A multi-objective path optimization system and method for dangerous chemical road transportation

Abstract

The application discloses a multi-objective path optimization system and method for hazardous chemical road transportation, which comprises the following modules: a data acquisition module for acquiring hazardous chemical transportation demand information and road network information, and generating a basic data set; a multi-objective optimization module for performing collaborative optimization of path planning and risk control based on the basic data set, and generating an optimization scheme; and a path generation module for generating a final transportation path, a time schedule and an emergency plan based on the optimization scheme, and dynamically adjusting according to real-time road conditions. The safety, reliability and efficiency of hazardous chemical road transportation are significantly improved, potential risk exposure is reduced, and comprehensive technical support is provided for hazardous chemical transportation management.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of path optimization, in particular to a multi-objective path optimization system and method for hazardous chemical road transportation. BACKGROUND

[0002] The intelligent planning system for hazardous chemical road transportation is a transportation support system with advanced technology and reliable safety, which plans the transportation path of hazardous chemicals by using a multi-objective optimization algorithm and comprehensively considers factors such as transportation distance, time, cost, safety risk and environmental impact.

[0003] The current hazardous chemical transportation system generally has the problems of module segmentation and single function, lacks systematic integration of data acquisition, multi-objective optimization and path generation, and is difficult to effectively utilize transportation demand and road network information. The traditional system usually ignores the differences in running state under different scenarios and cannot be optimized according to the type of hazardous chemicals, time period and weather conditions. The existing technology often separates the safety control and path planning, lacks a collaborative optimization mechanism, and is difficult to balance safety optimization and path optimization at the same time, and cannot minimize the risk while reducing transportation costs. In addition, the existing system generally lacks real-time dynamic adjustment capability and emergency plan generation function, and is difficult to cope with complex and variable transportation environment.

[0004] Therefore, there is an urgent need for a multi-objective path optimization system and method for hazardous chemical road transportation. SUMMARY

[0005] The present application provides a multi-objective path optimization system and method for hazardous chemical road transportation to solve the above problems existing in the prior art.

[0006] In order to achieve the above purpose, the present application provides the following technical scheme:

[0007] A multi-objective path optimization system for hazardous chemical road transportation, comprising:

[0008] A data acquisition module for acquiring hazardous chemical transportation demand information and road network information and generating a basic data set;

[0009] A multi-objective optimization module for collaborative optimization of path planning and risk control based on the basic data set to generate an optimization scheme;

[0010] A path generation module for generating a final transportation path, time schedule and emergency plan based on the optimization scheme and dynamically adjusting according to real-time traffic conditions.

[0011] The multi-objective optimization module comprises:

[0012] A scene traversal submodule for sequentially traversing various hazardous chemical transportation scenarios and dividing multiple running states according to different time periods and weather conditions;

[0013] an optimization training submodule configured to determine optimization results of the optimization model in the safety control and the path planning for each operating state, and use all the operating states and the collaborative optimization basis as a training basis of the optimization model.

[0014] The optimization training submodule comprises:

[0015] a safety optimization unit configured to interact with the simulation environment based on a preset safety control action space, generate a risk assessment result, and update safety control parameters to determine an optimization scheme that minimizes safety risks and environmental impacts;

[0016] a path optimization unit configured to interact with the simulation environment based on a preset path selection action space, generate a path planning result, and update path planning parameters to determine an optimization scheme that minimizes transportation costs and safety risks;

[0017] an integration unit configured to integrate the optimization schemes of the safety control parameters and the path planning parameters as a collaborative optimization basis under the current operating state.

[0018] The safety optimization unit comprises:

[0019] a risk analysis subunit configured to identify key influencing factors of safety risks and environmental impacts in the risk assessment result, determine a risk set therefrom, and take the highest-level risk in each risk set as a control optimization target;

[0020] a parameter adjustment subunit configured to, if a standard operating state representing that the control optimization target has been mitigated does not appear in the subsequent simulation environment, take the corresponding control optimization target as a risk point that needs to be further optimized and adjust the safety control parameters.

[0021] The path generation module comprises:

[0022] a path sorting submodule configured to sort all selectable paths in ascending order of safety risks and transportation costs according to the path planning result and the risk control scheme in the optimization scheme, and obtain an optimization path sequence;

[0023] a path selection submodule configured to divide the optimization path sequence into a plurality of local path groups, select a path with the highest safety and the lowest cost from each local path group in turn, generate a final optimized transportation path, and match a time arrangement and an emergency plan.

[0024] The path generation module further comprises:

[0025] a dynamic adjustment submodule configured to, when detecting a real-time road condition change or an emergency event, generate a dynamic adjustment scheme based on changed road network information;

[0026] The communication early warning sub-module is configured to establish real-time communication between the alternative route and the relevant personnel based on the dynamic adjustment scheme, send early warning information to the relevant personnel, and update the transportation scheme.

[0027] The dynamic adjustment sub-module comprises:

[0028] The demand matching unit is configured to pre-match adjustment demand templates based on real-time road condition changes or emergencies, and determine a plurality of alternative adjustment demands and their priorities according to historical optimization results.

[0029] The scheme generation unit is configured to sequentially traverse the alternative adjustment demands, generate a transportation scenario evolution sequence and show the evolution process, and generate a dynamic adjustment scheme according to the transportation scenario selected by the relevant personnel.

[0030] The demand matching unit comprises:

[0031] The demand generation sub-unit is configured to generate alternative adjustment demands based on key feature parameters input by real-time road condition changes or emergencies, in combination with adjustment demand generation templates and historical optimization results.

[0032] The priority setting sub-unit is configured to set the template weight of the adjustment demand generation template based on which the alternative adjustment demand is generated as the corresponding priority.

[0033] The data acquisition module comprises:

[0034] The demand acquisition sub-module is configured to acquire dangerous chemical product transportation demand information including dangerous chemical product types, quantities, and transportation time requirements.

[0035] The network acquisition sub-module is configured to acquire road network information including road node, road segment characteristics of connecting nodes, real-time road conditions, and environmental parameters.

[0036] The data integration sub-module is configured to integrate the dangerous chemical product transportation demand information and the road network information to generate a basic data set.

[0037] The multi-objective path optimization method for dangerous chemical product road transportation comprises:

[0038] S1: Acquire dangerous chemical product transportation demand information and road network information, and generate a basic data set;

[0039] S2: Perform collaborative optimization of path planning and risk control based on the basic data set, and generate an optimization scheme;

[0040] S3: Generate a final transportation path, time schedule, and emergency plan based on the optimization scheme, and dynamically adjust according to real-time road conditions.

[0041] Compared with the prior art, the present application has the following advantages:

[0042] A multi-objective path optimization system for hazardous chemical road transportation includes: a data acquisition module for acquiring hazardous chemical transportation demand information and road network information to generate a basic data set; a multi-objective optimization module for collaborative optimization of path planning and risk control based on the basic data set to generate an optimization scheme; and a path generation module for generating a final transportation path, time schedule and emergency plan based on the optimization scheme and dynamically adjusting according to real-time road conditions. The safety, reliability and efficiency of hazardous chemical road transportation are significantly improved, potential risk exposure is reduced, and comprehensive technical support is provided for hazardous chemical transportation management.

[0043] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the application.

[0044] The technical solutions of the present application are described in further detail below with the aid of the accompanying drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0045] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, illustrate the present application together with the embodiments thereof, and explain the present application, but are not intended to limit the present application. In the drawings:

[0046] Figure 1 A structure diagram of a multi-objective path optimization system for hazardous chemical road transportation in an embodiment of the present application;

[0047] Figure 2 A structure diagram of a multi-objective optimization module in an embodiment of the present application;

[0048] Figure 3 A flowchart of a multi-objective path optimization method for hazardous chemical road transportation in an embodiment of the present application. DETAILED DESCRIPTION

[0049] The preferred embodiments of the present application are described below with reference to the accompanying drawings, and it should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and do not limit the present application.

[0050] The embodiment of the present application provides a multi-objective path optimization system for hazardous chemical road transportation, which includes:

[0051] The data acquisition module is used to acquire hazardous chemical transportation demand information and road network information to generate a basic data set;

[0052] The multi-objective optimization module is used to perform collaborative optimization of path planning and risk control based on the basic data set to generate an optimization scheme;

[0053] A path generation module is configured to generate a final transportation path, a time schedule and an emergency plan based on the optimization scheme and dynamically adjust the final transportation path according to real-time road conditions.

[0054] The working principle of the technical solution is as follows: when receiving a dangerous chemical transportation request, the matching relationship between the dangerous chemical characteristics and the road network environment parameters is analyzed, and a basic data set suitable for the safe transportation of dangerous chemicals is constructed; in the data acquisition module, the dangerous chemical transportation request covers information such as dangerous chemical type, physical and chemical characteristics, quantity, loading state, starting location and destination, arrival time limit and the like; the road network environment parameters include road grade division, lane number, road surface condition, height and width limit, traffic capacity, distribution of sensitive areas along the line, meteorological conditions, traffic flow variation law and the like; the matching relationship analysis establishes a quantitative index of dangerous chemical characteristics and road environment adaptability by evaluating the transportation risk coefficients of different dangerous chemicals under various road conditions; the basic data set is stored in a multi-level graph structure, in which a node represents a road intersection or a key landmark, an edge represents a road section connecting the nodes, and each edge is attached to multi-dimensional attribute information including distance, travel time, risk coefficient, traffic restriction and the like;

[0055] Based on the constructed basic data set, a pre-trained multi-objective collaborative optimization algorithm is started to balance transportation time, cost and safety risk, and a multi-gradient trade-off optimization scheme set is generated; in the multi-objective optimization module, the multi-objective collaborative optimization algorithm adopts a hybrid strategy combining an improved genetic algorithm and simulated annealing, and finds a Pareto optimal solution set through iterative calculation; the optimization objective function includes three dimensions of time loss function, economic cost function and risk assessment function; the time loss function considers time factors such as road travel time, loading and unloading time, rest time and waiting time; the economic cost function takes into account economic factors such as fuel consumption, toll fee, labor cost and equipment wear and tear; the risk assessment function quantifies the safety risks such as leakage accidents, fire and explosion, traffic accidents that may be encountered during transportation, and performs weighted processing in combination with the population density and environmental sensitivity along the line; the multi-gradient trade-off optimization scheme set provides alternative schemes under different decision preferences, allowing decision makers to select the most suitable transportation strategy according to actual needs;

[0056] According to the optimization scheme set, real-time traffic conditions and weather change information are fused to generate fine transportation path planning and dynamic response mechanism, and full-process controllable transportation of dangerous chemicals and rapid emergency treatment are realized. In the path generation module, the fine transportation path planning includes main path design and alternative path preparation, and each road section is assigned with recommended speed, stop point position, and rest time arrangement. The dynamic response mechanism interacts with the vehicle sensor and the traffic management system data to monitor abnormal conditions in the transportation process in real time. When traffic congestion, severe weather, road construction, and other conditions are encountered, the system automatically evaluates the influence degree, makes local path adjustment within the preset threshold range, and switches to the alternative path when the threshold is exceeded. The rapid emergency treatment process pre-plans the evacuation channel in the dangerous area, the emergency rescue resource allocation scheme, the professional disposal team linkage mechanism, and formulates the targeted emergency disposal plan according to the type of dangerous chemicals.

[0057] The beneficial effects of the above technical solution are that the full-process controllable transportation realizes information sharing and collaborative decision-making of regulatory departments, transportation enterprises, and vehicle drivers through positioning tracking, state monitoring, and remote control, greatly improving the safety and reliability of dangerous chemical road transportation.

[0058] In another embodiment, the multi-objective optimization module includes:

[0059] The scene traversal submodule is used to sequentially traverse various dangerous chemical transportation scenarios, and divide multiple running states according to different time periods and weather conditions.

[0060] The optimization training submodule is used to determine the optimization results of the optimization model in safety control and path planning for each running state, and use all running states and collaborative optimization as the training basis of the optimization model.

[0061] The working principle of the above technical solution is that the multi-objective optimization module systematically identifies and processes various dangerous chemical transportation scenarios through the scene traversal submodule, and subdivides each scenario into multiple running states according to the space-time dimension characteristics. Among them, the dangerous chemical transportation scenario refers to the transportation activity scenario of flammable and explosive, toxic and harmful, and other dangerous chemicals in different transportation networks such as highways, railways, and waterways, for example, alkane gas highway transportation scenario, strong acid substance railway transportation scenario, flammable liquid water transportation scenario, etc. The space-time dimension characteristics include time period characteristics and weather condition characteristics. The time period characteristics cover different traffic flow distribution periods such as morning peak, flat peak, evening peak, and night. The weather condition characteristics include different meteorological environments such as fine, rain and snow, haze, and extreme weather. The running state refers to the specific state of dangerous chemical transportation based on the combination of space-time dimension characteristics, for example, the running state during the morning peak in fine weather, the running state at night in rain and snow, etc.

[0062] The optimization training submodule performs double-target optimization calculation for each operating state, dynamically balances safety control requirements and path planning efficiency, and generates a collaborative optimization basis under a specific operating state; wherein, the double-target optimization calculation refers to an optimization calculation process that simultaneously considers safety control targets and path planning targets; the safety control requirements include safety factors such as compliance with hazardous chemicals-related regulations, avoidance of risk-sensitive areas, and guarantee of emergency response capabilities; the path planning efficiency covers efficiency factors such as transportation time consumption, energy resource utilization, and economic cost control; the collaborative optimization basis refers to a decision-making reference basis with the best safety-efficiency balance under a specific operating state after double-target optimization calculation;

[0063] The optimization training submodule integrates all operating states and their corresponding collaborative optimization bases to form a training data set, and constructs an adaptive optimization model through iterative learning; wherein, the training data set is composed of multiple operating states and collaborative optimization basis mapping pairs; the iterative learning method uses a step-by-step model training strategy to continuously adjust optimization model parameters to improve its prediction accuracy and generalization ability; the adaptive optimization model can quickly generate optimization results that meet the dual requirements of safety control and path planning for new hazardous chemical transportation scenarios and operating states.

[0064] The above technical solution has the following beneficial effects: the scene traversal submodule systematically identifies various hazardous chemical transportation scenarios and subdivides multiple operating states according to spatiotemporal dimension characteristics, the optimization training submodule performs double-target optimization calculation for each operating state and generates a collaborative optimization basis, and then integrates all operating states and collaborative optimization bases to form a training data set to construct an adaptive optimization model, achieving dynamic balance between safety control and path planning during hazardous chemical transportation, and significantly improving the safety, efficiency, and reliability of hazardous chemical transportation.

[0065] In another embodiment, the optimization training submodule includes:

[0066] The safety optimization unit is configured to interact with the simulation environment based on a preset safety control action space, generate a risk assessment result, update safety control parameters, and determine an optimization scheme that minimizes safety risks and environmental impacts;

[0067] The path optimization unit is configured to interact with the simulation environment based on a preset path selection action space, generate a path planning result, update path planning parameters, and determine an optimization scheme that minimizes transportation costs and safety risks;

[0068] The integration unit is configured to integrate the optimization schemes of the safety control parameters and the path planning parameters as a collaborative optimization basis under the current operating state.

[0069] The working principle of the above technical solution is that the safety optimization unit interacts with the simulation environment based on the preset safety control action space, the system generates a comprehensive risk assessment result and dynamically updates the safety control parameters, and then determines the optimization scheme that minimizes the safety risk and environmental impact. The safety optimization unit establishes a safety risk quantification model by analyzing road conditions, traffic flow, meteorological conditions, and hazardous chemical characteristics, and combines historical accident data to perform risk rating on each road segment.

[0070] The path optimization unit interacts with the simulation environment based on the preset path selection action space, generates path planning results and updates path planning parameters by analyzing the road network topology, real-time traffic conditions, and risk levels of each road segment, and determines the optimization scheme that minimizes transportation cost and safety risk. The path optimization unit considers fuel consumption, time cost, road tolls, and safety risk factors, and generates a Pareto optimal solution set through a multi-objective optimization algorithm.

[0071] The integration unit integrates the optimization schemes of the safety control parameters and the path planning parameters, and uses them as the basis for cooperative optimization under the current operating state. During the integration process, the weight relationship between safety risk and cost benefit is adaptively adjusted according to decision preferences and actual transportation needs, and the final transportation execution scheme is generated.

[0072] The beneficial effects of the above technical solution are that the integration unit also establishes a feedback learning mechanism, continuously optimizes the decision model through analysis of historical transportation data, and improves the system's adaptability to complex transportation environments.

[0073] In another embodiment, the safety optimization unit includes:

[0074] A risk analysis subunit for identifying key influencing factors of safety risks and environmental impacts in the risk assessment result, determining a risk set therefrom, and taking the highest level risk in each risk set as a control optimization target;

[0075] A parameter adjustment subunit for adjusting the safety control parameters if the corresponding control optimization target is not present in the subsequent simulation environment, which represents a standard operating state where the control optimization target has been mitigated.

[0076] Wherein, identifying key influencing factors of safety risks and environmental impacts in the risk assessment result includes:

[0077] Obtain risk assessment results data for multiple target areas containing hazardous chemical transportation routes over a continuous period, including: identifying transportation routes containing potential safety and environmental risks based on historical accident data and environmental monitoring data of multiple transportation areas; and identifying target transportation routes containing significant risk characteristics based on risk assessment data corresponding to transportation routes containing potential safety and environmental risks.

[0078] For any target transportation route, based on the risk assessment data over a continuous time period, key influencing factors of safety risks and environmental impacts are identified. These key influencing factors include road conditions, weather changes, vehicle performance, and population distribution along the route. Identifying these key influencing factors based on the risk assessment data over a continuous time period involves: uniformly gridding the risk assessment data for each time period with the risk assessment data for the baseline time period; determining the risk contribution of road conditions based on road accident frequency and road surface quality indicators; determining the risk contribution of weather changes based on changes in meteorological conditions and visibility levels; determining the risk contribution of vehicle performance based on vehicle technical condition and load capacity; and determining the risk contribution of population distribution along the route based on population density distribution and sensitive area distribution.

[0079] Based on the spatial distribution characteristics of key influencing factors in the target transportation route, the risk set division criteria and the risk classification threshold corresponding to each key influencing factor are determined.

[0080] Based on the spatial distribution characteristics of key influencing factors in the target transportation route, risk set division criteria are determined, including: dividing the transportation route into several risk sets according to the similarity characteristics of key influencing factors, with each risk set representing a specific road segment or area with similar risk characteristics; if any road segment or area in the transportation route simultaneously meets the conditions of population density exceeding a set threshold and road grade falling below a set standard, then the road segment or area is classified into the urban dense risk set; if any road segment or area in the transportation route simultaneously meets the conditions of terrain complexity exceeding a set threshold and frequency of severe weather conditions exceeding a set proportion, then the road segment or area is classified into the terrain and climate risk set.

[0081] The risk levels of key influencing factors in each risk cluster are assessed, and the highest risk level is determined. The degree of safety threat and environmental impact corresponding to the highest risk level in each risk cluster is statistically analyzed. Specifically, this includes: statistically analyzing the risk level distribution of multiple key influencing factors in any risk cluster in each time period within a continuous period; identifying the influencing factor with the highest risk level in any risk cluster as the dominant risk factor of that risk cluster; assessing the degree of threat posed by the dominant risk factor to transportation safety and its potential impact on the surrounding environment; and determining the highest risk level of the risk cluster based on a comprehensive score of the degree of threat and impact.

[0082] determine the control optimization target of the risk set based on the degree of safety threat and the degree of environmental impact of the highest level risk in each risk set, including: if the highest level risk in the risk set mainly reflects the high-risk of traffic accidents, determining the reduction of accident probability as the control optimization target of the risk set; if the highest level risk in the risk set mainly reflects the pollution risk of the environmental sensitive area, determining the reduction of environmental impact degree as the control optimization target of the risk set; if the highest level risk in the risk set contains both safety threat and environmental impact, determining the comprehensive risk control as the control optimization target of the risk set;

[0083] store the control optimization targets corresponding to different risk sets and the optimization strategies corresponding to different control optimization targets to obtain a multi-objective control optimization model for optimizing the transportation path of the hazardous chemical.

[0084] The working principle of the above technical solution is that the risk analysis subunit first analyzes the risk assessment results of the transportation path, identifies the corresponding key influencing factors, which include road conditions, weather changes, transportation vehicle performance, and population distribution along the way. These key influencing factors affect the degree of safety hazards and environmental damage during transportation. The risk analysis subunit divides the transportation path into several risk sets according to the key influencing factors. Each risk set represents a specific section or area of the path with similar risk characteristics. For example, in a hazardous chemical transportation path, the section passing through the urban dense area will be classified into a risk set due to high population density, while the section passing through the rugged mountain road will be classified into another risk set due to complex terrain and narrow road. This division ensures the pertinence and accuracy of risk analysis. The risk analysis subunit selects the highest level risk from each risk set and determines the highest level risk as the control optimization target of the risk set. The highest level risk refers to the factor that poses the greatest threat to transportation safety or environmental impact, such as a section marked as a high-risk area due to frequent traffic accidents, or an area close to a water source protection zone with high environmental sensitivity.

[0085] After the control optimization target is determined, the parameter adjustment subunit optimizes the control optimization target through a simulation environment. The simulation environment simulates a real scenario of dangerous chemical product road transportation and provides a platform for dynamic testing and adjustment of safety control parameters. The parameter adjustment subunit monitors the operating state during the simulation, and pays particular attention to whether a standard operating state representing that the control optimization target has been mitigated appears. The standard operating state refers to a state in which, in the simulation, the risk of a certain control optimization target has been effectively controlled or eliminated. For example, by adjusting the transportation speed or replacing a low-risk path, the accident probability of a certain high-risk road section is reduced, thereby reaching the standard operating state. If the standard operating state representing that the control optimization target has been mitigated does not appear in the simulation environment, the parameter adjustment subunit identifies the target as a risk point that needs to be further optimized. The system then adjusts the safety control parameters. The safety control parameters include: transportation speed, vehicle spacing, and protective equipment configuration.

[0086] The mechanism of continuous optimization can flexibly adapt to different transportation scenarios according to the simulation results. For example, under rainy conditions, the system mitigates the risk of a slippery road section by reducing the vehicle speed and increasing emergency response measures.

[0087] The above technical scheme has the beneficial effects that: the risk analysis subunit ensures that the system can focus on the most threatening risk points through identification of key influencing factors and division of risk sets. The parameter adjustment subunit tailors safety control strategies for each transportation path through dynamic optimization in the simulation environment, avoiding the limitations of the traditional "one-size-fits-all" approach.

[0088] In another embodiment, the path generation module includes:

[0089] The path sorting sub-module is configured to sort all the selectable paths from low to high in terms of safety risk and transportation cost according to the path planning results in the optimization scheme and the risk control scheme, and obtain an optimized path sequence.

[0090] The path selection sub-module is configured to divide the optimized path sequence into multiple local path groups, select the path with the highest safety and the lowest cost from each local path group in turn, generate a final optimized transportation path, and match the time arrangement and emergency plan.

[0091] The working principle of the above technical solution is that the path sorting submodule sorts all the selectable paths from low to high according to the safety risk and transportation cost based on the path planning result in the optimization scheme and the risk control scheme, and obtains an optimized path sequence. In the path sorting submodule, the path sorting process first collects all feasible dangerous goods transportation path information, and then preliminarily screens these paths according to the existing path planning result. The system will comprehensively consider the safety risk factors of each path, such as road conditions, weather conditions, traffic density, dangerous goods transportation restricted areas, etc., while evaluating the transportation cost of each path, including fuel consumption, road tolls, time cost and other economic indicators. Through multi-dimensional evaluation, the system will sort all paths from low to high according to the comprehensive score of safety risk and transportation cost, forming an optimized path sequence. For example, in the scenario of dangerous goods transportation from A to B, the system will sort multiple paths composed of different types of roads such as highways, national roads and provincial roads, and prefer paths that avoid densely populated areas, have dedicated dangerous goods transportation roads and have lower transportation costs.

[0092] The path selection submodule divides the optimized path sequence into multiple local path groups, and selects the path with the highest safety and lowest cost from each local path group in turn according to the grouping order. In the path selection submodule, the system first divides the entire transportation path into multiple local path groups according to geographical location, administrative division or key nodes. This division method helps to optimize the path in a local range while taking into account the global optimal solution. For each local path group, the system will comprehensively analyze the safety risk index and transportation cost index of each path, and prefer the path with the highest cost-effectiveness under the premise of safety. For example, when dangerous goods need to pass through multiple cities, the system will divide the path into different groups such as city internal road segments and inter-city connecting road segments, and then select the optimal path for each group. The city internal road segment prefers to select the bypass road to avoid the city center, and the inter-city connecting road segment prefers to select the dedicated dangerous goods transportation channel.

[0093] In addition, in the path selection submodule, the selected optimal paths in each local path group are connected to form a complete dangerous goods transportation path, and according to the path characteristics and the type of dangerous goods, the corresponding time arrangement is matched, including determining the best departure time, the estimated arrival time and the key node passing time, so as to avoid the traffic peak period or adverse weather conditions. In addition, for various emergencies that may occur during transportation (including traffic accidents, adverse weather, vehicle breakdown), the system automatically generates the corresponding emergency plan (including alternative paths, emergency contact numbers and nearby emergency rescue points). For example, when the system generates a dangerous goods transportation path that passes through a mountainous area, it will simultaneously match the time arrangement to avoid traveling during the rainy season, and develop emergency disposal schemes for landslides and landslides on mountain roads.

[0094] The above technical scheme has the beneficial effects that: through the two key links of path sequencing and path selection, fine management of the dangerous chemical product transportation path is realized, which not only improves the safety guarantee level of the dangerous chemical product transportation process, but also reduces the transportation cost, and meets the special needs of dangerous chemical product road transportation.

[0095] In another embodiment, the path generation module further comprises:

[0096] The dynamic adjustment sub-module is configured to generate a dynamic adjustment scheme based on the changed road network information when detecting a real-time road condition change or an emergency event;

[0097] The communication warning sub-module is configured to establish real-time communication between the alternative route and the relevant personnel based on the dynamic adjustment scheme, issue warning information to the relevant personnel, and update the transportation scheme.

[0098] The dynamic adjustment scheme is generated based on the changed road network information, including:

[0099] Obtaining real-time monitoring information of the road network, identifying road condition change events according to the real-time monitoring information, and obtaining road condition change event information;

[0100] Obtaining pre-matching rational adjustment phase standard information, determining the adjustment phase in combination with the road condition change event information, and obtaining rational adjustment phase information;

[0101] Obtaining historical adjustment scheme data, identifying scheme differences and generating adjustment support requirements based on the rational adjustment phase information, and obtaining adjustment support requirement information;

[0102] Performing multi-objective path optimization according to the adjustment support requirement information in combination with the changed road network information to generate a dangerous chemical product transportation dynamic adjustment scheme;

[0103] The real-time monitoring information of the road network is obtained, and the road condition change event is identified according to the real-time monitoring information, specifically including:

[0104] Obtaining real-time monitoring information of the road network, preprocessing the real-time monitoring information, obtaining feature information of various traffic events, road conditions and dangerous chemical product transportation safety events based on big data retrieval, and constructing an event feature comparison data set;

[0105] Constructing a road condition change event identification model, constructing a training data set according to the event feature comparison data set, and performing deep learning and training on the road condition change event identification model, wherein the road condition change event identification model comprises a data fusion layer, an event detection layer and an influence evaluation layer;

[0106] According to the data fusion layer, real-time monitoring information is subjected to multi-source data fusion, traffic flow data, road condition data, meteorological data and emergency event data are fused, and a fusion feature matrix is constructed according to the weight of each data source to obtain fusion monitoring feature information;

[0107] The fusion monitoring feature information is input into the event detection layer for event detection, a time sequence attention mechanism is introduced, the event occurrence probability of each time node is calculated by combining the fusion monitoring feature information through the time sequence attention mechanism, and an event probability distribution graph is constructed to obtain event probability distribution information;

[0108] An event classifier is constructed based on an improved CNN-LSTM network, the fusion monitoring feature information and the event probability distribution information are subjected to feature fusion, a multi-scale convolution kernel is used for event type identification, an event classification result is generated, and event type identification information is obtained;

[0109] According to the event type identification information, the influence range of the detected event is evaluated, the influence degree and influence duration of the event on the dangerous chemical transportation path are calculated, and event influence evaluation information is obtained;

[0110] The event influence evaluation information is input into the influence evaluation layer for comprehensive evaluation, the safety risk and timeliness influence of the road condition change event on the dangerous chemical transportation are evaluated, and road condition change event information is obtained;

[0111] The pre-matching rational adjustment stage standard information is obtained, and the adjustment stage is determined in combination with the road condition change event information, specifically including:

[0112] The pre-matching rational adjustment stage standard information is obtained, and a phased adjustment standard library is constructed based on historical emergency event handling experience, including the determination standards of the emergency response stage, the path evaluation stage, the scheme optimization stage and the execution monitoring stage;

[0113] The road condition change event information is subjected to feature extraction, the event type feature, the influence degree feature and the emergency degree feature are extracted, similarity matching is performed with the phased adjustment standard library, and judgment is performed with the pre-set matching threshold, the corresponding rational adjustment stage of the current event is determined, and stage matching information is obtained;

[0114] The adjustment stage is accurately positioned in combination with the stage matching information and the road condition change event information, and the stage conversion condition analysis is performed, the stage conversion conditions are sorted according to the trigger priority, and stage conversion sequence information is obtained;

[0115] According to the road condition change event information, event development trend information and expected duration information are extracted, an event development trend graph is constructed according to the event intensity change and influence range change per unit time, the event development direction and adjustment opportunity are predicted, and adjustment opportunity prediction information is obtained;

[0116] The rational adjustment phase information is composed of phase matching information, phase transition sequence information and adjustment opportunity prediction information;

[0117] The historical adjustment scheme data is acquired, and scheme difference identification and adjustment support demand generation are performed based on the rational adjustment phase information, specifically including:

[0118] The historical adjustment scheme data is acquired, and the historical processing scheme of a similar event is retrieved according to the rational adjustment phase information to obtain historical scheme set information, and scheme effectiveness evaluation is performed according to the scheme execution effect to obtain scheme effectiveness evaluation information;

[0119] The rational adjustment phase information is acquired, and scheme difference analysis is performed in combination with the historical scheme set information to identify decision difference points existing in the historical schemes to obtain scheme difference identification information;

[0120] A difference coordination model is constructed based on the scheme difference identification information, the advantages and disadvantages and applicable conditions of each difference scheme are analyzed, part of the scheme difference is automatically coordinated, and the scheme difference that cannot be coordinated is reserved as an unsolved scheme difference to obtain unsolved scheme difference information;

[0121] An adjustment support demand generation model is constructed according to the rational adjustment phase information and the unsolved scheme difference information, the promotion effect of real-time road condition information on entering the next rational adjustment phase is analyzed, and phase promotion support demand information is obtained;

[0122] A difference coordination support demand analysis module is constructed, the support degree of real-time road condition information on unsolved scheme difference coordination is evaluated, the feasibility and safety of each difference scheme under the current road condition are calculated, and difference coordination support demand information is obtained;

[0123] The adjustment support demand information is composed of the phase promotion support demand information and the difference coordination support demand information; wherein, multi-objective path optimization is performed according to the adjustment support demand information in combination with the changed road network information to generate a dynamic adjustment scheme for hazardous chemical substance transportation, specifically including:

[0124] The adjustment support demand information is acquired, and constraint conditions and objective functions of path optimization are determined according to the adjustment support demand information to obtain optimization target setting information;

[0125] The changed road network information is acquired, and feasible path search is performed in combination with the optimization target setting information to construct a multi-objective optimization space considering safety and timeliness, and candidate path set information is obtained;

[0126] A path optimization model is constructed based on an improved multi-objective particle swarm optimization algorithm, safety risk minimization, transportation time minimization and transportation cost minimization are taken as optimization objectives, and a multi-objective optimization function is established;

[0127] The multi-objective optimization function is input according to the candidate path set information, iteration optimization is carried out by using a reservation strategy and a dynamic weight adjustment mechanism, and optimal solution set information is obtained.

[0128] A scheme evaluation decision model is constructed, the Pareto optimal solution set is comprehensively evaluated in combination with the adjusted support demand information, scheme sorting and screening are carried out by considering current road conditions, transportation time limit requirements and safety risk bearing capacity, and optimal adjustment scheme information is obtained.

[0129] Detailed path adjustment instructions are generated according to the optimal adjustment scheme information, including new path coordinates, expected travel time, matters needing attention and emergency plans, to form a dynamic adjustment scheme for hazardous chemical substance transportation.

[0130] The working principle of the above technical solution is that the pre-matching rational adjustment stage standard in the dynamic adjustment submodule refers to a pre-set standard for phased rational adjustment that matches real-time road condition changes, which is pre-set by the technician according to past experience in handling phased events of different roads. The rational adjustment stage standard is used to indicate how the system determines the next reasonable adjustment stage of the dangerous goods transportation path after detecting real-time road condition changes, i.e., the next rational adjustment stage. The dynamic adjustment submodule then identifies unresolved scheme differences in the adjustment stage of the system in handling similar road condition change events in history. In this process, the system analyzes the multiple schemes generated when handling similar road condition change events in history, and some scheme differences are automatically coordinated, while another part of the uncoordinated scheme differences is retained as unresolved scheme differences. The dynamic adjustment submodule then generates adjustment support requirements that real-time road condition information of the road network information source is beneficial to the system entering the next rational adjustment stage, and real-time road condition information of the road network information source is beneficial to the system coordinating the unresolved scheme differences. Real-time road condition information is information such as road conditions, traffic flow, and sudden events that the road network information source can currently obtain. The adjustment support requirements are divided into two aspects: first, real-time road condition information is beneficial to the system entering the next rational adjustment stage, which means that after processing real-time road condition information, the adjustment idea is guided into the next rational adjustment stage. For example, during a dangerous goods transportation process, the system receives real-time road condition information showing that a traffic accident has occurred on the road ahead, causing severe congestion and is expected to be unable to resume traffic in a short time. These information prompt the system to quickly judge after analysis that the path needs to be adjusted immediately, thereby entering the next rational adjustment stage, such as calculating alternative routes and evaluating the safety and timeliness of each alternative route to avoid additional risks caused by the transportation vehicle being stranded on the congested road section. Second, real-time road condition information is beneficial to the system coordinating the unresolved scheme differences, which means that after processing real-time road condition information, the adjustment idea is guided to coordinate the unresolved scheme differences. For example: if the system is handling a sudden traffic control event, there is a scheme difference between choosing to take a long-distance highway with good traffic conditions or choosing a national road with general traffic conditions. At this time, real-time road condition information provides detailed data about the real-time traffic flow, road construction conditions, and weather conditions of the two routes, helping the system to fully understand the current situation and potential risks, thereby coordinating the differences between different schemes under the guidance of information, and finally deciding to choose a safer route to ensure the safety of dangerous goods transportation.

[0131] The communication warning sub-module establishes a real-time communication link between the alternative route and the relevant personnel based on the dynamic adjustment scheme, sends warning information to the driver and the transportation management personnel through the link, and updates the transportation scheme. The communication warning sub-module first evaluates the warning priority, determines the priority of information sending according to the severity and urgency of the road condition change. The communication warning sub-module then generates the content of the warning information, including the details of the road condition change, the recommended alternative route, the predicted arrival time adjustment, and the safety precautions, and other key information. The content of the warning information is converted into simple and clear text and image information through natural language processing technology, ensuring that the driver can quickly understand during driving. The communication warning sub-module then selects the best communication channel, automatically selects the most reliable communication method such as satellite communication, mobile network or vehicle-specific communication equipment according to the current network coverage, information urgency and driver receiving device type, and ensures that the warning information can be delivered in a timely and reliable manner.

[0132] The beneficial effects of the above technical solutions are: in the process of dynamic adjustment and communication warning, the rational adjustment phase standard is introduced, the next rational adjustment phase is determined quickly based on the adjustment support demand generated from two aspects of promoting the system to enter the next rational adjustment phase and promoting the system to coordinate the unsolved scheme differences, and the unsolved scheme differences are identified, and finally the real-time road condition information of the road network information source can effectively guide the system to enter the next rational adjustment phase and coordinate the unsolved scheme differences after the wireless communication between the different road network information sources and the transportation system is established, greatly improving the precision, safety and efficiency of the dangerous chemical road transportation path optimization, and improving the adaptability of the system in complex traffic environment.

[0133] In another embodiment, the dynamic adjustment sub-module comprises:

[0134] The demand matching unit is configured to pre-match an adjustment demand template based on real-time road condition changes or sudden events, and determine a plurality of alternative adjustment demands and their priorities according to historical optimization results;

[0135] The scheme generation unit is configured to sequentially traverse the alternative adjustment demands, generate a transportation situation evolution sequence and display the evolution process, and generate a dynamic adjustment scheme according to the transportation situation selected by the relevant personnel.

[0136] The working principle of the above technical solution is that the demand matching unit first pre-matches the adjustment demand template based on real-time road condition changes or emergencies. The pre-matched adjustment demand template refers to an adjustment template that is pre-set to match the road condition changes or emergencies of dangerous goods road transportation, which can be pre-set by technical personnel according to past experience in handling different road condition changes or emergencies. The demand matching unit determines a plurality of alternative adjustment demands and their priorities by analyzing historical optimization results, providing a basis for subsequent scheme generation. In the process of determining alternative adjustment demands, the demand matching unit identifies unsolved adjustment conflicts in the historical optimization process. In the historical optimization process, various parties involved in dangerous goods transportation may have multi-objective conflicts, such as conflicts between safety and timeliness, and some of these conflicts are resolved during the handling process, while the unresolved ones are treated as unsolved adjustment conflicts.

[0137] The scheme generation unit iterates through the alternative adjustment demands and generates a transportation scenario evolution sequence based on two objectives: first, the transportation scenario evolution is beneficial to prompting relevant personnel to accept the next stage of path adjustment scheme, which means that after viewing the evolution sequence, the decision-making thought of the relevant personnel is guided into the next path adjustment stage; for example, in the process of dangerous goods transportation, the evolution sequence provided by the scheme generation unit shows real-time data that the road ahead is wet and slippery due to heavy rain and limited visibility, which prompts the relevant personnel to quickly identify the risk level of continuing the original route after viewing, thereby guiding them to accept the adjustment scheme of the alternative route. Second, the transportation scenario evolution is beneficial to prompting relevant personnel to resolve unsolved adjustment conflicts, which means that after viewing the evolution sequence, the decision-making thought of the relevant personnel is guided to resolve the unsolved adjustment conflicts; for example, if there is a disagreement among relevant personnel on whether to choose a longer but safer detour route when handling a dangerous goods transportation path adjustment, one party believes that timeliness should be prioritized, and the other party believes that safety must be prioritized; at this time, the evolution sequence provided by the scheme generation unit contains quantitative comparison data on the risk level of the original route and the time cost of the alternative route, helping relevant personnel to fully understand the current situation and potential risks, thereby prompting all parties to reach an agreement under the guidance of the data and ultimately decide to use a safer route to avoid potential accident risks.

[0138] The beneficial effects of the above technical solution are: when generating a dynamic adjustment scheme, the transportation scenario evolution sequence is introduced to quickly show the implementation effect of the adjustment scheme and identify unsolved adjustment conflicts, and finally the final dynamic adjustment scheme is generated from two aspects: beneficial to prompting relevant personnel to accept the next stage of path adjustment and beneficial to prompting relevant personnel to resolve unsolved adjustment conflicts, which enables dangerous goods road transportation to effectively respond to real-time road condition changes or emergencies, greatly improving the safety, timeliness and economy of dangerous goods road transportation, and improving the practical value of the system.

[0139] In another embodiment, the demand matching unit comprises:

[0140] a demand generation subunit configured to generate candidate adjustment demands based on key characteristic parameters of real-time road condition changes or emergency inputs, in combination with adjustment demand generation templates and historical optimization results;

[0141] a priority setting subunit configured to set the template weight of the adjustment demand generation template based on which the candidate adjustment demands are generated as the corresponding priority.

[0142] The working principle of the above technical solution is that the demand generation subunit receives key characteristic parameters of real-time road condition changes or emergency inputs, which include road congestion degree, weather conditions, accident conditions, and other road condition information related to dangerous chemical transportation. The demand generation subunit matches these parameters with pre-set adjustment demand generation templates, and generates multiple candidate adjustment demands in combination with historical optimization results. The adjustment demand generation template is a standardized template pre-established by the system based on past dangerous chemical transportation route adjustment experience, which contains optimal adjustment schemes under different road conditions. For example, when the system detects that the road ahead is wet and slippery due to rain and snow weather, the demand generation subunit will generate candidate adjustment demands including reducing the driving speed, replacing the route with a higher safety factor, etc. based on the corresponding adjustment demand generation template.

[0143] The priority setting subunit is responsible for assigning reasonable priorities to each of the generated candidate adjustment demands, so that the system can process these demands in order of importance. The priority setting subunit sets the template weight of the adjustment demand generation template based on which the candidate adjustment demands are generated as the corresponding priority. The template weight is pre-set by technical personnel based on dangerous chemical transportation safety standards, historical accident data, and expert experience, reflecting the importance of different adjustment demands in ensuring transportation safety and efficiency. For example, the template for handling dangerous chemical leakage risks may have the highest weight, while the route fine-tuning template for minor traffic congestion may have a relatively low weight.

[0144] The beneficial effects of the above technical solution are that by introducing a demand matching unit with real-time response capability, adaptive adjustment demands can be quickly generated according to dynamic changes in road conditions, and reasonable priorities can be established based on a professional knowledge system, achieving multi-objective dynamic optimization of dangerous chemical transportation paths. This technology not only improves the adaptability and response speed of the system to complex road conditions, but also enhances the standardization and consistency of adjustment decisions through template processing, significantly improving the safety, efficiency, and reliability of dangerous chemical road transportation, and has strong practical value.

[0145] In another embodiment, the data acquisition module comprises:

[0146] The demand collection submodule is configured to acquire dangerous chemical product transportation demand information including dangerous chemical product type, quantity, and transportation time requirement;

[0147] The network collection submodule is configured to acquire road network information including road node, road segment characteristic of connecting node, real-time traffic condition, and environmental parameter;

[0148] The data integration submodule is configured to integrate the dangerous chemical product transportation demand information and the road network information to generate a basic data set.

[0149] The working principle of the above technical solution is that the basic data set construction strategy refers to a pre-set data integration standard matched with dangerous chemical product transportation, which can be pre-set by technical personnel according to previous experience of constructing data sets in different dangerous chemical product transportation scenarios; the construction strategy is used to guide the collaborative work of the demand collection submodule and the network collection submodule to ensure that the acquired information can meet the calculation requirement of multi-objective path optimization;

[0150] The demand collection submodule acquires dangerous chemical product transportation demand information including dangerous chemical product type, quantity, and transportation time requirement; the demand collection submodule acquires specific dangerous chemical product transportation demand through interface connection with enterprise management system or manual input by user, the dangerous chemical product type determines the safety risk level in the transportation process, the quantity affects the selection of transportation vehicle and path planning, and the transportation time requirement provides a time constraint condition for path optimization; for example, a chemical enterprise needs to transport a batch of flammable liquid with a total weight of 15 tons and requires delivery within 48 hours, and this information acquired by the demand collection submodule will be used as a basic condition for path planning;

[0151] The network collection submodule acquires road network information including road node, road segment characteristic of connecting node, real-time traffic condition, and environmental parameter; the network collection submodule acquires static information and dynamic information of road network by connecting with a traffic monitoring system, the static information includes road segment characteristics such as road grade, speed limit, road width, slope, and curve radius, and the dynamic information includes real-time traffic flow, accident information, weather condition, and construction area; for example, the K85-K120 section of a certain expressway is wet and slippery due to heavy rain, the traffic flow is large, and the traffic speed is reduced, and the network collection submodule acquires these information in real time and transmits them to the data integration submodule;

[0152] The data integration submodule associates and matches hazardous chemical transportation demand information with road network information to generate a basic dataset. Based on the matching rules between hazardous chemical types and road safety levels, the data integration submodule associates demand information with network information to form a multi-dimensional data structure. For example, for flammable and explosive hazardous chemicals, the system automatically marks the risk level of special road sections such as tunnels and bridges, and calculates the passage time in combination with real-time traffic conditions, ultimately forming a network data structure containing nodes, edges, and weights, which serves as the input for the path optimization algorithm.

[0153] The beneficial effects of the above technical solution are as follows: When constructing the basic dataset for hazardous chemical transportation, the embodiments of the present invention introduce a two-way correlation mechanism between demand information and network information. Hazardous chemical attribute parameters are obtained through the demand acquisition submodule, and road condition changes are captured in real time by the network acquisition submodule. Finally, the data integration submodule intelligently matches and merges the two types of information, enabling the basic dataset to comprehensively reflect the safety risks and efficiency factors of hazardous chemical transportation. This provides accurate, dynamic, and comprehensive data support for subsequent multi-objective path optimization, significantly improves the rationality and safety of path planning, and enhances the system's adaptability to complex road environments.

[0154] In another embodiment, a multi-objective route optimization method for road transportation of hazardous chemicals includes:

[0155] S1: Obtain information on hazardous chemical transportation demand and road network information to generate a basic dataset;

[0156] S2: Based on the basic dataset, perform collaborative optimization of path planning and risk management to generate an optimized solution;

[0157] S3: Based on the optimized plan, generate the final transportation route, schedule and emergency plan, and dynamically adjust them according to real-time traffic conditions.

[0158] The working principle of the above technical solution is as follows: When a hazardous chemical transportation request is received, the matching relationship between the characteristics of the hazardous chemicals and the road network environment parameters is analyzed to construct a basic dataset suitable for the safe transportation of hazardous chemicals. In the data acquisition module, the hazardous chemical transportation request covers information such as the type of hazardous chemicals, physical and chemical properties, quantity, loading status, origin and destination, and arrival time limit. The road network environment parameters include road classification, number of lanes, road surface conditions, height and width restrictions, traffic capacity, distribution of sensitive areas along the route, meteorological conditions, and traffic flow variation patterns. The matching relationship analysis establishes a quantitative index of the adaptability of hazardous chemical characteristics to the road environment by evaluating the transportation risk coefficient of different hazardous chemicals under various road conditions. The basic dataset is stored in a multi-level graph structure, where nodes represent road intersections or key landmarks, edges represent road segments connecting nodes, and each edge is accompanied by multi-dimensional attribute information, including distance, travel time, risk coefficient, and traffic restriction regulations.

[0159] Based on the constructed basic data set, a pre-trained multi-objective collaborative optimization algorithm is started to balance the transportation time, cost and safety risk, and a multi-gradient trade-off optimization scheme set is generated; in the multi-objective optimization module, the multi-objective collaborative optimization algorithm adopts a hybrid strategy combining improved genetic algorithm and simulated annealing, and finds a Pareto optimal solution set through iterative calculation; the optimization objective function includes three dimensions of time loss function, economic cost function and risk assessment function; the time loss function considers time factors such as road travel time, loading and unloading time, rest time, waiting time, etc.; the economic cost function takes into account economic factors such as fuel consumption, toll, labor cost, equipment wear and tear, etc.; the risk assessment function quantifies the safety risks that may be faced in the transportation process, such as leakage accidents, fires and explosions, traffic accidents, etc., and combines the population density along the line and environmental sensitivity for weighted processing; the multi-gradient trade-off optimization scheme set provides alternative schemes under different decision preferences, allowing decision makers to select the most suitable transportation strategy according to actual needs;

[0160] According to the optimization scheme set, real-time traffic conditions and weather change information are fused to generate fine transportation path planning and dynamic response mechanism, realizing controllable transportation of dangerous goods and rapid handling of emergency situations; in the path generation module, the fine transportation path planning includes main path design and alternative path preparation, and assigns recommended speed, stopping point location and rest time arrangement for each road section; the dynamic response mechanism interacts with the vehicle sensor and the traffic management system data to monitor abnormal situations in the transportation process in real time; when encountering traffic congestion, bad weather, road construction and other situations, the system automatically assesses the impact and makes local path adjustments within the preset threshold range, and exceeds the threshold to switch to the alternative path; the rapid handling process of emergency situations pre-plans the evacuation channel in the dangerous area, the emergency rescue resource allocation scheme, the professional disposal team linkage mechanism, and formulates the targeted emergency disposal plan according to the type of dangerous goods; the controllable transportation realizes information sharing and collaborative decision-making of regulatory departments, transportation enterprises and vehicle drivers through positioning tracking, state monitoring and remote control, greatly improving the safety and reliability of dangerous goods road transportation.

[0161] The beneficial effects of the above technical solutions are: by introducing the collaborative optimization mechanism of risk control and path planning, the optimal path balancing transportation efficiency and safety is quickly generated based on the multi-objective optimization algorithm, and dynamic adjustment is made combined with real-time traffic information, effectively solving the problem of single objective optimization in traditional dangerous goods transportation path planning, significantly improving the safety, reliability and efficiency of dangerous goods road transportation, reducing the potential risk exposure, and providing comprehensive technical support for dangerous goods transportation management.

[0162] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application.

Claims

1. A multi-objective path optimization system for hazardous chemical road transportation, characterized in that, The application relates to a hazardous chemical transportation path planning and risk management system. The system comprises: a data acquisition module for acquiring hazardous chemical transportation demand information and road network information and generating a basic data set; a multi-objective optimization module for collaborative optimization of path planning and risk management based on the basic data set and generating an optimized scheme; the multi-objective optimization module comprises: a scenario traversal submodule for sequentially traversing various hazardous chemical transportation scenarios and dividing multiple operating states according to different time periods and weather conditions; an optimization training submodule for determining the optimization results of the optimization model in safety management and path planning for each operating state and taking all operating states and collaborative optimization as the training basis of the optimization model; the optimization training submodule comprises: a safety optimization unit for interacting with a simulation environment based on a preset safety management action space, generating a risk assessment result and updating safety management parameters, and determining an optimization scheme that minimizes safety risks and environmental impacts; a path optimization unit for interacting with a simulation environment based on a preset path selection action space, generating a path planning result and updating path planning parameters, and determining an optimization scheme that minimizes transportation costs and safety risks; and an integration unit for integrating the optimization schemes of the safety management parameters and the path planning parameters as the collaborative optimization basis for the current operating state; a path generation module for generating a final transportation path, a time schedule and an emergency plan based on the optimized scheme and dynamically adjusting according to real-time road conditions; the path generation module further comprises: a dynamic adjustment submodule for generating a dynamic adjustment scheme based on changed road network information when detecting real-time road condition changes or emergencies; a communication warning submodule for establishing real-time communication between alternative routes and relevant personnel based on the dynamic adjustment scheme, sending warning information to the relevant personnel and updating the transportation scheme; the dynamic adjustment submodule comprises: a demand matching unit for pre-matching an adjustment demand template based on real-time road condition changes or emergency events and determining multiple alternative adjustment demands and their priorities according to historical optimization results; a scheme generation unit for sequentially traversing the alternative adjustment demands, generating a transportation scenario evolution sequence and displaying the evolution process, and generating a dynamic adjustment scheme according to the selected transportation scenario of the relevant personnel; the demand matching unit comprises: a demand generation submodule for generating alternative adjustment demands based on the key feature parameters input by real-time road condition changes or emergencies, combining the adjustment demand generation template and historical optimization results; 2. The multi-objective path optimization system for the hazardous material road transport according to claim 1, characterized in that, a priority setting submodule for taking the template weight of the adjustment demand generation template based on which the alternative adjustment demand is generated as the corresponding priority. The safety optimization unit comprises: a risk analysis submodule for identifying key influencing factors of safety risks and environmental impacts in the risk assessment result, determining a risk set therefrom, and taking the highest level risk in each risk set as a management optimization target; 3. The multi-objective path optimization system for the hazardous material road transport according to claim 1, characterized in that, a parameter adjustment submodule for taking the corresponding management optimization target as a risk point that needs to be further optimized and adjusting the safety management parameters if a standard operating state representing that the management optimization target has been alleviated does not appear in the subsequent simulation environment. The path generation module comprises: The path ranking submodule is configured to rank all the optional paths from low to high in terms of safety risks and transportation costs according to the path planning result and the risk control scheme in the optimization scheme, and obtain an optimized path sequence. The path selection submodule is configured to divide the optimized path sequence into a plurality of local path groups, select a path with the highest safety and the lowest cost from each local path group in sequence, and generate a final optimized transportation path and match a time arrangement and an emergency plan.

4. The multi-objective path optimization system for hazardous material road transport of claim 1, wherein, The data acquisition module comprises: The demand acquisition submodule is configured to acquire dangerous chemical product transportation demand information including dangerous chemical product types, quantities, and transportation time requirements. The network acquisition submodule is configured to acquire road network information including road node, road segment characteristics of connection nodes, real-time road conditions, and environmental parameters. The data integration submodule is configured to integrate the dangerous chemical product transportation demand information and the road network information to generate a basic data set.

5. A multi-objective path optimization method for dangerous goods road transportation applied to the system of any one of claims 1 to 4, characterized in that, The method comprises: S1: acquiring dangerous chemical product transportation demand information and road network information to generate a basic data set; S2: performing collaborative optimization of path planning and risk control based on the basic data set to generate an optimization scheme; Specifically, the method comprises: sequentially traversing various dangerous chemical product transportation scenarios, and dividing a plurality of running states according to different time periods and weather conditions; determining optimization results of the optimization model in safety control and path planning for each running state, and taking all the running states and the collaborative optimization basis as a training basis of the optimization model; specifically, based on a preset safety control action space and a simulation environment, a risk assessment result is generated and safety control parameters are updated, an optimization scheme minimizing safety risks and environmental impacts is determined, based on a preset path selection action space and the simulation environment, a path planning result is generated and path planning parameters are updated, an optimization scheme minimizing transportation costs and safety risks is determined, and the optimization schemes of the safety control parameters and the path planning parameters are integrated as a collaborative optimization basis for the current running state; S3: generating a final transportation path, a time arrangement, and an emergency plan based on the optimization scheme, and dynamically adjusting according to real-time road conditions; The method further comprises: when a real-time road condition change or an emergency event is detected, generating a dynamic adjustment scheme based on changed road network information; specifically, based on key feature parameters input by the real-time road condition change or the emergency event, combining generated templates and historical optimization results to generate alternative adjustment requirements, taking a template weight of an adjustment requirement generation template based on which the alternative adjustment requirements are generated as a corresponding priority, sequentially traversing the alternative adjustment requirements, generating a transportation situation evolution sequence and displaying an evolution process, and generating a dynamic adjustment scheme according to a selected transportation situation by relevant personnel; based on the dynamic adjustment scheme, establishing real-time communication between alternative routes and relevant personnel, sending warning information to the relevant personnel, and updating the transportation scheme.

Images