A road intelligent guardrail decision method based on digital twinning

Abstract

The application provides a road intelligent guardrail decision-making method based on digital twinning, comprising the following steps: S1, obtaining historical static data and historical dynamic data of the intelligent guardrail and adding the historical static data and the historical dynamic data to a pre-constructed intelligent guardrail digital twinning model; S2, collecting vehicle data left by vehicles passing by both sides of the intelligent guardrail in real time, dividing the vehicle data into real-time static data and real-time dynamic data, and then updating the intelligent guardrail digital twinning model in real time; S3, calibrating a direction as a d side for the intelligent guardrail, obtaining road condition information of the d side of the intelligent guardrail in real time, and inputting the road condition information into the intelligent guardrail digital twinning model to obtain a moving adjustment probability of the intelligent guardrail to the d side, so as to assist an operator in adjusting the position of the intelligent guardrail. The beneficial effect is that the application can obtain a moving adjustment probability for decision support according to road condition information analysis, and ensure the reliability of the position adjustment of the intelligent guardrail.

Description

Technical Field

[0001] The present invention relates to the technical field of road traffic facility management, and in particular to a road intelligent guardrail decision-making method based on digital twins. Background Art

[0002] Traditional road guardrails will restrict the fluidity of traffic when there is a large difference in traffic volume on both sides of the guardrail. This is because traditional road guardrails are closed structures and vehicles cannot pass through. This may cause traffic jams and increase vehicle travel time. Therefore, the use of movable or adjustable guardrail designs when necessary is a key measure to reduce traffic congestion.

[0003] Smart road guardrails are an application based on intelligent technology that aims to improve road safety and traffic efficiency. This technology usually involves the use of various sensors, monitoring equipment, computer vision, artificial intelligence, and data analysis to monitor and analyze traffic conditions on the road in real time, and make corresponding decisions and control measures based on the collected data. However, effective data processing and analysis to extract useful information and provide decision support, as well as to ensure the stability and reliability of smart guardrails, are difficult problems that smart road guardrails urgently need to solve.

[0004] Digital twins can establish and simulate a physical entity, process or system within a virtual world platform. With the help of digital twins, the status of real-world physical entities can be understood on the virtual world platform, and predefined interface components in the physical entity can be controlled. Digital twins can integrate physical feedback data, supplemented by artificial intelligence, machine learning and software analysis, to establish a digital simulation within the virtual world platform. This simulation will automatically make corresponding changes based on feedback as the physical entity changes. Ideally, digital twins can self-learn based on multiple feedback source data and present the true status of the physical entity in the digital world in almost real time.

[0005] However, the digital twin technology currently used in roads is mostly manifested in road simulation navigation, road obstacle avoidance, real-time road condition simulation, etc., and lacks application in smart road guardrails. As a result, manual judgment is still required for the position adjustment of smart guardrails, and the reliability is low. Traditional road analysis systems lack effective data processing and analysis methods, lack decision-making support, and have low reliability in the position adjustment of smart guardrails. Summary of the Invention

[0006] The problem to be solved by the present invention is to provide a road smart guardrail decision-making method based on digital twins, which can provide effective data processing and analysis means and decision support and improve the reliability of smart guardrail position adjustment.

[0007] To solve the above problems, the present invention provides a road smart guardrail decision-making method based on digital twins, comprising the following steps:

[0008] Step S1, obtaining historical static data and historical dynamic data of the smart guardrail and adding the historical static data and the historical dynamic data to a pre-built digital twin model of the smart guardrail;

[0009] Step S2: collecting vehicle data left by vehicles passing through the two sides of the smart guardrail in real time, dividing the vehicle data into real-time static data and real-time dynamic data, and then updating the digital twin model of the smart guardrail in real time;

[0010] Step S3: Mark the left or right side of the smart guardrail as side d, extract the road condition information of side d of the smart guardrail from the historical static data, the historical dynamic data, the real-time static data and the real-time dynamic data, and input the road condition information into the digital twin model of the smart guardrail to obtain the movement adjustment probability of the smart guardrail to side d, so as to assist the operator to adjust the position of the smart guardrail according to the movement adjustment probability.

[0011] Preferably, before executing step S1, the method further includes:

[0012] The digital twin model of the smart guardrail is obtained and constructed based on the structural parameters of the existing road where the smart guardrail is located, the structural parameters of the smart guardrail and the vehicle information on the existing road.

[0013] Preferably, at least one sensor is pre-installed on the smart guardrail, and in step S2, the vehicle data is collected in real time by the sensor.

[0014] Preferably, the historical static data includes the historical length of the road where the smart guardrail is located, the historical width of the road where the smart guardrail is located, the historical number of channels on the left and right sides of the smart guardrail, and the historical number of channels offset to the left or right side of the smart guardrail relative to the initial position; the historical dynamic data includes the historical number of vehicles passing through the left and right sides of the smart guardrail per unit time, the historical vehicle detention time per unit length on the left and right sides of the smart guardrail, the historical number of vehicles passing through the left and right sides of the smart guardrail on different dates, the historical number of vehicles passing through the left and right sides of the smart guardrail at different times, and the historical number of vehicles passing through the left and right sides of the smart guardrail in different weather conditions. In step S1, the historical length of the road, the historical width of the road, the historical number of channels on the left and right sides, the historical number of offset channels, the historical number of vehicles passing through the unit time, the historical vehicle detention time per unit length, the historical number of vehicles passing through on different dates, the historical number of vehicles passing through at different times, and the historical number of vehicles passing through in different weather conditions are added to the digital twin model of the smart guardrail.

[0015] Preferably, the real-time static data includes the current length of the road where the smart guardrail is located, the current width of the road where the smart guardrail is located, the number of channels on the left side of the smart guardrail, the number of channels on the right side of the smart guardrail, the first current offset channel number of the smart guardrail to the left relative to the initial position, and the second current offset channel number of the smart guardrail to the right relative to the initial position; the current dynamic data includes the first difference in the current number of passing vehicles per unit time between the left and right sides of the smart guardrail, the second difference in the current vehicle detention time per unit length between the left and right sides of the smart guardrail, and the number of different day-to-day differences between the left and right sides of the smart guardrail. The third difference of the current number of passing vehicles at different times on the left and right sides of the smart guardrail, the fourth difference of the current number of passing vehicles at different times on the left and right sides of the smart guardrail, and the fifth difference of the current number of passing vehicles on the left and right sides of the smart guardrail in different weather conditions, then in step S2, the digital twin model of the smart guardrail is updated according to the current length of the road, the current width of the road, the number of left channels, the number of right channels, the current number of offset channels, the first current number of offset channels, the second current number of offset channels, the first difference, the second difference, the third difference, the fourth difference and the fifth difference.

[0016] Preferably, in step S2, the smart guardrail digital twin model is updated using the following expression:

[0017] DT t (L,W,N l ,N r ,O l ,O R )

[0018] =f(DT t-1 (L,W,N l ,N r ,O l ,O R ,N vpt ,T dpl ,N vd ,N vj ,N vw ))

[0019] in,

[0020] DT t Represents the digital twin model of the smart guardrail at time t;

[0021] DT t-1 Represents the digital twin model of the smart guardrail at time t-1;

[0022] f represents the update function of the smart guardrail digital twin model;

[0023] L represents the current length of the road;

[0024] W represents the current width of the road;

[0025] N l Indicates the number of left channels;

[0026] N r Indicates the number of right channels;

[0027] O l Indicates the first current offset channel number;

[0028] O R Indicates the second current offset channel number;

[0029] N vpt represents the first difference;

[0030] T dpl represents the second difference;

[0031] N vd represents the third difference;

[0032] N vj represents the fourth difference;

[0033] N vw represents the fifth difference.

[0034] Preferably, the road condition information includes the current number of channels on the side of the smart guardrail d, the total number of channels on the road where the smart guardrail is located, the current vehicle detention time per unit length on the side of the smart guardrail d, the current number of vehicles passing through the side of the smart guardrail d per unit time, the current number of vehicles passing through the side of the smart guardrail d on the current date, the historical number of vehicles passing through the side of the smart guardrail d on the same date in history, the current number of vehicles passing through the side of the smart guardrail d at the current moment, the historical number of vehicles passing through the side of the smart guardrail d at the same moment in history, the current number of vehicles passing through the side of the smart guardrail d under the current weather conditions, and the historical number of vehicles passing through the side of the smart guardrail d under the current weather conditions. The historical number of vehicles passing through under the same weather conditions in history, then in the step S3, the digital twin model of the smart guardrail obtains the movement adjustment probability of the smart guardrail to the d side according to the current number of channels, the total number of channels of the road, the current vehicle detention time under the unit length, the current number of vehicles passing through per unit time, the current number of vehicles passing through on the current date, the historical number of vehicles passing through on the same date in history, the current number of vehicles passing through at the current moment, the historical number of vehicles passing through at the same moment in history, the current number of vehicles passing through under the current weather conditions and the historical number of vehicles passing through under the same weather conditions in history.

[0035] Preferably, in step S3, the movement adjustment probability is obtained by the following calculation formula:

[0036]

[0037] in,

[0038] P d represents the movement adjustment probability;

[0039] N d Indicates the current channel number;

[0040] N l +N r Indicates the total number of channels on the road;

[0041] T dpld Indicates the current vehicle detention time under the unit length;

[0042] N vptd Indicates the current number of vehicles passing through in the unit time;

[0043] f DT Indicates that the digital twin model of the smart guardrail is sensitive to current and historical road condition information.

[0044] The comparison function of information;

[0045] N vddn Indicates the current number of vehicles passing through on the current date;

[0046] N vdd Indicates the number of vehicles that have passed through on the same date;

[0047] N vjdn Indicates the current number of vehicles passing through at the current moment;

[0048] N vjd Indicates the number of vehicles that have passed through at the same historical moment;

[0049] N vwdn Indicates the current number of vehicles passing under the current weather conditions;

[0050] N vwd Indicates the number of vehicles that passed through in the same weather conditions.

[0051] The present invention has the following beneficial effects: In the present invention, a digital twin model of a smart guardrail is constructed based on digital twin technology. When a vehicle travels on both sides of the smart guardrail, vehicle data is collected to update the dynamic data and static data of the digital twin model of the smart guardrail to ensure real-time performance, and useful information is extracted from it, namely the road condition information on the d side of the smart guardrail to perform effective data processing and analysis to obtain the movement adjustment probability of the smart guardrail to the d side, which is used as decision support to assist operators in adjusting the position of the smart guardrail. At the same time, the movement adjustment probability obtained by combining the digital twin model of the smart guardrail with a large amount of historical data and current data can improve the reliability of the position adjustment of the smart guardrail. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is a flow chart of the steps of the present invention;

[0053] Figure 2 This is a flow chart of the method in Embodiment 2 of the present invention;

[0054] Figure 3 This is a diagram of the method model in the second embodiment of the present invention.

[0055] Figure 4 This is a schematic diagram of the structure of the digital twin model of the smart guardrail in the second embodiment of the present invention;

[0056] Figure 5 This is a flowchart of the update and storage process of the digital twin model of the smart guardrail in the second embodiment of the present invention;

[0057] Figure 6 This is a schematic diagram of the decision-making process of the smart guardrail in the second embodiment of the present invention on an actual road;

[0058] Figure 7 This is a flow chart of the movement and adjustment of the smart guardrail in Example 2 of the present invention. DETAILED DESCRIPTION

[0059] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0060] In a preferred embodiment of the present invention, based on the above problems existing in the prior art, a road smart guardrail decision-making method based on digital twin is provided. Figure 1 As shown, the following steps are included:

[0061] Step S1, obtaining historical static data and historical dynamic data of the smart guardrail and adding the historical static data and historical dynamic data to a pre-built digital twin model of the smart guardrail;

[0062] Step S2: Real-time collection of vehicle data from vehicles passing through the smart guardrail, dividing the vehicle data into real-time static data and real-time dynamic data, and then updating the smart guardrail digital twin model in real time;

[0063] In step S3, the left or right side of the smart guardrail is calibrated as side d, and the road condition information of side d of the smart guardrail is extracted from the historical static data, historical dynamic data, real-time static data, and real-time dynamic data. The road condition information is input into the digital twin model of the smart guardrail to obtain the movement adjustment probability of the smart guardrail to side d, so as to assist the operator in adjusting the position of the smart guardrail according to the movement adjustment probability.

[0064] Specifically, in this embodiment, the present invention uses digital twins to construct a digital twin model of a smart guardrail in the virtual world to make decisions on the road conditions on both sides of the road in the physical world. By monitoring and predicting the road conditions on both sides of the smart guardrail and the passing vehicles, effective data processing and analysis are performed in the digital twin model of the smart guardrail to extract useful information and provide decision support as well as to ensure the stability and reliability of the smart guardrail. This can overcome the problem of existing guardrails increasing the driving time of vehicles in the case of one-sided traffic congestion. The physical world and the road conditions in the digital twin scene are closely integrated. Compared with traditional smart guardrails, it can achieve accuracy, timeliness, and efficiency in decision-making, and has stronger practicality.

[0065] Specifically, in this embodiment, the movement adjustment probability obtained by analyzing the digital twin model of the smart guardrail can be mapped to the physical world, and the position of the smart guardrail can be moved and adjusted in the physical world to ensure that vehicles can pass through the roads on both sides of the smart guardrail normally.

[0066] Specifically, in this embodiment, during the process of the smart guardrail digital twin model processing the collected vehicle data, the smart guardrail digital twin model selects and processes three factors: the type of identification data, the size of the data set, and whether the data is reliable. The processed vehicle data is divided into real-time dynamic data and real-time static data, and the smart guardrail digital twin model is updated.

[0067] Preferably, the smart guardrail digital twin model records the current static data and the current dynamic data and predicts the probability of movement adjustment. The feasibility and timeliness of the update of the smart guardrail digital twin model must be ensured. In an emergency, the update and preservation of the smart guardrail digital model must be abandoned.

[0068] In a preferred embodiment of the present invention, before executing step S1, the following steps are further included:

[0069] The digital twin model of the smart guardrail is obtained and constructed based on the structural parameters of the existing road where the smart guardrail is located, the structural parameters of the smart guardrail and the vehicle information on the existing road.

[0070] Specifically, in this embodiment, before constructing the digital twin model of the smart guardrail based on the structural parameters and vehicle information of the existing roads and smart guardrails, the existing roads, smart guardrails and vehicle information are digitally modeled or three-dimensionally modeled to obtain a model containing a large number of parameters and attributes as the model basis of the digital twin model of the smart guardrail.

[0071] In a preferred embodiment of the present invention, at least one sensor is pre-installed on the smart guardrail, and in step S2, vehicle data is collected in real time through the sensor.

[0072] In a preferred embodiment of the present invention, the historical static data includes the historical length of the road where the smart guardrail is located, the historical width of the road where the smart guardrail is located, the historical number of channels on the left and right sides of the smart guardrail, and the historical number of channels offset to the left or right of the smart guardrail relative to the initial position; the historical dynamic data includes the historical number of vehicles passing through the left and right sides of the smart guardrail per unit time, the historical vehicle detention time per unit length on the left and right sides of the smart guardrail, the historical number of vehicles passing through the left and right sides of the smart guardrail on different dates, the historical number of vehicles passing through the left and right sides of the smart guardrail at different times, and the historical number of vehicles passing through the left and right sides of the smart guardrail in different weather conditions. In step S1, the historical length of the road, the historical width of the road, the historical number of channels on the left and right sides, the historical number of offset channels, the historical number of vehicles passing through per unit time, the historical vehicle detention time per unit length, the historical number of vehicles passing through on different dates, the historical number of vehicles passing through at different times, and the historical number of vehicles passing through in different weather conditions are added to the digital twin model of the smart guardrail.

[0073] In a preferred embodiment of the present invention, the real-time static data includes the current length of the road where the smart guardrail is located, the current width of the road where the smart guardrail is located, the number of channels on the left side of the smart guardrail, the number of channels on the right side of the smart guardrail, the first current offset channel number of the smart guardrail to the left relative to the initial position, and the second current offset channel number of the smart guardrail to the right relative to the initial position. The current dynamic data includes the first difference between the current number of passing vehicles per unit time on the left and right sides of the smart guardrail, the second difference between the current vehicle detention time per unit length on the left and right sides of the smart guardrail, the third difference between the current number of passing vehicles on the left and right sides of the smart guardrail on different dates, the fourth difference between the current number of passing vehicles on the left and right sides of the smart guardrail at different times, and the fifth difference between the current number of passing vehicles on the left and right sides of the smart guardrail in different weather conditions. In step S2, the digital twin model of the smart guardrail is updated according to the current length of the road, the current width of the road, the number of channels on the left, the number of channels on the right, the current offset channel number, the first current offset channel number, the second current offset channel number, the first difference, the second difference, the third difference, the fourth difference, and the fifth difference.

[0074] In a preferred embodiment of the present invention, in step S2, the smart guardrail digital twin model is updated using the following expression:

[0075] DT t (L,W,N l ,N r ,O l ,O R )

[0076] =f(DT t-1 (L,W,N l ,N r ,O l ,O R ,N vpt ,T dpl ,N vd ,N vj ,N vw ))

[0077] in,

[0078] DT t Represents the digital twin model of the smart guardrail at time t;

[0079] DT t-1 Represents the digital twin model of the smart guardrail at time t-1;

[0080] f represents the update function of the smart guardrail digital twin model;

[0081] L represents the current length of the road;

[0082] W represents the current width of the road;

[0083] N l Indicates the number of left channels;

[0084] N r Indicates the number of right channels;

[0085] O l Indicates the first current offset channel number;

[0086] O R Indicates the second current offset channel number;

[0087] N vpt represents the first difference;

[0088] T dpl represents the second difference;

[0089] N vd represents the third difference;

[0090] N vj represents the fourth difference;

[0091] N vw Indicates the fifth difference.

[0092] In a preferred embodiment of the present invention, the road condition information includes the current number of channels on the d side of the smart guardrail, the total number of channels on the road where the smart guardrail is located, the current vehicle retention time per unit length on the d side of the smart guardrail, the current number of vehicles passing through the d side of the smart guardrail per unit time, the current number of vehicles passing through the d side of the smart guardrail on the current date, the historical number of vehicles passing through the d side of the smart guardrail on the same historical date, the current number of vehicles passing through the d side of the smart guardrail at the current moment, the historical number of vehicles passing through the d side of the smart guardrail at the same historical moment, the current number of vehicles passing through the d side of the smart guardrail in the current weather, and the historical number of vehicles passing through the d side of the smart guardrail in the same historical weather. In step S3, the digital twin model of the smart guardrail obtains the probability of adjusting the movement of the smart guardrail to the d side based on the current number of channels, the total number of channels on the road, the current vehicle retention time per unit length, the current number of vehicles passing through per unit time, the current number of vehicles passing through on the current date, the historical number of vehicles passing through on the same historical date, the current number of vehicles passing through at the current moment, the historical number of vehicles passing through at the same historical moment, the current number of vehicles passing through in the current weather, and the historical number of vehicles passing through in the same historical weather.

[0093] In a preferred embodiment of the present invention, in step S3, the movement adjustment probability is obtained by the following calculation formula:

[0094]

[0095] in,

[0096] P d represents the probability of mobile adjustment;

[0097] N d Indicates the current channel number;

[0098] N l +N r Indicates the total number of lanes on the road;

[0099] T dpld Indicates the current vehicle detention time per unit length;

[0100] N vptd Indicates the current number of vehicles passing through per unit time;

[0101] f DT Indicates the current and historical road condition information of the smart guardrail digital twin model

[0102] contrast function;

[0103] N vddn Indicates the current number of vehicles passing through on the current date;

[0104] N vdd Indicates the number of vehicles that passed through on the same historical date;

[0105] N vjdn Indicates the number of vehicles passing through at the current moment;

[0106] N vjd Indicates the number of vehicles passing through at the same historical moment;

[0107] N vwdn Indicates the current number of passing vehicles under the current weather conditions;

[0108] N vwd Indicates the number of vehicles that passed through in the same historical weather conditions.

[0109] Example 1

[0110] A road smart guardrail decision-making method based on digital twins is provided, including:

[0111] In the physical world, smart guardrails S Collect static and dynamic data on both sides of the road to initialize the digital twin model of the smart guardrail, including static data such as the length L of the road where the smart guardrail is located, the width W of the road where the smart guardrail is located, and the number of road channels N on the left side of the smart guardrail. l and the number of right road lanes N r , the number of channels O that the smart guardrail shifts to the left and right of the initial position l and O RThe information is used to build the static structure of the digital twin model of the smart guardrail. S Dynamic information of the roads on both sides, such as the number of vehicles N passing through the smart guardrail d side per unit time vptd , the time T that a vehicle stays at the smart guardrail per unit length on the d side of the smart guardrail dpld , the number of vehicles N passing through the smart guardrail on the d side of the smart guardrail on different dates vdd , the number of vehicles N passing through the smart guardrail on the d side at different times vjd , the number of vehicles N passing through the smart guardrail on the d side under different weather conditions vwd The dynamic structure of the digital twin model of the smart guardrail is constructed based on information such as the left side or the right side of the smart guardrail.

[0112] Smart guardrails regularly collect static and dynamic data M on both sides of the guardrail in the physical world at time t t , stored by the smart guardrail storage device and sent to the smart guardrail computer device for processing.

[0113] Digital twin model DT of the smart guardrail at time t-1 t-1 The reliability of the data collected and processed by the smart guardrail at time t is monitored and combined with the digital twin model DT t-1 Status is updated, including:

[0114] DT t (L,W,N l ,N r ,O l ,O R )=f(DT t-1 (L,W,N l ,N r ,O l ,O R ,N vpt ,T dpl ,N vd ,N vj ,N vw )) (1)

[0115] Among them, DT t and DT t-1 represents the digital twin model of the smart guardrail at time t and time t-1, L represents the length of the road where the current smart guardrail is located, W represents the width of the road where the current smart guardrail is located, and N l and N r Respectively represent the number of road channels on the left and right sides of the smart guardrail, O l and O R Respectively represent the number of channels of the smart guardrail that shift to the left and right relative to the initial position, where O l +OR =0,0≤O l ,O R ≤(N l +N r ) / 2, f represents the update function of the digital twin model of the smart guardrail, N vpt It represents the difference between the number of vehicles passing through the right side of the smart guardrail and the number of vehicles passing through the left side of the smart guardrail per unit time, T dpl It represents the difference between the time a vehicle stays on the smart guardrail per unit length on the right side and the time a vehicle stays on the smart guardrail per unit length on the left side. vd N represents the difference between the number of vehicles passing through the smart guardrail on the right side and the number of vehicles passing through the smart guardrail on the left side on different dates. vj N represents the difference between the number of vehicles passing the smart guardrail on the right side and the number of vehicles passing the smart guardrail on the right side at different times. vw Indicates the difference between the number of vehicles passing through the smart guardrail on the right side and the number of vehicles passing through the smart guardrail on the left side in different weather conditions.

[0116] The updated smart guardrail digital twin model DT calculates the probability of the smart guardrail moving or offsetting to side d in the digital twin:

[0117]

[0118] Among them, P d N represents the probability of the smart guardrail moving and adjusting to side d. d Indicates the number of channels on the current smart guardrail d side, N l +N r Indicates the total number of lanes on the road where the smart guardrail is located. The ratio of the time that vehicles stay at the smart guardrail per unit length on the d side to the number of vehicles passing through the smart guardrail per unit time on the d side is used to describe the congestion situation on the d side of the smart guardrail. Indicates the ratio of the number of vehicles passing through the smart guardrail d side on the current date to the number of vehicles passing through the smart guardrail d side on the same date in history. Indicates the ratio of the number of vehicles passing through the smart guardrail d side at the current moment to the number of vehicles passing through the smart guardrail d side at the same moment in history. It represents the ratio of the number of vehicles passing through the smart guardrail d side in the current weather to the number of vehicles passing through the smart guardrail d side in the same weather. DT The function represents the comparison function of the smart guardrail digital twin model between the current road conditions and the same historical conditions.

[0119] Smart Guardrail Digital Twin Model DT t The calculated probability P of moving to the d side and offsetting dCompare the probability thresholds of smart guardrail movement and offset at the current time t In the digital twin, the smart guardrail makes decisions such as: 1. Move to the left, offset; 2. Do not move, offset; 3. Offset to the right, move.

[0120] The smart guardrail digital twin model executes decisions to generate the smart guardrail digital twin model DT t‘ , and predict the digital twin model DT of smart guardrail t‘ Compared with the digital twin model DT of smart guardrail t Impact on road conditions t‘ ,include:

[0121]

[0122] where δ t It represents the impact of the unexecuted decision-making guardrail state on the road condition of the smart guardrail digital twin at time t.

[0123] The impact of the smart guardrail digital twin model on the decision to change the current road conditionsδ t‘ The average value of the road condition δ from time t to time n when the smart guardrail digital twin model does not take a decision must be met to ensure the feasibility of the decision for the digital twin.

[0124] The digital twin model of the smart guardrail selects decisions and executes them on the smart guardrail in the physical world. The guardrail moves and adjusts according to the decisions to change the number of road lanes to solve the problem of road traffic congestion.

[0125] The digital twin model of the smart guardrail uses formula (1) to model and update the road conditions in the physical world to meet the real-time monitoring of the road conditions in the physical world. The digital twin makes decisions on the movement and adjustment of the smart guardrail through formulas (2) and (3) and analyzes the feasibility of the decisions to ensure that the smart guardrail after movement and adjustment does not reduce the vehicle traffic efficiency of the road. The decision is then executed in the physical world, thereby providing the practicality of the smart guardrail through the digital twin.

[0126] Example 2

[0127] A road smart guardrail decision-making method based on digital twins is proposed for a section of road. The model diagram and processing flow of this method are shown in the following figure. Figure 2 、 Figure 3 and Figure 4 As shown, it includes the following steps:

[0128] Step 1: Initialize the digital twin model of the smart guardrail. The physical world computers and electronic devices of the smart guardrail collect road information, including static and dynamic road information.

[0129] Step 2: The smart guardrail digital twin model uses the collected road information to update the model. The flow chart is as follows: Figure 5 The specific operations are as follows:

[0130] Determine whether the digital twin model of the smart guardrail is constructed for the first time. If it is the first time to construct a digital twin model, the digital twin model of the existing road, guardrail, and vehicle information is constructed based on the information collected by the computer equipment. Figure 6 As shown, if it is determined that the current smart guardrail is not the first time to build a digital twin model, it is determined that the current smart guardrail digital twin model is updating its own model. At this time, it is necessary to collect and process the road, guardrail, and vehicle information on both sides of the smart guardrail to update the digital twin model. The update method of the smart guardrail digital twin model includes:

[0131] DTt(L,W,N l ,N r ,O l ,O R )

[0132] =f(DT t-1 (L,W,N l ,N r ,O l ,O R ,N vpt ,T dpl ,N vd ,N vj ,N vw ))

[0133] Among them, DT t and DT t-1 represents the digital twin model of the smart guardrail at time t and time t-1, L represents the length of the road where the current smart guardrail is located, W represents the width of the road where the current smart guardrail is located, and N l and N r Respectively represent the number of road channels on the left and right sides of the smart guardrail, O l and O R Respectively represent the number of channels of the smart guardrail that shift to the left and right relative to the initial position, where O l +O R =0,0≤O l ,O R ≤(N l +N r ) / 2, f represents the update function of the digital twin model of the smart guardrail, N vpt It represents the difference between the number of vehicles passing through the right side of the smart guardrail and the number of vehicles passing through the left side of the smart guardrail per unit time, T dplIt represents the difference between the time a vehicle stays on the smart guardrail per unit length on the right side and the time a vehicle stays on the smart guardrail per unit length on the left side. vd N represents the difference between the number of vehicles passing through the smart guardrail on the right side and the number of vehicles passing through the smart guardrail on the left side on different dates. vj N represents the difference between the number of vehicles passing the smart guardrail on the right side and the number of vehicles passing the smart guardrail on the right side at different times. vw Indicates the difference between the number of vehicles passing through the smart guardrail on the right side and the number of vehicles passing through the smart guardrail on the left side in different weather conditions.

[0134] Step 3: The smart guardrail makes decisions based on the current road conditions. The flowchart is as follows: Figure 7 The specific operations are as follows:

[0135] In the physical world, smart guardrails monitor current road conditions and transmit this information to the smart guardrail computer. After receiving this information, the smart guardrail's digital twin model constructs the current road conditions and calculates the probability of the smart guardrail moving or adjusting based on these conditions. The digital twin model determines the probability of the smart guardrail needing to move or adjust under the current conditions using the following formula:

[0136]

[0137] Among them, P d N represents the probability of the smart guardrail moving and adjusting to side d. d Indicates the number of channels on the current smart guardrail d side, N l +N r Indicates the total number of lanes on the road where the smart guardrail is located. The ratio of the time that vehicles stay at the smart guardrail per unit length on the d side to the number of vehicles passing through the smart guardrail per unit time on the d side is used to describe the congestion situation on the d side of the smart guardrail. Indicates the ratio of the number of vehicles passing through the smart guardrail d side on the current date to the number of vehicles passing through the smart guardrail d side on the same date in history. Indicates the ratio of the number of vehicles passing through the smart guardrail d side at the current moment to the number of vehicles passing through the smart guardrail d side at the same moment in history. It represents the ratio of the number of vehicles passing through the smart guardrail d side in the current weather to the number of vehicles passing through the smart guardrail d side in the same weather. DT The function represents the comparison function of the smart guardrail digital twin model between the current road conditions and the same historical conditions.

[0138] The digital twin determines whether the movement and adjustment probability exceeds the threshold. Based on this determination, the smart guardrail makes the following decisions:

[0139] 1. Move left and adjust

[0140] 2. No movement or adjustment

[0141] 3. Move right and adjust

[0142] The smart guardrail executes decisions in the digital twin, which then calculates the impact of the decision to determine whether the decision is reliable. The formula is as follows:

[0143]

[0144] where δ t It represents the impact of the unexecuted decision-making guardrail state on the road condition of the smart guardrail digital twin at time t.

[0145] After determining that the decision is reliable, the smart guardrail digital twin will send the decision to the physical world smart guardrail through computer equipment and execute the decision in the physical world.

[0146] In summary, the second embodiment of the present invention uses a smart guardrail model constructed in a digital twin to make decisions on the movement and adjustment of the smart guardrail in the physical world. It can reduce the risk of movement and adjustment of the smart guardrail in the physical world through feasibility analysis of the decision through the digital twin under the premise of ensuring that the smart guardrail improves the road traffic capacity. The establishment of a digital twin model of the smart guardrail can provide assistance for the current guardrail movement and adjustment decision, effectively improve the smart decision-making ability and risk resistance, and realize the intelligence of the smart guardrail decision. The present invention combines past smart guardrail movement and adjustment decisions with the currently selected decision by continuously updating and iterating the smart guardrail digital twin model, and realizes the safety of the execution of decisions in the physical world by setting the movement and offset probability thresholds and the parameters of the decision's impact on road conditions, effectively improving the accuracy, timeliness, and efficiency of the smart guardrail movement and adjustment decisions.

[0147] Example: The smart guardrail model makes decisions about the movement and adjustment of smart guardrails in the physical world

[0148] In the smart guardrail F S Static data is constructed on both sides. The road length L is 800 meters, the road width is 25 meters, and the number of road channels on the left and right sides of the smart guardrail is N. l and N r There are 3 channels in each case, so the number of channels that the smart guardrail has shifted to the left and right of the initial position is O. l and O R The dynamic information sets the difference N in the number of vehicles passing through the two sides of the smart guardrail per unit time. vpt =10, which is the number of vehicles N passing the left side of the smart guardrail per unit time vptl =20, the number of vehicles N passing the left side of the smart guardrail per unit time vptr=30, the time T that a vehicle stays on the smart guardrail per unit length on the left side of the smart guardrail dpll The time T of the vehicle staying at the smart guardrail per unit length on the right side of the smart guardrail is 5 seconds. dplr For 3 seconds, the number of vehicles N passing through the smart guardrail on the left side of the smart guardrail on the current date vdl is 500, the number of vehicles passing through the smart guardrail on the right side is N vdr =300, the number of vehicles N passing through the smart guardrail on the left side at the current moment vjl =50, the number of vehicles N passing through the smart guardrail on the right side at the current moment vjr =30, the number of vehicles N passing through the smart guardrail on the left side under the current weather conditions vwl is 50, the number of vehicles passing through the smart guardrail on the right side is N vwl is 30.

[0149] After collecting information about the physical world, the smart guardrail updates its own model by inserting the data into Formula 1 to generate the digital twin model DT of the smart guardrail at time t. t After that, the digital twin model calculates the movement and adjustment probability of the current road conditions. The data needs to be put into formula 2 to calculate the movement and adjustment P d , execute decisions in the digital twin model and monitor their impact. Substitute Equation 3 into it to determine whether the decision is reliable. The specific calculation of this process is as follows:

[0150] DT t-1 (L,W,N l ,N r ,O l ,O R ,N vpt ,T dpl ,N vd ,N vj ,N vw )

[0151] DT t (L,W,N l ,N r ,O l ,O R )=f(DT t-1 )

[0152]

[0153] where f DT Take f(x) = x function, the road conditions at the historical moment are the same as at this moment, that is, N vddn =N vddn , N vjdn =N vjd , N vwdn =N vwd .

[0154]

[0155]

[0156] Set the current decision deviation threshold is 0.05, that is:

[0157] P l -P r >0.05

[0158] According to the decision, the smart guardrail executes the movement and adjustment decision to the left or right in the digital chaos model.

[0159] After the decision is made, the impact of the decision on the road conditions in the digital twin is judged and obtained.

[0160]

[0161] Decisions are executed in the physical world based on the reliability of their execution.

[0162] This example fully demonstrates that in the process of intelligent analysis, it is very necessary to map the judgment execution of decisions and the impact of decisions on road conditions in the digital twin model to the physical world.

[0163] In this example, the relevant symbols are shown in Table 1:

[0164] Table 1 Symbol Notes

[0165]

[0166]

[0167] Example 3

[0168] An electronic device is provided, comprising a memory and a processor, wherein the processor and the memory communicate with each other, the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute a road smart guardrail decision-making method based on digital twins, the method comprising the following process steps:

[0169] Build a digital twin model of the smart guardrail based on existing road, guardrail, and vehicle information, and add the existing static and dynamic data of local vehicles to the digital twin model;

[0170] When a vehicle passes through the smart guardrail, the smart guardrail collects data left by vehicles on both sides of the guardrail through sensors and uploads the vehicle data to the digital twin model;

[0171] The smart guardrail digital twin model processes the collected vehicle data and updates the smart guardrail digital twin model based on the processed static and dynamic data;

[0172] The smart guardrail digital twin model monitors current road conditions in real time and presents the collected road condition information within the digital twin model. It also moves and adjusts the smart guardrail, predicting and analyzing its impact on vehicle traffic. Finally, the digital twin determines the decision-making method for the smart guardrail.

[0173] The selected road smart guardrail decision method is mapped to the physical world, and the smart guardrail is moved and adjusted in the physical world to ensure that vehicles can pass through the roads on both sides of the smart guardrail normally.

[0174] Example 4

[0175] A computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, a method for making a decision on a road smart guardrail based on a digital twin is implemented. The method includes the following steps:

[0176] Build a digital twin model of the smart guardrail based on existing road, guardrail, and vehicle information, and add the existing static and dynamic data of local vehicles to the digital twin model;

[0177] When a vehicle passes through the smart guardrail, the smart guardrail collects data left by vehicles on both sides of the guardrail through sensors and uploads the vehicle data to the digital twin model;

[0178] The smart guardrail digital twin model processes the collected vehicle data and updates the smart guardrail digital twin model based on the processed static and dynamic data;

[0179] The smart guardrail digital twin model monitors current road conditions in real time and presents the collected road condition information within the digital twin model. It also moves and adjusts the smart guardrail, predicting and analyzing its impact on vehicle traffic. Finally, the digital twin determines the decision-making method for the smart guardrail.

[0180] The selected road smart guardrail decision method is mapped to the physical world, and the smart guardrail is moved and adjusted in the physical world to ensure that vehicles can pass through the roads on both sides of the smart guardrail normally.

[0181] Example 5

[0182] A computer device is provided, comprising a memory and a processor, wherein the processor and the memory communicate with each other, the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute a road smart guardrail decision-making method based on digital twins, the method comprising the following process steps:

[0183] Build a digital twin model of the smart guardrail based on existing road, guardrail, and vehicle information, and add the existing static and dynamic data of local vehicles to the digital twin model;

[0184] When a vehicle passes through the smart guardrail, the smart guardrail collects data left by vehicles passing on both sides of the guardrail through sensors and uploads the vehicle data to the digital twin model.

[0185] Although the present disclosure is disclosed as above, the protection scope of the present disclosure is not limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present disclosure, and these changes and modifications will fall within the protection scope of the present invention.

Claims

1. A road smart guardrail decision-making method based on digital twins, characterized by: The smart guardrail is pre-installed in the middle of an existing road to divide the existing road into a road on the left side of the smart guardrail and a road on the right side of the smart guardrail, and the length direction of the smart guardrail is the same as the direction of vehicle travel on the existing road, including the following steps: Step S1, obtaining historical static data and historical dynamic data of the smart guardrail and adding the historical static data and the historical dynamic data to a pre-built digital twin model of the smart guardrail; Step S2: collecting vehicle data left by vehicles passing through the two sides of the smart guardrail in real time, dividing the vehicle data into real-time static data and real-time dynamic data, and then updating the digital twin model of the smart guardrail in real time; Step S3: Demarcate the left or right side of the smart guardrail as side d, extract road condition information on side d of the smart guardrail from the historical static data, the historical dynamic data, the real-time static data, and the real-time dynamic data, and input the road condition information into the smart guardrail digital twin model to obtain a movement adjustment probability of the smart guardrail toward side d, thereby assisting operators in adjusting the position of the smart guardrail based on the movement adjustment probability. The road condition information includes the current number of lanes on the smart guardrail d side, the total number of lanes on the road where the smart guardrail is located, the current vehicle detention time per unit length on the smart guardrail d side, the current number of vehicles passing through the smart guardrail d side per unit time, the current number of vehicles passing through the smart guardrail d side on the current date, the historical number of vehicles passing through the smart guardrail d side on the same date in history, the current number of vehicles passing through the smart guardrail d side at the current moment, the historical number of vehicles passing through the smart guardrail d side at the same moment in history, the current number of vehicles passing through the smart guardrail d side under the current weather conditions, and the historical number of vehicles passing through the smart guardrail d side under the same weather conditions in history. The historical number of vehicles passing through under certain weather conditions, then in step S3, the smart guardrail digital twin model obtains the movement adjustment probability of the smart guardrail to the d side according to the current number of channels, the total number of channels on the road, the current vehicle detention time per unit length, the current number of vehicles passing through per unit time, the current number of vehicles passing through on the current date, the historical number of vehicles passing through on the same date in history, the current number of vehicles passing through at the current moment, the historical number of vehicles passing through at the same moment in history, the current number of vehicles passing through under the current weather conditions, and the historical number of vehicles passing through under the same weather conditions in history; In step S3, the movement adjustment probability is obtained by the following calculation formula: in, P d represents the movement adjustment probability; N d Indicates the current channel number; N l +N r Indicates the total number of channels on the road; T dpld Indicates the current vehicle detention time under the unit length; N vptd Indicates the current number of vehicles passing through in the unit time; The ratio of the current vehicle detention time per unit length to the current number of vehicles passing through per unit time is used to describe the congestion situation on the side d of the smart guardrail. f DT represents the comparison function of the digital twin model of the smart guardrail for the current road condition information and the historical road condition information, f DT Take f(x) = x function; N vddn Indicates the current number of vehicles passing through on the current date; N vdd Indicates the number of vehicles that have passed through on the same date; N vjdn Indicates the current number of vehicles passing through at the current moment; N vjd Indicates the number of vehicles that have passed through at the same historical moment; N vwdn Indicates the current number of vehicles passing under the current weather conditions; N vwd Indicates the number of vehicles that passed through in the same weather conditions.

2. The road intelligent guardrail decision-making method according to claim 1 is characterized in that: Before executing step S1, the method further includes: The structural parameters of the existing road where the smart guardrail is located, the structural parameters of the smart guardrail and the vehicle information on the existing road are obtained, and the digital twin model of the smart guardrail is constructed based on the structural parameters of the existing road where the smart guardrail is located, the structural parameters of the smart guardrail and the vehicle information on the existing road.

3. The road intelligent guardrail decision-making method according to claim 1 is characterized in that: At least one sensor is pre-installed on the smart guardrail, and in step S2, the vehicle data is collected in real time by the sensor.

4. The road intelligent guardrail decision-making method according to claim 1 is characterized in that: The historical static data includes the historical length of the road where the smart guardrail is located, the historical width of the road where the smart guardrail is located, the historical number of channels on the left and right sides of the smart guardrail, and the historical number of channels offset to the left or right side of the smart guardrail relative to the initial position. The historical dynamic data includes the historical number of vehicles passing through the left and right sides of the smart guardrail per unit time, the historical vehicle detention time per unit length on the left and right sides of the smart guardrail, the historical number of vehicles passing through the left and right sides of the smart guardrail on different dates, the historical number of vehicles passing through the left and right sides of the smart guardrail at different times, and the historical number of vehicles passing through the left and right sides of the smart guardrail in different weather conditions. In step S1, the historical length of the road, the historical width of the road, the historical number of channels on the left and right sides, the historical number of offset channels, the historical number of vehicles passing through the unit time, the historical vehicle detention time per unit length, the historical number of vehicles passing through on different dates, the historical number of vehicles passing through at different times, and the historical number of vehicles passing through in different weather conditions are added to the digital twin model of the smart guardrail.

5. The road intelligent guardrail decision-making method according to claim 1 is characterized in that: The real-time static data includes the current length of the road where the smart guardrail is located, the current width of the road where the smart guardrail is located, the number of channels on the left side of the smart guardrail, the number of channels on the right side of the smart guardrail, the first current offset channel number of the smart guardrail to the left relative to the initial position, and the second current offset channel number of the smart guardrail to the right relative to the initial position. The real-time dynamic data includes the first difference in the current number of passing vehicles per unit time between the left and right sides of the smart guardrail, the second difference in the current vehicle detention time per unit length between the left and right sides of the smart guardrail, the number of channels on the left and right sides of the smart guardrail, and the number of channels on the left and right sides of the smart guardrail. The third difference between the current number of passing vehicles on different dates, the fourth difference between the current number of passing vehicles on the left and right sides of the smart guardrail at different times, and the fifth difference between the current number of passing vehicles on the left and right sides of the smart guardrail in different weather conditions, then in step S2, the digital twin model of the smart guardrail is updated according to the current length of the road, the current width of the road, the number of channels on the left, the number of channels on the right, the first current number of offset channels, the second current number of offset channels, the first difference, the second difference, the third difference, the fourth difference and the fifth difference.

6. The road intelligent guardrail decision-making method according to claim 5 is characterized in that: In step S2, the smart guardrail digital twin model is updated using the following expression: DT t (L, W, N l ,N r ,O l ,O R )=f(DT t-1 (L, W, N l ,N r ,O l ,O R ,N vpt ,T dpl ,N vd ,N vj ,N vw )) in, DT t Represents the digital twin model of the smart guardrail at time t; DT t-1 Represents the digital twin model of the smart guardrail at time t-1; f represents the update function of the smart guardrail digital twin model; L represents the current length of the road; W represents the current width of the road; N l Indicates the number of left channels; N r Indicates the number of right channels; O l Indicates the first current offset channel number; O R Indicates the second current offset channel number; N vpt represents the first difference; T dpl represents the second difference; N vd represents the third difference; N vj represents the fourth difference; N vw represents the fifth difference.

Images