A dangerous chemical goods transportation vehicle supervision method and system

Abstract

The application discloses a dangerous chemical goods transportation vehicle supervision method and system, and relates to the technical field of vehicle supervision.The method comprises the following steps: dividing the dangerous chemical area in the transportation vehicle, collecting the environmental data of the divided dangerous chemical area, and predicting the risk behavior of the dangerous chemical in the transportation process based on the environmental data; extracting the action behavior of the target group associated with the risk behavior of the dangerous chemical on the goods transportation path, respectively performing risk assessment on the action behavior of the target group, obtaining the risk assessment result of the target group, and the target group comprises pedestrians, motor vehicles and non-motor vehicles.In the process of optimizing the diffusion prediction model, the introduction of the time factor can enhance the dynamic adaptability of the model, ensure that the model can accurately predict the diffusion trend of the dangerous chemical in different time periods, and thus provide more stable and accurate prediction results.

Description

Technical Field

[0001] This invention relates to the field of vehicle monitoring technology, and more specifically, to a method and system for monitoring vehicles transporting hazardous chemicals. Background Technology

[0002] Hazardous chemicals are chemical substances that may cause significant harm to human health, the environment, or property during their production, transportation, storage, or use. These include substances with hazardous properties such as flammability, explosiveness, toxicity, corrosiveness, radioactivity, and oxidizing properties. If these substances leak, explode, fire, or otherwise cause accidents, they may cause immense harm to the surrounding environment and people, and are therefore classified as hazardous chemicals.

[0003] Because hazardous chemicals are flammable, explosive, toxic, and corrosive, leaks or accidents can cause serious environmental pollution and endanger the lives and safety of people around the transport vehicle, as well as public safety. Supervision is crucial to ensure the safe transport of hazardous chemicals and prevent accidents caused by vehicle malfunctions, improper operation, or external environmental factors. However, when hazardous chemicals encounter pedestrians or other vehicles during transport, or when accidents occur with other road users in densely trafficked areas, failure to consider the surrounding environment can hinder a rapid response or appropriate measures in case of leaks or other emergencies, thus increasing the probability and severity of accidents.

[0004] There are currently no effective solutions to the problems in the relevant technologies. Summary of the Invention

[0005] In view of the problems in related technologies, this invention proposes a method and system for supervising vehicles transporting hazardous chemicals, so as to overcome the above-mentioned technical problems existing in the existing related technologies.

[0006] Therefore, the specific technical solution adopted by the present invention is as follows: According to one aspect of the present invention, a method for supervising vehicles transporting hazardous chemicals is provided, the method comprising: The hazardous chemical areas in transport vehicles are divided, environmental data of the divided hazardous chemical areas are collected, and the risk behavior of hazardous chemicals during transportation is predicted based on the environmental data. Extract the actions and behaviors of the target group related to the risk behaviors of hazardous chemicals along the cargo transportation route, and conduct risk assessments on the actions and behaviors of the target group to obtain the risk assessment results of the target group; Based on the risk assessment results of the target group, develop control measures for transport vehicles and optimize the routes of transport vehicles in accordance with the control measures.

[0007] Preferably, the hazardous chemical area in the transport vehicle is divided, environmental data of the divided hazardous chemical area is collected, and the risk behavior of hazardous chemicals during transportation is predicted based on the environmental data, including: The internal area of ​​the transport vehicle is divided according to the characteristic parameters of the hazardous chemicals to obtain the divided hazardous chemical area. The system uses a cluster of sensors to collect environmental data from the divided hazardous chemical areas. Based on the environmental data, it determines whether there are any risky behaviors related to hazardous chemicals. If risky behaviors are found, the system proceeds to the next step; otherwise, it continues to monitor the environmental data. A diffusion prediction model is established based on environmental data to predict the dynamic diffusion behavior of hazardous chemicals during transportation. The diffusion prediction model is incorporated into a pre-built marker tree model, and environmental factors are introduced into the marker tree model to enable the diffusion prediction model to predict the dynamic diffusion behavior of hazardous chemicals under different environments.

[0008] Preferably, a diffusion prediction model is established based on environmental data, and the dynamic diffusion behavior of hazardous chemicals during transportation is predicted using the diffusion prediction model, including: Environmental measurement data is extracted to establish a diffusion prediction model for hazardous chemicals. The dynamic distribution of hazardous chemicals is output through the diffusion prediction model, and a Gaussian distribution is formed based on the dynamic distribution of hazardous chemicals. The quantity of hazardous chemicals in the divided hazardous chemical areas is determined. If the quantity of hazardous chemicals is greater than or equal to a preset threshold, the combined effect of several hazardous chemical source diffusion points is randomly superimposed based on the Gaussian distribution of the hazardous chemicals to obtain an optimized diffusion prediction model. Otherwise, the dynamic diffusion behavior of hazardous chemicals in the future time period is predicted through the diffusion prediction model. The diffusion coefficients between adjacent hazardous chemical sources are obtained by solving the optimized diffusion prediction model, and the average value of the diffusion coefficients is used as the parameters of the optimized diffusion prediction model. By introducing a time factor into the optimized diffusion prediction model parameters, a time-weighted diffusion prediction model is obtained and a stable diffusion field is output. The dynamic diffusion behavior of hazardous chemicals in future time periods is analyzed based on the stable diffusion field.

[0009] Preferably, the diffusion prediction model is incorporated into a pre-built marker tree model, and environmental factors are introduced into the marker tree model so that the diffusion prediction model can predict the dynamic diffusion behavior of hazardous chemicals under different environments, including: Using the characteristic parameters of hazardous chemicals as target variables, a predefined gradient boosting tree is used to train the target variables to obtain a trained label tree model. The environmental factors adapted to hazardous chemicals are then calculated using the label tree model. The output of the diffusion prediction model is extracted as the input of the labeling tree model, and the tree depth, minimum sample split, and maximum number of leaf nodes of the labeling tree model are adjusted in sequence to enable the diffusion prediction model to make dynamic predictions based on changes in environmental factors.

[0010] Preferably, the actions of the target group along the cargo transportation route that are associated with the risky behavior of hazardous chemicals are extracted, and risk assessments are performed on the actions of the target group respectively. The risk assessment results of the target group include: Spatial clustering algorithm is used to cluster the actions and behaviors of target groups along the cargo transportation route that are affected by the dynamic diffusion of hazardous chemicals, and the target groups include pedestrians, motor vehicles and non-motor vehicles; Identify high-risk areas along cargo transportation routes; A risk assessment model is established based on the actions and behaviors of the target group to assess the risk index when the actions and behaviors of the target group come into contact with high-risk areas; The risk index is compared with a preset risk threshold, and the risk level of the target group is divided according to the comparison results to obtain the risk assessment results of the target group.

[0011] Preferably, the actions of a target group along a cargo transportation route affected by the dynamic diffusion of hazardous chemicals are clustered using a spatial clustering algorithm, including: Identify the trajectory points along the cargo transportation route where the target group is affected by the dynamic diffusion behavior of hazardous chemicals, and calculate the number of points contained in the neighborhood of each trajectory point; The number of points is compared with the MinPts parameter. If the number of points in the neighborhood of the current trajectory point is greater than the MinPts parameter, the current trajectory point is considered a core point. All trajectory points in the neighborhood are then connected to the core point to form a clustering result. Otherwise, the current trajectory point is marked as an outlier and removed. The activity area of ​​the target group is calculated based on the time difference and distance difference between adjacent trajectory points in the same clustering result, and the action behavior of the target group is analyzed based on the time the target group stays in the same activity area.

[0012] Preferably, a risk assessment model is established based on the actions and behaviors of the target group to assess the risk index when the target group's actions and behaviors come into contact with high-risk areas, including: A single-agent risk assessment model is constructed based on pedestrian behavior, and the risk index of pedestrians coming into contact with hazardous chemicals when passing through high-risk areas is analyzed through the single-agent risk assessment model. A multi-agent risk assessment model is constructed based on the actions and behaviors of motor vehicles and non-motor vehicles. The risk index of motor vehicles and non-motor vehicles coming into contact with hazardous chemicals when passing through high-risk areas is analyzed through the multi-agent risk assessment model.

[0013] Preferably, a multi-agent risk assessment model is constructed based on the actions and behaviors of motor vehicles and non-motor vehicles. This model is then used to analyze the risk indices of contact between motor vehicles and non-motor vehicles and hazardous chemicals when they pass through high-risk areas. These indices include: Using motor vehicles and non-motor vehicles as participants, the payoff functions for motor vehicles and non-motor vehicles are calculated separately using a non-cooperative game strategy. Motor vehicles and non-motor vehicles are treated as intelligent agents, and a set of strategies for the intelligent agents is set. The payoff function of the intelligent agents is defined to construct a multi-agent risk assessment model. In the multi-agent risk assessment model, Nash equilibrium is used to select the best strategy for each intelligent agent from the set of strategies. A multi-agent risk assessment model is trained using reinforcement learning, enabling each agent to adopt the optimal strategy in high-risk areas. When adopting the optimal strategy, the risk index of the agent's contact with hazardous chemicals is calculated.

[0014] Preferably, the expression for the diffusion prediction model is: ; In the formula, C ( x , y , t ) represents the functional form of the diffusion prediction model; Q Indicates the source intensity of the released hazardous chemicals; s x and s y They represent horizontal directions respectively. x and longitudinal y The diffusion coefficient; x 0, y 0) indicates the coordinates of the hazardous chemical diffusion source; exp This represents an exponential function.

[0015] According to another aspect of the present invention, a monitoring system for vehicles transporting hazardous chemicals is also provided, the system comprising: The hazardous chemicals risk prediction module is used to divide the hazardous chemicals area in the transport vehicle, collect environmental data of the divided hazardous chemicals area, and predict the risk behavior of hazardous chemicals during the transportation process based on the environmental data. The transport vehicle route analysis module is used to extract the actions and behaviors of the target group and the hazardous chemicals along the cargo transport route, and to conduct risk assessments on the actions and behaviors of the target group to obtain the risk assessment results of the target group. The transport vehicle management module is used to formulate transport vehicle management measures based on the risk assessment results of the target group, and to optimize the transport vehicle routes in accordance with the management measures.

[0016] The beneficial effects of this invention are as follows: 1. The diffusion prediction model based on environmental data in this invention can simulate the dynamic diffusion behavior of hazardous chemicals during transportation by collecting environmental parameters in real time, thereby better predicting possible leaks or diffusions during transportation, providing timely warnings of changes in dangerous areas, and adjusting emergency plans. In addition, the diffusion prediction model based on Gaussian distribution can predict the diffusion behavior of hazardous chemicals under different environments by simulating the diffusion path and concentration distribution of hazardous chemicals, further improving the accuracy of emergency response.

[0017] 2. In optimizing the diffusion prediction model, this invention introduces a time factor to enhance the model's dynamic adaptability, ensuring that the model can accurately predict the diffusion trend of hazardous chemicals in different time periods, thereby providing more stable and accurate prediction results. Furthermore, by combining the diffusion prediction model with a marker tree model, dynamic adjustments are made based on environmental factors, improving the model's flexibility and response capabilities. Through training and optimization, the marker tree model can provide personalized risk assessments based on the characteristics of hazardous chemicals and environmental conditions, thereby optimizing transportation route planning and emergency response strategies, and further reducing risks during transportation.

[0018] 3. This invention utilizes a spatial clustering algorithm to cluster the actions and behaviors of target groups along cargo transportation routes. This effectively identifies the specific behavioral patterns of different groups along the transportation routes and further analyzes the spatial distribution of these behaviors under the influence of the dynamic diffusion of hazardous chemicals. This not only helps to identify high-density activity areas of target groups but also reveals the dynamic risk exposure of groups, aiding in risk management at key locations. Furthermore, the risk assessment model built based on the actions and behaviors of target groups can accurately calculate the risk index of each target group when it comes into contact with high-risk areas, thus providing specific data support for risk control.

[0019] 4. This invention, through single-agent and multi-agent risk assessment models, can independently analyze the risk of hazardous chemical exposure for different participants (such as pedestrians, motor vehicles, and non-motor vehicles) when passing through high-risk areas. This ensures that the risk assessment for each group is targeted and personalized. This precise risk assessment helps identify the potential risks of specific groups at specific times and locations, enabling the implementation of effective control measures in advance to prevent accidents. At the same time, by combining game theory methods such as non-cooperative game theory and Nash equilibrium, the decision-making process of group behavior can be optimized, allowing different participants to make optimal decisions based on environmental changes and their own interests in high-risk areas, thereby minimizing the risk of exposure to hazardous chemicals. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a method for supervising vehicles transporting hazardous chemicals according to an embodiment of the present invention; Figure 2 This is a schematic diagram of a hazardous chemical cargo transport vehicle monitoring system according to an embodiment of the present invention.

[0022] In the picture: 1. Hazardous chemical risk prediction module; 2. Transport vehicle route analysis module; 3. Transport vehicle management module. Detailed Implementation

[0023] To further illustrate the various embodiments, the present invention provides accompanying drawings, which are part of the disclosure of the present invention. These drawings are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these drawings, those skilled in the art should be able to understand other possible implementation methods and the advantages of the present invention. The components in the drawings are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0024] According to embodiments of the present invention, a method and system for supervising vehicles transporting hazardous chemicals are provided.

[0025] The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments, such as... Figure 1 As shown, according to an embodiment of the present invention, a method for supervising vehicles transporting hazardous chemicals includes: S1. Divide the hazardous chemical areas in the transport vehicles, collect environmental data of the divided hazardous chemical areas, and predict the risk behavior of hazardous chemicals during transportation based on the environmental data.

[0026] This includes dividing the hazardous chemical transport vehicle into designated areas, collecting environmental data for these areas, and predicting the risk behavior of hazardous chemicals during transport based on this data. The internal area of ​​the transport vehicle is divided according to the characteristic parameters of the hazardous chemicals to obtain the divided hazardous chemical area.

[0027] It should be noted that the internal area of ​​the transport vehicle is divided according to the characteristic parameters of the hazardous chemicals. The resulting hazardous chemical area includes: Step 1: Collect and organize the characteristic parameters of hazardous chemicals: The characteristic parameters of hazardous chemicals typically include their physical properties, chemical properties, and hazardous characteristics. Collecting and organizing these parameters is crucial for delineating the internal areas of transport vehicles.

[0028] Physical properties: Density: The density of hazardous chemicals determines whether they require special containers or protective measures.

[0029] Boiling point and flash point: These affect the volatility and fire / explosion hazard of hazardous chemicals.

[0030] Odor and color: helpful for sensory monitoring and leak detection.

[0031] Viscosity: Affects the fluidity of liquids, which in turn affects container design and leak prevention.

[0032] Chemical properties: Corrosiveness: Some hazardous chemicals may corrode containers and other substances.

[0033] Reactivity: Hazardous chemicals may react with other substances, producing heat, gas, or explosion.

[0034] Volatility: Determines whether hazardous chemicals will evaporate into the air, increasing the risk of leakage or poisoning.

[0035] Hazardous characteristics: Toxicity: The degree of harm to humans or the environment.

[0036] Flammability or explosiveness: Flammable hazardous chemicals require special isolation areas.

[0037] Radioactivity: Requires a dedicated protected area and container.

[0038] Step 2: Divide the region according to the characteristic parameters: Based on the different characteristics of hazardous chemicals, the interior of transport vehicles should be rationally divided into zones of different hazard levels. The specific criteria for this division may include the following factors: Chemical reactivity: Separate highly reactive hazardous chemicals from other materials to avoid accidental reactions.

[0039] Fire and explosion hazards: Flammable and explosive hazardous chemicals should be isolated from other items and placed in a dedicated fire-prevention area.

[0040] Volatility: For highly volatile hazardous chemicals, sealed containers or areas should be provided, and appropriate ventilation systems should be installed.

[0041] Toxicity and Corrosivity: Designate special areas for substances with high toxicity and corrosivity, and equip them with appropriate protective facilities.

[0042] Regional division model: Safety isolation: Isolate according to the hazardous characteristics of hazardous chemicals to ensure that flammable, explosive, highly corrosive or highly reactive chemicals do not come into contact with each other.

[0043] Ventilation and temperature control: For volatile hazardous chemicals, a good ventilation system is required; for temperature-sensitive substances (such as cryogenic liquids), a temperature-controlled area is required.

[0044] Signage and warnings: Each zone should have clear signage and warnings indicating the types of hazardous chemicals stored in that zone and the corresponding safe operating requirements.

[0045] This involves dividing the interior areas of transport vehicles based on the characteristic parameters of hazardous chemicals, and utilizing clustering algorithms to effectively divide safe zones according to the characteristics of hazardous chemicals, ensuring that no dangerous cross-reactions occur during transportation. Specifically, this includes: Hazardous chemicals are classified into different clusters (regions) based on characteristic parameters (such as hazard, reactivity, density, volatility, etc.).

[0046] The number of clusters needs to be specified in advance, and the center of each cluster is determined by calculating the similarity in the feature space.

[0047] The system uses a cluster of sensors to collect environmental data from the designated hazardous chemical areas. Based on this data, it determines whether there are any risky activities related to hazardous chemicals. If risky activities are found, the system proceeds to the next step; otherwise, it continues to monitor the environmental data.

[0048] It should be noted that the use of sensor clusters to collect environmental data from the demarcated hazardous chemical areas, and the determination of whether hazardous chemical activities pose a risk based on this environmental data, includes: Step 1: Install a set of sensors in different areas of the transport vehicle to collect environmental data in real time. The type and function of these sensors should be selected according to the characteristics of the hazardous chemicals, specifically including: Temperature sensors: monitor temperature changes during transportation, especially since high temperatures may cause hazardous chemicals to volatilize or react.

[0049] Humidity sensor: For some hazardous chemicals (such as dust or gas), changes in humidity may affect their stability or trigger a reaction.

[0050] Gas sensors: used to monitor the concentration of toxic or flammable gases, such as ammonia, sulfur dioxide, methane, etc.

[0051] Pressure sensor: Monitors pressure changes inside the container during transportation to prevent leakage due to excessive pressure.

[0052] Volatile organic compounds (VOCs) sensors: used to detect signs of gas leaks, especially of volatile hazardous chemicals.

[0053] Fire detectors: monitor potential fire risks, especially in areas containing flammable or explosive materials.

[0054] Step 2: The data collected by the sensors needs to be preprocessed and analyzed in real time in order to identify potential risky behaviors in a timely manner. By utilizing machine learning models, rule engines, or threshold detection methods, sensor data can be analyzed in real time to identify abnormal changes in the environment, such as: If the temperature exceeds the predetermined threshold, it indicates an abnormality during transportation, which could lead to a dangerous reaction of certain hazardous chemicals.

[0055] If the gas concentration exceeds the safety standard, it indicates that there may be a leak.

[0056] If the pressure is too high or too low, there may be a risk of container rupture or leakage.

[0057] Rule-based models: Threshold rules are set based on different hazardous chemical characteristics (such as temperature, gas concentration, pressure, etc.). When sensor data exceeds these thresholds, it is judged as a risky behavior. For example: If the temperature exceeds the set threshold, it is determined that there may be a risk of overheating or chemical reaction.

[0058] If the gas concentration exceeds the set standard, it is determined that there is a risk of leakage or explosion.

[0059] Machine learning-based models: For example, using supervised learning models (such as decision trees and support vector machines) to train on historical data to build a more accurate risk prediction model, taking environmental data as input and outputting whether risky behavior exists.

[0060] A diffusion prediction model is established based on environmental data to predict the dynamic diffusion behavior of hazardous chemicals during transportation.

[0061] Among these, establishing a diffusion prediction model based on environmental data, and predicting the dynamic diffusion behavior of hazardous chemicals during transportation using this model, includes: Environmental measurement data is extracted to establish a diffusion prediction model for hazardous chemicals. The dynamic distribution of hazardous chemicals is output through the diffusion prediction model, and a Gaussian distribution is formed based on the dynamic distribution of hazardous chemicals.

[0062] The diffusion prediction model is a Gaussian distribution model, used to predict the diffusion behavior of hazardous chemicals. The mathematical expression for diffusion can generally be the Gaussian diffusion equation, which describes the spatial distribution of hazardous chemical gases under given conditions. The expression for the diffusion prediction model is as follows: ; In the formula, C ( x , y , t ) indicates the position ( x , y ) and time t The concentration of hazardous chemicals at the location; Q This indicates the source intensity of the released hazardous chemicals (i.e., the amount of hazardous chemicals released per unit time). s x and s y These represent the lateral and longitudinal diffusion coefficients, respectively, indicating the extent of diffusion; x 0, y 0) indicates the coordinates of the hazardous chemical diffusion source; exp This represents an exponential function, meaning the concentration decreases rapidly with increasing distance.

[0063] It should be noted that the Gaussian distribution model is used to obtain the dynamic spatial distribution of hazardous chemicals. In this model, the concentration of hazardous chemicals changes with time and spatial location. For example, suppose the initial source of the hazardous chemical is located at location ( x 0, y (0,0) = (0,0), and diffuses within a certain time interval, for example: Q =100g / s (source intensity, i.e., the amount of hazardous chemicals released per unit time).

[0064] s x =10m, s y =10m (diffusion coefficient, which determines the range of diffusion).

[0065] At this point, the concentration of hazardous chemicals at different locations can be predicted using the Gaussian diffusion equation. C ( x , y , t For example, in t At time 0, calculate the concentration of the hazardous chemical at a certain location. If the target location is ( x =5, y =5), substitute into the diffusion prediction model; ; This gives the concentration value at point (5,5).

[0066] The quantity of hazardous chemicals in the divided hazardous chemical areas is determined. If the quantity of hazardous chemicals is greater than or equal to a preset threshold, the combined effect of several hazardous chemical source diffusion points is randomly superimposed based on the Gaussian distribution of the hazardous chemicals to obtain an optimized diffusion prediction model. Otherwise, the dynamic diffusion behavior of hazardous chemicals in the future time period is predicted through the diffusion prediction model.

[0067] It should be noted that if the quantity of hazardous chemicals is greater than or equal to the threshold, an optimized diffusion prediction model is obtained by randomly superimposing the combined effects of several hazardous chemical source diffusion points according to the Gaussian distribution pattern.

[0068] The overall diffusion effect is obtained by superimposing the Gaussian distributions of multiple hazardous chemical sources. Assume there are... n The diffusion of several hazardous chemical sources can be represented as the sum of multiple Gaussian distributions: ; In the formula, This represents an optimized diffusion prediction model; i Indicates the first i One dangerous object; n This indicates a source of hazardous chemicals.

[0069] The diffusion coefficients between adjacent hazardous chemical sources are obtained by solving the optimized diffusion prediction model, and the average value of the diffusion coefficients is used as the parameters of the optimized diffusion prediction model. By introducing a time factor into the optimized diffusion prediction model parameters, a time-weighted diffusion prediction model is obtained and a stable diffusion field is output. The dynamic diffusion behavior of hazardous chemicals in future time periods is analyzed based on the stable diffusion field.

[0070] It should be noted that by introducing a time factor into the optimized diffusion prediction model parameters, a time-weighted diffusion prediction model is obtained, which outputs a stable diffusion field. The dynamic diffusion behavior of hazardous chemicals over future time periods is analyzed based on this stable diffusion field, including: Step 1: Introduce the time factor into the diffusion prediction model: The diffusion process is significantly affected by time, especially under changing environmental conditions (such as wind speed, temperature, and humidity), where diffusion behavior changes over time. Therefore, a time factor should be incorporated into diffusion models to ensure that the models reflect changes in hazardous chemical concentrations over time.

[0071] Based on the original Gaussian diffusion model, a time factor is added to describe the dynamic changes in the diffusion process. Assume the source of diffusion is ( x 0, y 0), the release intensity of the source is Q In time t The subsequent concentration distribution can be expressed as: ; In the formula,f ( t This indicates the introduction of a time factor, representing the change in diffusion behavior over time. Time factor f ( t It may be affected by environmental changes and can usually be designed in the following forms: Exponential decay factor: f ( t )= exp (- λt ),in l It is a decay constant, representing the rate at which the concentration decreases over time during the diffusion process; a larger value indicates a lower concentration. l This indicates a relatively fast diffusion rate and a rapid concentration decay.

[0072] Linear factor: f ( t )=1+ αt ,in α It is a constant, representing the linear increase in concentration over time during the diffusion process.

[0073] Environmental adjustment factors: can be adjusted based on real-time environmental data (such as wind speed, temperature, and humidity). f ( t For example, in cases of high wind speed, the diffusion rate may be faster, therefore f ( t It can change with wind speed.

[0074] Step 2: Calculate the time-weighted diffusion field: The time-weighted diffusion field represents the dynamic spatial distribution of hazardous chemical concentrations over time. To obtain a stable diffusion field, integration or averaging over time can be performed to obtain the steady state reached by the system after long-term operation.

[0075] Calculation of the stable diffusion field: A stable diffusion field can be solved using a time-weighted diffusion model over a time period. T Within this process, the diffusion field at each time step is calculated and weighted averaged to obtain the concentration distribution under steady-state conditions, expressed as: ; In the formula, C stable(x,y) Represents a stable diffusion field over a time period T The average concentration distribution within a given time period is calculated by weighting the concentration distribution at each time point, thus obtaining the steady state over a long period.

[0076] If the time factor decays exponentially, the integral result will focus on the recent time period, reflecting the rapid changes in the diffusion process.

[0077] If the time factor increases linearly, it may indicate that the concentration gradually increases during the diffusion process, reflecting the continuous release from certain sources.

[0078] Step 3: Stable diffusion field analysis and prediction of future diffusion behavior: After obtaining the stable diffusion field, the dynamic diffusion behavior of hazardous chemicals in the future can be predicted using this field. The stable diffusion field provides a concentration distribution map under long-term steady-state conditions, which can be used to analyze potential future risks. The stable diffusion field can be analyzed in the following ways: High-concentration area identification: Based on the stable diffusion field, areas with high concentrations of hazardous chemicals are identified, which may represent high-risk areas.

[0079] Diffusion direction and velocity: By stabilizing the diffusion field, we can understand the main direction and velocity of hazardous chemical diffusion. This helps in determining the diffusion range and potential impact area.

[0080] Dynamic change trend: If the diffusion source changes (such as an increase in intensity or a change in location), the future diffusion behavior can be predicted based on the changing trend of the stable diffusion field.

[0081] Predictions of diffusion behavior in the future: Based on a stable diffusion field and a time-weighted diffusion model, the diffusion of hazardous chemicals over a future period can be predicted. This assumes that the stable diffusion field at the current moment is already obtained. C stable(x,y) Therefore, we can extrapolate the concentration distribution at future times based on this field.

[0082] If significant changes in future weather conditions are anticipated (such as increased wind speed), an adjusted time factor can be used based on a stable diffusion field. f ( t The concentration at future moments is updated.

[0083] Assume the current time is t =0, the stable diffusion field is C stable(x,y) If the wind speed is expected to increase within the next hour, then the impact of the increased wind speed can be reflected in the time factor. f ( t In this context, the diffusion model is adjusted to predict the concentration distribution of hazardous chemicals one hour later. The expression for this prediction is: ; In the formula, f ( t +1) indicates the time factor adjusted according to changes in wind speed.

[0084] The diffusion prediction model is incorporated into a pre-built marker tree model, and environmental factors are introduced into the marker tree model to enable the diffusion prediction model to predict the dynamic diffusion behavior of hazardous chemicals under different environments.

[0085] Specifically, the diffusion prediction model is incorporated into a pre-built marker tree model, and environmental factors are introduced into the marker tree model to enable the diffusion prediction model to predict the dynamic diffusion behavior of hazardous chemicals under different environments, including: Using the characteristic parameters of hazardous chemicals as target variables, a predefined gradient boosting tree is used to train the target variables to obtain a trained label tree model. The environmental factors adapted to hazardous chemicals are then calculated using the label tree model. The output of the diffusion prediction model is extracted as the input of the labeling tree model, and the tree depth, minimum sample split, and maximum number of leaf nodes of the labeling tree model are adjusted in sequence to enable the diffusion prediction model to make dynamic predictions based on changes in environmental factors.

[0086] It should be noted that the diffusion prediction model is incorporated into a pre-built marker tree model, and environmental factors are included in the marker tree model. This allows the diffusion prediction model to predict the dynamic diffusion behavior of hazardous chemicals under different environments in practical applications, including: In this task, the objective is to use the characteristic parameters of hazardous chemicals (such as hazard and reactivity) as target variables, train the target variables using Gradient Boosting Trees (GBT), and calculate environmental factors adapted to hazardous chemicals using the trained labeled tree model. Then, the output of the diffusion prediction model is used as input, and by adjusting the model's hyperparameters (tree depth, minimum sample split, maximum number of leaf nodes, etc.), the diffusion prediction model can dynamically predict based on changes in environmental factors. Specifically, this includes: Step 1: Train a gradient boosting tree model based on the characteristic parameters of hazardous chemicals: Gradient Boosting Tree (GBT) is an ensemble learning method that improves the predictive performance of a model by constructing a series of decision trees and progressively optimizing each tree. GBT is commonly used for regression and classification tasks.

[0087] 1. Target variable selection: Choose the characteristic parameters of hazardous chemicals as the target variable, for example: The volatility of hazardous chemicals (such as vapor pressure, temperature sensitivity, etc.).

[0088] The reactivity of hazardous chemicals (e.g., reaction rate, chemical stability, etc.).

[0089] The toxicity of hazardous chemicals (such as LD50 value, or related biological effects, etc.).

[0090] The explosiveness or flammability of hazardous chemicals.

[0091] Select one or more characteristic parameters as target variables according to actual needs. Each characteristic parameter will be used as the output of the GBT model.

[0092] 2. Feature selection: Feature data can come from various sensor data, historical records, environmental data (such as wind speed, temperature, humidity, etc.), and other factors during the storage / transportation of hazardous chemicals. Input features include: Environmental parameters: such as temperature, humidity, air pressure, etc.; Physicochemical properties: such as density, solubility, etc.; Storage / transportation conditions: such as container type, container sealing, and the possibility of chemical reactions.

[0093] 3. Training gradient boosting tree models includes: Initialize the model: Initialize using the mean of the training data or a simple model.

[0094] Iterative training: In each iteration, a new tree is trained with the goal of minimizing the error between the current model and the actual value (optimized through gradient descent).

[0095] Update the model: By weighting each new tree, the model's prediction results are gradually optimized.

[0096] During training, loss functions such as mean squared error (MSE) or log loss (Log Loss) are typically used.

[0097] 4. Output the labeled tree model: After training, a labeled tree model (GBDT model) is obtained. This model uses characteristic parameters as target variables and predicts the characteristic parameters of hazardous chemicals based on different environmental factors (input features). This model will be used as input for the diffusion prediction model in subsequent steps.

[0098] Step 2: Extract the output of the diffusion prediction model as input features: The output of a diffusion prediction model can be used to obtain the spatial concentration distribution of hazardous chemicals through a Gaussian distribution model or other diffusion models. The diffusion prediction model generates a dynamic hazardous chemical concentration field based on changes in environmental factors (such as temperature, wind speed, and humidity).

[0099] 1. Output of diffusion prediction model: Spatial distribution: Hazardous chemical concentration values ​​at various locations.

[0100] Changes over time: How the concentration of hazardous chemicals will change at some point in the future.

[0101] Risk assessment: Based on the diffusion model, assess the potential risks in different regions and predict potentially high-risk areas.

[0102] These outputs will serve as input to the gradient boosting tree model, influencing the prediction of hazardous chemical characteristic parameters.

[0103] 2. Input features of the model: Environmental factors: such as temperature, humidity, wind speed, air pressure, etc.

[0104] Output of the diffusion model: Concentration values ​​of hazardous chemicals at different locations and time points.

[0105] Spatial information: the main direction, speed, and path of hazardous chemical diffusion.

[0106] 3. Adjust the hyperparameters of the marker tree model: In order for the diffusion prediction model to make dynamic predictions based on changes in environmental factors, the hyperparameters of the marker tree model need to be adjusted to ensure that the prediction results can be adjusted according to actual environmental changes.

[0107] 3.1 Adjusting Tree Depth: Tree depth determines the complexity of the model. Deeper trees can capture more complex relationships between features, but may also lead to overfitting. Shallower trees may not be able to fully learn the patterns in the data. Tree depth needs to be selected based on the complexity of the data.

[0108] A deeper tree can capture more complex patterns and is suitable for data with strong non-linear relationships.

[0109] Smaller tree depth: reduces model complexity, prevents overfitting, and is suitable for linear relationships between features and targets.

[0110] 3.2 Minimum Samples Split: Minimum sample split is a parameter that controls the minimum number of samples for each node. Before a node splits, at least this number of samples must be available to continue splitting. Adjusting this parameter can prevent the model from learning noisy data during training.

[0111] Increasing the minimum number of sample splits reduces the complexity of the tree and prevents overfitting.

[0112] Reducing the minimum number of sample splits can improve the model's fitting ability, but may lead to overfitting.

[0113] 3.3 Maximum number of leaf nodes: The maximum number of leaf nodes determines the maximum number of leaf nodes a tree can have. A larger number of leaf nodes enhances the predictive power of the tree, but may also lead to overfitting of the model.

[0114] Increasing the number of leaf nodes can increase the complexity and accuracy of the model, but may lead to overfitting.

[0115] Reducing the number of leaf nodes can help prevent overfitting, but it may also reduce the model's performance.

[0116] Step 4: Dynamic Prediction and Model Application Once a labeled tree model is trained using gradient boosting trees and the hyperparameters (tree depth, minimum sample split, maximum number of leaf nodes, etc.) are adjusted, the model can be applied to dynamic prediction in hazardous chemical diffusion prediction, which specifically includes: The real-time diffusion prediction model output data (such as hazardous chemical concentration distribution and risk assessment) is used as the input features of the label tree; based on updated environmental factors (such as wind speed, temperature changes, etc.), the model will dynamically predict changes in hazardous chemical characteristics (such as concentration, reactivity, etc.).

[0117] S2. Extract the actions and behaviors of the target group related to the risk behaviors of hazardous chemicals along the cargo transportation route, and conduct risk assessments on the actions and behaviors of the target group to obtain the risk assessment results of the target group.

[0118] This involves extracting the actions and behaviors of the target group related to the risky activities of hazardous chemicals along the cargo transportation route, and conducting risk assessments on these actions and behaviors to obtain the following risk assessment results for the target group: Spatial clustering algorithm is used to cluster the actions of target groups along the cargo transportation route affected by the dynamic diffusion of hazardous chemicals, and the target groups include pedestrians, motor vehicles and non-motor vehicles.

[0119] Among them, the actions of target groups along cargo transportation routes affected by the dynamic diffusion of hazardous chemicals, which are clustered using spatial clustering algorithms, include: Identify the trajectory points along the cargo transportation route where the target group is affected by the dynamic diffusion behavior of hazardous chemicals, and calculate the number of points contained in the neighborhood of each trajectory point; The number of points is compared with the MinPts parameter. If the number of points in the neighborhood of the current trajectory point is greater than the MinPts parameter, the current trajectory point is considered a core point. All trajectory points in the neighborhood are then connected to the core point to form a clustering result. Otherwise, the current trajectory point is marked as an outlier and removed. The activity area of ​​the target group is calculated based on the time difference and distance difference between adjacent trajectory points in the same clustering result, and the action behavior of the target group is analyzed based on the time the target group stays in the same activity area.

[0120] It should be noted that the spatial clustering algorithm used is the DBSCAN clustering algorithm. Using DBSCAN to cluster the actions and behaviors of target groups along cargo transportation routes affected by the dynamic diffusion of hazardous chemicals can effectively classify the behavior of target groups into different categories and identify which behaviors are affected by the diffusion of hazardous chemicals. This is of great significance for analyzing the reactions of various groups during the transportation of hazardous materials, predicting potential safety risks, and taking effective emergency response measures.

[0121] Identify high-risk areas along cargo transportation routes.

[0122] It should be noted that using GIS software for spatial correlation analysis to determine the relationship between hazardous chemical diffusion areas and transportation routes, and to identify high-risk areas along cargo transportation routes, includes: By importing hazardous chemical diffusion and transportation route data into GIS software, the diffusion data can be modeled using meteorological data, topographic features, and the physicochemical properties of the hazardous chemicals to obtain the spatial distribution of their concentrations. Transportation route data includes the roads, routes, and traffic information used by transport vehicles. Spatial analysis tools can be used to spatially overlay hazardous chemical diffusion areas with transportation routes, identifying which routes traverse or approach areas with high concentrations of hazardous chemicals. Secondly, by combining the diffusion patterns of hazardous chemicals with traffic flow, buffer zone analysis is performed. This involves establishing buffer zones around the hazardous chemical diffusion areas and assessing the overlap of transportation routes within these buffer zones to identify high-risk areas.

[0123] A risk assessment model is established based on the actions and behaviors of the target group to evaluate the risk index when the actions and behaviors of the target group come into contact with high-risk areas.

[0124] It should be noted that the risk index for pedestrians differs from that for motor vehicles and non-motor vehicles in the following ways: Pedestrians: The risk index is relatively high because pedestrians have a longer exposure time in high-risk areas and may be more likely to come into contact with hazardous chemicals due to their slow speed; at the same time, pedestrians have a strong ability to avoid danger, but they are exposed for a longer time when they are standing still or walking slowly.

[0125] Motor vehicles: The risk index is relatively low because motor vehicles travel through high-risk areas at high speeds and have shorter exposure times; however, the poor air circulation and enclosed nature of motor vehicles may lead to the risk of occupants being exposed to hazardous chemicals.

[0126] Non-motorized vehicles: The risk index is between that of pedestrians and motorized vehicles. They have moderate speeds and short exposure times, but they have strong risk avoidance capabilities and can easily avoid direct contact with high-risk areas.

[0127] The difference between constructing a single-agent model (single-agent risk assessment model) and a multi-agent game model (multi-agent risk assessment model) based on the above distinctions lies in: Single-agent model: The decision-making process is relatively simple, mainly considering the agent's own risk exposure and optimal action. Each agent makes decisions independently, and risk assessment is based on its own behavior and the environment.

[0128] Multi-agent game theory models: The decision-making process is more complex, as each agent must consider not only its own risks and rewards but also the behavior of other agents. Game theory comes into play here, and agents may compete, cooperate, or coordinate with each other. For example, how do multiple pedestrians choose the best evacuation route in the same danger zone to avoid collisions or congestion in certain areas?

[0129] Among them, a risk assessment model is established based on the actions and behaviors of the target group to assess the risk index when the target group's actions and behaviors come into contact with high-risk areas, including: A single-agent risk assessment model is constructed based on pedestrian behavior, and the risk index of pedestrians coming into contact with hazardous chemicals when passing through high-risk areas is analyzed using the single-agent risk assessment model.

[0130] It should be noted that a single-agent risk assessment model is constructed based on pedestrian behavior, and the risk index of pedestrians coming into contact with hazardous chemicals when passing through high-risk areas is analyzed using this model. This includes: In single-agent models, pedestrian behavior typically needs to be modeled through state space and decision-making mechanisms. Key elements for constructing the model based on pedestrian movement and reactions include: State space: describes the current state of a pedestrian, including position, velocity, acceleration, and behavior pattern.

[0131] Action space: Defines the actions that pedestrians may take (e.g., walking, running, stopping, dodging, avoiding high-concentration areas, etc.).

[0132] Reward function: Assigns a "reward" to each action, assessing whether the pedestrian's action reduces or increases risk. For example, the reward for evasive behavior in a high-concentration area is higher.

[0133] The construction of a single-agent risk assessment model includes: Hazardous area identification: Based on the output of hazardous chemical diffusion models, determine the extent and concentration of hazardous chemicals in high-risk areas. For example, use a Gaussian diffusion model to predict the concentration of hazardous chemicals at certain points or in certain areas and identify areas that exceed safety thresholds.

[0134] Risk Index Calculation: The risk index can be calculated by assessing the probability and concentration of pedestrian exposure to hazardous chemicals. It calculates the likelihood and severity of pedestrian exposure when they pass through a certain area. For example: Contact probability: The contact probability is calculated by the overlap between the pedestrian's location and the high-risk area.

[0135] Concentration Impact: Based on the concentration of hazardous chemicals, assess the risk of pedestrian exposure at that concentration. For example, exposure to high concentration areas may increase the risk of poisoning. The risk index can be calculated using the following formula: ; In the formula, R i pedestrian i The risk index; P contact This indicates the probability of a pedestrian coming into contact with hazardous chemicals; C conc This indicates the concentration of hazardous chemicals in the area; W area The weight of a region can be its hazard level or other relevant factors.

[0136] A multi-agent risk assessment model is constructed based on the actions and behaviors of motor vehicles and non-motor vehicles. The risk index of motor vehicles and non-motor vehicles coming into contact with hazardous chemicals when passing through high-risk areas is analyzed through the multi-agent risk assessment model.

[0137] Among them, a multi-agent risk assessment model is constructed based on the actions and behaviors of motor vehicles and non-motor vehicles. This model is then used to analyze the risk indices of contact between motor vehicles and non-motor vehicles and hazardous chemicals when they pass through high-risk areas. These indices include: Using motor vehicles and non-motor vehicles as participants, the payoff functions for motor vehicles and non-motor vehicles are calculated separately using a non-cooperative game strategy. Motor vehicles and non-motor vehicles are treated as intelligent agents, and a set of strategies for the intelligent agents is set. The payoff function of the intelligent agents is defined to construct a multi-agent risk assessment model. In the multi-agent risk assessment model, Nash equilibrium is used to select the best strategy for each intelligent agent from the set of strategies. A multi-agent risk assessment model is trained using reinforcement learning, enabling each agent to adopt the optimal strategy in high-risk areas. When adopting the optimal strategy, the risk index of the agent's contact with hazardous chemicals is calculated.

[0138] The risk index is compared with a preset risk threshold, and the risk level of the target group is divided according to the comparison results to obtain the risk assessment results of the target group.

[0139] It should be noted that the multi-agent risk assessment model is constructed based on the actions and behaviors of motor vehicles and non-motor vehicles. The analysis of the risk indices of motor vehicles and non-motor vehicles coming into contact with hazardous chemicals when passing through high-risk areas using this model includes, in practical applications: It should be noted that developing control measures for transport vehicles based on the risk assessment results of the target group, and optimizing transport vehicle routes in accordance with these control measures, includes: Step 1: Establish a non-cooperative game model and calculate the payoff functions for motor vehicles and non-motor vehicles: In high-risk areas, motor vehicles and non-motor vehicles may compete for the optimal path or adopt different strategies to reduce risk. This competitive relationship can be modeled using non-cooperative game theory.

[0140] 1. Participants (Agents): Intelligent agent 1: Motor vehicles (such as cars and trucks); Agent 2: Non-motorized vehicles (such as bicycles, motorcycles, and electric vehicles); 2. Strategy Space: Each agent has different available strategies: Motor vehicle strategy set S m : Quick Pass: Speed ​​up the passage through high-risk areas; Slow down: Pass through at a reduced speed; Detour: Avoid high-risk areas; Stop and wait: Wait for the concentration of hazardous chemicals to decrease before proceeding; Non-motorized vehicle strategy set S n : Quick Pass: Speed ​​up the passage through high-risk areas; Slow down: Pass through at a reduced speed; Detour: Avoid high-risk areas; Stop and wait: Wait for the concentration of hazardous chemicals to decrease before proceeding; 3. Calculation of the payoff function: The agent's reward function U The following factors need to be considered: Efficiency: Faster passage yields higher returns, while slower or stagnant passage yields lower returns.

[0141] Safety: Higher risk of exposure to hazardous chemicals reduces profits.

[0142] Collision risk: Non-motorized vehicles may collide with motorized vehicles.

[0143] For example: P contactThe probability of an agent being exposed to hazardous chemicals in this area. R collision The probability of an agent colliding with another agent. T pass Time taken by the agent to travel through the region α , β , c As a weighting factor; Then you will get: U m = U n = α (1- P contact )+ β (1- R collision )- γT pass ; In the formula, the benefits of different strategies will vary depending on the concentration of hazardous chemicals, traffic conditions, and mode of transportation.

[0144] Step 2: Construct a multi-agent risk assessment model: In a multi-agent environment, the optimal policy combination is found so that each agent can pass through the high-risk zone with minimal risk. The optimal policy choice of the agents is analyzed by using Nash equilibrium.

[0145] 1. Define the policy set of the agent: Strategy set: S ={ S m , S n},in: Motor vehicle strategy set S m ; Non-motorized vehicle strategy set S n ; In a game theory framework, each agent aims to minimize its own risk while maximizing passage efficiency, while other agents will also try to optimize their own strategies.

[0146] 2. Calculate the Nash equilibrium: ; ; In the formula, when all agents choose the optimal strategy... After that, no agent can gain higher returns by changing its strategy.

[0147] 3. Solve for Nash equilibrium: The strategy choices and payoffs of agents are represented using game theory matrices, and the optimal strategy combination is found using game theory solutions (such as min-max optimization or mixed-strategy Nash equilibrium).

[0148] Step 3: Optimize strategies using reinforcement learning: Due to the complexity of the environment, multi-agent reinforcement learning (MARL) is used to optimize the agent's policy selection, enabling it to adaptively make optimal decisions. Specifically, this includes: Input: Current environmental conditions (concentration of hazardous chemicals, traffic flow, driving speed).

[0149] Actions: Different strategy choices (fast passage, slow movement, detour, wait).

[0150] award: R = U m + U n Those who are less exposed to hazardous chemical areas and have fewer conflicts with other agents will receive higher rewards.

[0151] Step 4: Calculate the agent's risk index: The trained model can be used to evaluate the risk index of an agent, and its expression is: R index = P contact × C conc ; In the formula, R index This represents the risk index of the intelligent agent; P contact This represents the probability of interaction between the agent and the hazardous materials area. C conc This indicates the concentration of hazardous chemicals, where the risk index varies depending on the strategy employed. Quick pass: R index It may be low, but at high speeds, it can increase the risk of a collision.

[0152] bypass: R index It may be close to 0, but the driving efficiency is low.

[0153] Slow down and pass: R index It may be higher, but the ability to avoid risks is enhanced.

[0154] Step 5: Risk Level Classification: The calculated risk index is compared with a preset risk threshold to classify the risk level of the target group: Low risk ( R index <0.2): The agent is basically safe.

[0155] Medium risk (0.2≤ R index <0.5): May indicate temporary exposure to hazardous chemicals; caution is advised.

[0156] High risk ( R index ≥0.5): High probability of exposure to hazardous chemicals, emergency avoidance measures must be taken.

[0157] S3. Develop control measures for transport vehicles based on the risk assessment results of the target group, and optimize the routes of transport vehicles in accordance with the control measures.

[0158] It should be noted that corresponding control measures are formulated based on the assessment results of different risk levels, with a focus on the control of high-risk areas and time periods: High-risk area control: Speed ​​Limit Management: In high-risk areas, implement vehicle speed limits to reduce the speed of transport vehicles in the area. Lower speeds increase the reaction time of transport vehicles to avoid hazards, reducing the risk of exposure to hazardous chemical environments.

[0159] Restricted Entry: In specific high-risk areas, it may be necessary to restrict the entry of certain types of transport vehicles (such as vehicles transporting flammable or explosive hazardous materials). For example, in areas with a high level of danger, restricted zones or time periods may be established.

[0160] Road closures and detours: If the concentration of hazardous chemicals in a high-risk area is too high, it may be necessary to close roads or plan detour routes for transport vehicles. Traffic management systems should be used to notify relevant vehicles in advance to prevent them from entering high-risk areas.

[0161] High-risk period control: Traffic management: Strengthen traffic control and manage traffic flow during high-risk periods (such as high wind speeds or severe weather). For example, reduce congestion during high-risk periods by adjusting traffic lights and controlling road flow, and prevent transport vehicles from stalling in areas with high concentrations of hazardous chemicals.

[0162] Dynamically adjust transportation schedules: By planning ahead, transportation can avoid high-risk periods. Transportation plans are dynamically adjusted based on real-time weather, traffic conditions, and the spread of hazardous chemicals. For example, periods of high temperature or wind speed are avoided to reduce the spread rate and risk of hazardous chemicals.

[0163] Monitoring and guidance of transport vehicles: Real-time monitoring: Real-time monitoring of transport vehicles, using technologies such as sensors, GPS, and drones to collect real-time data on vehicle location, driving status, and environmental data (such as hazardous chemical concentration and meteorological data), and to adjust vehicle driving routes in a timely manner.

[0164] Route optimization guidance: By using real-time traffic information and risk assessment data, the system provides optimal route guidance to transport vehicles, avoiding high-risk areas, reducing parking and waiting time, and lowering the possibility of contact with hazardous chemicals.

[0165] According to another embodiment of the invention, such as Figure 2 As shown, a hazardous chemical cargo transport vehicle monitoring system is also provided, which includes a hazardous chemical risk prediction module 1, a transport vehicle route analysis module 2, and a transport vehicle control module 3. Hazardous materials risk prediction module 1 is connected to transport vehicle route analysis module 2, and transport vehicle route analysis module 2 is connected to transport vehicle control module 3; Hazardous chemical risk prediction module 1 is used to divide the hazardous chemical area in the transport vehicle, collect environmental data of the divided hazardous chemical area, and predict the risk behavior of hazardous chemicals during the transportation process based on the environmental data. The transport vehicle route analysis module 2 is used to extract the actions and behaviors of the target group and the hazardous chemicals along the cargo transport route, and to conduct risk assessments on the actions and behaviors of the target group to obtain the risk assessment results of the target group. The transport vehicle management module 3 is used to formulate transport vehicle management measures based on the risk assessment results of the target group, and to optimize the transport vehicle routes in accordance with the management measures.

[0166] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for supervising vehicles transporting hazardous chemicals, characterized in that, The method includes: The hazardous chemical areas in transport vehicles are divided, environmental data of the divided hazardous chemical areas are collected, and the risk behavior of hazardous chemicals during transportation is predicted based on the environmental data. Extract the actions and behaviors of target groups along the cargo transportation route that are associated with the risk behaviors of hazardous chemicals, and conduct risk assessments on the actions and behaviors of the target groups to obtain the risk assessment results of the target groups. The target groups include pedestrians, motor vehicles and non-motor vehicles. Based on the risk assessment results of the target group, develop control measures for transport vehicles and optimize the routes of transport vehicles in accordance with the control measures; Among these, predicting the risk behavior of hazardous chemicals during transportation based on environmental data includes: A diffusion prediction model is established based on environmental data to predict the dynamic diffusion behavior of hazardous chemicals during transportation. The aforementioned diffusion prediction model based on environmental data, used to predict the dynamic diffusion behavior of hazardous chemicals during transportation, includes: Environmental measurement data is extracted to establish a diffusion prediction model for hazardous chemicals. The dynamic distribution of hazardous chemicals is output through the diffusion prediction model, and a Gaussian distribution is formed based on the dynamic distribution of hazardous chemicals. The quantity of hazardous chemicals in the divided hazardous chemical areas is determined. If the quantity of hazardous chemicals is greater than or equal to a preset threshold, the combined effect of several hazardous chemical source diffusion points is randomly superimposed based on the Gaussian distribution of the hazardous chemicals to obtain an optimized diffusion prediction model. Otherwise, the dynamic diffusion behavior of hazardous chemicals in the future time period is predicted through the diffusion prediction model. The diffusion coefficients between adjacent hazardous chemical sources are obtained by solving the optimized diffusion prediction model, and the average value of the diffusion coefficients is used as the parameters of the optimized diffusion prediction model. By introducing a time factor into the optimization of diffusion prediction model parameters, a time-weighted diffusion prediction model is obtained and a stable diffusion field is output. The dynamic diffusion behavior of hazardous chemicals in future time periods is analyzed based on the stable diffusion field. The diffusion prediction model is introduced into a pre-built label tree model, and environmental factors are introduced into the label tree model so that the diffusion prediction model can predict the dynamic diffusion behavior of hazardous chemicals under different environments. Risk assessments were conducted on the actions and behaviors of the target group, and the risk assessment results for the target group included: A risk assessment model is established based on the actions and behaviors of the target group to assess the risk index when the actions and behaviors of the target group come into contact with high-risk areas; The risk assessment model established based on the target group's behavior, to assess the risk index when the target group's behavior comes into contact with high-risk areas, includes: A single-agent risk assessment model is constructed based on pedestrian behavior, and the risk index of pedestrians coming into contact with hazardous chemicals when passing through high-risk areas is analyzed through the single-agent risk assessment model. A multi-agent risk assessment model is constructed based on the actions and behaviors of motor vehicles and non-motor vehicles. The risk index of motor vehicles and non-motor vehicles coming into contact with hazardous chemicals when passing through high-risk areas is analyzed by the multi-agent risk assessment model. The multi-agent risk assessment model is constructed based on the actions and behaviors of motor vehicles and non-motor vehicles. The model is used to analyze the risk indices of contact between motor vehicles and non-motor vehicles and hazardous chemicals when they pass through high-risk areas. These indices include: Using motor vehicles and non-motor vehicles as participants, the payoff functions for motor vehicles and non-motor vehicles are calculated separately using a non-cooperative game strategy. Motor vehicles and non-motor vehicles are treated as intelligent agents, and a set of strategies for the intelligent agents is set. The payoff function of the intelligent agents is defined to construct a multi-agent risk assessment model. In the multi-agent risk assessment model, Nash equilibrium is used to select the best strategy for each intelligent agent from the set of strategies. A multi-agent risk assessment model is trained using reinforcement learning, enabling each agent to adopt the optimal strategy in high-risk areas. When adopting the optimal strategy, the risk index of the agent's contact with hazardous chemicals is calculated.

2. The method for supervising vehicles transporting hazardous chemicals according to claim 1, characterized in that, The process of dividing the hazardous chemical storage area within the transport vehicle and collecting environmental data for the divided hazardous chemical storage area includes: The internal area of ​​the transport vehicle is divided according to the characteristic parameters of the hazardous chemicals to obtain the divided hazardous chemical area. The system uses a cluster of sensors to collect environmental data from the designated hazardous chemical areas. Based on this data, it determines whether there are any risky activities related to hazardous chemicals. If risky activities are found, the system proceeds to the next step; otherwise, it continues to monitor the environmental data.

3. The method for supervising vehicles transporting hazardous chemicals according to claim 1, characterized in that, The process involves extracting the actions and behaviors of the target group along the cargo transportation route that are associated with the risk of hazardous chemicals, and conducting risk assessments on these actions and behaviors to obtain the risk assessment results for the target group, including: Spatial clustering algorithms are used to cluster the actions and behaviors of target groups along cargo transportation routes that are affected by the dynamic diffusion of hazardous chemicals. Identify high-risk areas along cargo transportation routes; Following the establishment of a risk assessment model based on the target group's behavior to assess the risk index when the target group's behavior comes into contact with high-risk areas, the following is included: The risk index is compared with a preset risk threshold, and the risk level of the target group is divided according to the comparison results to obtain the risk assessment results of the target group.

4. The method for supervising vehicles transporting hazardous chemicals according to claim 3, characterized in that, The actions of clustering target groups along cargo transportation routes using spatial clustering algorithms to classify the impact of the dynamic diffusion of hazardous chemicals include: Identify the trajectory points along the cargo transportation route where the target group is affected by the dynamic diffusion behavior of hazardous chemicals, and calculate the number of points contained in the neighborhood of each trajectory point; The number of points is compared with the MinPts parameter. If the number of points in the neighborhood of the current trajectory point is greater than the MinPts parameter, the current trajectory point is considered a core point. All trajectory points in the neighborhood are then connected to the core point to form a clustering result. Otherwise, the current trajectory point is marked as an outlier and removed. The activity area of ​​the target group is calculated based on the time difference and distance difference between adjacent trajectory points in the same clustering result, and the action behavior of the target group is analyzed based on the time the target group stays in the same activity area.

5. A monitoring system for hazardous chemical transport vehicles, used to implement the monitoring method for hazardous chemical transport vehicles as described in any one of claims 1-4, characterized in that, The system includes: The hazardous chemicals risk prediction module is used to divide the hazardous chemicals area in the transport vehicle, collect environmental data of the divided hazardous chemicals area, and predict the risk behavior of hazardous chemicals during the transportation process based on the environmental data. The transport vehicle route analysis module is used to extract the actions and behaviors of the target group and the hazardous chemicals along the cargo transport route, and to conduct risk assessments on the actions and behaviors of the target group to obtain the risk assessment results of the target group. The transport vehicle management module is used to formulate transport vehicle management measures based on the risk assessment results of the target group, and to optimize the transport vehicle routes in accordance with the management measures.

Images