computing resources; represents the -th iteration of the spatial concentration distribution; represents the -th iteration of the equipment resistance value.

[0036] The convergence condition is the residual: ; where, represents the L2 norm of the residual, used to quantify the difference between the results of two adjacent iterations; represents the total number of spatial grids, represents the index number of the spatial grid, with a value range from 1 to , used to traverse all grid points; represents a preset residual threshold, set to according to the statistical analysis of historical simulation errors.

[0037] The finally output dynamic spatio-temporal propagation parameters include: The risk diffusion direction vector is: ; where is the flow field velocity direction vector (output by the flow field model), is the equipment resistance direction vector (generated by calculating the resistance gradient), and the weights and are dynamically allocated according to the real-time risk level. For example, at high risk , .

[0038] The propagation rate gradient is determined by calculating , represents the partial derivative operator, and the grid gradient step size is set according to the equipment layout density classification (step size in high-risk areas ≤ 1 meter, step size in open areas ≤ 5 meters); the spatial energy density distribution is obtained by integrating , and its expression is: ; where, represents the spatial energy density distribution (unit: J / m3); Indicates the left boundary coordinates of the integral (unit: meter), which is determined by the minimum position of the current area; Indicates the coordinates of the right boundary of the integral (meters), which is determined by the maximum position of the current area; represents the correction weight factor (dimensionless), which is calibrated by experiments and has a value range of [0,2]; represents the time attenuation coefficient; Represents the spatial integral differential element (unit: meter).

[0039] The integration priority is divided according to the risk level (for example, Gaussian integration is used for high-risk areas and rectangular integration is used for low-risk areas).

[0040] By integrating the dynamic coupling mechanism of the path correction coefficient and the time attenuation coefficient, the problem of prediction deviation caused by the isolated treatment of space or time dimensions in the traditional risk diffusion model is solved. Compared with the existing technology, the extreme value normalization method driven by historical data is used to quantify the impact of the non-uniformity of equipment layout on the diffusion path, rather than relying on static empirical coefficients; the time attenuation coefficient is adjusted based on the dynamic deviation of the real-time diffusion rate and the historical attenuation model to replace the fixed time weight; the fluid diffusion equation and the equipment resistance equation are combined to achieve accurate modeling of multi-physical field interactions through iterative decoupling solution. The model can simultaneously characterize the synergistic effects of equipment layout resistance, microclimate flow field and historical accident attenuation trends, reduce the diffusion prediction error in complex environments, shorten the emergency response time, and solve the problems of early warning lag and misjudgment caused by ignoring multi-field coupling in existing technologies, providing a reusable solution for dynamic risk management and control in chemical parks.

[0041] According to the vector superposition results of dynamic spatiotemporal propagation parameters and the three-dimensional topological map of the chemical park, the diffusion direction and impact area of ​​risk events are predicted. The specific implementation is as follows: Vector superposition is performed between the risk diffusion direction vector in the dynamic spatio-temporal propagation parameters and the geographical coordinates in the 3D topological map of the chemical industrial park to generate the risk propagation path vector field after superposition. The direction of the risk diffusion direction vector is synthesized by the flow field velocity direction and the equipment resistance direction, with the unit of meters per second; the geographical coordinates of the 3D topological map of the chemical industrial park are in a 3D Cartesian coordinate system, including the spatial coordinates of all equipment, buildings and terrain, with the unit of meters. In the superposition operation, the risk diffusion direction vector is decomposed into components according to the X, Y, and Z axes of the 3D coordinate system, and the velocity values of each component are matched with the coordinates of the corresponding geographical grid center point and then superimposed to generate a vector field including direction and rate. For example, if the center coordinates of a certain grid are (100 meters, 50 meters, 10 meters), and the corresponding risk diffusion direction vector is (1.2 meters per second, -0.3 meters per second, 0.5 meters per second), then in the vector field after superposition, the propagation direction of this grid is to diffuse from the coordinate point (100, 50, 10) along the direction of (1.2, -0.3, 0.5), and the rate is 1.36 meters per second (obtained through vector modulus calculation).

[0042] Based on the risk propagation path vector field after superposition, dynamic grid division is performed on the chemical industrial park, and the grid resolution is adjusted according to the spatial energy density distribution. The value of the spatial energy density distribution represents the risk diffusion energy intensity per unit volume, with the unit of joules per cubic meter. The adjustment rule is: the grid side length in the high energy density area is smaller than that in the low energy density area, which is specifically achieved by setting the energy density segmentation threshold. For example, when the energy density of a certain area is greater than or equal to 1000 joules per cubic meter, the grid side length is set to 1 meter; when the energy density is between 500 and 1000 joules per cubic meter, the grid side length is set to 2 meters; when the energy density is less than 500 joules per cubic meter, the grid side length is set to 5 meters. The threshold is set according to the statistical relationship between the energy density and the accident consequences in historical accidents. For example, statistical analysis shows that areas with an energy density greater than or equal to 1000 joules per cubic meter will trigger equipment chain reactions in 80% of the accidents.

[0043] Calculate the spatial change rate of the risk diffusion rate within the grid according to the propagation rate gradient, and combine the fluid viscosity and the equipment layout resistance equation to generate the risk diffusion priority coefficient for each grid. The propagation rate gradient is obtained by calculating the difference in diffusion rates between adjacent grids. For example, if the diffusion rate of a grid is 1.36 meters per second, the diffusion rate of its adjacent grid to the east is 1.28 meters per second, and the grid spacing is 1 meter, then the eastward gradient is a decrease of 0.08 meters per second per second; the fluid viscosity is obtained by matching the real-time temperature through the physical property parameter library. For example, when the temperature is 25 degrees Celsius, the air viscosity is 0.000018 Pa·s; the equipment layout resistance equation is derived from the resistance calculation model. The calculation formula for the risk diffusion priority coefficient is the absolute value of the rate gradient divided by the fluid viscosity and then multiplied by the equipment resistance value. For example, if the absolute value of the rate gradient of a grid is 0.08 per second, the fluid viscosity is 0.000018 Pa·s, and the equipment resistance value is 120 N / m², then the priority coefficient is (0.08 / 0.000018) × 120 = 53333.

[0044] Based on the risk diffusion priority coefficient and the preset diffusion threshold, mark the continuous grid area with a priority coefficient exceeding the threshold as the impact area, and output the diffusion direction and the set of spatial coordinates of the impact area. The preset diffusion threshold is set through statistical analysis of historical accident data. For example, take the lowest priority coefficient of 90% of the accident cases in the past three years as the threshold (such as 50000), and trigger the marking when the priority coefficient calculated in real time exceeds this value; the determination rule for the continuous grid area is that the priority coefficients of at least three adjacent grids (including diagonally adjacent) exceed the threshold. In the output result, the set of spatial coordinates of the impact area is recorded as a list of grid center point coordinates, and the diffusion direction is determined by the local principal direction of the vector field. For example, the principal direction of an impact area is the northeast direction, and the coordinate list includes adjacent grid points such as (100 m, 50 m, 10 m), (101 m, 51 m, 10 m), etc.

[0045] Through the dynamic grid division and vector superposition mechanism, the defects of fixed spatial resolution and ignoring the multi-field coupling effect in traditional risk prediction models are solved. Compared with the existing technology, the grid resolution is dynamically adjusted based on the energy density (1 meter in the high-density area and 5 meters in the low-density area), replacing the static grid division, which improves the calculation efficiency and accuracy; the risk diffusion direction vector is superimposed on the three-dimensional topological map (such as the coordinate (100, 50, 10) matching the vector (1.2, -0.3, 0.5)), realizing the precise integration of geographical space and flow field parameters; the synergistic effects of gradient, viscosity, and resistance are quantified through the priority coefficient, replacing the single rate threshold determination. It solves the problem of early warning lag caused by ignoring the interaction between equipment layout and climate in traditional methods, providing a reusable technical path for dynamic risk management.

[0046] Based on the diffusion direction and the affected area, adjust the priority and trigger range of the automation control instructions, and generate a dynamic control instruction set that matches the risk diffusion path. The specific implementation is as follows: Establish a control instruction priority mapping table according to the set of spatial coordinates of the affected area and the risk diffusion direction vector. The set of spatial coordinates of the affected area contains a list of the grid center point coordinates marked as high-risk areas; the risk diffusion direction vector is derived from dynamic spatio-temporal propagation parameters, and its direction is synthesized by the flow field velocity and the equipment resistance, with the unit of meters per second. The construction rule of the priority mapping table is: associate the spatial coordinates of each affected area with the corresponding risk diffusion priority coefficient, and the level of the control instruction is dynamically adjusted according to the spatial energy density distribution of the area. For example, if the priority coefficient of a certain affected area is 53333 and the spatial energy density is 1200 joules per cubic meter, the control instruction level of this area in the mapping table is set to the highest level (level 1); if the priority coefficient is 45000 and the energy density is 800 joules per cubic meter, the level is set to the intermediate level (level 2). The level division threshold is set according to the statistics of the control response effect in historical accidents. For example, level 1 corresponds to immediately cutting off the power supply of the equipment, and level 2 corresponds to reducing the operating power of the equipment.

[0047] Based on the dynamic control instruction set and the topological relationship of the equipment layout in the chemical industrial park, adjust the trigger range of the automation control instructions. The topological relationship of the equipment layout is derived from a three-dimensional topological map, including equipment coordinates and connection relationships; the trigger range covers the equipment coordinates in the affected area and its adjacent grids where the risk diffusion priority coefficient exceeds the preset diffusion threshold. The determination rule for adjacent grids is the grids that share at least one edge or corner point with the grids in the affected area. For example, if the grid coordinates of a certain affected area are (100 meters, 50 meters, 10 meters), its adjacent grid to the east is (101 meters, 50 meters, 10 meters), and the adjacent grid to the northeast diagonal is (101 meters, 51 meters, 10 meters). When adjusting the trigger range, if the priority coefficient of the adjacent grid exceeds the preset diffusion threshold (such as 50000), the equipment coordinates in this grid are included in the control instruction trigger range. For example, if the priority coefficient of an adjacent grid is 52000 and it contains the equipment coordinates of a reactor (101 meters, 51 meters, 10 meters), a shutdown instruction for this reactor is generated.

[0048] Based on the real-time diffusion rate and equipment operation status data, mark the emergency control instructions that need to be executed immediately in the priority mapping table to generate a dynamic control instruction set. The real-time diffusion rate is derived from the calculation result of the propagation rate gradient, with the unit of meters per second; the equipment operation status data is collected in real time through equipment sensors, including the equipment switch status, operating power, and temperature parameters. The marking rule is: if the real-time diffusion rate exceeds the preset safety threshold (e.g., 2 meters per second) and the equipment is in the operating state, mark the corresponding control instruction as an emergency instruction. For example, if the real-time diffusion rate in a certain area is 2.5 meters per second and the pump equipment in this area is in the operating state, then mark "shut down the pump" as an emergency instruction. The generation logic of the dynamic control instruction set is: sort the instructions from the highest to the lowest priority level, and arrange them in the order of the equipment topological connection within the same level. For example, close the upstream equipment first and then the downstream equipment.

[0049] Verify the logical consistency of the dynamic control instruction set through the spatial matching degree between the risk diffusion path vector field and the equipment topological relationship, and eliminate the instructions that conflict with the diffusion path. The risk diffusion path vector field is derived from the vector superposition result, including the diffusion direction and rate of each grid; the equipment topological relationship is the defined equipment connection relationship. The verification method is: traverse each instruction in the dynamic control instruction set and check whether the corresponding equipment coordinates are located on the propagation direction of the diffusion path vector field. If the equipment coordinates are located in the opposite direction or perpendicular direction of the diffusion direction, it is determined as a logical conflict. For example, if an instruction requires closing the storage tank valve located in the opposite direction of the diffusion direction, and the vector field shows that the positive diffusion area is from equipment A to equipment B, then eliminate this instruction to avoid blocking the diffusion path. The finally output dynamic control instruction set only contains the equipment control instructions that are consistent with the diffusion path direction.

[0050] Execute the dynamic control instruction set to control the emergency equipment in the target area to block the risk diffusion path according to the preset logic. The specific implementation is as follows: Sort the control instructions in the dynamic control instruction set from the highest to the lowest priority level, and send control instructions to the emergency equipment in the target area level by level. The dynamic control instruction set contains a list of equipment operation instructions sorted by priority level; the priority level of the control instruction is determined according to the priority mapping table, with level 1 being the highest priority and level 3 being the lowest priority. Each control instruction contains the equipment operation type and execution parameters. For example, the operation type of the instruction to close the valve is "close", and the execution parameter is the valve closing speed (such as 0.5 meters per second); the operation type of starting the sprinkler system is "start", and the execution parameter is the sprinkler flow rate (such as 10 cubic meters per minute). When sending instructions, first send instructions to the emergency equipment at level 1. After confirming the execution is completed, then send level 2 instructions, and so on. For example, in a certain area, the level 1 instruction is to close the feed valve of the reactor, the level 2 instruction is to start the surrounding sprinkler system, and the level 3 instruction is to reduce the power of the pump.

[0051] Based on the spatial matching degree between the equipment topological relationship in the chemical industrial park and the risk diffusion path vector field, control instructions in the same priority level that are consistent with the diffusion path direction are executed in parallel. The equipment topological relationship is derived from a three-dimensional topological map, which describes the spatial connection relationship between equipment; the risk diffusion path vector field is derived from the vector superposition result, including the diffusion direction and rate of each grid. The parallel execution rule is: in the same priority level, if multiple devices are in the same direction of the risk diffusion path vector field and there is no topological dependence conflict, control instructions are sent simultaneously. For example, if the diffusion path direction is northeast, a priority 1 instruction is to close storage tank A and reactor B in the northeast direction, and there is no upstream and downstream dependence between them, then the closing instructions are sent simultaneously. If there is a topological dependence between devices (such as storage tank A being the raw material source of reactor B), they are executed in the order of dependence.

[0052] Collect the execution status data of emergency equipment, and adjust the priority level of unexecuted instructions according to the deviation value between the execution status data and the preset response logic. The execution status data is obtained in real time through equipment sensors, including parameters such as valve opening, spray flow rate, and pump power; the preset response logic is the expected state after the instruction is executed. For example, the expected opening of a closed valve is 0%, and the expected flow rate of a started spray is 10 cubic meters per minute. The deviation value is calculated as the percentage of the absolute difference between the real-time state and the expected state. For example, if the real-time valve opening is 10% and the expected is 0%, the deviation value is 10%. The adjustment rule is: if the deviation value exceeds the preset threshold (such as 5%), the priority of the unexecuted associated instruction is raised by one level; if the equipment status is normal (deviation ≤ 5%), the original priority is maintained. For example, a level 2 instruction requires starting the spray system. If the real-time flow rate is only 8 cubic meters per minute (deviation 20%), the level 3 instruction (such as closing the ventilation system) associated with this instruction is raised to level 2.

[0053] Through the feedback data of the real-time risk diffusion rate and the equipment execution status, verify the effectiveness of the executed control instructions. If the diffusion rate does not drop to the safety threshold, redundant control instructions are triggered. The real-time risk diffusion rate is derived from the calculation result of the propagation rate gradient, with the unit of meters per second; the safety threshold is set according to the average diffusion rate under historical accident-free conditions. For example, the safety threshold for a certain area is 0.5 meters per second. The verification logic is: if the diffusion rate in the area corresponding to the executed instruction does not drop to the safety threshold within the preset time (such as 3 minutes), redundant control instructions are triggered. The generation rule of redundant instructions is: based on the equipment topological relationship, select standby equipment that has no dependence on the executed equipment to perform the same operation. For example, after closing the valve of storage tank A, the diffusion rate is still 1.2 meters per second, then a redundant instruction to close the valve of standby storage tank C is triggered. The priority of the redundant instruction is the same as that of the original instruction, and the equipment topological dependence relationship needs to be verified again before execution.

[0054] All the calculations involved in the embodiments are dimensionless numerical calculations. The preset parameters and threshold selections in the calculations are set by those skilled in the art according to the actual situation.

[0055] It should be noted that the present invention can be deployed on the device itself to achieve embedded applications, or can also run on a PC or other terminals with a user interface, so as to meet various hardware environments and usage requirements.

[0056] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center by wire (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0057] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0058] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there can be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or modules can be in electrical, mechanical or other forms.

[0059] The module described as a separation component may or may not be physically separated. The component shown as a module may or may not be a physical module. It may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0060] In addition, in each embodiment of this application, each functional module can be integrated into a processing module, or each module can exist physically alone, or two or more modules can be integrated into one module.

[0061] If the function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of this application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0062] As described above, it is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0063] Finally: The above is only the preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A safety risk control system for chemical industrial parks, characterized in that, It includes the following modules: A data acquisition module, which is used to obtain the real-time environmental parameters and equipment status data of multiple monitoring points in the chemical industrial park; A fluid correction module, which is used to extract the persistent homology barcode of turbulent vortices through computational fluid dynamics according to the real-time environmental parameters and equipment status data, and generate a path correction coefficient by combining the resonance frequency matching degree between the equipment layout and the microclimate vortices; A coupled modeling module, which is used to generate dynamic spatio-temporal propagation parameters through a multi-physics field coupling equation based on the path correction coefficient and the risk diffusion rate in the time dimension; A path prediction module, which is used to predict the diffusion direction and influence area of a risk event according to the vector superposition result of the dynamic spatio-temporal propagation parameters and the 3D topological map of the chemical industrial park; An instruction optimization module, which is used to adjust the priority and trigger range of the automatic control instructions based on the diffusion direction and influence area, and generate a dynamic control instruction set matching the risk diffusion path; An execution control module, which is used to execute the dynamic control instruction set and control the emergency equipment in the target area to block the risk diffusion path according to the preset logic.

2. The chemical industrial park safety risk control system according to claim 1, wherein Obtain the real-time environmental parameters and equipment status data of multiple monitoring points in the chemical industrial park, including: Collect the temperature data, gas concentration data and wind speed data in the real-time environmental parameters through temperature sensors, gas concentration sensors and wind speed sensors; Collect the pipeline pressure data and valve opening data in the equipment status data through pressure sensors and valve opening sensors; Calculate the current risk level in real time according to the temperature data, gas concentration data and wind speed data, and dynamically adjust the data acquisition frequency based on the current risk level.

3. The chemical industrial park safety risk control system according to claim 1, wherein, Extract the persistent homology barcode of turbulent vortices through computational fluid dynamics according to the real-time environmental parameters and equipment status data, and generate a path correction coefficient by combining the resonance frequency matching degree between the equipment layout and the microclimate vortices, including: Perform dynamic filtering on the wind speed and wind direction data in the real-time environmental parameters to separate the persistent wind speed component and the instantaneous pulsation component representing the macroscopic flow field trend; Based on the persistent wind speed component, construct a three-dimensional transient flow field model through computational fluid dynamics, and extract the persistent homology barcode of the turbulent vortices in the flow field; Synchronously perform spatial Fourier transform on the equipment layout coordinates in the equipment status data to identify the energy concentration area of the equipment layout at the dominant frequency of the microclimate vortices; Calculate the resonance coupling strength between the vortex energy diffusion path and the equipment layout according to the topological evolution characteristics of the persistent homology barcode and the spectral distribution of the energy concentration area, and generate a path correction coefficient.

4. The chemical industrial park safety risk control system according to claim 3, wherein, The persistent homology barcode is generated by quantifying the topological evolution characteristics of the topological connectivity of the vortex boundary within a preset time window.

5. The chemical industrial park safety risk control system according to claim 1, characterized in that Generate dynamic spatio-temporal propagation parameters through a multi-physics field coupling equation based on the path correction coefficient and the risk diffusion rate in the time dimension, including: Normalize the path correction coefficient to generate a correction weight factor; Perform time series weighting on the risk diffusion rate in the time dimension to generate a time decay coefficient, and the weighting is dynamically adjusted based on the decay trend of the historical accident diffusion rate. Establish a multi-physics coupling equation, which uses the correction weight factor as the space correction term and the time attenuation coefficient as the time correction term, and combines the fluid mechanics diffusion equation with the equipment layout resistance equation for simultaneous solution; By iteratively solving the multi-physics field coupling equations, the dynamic space-time propagation parameters are output. The dynamic space-time propagation parameters include the risk diffusion direction vector, propagation rate gradient and spatial energy density distribution.

6. The chemical industrial park safety risk control system according to claim 1, characterized in that, According to the vector superposition results of dynamic spatiotemporal propagation parameters and the three-dimensional topological map of the chemical park, the diffusion direction and impact area of ​​risk events are predicted, including: The risk diffusion direction vector in the dynamic spatiotemporal propagation parameter is vector-superimposed with the geographic coordinates in the three-dimensional topological map of the chemical park to generate a superimposed risk propagation path vector field; Based on the superimposed risk propagation path vector field, the chemical park is dynamically meshed; The spatial variation rate of the risk diffusion rate in the grid is calculated based on the transmission rate gradient, and the risk diffusion priority coefficient of each grid is generated by combining the fluid viscosity and equipment layout resistance equation; Based on the risk diffusion priority coefficient and the preset diffusion threshold, the continuous grid area where the risk diffusion priority coefficient exceeds the preset diffusion threshold is marked as the impact area, and the diffusion direction and the spatial coordinate set of the impact area are output.

7. The chemical industrial park safety risk control system according to claim 6, wherein The grid resolution in the dynamic grid division of the chemical park is adjusted according to the spatial energy density distribution, and the grid edge length in the high energy density area is smaller than that in the low energy density area.

8. The chemical industrial park safety risk control system according to claim 1, characterized in that, Based on the diffusion direction and impact area, adjust the priority and trigger range of the automated control instructions to generate a dynamic control instruction set that matches the risk diffusion path, including: According to the spatial coordinate set of the impact area and the risk diffusion direction vector, a control instruction priority mapping table is established, and the level of the control instruction in the priority mapping table is dynamically adjusted according to the spatial energy density distribution and the risk diffusion priority coefficient; Based on the topological relationship between the dynamic control instruction set and the equipment layout of the chemical park, the trigger range of the automation control instruction is adjusted. The trigger range covers the coordinates of the equipment whose risk diffusion priority coefficient exceeds the preset diffusion threshold in the affected area and its adjacent grids; According to the real-time diffusion rate and equipment operation status data, the emergency control instructions that need to be executed immediately are marked in the priority mapping table to generate a dynamic control instruction set; The logical consistency of the dynamic control instruction set is verified by the spatial matching degree between the risk diffusion path vector field and the equipment topology relationship, and the instructions that conflict with the diffusion path are eliminated.

9. The chemical industrial park safety risk control system according to claim 1, characterized in that Execute dynamic control instruction sets to control the emergency equipment in the target area to block the risk diffusion path according to preset logic, including: Sort the control instructions in the dynamic control instruction set from high to low priority, and send control instructions to the emergency equipment in the target area step by step. The control instructions include equipment operation type and execution parameters; Based on the spatial matching degree between the topological relationship of chemical park equipment and the risk diffusion path vector field, control instructions with the same priority level and consistent with the diffusion path direction are executed in parallel; Collect the execution status data of the emergency equipment, and adjust the priority level of the unexecuted instructions according to the deviation value between the execution status data and the preset response logic; Verify the effectiveness of the executed control instruction through the feedback data of the real-time risk diffusion rate and the device execution status. If the diffusion rate does not drop to the safety threshold, trigger a redundant control instruction.

Images