Method and system for evaluating self-adaptive traffic capacity of highway toll station

Abstract

The invention relates to the technical field of highway toll station traffic capacity evaluation, in particular to a highway toll station adaptive traffic capacity evaluation method and system. Comprising the following steps: S1, setting a monitoring device in a set area of a toll station; s2, real-time monitoring is carried out through a monitoring device, and flowing vehicle information in the set area is obtained; s3, calculating the traffic capacity in the set area in combination with the vehicle flow information, and obtaining the traffic capacity in unit time; and S4, sending the calculated traffic capacity per unit time to the master control platform, storing data related to calculation per unit time in the storage unit, and returning to the step S2. Through real-time monitoring of the monitoring device, information of flowing vehicles in a set area of the highway toll station can be obtained in time, and through real-time calculation of the processing core, the traffic capacity in unit time can be evaluated in time, so that operators of the master control platform can intervene and adjust in time.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of toll station traffic capacity prediction, in particular to a self-adaptive traffic capacity evaluation method and system for a highway toll station. BACKGROUND

[0002] With the wide popularization of the ETC system of the highway, the traditional traffic capacity evaluation method mainly based on static layout and manual experience cannot meet the precise evaluation demand of traffic capacity under real-time traffic flow fluctuation and special scenarios (such as peak period, holiday, construction detour, etc.). The existing method mainly relies on the central system to collect transaction data, and it is difficult to timely perceive the microscopic features such as traffic conflict, queue length and vehicle type distribution, and the management decision support capability under sudden situation is limited. SUMMARY

[0003] In order to solve the above technical problems, the present application provides the following technical scheme: a self-adaptive traffic capacity evaluation method for a highway toll station, comprising the following steps:

[0004] S1. A monitoring device is arranged in a set area of the toll station;

[0005] S2. Real-time monitoring is performed by the monitoring device to obtain vehicle information flowing in the set area;

[0006] S3. The traffic capacity in the set area is calculated in combination with the vehicle flow information to obtain the traffic capacity per unit time;

[0007] S4. The traffic capacity per unit time calculated is sent to a general control platform, and the data involved in the calculation of the traffic capacity per unit time is stored in a storage unit, and the step S2 is returned.

[0008] Preferably, in step S1, the set area includes an entrance square, a ramp area and a merging and diverging area of the toll station.

[0009] Preferably, in step S3, the traffic capacity is calculated by a traffic capacity formula, and the traffic capacity formula is , wherein C is the traffic capacity per unit time, is the headway, is the delay time, is the average vehicle length, is the average vehicle speed, is the minimum safe distance.

[0010] Preferably, in step S3, the historical data in the storage unit is obtained, an adaptive correction term is introduced to construct an extended model, and the traffic capacity corrected by the extended model is used as the new traffic capacity per unit time to replace the original traffic capacity per unit time, and the formula of the extended model is , wherein a correction factor, a correction factor.

[0011] Preferably, the correction factor obtained by a correction factor calculation formula, the correction factor calculation formula being , wherein is a lane utilization rate, is a standard deviation of traffic flow in the current time window, is a traffic flow fluctuation threshold, is a large vehicle proportion, , , is a weight parameter obtained by experience or model optimization, and satisfies .

[0012] A highway toll station adaptive traffic capacity evaluation system for executing the above method is arranged at the entrance of the highway toll station, and comprises a general control platform for controlling various devices of the highway toll station and a monitoring device. The monitoring device is arranged on a mobile workstation, and the monitoring device comprises image monitoring equipment and ranging monitoring equipment. The mobile workstation is provided with rollers, and the mobile workstation is provided with a processing core. The processing core is electrically connected with a wireless transceiver module, an external display screen, a loudspeaker and a built-in power supply. The monitoring device is electrically connected with the processing core, and the processing core is connected with the general control platform through wireless signals through the wireless transceiver module

[0013] Compared with the prior art, the present application has the following beneficial effects:

[0014] (1) Through the cooperation of the image monitoring of the camera, the laser radar and the processing core, the vehicle information in the flowing region of the highway toll station can be obtained in time. Through the real-time calculation of the processing core, the traffic capacity per unit time can be evaluated in time, so that the operating personnel of the general control platform can intervene and adjust in time.

[0015] (2) The dynamic correction factor is introduced. In the case of combining historical data, a real-time estimation framework with adaptability is formed, and then the complex actual traffic situation is adapted. Based on the historical error feedback, the parameters are self-adjusted and the structure is optimized, and the continuous evolution ability is possessed. In complex scenes such as traffic emergencies, high-density traffic or temporary construction adjustment, the evaluation accuracy and response efficiency can be maintained, and a solid data foundation and intelligent support are provided for highway lane guidance, congestion intervention, charging scheduling and the like, and the overall traffic efficiency and service level of the toll station are improved.

[0016] Other advantages, objects, and features of the application will be set forth in part in the following specification taken in conjunction with the accompanying drawings, and in part will become apparent to those skilled in the art from a consideration of the following specification and drawings. Attached Figure Description

[0017] Fig. 1 This is a schematic diagram of the method flow of the present invention;

[0018] Fig. 2 This is a schematic diagram of the execution flow of the system of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0020] Please see Figs. 1-2 This invention provides an adaptive traffic capacity assessment system for highway toll stations, installed at highway toll stations. It includes a central control platform controlling various equipment at the toll station. The system is characterized by a monitoring device for monitoring the highway toll station, comprising an image monitoring device and a ranging monitoring device. In this embodiment, both the camera used as the image monitoring device and the lidar used as the ranging monitoring device are conventional technologies. The image monitoring device performs grayscale conversion, filtering, and gradient calculation using methods such as the Sobel operator to obtain edge information from real-time captured images. Similarly, the lidar used as the ranging monitoring device can obtain the movement information, speed information, and distance information between multiple vehicles, provided it can measure distances in real time. The monitoring device is electrically connected to the central control platform. The monitoring device monitors vehicles at the highway toll station entrance and sends the obtained information to the central control platform, which then makes targeted adjustments, such as opening more toll station entrances, closing unnecessary entrances, or guiding different vehicles to designated entrances. The monitoring device can be fixedly installed at a specific location at the highway toll station entrance to monitor a designated area.

[0021] In the embodiment, the monitoring device is part of a mobile workstation which is provided with a moving device such as a roller so that the mobile workstation can move by itself, facilitating the active replacement of the monitoring area by the operator according to the actual situation. The monitoring device is arranged on the mobile workstation, facilitating the movement of the monitoring device along with the mobile workstation. The mobile workstation is provided with a processing core which is electrically connected with a wireless transceiver module, an external display screen, a loudspeaker and a built-in power supply. The monitoring device is electrically connected with the processing core. The built-in power supply enables the monitoring device to independently travel to a specific area for independent work. After the processing core preliminarily calculates the data monitored by the monitoring device, the wireless transceiver module is connected with the total control platform through wireless signals. In the embodiment, the wireless transceiver module adopts a 5G communication module. At the same time, the external display screen and the loudspeaker can prompt and warn the vehicles at the entrance of the toll station or act as the megaphone of the total control platform to guide the vehicles. Further, through the combination of the camera as the image monitoring equipment and the laser radar as the distance monitoring equipment, the speed, distance, type, queue length, passing time and headway of the vehicles in each lane can be obtained, so as to be calculated and processed by the processing core in the subsequent process.

[0022] The control method of the system comprises the steps of:

[0023] S1. The monitoring device is arranged in the set area of the toll station, and the vehicle information content to be monitored by the monitoring device is set, including the preset related parameters such as the classification standard of large and small vehicles. The set area includes the entrance square, ramp area and split-flow area of the toll station. Fixed monitoring devices can be arranged in the above-mentioned areas. Based on the monitoring device in the embodiment which is provided with a movable roller, the monitoring device in the embodiment can be moved to the above-mentioned set area for monitoring according to the actual needs.

[0024] S2. Real-time monitoring is performed by the monitoring device to obtain the flowing vehicle information in the set area. Edge information of each vehicle at the entrance of the toll station within the monitoring range of the image monitoring device is obtained by edge detection through the image monitoring device. The size of the vehicle is obtained through the edge information of each vehicle, for example, the vehicle can be further divided into large and small vehicles. A two-dimensional coordinate system is established in the monitoring range of the image monitoring device by taking the lane within the monitoring range of the image monitoring device as a reference, and the vehicle proportion in different lanes is obtained. Further, the vehicle density in the lane and other information are obtained through the number of vehicles in the lane. Through the combination of the laser radar as the ranging monitoring device and the camera as the image monitoring device, the speed of the corresponding vehicle and the distance between the adjacent two vehicles are obtained while obtaining the edge information of each vehicle. In the case where the expressway toll station is determined as the terminal point, the passing time of the vehicle can be obtained by the speed of the vehicle and the distance of the vehicle from the terminal point. The average passing time of the vehicle and the number of passing vehicles per unit time can also be obtained by adding a timer to the vehicle when the edge information of the vehicle is obtained, and the timer stops when the vehicle reaches the terminal point.

[0025] S3. The passing capacity in the set area is calculated in combination with the vehicle flow information to obtain the passing capacity per unit time. The passing capacity is calculated by the passing capacity formula, and the passing capacity formula is , wherein C is the passing capacity per unit time, the unit is pcu / h, the constant is 3600, and the constant 3600 is the number of seconds in one hour converted into seconds, i.e. 3600 seconds; is the headway, the unit is s (second); is the delay time of the vehicle passing through the ETC toll lane, the unit is s (second); is the average vehicle length, the unit is m (meter); is the average speed of the vehicle, the unit is m / s (meter per second); is the minimum safe distance, the unit is m (meter). The above information can be directly obtained in combination with the conventional prior art.

[0026] In order to further improve the accuracy of the passing capacity evaluation, historical data can be combined to introduce an adaptive correction term to dynamically adjust the passing capacity formula to adapt to the core quantity of different traffic states, and to build a better evaluation and prediction model. In step S3, the historical data in the storage unit is obtained, the adaptive correction term is introduced to build an extended model, and the passing capacity per unit time corrected by the extended model is covered as the original passing capacity per unit time as the passing capacity per unit time. The formula of the extended model is , wherein is the corrected passing capacity per unit time, is a correction factor. Thus, when there is historical data in the storage unit, the calculated unit time capacity is obtained after the calculation of the expansion model to obtain a new unit time capacity.

[0027] wherein the correction factor is obtained by the correction factor calculation formula, and the correction factor calculation formula is , wherein is the lane utilization rate, which is the ratio of the actual traffic volume to the design capacity of the lane, and the range is [0, 1]; is the standard deviation of the traffic flow in the current time window; is the traffic flow fluctuation threshold, which is set based on historical data, for example, collect the traffic flow data of the same time period (such as early morning peak 8:00-9:00) in the past month, calculate the standard deviation sequence, and set the quantile value of a certain percentage of the sequence as , this threshold can be updated regularly according to the actual situation; is the large vehicle proportion, which is based on the monitoring device monitoring at a fixed position, and the size of the vehicle monitored at a specific location in the monitoring range can be compared with each other, which can be set by setting the fixed value of the edge information, when the range of the edge information of the vehicle is greater than the fixed value and is determined as a large vehicle, or by setting a proportion threshold, when the size of the edge information is greater than the proportion threshold, it is determined as a large vehicle; is the weight parameter obtained by experience or model optimization, which satisfies , which can be set manually, or can be calculated by historical data, using regression analysis, machine learning and other optimization algorithms to calculate the weight parameter that can minimize the error between the predicted unit time capacity and the actual unit time capacity.

[0028] S4. The calculated unit time capacity is sent to the total control platform, and the data involved in the calculation of the unit time is stored in the storage unit. When there is no historical data, the processing core directly sends the unit time capacity C calculated by the capacity formula to the total control platform; when there is historical data, the total control platform sends the corrected unit time capacity after the correction of the expansion model. After the data is sent to the total control platform, it is saved to the storage unit, which is used to establish the corrected unit time capacity ​​Reserve historical data. The storage unit can be directly set in the mobile workstation, based on the wireless signal connection between the mobile workstation and the total control platform, the storage unit can also be set in the total control platform, the processing core according to the need and in time from the total control platform call historical data. The unit time traffic capacity is sent to the total control platform, and the operator of the total control platform makes a decision according to the evaluation result, and the total control platform can set up a decision library matched with the unit time traffic capacity to assist the operator to make a decision. When the unit time traffic capacity is sent to the total control platform and the relevant data is stored in the storage unit, the system returns to step S2 to continue to monitor continuously, and continuously updates the evaluation of the unit time traffic capacity.

[0029] On the basis of the above-mentioned embodiments, the processor, module, corresponding control program, algorithm program and other supporting technologies mentioned in the present application can be implemented in combination with existing electrical technology, information technology, software technology and general protocol, which are not within the protection scope required by the present application, and will not be described in detail in the present application.

[0030] It is obvious for those skilled in the art that the present application is not limited to the details of the above-mentioned exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application. Therefore, the embodiments should be regarded as exemplary and non-limiting from any point of view.

Claims

1. A method for adaptive traffic capacity assessment of highway toll stations, characterized in that, Including the following steps: S1. Install monitoring devices in the designated area of ​​the toll station; S2. By monitoring in real time through the monitoring device, information on vehicles moving within the designated area is obtained; S3. Calculate the traffic capacity within the designated area by combining vehicle flow information to obtain the traffic capacity per unit time; S4. Send the calculated unit-time passage capability to the central control platform, and store the data related to the calculation of the unit time in the storage unit, then return to step S2.

2. The adaptive traffic capacity assessment method for highway toll stations according to claim 1, characterized in that, In step S1, the designated area includes the entrance plaza, ramp area, and merging / diverting area of ​​the toll station.

3. The adaptive traffic capacity assessment method for highway toll stations according to claim 1, characterized in that, In step S3, the traffic capacity is calculated using a traffic capacity formula, which is: In the formula, C represents the throughput capacity per unit time. The headway is the distance between the front and rear of the train. To delay time, For average vehicle length, The average speed of the vehicle. The minimum safe following distance.

4. The adaptive traffic capacity assessment method for highway toll stations according to claim 3, characterized in that, In step S3, historical data within the storage unit is acquired, an adaptive correction term is introduced to construct an extended model, and the access capacity corrected by the extended model is used to overwrite the original unit-time access capacity as the new unit-time access capacity. The formula for the extended model is as follows: In the formula This represents the corrected throughput per unit time. This is a correction factor.

5. The adaptive traffic capacity assessment method for highway toll stations according to claim 4, characterized in that, The correction factor The correction factor is obtained through the formula for calculating the correction factor. In the formula For lane utilization, The standard deviation of traffic flow within the current time window. Traffic flow fluctuation threshold The proportion of large vehicles, , , The weight parameters obtained from experience or model optimization satisfy... .

6. An adaptive traffic capacity assessment system for highway toll stations, executing the method described in any one of claims 1-5, installed at the entrance of a highway toll station, comprising a central control platform for controlling various equipment of the highway toll station and a monitoring device, characterized in that, The system includes a mobile workstation, on which the monitoring device is installed. The monitoring device includes an image monitoring device and a ranging monitoring device. The mobile workstation is equipped with wheels and a processing core. The processing core is electrically connected to a wireless transceiver module, an external display screen, a speaker, and a built-in power supply. The monitoring device is electrically connected to the processing core, and the processing core is wirelessly connected to the central control platform via the wireless transceiver module.

Images