Hazardous chemical substance transportation path dynamic risk prevention and control system and method based on space-time fusion

Abstract

The invention relates to the field of intelligent traffic safety, in particular to a hazardous chemical substance transportation path dynamic risk prevention and control system and method based on space-time fusion, and provides a method for calculating a multi-dimensional risk index matrix through a risk index quantification module and combining a space-time environment sensitivity prediction matrix generated by an environment sensitivity analysis module. According to a risk spreading probability cloud picture of the risk spreading prediction module, accurate evaluation of the dynamic risk of the road section is realized; the system establishes a collaborative risk factor assessment model, adjusts a safety threshold according to historical accident data, and generates a space-time road network risk scoring matrix; the risk prevention and control decision module determines an early warning level, selects prevention and control measures, optimizes a transportation path, formulates an emergency response plan for a high-risk road section, and outputs an intelligent decision instruction set; according to the system, comprehensive quantification of hazardous chemical substance characteristics is realized, and the comprehensiveness of risk assessment and the intelligence of prevention and control decision making are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent traffic safety, and particularly to a dynamic risk prevention and control system and method for the transportation route of hazardous chemicals based on spatio-temporal fusion, which is used to predict, evaluate, and prevent and control the safety risks during the transportation of hazardous chemicals. Background Art

[0002] There are significant safety risks during the transportation of hazardous chemicals. Once accidents such as leakage, fire, or explosion occur, they will not only cause direct economic losses, but may also lead to serious environmental pollution and casualties.

[0003] In the prior art, Chinese Patent CN 107591012 B discloses a warning method for the transportation of hazardous chemicals. This method establishes a balance model for vehicles under different road conditions and different load states. Based on the current vehicle state information and road information, it estimates the balance of the vehicle during future road driving, and then decides whether to send an alarm to the user. This technology mainly focuses on the physical stability of the vehicle and reduces accidents such as rollovers by predicting the balance state of the vehicle under specific road conditions.

[0004] However, the prior art has the following deficiencies: First, it only focuses on the physical stability of the vehicle and ignores the interaction risks between the characteristics of hazardous chemicals and the external environment; second, it does not consider the differences in the physical and chemical characteristics of different hazardous chemicals and the impact range after leakage; third, it lacks a risk weighted assessment of sensitive areas such as densely populated areas; fourth, it does not provide a specific alternative route planning scheme after warning; fifth, the system does not integrate dynamic factors such as real-time traffic congestion and meteorological conditions; sixth, there is no security guarantee mechanism for data transmission and storage. These deficiencies seriously limit the effect of risk prevention and control and cannot achieve systematic safety guarantee for the whole process of hazardous chemical transportation. Summary of the Invention

[0005] The purpose of the present invention is to provide a dynamic risk prevention and control system and method for the transportation route of hazardous chemicals based on spatio-temporal fusion, aiming to overcome the deficiency in the prior art that only focuses on vehicle stability and ignores the interaction between the characteristics of hazardous chemicals and the environment, and to achieve a technical leap from simple vehicle physical balance warning to all-round multi-dimensional risk perception and active prevention and control.

[0006] To achieve the above purpose, the present invention provides a dynamic risk prevention and control system for the transportation route of hazardous chemicals based on spatio-temporal fusion, including a risk index quantification module, an environmental sensitivity analysis module, a risk diffusion prediction module, a section risk assessment module, and a risk prevention and control decision module. Through the coordinated operation of the five modules, a complete closed-loop system from risk perception, assessment to active prevention and control is formed.

[0007] The present invention proposes a dynamic risk prevention and control system for the transportation route of hazardous chemicals based on spatio-temporal fusion, including:

[0008] A risk index quantification module, used for:

[0009] Receive the hazardous chemical attribute parameters, which include physical state, chemical activity, toxicity level, explosiveness, flash point, vapor pressure, water solubility, corrosiveness, reactivity, stability, volatility, carcinogenicity, teratogenicity, bioaccumulation, and environmental persistence;

[0010] Based on the hazardous chemical attribute parameters, calculate the leakage risk index, fire and explosion risk index, health hazard risk index, environmental pollution risk index, and reaction hazard risk index;

[0011] Generate a multi-dimensional risk index matrix for hazardous chemicals;

[0012] The environmental sensitivity analysis module, connected to the risk index quantification module, is used for:

[0013] Obtain environmental sensitive data, which includes real-time meteorological data, geographic information data, population distribution data, and sensitive target data;

[0014] Construct a grid-based spatio-temporal fusion model and calculate the environmental sensitivity index for each spatio-temporal grid;

[0015] Establish a Bayesian spatio-temporal network prediction model based on historical data to predict the changes in environmental sensitivity of each grid in the future period;

[0016] Generate a spatio-temporal environmental sensitivity prediction matrix;

[0017] The risk diffusion prediction module, connected to the risk index quantification module and the environmental sensitivity analysis module, is used for:

[0018] According to the multi-dimensional risk index matrix of hazardous chemicals and the spatio-temporal environmental sensitivity prediction matrix, construct a multi-media migration model;

[0019] Preset multiple leakage scenarios and conduct Monte Carlo risk propagation simulations;

[0020] Generate a risk propagation probability cloud map;

[0021] The road section risk assessment module, connected to the risk diffusion prediction module, is used for:

[0022] Receive road network data and discretize it into standard road sections;

[0023] Combine the multi-dimensional risk index matrix of hazardous chemicals, the spatio-temporal environmental sensitivity prediction matrix, and the risk propagation probability cloud map to calculate the dynamic risk scores of each road section at different times;

[0024] Establish a collaborative risk factor assessment model;

[0025] Dynamically adjust the safety threshold based on historical accident data;

[0026] Generate a risk scoring matrix for the spatio-temporal road network;

[0027] A risk prevention and control decision-making module, connected to the road section risk assessment module, for:

[0028] Based on the comparison between the spatio-temporal road network risk scoring matrix and the safety threshold, determine the warning level;

[0029] According to different warning levels, select corresponding prevention and control measures from the prevention and control measure library;

[0030] Execute multi-objective optimization decision-making to generate the optimal transportation route;

[0031] Generate an emergency response plan for high-risk road sections;

[0032] Output a risk intelligent decision-making instruction set.

[0033] Preferably, the risk index quantification module includes:

[0034] A parameter characterization unit for standardizing the hazardous chemical attribute parameters into a scale of 0-10;

[0035] A risk calculation unit for calculating five types of risk indexes according to the standardized hazardous chemical attribute parameters;

[0036] A weight adjustment unit for dynamically adjusting the weight coefficients according to different scenarios and calculating the comprehensive risk index CRI:

[0037] CRI = w1·LRI + w2·FERI + w3@HHRI + w4·EPRI + w5·RHRI,

[0038] where LRI is the leakage risk index, FERI is the fire and explosion risk index, HHRI is the health hazard risk index, EPRI is the environmental pollution risk index, RHRI is the reaction hazard risk index, w1 to w5 are weight coefficients, and w1 + w2 + w3 + w4 + w5 = 1.

[0039] Preferably, the environmental sensitivity analysis module includes:

[0040] A data access unit for obtaining and preprocessing multi-source environmental data;

[0041] A grid division unit for constructing a standard grid unit of 100m×100m and establishing a time matrix of 24 hours×7 days on each grid;

[0042] A sensitivity calculation unit for calculating the environmental sensitivity index ESI of each spatio-temporal grid;

[0043] ESI(x, y, t) = α·P(x, y, t) + β·W(x, y) + γ·S(x, y) + δ·M(x, y, t),

[0044] where P(x, y, t) is the population density index of grid (x, y) at time t, W(x, y) is the water source sensitivity index of grid (x, y), S(x, y) is the special sensitive target index of grid (x, y), M(x, y, t) is the meteorological condition index of grid (x, y) at time t, and α, β, γ, δ are weight coefficients and α + β + γ + δ = 1;

[0045] A prediction modeling unit for constructing a Bayesian network based on historical data to predict the environmental sensitivity changes of each grid within the next 24 hours.

[0046] Preferably, the risk diffusion prediction module includes:

[0047] A migration model unit for establishing migration and diffusion models for three media: atmosphere, water body, and soil;

[0048] A scenario presetting unit for presetting various leakage scenarios such as small leakage, medium leakage, large leakage, leakage accompanied by fire, and leakage accompanied by explosion according to the characteristics of hazardous chemicals and environmental conditions;

[0049] A Monte Carlo simulation unit for performing 10,000 Monte Carlo simulations for each leakage scenario to generate a risk probability distribution cloud map.

[0050] Preferably, the migration model unit includes:

[0051] An atmospheric diffusion calculation sub-unit for calculating the diffusion concentration of hazardous chemicals in the atmosphere using an improved Gaussian plume model;

[0052] A water body diffusion calculation sub-unit for calculating the migration process of hazardous chemicals in the water body using a two-dimensional convection-diffusion equation;

[0053] A soil penetration calculation sub-unit for simulating the penetration behavior of hazardous chemicals in the soil based on the Richards equation.

[0054] Preferably, the road section risk assessment module includes:

[0055] A road section discretization unit for discretizing the road network into road sections with a standard length of 500 m;

[0056] A risk scoring unit for calculating the dynamic risk score RSI of each road section at different time periods:

[0057] RSI(r, t) = CRI·ESI(r, t)·IAF(r, t),

[0058] Among them, CRI is the comprehensive risk index of hazardous chemicals, ESI(r,t) is the environmental sensitivity index of section r at time t, and IAF(r,t) is the impact amplification factor;

[0059] The collaborative risk assessment unit is used to evaluate the collaborative risk factors of vehicle status, road conditions, driving behavior patterns, and hazardous chemical characteristics;

[0060] The threshold adaptive unit is used to dynamically adjust the safety threshold according to historical accident data:

[0061] Threshold(t + 1) = Threshold(t) + η · (TargetSafety - CurrentSafety), where η is the learning rate, TargetSafety is the target safety level, and CurrentSafety is the current safety level.

[0062] Preferably, the risk prevention and control decision-making module includes:

[0063] The early warning determination unit is used to determine four early warning levels: green, yellow, orange, or red based on the comparison between the section risk score and the safety threshold;

[0064] The prevention and control measure unit is used to select corresponding driver operation suggestions, vehicle parameter adjustments, and route planning change measures according to the early warning level;

[0065] The multi-objective optimization unit is used to perform multi-objective optimization decisions on route planning considering three objectives: safety, timeliness, and economy;

[0066] The pre-plan generation unit is used to generate emergency response pre-plans for high-risk sections.

[0067] Preferably, the optimization function of the multi-objective optimization unit is:

[0068] minZ = [z1(x), z2(x), z3(x)],

[0069] Among them, z1(x) is the safety objective, reflecting the total risk of the route, z2(x) is the timeliness objective, reflecting the transportation time, and z3(x) is the economy objective, reflecting the transportation cost;

[0070] The constraint conditions are:

[0071] g1(x) = the maximum section risk score ≤ the allowable risk threshold,

[0072] g2(x) = the total transportation time ≤ the maximum allowable transportation time,

[0073] g3(x) = the total transportation cost ≤ the budget ceiling.

[0074] 9. The system according to claim 1, wherein the data flow process between modules is as follows:

[0075] The multi-dimensional risk index matrix of hazardous chemicals generated by the risk quantification module is transmitted to the environmental sensitivity analysis module and the risk diffusion prediction module;

[0076] The spatio-temporal environmental sensitivity prediction matrix generated by the environmental sensitivity analysis module is transmitted to the risk diffusion prediction module and the road section risk assessment module;

[0077] The risk propagation probability cloud map generated by the risk diffusion prediction module is transmitted to the road section risk assessment module;

[0078] The spatio-temporal road network risk scoring matrix generated by the road section risk assessment module is transmitted to the risk prevention and control decision-making module;

[0079] The risk intelligent decision-making instruction set of the risk prevention and control decision-making module is transmitted to the vehicle-mounted terminal and the monitoring center through the communication network.

[0080] The method corresponding to the above-mentioned dynamic risk prevention and control system for hazardous chemical transportation paths based on spatio-temporal fusion includes the following steps:

[0081] Receive hazardous chemical attribute parameters and calculate the multi-dimensional risk index matrix of hazardous chemicals;

[0082] Obtain environmental sensitive data, construct a grid spatio-temporal fusion model, and generate a spatio-temporal environmental sensitivity prediction matrix;

[0083] According to the multi-dimensional risk index matrix of hazardous chemicals and the spatio-temporal environmental sensitivity prediction matrix, construct a multi-media migration model, conduct Monte Carlo risk propagation simulation, and generate a risk propagation probability cloud map;

[0084] Discretize the road network into standard road sections, and combine the multi-dimensional risk index matrix of hazardous chemicals, the spatio-temporal environmental sensitivity prediction matrix, and the risk propagation probability cloud map to calculate the spatio-temporal road network risk scoring matrix;

[0085] Based on the comparison between the spatio-temporal road network risk scoring matrix and the safety threshold, determine the early warning level, select prevention and control measures, execute multi-objective optimization decision-making to generate the optimal transportation path, and output the risk intelligent decision-making instruction set.

[0086] The beneficial effects of the present invention are as follows: First, it realizes the multi-dimensional quantification of the characteristics of hazardous chemicals, establishes five types of risk indices including leakage, fire and explosion, health hazards, environmental pollution, and reaction hazards, making the risk assessment more comprehensive; second, it constructs a spatio-temporal environmental sensitivity model to dynamically evaluate the sensitivity changes of the environment around the transportation route; third, through Monte Carlo simulation, it visually displays the possible impact range of hazardous chemical leakage, supporting more accurate risk assessment; fourth, it innovatively integrates vehicle status, road condition characteristics, and driving behavior to construct a collaborative risk assessment model; fifth, based on a multi-objective optimization algorithm, it achieves a balance among safety, timeliness, and economy, and generates the optimal transportation route. Experimental data shows that this system can reduce the exposure time of high-risk sections by 55%, advance the emergency response preparation time by 12 minutes, and effectively reduce the incidence rate of hazardous chemical transportation safety accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] Figure 1 FIG. is the overall architecture diagram of the dynamic risk prevention and control system for hazardous chemical transportation routes based on spatio-temporal fusion of the present invention;

[0088] Figure 2 FIG. is the structural schematic diagram of the risk index quantification module of the present invention;

[0089] Figure 3 FIG. is the structural schematic diagram of the environmental sensitivity analysis module of the present invention;

[0090] Figure 4 FIG. is the structural schematic diagram of the risk diffusion prediction module of the present invention;

[0091] Figure 5 FIG. is the structural schematic diagram of the road section risk assessment module of the present invention;

[0092] Figure 6 FIG. is the structural schematic diagram of the risk prevention and control decision-making module of the present invention;

[0093] Figure 7 FIG. is the flow chart of the dynamic risk prevention and control method for hazardous chemical transportation routes of the present invention;

[0094] Figure 8 FIG. is the comparison diagram of the application effects of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0095] Please refer to the attached Figure 1-8 FIGURES, and the present invention will be further described in detail below with reference to the attached drawings and specific embodiments. Embodiment 1: Overall Architecture of the Dynamic Risk Prevention and Control System for Hazardous Chemical Transportation Routes Based on Spatio-Temporal Fusion

[0096] As Figure 1As shown in the figure, the dynamic risk prevention and control system for the transportation route of hazardous chemicals based on spatio-temporal fusion provided by the present invention includes a risk index quantification module 1, an environmental sensitivity analysis module 2, a risk diffusion prediction module 3, a road section risk assessment module 4, and a risk prevention and control decision-making module 5.

[0097] The risk index quantification module 1 is used to receive the hazardous chemical attribute parameters, calculate the leakage risk index, fire and explosion risk index, health hazard risk index, environmental pollution risk index, and reaction hazard risk index based on these parameters, and generate a multi-dimensional risk index matrix of hazardous chemicals. The hazardous chemical attribute parameters include physical state, chemical activity, toxicity level, explosiveness, ignition point, vapor pressure, water solubility, corrosiveness, reactivity, stability, volatility, carcinogenicity, teratogenicity, bioaccumulation, and environmental persistence.

[0098] The environmental sensitivity analysis module 2 is connected to the risk index quantification module 1, and is used to obtain environmental sensitive data, construct a grid spatio-temporal fusion model, calculate the environmental sensitivity index for each spatio-temporal grid, and establish a Bayesian spatio-temporal network prediction model based on historical data to predict the change of environmental sensitivity of each grid in the future period, and generate a spatio-temporal environmental sensitivity prediction matrix. The environmental sensitive data includes real-time meteorological data, geographic information data, population distribution data, and sensitive target data.

[0099] The risk diffusion prediction module 3 is connected to the risk index quantification module 1 and the environmental sensitivity analysis module 2, and is used to construct a multi-media migration model according to the multi-dimensional risk index matrix of hazardous chemicals and the spatio-temporal environmental sensitivity prediction matrix, preset a variety of leakage scenarios and conduct Monte Carlo risk propagation simulation, and generate a risk propagation probability cloud map.

[0100] The road section risk assessment module 4 is connected to the risk diffusion prediction module 3, and is used to receive road network data and discretize it into standard road sections, combine the multi-dimensional risk index matrix of hazardous chemicals, the spatio-temporal environmental sensitivity prediction matrix, and the risk propagation probability cloud map, calculate the dynamic risk score of each road section at different times, establish a collaborative risk factor assessment model, dynamically adjust the safety threshold based on historical accident data, and generate a spatio-temporal road network risk score matrix.

[0101] The risk prevention and control decision-making module 5 is connected to the road section risk assessment module 4, and is used to determine the warning level based on the comparison between the spatio-temporal road network risk score matrix and the safety threshold, select corresponding prevention and control measures according to different warning levels, execute multi-objective optimization decision-making to generate the optimal transportation route, generate an emergency response plan for high-risk road sections, and output a risk intelligent decision-making instruction set.

[0102] Each module is connected through a standardized data interface, supporting real-time data exchange and processing. The system adopts a distributed architecture, with the core algorithm deployed on a cloud server, and the data collection and early warning prompt functions deployed on in-vehicle terminal devices, realizing real-time data transmission and processing through 4G / 5G networks.

[0103] Embodiment 2: Specific implementation of the risk index quantification module

[0104] As Figure 2 shown, the risk index quantification module 1 includes a parameter characterization unit 11, a risk calculation unit 12, and a weight adjustment unit 13.

[0105] The parameter characterization unit 11 receives the hazardous chemical property parameters, standardizes these parameters, and uniformly converts each index into a scale of 0-10. For example, for the physical state, a solid is assigned a value of 1-3, a liquid is assigned a value of 4-7, and a gas is assigned a value of 8-10; for the flash point, it is linearly mapped to the 0-10 interval according to the actual temperature value, and the lower the flash point, the higher the assigned value. This standardization helps in the comparison and comprehensive evaluation of different property parameters.

[0106] The risk calculation unit 12 calculates five types of risk indices based on the standardized hazardous chemical property parameters:

[0107] The formula for the leakage risk index (LRI) is:

[0108] LRI = α1·P state +α2·P vapor +α3·P volatile +α4·P stability ,

[0109] where P state is the physical state parameter value, P vapor is the vapor pressure parameter value, P volatile is the volatility parameter value, P stability is the stability parameter value, and α1 to α4 are weight coefficients, and α1 + α2 + α3 + α4 = 1.

[0110] Similarly, the fire and explosion risk index (FERI), health hazard risk index (HHRI), environmental pollution risk index (EPRI), and reaction hazard risk index (RHRI) are also calculated through weighted calculation of corresponding parameters.

[0111] The weight adjustment unit 13 dynamically adjusts the weight coefficients according to different scenarios and calculates the comprehensive risk index CRI:

[0112] CRI = w1·LRI + w2·FERI + w3·HHRI + w4·EPRI + w5·RHRI,

[0113] Among them, w1 to w5 are weight coefficients, and w1 + w2 + w3 + w4 + w5 = 1. The weight coefficients will be dynamically adjusted according to environmental characteristics. For example, in densely populated areas, w3 is increased by 30%, in water source protection areas, w4 is increased by 40%, in transportation hubs, w2 is increased by 25%, on highway sections, w1 is increased by 20%, and in chemical industrial parks, w5 is increased by 35%.

[0114] Preferably, the risk index quantification module 1 further includes a data storage unit 14 for storing the attribute parameters of known hazardous chemicals and pre-calculated risk indexes to form a hazardous chemical risk knowledge base, supporting quick queries and risk comparisons.

[0115] Example 3: Specific implementation of the environmental sensitivity analysis module

[0116] As Figure 3 shown, the environmental sensitivity analysis module 2 includes a data access unit 21, a grid division unit 22, a sensitivity calculation unit 23, and a prediction modeling unit 24.

[0117] The data access unit 21 is responsible for obtaining and preprocessing multi-source environmental data, including real-time meteorological data (wind direction, wind speed, temperature, humidity, air pressure, precipitation, sampling frequency is 5 minutes / time), geographical information data (terrain elevation, water system distribution, vegetation coverage, soil type), population distribution data (permanent population density, floating population density, time period distribution characteristics), and sensitive target data (schools, hospitals, water sources, nature reserves, etc., including spatial coordinates and sensitive levels).

[0118] The grid division unit 22 divides the spatial area into standard grid cells of 100m × 100m and establishes a time matrix of 24 hours × 7 days on each grid to form a spatio-temporal grid data structure. This fine-grained spatio-temporal division helps to accurately capture the spatio-temporal variation characteristics of environmental sensitivity.

[0119] The sensitivity calculation unit 23 calculates the environmental sensitivity index ESI of each spatio-temporal grid:

[0120] ESI(x,y,t) = α·P(x,y,t) + β·W(x,y) + γ·S(x,y) + δ·M(x,y,t),

[0121] where P(x,y,t) is the population density index of the grid (x,y) at time t, W(x,y) is the water source sensitivity index of the grid (x,y), S(x,y) is the special sensitive target index of the grid (x,y), M(x,y,t) is the meteorological condition index of the grid (x,y) at time t, and α, β, γ, δ are weight coefficients and α + β + γ + δ = 1.

[0122] The prediction modeling unit 24 constructs a Bayesian network based on historical data to predict the environmental sensitivity changes of each grid within the next 24 hours. The establishment of the Bayesian network mainly considers factors such as time characteristics (hours, weekdays / weekends, seasons, etc.), historical environmental sensitivity, and weather forecast data, and realizes the prediction through conditional probability reasoning.

[0123] Preferably, the sensitivity calculation unit 23 also considers the time fluctuation factor. For example, during the peak commuting hours on weekdays, the weight of the population density index will increase accordingly; during rainy or snowy weather, the weight of the water source sensitivity index will increase accordingly. The prediction modeling unit 24 updates the prediction model using a sliding time window and updates the prediction results hourly to ensure the timeliness and accuracy of the prediction.

[0124] Example 4: Specific implementation of the risk diffusion prediction module

[0125] As Figure 4 shown, the risk diffusion prediction module 3 includes a migration model unit 31, a scenario presetting unit 32, and a Monte Carlo simulation unit 33.

[0126] The migration model unit 31 establishes migration and diffusion models for three media, namely the atmosphere, water body, and soil, based on the physical and chemical properties of hazardous chemicals and environmental conditions. For atmospheric diffusion, an improved Gaussian plume model is used; for water body diffusion, a two-dimensional convection-diffusion equation is used; and for soil infiltration, a model based on the Richards equation is used.

[0127] The scenario presetting unit 32 presets various leakage scenarios such as small leakage, medium leakage, large leakage, leakage accompanied by fire, and leakage accompanied by explosion according to the characteristics of hazardous chemicals and environmental conditions. For example, small leakage is defined as a leakage volume of 0 - 100 kg and a leakage rate of 0 - 5 kg / min; medium leakage is defined as a leakage volume of 100 - 1000 kg and a leakage rate of 5 - 50 kg / min; large leakage is defined as a leakage volume > 1000 kg and a leakage rate > 50 kg / min. Leakage accompanied by fire and leakage accompanied by explosion also consider the influence ranges of thermal radiation and shock waves.

[0128] The Monte Carlo simulation unit 33 conducts multiple Monte Carlo simulations for each leakage scenario based on the diffusion model under random meteorological conditions to generate a risk probability distribution cloud map. The simulation process first randomly generates a set of meteorological conditions that conform to the local meteorological characteristics, then calculates the diffusion concentration distribution, determines whether each grid unit exceeds the hazard threshold, calculates the number of affected people and the degree of environmental damage, and finally generates the risk probability distribution.

[0129] Preferably, to improve the simulation efficiency, the Monte Carlo simulation unit 33 adopts a stratified sampling strategy, focuses on sampling key parameters (such as wind direction and wind speed), and simultaneously uses parallel computing technology to accelerate the simulation process. For common hazardous chemicals, the system pre-computes and stores the risk propagation probability cloud map under standard conditions, and only parameter adjustment and rapid correction are required during actual application, greatly improving the response speed.

[0130] Example 5: Specific implementation of the migration model unit in the risk diffusion prediction module

[0131] As Figure 4 shown, the migration model unit 31 includes an atmospheric diffusion calculation sub-unit 311, a water body diffusion calculation sub-unit 312, and a soil penetration calculation sub-unit 313.

[0132] The atmospheric diffusion calculation sub-unit 311 uses an improved Gaussian plume model to calculate the diffusion concentration of hazardous chemicals in the atmosphere:

[0133]

[0134] Among them, C(x, y, z, t) represents the pollutant concentration at the point (x, y, z) at time t, Q is the source strength, σ y and σ z are the diffusion parameters in the horizontal and vertical directions respectively, which are related to the atmospheric stability and the distance from the source, u is the wind speed, H is the effective source height, x is the downwind distance, y is the crosswind distance, and z is the vertical height.

[0135] The water body diffusion calculation sub-unit 312 uses a two-dimensional convection-diffusion equation to calculate the migration process of hazardous chemicals in the water body:

[0136]

[0137] Among them, C is the pollutant concentration, t is the time, u and v are the flow velocities in the x and y directions respectively, D x and D y are the diffusion coefficients in the x and y directions respectively, and k is the degradation coefficient.

[0138] The soil penetration calculation sub-unit 313 simulates the penetration behavior of hazardous chemicals in the soil based on the Richards equation:

[0139]

[0140] Among them, θ is the soil water content, h is the soil water potential, K(h) is the unsaturated hydraulic conductivity function, z is the vertical coordinate, and S is the source-sink term.

[0141] Preferably, the atmospheric diffusion calculation takes into account the terrain influence and the building blocking effect, the water body diffusion calculation takes into account the river flow velocity change and the seasonal hydrological characteristics, and the soil infiltration calculation takes into account the influence of different soil types and the groundwater level. Each sub-unit adopts the adaptive grid meshing technology, and finer grids are used in the key areas to improve the calculation accuracy.

[0142] Embodiment 6: Specific implementation of the road section risk assessment module

[0143] As Figure 5 shown, the road section risk assessment module 4 includes a road section discretization unit 41, a risk scoring unit 42, a collaborative risk assessment unit 43, and a threshold adaption unit 44.

[0144] The road section discretization unit 41 receives the road network data and discretizes the road network into road sections with a standard length of 500m. For complex road structures such as overpasses and tunnels, flexible division is carried out according to the actual structural characteristics to ensure that each road section has relatively homogeneous characteristics.

[0145] The risk scoring unit 42 calculates the dynamic risk score RSI of each road section at different time periods:

[0146] RSI(r,t) = CRI·ESI(r,t)·IAF(r,t),

[0147] where CRI is the comprehensive risk index of hazardous chemicals, ESI(r,t) is the environmental sensitivity index of road section r at time t, and IAF(r,t) is the impact amplification factor, which is related to the traffic conditions and weather conditions of road section r at time t.

[0148] The collaborative risk assessment unit 43 evaluates the collaborative risk factor CRF of vehicle status, road conditions, driving behavior patterns, and hazardous chemical characteristics:

[0149] CRF = f(vehicle status, road conditions, driving behavior patterns, hazardous chemical characteristics),

[0150] The vehicle status includes parameters such as vehicle age, technical condition, loading ratio, tire wear degree, and braking system response time; the road conditions include parameters such as road surface type, friction coefficient, slope, curve radius, and road surface condition; the driving behavior patterns include parameters such as the frequency of rapid acceleration, the frequency of rapid braking, steering stability, and vehicle speed volatility.

[0151] The threshold adaption unit 44 dynamically adjusts the safety threshold according to historical accident data:

[0152] Threshold(t + 1) = Threshold(t) + η·[TargetSafety - CurrentSafety], where η is the learning rate, generally set to 0.05 - 0.1, TargetSafety is the target safety level set by regulatory requirements, and CurrentSafety is the current safety level calculated from the accident rate and approximate accident rate.

[0153] Preferably, the risk scoring unit 42 takes into account the time-varying characteristics of the road section, such as the impact of rain, snow, and other weather conditions on the road surface friction coefficient, and the impact of night on visibility, etc. The collaborative risk assessment unit 43 uses the fuzzy logic reasoning method to handle uncertain factors and improve the robustness of the assessment. The threshold adaptive unit 44 sets upper and lower limit constraints to ensure that the safety threshold is adjusted within a reasonable range.

[0154] Example 7: Specific implementation of the risk prevention and control decision-making module

[0155] As Figure 6 shown, the risk prevention and control decision-making module 5 includes a warning determination unit 51, a prevention and control measure unit 52, a multi-objective optimization unit 53, and a plan generation unit 54.

[0156] The warning determination unit 51 determines the warning level based on the comparison between the road section risk score and the safety threshold. If the road section risk score RSI is lower than the first threshold Threshold_1, it is determined to be the green (safe) level; if RSI is between the first threshold Threshold_1 and the second threshold Threshold_2, it is determined to be the yellow (attention) level; if RSI is between the second threshold Threshold_2 and the third threshold Threshold_3, it is determined to be the orange (warning) level; if RSI exceeds the third threshold Threshold_3, it is determined to be the red (dangerous) level.

[0157] The prevention and control measure unit 52 selects corresponding prevention and control measures from the prevention and control measure library according to the warning level. The prevention and control measures include driver operation suggestions (such as deceleration, avoidance, parking, etc.), vehicle parameter adjustments (such as maximum speed limit, maximum steering angular velocity, brake pressure adjustment, etc.), and route planning changes (such as whether to recommend changing the route, alternative route list, recommended departure time adjustment, etc.).

[0158] The multi-objective optimization unit 53 considers three objectives: safety, timeliness, and economy, and makes multi-objective optimization decisions for route planning:

[0159] minZ = [z1(x), z2(x), z3(x)],

[0160] Among them, z1(x) is the safety objective, reflecting the total path risk, z2(x) is the timeliness objective, reflecting the transportation time, and z3(x) is the economic objective, reflecting the transportation cost. The constraints include that the maximum road section risk score does not exceed the allowable risk threshold, the total transportation time does not exceed the maximum allowable transportation time, and the total transportation cost does not exceed the budget ceiling, etc.

[0161] The pre-plan generation unit 54 generates an emergency response pre-plan for high-risk road sections. The pre-plan generation process includes: identifying the set of high-risk road sections, extracting the environmentally sensitive points around the road sections, predicting the influence range based on the risk propagation model, generating evacuation routes and safe areas, calculating the location of the nearest emergency resources and the response time, and forming a structured pre-plan document.

[0162] Preferably, the early warning determination unit 51 can adjust the early warning trigger threshold according to factors such as the type of transportation vehicle and the driver's experience. The prevention and control measure unit 52 adopts a hierarchical progressive strategy, preferentially using mild intervention measures and upgrading to mandatory measures when necessary. The multi-objective optimization unit 53 uses an improved NSGA-II algorithm to solve the multi-objective optimization problem and improve the solution efficiency. The pre-plan generation unit 54 is connected to the emergency management department system to achieve automatic push and response of the pre-plan.

[0163] Embodiment 8: Specific implementation of the multi-objective optimization unit

[0164] As Figure 6 shown, the optimization function of the multi-objective optimization unit 53 is:

[0165] minZ = [z1(x), z2(x), z3(x)],

[0166] Among them, z1(x) is the safety objective, and its calculation formula is:

[0167]

[0168] z2(x) is the timeliness objective, and its calculation formula is:

[0169]

[0170] z3(x) is the economic objective, and its calculation formula is:

[0171]

[0172] Among them, RSI(r i , t i ) is the risk score of road section r i at time t i , L(r i ) is the length of road section r i , T(r i , ti ) is the travel time of road section r i at time t i , W(r i , t i ) is the waiting time of road section r i at time t i , F(r i ) is the fuel consumption rate C of road section r i t is the time cost, P(r i ) is the toll of road section r i max . n is the number of road sections included in the path.

[0173] The constraint conditions are:

[0174]

[0175] Among them, RSI max is the allowable risk threshold, T max is the maximum allowable transportation time, C max is the budget cap.

[0176] The multi-objective optimization unit 53 uses an improved NSGA-II algorithm to solve the multi-objective optimization problem. The algorithm process includes: initializing the population, non-dominated sorting, calculating the crowding distance, selection operation, crossover operation, mutation operation, merging the population, non-dominated sorting and crowding calculation again, and selecting the next generation population by the elitist retention strategy, and iterating until convergence or reaching the maximum number of iterations.

[0177] To improve the algorithm efficiency, adaptive crossover and mutation operations are adopted, and the crossover rate and mutation rate are dynamically adjusted according to the population diversity; a greedy strategy is used to generate the initial population to improve the quality of the initial solution; a local search strategy is used to optimize the non-dominated solution set to improve the quality of the solution.

[0178] Example 9: System data flow process

[0179] As Figure 1 shown, the data flow process between each module is:

[0180] The risk index quantification module 1 receives the hazardous chemical attribute parameters, generates a multi-dimensional risk index matrix of hazardous chemicals, and transmits it to the environmental sensitivity analysis module 2 and the risk diffusion prediction module 3. The multi-dimensional risk index matrix of hazardous chemicals contains five types of risk indexes and the comprehensive risk index of hazardous chemicals, and is stored in matrix form for quick access and processing by subsequent modules.

[0181] The environmental sensitivity analysis module 2 obtains environmental sensitive data, generates a spatio-temporal environmental sensitivity prediction matrix, and transmits it to the risk diffusion prediction module 3 and the road section risk assessment module 4. The spatio-temporal environmental sensitivity prediction matrix contains the environmental sensitivity indexes of each grid within the prediction period, which is stored in a three-dimensional array (x coordinate, y coordinate, time), supporting efficient spatio-temporal queries.

[0182] Based on the multi-dimensional risk index matrix of hazardous chemicals and the spatio-temporal environmental sensitivity prediction matrix, the risk diffusion prediction module 3 generates a risk propagation probability cloud map and transmits it to the road section risk assessment module 4. The risk propagation probability cloud map is stored in the form of a two-dimensional grid, and each grid cell contains probability values of different influence degrees, supporting spatial correlation analysis.

[0183] Combining the multi-dimensional risk index matrix of hazardous chemicals, the spatio-temporal environmental sensitivity prediction matrix and the risk propagation probability cloud map, the road section risk assessment module 4 generates a spatio-temporal road network risk score matrix and transmits it to the risk prevention and control decision-making module 5. The spatio-temporal road network risk score matrix contains the risk scores of each road section at different times, which is stored in the form of a two-dimensional table indexed by road section ID and time.

[0184] Based on the spatio-temporal road network risk score matrix, the risk prevention and control decision-making module 5 generates a risk intelligent decision-making instruction set, which is transmitted to the on-vehicle terminal and the monitoring center through the communication network. The risk intelligent decision-making instruction set adopts the structured JSON format and contains early warning information, prevention and control suggestions, path optimization schemes and emergency plans, etc.

[0185] During the data flow process, a distributed event-driven architecture is adopted to support real-time data processing and push. A caching mechanism is set for key data nodes to reduce calculation latency. The data transmission uses an encrypted channel to ensure data security. The entire system forms a closed-loop feedback mechanism, and the outputs of each module are used as the inputs of other modules, collaborating with each other to jointly improve the safety level of hazardous chemical transportation.

[0186] Embodiment 10: Dynamic risk prevention and control method for hazardous chemical transportation routes

[0187] As Figure 7 shown, the dynamic risk prevention and control method for hazardous chemical transportation routes of the present invention includes the following steps:

[0188] First, receive the attribute parameters of hazardous chemicals and calculate the multi-dimensional risk index matrix of hazardous chemicals. The system obtains 15 attribute parameters such as the physical state, chemical activity, and toxicity level of hazardous chemicals through the electronic waybill or manual input. After standardization processing, five types of risk indexes and a comprehensive risk index are calculated to form the multi-dimensional risk index matrix of hazardous chemicals.

[0189] Secondly, obtain environment-sensitive data, construct a grid-based spatio-temporal fusion model, and generate a spatio-temporal environmental sensitivity prediction matrix. The system obtains real-time meteorological data, geographical information data, population distribution data, and sensitive target data through an interface, divides the spatial area into standard grid cells, calculates the environmental sensitivity index of each spatio-temporal grid, and predicts the change in environmental sensitivity in future periods through a Bayesian network.

[0190] Then, based on the multi-dimensional risk index matrix of hazardous chemicals and the spatio-temporal environmental sensitivity prediction matrix, construct a multi-media migration model, conduct Monte Carlo risk propagation simulation, and generate a risk propagation probability cloud map. The system establishes migration and diffusion models for three media: atmosphere, water body, and soil, presets multiple leakage scenarios, conducts multiple Monte Carlo simulations, and generates a visual risk probability distribution.

[0191] Next, discretize the road network into standard road segments, and combine the multi-dimensional risk index matrix of hazardous chemicals, the spatio-temporal environmental sensitivity prediction matrix, and the risk propagation probability cloud map to calculate the spatio-temporal road network risk score matrix. The system calculates the dynamic risk score of each road segment at different times, considers the collaborative risk factors of vehicle status, road conditions, and driving behavior, and dynamically adjusts the safety threshold based on historical accident data.

[0192] Finally, based on the comparison between the spatio-temporal road network risk score matrix and the safety threshold, determine the warning level, select prevention and control measures, execute multi-objective optimization decision-making to generate the optimal transportation route, and output the intelligent risk decision instruction set. The system determines four warning levels: green, yellow, orange, or red according to the risk score, selects corresponding prevention and control measures, optimizes the route considering three objectives: safety, timeliness, and economy, and generates an emergency response plan for high-risk road segments.

[0193] The entire method forms a closed-loop control process, which reduces the safety risk during the transportation of hazardous chemicals through real-time data collection, dynamic risk assessment, and proactive prevention and control measures. The method adopts a modular design, and each step can be flexibly configured according to actual needs to adapt to different scales and types of hazardous chemical transportation scenarios.

[0194] To verify the effectiveness of the present invention, the liquid chlorine transportation task of a chemical enterprise is selected as an application case. The enterprise needs to transport 15 tons of liquid chlorine from the production plant to a user factory 300 kilometers away, and the transportation route passes through multiple towns and water source protection areas.

[0195] First, the system receives the property parameters of liquid chlorine: the physical state is liquefied gas (9 points), the chemical activity is 8 points, the toxicity level is 9 points, the explosiveness is 5 points, the ignition point is not applicable, the vapor pressure is 8 points, the water solubility is 7 points, the corrosiveness is 9 points, the reactivity is 8 points, the stability is 6 points, the volatility is 9 points, the carcinogenicity is no, the teratogenicity is no, the bioaccumulation is 3 points, and the environmental persistence is 5 points. The system calculates that the leakage risk index of liquid chlorine is 8.5, the fire and explosion risk index is 5.5, the health hazard risk index is 9.0, the environmental pollution risk index is 6.8, the reaction hazard risk index is 8.2, and the comprehensive risk index is 7.6.

[0196] Secondly, the system obtains the environmental sensitive data around the transportation route and constructs a grid-based spatio-temporal fusion model. Analysis reveals that the transportation route passes through two densely populated areas (with the largest pedestrian flow from 8-9 am and 5-6 pm respectively) and an important water source protection area. The system predicts the changes in environmental sensitivity of each grid within the next 24 hours and generates a spatio-temporal environmental sensitivity prediction matrix.

[0197] Then, based on the characteristics of liquid chlorine and environmental conditions, the system constructs a multi-media migration model, presets a medium-scale leakage scenario (leakage volume of 500 kg, leakage rate of 30 kg / min), and conducts 10,000 Monte Carlo simulations. The results show that under adverse meteorological conditions, the liquid chlorine leakage may affect the area within a radius of 3.2 kilometers, with a potential affected population of 21,000 people.

[0198] Next, the system discretizes the transportation route into 604 standard sections and calculates the dynamic risk scores of each section at different times by combining the risk index of liquid chlorine, environmental sensitivity, and risk propagation probability. Analysis finds that 28 sections have risk scores exceeding the safety threshold during specific time periods, and 12 of them are at the red warning level.

[0199] Finally, based on the risk score matrix, the system executes a multi-objective optimization decision to generate the optimal transportation route. The optimized route bypasses the peak hours of the densely populated areas, increasing the journey by 27 kilometers (an increase of 9%), but reducing the exposure time of high-risk sections by 62% and the potential affected population by 78%. The system also generates an emergency response plan for high-risk sections, including leakage disposal, personnel evacuation, and environmental protection measures, and shares it with the emergency departments along the route in advance.

[0200] As Figure 8 shown, comparing the traditional method and the method of the present invention, the traditional method mainly considers transportation distance and time while ignoring risk factors; the method of the present invention significantly reduces safety risks while appropriately increasing transportation time and cost. Practical applications show that this system can effectively improve the safety level of hazardous chemical transportation, reduce the accident rate and potential impact.

[0201] Although embodiments of the present invention have been shown and described, various changes, modifications, substitutions, and variations can be made to these embodiments by those of ordinary skill in the art without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the claims and their equivalents.

[0202] The foregoing are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A dynamic risk prevention and control system for the transportation route of hazardous chemicals based on spatio-temporal fusion, characterized in that, It includes: A risk index quantification module, which is used for: Receiving hazardous chemical property parameters, where the hazardous chemical property parameters include physical state, chemical activity, toxicity level, explosiveness, flash point, vapor pressure, water solubility, corrosiveness, reactivity, stability, volatility, carcinogenicity, teratogenicity, bioaccumulation, and environmental persistence; Based on the hazardous chemical property parameters, calculating a leakage risk index, a fire and explosion risk index, a health hazard risk index, an environmental pollution risk index, and a reaction hazard risk index; Generating a multi-dimensional risk index matrix of hazardous chemicals; An environmental sensitivity analysis module, connected to the risk index quantification module, which is used for: Obtaining environmental sensitive data, where the environmental sensitive data includes real-time meteorological data, geographic information data, population distribution data, and sensitive target data; Constructing a grid-based spatio-temporal fusion model and calculating the environmental sensitivity index for each spatio-temporal grid; Establishing a Bayesian spatio-temporal network prediction model based on historical data to predict the changes in environmental sensitivity of each grid in future time periods; Generating a spatio-temporal environmental sensitivity prediction matrix; A risk diffusion prediction module, connected to the risk index quantification module and the environmental sensitivity analysis module, which is used for: According to the multi-dimensional risk index matrix of hazardous chemicals and the spatio-temporal environmental sensitivity prediction matrix, constructing a multi-media migration model; Presetting multiple leakage scenarios and conducting Monte Carlo risk propagation simulations; Generating a risk propagation probability cloud map; A section risk assessment module, connected to the risk diffusion prediction module, which is used for: Receiving road network data and discretizing it into standard sections; Combining the multi-dimensional risk index matrix of hazardous chemicals, the spatio-temporal environmental sensitivity prediction matrix, and the risk propagation probability cloud map to calculate the dynamic risk score of each section at different time periods; Establishing a collaborative risk factor assessment model; Dynamically adjusting the safety threshold based on historical accident data; Generating a spatio-temporal road network risk score matrix; A risk prevention and control decision-making module, connected to the section risk assessment module, which is used for: Based on the comparison between the spatio-temporal road network risk score matrix and the safety threshold, determining the early warning level; According to different early warning levels, selecting corresponding prevention and control measures from the prevention and control measure library; Executing multi-objective optimization decision-making to generate the optimal transportation route; Generating an emergency response plan for high-risk sections; Outputting a risk intelligent decision-making instruction set.

2. The system according to claim 1, wherein The risk index quantification module includes: A parameter characterization unit, which is used to standardize the hazardous chemical property parameters into a scale of 0-10; A risk calculation unit, which is used to calculate five types of risk indices according to the standardized hazardous chemical property parameters; A weight adjustment unit, which is used to dynamically adjust the weight coefficients according to different scenarios and calculate the comprehensive risk index CRI: CRI = w1·LRI + w2·FERI + w3·HHRI + w4·EPRI + w5·RHRI, where LRI is the leakage risk index, FERI is the fire and explosion risk index, HHRI is the health hazard risk index, EPRI is the environmental pollution risk index, RHRI is the reaction hazard risk index, w1 to w5 are weight coefficients, and w1 + w2 + w3 + w4 + w5 = 1.

3. The system according to claim 1, wherein The environmental sensitivity analysis module includes: Data access unit, which is used to obtain and preprocess multi-source environmental data; Grid division unit, which is used to construct a standard grid unit of 100m×100m and establish a time matrix of 24 hours×7 days on each grid; Sensitivity calculation unit, which is used to calculate the environmental sensitivity index ESI of each spatio-temporal grid: ESI(x,y,t)=α·P(x,y,t)+δ·W(x,y)+γ·S(x,y)+δ·M(x,y,t), where P(x,y,t) is the population density index of grid (x,y) at time t, W(x,y) is the water source sensitivity index of grid (x,y), S(x,y) is the special sensitive target index of grid (x,y), M(x,y,t) is the meteorological condition index of grid (x,y) at time t, and α, β, γ, δ are weight coefficients and α+β+γ+δ=1; Prediction and modeling unit, which is used to construct a Bayesian network based on historical data and predict the change of environmental sensitivity of each grid within the next 24 hours.

4. The system according to claim 1, wherein The risk diffusion prediction module includes: Migration model unit, which is used to establish migration and diffusion models for three media of atmosphere, water body and soil; Scenario preset unit, which is used to preset various leakage scenarios such as small leakage, medium leakage, large leakage, leakage accompanied by fire and leakage accompanied by explosion according to the characteristics of hazardous chemicals and environmental conditions; Monte Carlo simulation unit, which is used to perform 10,000 Monte Carlo simulations for each leakage scenario to generate a risk probability distribution cloud map.

5. The system according to claim 4, characterized in that, The migration model unit includes: Atmospheric diffusion calculation sub-unit, which uses an improved Gaussian plume model to calculate the diffusion concentration of hazardous chemicals in the atmosphere; Water body diffusion calculation sub-unit, which uses a two-dimensional convection-diffusion equation to calculate the migration process of hazardous chemicals in the water body; Soil penetration calculation sub-unit, which simulates the penetration behavior of hazardous chemicals in the soil based on the Richards equation.

6. The system according to claim 1, wherein The road section risk assessment module includes: Road section discretization unit, which is used to discretize the road network into road sections with a standard length of 500m; Risk scoring unit, which is used to calculate the dynamic risk score RSI of each road section at different times: RSI(r,t)=CRI·ESI(r,t)·IAF(r,t), where CRI is the comprehensive risk index of hazardous chemicals, ESI(r,t) is the environmental sensitivity index of road section r at time t, and IAF(r,t) is the impact amplification factor; Collaborative risk assessment unit, which is used to assess the collaborative risk factors of vehicle status, road conditions, driving behavior patterns and hazardous chemical characteristics; Threshold adaptive unit, which is used to dynamically adjust the safety threshold according to historical accident data: Threshold(t+1)=Threshold(t)+η·[TargetSafety-CurrentSafety], where η is the learning rate, TargetSafety is the target safety level, and CurrentSafety is the current safety level.

7. The system according to claim 1, wherein The risk prevention and control decision-making module includes: Early warning determination unit, which is used to determine four early warning levels of green, yellow, orange or red based on the comparison between the road section risk score and the safety threshold; A prevention and control measure unit, which is used to select corresponding driver operation suggestions, vehicle parameter adjustments, and route planning change measures according to the warning level; A multi-objective optimization unit, which is used to consider three objectives of safety, timeliness, and economy, and make multi-objective optimization decisions for route planning; A pre-plan generation unit, which is used to generate emergency response pre-plans for high-risk sections.

8. The system according to claim 7, characterized in that, The optimization function of the multi-objective optimization unit is: minZ = [z1(x), z2(x), z3(x)], where z1(x) is the safety objective, reflecting the total risk of the route, z2(x) is the timeliness objective, reflecting the transportation time, and z3(x) is the economy objective, reflecting the transportation cost; The constraint conditions are: g1(x) = the maximum section risk score ≤ the allowable risk threshold, g2(x) = the total transportation time ≤ the maximum allowable transportation time, g3(x) = the total transportation cost ≤ the budget ceiling.

9. The system according to claim 1, characterized in that, The data flow process between each module is as follows: The multi-dimensional risk index matrix of hazardous chemicals generated by the risk quantification module is transmitted to the environmental sensitivity analysis module and the risk diffusion prediction module; The spatio-temporal environmental sensitivity prediction matrix generated by the environmental sensitivity analysis module is transmitted to the risk diffusion prediction module and the section risk assessment module; The risk propagation probability cloud map generated by the risk diffusion prediction module is transmitted to the section risk assessment module; The spatio-temporal road network risk score matrix generated by the section risk assessment module is transmitted to the risk prevention and control decision-making module; The risk intelligent decision-making instruction set of the risk prevention and control decision-making module is transmitted to the on-vehicle terminal and the monitoring center through the communication network.

10. The method corresponding to the dynamic risk prevention and control system for the transportation route of hazardous chemicals based on spatio-temporal fusion according to any one of claims 1-9, characterized in that, It includes the following steps: Receiving the attribute parameters of hazardous chemicals and calculating the multi-dimensional risk index matrix of hazardous chemicals; Obtaining environmental sensitive data, constructing a grid spatio-temporal fusion model, and generating a spatio-temporal environmental sensitivity prediction matrix; According to the multi-dimensional risk index matrix of hazardous chemicals and the spatio-temporal environmental sensitivity prediction matrix, constructing a multi-media migration model, conducting Monte Carlo risk propagation simulation, and generating a risk propagation probability cloud map; Discretizing the road network into standard sections, and combining the multi-dimensional risk index matrix of hazardous chemicals, the spatio-temporal environmental sensitivity prediction matrix, and the risk propagation probability cloud map to calculate the spatio-temporal road network risk score matrix; Based on the comparison between the spatio-temporal road network risk score matrix and the safety threshold, determining the warning level, selecting prevention and control measures, performing multi-objective optimization decisions to generate the optimal transportation route, and outputting the risk intelligent decision-making instruction set.

Images