Traffic dispatching method and system for tunnel construction scenarios based on smart transportation

Abstract

The present invention discloses a traffic scheduling method and system for tunnel construction scenarios based on smart transportation. The method includes: obtaining a set of vehicle status data for each traffic node in the tunnel construction area; performing dynamic scheduling processing on the vehicle status data set; generating a set of traffic light control instructions corresponding to each traffic node; executing a scheduling strategy generation process based on the traffic light control instruction set to obtain a global traffic scheduling strategy for the tunnel construction area; and feeding the global traffic scheduling strategy back to the traffic light control system in the tunnel construction area to instruct the traffic light control system to execute traffic node traffic status switching operations according to a preset time window. This method can improve the problems of delayed scheduling instructions and low resource utilization.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of smart transportation technology, and specifically to a traffic scheduling method and system for tunnel construction scenarios based on smart transportation. Background Art

[0002] During tunnel construction, the simultaneous advancement of multiple working faces creates a high-density cross-traffic demand for construction vehicles within limited channels. Traditional traffic dispatching technologies, which rely heavily on manual command or fixed-time signal light control, struggle to adapt to the dynamic changes in construction processes and vehicle flow distribution. This is especially true at the intersection of the main line and auxiliary tunnels, where the equipment dispatching demands of different construction faces overlap, easily leading to inefficient conditions where traffic jams and idle machinery coexist. Consequently, when faced with complex construction scenarios involving multiple parallel processes, existing technologies often suffer from issues such as delayed dispatching instructions and low resource utilization. This often makes it difficult to quickly generate optimized solutions that balance construction progress and traffic efficiency, severely restricting the construction efficiency of large-scale tunnel projects. Summary of the Invention

[0003] The embodiments of the present invention provide a traffic scheduling method and system for tunnel construction scenarios based on smart transportation, which is used to quickly generate a global traffic scheduling strategy that takes into account both construction progress and traffic efficiency, thereby improving the problems of delayed scheduling instructions and low resource utilization.

[0004] In a first aspect, an embodiment of the present invention provides a traffic scheduling method for a tunnel construction scenario based on smart transportation, which is applied to a traffic scheduling system for a tunnel construction scenario. The method includes: obtaining a vehicle status data set for each traffic node in a tunnel construction area, the vehicle status data set including vehicle traffic records and vehicle identity identification captured in real time by an RFID reader array deployed at a fixed position, the vehicle traffic records including the time the vehicle enters the tunnel, the time the vehicle leaves the tunnel, and the position coordinates of the traffic node at which the vehicle is located; dynamically scheduling the vehicle status data set to generate a traffic light control instruction set corresponding to each traffic node, the traffic light control instruction set being used to adjust the traffic priority and vehicle release interval duration of the corresponding traffic node; executing a scheduling strategy generation process based on the traffic light control instruction set to obtain a global traffic scheduling strategy for the tunnel construction area, the global traffic scheduling strategy including a vehicle traffic route optimization plan and an equipment resource allocation plan associated with different construction faces; and feeding back the global traffic scheduling strategy to a traffic light control system in the tunnel construction area to instruct the traffic light control system to execute a traffic node traffic status switching operation according to a preset time window.

[0005] In a second aspect, an embodiment of the present invention provides a tunnel construction scenario traffic dispatching system, including:

[0006] processor;

[0007] a storage device having a computer program stored thereon,

[0008] When the computer program is executed by the processor, the processor implements any of the traffic scheduling methods for tunnel construction scenarios based on smart transportation.

[0009] An embodiment of the present invention provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the traffic scheduling method for tunnel construction scenarios based on smart transportation are implemented.

[0010] It can be seen that the embodiments of the present invention have the following beneficial effects: First, by deploying a fixed RFID reader array, the vehicle position coordinates, identity identification and traffic time series data are collected in real time, and a multi-dimensional dynamic traffic situation awareness network is constructed, which breaks through the technical difficulties of information lag and positioning ambiguity in traditional manual scheduling. Secondly, based on the real-time captured vehicle spatiotemporal trajectory data, the dynamic scheduling algorithm is used to autonomously generate traffic node priority parameters and release interval parameters, so as to achieve dynamic adaptation of the traffic strategy of each intersection and the construction process, and effectively solve the path conflict problem of multi-face construction vehicles at the intersection node; then, by integrating the control instruction set of the global traffic nodes, a global optimization model for the construction process is constructed, and a comprehensive strategy that takes into account the optimization of vehicle traffic routes and the coordinated allocation of equipment resources is generated, which significantly improves the collaborative operation efficiency of construction machinery; finally, the traffic state switching is accurately controlled through the preset time window, forming a dynamic coupling mechanism between the construction process and traffic scheduling, and providing a complete spatiotemporal trajectory data chain for vehicle operation efficiency evaluation.

[0011] In summary, the embodiments of the present invention, through the deep integration of non-invasive data collection and intelligent decision-making, can quickly generate a global traffic scheduling strategy that takes into account both construction progress and traffic efficiency, and based on the global traffic scheduling strategy, instruct the traffic light control system to execute the switching operation of the traffic node traffic status according to the preset time window, thereby realizing the adaptive dynamic reorganization of the construction traffic flow, significantly reducing the vehicle idle rate while ensuring construction safety, thereby improving the problems of scheduling instruction lag and low resource utilization, and providing multi-dimensional data support for project cost analysis and resource optimization allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A flow chart of a traffic scheduling method for tunnel construction scenarios based on smart transportation provided by an embodiment of the present invention.

[0013] Figure 2 A schematic diagram of the basic structure of a traffic dispatching system for a tunnel construction scenario provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0014] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0015] See also Figure 1 As shown in FIG, this figure is a flow chart of a tunnel construction scene traffic scheduling method based on smart transportation provided by an embodiment of the present invention. The method can be applied to a tunnel construction scene traffic scheduling system. Figure 1 As shown, the method may include steps S110 to S140.

[0016] Step S110: Acquire a set of vehicle status data of each traffic node in the tunnel construction area.

[0017] Optionally, the vehicle status data set includes vehicle traffic records and vehicle identification tags captured in real time by an RFID reader array deployed at a fixed position, and the vehicle traffic records include the time when the vehicle enters the tunnel, the time when the vehicle leaves the tunnel, and the location coordinates of the traffic node where the vehicle is located.

[0018] Optionally, a tunnel construction project may contain multiple traffic nodes, such as M, N, and P. Multiple RFID reader arrays are deployed at the intersection of the tunnel mainline and auxiliary tunnels within the tunnel construction area. Each RFID reader array includes a directional antenna and a signal enhancement module. The directional antennas are responsible for capturing the identification codes of vehicle electronic tags. For example, eight RFID reader arrays are deployed, distributed at key locations within the intersection. Simultaneously, infrared cameras at each traffic node are activated to capture vehicle outline images and license plate information. For example, at traffic node M, the infrared camera captures 30 frames of vehicle outline images per minute and performs license plate recognition. The captured license plate information is then cross-verified with the identification code captured by the RFID reader array. If the identification code captured by the RFID reader array for a vehicle is "V003" and the license plate captured by the infrared camera is "Plate XXXXX," the two are cross-verified to confirm the vehicle's identity. If the cross-verification detects damage to the electronic tag or signal loss, the vehicle outline image captured by the infrared camera is used to perform vehicle type matching and compensation to generate a supplemental vehicle identity. If a vehicle's electronic tag signal is lost, it can be identified as a dump truck through matching with the vehicle model database, generating a supplementary vehicle ID "ZXC-005." Finally, the timestamps of the cross-validated vehicle IDs and vehicle traffic records are aligned to form a vehicle status data set. For example, if a vehicle enters a tunnel at 2:00 PM, the timestamp at traffic node N is recorded as 14:05:15. It leaves the tunnel at 3:00 PM, with the timestamp at traffic node P recorded as 14:35:20. This time information is then associated with the vehicle ID "V003" to form the vehicle status data set.

[0019] In an optional embodiment, step S110 of obtaining a set of vehicle status data of each traffic node in the tunnel construction area includes:

[0020] Step S111: deploy multiple groups of RFID reader arrays at the intersection of the tunnel main line and the auxiliary tunnel in the tunnel construction area. Each group of RFID reader arrays includes a directional antenna and a signal enhancement module. The directional antenna is used to capture the identification code of the vehicle electronic tag.

[0021] In the tunnel construction area, analysis of the terrain and vehicle traffic paths determined the optimal placement of RFID reader arrays at the intersection of the tunnel's mainline and auxiliary tunnels. For example, based on past construction experience and traffic flow simulations, a set of RFID reader arrays was deployed at each of the four corners and the center of the intersection. The directional antennas of each RFID reader array were tuned to ensure their coverage effectively captures the electronic tag identification codes of passing vehicles. For example, the directional antennas of one corner RFID reader array were adjusted to cover the electronic tag signals of vehicles within a 5-meter radius around that corner, ensuring accurate capture of the identification codes of all passing vehicles.

[0022] Step S112: Synchronously start the infrared camera device deployed at the traffic node to collect the vehicle outline image and license plate recognition information, and cross-verify the license plate recognition information with the identification code captured by the RFID reader array.

[0023] Optionally, infrared cameras and RFID reader arrays at traffic nodes are activated synchronously. At each traffic node, such as Traffic Node Q, the infrared cameras capture vehicle outline images at a rate of 15 frames per second. Simultaneously, the license plate recognition system processes these images in real time to extract license plate information. For example, when a vehicle passes through Traffic Node Q, the infrared camera rapidly captures multiple frames of vehicle outline images, from which the license plate recognition system identifies the license plate as "License Plate YYYYY." This license plate recognition information is then cross-verified with the vehicle identification code "V007" captured by the RFID reader array, and the accuracy of the vehicle's identity is confirmed by comparing it with a pre-stored vehicle information database.

[0024] Step S113: When the cross-validation result indicates that the electronic tag is damaged or the signal is lost, the vehicle outline image captured by the infrared camera device is activated to perform vehicle type matching compensation to generate a supplementary vehicle identity.

[0025] If the cross-validation process detects damage to the electronic tag or signal loss, the vehicle's outline image, captured by the infrared camera, is used for processing. For example, at traffic node R, a vehicle passes through, but the RFID reader array fails to capture a valid identification code. However, the infrared camera captures a clear image of the vehicle's outline. This image is compared with a pre-established vehicle model database, which stores the outline features of various vehicle models. A detailed comparison of the vehicle's dimensions, body structure, and other features confirms that the vehicle is a concrete mixer truck. A supplementary vehicle identification code, "JBC-008," is then generated based on pre-set rules to ensure the integrity of the vehicle information.

[0026] Step S114: performing time stamp alignment processing on the vehicle identity identifiers and vehicle travel records that have passed the cross-validation to form the vehicle status data set.

[0027] For vehicles that pass cross-validation, the timestamps of their ID and traffic records are aligned. For example, vehicle "V009" enters the tunnel at 16:00, with a timestamp of 16:03:45 at traffic node S. It leaves the tunnel at 17:00, with a timestamp of 16:40:30 at traffic node T. This accurate time information is associated with the vehicle ID "V009" and organized in chronological order to form a complete vehicle status data set. This vehicle status data set contains detailed information about the vehicle at each traffic node at different time points, serving as the data foundation for subsequent scheduling.

[0028] Step S120: performing dynamic scheduling processing on the vehicle status data set to generate a traffic light control instruction set corresponding to each traffic node.

[0029] Optionally, the traffic light control instruction set is used to adjust the traffic priority and vehicle release interval duration of the corresponding traffic node.

[0030] In an embodiment of the present invention, after obtaining a set of vehicle status data, it is dynamically scheduled to generate a set of traffic light control instructions. First, the vehicle type code and equipment loading parameters in the vehicle identification are parsed, and the priority level of each vehicle is determined based on the vehicle type code. The theoretical travel time of the vehicle through the current traffic node is calculated according to the equipment loading parameters. For example, the vehicle type code of the vehicle identification "V010" is "YLJ", which means a road roller, and the equipment loading parameters show that it is loaded with 8 tons of equipment. According to the pre-set traffic priority rules, the traffic priority of the road roller is medium. At the same time, the theoretical travel time of the vehicle through the current traffic node can be calculated as 3 minutes based on factors such as the equipment loading weight and the road conditions of the traffic node.

[0031] In one implementation, step S120 performs dynamic scheduling processing on the vehicle status data set to generate a traffic light control instruction set corresponding to each traffic node, including:

[0032] Step S121: parse the vehicle type code and equipment loading parameters in the vehicle identity, determine the passage priority level of each vehicle based on the vehicle type code, and calculate the theoretical passage time of the vehicle through the current traffic node according to the equipment loading parameters.

[0033] Taking vehicle "V011" as an example, its vehicle type code in the vehicle identification is "SZJ," representing a water sprinkler truck. According to a pre-defined vehicle type and traffic priority comparison table, a water sprinkler truck, due to its specialized operation, is assigned a higher priority (e.g., the second-highest priority). Its equipment loading parameters indicate a water tank capacity of 10 cubic meters. Taking into account factors such as the road width and slope at the traffic node, as well as the vehicle's own performance, the theoretical travel time for this vehicle to pass through the current traffic node is calculated. The calculation process begins by first calculating the average speed of vehicles at the traffic node based on previous records, assuming that each cubic meter of water increases driving resistance by a certain percentage and reduces vehicle speed. Taking into account the speed limit at the traffic node, the average speed of vehicles at the traffic node is calculated. For example, a normal vehicle speed of 20 km / h is reduced to 15 km / h due to the 10 cubic meters of water in the water tank. The length of the traffic node is 500 meters. Based on the equation "time = distance ÷ speed," the theoretical travel time is 0.5 ÷ 15 × 60 = 2 minutes.

[0034] In another exemplary application scenario, traffic priority can be divided into five levels: high, high, medium, low, and low. The corresponding vehicle types are as follows:

[0035] (1) Higher priority: Special vehicles transporting hazardous materials, such as vehicles transporting flammable and explosive hazardous materials, need priority in ensuring their passage due to the special nature and danger of their transportation tasks; emergency rescue vehicles are used to respond to sudden emergencies during tunnel construction to ensure construction safety and the safety of life and property of personnel.

[0036] (2) High priority: Concrete mixer trucks, due to the characteristics of concrete, need to be transported to the construction site in a timely manner to ensure the quality of the concrete and the construction progress; large equipment transport vehicles, such as vehicles transporting large construction machinery, the equipment they transport is crucial to the construction process, and they have a greater impact on traffic during driving, so they need to be given priority for passage.

[0037] (3) Medium priority: Loaders and dump trucks are commonly used transport vehicles in tunnel construction and operate more frequently, but the urgency and importance of their transport tasks are slightly lower than those of high-priority vehicles; road rollers play a role in road construction and maintenance and have a certain impact on the construction progress, but their traffic priority is at a medium level.

[0038] (4) Low priority: Small trucks are usually used to transport some auxiliary materials or tools. The transportation volume is relatively small and the impact on the construction progress is relatively small. Sprinkler trucks are mainly used for dust reduction operations. Although they play an important role in the construction environment, their operation time and routes are relatively flexible and their traffic priority is low.

[0039] (5) Lower priority: Temporary vehicles not related to construction, such as inspection vehicles and maintenance vehicles that occasionally enter the tunnel construction area, whose traffic needs are not as urgent and important as those of construction vehicles.

[0040] Step S122: Based on the traffic priority level and the theoretical traffic time, a dynamic sorting model for a multi-vehicle queue in a traffic node is constructed. The dynamic sorting model is used to output initial scheduling parameters including the traffic priority order and the basic release interval time.

[0041] At traffic node U, several vehicles are waiting to pass, including "V012" (a loader with medium priority and a theoretical travel time of 4 minutes), "V013" (a dump truck with high priority and a theoretical travel time of 3 minutes), and "V014" (a minivan with low priority and a theoretical travel time of 2 minutes). These vehicle priorities and theoretical travel times are input into a dynamic sorting model, which can be implemented using a greedy algorithm. The dynamic sorting model first performs a preliminary sorting based on travel priority, placing the dump truck "V013" first due to its high priority, followed by the loader "V012," and finally the minivan "V014." The basic release interval duration is then calculated based on factors such as the theoretical travel time and the traffic node's capacity. For example, the maximum traffic capacity of traffic node U is 2 vehicles per minute. Taking into account factors such as vehicle startup and acceleration, the basic release interval is calculated as follows: after the dump truck "V013" is released, the loader "V012" is released after an interval of 1 minute, and the small truck "V014" is released after an interval of another 1 minute. The initial scheduling parameters including the traffic priority order and the basic release interval are output.

[0042] Step S123: Collecting real-time environmental parameters of the tunnel construction area, the real-time environmental parameters include dust concentration data and construction machinery displacement, and dynamically compensating the basic release interval based on the real-time environmental parameters to obtain the compensated release interval.

[0043] In the tunnel construction area, dust concentration sensors and construction machinery displacement monitoring equipment are installed to collect real-time environmental parameters. For example, at a certain moment, the dust concentration sensor indicates a dust concentration of 50 mg / m³ near traffic node V. The construction machinery displacement monitoring equipment detects a large excavator moving significantly near this traffic node, impacting road traffic. According to pre-set compensation rules, when the dust concentration exceeds 30 mg / m³, the basic release interval increases by 30 seconds for every 10 mg / m³ increase. When the construction machinery displacement impacts road traffic to a certain percentage, the basic release interval increases by an additional minute. For vehicles with an original basic release interval of 1 minute, calculations show that the increase of 30 seconds due to dust concentration and an additional minute due to construction machinery displacement results in a release interval of 2 minutes and 30 seconds after compensation.

[0044] Step S124: performing instruction fusion processing on the traffic priority sequence and the compensated release interval duration to generate a traffic light control instruction set including a traffic priority mapping relationship and a dynamic release interval duration.

[0045] The priority order and compensated release interval calculated at traffic node W are integrated. For example, vehicles "V015" (high priority, compensated release interval of 2 minutes), "V016" (medium priority, compensated release interval of 3 minutes), and "V017" (low priority, compensated release interval of 4 minutes) are organized into a command format to form a traffic light control command set. This traffic light control command set contains a mapping relationship between traffic priorities, that is, it clearly defines the corresponding traffic order of vehicles with different priorities. It also includes dynamic release intervals, such as a green light release time of 2 minutes for vehicle "V015", a green light release time of 3 minutes for vehicle "V016", and a green light release time of 4 minutes for vehicle "V017". The traffic light control system adjusts the traffic status of the traffic node according to these commands.

[0046] Step S130: executing a scheduling strategy generation process according to the traffic light control instruction set to obtain a global traffic scheduling strategy for the tunnel construction area.

[0047] Optionally, the global traffic scheduling strategy includes vehicle route optimization schemes and equipment resource allocation schemes associated with different construction faces.

[0048] Specifically, the equipment resources involved in the equipment resource allocation plan primarily include various types of engineering vehicles used during tunnel construction, such as loaders, dump trucks, concrete mixers, water trucks, and road rollers, as well as construction machinery such as excavators and cranes. Furthermore, the equipment resource allocation plan dynamically adjusts the deployment density, usage time, and allocation location of these equipment based on construction schedule data, vehicle operating efficiency, and the needs of different construction faces. For example, when the demand for material transportation increases at a certain construction face, the number of transport vehicles such as loaders and dump trucks in that area will be increased accordingly. Based on the operating hours and task schedules of construction machinery, the use of equipment such as cranes will be rationally allocated to ensure coordinated operation and improve construction efficiency.

[0049] In this embodiment of the present invention, a scheduling strategy is generated based on the generated set of traffic light control instructions to obtain a global traffic scheduling strategy. First, the vehicle operation duration and tunnel entry and exit times in the vehicle traffic records are counted. The vehicle operation duration is the difference between the time a vehicle enters the tunnel and the time it leaves the tunnel. For example, vehicle "V018" enters the tunnel at 6:00 PM and leaves at 8:00 PM, resulting in a vehicle operation duration of 2 hours. The vehicle also enters and exits the tunnel 5 times in a single day.

[0050] Optionally, in one implementation, the step S130 of performing a scheduling strategy generation process according to the traffic light control instruction set to obtain a global traffic scheduling strategy for the tunnel construction area includes:

[0051] Step S131: Counting the vehicle operation time and the number of times the vehicle enters and exits the tunnel in the vehicle passage record, wherein the vehicle operation time is the time difference between the time when the vehicle enters the tunnel and the time when the vehicle leaves the tunnel.

[0052] For example, vehicle "V019" entered the tunnel at 9:30 and exited at 11:45. To calculate the vehicle's operating time, convert the time to minutes: 9:30 is 9 × 60 + 30 = 570 minutes, and 11:45 is 11 × 60 + 45 = 705 minutes. The vehicle's operating time = 705 - 570 = 135 minutes, or 2 hours and 15 minutes. Also, record the vehicle's entry and exit times as three on that day.

[0053] Step S132: generating efficiency indices for different types of vehicles in the tunnel construction area based on the vehicle operation time and the number of times the vehicles enter and exit the tunnel, wherein the efficiency indices are used to evaluate the transportation efficiency of the vehicles in the tunnel construction area.

[0054] Based on data from multiple vehicles, such as "V018" (2 hours of operation, 5 tunnel entries and exits) and "V019" (2 hours and 15 minutes of operation, 3 tunnel entries and exits), efficiency indicators for different vehicle types were generated. For example, for loaders, the operation time and tunnel entry and exit times for 10 loaders were collected. The average operation time per loader was calculated (operation time divided by tunnel entry and exit times). For example, the average operation time for these 10 loaders was 0.4 hours and 0.5 hours, respectively. Based on this data, an overall efficiency index for loader vehicles was calculated. For example, a weighted average was used, taking into account factors such as the importance of the work tasks of different loaders. The final efficiency index for loader vehicles was p (a real number between 0 and 1). This index reflects the transport efficiency of loaders in the tunnel construction area and provides a reference for subsequent resource allocation.

[0055] Step S133: Acquire construction schedule data, wherein the construction schedule data includes a tunnel face excavation stage identifier and a material transportation demand schedule. Based on the tunnel face excavation stage identifier, perform a matching analysis on the efficiency index and the material transportation demand schedule to obtain a matching analysis result.

[0056] In an embodiment of the present invention, construction schedule data is obtained, in which the tunnel face excavation stage identification is divided into three stages: A, B, and C, and the material transportation demand schedule records in detail the transportation time and quantity of materials required for different stages. For example, in tunnel face excavation stage A, 50 tons of stone need to be transported from 10 am to 12 pm. According to the efficiency indicators of different vehicle types calculated previously, such as the efficiency indicator of the loader is to transport 10 tons of stone per hour, the ability of the loader to meet the material transportation demand within this time period is analyzed. The matching degree is calculated by comparing the transportation capacity of the loader with the requirements in the material transportation demand schedule. For example, the loader can actually transport 40 tons of stone within this time period, compared with the required 50 tons, the matching degree = 40 ÷ 50 = 0.8, and the matching degree analysis result is obtained.

[0057] Step S134: Generate a global traffic scheduling strategy including route adjustment parameters and resource allocation parameters based on the matching analysis results, wherein the route adjustment parameters are used to optimize the turning rules of vehicles at intersections in the tunnel construction area, and the resource allocation parameters are used to dynamically adjust the equipment deployment density.

[0058] Specifically, based on the matching analysis results, if the matching degree of the loader is low during face excavation phase A, a global traffic scheduling strategy is generated to meet material transportation needs. Regarding route adjustment parameters, for example, at an intersection in the tunnel construction area, vehicle "V020" (loader) originally followed conventional steering rules. However, to improve transportation efficiency, its steering rules are adjusted, allowing it to reach the stone transportation location more quickly and reducing travel time. Regarding resource allocation parameters, due to insufficient loader transportation capacity, the equipment deployment density is dynamically adjusted, increasing the number of loaders in this area from three to five to ensure that the material transportation task can be completed on time. This results in a global traffic scheduling strategy that incorporates both route adjustment and resource allocation parameters.

[0059] Step S135: Identify the construction team code and equipment lessor ID in the vehicle identification, associate and map the vehicle operation time with the construction team code, and generate a construction team work efficiency statistics table.

[0060] When processing vehicle status data, identify the construction team code and equipment lessor ID in the vehicle identification. For example, the construction team code of vehicle "V021" is "SDW-01", and the equipment lessor ID is "ZL-02". Count the operating hours of all vehicles with the construction team code "SDW-01", such as the operating time of "V021" is 3 hours, the operating time of "V022" is 2.5 hours, etc. The operating hours of these vehicles are aggregated and calculated, and the total operating time of the construction team "SDW-01" is 5.5 hours. According to the preset statistical rules, such as in units of days, count the number of vehicles participating in the operation of the construction team on that day, for example, 5 vehicles. By calculating the ratio of the total operating time to the number of vehicles, the average operating efficiency of each vehicle of the construction team "SDW-01" is obtained, and a construction team work efficiency statistics table is generated. The construction team work efficiency statistics table can reflect the work efficiency of each construction team.

[0061] Step S136: Calculate the equipment utilization index of different lessees based on the equipment lessee identifier and the tunnel entry and exit times. The equipment utilization index is used to generate equipment maintenance cycle recommendations and leased resource statistical tags.

[0062] Optionally, based on the tunnel entry and exit data for vehicle "V021" (equipment lessor identified as "ZL-02" with 4 tunnel entries and exits) and other vehicles identified as "ZL-02," the total tunnel entry and exit count for all vehicles with equipment provided by the "ZL-02" lessor on that day is calculated, for example, 20 times. The total number of devices provided by this lessor on that day is also calculated, for example, 10. By calculating the ratio of total tunnel entry and exit counts to the total number of devices, the equipment utilization index is calculated as 2 times / device. Based on this index, equipment maintenance cycle recommendations are generated, such as recommending shortening the maintenance cycle due to high equipment utilization. A rental resource statistical tag, such as "High-Utilization Equipment Lessor - ZL-02," is also generated to provide a basis for subsequent equipment management and rental resource allocation.

[0063] Step S137: Input the construction team work efficiency statistics table and the equipment utilization rate index into the resource optimization decision model, and output the construction project resource optimization strategy, which includes a human resource deployment plan and an equipment leasing contract revision plan.

[0064] In this step, the generated construction team efficiency statistics and equipment utilization indicators are input into the resource optimization decision model. For example, construction team "SDW-01" has low efficiency, while lessee "ZL-02" has high equipment utilization. The resource optimization decision model analyzes this data and outputs a resource optimization strategy for the construction project. Regarding human resource allocation, consideration is given to assigning more experienced operators to the less efficient construction team "SDW-01" to improve its efficiency. Regarding equipment lease contract revisions, consideration is given to increasing the number of leased equipment or adjusting lease fees for lessee "ZL-02," which has high equipment utilization, to better meet the resource needs of the construction project.

[0065] For example, a resource optimization decision-making model can be understood as an intelligent decision-making model based on data analysis and algorithms. It is used to comprehensively consider multiple factors in a construction project and achieve optimal resource allocation. The model can analyze and process input data such as construction team work efficiency statistics and equipment utilization indicators. For example, by comprehensively evaluating various data such as the work efficiency of different construction teams, equipment usage, and construction schedule requirements, and using algorithms such as linear programming and dynamic programming, it can calculate the optimal allocation plan for human and equipment resources to achieve goals such as improving construction efficiency and reducing costs.

[0066] Step S138: performing data fusion processing on the construction project resource optimization strategy and the global traffic scheduling strategy to update the resource allocation parameters in the global traffic scheduling strategy.

[0067] For example, a construction project resource optimization strategy that calls for increasing the number of loaders in a specific area aligns with the global traffic scheduling strategy's allocation of equipment resources to meet the demands of transporting materials to the tunnel face. During the integration process, the impact of human resource allocation and equipment lease contract revisions in the construction project resource optimization strategy on resource allocation is fully incorporated into the resource allocation parameters of the global traffic scheduling strategy.

[0068] Specifically, if a decision is made to assign more experienced operators to construction team "SDW-01" regarding human resource allocation, this could affect the efficiency of the vehicles used by that team. For example, the team's loaders originally had an average hourly transport capacity of 8 tons, but after the personnel allocation, this capacity is expected to increase to 10 tons. Therefore, within the resource allocation parameters of the global traffic scheduling strategy, the transport capacity assessment of the team's vehicles and the resource allocation weights for material transport tasks would need to be adjusted accordingly.

[0069] Regarding the revised equipment lease agreement, if the number of leased equipment with the "ZL-02" lessor increases, for example, from 10 to 15 units, the resource allocation parameters related to equipment deployment density will need to be updated within the global traffic scheduling strategy. The number of equipment that can be accommodated and effectively deployed at each traffic node and in different construction face areas will be reassessed to ensure that the newly added equipment can be properly allocated to the corresponding construction tasks and transportation routes. This will optimize the overall allocation of resources and better serve the traffic scheduling and construction progress requirements of the tunnel construction, thereby completing the update of the resource allocation parameters within the global traffic scheduling strategy.

[0070] Step S140: Feedback the global traffic scheduling strategy to the traffic light control system in the tunnel construction area to instruct the traffic light control system to execute the switching operation of the traffic node traffic status according to the preset time window.

[0071] After the global traffic scheduling strategy is developed and optimized, it is fed back into the traffic light control system within the tunnel construction area. For example, the global traffic scheduling strategy establishes new traffic rules and traffic light control instructions for traffic node X. This stipulates that during the preset time window from 9:00 AM to 11:00 AM, the green light release time for high-priority vehicles heading to area A at the tunnel face is extended to 90 seconds to ensure timely material transportation.

[0072] After receiving these instructions, the traffic light control system strictly executes the switching operation of the traffic node's traffic status according to the preset time window. At 9:00 AM, the traffic light control system adjusts the signal light status of traffic node X according to the requirements of the global traffic scheduling strategy, turning on the green light for 90 seconds for high-priority vehicles heading to area A of the tunnel face, ensuring that these vehicles can pass through the traffic node smoothly and enter the corresponding construction area. At the same time, for vehicles of other directions and priorities, the traffic light status is accurately switched according to the traffic priority and release interval duration specified by the global traffic scheduling strategy, ensuring the orderly scheduling of traffic throughout the tunnel construction area.

[0073] In an optional embodiment, after obtaining the vehicle status data set of each traffic node in the tunnel construction area in step S110, the method further includes:

[0074] Step S150: performing trajectory reconstruction processing on the vehicle passage record to generate a three-dimensional motion path of the vehicle in the tunnel construction area, wherein the three-dimensional motion path includes time dimension coordinates and space dimension coordinates.

[0075] In this embodiment of the present invention, for example, vehicle "V023" has a travel record containing information about its passage through various traffic nodes at different time points. In terms of time, the vehicle enters traffic node Y at 10:05 and leaves at 10:12; enters traffic node Z at 10:20 and leaves at 10:25; and so on. In terms of space, each traffic node has its corresponding location coordinates. Traffic node Y has coordinates (X1, Y1, Z1), and traffic node Z has coordinates (X2, Y2, Z2).

[0076] By integrating this temporal and spatial information and leveraging existing algorithms and models, a three-dimensional motion path for vehicle "V023" within the tunnel construction area was generated. This 3D motion path not only accurately records the vehicle's spatial position at different moments in time but also intuitively displays its trajectory within the tunnel. For example, the 3D motion path shows that after entering the tunnel from the entrance, vehicle "V023" followed a predefined route, passing through traffic nodes Y and Z, and ultimately reaching area B on the tunnel face.

[0077] Step S151: identifying abnormal stay points and repeated round-trip sections in the three-dimensional motion path, wherein the abnormal stay points represent coordinate points where the vehicle stays in a non-operating area for a period exceeding a preset threshold.

[0078] After generating the 3D motion path of vehicle "V023," the system analyzed it to identify unusual stops and repeated round-trip sections. A threshold of 15 minutes was set, meaning any vehicle remaining in a non-operating area for more than 15 minutes was considered an unusual stop. By examining the temporal and spatial information of the 3D motion path, it was determined that vehicle "V023" remained at coordinates (X3, Y3, Z3) for 20 minutes. This location does not fall within any operating area, and therefore was identified as an unusual stop.

[0079] At the same time, by comparing and analyzing vehicle trajectories, it was determined that vehicle "V023" made multiple round trips on a certain route. For example, on the section between traffic nodes C and D, vehicle "V023" made four round trips within an hour, significantly exceeding normal transportation demand. This section was identified as a repeated round trip section. Identifying these unusual stops and repeated round trips helps identify potential traffic problems within the tunnel construction area.

[0080] Step S152: Generate a traffic flow line optimization suggestion based on the abnormal stop point and the repeated round-trip road section, wherein the traffic flow line optimization suggestion is used to adjust the one-way traffic rules and the temporary roadblock setting location in the tunnel construction area.

[0081] For example, based on the identified unusual stop points and repeated travel times for vehicle "V023," traffic flow optimization recommendations are generated. For the unusual stop points (X3, Y3, Z3), analysis suggests possible reasons for the stoppage, such as traffic congestion or unclear road signs. Therefore, it is recommended to install clear signage near this area to guide vehicles through quickly and avoid unnecessary stops. Furthermore, consideration should be given to adjusting traffic control measures in this area, such as setting up temporary roadblocks to limit the amount of time vehicles can stay there.

[0082] Analysis of the repeated round-trip traffic on this section suggests it may be due to inappropriate transportation route planning or improper construction arrangements. Therefore, it is recommended to adjust the one-way traffic rules within the tunnel construction area. For example, the section between traffic nodes C and D should be set to one-way traffic to reduce vehicle intersection conflicts and improve traffic efficiency. Furthermore, based on the new one-way traffic rules, the placement of temporary roadblocks should be rationally adjusted to ensure that vehicles can follow the prescribed routes, thereby optimizing traffic flow and improving traffic efficiency within the tunnel construction area.

[0083] Step S153: performing a logic check process on the traffic flow optimization suggestion and the global traffic scheduling strategy, and triggering a regeneration operation of the global traffic scheduling strategy when the logic check process indicates that a path conflict is detected.

[0084] For example, a traffic flow optimization proposal proposed setting traffic flow between nodes C and D as one-way, while the global traffic scheduling strategy originally planned multiple vehicle routes through this section, involving two-way traffic. A detailed logical comparison and analysis of the two revealed that this one-way traffic proposal conflicted with some vehicle routes in the global traffic scheduling strategy.

[0085] When such a path conflict is detected, the system automatically triggers the regeneration of the global traffic scheduling strategy. Vehicle status data, construction schedules, and other relevant information are recollected and analyzed, and the adjustments suggested by the traffic flow optimization recommendations are comprehensively considered to replan and formulate the global traffic scheduling strategy. For example, the material transportation needs and vehicle traffic priorities of each construction face are reassessed, and vehicle routes and traffic light control instructions are adjusted to ensure that the newly generated global traffic scheduling strategy not only meets construction needs but also effectively optimizes traffic flow, avoids path conflicts, and ensures smooth traffic flow in the tunnel construction area.

[0086] In another optional embodiment, before feeding back the global traffic scheduling strategy to the traffic light control system of the tunnel construction area, the method further includes:

[0087] Step S160: Acquire historical traffic dispatch strategy execution effect data, wherein the execution effect data includes a reduction ratio of average vehicle waiting time and an improvement range of construction equipment utilization rate.

[0088] In this step, historical data on the effectiveness of traffic scheduling strategies can be obtained from historical data records. For example, traffic scheduling strategies implemented over the past week can be analyzed to calculate the percentage decrease in average vehicle waiting time and the increase in construction equipment utilization. By analyzing detailed records of vehicle waiting times at each traffic node, it can be calculated that before the implementation of a certain historical traffic scheduling strategy, the average vehicle waiting time was 30 minutes. After implementation, the average vehicle waiting time decreased to 20 minutes. The percentage decrease in average vehicle waiting time = (30-20) ÷ 30 ≈ 33.3%.

[0089] At the same time, by monitoring and statistics on the use of construction equipment, it was found that before the implementation of the historical traffic scheduling strategy, the utilization rate of construction equipment was 60%, and it increased to 70% after implementation. The increase in construction equipment utilization rate = (70%-60%) ÷ 60% ≈ 16.7%. These execution effect data can intuitively reflect the actual effectiveness of the historical traffic scheduling strategy and provide an important reference basis for subsequent strategy evaluation and optimization.

[0090] Step S161: establishing a strategy evaluation model based on the execution effect data, wherein the strategy evaluation model is used to calculate the expected benefit value and implementation risk level of different scheduling strategies.

[0091] In this embodiment of the present invention, a strategy evaluation model is established based on historical traffic scheduling strategy execution performance data. This model comprehensively considers the reduction in average vehicle waiting time, the increase in construction equipment utilization, and other relevant factors, such as traffic congestion relief and the on-time completion rate of construction progress.

[0092] For example, the model assigns weights to different factors: a 0.4 weight for the percentage decrease in average vehicle waiting time, a 0.3 weight for the increase in construction equipment utilization, a 0.2 weight for traffic congestion relief, and a 0.1 weight for the on-time completion rate of construction progress. Through quantitative evaluation and weighted calculation of these factors, the expected benefits of different scheduling strategies are derived. At the same time, the implementation risk level is assessed based on issues found in historical data, such as the number of traffic jams, the correlation between equipment failures, and scheduling strategies. For example, if traffic jams frequently occur during the implementation of a historical scheduling strategy, the implementation risk level of that strategy will be increased accordingly in the strategy evaluation model, providing comprehensive evaluation support for the subsequent formulation of more reasonable and effective scheduling strategies.

[0093] For example, implementation risk levels are divided into three levels: low, medium, and high. A low risk level indicates that during the implementation of the scheduling strategy, there is a low probability of problems such as traffic congestion and equipment failure, which will have a small impact on construction progress and safety. A medium risk level means that there is a certain risk, and occasional traffic congestion or equipment failure may occur, but these can be effectively addressed through reasonable scheduling and maintenance measures. A high risk level indicates a high risk, with a high probability of frequent traffic congestion and equipment failure, which may seriously affect construction progress and safety.

[0094] Based on this, the strategy assessment model assesses the implementation risk level based on historical data issues, such as the number of traffic jams, the correlation between equipment failures and scheduling strategies, and other factors, combined with pre-set risk assessment rules. For example, if a historical scheduling strategy implementation experience shows frequent traffic jams with significant impact on construction progress, and there is a clear correlation between equipment failures and scheduling strategies, the strategy's implementation risk level is determined to be high.

[0095] In one example, the strategy evaluation model can be implemented based on a multi-index comprehensive evaluation model, using the Analytic Hierarchy Process (AHP) to determine the weights of each factor. The AHP is a decision-making method that breaks down decision-making elements into hierarchies such as goals, criteria, and options, and then conducts qualitative and quantitative analysis based on these hierarchies.

[0096] Step S162: inputting the global traffic scheduling strategy into the strategy evaluation model to obtain a strategy verification report including multi-dimensional scoring indicators, wherein the multi-dimensional scoring indicators include a traffic congestion relief index and an equipment collaborative operation index.

[0097] In this embodiment of the present invention, the currently generated global traffic scheduling strategy is input into a strategy evaluation model for evaluation. The model comprehensively analyzes the global traffic scheduling strategy based on pre-set algorithms and rules. For example, by simulating vehicle traffic within a tunnel construction area, combined with traffic light control instructions and vehicle priority scheduling, the model evaluates the traffic congestion relief index. For example, during the simulation, it was estimated that the implementation of the global traffic scheduling strategy would reduce the average queue length at congestion points by 40%. Based on the pre-set conversion rule (traffic congestion relief index = average percentage reduction in queue length / 50), the resulting traffic congestion relief index is 0.8.

[0098] The equipment coordination index is also evaluated by analyzing the usage of construction equipment across different tasks and time periods. For example, it assesses whether the equipment is coordinating smoothly and whether any equipment is idle or overused. If the evaluation indicates improved coordination efficiency among construction equipment and reduced idle time, the equipment coordination index is calculated as 0.7 based on the corresponding evaluation criteria. Finally, the strategy evaluation model generates a strategy verification report that incorporates these multi-dimensional scoring indicators, providing a detailed quantitative basis for determining the rationality and effectiveness of the overall traffic scheduling strategy.

[0099] For example, the device collaborative operation index is quantified in the following way:

[0100] First, a detailed analysis is conducted on the usage of construction equipment in different tasks and time periods, including the equipment's start-up time, operating time, idle time, and the coordination between equipment.

[0101] Next, we set evaluation indicators, such as equipment utilization, equipment idle rate, and the proportion of time spent on equipment collaborative operation, and assign appropriate weights to each indicator. For example, equipment utilization is weighted 0.4, equipment idle rate is weighted -0.3 (negative weights indicate a lower metric is better), and the proportion of time spent on equipment collaborative operation is weighted 0.3. By comprehensively calculating these indicators, we arrive at the Equipment Collaboration Index: Equipment Utilization * 0.4 - Equipment Idle Rate * 0.3 + Proportion of Time Worked on Equipment Collaboratively * 0.3.

[0102] Step S163: When there are scoring indicators in the strategy verification report that do not meet the preset conditions, the global traffic scheduling strategy is iteratively optimized until all scoring indicators meet the corresponding preset conditions.

[0103] After receiving the strategy verification report, check whether the scoring indicators meet the preset conditions. For example, the preset traffic congestion relief index must reach 0.9 or above, and the equipment coordination index must reach 0.8 or above. If the strategy verification report shows a traffic congestion relief index of 0.8, the preset conditions are not met. At this time, iterative parameter optimization of the global traffic scheduling strategy is carried out.

[0104] If the traffic congestion relief index fails to meet the target, we analyze parameters that may affect it, such as traffic light release intervals and vehicle priority settings. For example, we can appropriately shorten the vehicle release intervals at some traffic nodes and reroute high-priority vehicles to avoid excessive concentration of vehicles in certain areas. The optimized global traffic scheduling strategy is then input into the strategy evaluation model for evaluation. If, after multiple iterations of optimization, the traffic congestion relief index improves to 0.92 and the equipment coordination index reaches 0.85, and all scoring indicators meet the corresponding preset conditions, the global traffic scheduling strategy is considered a satisfactory optimization strategy and can be used for actual traffic scheduling in tunnel construction areas.

[0105] In other optional embodiments, after instructing the traffic light control system to perform a switching operation of the traffic node's traffic state according to a preset time window, the method further includes:

[0106] Step S170: monitor the length of the vehicle queue and the vehicle travel speed at the traffic node in real time, and generate real-time vehicle travel status parameters.

[0107] Monitoring equipment is installed at various traffic nodes within the tunnel construction area to monitor vehicle queue lengths and speeds in real time. For example, at traffic node E, laser sensors and cameras installed above the road capture real-time vehicle queue information and speed data. Every minute, the system records the queue length and speed. At a specific moment, the queue length at traffic node E was monitored to be 80 meters long, and the vehicle speed was 15 km / h. These data are recorded and transmitted as real-time vehicle traffic status parameters. These real-time vehicle traffic status parameters provide a timely reflection of the actual traffic conditions at the traffic node, providing accurate on-site data support for subsequent traffic scheduling decisions, enabling the timely detection of abnormal situations such as traffic congestion and the implementation of appropriate measures.

[0108] Step S171: Compare and analyze the real-time vehicle traffic status parameters with the traffic efficiency threshold preset in the global traffic scheduling strategy. When the comparison and analysis result indicates that the length of the vehicle queue exceeds the length threshold and the vehicle speed is lower than the speed threshold, an emergency scheduling trigger signal is generated.

[0109] In an embodiment of the present invention, the vehicle traffic status parameters obtained through real-time monitoring are compared with the traffic efficiency thresholds preset in the global traffic scheduling strategy. For example, the vehicle queue length threshold for traffic node E is preset in the global traffic scheduling strategy as 60 meters, and the vehicle speed threshold is 20 kilometers per hour. When the vehicle queue length at traffic node E is monitored to be 80 meters, exceeding the length threshold of 60 meters, and the vehicle speed is 15 kilometers per hour, which is lower than the speed threshold of 20 kilometers per hour, the system automatically generates an emergency dispatch trigger signal. This emergency dispatch trigger signal indicates that the traffic conditions at the current traffic node are abnormal and that emergency dispatch measures need to be taken in a timely manner to ensure smooth traffic in the tunnel construction area and prevent further deterioration of traffic congestion that affects the construction progress.

[0110] Step S172: Based on the emergency dispatch trigger signal, the special vehicle identification for transporting hazardous materials is screened from the vehicle identifications, and an emergency passage priority list including priority passage rights for special vehicles is generated.

[0111] After receiving the emergency dispatch trigger signal, the system screens the vehicle IDs for special vehicles transporting hazardous materials. For example, by identifying the vehicle type code and related markings among all passing vehicles, it is discovered that vehicle "V024" is transporting flammable and explosive hazardous materials and has a special hazardous materials transport mark on its vehicle ID.

[0112] The identification of special vehicles transporting hazardous materials is organized, and a priority list for emergency access is generated according to pre-set rules, including priority access for special vehicles. For example, "V024" is placed at the top of the priority list based on the hazardous material's level of danger and the urgency of its transportation. This ensures that these special vehicles receive priority access in emergency situations, safeguarding both transportation safety and the overall security of the tunnel construction area.

[0113] Step S173: According to the emergency passage priority list, an emergency dispatch instruction is sent to the traffic light control system, wherein the emergency dispatch instruction includes the mandatory extension of the green light duration of the traffic node where the special vehicle is located and the synchronous shortening of the red light duration of the adjacent traffic nodes.

[0114] Optionally, based on the generated emergency passage priority list, an emergency dispatch instruction is sent to the traffic light control system. For example, for a special vehicle "V024" at traffic node F, the emergency dispatch instruction requires that the green light at traffic node F be extended to 120 seconds, while the red lights at adjacent traffic nodes G and H are simultaneously shortened to 30 seconds.

[0115] Upon receiving these instructions, the traffic light control system immediately adjusted the traffic light status accordingly. At traffic node F, the green light illuminated for 120 seconds, ensuring that special vehicle "V024" could pass smoothly through the node. Simultaneously, the red light duration at adjacent traffic nodes G and H was shortened, reducing waiting times for other vehicles and minimizing the impact on overall traffic flow, ensuring that special vehicles could pass quickly and safely in emergency situations.

[0116] Step S174: acquiring the dynamic position coordinates of the special vehicle in real time, and dynamically adjusting the attenuation coefficient of the mandatory green light extension time based on the distance between the dynamic position coordinates and the target tunnel face position.

[0117] As the special vehicle "V024" travels, its dynamic position coordinates are acquired in real time using the positioning equipment installed on the vehicle. For example, the special vehicle "V024" departs from traffic node F and travels toward the target tunnel face I. As the vehicle travels, its distance to the target tunnel face I is continuously calculated.

[0118] For example, at a certain moment, special vehicle "V024" is 500 meters away from target face I. Based on this distance, the attenuation coefficient for the mandatory green light extension is dynamically adjusted according to preset rules and algorithms. For example, if the distance to the target face is relatively close, to avoid excessive impact on other traffic, the attenuation coefficient for the mandatory green light extension is appropriately reduced, gradually shortening the green light extension time at subsequent traffic nodes. At traffic node J, if the mandatory green light extension is initially set to 100 seconds, the actual green light extension time is adjusted to 80 seconds due to the closer distance to the target face and the adjusted attenuation coefficient. This allows traffic light control to be dynamically adjusted based on the special vehicle's location, ensuring the passage of special vehicles while maintaining overall traffic balance.

[0119] Specifically, the real-time positioning system obtains the dynamic distance (e.g., 500 meters) between the special vehicle and the target tunnel face. Based on a preset distance-attenuation coefficient mapping rule (the closer the distance, the smaller the attenuation coefficient), the mandatory green light extension time is dynamically adjusted. The algorithm employs a distance threshold piecewise function or proportional control model. When a vehicle approaches the target (e.g., below the set threshold), the algorithm automatically reduces the attenuation coefficient to shorten the green light extension time at subsequent traffic nodes (e.g., from 100 seconds to 80 seconds). This dynamically compresses the green light window to balance overall traffic flow while ensuring priority passage for special vehicles, avoiding congestion at adjacent nodes caused by excessive local green light extensions. This mechanism optimizes traffic resources through negative feedback regulation of distance parameters and delay effects.

[0120] Step S175: After the special vehicle passes the target traffic node, the traffic light control instruction change record and the vehicle speed recovery time during the emergency dispatch process are extracted to generate an emergency dispatch process log.

[0121] As you can understand, after special vehicle "V024" passes the target traffic node, the system automatically extracts relevant information from the emergency dispatch process. This includes changes to traffic light control instructions, such as the specific adjustments to extend the duration of green lights at nodes F and J, and shorten the duration of red lights at adjacent nodes. It also records the vehicle speed recovery time—the time from when the emergency dispatch is triggered until the vehicle speed at the traffic node returns to near-normal levels.

[0122] For example, during this emergency dispatch, detailed information was recorded, including the extension of the green light at traffic node F to 120 seconds and at traffic node J to 80 seconds. After the emergency dispatch was triggered, vehicle speeds gradually returned to a near-normal 20 km / h over the next 10 minutes. This information is compiled into an emergency dispatch process log, providing detailed data for subsequent analysis of the dispatch's effectiveness and lessons learned.

[0123] Step S176: feature matching is performed on the emergency dispatch process log and the historical emergency event handling log, and combinations of traffic node locations and vehicle types whose trigger times exceed the set frequency are extracted to generate an emergency strategy optimization knowledge base.

[0124] Optionally, the generated emergency dispatch process log is feature-matched with historical emergency event handling logs. For example, suppose the trigger frequency is set to 5. By statistically analyzing the combinations of traffic node locations and vehicle types in the log, it is found that in past emergency events at traffic node K, vehicles transporting concrete mixer trucks triggered emergency dispatch 7 times, exceeding the set frequency.

[0125] The traffic node locations and vehicle type combinations that are triggered more than the set frequency are sorted out to generate an emergency strategy optimization knowledge base. This knowledge base records key information that is likely to cause emergencies, providing an important basis for subsequent optimization of emergency strategies, so that more effective response measures can be formulated in advance for these high-incidence areas and vehicle types, reducing the frequency and impact of emergency events.

[0126] Step S177: Mapping the frequent triggering features of the traffic node positions in the emergency strategy optimization knowledge base to the path conflict dimension of the implementation risk level parameter in the strategy evaluation model to update the path conflict probability value.

[0127] In the emergency strategy optimization knowledge base, we analyze the path conflicts reflected by traffic nodes that are triggered more frequently than the set frequency. For example, traffic node K frequently triggers emergency dispatches due to vehicles transporting concrete mixer trucks. Analysis reveals that the planned traffic paths for this node do not match the driving characteristics of the concrete mixer trucks, leading to traffic congestion and conflicts.

[0128] This frequent triggering feature is mapped to the path conflict dimension of the implementation risk level parameter in the strategy evaluation model. In the strategy evaluation model, the path conflict dimension originally has a basic path conflict probability value. Based on the frequent triggering of traffic node K in the emergency strategy optimization knowledge base, the path conflict probability value of this dimension is updated. For example, if the original path conflict probability value is 0.2, because the frequent triggering events of traffic node K indicate a high path conflict risk in this area, the path conflict probability value is increased to 0.4. This enables the strategy evaluation model to more accurately reflect the actual situation and provide a more precise risk assessment basis for the subsequent formulation of global traffic scheduling strategies.

[0129] For example, the path conflict probability is quantified based on historical data and real-time monitoring data. Specifically, by collecting and analyzing long-term traffic operation data within the tunnel construction area, including vehicle trajectories, traffic conditions at traffic nodes, and the frequency of path conflict events, the probability of path conflicts occurring at different traffic nodes and road sections is calculated. For example, if, after a period of data analysis, a certain traffic node experiences 20 path conflict events out of 1,000 vehicle passes, the initial path conflict probability for that traffic node is 20 ÷ 1,000 = 0.02. As emergencies and other situations occur, if traffic node K frequently triggers emergency dispatch due to vehicles transporting concrete mixer trucks, the reasons for this frequent triggering are analyzed, such as a mismatch between the route planning and the vehicle's driving characteristics. Pre-set rules and algorithms are used to consider the impact of frequent triggering events on the path conflict probability. For example, if a traffic node triggers emergency dispatch more than a set frequency (e.g., 5 times), the path conflict probability is increased by a certain percentage (e.g., doubled). Therefore, the original path conflict probability value is 0.2. Since the frequent triggering events of traffic node K indicate that the path conflict risk in this area is high, the path conflict probability value is increased to 0.4.

[0130] Specifically, when a traffic node triggers emergency dispatch more than a set frequency (e.g., 5 times), the path conflict probability value is doubled (e.g., from 0.2 to 0.4). This is achieved based on the following comprehensive considerations:

[0131] (1) Experience judgment: Based on past experience in similar tunnel construction scenarios, when a certain traffic node triggers emergency dispatch a certain frequency, it indicates that there is a large mismatch between the path planning and actual traffic operation in the area. A doubling of the path conflict probability value can reasonably reflect the higher path conflict risk in this area compared to other areas.

[0132] (2) Highlighting risk: Doubling the risk can significantly increase the risk weight of the traffic node in the strategy evaluation model, allowing it to receive more attention when formulating the global traffic scheduling strategy. Based on this adjusted probability value, the model will redistribute the weights of the vehicle route optimization schemes for the relevant construction face, thereby more effectively reducing the path conflict risk in the area and ensuring the safety and efficiency of traffic scheduling.

[0133] This design constructs a relatively reasonable risk quantification and adjustment mechanism to adapt to the complex and changing traffic environment of tunnel construction. In actual application, the increase ratio can be further adjusted according to the specific construction situation and data feedback to achieve the best traffic scheduling effect.

[0134] Step S178: Based on the updated path conflict probability value, the vehicle route optimization schemes associated with different construction faces in the global traffic scheduling strategy are weighted redistributed through the resource optimization decision model to generate a global traffic scheduling optimization strategy including dynamic avoidance rules.

[0135] In an embodiment of the present invention, the updated path conflict probability value is input into a resource optimization decision model. Based on the updated path conflict probability value, the resource optimization decision model redistributes the weights of vehicle route optimization solutions associated with different construction faces in the global traffic scheduling strategy.

[0136] For example, the vehicle route optimization plan for construction face L, associated with traffic node K, originally had a weight of 0.3 in the global traffic scheduling strategy. However, due to an increase in the path conflict probability for traffic node K, the resource optimization decision model reassessed the weight of the vehicle route optimization plan for construction face L to 0.2 to reduce the risk of path conflict in that area. Simultaneously, the weights of the vehicle route optimization plans for other construction faces with relatively safer paths and lower conflict probabilities were increased accordingly.

[0137] The weight redistribution process incorporates dynamic avoidance rules. For example, if traffic flow near a traffic node K approaches a congestion threshold, vehicles approaching from other directions are required to proactively select alternative routes according to specific dynamic avoidance rules to avoid the potentially congested area at that node. This approach generates a global traffic scheduling optimization strategy incorporating dynamic avoidance rules, further improving the safety and efficiency of traffic scheduling within the tunnel construction area and reducing the occurrence of route conflicts and traffic congestion.

[0138] For example, weight adjustments are made quantitatively based on the algorithms and principles of the resource optimization decision-making model. The model considers multiple factors to determine the weight adjustments, including changes in the probability of path conflict, material transportation requirements at the construction face, and vehicle traffic efficiency. For example, if the path conflict probability at a certain traffic node increases, the model will comprehensively consider the conditions at other construction faces to reduce the risk of path conflict in that area and adjust the weights of the vehicle route optimization solutions for those construction faces according to a specific proportional relationship.

[0139] The specific algorithm can be based on calculations based on linear or nonlinear relationships. Taking a linear relationship as an example, the relationship between the path conflict probability value and the weight adjustment is: weight adjustment = (change in path conflict probability value × preset weight adjustment coefficient). For example, when the path conflict probability value at traffic node K increases from 0.2 to 0.4, the change in path conflict probability value is 0.2. Therefore, the weight adjustment for the vehicle route optimization plan for construction face L associated with traffic node K is 0.2 * 0.5 (preset weight adjustment coefficient) = 0.1. The original weight is 0.3, which after adjustment becomes 0.3 - 0.1 = 0.2. At the same time, to ensure that the overall weight sums to 1, the weights of the vehicle route optimization plans for construction faces with relatively safer paths and lower conflict probabilities are increased accordingly. Therefore, the resource optimization decision model can be implemented based on a linear programming model. Linear programming is the problem of maximizing or minimizing a linear objective function under a set of linear constraints.

[0140] It can be seen that the resource optimization decision model includes the following algorithm branches and their functions:

[0141] 1. Linear Programming and Dynamic Programming Algorithm Branch: This branch comprehensively processes various data from construction projects, including the work efficiency of different construction teams, equipment usage, and construction schedule requirements. By comprehensively evaluating this data, this branch calculates the optimal allocation of human and equipment resources, thereby achieving goals such as improving construction efficiency and reducing costs. This branch aims to optimize the overall allocation of resources in construction projects, comprehensively considering multiple factors at a macro level to rationally allocate resources.

[0142] Second, a branch of weight adjustment algorithms based on linear or nonlinear relationships: This branch primarily adjusts the weights of vehicle route optimization solutions for construction faces. This branch considers multiple factors, including changes in path conflict probability, material transportation requirements for the construction face, and vehicle traffic efficiency, to determine the weight adjustment values. Taking linear relationships as an example, using the calculation method of "weight adjustment = (change in path conflict probability × preset weight adjustment coefficient)," when the path conflict probability value of a traffic node changes, the model will consider the conditions of other construction faces and proportionally adjust the weights of the vehicle route optimization solutions for the relevant construction faces, while ensuring that the sum of the overall weights is 1. This balances resource allocation across construction faces, reduces the risk of path conflicts in specific areas, and improves the safety and efficiency of traffic scheduling.

[0143] In an alternative embodiment, the method further comprises:

[0144] Step S180: monitor the emergency dispatch instruction change record after the traffic node switching operation in real time, extract the traffic node position and green light extension time parameters in the emergency dispatch instruction change record, calculate the time difference between the red light synchronization shortening time of adjacent traffic nodes and the preset time window based on the green light extension time parameters, generate a traffic light control instruction recovery schedule, and based on the traffic node position and the traffic light control instruction recovery schedule, send a scheduling rollback instruction containing the recovery priority order to the traffic light control system.

[0145] During tunnel construction, the system continuously monitors the emergency dispatch instruction change logs after traffic node switching operations. For example, during one emergency dispatch, the green light at traffic node M was extended to 150 seconds, while the red light at adjacent traffic node N was shortened accordingly. After the emergency dispatch, the system accurately extracts the location of traffic node M and the green light extension parameter of 150 seconds from the emergency dispatch instruction change log.

[0146] Based on pre-defined rules and relationships, the time difference between the duration of the synchronously shortened red light at adjacent traffic node N and the preset time window is calculated. For example, if the normal duration of the red light at traffic node N within the preset time window is 60 seconds, and during emergency dispatch, the red light is shortened to 30 seconds, the time difference is 30 seconds. Based on this information and the locations of traffic nodes M and N, a traffic light control instruction restoration schedule is generated.

[0147] This restoration schedule specifies the specific timing and order for restoring traffic lights at each node. For example, the green light duration at node M will be restored to its normal 90 seconds, followed by the red light duration at node N, which will be restored to 60 seconds after a 30-second interval. Following this restoration schedule and the established restoration priority, a rollback instruction is sent to the traffic light control system. Upon receiving the instruction, the control system gradually restores the traffic lights to their normal state prior to the emergency dispatch, ensuring a smooth transition of traffic order within the tunnel construction area.

[0148] Step S181: Collect vehicle speed recovery data and construction equipment restart status parameters after the scheduling rollback instruction is executed, perform a difference comparison between the vehicle speed recovery data and the historical benchmark speed, and update the weight coefficient of the route optimization plan in the global traffic scheduling strategy according to the difference comparison result.

[0149] After the dispatch rollback instruction is executed, closely collect vehicle speed recovery data and construction equipment restart status parameters. For example, speed monitoring devices installed at various traffic nodes can record the recovery of vehicle speed. For example, before the dispatch rollback instruction was executed, the vehicle speed at traffic node P dropped to 10 km / h due to emergency dispatch. After a period of time after the dispatch rollback instruction was executed, the vehicle speed returned to 18 km / h. At the same time, the restart status of construction equipment is monitored. For example, a large excavator that was suspended during the emergency dispatch successfully restarted and resumed normal operations after the dispatch rollback.

[0150] Compare the difference between the collected vehicle speed data and the historical baseline speed. For example, if the historical baseline speed at traffic node P is 20 km / h, the difference is 20-18 = 2 km / h. Based on this difference comparison, the weight coefficients of the route optimization plan in the global traffic scheduling strategy are updated.

[0151] If the difference is significant, it indicates that the current route optimization plan may still have some issues and require further adjustment. For example, the weight coefficient of the route optimization plan for traffic node P was originally 0.4. Considering that speed recovery has not reached historical benchmark levels, the weight coefficient was appropriately reduced to 0.35. At the same time, the weight coefficients of other related route optimization plans were adjusted and rebalanced accordingly. In this way, the global traffic scheduling strategy is continuously optimized according to actual conditions to improve traffic operation efficiency and stability throughout the tunnel construction area.

[0152] In a non-limiting embodiment, the method further comprises:

[0153] Step S190: Obtain the displacement change trend data of the construction machinery, identify the construction equipment identification of the mechanical arm extension angle exceeding the limit in the displacement change trend data, locate the target tunnel face area according to the construction equipment identification, and extract the intersection turning rules in the vehicle route optimization plan associated with the target tunnel face.

[0154] Displacement monitoring devices installed on construction machinery continuously capture trend data on the displacement of construction machinery. For example, the displacement of multiple large excavators, loaders, and other construction equipment is monitored in real time. When analyzing this data, changes in the extension angle of the robotic arms are particularly important.

[0155] For example, the arm extension angle of an excavator named "WJ-001" continuously increases over time, exceeding a preset safety angle threshold. The equipment identification system identifies the construction equipment as "WJ-001." Based on the pre-established relationship between construction equipment and target face areas, the target face area where the equipment is currently operating is determined to be face C.

[0156] Next, the global traffic scheduling strategy extracts an optimized vehicle routing plan associated with tunnel face C. Within this plan, the section involving intersection turning rules is identified. For example, it stipulates that vehicles passing through intersection Q associated with tunnel face C must proceed in a clockwise direction. This ensures that vehicles and construction machinery do not interfere with each other, ensuring construction safety and smooth traffic flow.

[0157] Step S191: Generate a temporary roadblock coordinate point based on the robot arm extension angle overlimit parameter, perform spatial overlay analysis on the temporary roadblock coordinate point and the intersection turning rule, generate a local traffic light control parameter correction table containing a detour sign position update instruction according to the overlay analysis result, and send the local traffic light control parameter correction table to the signal controller of the corresponding traffic node to cover the original turning rule.

[0158] Based on the parameters of the "WJ-001" construction machine's arm extension angle exceeding the limit, combined with the construction site's geographic information and safety requirements, a temporary roadblock coordinate point is generated. For example, because the arm's extension angle exceeding the limit could affect the normal passage of vehicles at intersection Q, a temporary roadblock coordinate point (X4, Y4, Z4) is generated at a specific location at intersection Q.

[0159] The coordinates of these temporary roadblocks were spatially overlaid with the original turning rules at intersection Q. The impact of the temporary roadblocks on vehicles following the original turning rules was analyzed. For example, it was found that after the temporary roadblocks were set up, vehicles that originally traveled in a clockwise direction would have difficulty passing through the area.

[0160] Based on the overlay analysis results, a local traffic light control parameter correction table is generated, including instructions for updating the detour sign position. For example, the correction table stipulates that a detour sign be placed near a temporary roadblock to instruct vehicles to turn right in advance and avoid the robotic arm's extended area. At the same time, traffic light control parameters are adjusted, such as extending the green light duration in a specific direction at intersection Q, to guide vehicles around the detour smoothly.

[0161] This local traffic light control parameter correction table is sent to the signal controller at the corresponding traffic node Q. Upon receiving the correction table, the signal controller updates the traffic light control parameters and sets detour signs according to the instructions contained therein, overwriting the original turning rules. This ensures that vehicles can pass safely and smoothly when construction machinery malfunctions, preventing serious traffic disruptions caused by construction machinery operations.

[0162] In a non-limiting embodiment, the method further comprises:

[0163] Step S200: synchronously obtain real-time wind speed monitoring data of the ventilation system in the tunnel, identify the coordinates of the tunnel section where the wind speed is lower than a preset threshold, extract the vehicle type code in the vehicle traffic record corresponding to the tunnel section coordinates, screen the diesel vehicle identification that depends on the ventilation conditions, and generate an exhaust emission control instruction set including a speed limit value and a minimum following distance based on the diesel vehicle identification.

[0164] Optionally, wind speed monitoring equipment installed in the tunnel can be used to simultaneously acquire real-time wind speed data from the ventilation system. For example, wind speed data for each tunnel section can be collected every five minutes. The preset wind speed threshold is 3 m / s. If the wind speed in a tunnel section, such as Tunnel Section D, is 2 m / s, which is below the preset threshold, the system can detect a wind speed below the threshold.

[0165] Vehicle traffic records corresponding to tunnel section D were extracted and the vehicle type codes were obtained from these records. For example, several vehicles were found with the vehicle type code "CYL," representing diesel vehicles. Further analysis and screening determined that these diesel vehicles were ventilation-dependent. In low wind speeds, exhaust emissions from diesel vehicles are difficult to effectively disperse, potentially impacting tunnel air quality and occupant health.

[0166] Based on these diesel vehicle identifications, combined with low wind speed environments and exhaust emission standards, exhaust emission control instructions are generated, including speed limits and minimum following distances. For example, within tunnel section D, the speed limit for diesel vehicles is 15 km / h, and the minimum following distance is 50 meters. This instruction set aims to reduce the accumulation of diesel vehicle exhaust emissions and minimize pollution within the tunnel environment by limiting vehicle speeds and maintaining a safe following distance.

[0167] Step S201: coupling calculation is performed on the dynamic release interval duration in the exhaust emission control instruction set and the traffic light control instruction set, dynamically extending the red light interval duration of the traffic node in the tunnel section according to the coupling calculation result and generating a ventilation abnormality alarm log.

[0168] Optionally, the generated exhaust emission control instruction set is coupled with the dynamic release interval duration in the traffic light control instruction set for calculation. For example, the exhaust emission control instruction set stipulates a speed limit of 15 km / h for diesel vehicles in tunnel section D, while the dynamic release interval duration for traffic node E in the same tunnel section is originally set at 60 seconds in the traffic light control instruction set.

[0169] A coupled calculation was performed, taking into account the exhaust emissions of diesel vehicles in low-wind environments and speed limit requirements. For example, the calculation determined that the red light interval at traffic node E needed to be extended to ensure sufficient time for exhaust emissions to dissipate after a vehicle passed through. This coupled calculation process incorporated factors such as vehicle speed and tunnel ventilation capacity, performing a weighted summation to ultimately determine the extension of the red light interval to 90 seconds.

[0170] Based on the coupled calculation results, the red light intervals at traffic nodes within tunnel section D are dynamically adjusted. Simultaneously, a ventilation anomaly alarm log is generated, recording information such as the coordinates of the tunnel section (e.g., tunnel section D) where the ventilation system wind speed falls below a preset threshold, the identification of the diesel vehicle involved, the content of the exhaust emission control instruction set, and the red light interval adjustment status. This ventilation anomaly alarm log provides a detailed record for subsequent analysis and resolution of ventilation issues, enabling timely measures to improve the tunnel's ventilation environment and ensure construction safety and personnel health.

[0171] In a non-limiting embodiment, the method further comprises:

[0172] Step S310: Continuously collect data on the number of sudden braking times and light flashing frequencies of vehicles at each traffic node, identify the traffic node locations where the number of sudden braking times exceeds the limit, extract the historical vehicle traffic records of the traffic node locations, and count the vehicle type combinations corresponding to the high-frequency sudden braking periods at the location.

[0173] At each traffic node in the tunnel construction area, sensors and monitoring equipment installed on the road continuously collect data on vehicle sudden braking and light flashing frequency. For example, the number of vehicle sudden braking and light flashing frequency at each traffic node is counted every hour.

[0174] After a period of data collection and analysis, it was found that the number of sudden braking times at traffic node F reached 20 on a certain day, exceeding the preset limit of 15 times. The traffic node location where the sudden braking times exceeded the limit was identified as F.

[0175] Historical vehicle traffic records for traffic node F were extracted. These records detailed information about passing vehicles, including vehicle type and travel time. Statistical analysis of these historical records identified the vehicle type combinations corresponding to the high-frequency sudden braking periods at this traffic node. For example, during the period from 2:00 PM to 4:00 PM, the primary types of vehicles involved were dump trucks and concrete mixer trucks. Understanding these vehicle type combinations facilitated in-depth analysis of the causes of sudden braking and provided a basis for developing targeted measures.

[0176] Step S311: Generate time-based no-entry rules based on the vehicle type combination, and perform conflict detection on the no-entry rules and the traffic priority order in the traffic light control instruction set. Adjust the effective time window of the no-entry rules based on the conflict detection result, and send an avoidance strategy notification including a detour voice prompt to the construction personnel terminal. Synchronize and calibrate the avoidance strategy notification with the phase switching timing of the traffic light control system.

[0177] Based on the statistically determined vehicle type combinations (dump trucks and concrete mixer trucks) that correspond to the most frequent sudden braking periods at traffic node F, time-based prohibition rules are generated. For example, between 2:00 PM and 4:00 PM, dump trucks and concrete mixer trucks are prohibited from entering traffic node F.

[0178] The generated prohibition rules are then checked for conflicts with the priority order in the traffic light control set. The prohibition rules are checked to see if they conflict with the existing priority order. For example, if a dump truck has a higher priority in the traffic light control set during a certain time period, but is not allowed to pass according to the prohibition rules, this creates a conflict.

[0179] Based on the conflict detection results, the effective time window of the no-traffic rule is adjusted. If a conflict is found, the no-traffic rule is optimized, such as adjusting the no-traffic time window to 2:30 pm to 3:30 pm, to minimize the impact on normal traffic scheduling.

[0180] At the same time, a notification of the avoidance strategy, including voice prompts for detours, is sent to construction workers' terminals. For example, through the tunnel's public address system and the workers' handheld terminals, notifications are sent to relevant construction workers, informing them that dump trucks and concrete mixer trucks must use alternative routes during the restricted driving period, and detailed voice prompts are provided.

[0181] Finally, the avoidance strategy notifications are synchronized with the traffic light control system's phase switching timing. This ensures that traffic light switching is coordinated with vehicle detours and prohibited traffic arrangements. For example, at the start of a prohibited traffic period, traffic light phases are adjusted to guide vehicles according to the avoidance strategy, avoiding traffic congestion and ensuring the orderly flow of traffic within the tunnel construction area.

[0182] In a non-limiting embodiment, the method further comprises:

[0183] Step S320: Receive a request for a change in construction material transportation demand, parse the newly added unloading point coordinates and urgency tag in the change request, recalculate the shortest path distance between the position coordinates of all vehicles in transit and the unloading point based on the newly added unloading point coordinates, and generate a path occupancy period table including temporary dedicated lanes based on the urgency tag and the shortest path distance.

[0184] During tunnel construction, a change request for construction material transportation requirements is received. For example, the construction department sends a change request containing the coordinates of a new unloading point (X5, Y5, Z5) and the urgency tag "High."

[0185] After parsing the information in the change request, the shortest path distance between the location coordinates of all vehicles in transit and the new unloading point is recalculated based on the coordinates of the newly added unloading point. For example, there are three vehicles in transit, "V025," "V026," and "V027." Their current location coordinates are obtained through the positioning system. Using a specific path calculation algorithm, taking into account the tunnel layout and road connectivity, the shortest path distance between these three vehicles and the newly added unloading point (X5, Y5, Z5) is calculated. For example, the shortest path distance between "V025" and the new unloading point is 800 meters, "V026" is 600 meters, and "V027" is 1000 meters.

[0186] Based on the urgency tag and the shortest path distance, a route occupancy table is generated, including temporary dedicated lanes. Because the urgency tag is "High," vehicle "V026," which is closer to the newly added unloading point, is prioritized for a temporary dedicated lane. A temporary dedicated lane is created for "V026" 30 minutes after the change request is received, with a 60-minute occupancy period to ensure it can reach the newly added unloading point quickly and safely. Simultaneously, the routes and occupancy periods of other vehicles are rationally arranged based on their proximity and urgency, forming a complete route occupancy table to ensure smooth changes in construction material transportation needs.

[0187] Step S321: performing a time period overlap check on the path occupancy time period table and the dynamic release interval duration in the traffic light control instruction set, and inserting the highest priority lane clearing control instruction into the relevant traffic node within the overlapping time period according to the time period overlap check result.

[0188] Optionally, the generated route occupancy period table is checked for overlap with the dynamic release interval duration in the traffic light control instruction set. For example, the route occupancy period table specifies that "V026" will occupy the temporary dedicated lane for 60 minutes starting 30 minutes later, while the traffic light control instruction set specifies a normal dynamic release interval duration for the relevant traffic node G during the same time period.

[0189] By comparing the time periods, it was found that the path occupancy period overlaps with the time period of the traffic light control instruction. For example, there is an overlap between 35 minutes and 50 minutes. Based on the time period overlap verification results, the highest priority lane clearance control instruction is inserted into the relevant traffic node G during the overlapping period. In other words, between 35 minutes and 50 minutes, the traffic light control system will prioritize the passage of "V026" on the temporary dedicated lane. By adjusting the traffic light status and clearing other vehicles on the lane, "V026" can quickly pass through traffic node G and arrive at the newly added unloading point on time, meeting the emergency change in construction material transportation needs while minimizing the impact on other normal traffic.

[0190] It should be noted that when implementing the above technical solution, for the determination of the traffic priority level in dynamic scheduling processing and the algorithm implementation of calculating the theoretical travel time based on equipment loading parameters, technical personnel in this field can also combine the vehicle classification rules, path planning algorithms (such as Dijkstra, A*, etc.) in the existing technology and empirical models or machine learning models (such as regression analysis) based on vehicle attributes and road conditions to further optimize the processing.

[0191] When using greedy algorithms in dynamic sorting models, you can refer to the greedy strategies and priority queue implementations for solving job sorting problems in the existing technology.

[0192] It is worth mentioning that the linear programming and dynamic programming in the resource optimization decision-making model are both mature algorithms in operations research. Their implementation details can be referred to the standard algorithm libraries and solvers in related fields.

[0193] In addition, the analytic hierarchy process (AHP) involved in the strategic evaluation model is also a mature decision analysis method. Its application steps and weight calculation rules have been widely used in the field of project management, and can be implemented according to the standard AHP process.

[0194] Furthermore, technical details such as dynamic compensation of real-time environmental parameters (such as dust concentration and mechanical displacement), quantification and adjustment of path conflict probability values ​​(which can be based on statistical analysis or Bayesian update methods), and application of position-related attenuation coefficients in emergency dispatch (such as positioning technology based on received signal strength indication (RSSI) or time difference to assist dynamic distance calculation) can all be achieved by drawing on existing sensor data processing rules, risk assessment methods, positioning technology, and spatiotemporal scheduling logic.

[0195] Similarly, technologies such as timestamp processing, 3D trajectory reconstruction, and unusual stop point identification can also rely on existing technologies for spatiotemporal data mining and pattern recognition. By comprehensively leveraging these mature existing technologies, those skilled in the art can overcome implementation barriers and implement a comprehensive process encompassing vehicle status data acquisition, dynamic scheduling, global strategy generation, and feedback execution.

[0196] The embodiment of the present invention first deploys a fixed RFID reader array to collect vehicle position coordinates, identity identification and traffic time series data in real time, and builds a multi-dimensional dynamic traffic situation awareness network, breaking through the technical difficulties of information lag and positioning ambiguity in traditional manual scheduling. Secondly, based on the real-time captured vehicle spatiotemporal trajectory data, the dynamic scheduling algorithm autonomously generates traffic node priority parameters and release interval parameters to achieve dynamic adaptation of traffic strategies at each intersection and the construction process, effectively solving the path conflict problem of multi-face construction vehicles at intersection nodes; then, by integrating the control instruction set of global traffic nodes, a global optimization model for construction processes is constructed to generate a comprehensive strategy that takes into account both vehicle route optimization and coordinated allocation of equipment resources, significantly improving the collaborative operation efficiency of construction machinery; finally, the traffic state switching is accurately controlled through the preset time window to form a dynamic coupling mechanism between the construction process and traffic scheduling, providing a complete spatiotemporal trajectory data chain for vehicle operation performance evaluation.

[0197] In summary, the embodiments of the present invention, through the deep integration of non-invasive data collection and intelligent decision-making, can quickly generate a global traffic scheduling strategy that takes into account both construction progress and traffic efficiency, and based on the global traffic scheduling strategy, instruct the traffic light control system to execute the switching operation of the traffic node traffic status according to the preset time window, thereby realizing the adaptive dynamic reorganization of the construction traffic flow, significantly reducing the vehicle idle rate while ensuring construction safety, thereby improving the problems of scheduling instruction lag and low resource utilization, and providing multi-dimensional data support for project cost analysis and resource optimization allocation.

[0198] See also Figure 2 As shown in FIG. 1 , this figure is a schematic diagram of the basic structure of a tunnel construction scene traffic scheduling system 200 provided by an embodiment of the present invention. The tunnel construction scene traffic scheduling system 200 includes:

[0199] Processor 201;

[0200] a storage device 202 having a computer program 2020 stored thereon;

[0201] When the computer program 2020 is executed by the processor 201, the processor 201 implements any of the traffic scheduling methods for tunnel construction scenarios based on smart transportation.

[0202] Based on the above, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the above method are implemented.

[0203] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the systems or devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

Claims

1. A traffic dispatching method for tunnel construction scenarios based on smart transportation, characterized in that: include: Acquire a set of vehicle status data at each traffic node in the tunnel construction area. The vehicle status data set includes vehicle traffic records and vehicle identification tags captured in real time by an array of RFID readers deployed at fixed locations. The vehicle traffic records include the time the vehicle entered the tunnel, the time the vehicle left the tunnel, and the location coordinates of the traffic node at which the vehicle is located. Dynamically dispatching the vehicle status data set to generate a traffic light control instruction set corresponding to each traffic node, wherein the traffic light control instruction set is used to adjust the traffic priority and vehicle release interval of the corresponding traffic node; Performing a scheduling strategy generation process according to the traffic light control instruction set to obtain a global traffic scheduling strategy for the tunnel construction area, wherein the global traffic scheduling strategy includes a vehicle route optimization plan and an equipment resource allocation plan associated with different construction faces; Feedback the global traffic scheduling strategy to the traffic light control system in the tunnel construction area to instruct the traffic light control system to execute the switching operation of the traffic node traffic state according to the preset time window; Real-time monitoring of vehicle queue length and vehicle speed at traffic nodes to generate real-time vehicle traffic status parameters; Comparing and analyzing the real-time vehicle traffic state parameters with a traffic efficiency threshold preset in the global traffic dispatch strategy, and generating an emergency dispatch trigger signal when the comparison and analysis result indicates that the length of the vehicle queue exceeds the length threshold and the vehicle speed is lower than the speed threshold; Based on the emergency dispatch trigger signal, screening the special vehicle identification for transporting hazardous materials from the vehicle identifications, and generating an emergency passage priority list including priority passage rights for special vehicles; Sending an emergency dispatch instruction to the traffic light control system according to the emergency passage priority list, wherein the emergency dispatch instruction includes extending the mandatory green light duration of the traffic node where the special vehicle is located and synchronously shortening the red light duration of the adjacent traffic nodes; Acquiring the dynamic position coordinates of the special vehicle in real time, and dynamically adjusting the attenuation coefficient of the mandatory green light extension time based on the distance between the dynamic position coordinates and the target tunnel face position; After the special vehicle passes the target traffic node, the traffic light control instruction change record and vehicle speed recovery time during the emergency dispatch process are extracted to generate an emergency dispatch process log; Perform feature matching on the emergency dispatch process log and the historical emergency event handling log, extract the traffic node location and vehicle type combinations that are triggered more than the set frequency, and generate an emergency strategy optimization knowledge base; Mapping the frequent triggering features of the traffic node locations in the emergency strategy optimization knowledge base to the path conflict dimension of the implementation risk level parameter in the strategy evaluation model to update the path conflict probability value; According to the updated path conflict probability value, the vehicle route optimization schemes associated with different construction faces in the global traffic scheduling strategy are weighted redistributed through the resource optimization decision model to generate a global traffic scheduling optimization strategy including dynamic avoidance rules.

2. The method according to claim 1, wherein The dynamically scheduling the vehicle status data set to generate a traffic light control instruction set corresponding to each traffic node includes: Parsing the vehicle type code and equipment loading parameters in the vehicle identification, determining the passage priority level of each vehicle based on the vehicle type code, and calculating the theoretical passage time of the vehicle through the current traffic node based on the equipment loading parameters; Combining the traffic priority levels and the theoretical travel duration, a dynamic sorting model for a multi-vehicle queue within a traffic node is constructed, wherein the dynamic sorting model is used to output initial scheduling parameters including a traffic priority order and a basic release interval duration; Collecting real-time environmental parameters of the tunnel construction area, including dust concentration data and construction machinery displacement, and dynamically calculating compensation for the basic release interval based on the real-time environmental parameters to obtain a compensated release interval. When the construction machinery displacement affects the road traffic space to a set proportion, the basic release interval is increased. The traffic priority sequence and the compensated release interval duration are subjected to instruction fusion processing to generate a traffic light control instruction set including a traffic priority mapping relationship and a dynamic release interval duration.

3. The method according to claim 1, wherein The performing of the scheduling strategy generation process according to the traffic light control instruction set to obtain a global traffic scheduling strategy for the tunnel construction area includes: Counting the vehicle operation time and the number of tunnel entries and exits in the vehicle passage record, wherein the vehicle operation time is the time difference between the time when the vehicle enters the tunnel and the time when the vehicle leaves the tunnel; generating, based on the vehicle operation time and the number of tunnel entries and exits, efficiency indices for different vehicle types within the tunnel construction area, the efficiency indices being used to evaluate the transport efficiency of the vehicles within the tunnel construction area; Acquiring construction schedule data, the construction schedule data including a tunnel face excavation stage identifier and a material transportation demand schedule, and performing a matching analysis between the efficiency index and the material transportation demand schedule based on the tunnel face excavation stage identifier to obtain a matching analysis result; A global traffic scheduling strategy including route adjustment parameters and resource allocation parameters is generated based on the matching analysis results. The route adjustment parameters are used to optimize the turning rules of vehicles at intersections in the tunnel construction area, and the resource allocation parameters are used to dynamically adjust the equipment deployment density.

4. The method according to claim 3, wherein After counting the vehicle operation time and the number of tunnel entries and exits in the vehicle traffic record, the method further includes: Identify the construction team code and equipment lessor ID in the vehicle identification, associate and map the vehicle operation time with the construction team code, and generate a construction team work efficiency statistics table; Calculating equipment utilization indicators for different lessees based on the equipment lessee identifier and the number of tunnel entries and exits, wherein the equipment utilization indicators are used to generate equipment maintenance cycle recommendations and leased resource statistical tags; Input the construction team work efficiency statistics table and the equipment utilization rate index into a resource optimization decision model to output a construction project resource optimization strategy, wherein the construction project resource optimization strategy includes a human resource deployment plan and an equipment leasing contract revision plan; The construction project resource optimization strategy is data-fused with the global traffic scheduling strategy to update resource allocation parameters in the global traffic scheduling strategy.

5. The method according to claim 1, wherein After obtaining the vehicle status data set of each traffic node in the tunnel construction area, the method further includes: Performing trajectory reconstruction on the vehicle passage record to generate a three-dimensional motion path of the vehicle in the tunnel construction area, the three-dimensional motion path including time dimension coordinates and space dimension coordinates; Identifying abnormal stay points and repeated round-trip sections in the three-dimensional motion path, wherein the abnormal stay points represent coordinate points where the vehicle stays in a non-operating area for a period exceeding a preset threshold; generating a traffic flow optimization suggestion based on the abnormal stop point and the repeated round-trip road section, wherein the traffic flow optimization suggestion is used to adjust the one-way traffic rules and the location of temporary roadblocks in the tunnel construction area; The traffic flow optimization suggestion is logically verified with the global traffic scheduling strategy, and when the logic verification indicates that a path conflict is detected, a regeneration operation of the global traffic scheduling strategy is triggered.

6. The method according to claim 1, wherein Before feeding back the global traffic scheduling strategy to the traffic light control system in the tunnel construction area, the method further includes: Obtaining historical traffic dispatch strategy execution effect data, including the percentage of decrease in average vehicle waiting time and the extent of increase in construction equipment utilization; Establishing a strategy evaluation model based on the execution effect data, wherein the strategy evaluation model is used to calculate the expected benefit value and implementation risk level of different scheduling strategies; Inputting the global traffic scheduling strategy into the strategy evaluation model to obtain a strategy verification report including multi-dimensional scoring indicators, wherein the multi-dimensional scoring indicators include a traffic congestion relief index and an equipment collaborative operation index; When there are scoring indicators in the strategy verification report that do not meet the preset conditions, the parameters of the global traffic scheduling strategy are iteratively optimized until all scoring indicators meet the corresponding preset conditions.

7. The method according to claim 1, wherein The step of obtaining a set of vehicle status data at each traffic node in the tunnel construction area includes: Multiple RFID reader arrays are deployed at the intersection of the tunnel mainline and the auxiliary tunnel in the tunnel construction area. Each RFID reader array includes a directional antenna and a signal enhancement module. The directional antenna is used to capture the identification code of the vehicle electronic tag; Synchronously activate infrared cameras deployed at traffic nodes to capture vehicle outline images and license plate recognition information, and cross-verify the license plate recognition information with the identification code captured by the RFID reader array; When the cross-validation result indicates that the electronic tag is damaged or the signal is lost, the vehicle outline image captured by the infrared camera device is activated to perform vehicle type matching compensation to generate a supplementary vehicle identity mark; The vehicle identity identifiers and vehicle travel records that have passed the cross-validation are timestamp aligned to form the vehicle status data set.

8. The method according to claim 1, wherein The method further comprises: monitoring in real time the emergency dispatch instruction change records after the traffic node switching operation, extracting the traffic node location and green light extension duration parameters from the emergency dispatch instruction change records, calculating the time difference between the red light synchronous shortening duration of adjacent traffic nodes and a preset time window based on the green light extension duration parameters, generating a traffic light control instruction restoration schedule, and sending a dispatch rollback instruction including a restoration priority order to the traffic light control system based on the traffic node location and the traffic light control instruction restoration schedule; Collect vehicle speed recovery data and construction equipment restart status parameters after the scheduling rollback instruction is executed, perform difference comparison between the vehicle speed recovery data and the historical benchmark speed, and update the weight coefficient of the traffic route optimization plan in the global traffic scheduling strategy according to the difference comparison result.

9. A tunnel construction scene traffic dispatching system, characterized in that: include: processor; A storage device having a computer program stored thereon, wherein when the computer program is executed by the processor, the processor implements the traffic scheduling method for tunnel construction scenarios based on smart transportation as described in any one of claims 1-8.

Images