An all-terrain intelligent monitoring method and system based on big data simulation

Abstract

The present application relates to the technical field of traffic monitoring, and more particularly to a full-road-condition intelligent monitoring method and system based on big data simulation. By parallel design of endogenous traffic dynamics and exogenous environmental safety boundary mechanism, through forced decoupling, the system can accurately calculate the endogenous impulse (traffic dynamic pressure) of traffic flow and the exogenous constraint (limit) of the environment respectively, not only preserving the physical purity of the respective data, but also laying the foundation for subsequent accurate quantification of the conflict between the two; by calculating the normalized distance of traffic dynamic pressure approaching the environmental boundary, a coupling compression factor is generated to realize the explicitization of implicit risks; using the coupling compression factor to real-time correct the constitutive parameters of the simulation model, the simulation model is no longer a stereotyped formula, but becomes an adaptive digital twin that can perceive environmental compression and automatically adjust behavior logic, improving the accuracy of future road condition deduction; combined with partial derivatives for abnormal source tracing and attribution, decision support is provided.

Description

Technical Field

[0001] This invention relates to the field of traffic monitoring technology, and in particular to a method and system for intelligent monitoring of all road conditions based on big data simulation. Background Technology

[0002] With the acceleration of urbanization and the surge in motor vehicle ownership, intelligent transportation systems have become a key means to alleviate congestion and improve road safety. In the existing comprehensive road condition monitoring technology system, big data simulation or digital twin technology is gradually replacing traditional statistical analysis as the mainstream approach. This type of technology typically collects real-time data from multi-source sensors along the roadside, constructs a virtual mapping of the road network, and utilizes traffic flow simulation models, such as cellular transport models (CTM) and car-following models, to extrapolate and predict future road conditions.

[0003] The shortcomings of existing technologies are as follows: Existing technologies often mix environmental data with traffic data during the data preprocessing stage, or simply treat environmental impact as a linear correction term in the traffic flow formula. This approach obscures the essential independence between traffic flow dynamics and the physical boundaries of the environment. Existing monitoring usually focuses on outcome indicators, such as congestion index and average speed, and lacks mediating indicators that quantify the system's sense of pressure. Risk warnings are passive, and existing technologies cannot quantify the intensity of the conflict between this kinetic energy and the boundary, thus failing to achieve true forward-looking tracking. The constitutive parameters of traditional simulation models are usually fixed values ​​calibrated offline, such as driver reaction time and expected headway, which lack environmental adaptability, causing the predicted evolution trajectory to fail in complex environments. Summary of the Invention

[0004] The main objective of this invention is to provide a method for intelligent monitoring of all road conditions based on big data simulation, and further to provide an intelligent monitoring system for all road conditions based on big data simulation that can run and implement the above method, effectively solving the problems mentioned in the background art.

[0005] The technical solution of the present invention is as follows:

[0006] Firstly, a comprehensive road condition intelligent monitoring method based on big data simulation is proposed, which includes the following steps:

[0007] S1. Real-time monitoring of vehicle speed, vehicle location tag, road segment flow, road surface water film thickness, and atmospheric visibility to obtain the average speed and road segment density.

[0008] S2. Based on the average speed and density of road segments, calculate the traffic dynamic pressure of road segments that characterizes the impact of traffic flow, and at the same time calculate the congestion wave propagation speed between adjacent road segments to construct the traffic flow state vector of road segments.

[0009] S3. Based on the road surface water film thickness, the effective adhesion coefficient of the road section is obtained, and the maximum safe speed of the road section is further obtained. Based on the maximum safe speed of the road section, the environmental safety dynamic pressure boundary of the road section is obtained, and the environmental safety boundary vector is constructed.

[0010] S4. Calculate the normalized distance between the traffic dynamic pressure boundary and the environmental safety dynamic pressure boundary of the road segment to obtain the road segment coupling pressure factor.

[0011] S5. Construct a vehicle car-following digital twin model, and based on the road segment coupling pressure factor, correct the constitutive parameters of the vehicle car-following digital twin model. The constitutive parameters include the driver's reaction time and the vehicle's expected distance. Output the driver's reaction time correction value and the vehicle's expected distance correction value.

[0012] S6. Based on the driver reaction time correction value and the vehicle expected spacing correction value, calculate the upper limit of the dynamic traffic capacity of the road segment, predict the free flow speed of vehicles and the traffic flow of the road segment in the future period, and output the road condition evolution trajectory sequence in the future period.

[0013] S7. Based on the road segment coupling compression factor and road condition evolution trajectory sequence, the road segment operation efficiency index is obtained. When the road segment operation efficiency index is lower than the preset efficiency threshold, it is determined to be an abnormal road segment, and the abnormal source of the abnormal road segment is traced.

[0014] A further improvement of the present invention is that step S1 includes the following specific steps:

[0015] S11, Real-time vehicle speed monitoring Road section label where the vehicle is located Traffic flow on road sections Road surface water film thickness and atmospheric visibility Where k is the vehicle index, i is the road segment index, and t is the time node index;

[0016] S12. Calculate the spatial average speed of each road segment using the harmonic mean. The calculation formula is as follows: ;in, This represents the spatial average speed of road segment i. Let be the number of vehicles in road segment i. Let i be the set of vehicles in road segment i; calculate the road segment density using the following formula: ;in, Let be the density of road segment i.

[0017] A further improvement of the present invention is that step S2 includes the following specific steps:

[0018] S21. Based on the average speed and density of road segments, calculate the traffic dynamic pressure of road segments, which characterizes the impact force of traffic flow. The calculation formula is as follows: ,in, Let i be the traffic dynamic pressure of road segment i;

[0019] S22. Calculate the congestion wave propagation speed between adjacent road segments. The calculation formula is:

[0020] ;

[0021] in, Let i be the congestion wave propagation speed between road segment i and adjacent road segment i+1. Let i be the traffic flow of segment i. Let i be the road segment density of road segment i+1;

[0022] S23. Construct a traffic flow state vector for a road segment based on congestion wave propagation velocity and traffic dynamic pressure. ,in, Let be the traffic flow state vector for road segment i.

[0023] A further improvement of the present invention is that step S3 includes the following specific steps:

[0024] S31. The effective adhesion coefficient of a road section is obtained based on the thickness of the water film on the road surface. The calculation formula is as follows:

[0025] ;

[0026] in, Let i be the effective adhesion coefficient of road segment i. The coefficient of friction for dry road surfaces. For road surface texture influencing factors;

[0027] S32. Calculate the maximum safe speed for the road segment using the following formula:

[0028] ;

[0029] in, Let i be the maximum safe speed for road segment i. This is the vehicle's dynamic limit speed;

[0030] S33. Obtain the safe dynamic pressure boundary of the road section environment, using the following formula: ;

[0031] in, Let i be the environmental safety dynamic pressure boundary. The blocking density constant;

[0032] S34. Construct the road segment environmental safety boundary vector ,in, Let i be the environmental safety boundary vector of road segment i.

[0033] A further improvement of the present invention is that step S4 includes the following specific steps:

[0034] S41. Calculate the normalized distance between the traffic dynamic pressure boundary and the environmental safety dynamic pressure boundary of the road segment. The expression for the normalized distance is: ; Let be the normalized distance between the traffic dynamic pressure and environmental safety dynamic pressure boundaries of road segment i. This is the normalization factor for the standard deviation of dynamic pressure;

[0035] S42. Further, the road segment coupling pressure factor is obtained, and the calculation formula for the road segment coupling pressure factor is as follows: ; Let i be the coupling pressure factor of road segment i. To take a positive function, This is the normalization coefficient.

[0036] A further improvement of this invention is that the construction process of the vehicle car-following digital twin model in S5 is as follows: acquiring static topology data and static attribute data of the road network, wherein the static topology data includes road segment length, number of road segments, and road segment connection relationships; and the static attribute data includes the free-flow speed of vehicles on each road segment and the saturated flow rate of each road segment; and constructing a directed graph G(V,E), mapping road segment i to edges. Map the intersection to nodes Each edge is assigned static road network attributes, and an independent instance is created for each vehicle based on its speed and actual position coordinates. The resulting vehicle-following digital twin model uses the intelligent driver model as its constitutive model.

[0037] A further improvement of the present invention is that S5 further includes:

[0038] S51. Based on the road segment coupling pressure factor, the constitutive parameters of the vehicle following digital twin model are corrected. The constitutive parameters include the driver's reaction time and the vehicle's expected distance. The corrected values ​​for the driver's reaction time and the vehicle's expected distance are obtained. The formula for calculating the corrected value for the driver's reaction time is as follows:

[0039] ;

[0040] in, This is a correction value for driver reaction time. This serves as a baseline value for driver reaction time. This is the first correction factor;

[0041] S52, The formula for calculating the vehicle desired spacing correction value is as follows:

[0042] ;

[0043] in, This is the correction value for the desired vehicle spacing. This is the baseline value for the desired vehicle spacing. This is the second correction factor.

[0044] A further improvement of the present invention is that step S6 includes the following specific steps:

[0045] S61. The upper limit of the dynamic capacity of the road segment is calculated based on the driver reaction time correction value and the vehicle expected spacing correction value. The calculation formula for the upper limit of the dynamic capacity of the road segment is as follows:

[0046] ;

[0047] in, Let i be the upper limit of the dynamic traffic capacity of road segment i. Let be the free-flow velocity of vehicles on road segment i;

[0048] S62, Future Time Period Internally, road segment density is updated based on the fluid continuity equation:

[0049] ;

[0050] in, The simulation time step for the vehicle-tracking digital twin model. For the updated time node The road segment density of road segment i Let i be the length of the road segment. Let i be the inflow rate of road segment i. Let i be the outflow rate of road segment i. ;

[0051] S63. The formula for predicting the free-flow speed of vehicles on a road segment in the future is: Simultaneously, the traffic flow of road sections in future periods is predicted using the following formula: Output the future road condition evolution trajectory sequence. .

[0052] A further improvement of the present invention is that S7 includes:

[0053] S71. The road segment operation efficiency index is obtained based on the road segment coupling compression factor and the road condition evolution trajectory sequence. The formula is as follows:

[0054] ;

[0055] in, This represents the operational efficiency index of road segment i in the future time period. The turbulent dissipation energy flux of road segment i is calculated using the following formula: ;in, This is the normalized adjustment coefficient;

[0056] S72. When the road segment's operational efficiency index is lower than a preset efficiency threshold, it is determined to be an abnormal road segment, and the source of the abnormality is traced. If it is an environment-driven anomaly, then it is a flow-driven anomaly.

[0057] Secondly, a full-road-condition intelligent monitoring system based on big data simulation is proposed. The system includes: a data acquisition module, an endogenous traffic calculation module, an exogenous environment calculation module, a coupled pressure calculation module, a simulation correction module, a road condition evolution module, and an efficiency evaluation and source tracing module.

[0058] The data acquisition module is used to monitor vehicle speed, road segment label, road segment flow, road surface water film thickness, and atmospheric visibility in real time, and obtain the average speed and road segment density in the road segment space.

[0059] The endogenous traffic calculation module is used to calculate the traffic dynamic pressure of road segments, which represents the impact force of traffic flow, based on the average speed and density of road segments, and to calculate the congestion wave propagation speed between adjacent road segments to construct the traffic flow state vector of road segments.

[0060] The exogenous environment calculation module is used to obtain the effective adhesion coefficient of the road section based on the road surface water film thickness, further obtain the maximum safe speed of the road section, obtain the environmental safety dynamic pressure boundary of the road section based on the maximum safe speed of the road section, and construct the environmental safety boundary vector.

[0061] The coupled pressure calculation module is used to calculate the normalized distance between the traffic dynamic pressure of the road segment and the boundary of the environmental safety dynamic pressure of the road segment, and further obtain the road segment coupled pressure factor.

[0062] The simulation correction module is used to construct a vehicle car-following digital twin model and correct the constitutive parameters of the vehicle car-following digital twin model based on the road segment coupling pressure factor. The constitutive parameters include the driver's reaction time and the vehicle's expected distance. The module outputs the driver's reaction time correction value and the vehicle's expected distance correction value.

[0063] The road condition evolution module is used to calculate the upper limit of the dynamic traffic capacity of the road segment based on the driver reaction time correction value and the vehicle expected spacing correction value, and to predict the free flow speed of vehicles and the traffic flow of the road segment in future time periods, and output the road condition evolution trajectory sequence in future time periods.

[0064] The efficiency assessment and tracing module is used to obtain the road segment operation efficiency index based on the road segment coupling pressure factor and the road condition evolution trajectory sequence. When the road segment operation efficiency index is lower than the preset efficiency threshold, it is determined to be an abnormal road segment, and the abnormality of the abnormal road segment is traced.

[0065] The technical effects of this invention are as follows:

[0066] A comprehensive intelligent road condition monitoring method based on big data simulation was constructed. This method, through parallel design of endogenous traffic dynamics and exogenous environmental safety boundary mechanisms and forced decoupling, enables the system to accurately calculate the endogenous impulses (traffic dynamic pressure) of traffic flow and the exogenous constraints (limits) of the environment, respectively. This not only preserves the physical purity of the respective data but also lays the foundation for subsequent accurate quantification of the conflict between the two. By calculating the normalized distance of traffic dynamic pressure approaching the environmental boundary, a coupling pressure factor is generated, making implicit risks explicit. The coupling pressure factor is used to correct the constitutive parameters of the simulation model in real time. The simulation model is no longer a rigid formula but an adaptive digital twin that can sense environmental pressure and automatically adjust its behavioral logic, improving the accuracy of future road condition predictions. Combining partial derivatives for anomaly attribution provides decision support. Attached Figure Description

[0067] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0068] Figure 1 This is a flowchart illustrating a method for intelligent monitoring of all road conditions based on big data simulation, according to Embodiment 1 of the present invention.

[0069] Figure 2 This is a schematic diagram of the structure of a full-road condition intelligent monitoring system based on big data simulation, according to Embodiment 2 of the present invention. Detailed Implementation

[0070] Example 1: This example constructs a full-condition intelligent monitoring method based on big data simulation. This method designs endogenous traffic dynamics and exogenous environmental safety boundary mechanisms in parallel. Through forced decoupling, the system can accurately calculate the endogenous impulses (traffic dynamic pressure) of traffic flow and the exogenous constraints (limits) of the environment, respectively. This not only preserves the physical purity of their respective data but also lays the foundation for subsequent accurate quantification of the conflict between the two. By calculating the normalized distance of traffic dynamic pressure approaching the environmental boundary, a coupling pressure factor is generated, making implicit risks explicit. The coupling pressure factor is used to correct the constitutive parameters of the simulation model in real time. The simulation model is no longer a rigid formula but an adaptive digital twin that can sense environmental pressure and automatically adjust its behavioral logic, improving the accuracy of future road condition predictions. Combining partial derivatives for anomaly attribution provides decision support.

[0071] A comprehensive road condition intelligent monitoring method based on big data simulation, such as... Figure 1 As shown, the specific steps include the following:

[0072] S1. Real-time monitoring of vehicle speed, vehicle location tag, road segment flow, road surface water film thickness, and atmospheric visibility to obtain the average speed and road segment density.

[0073] S2. Based on the average speed and density of road segments, calculate the traffic dynamic pressure of road segments that characterizes the impact of traffic flow, and at the same time calculate the congestion wave propagation speed between adjacent road segments to construct the traffic flow state vector of road segments.

[0074] S3. Based on the road surface water film thickness, the effective adhesion coefficient of the road section is obtained, and the maximum safe speed of the road section is further obtained. Based on the maximum safe speed of the road section, the environmental safety dynamic pressure boundary of the road section is obtained, and the environmental safety boundary vector is constructed.

[0075] S4. Calculate the normalized distance between the traffic dynamic pressure boundary and the environmental safety dynamic pressure boundary of the road segment to obtain the road segment coupling pressure factor.

[0076] S5. Construct a vehicle car-following digital twin model, and based on the road segment coupling pressure factor, correct the constitutive parameters of the vehicle car-following digital twin model. The constitutive parameters include the driver's reaction time and the vehicle's expected distance. Output the driver's reaction time correction value and the vehicle's expected distance correction value.

[0077] S6. Based on the driver reaction time correction value and the vehicle expected spacing correction value, calculate the upper limit of the dynamic traffic capacity of the road segment, predict the free flow speed of vehicles and the traffic flow of the road segment in the future period, and output the road condition evolution trajectory sequence in the future period.

[0078] S7. Based on the road segment coupling compression factor and road condition evolution trajectory sequence, the road segment operation efficiency index is obtained. When the road segment operation efficiency index is lower than the preset efficiency threshold, it is determined to be an abnormal road segment, and the abnormal source of the abnormal road segment is traced.

[0079] In this embodiment, step S1 includes the following specific steps:

[0080] S11, Real-time vehicle speed monitoring Road section label where the vehicle is located Traffic flow on road sections Road surface water film thickness and atmospheric visibility Where k is the vehicle index, i is the road segment index, and t is the time node index;

[0081] S12. Calculate the spatial average speed of each road segment using the harmonic mean. The calculation formula is as follows: ;in, This represents the spatial average speed of road segment i. Let be the number of vehicles in road segment i. Let i be the set of vehicles in road segment i; calculate the road segment density using the following formula: ;in, Let be the density of road segment i.

[0082] In this embodiment, step S2 includes the following specific steps:

[0083] S21. Based on the average speed and density of road segments, calculate the traffic dynamic pressure of road segments, which characterizes the impact force of traffic flow. The calculation formula is as follows: ,in, Let i be the traffic dynamic pressure of road segment i;

[0084] S22. Calculate the congestion wave propagation speed between adjacent road segments. The calculation formula is:

[0085] ;

[0086] in, Let i be the congestion wave propagation speed between road segment i and adjacent road segment i+1. Let i be the traffic flow of segment i. Let i be the road segment density of road segment i+1;

[0087] S23. Construct a traffic flow state vector for a road segment based on congestion wave propagation velocity and traffic dynamic pressure. ,in, Let be the traffic flow state vector for road segment i.

[0088] In this embodiment, step S3 includes the following specific steps:

[0089] S31. The effective adhesion coefficient of a road section is obtained based on the thickness of the water film on the road surface. The calculation formula is as follows:

[0090] ;

[0091] in, Let i be the effective adhesion coefficient of road segment i. The coefficient of friction for dry road surfaces. For road surface texture influencing factors;

[0092] S32. Based on the principle of kinematic safety, vehicles must be able to brake completely to a stop within the current visibility range. Calculate the maximum safe speed for the road segment using the following formula:

[0093] ;

[0094] in, Let i be the maximum safe speed for road segment i. This is the vehicle's dynamic limit speed; if the vehicle speed exceeds the maximum safe speed for the road segment, under the current visibility... When an obstacle is detected, the effective adhesion coefficient of the road segment will not be available within the remaining distance. Braking to stop;

[0095] S33. Convert the speed limit to the dynamic pressure limit to obtain the safe dynamic pressure boundary of the road section environment. The formula is: ;in, Let i be the environmental safety dynamic pressure boundary. The congestion density constant defines the maximum traffic energy density that the environment can tolerate.

[0096] S34. Construct the road segment environmental safety boundary vector ,in, Let i be the environmental safety boundary vector of road segment i.

[0097] In this embodiment, step S4 includes the following specific steps:

[0098] S41. Calculate the normalized distance between the traffic dynamic pressure boundary and the environmental safety dynamic pressure boundary of the road segment. The expression for the normalized distance is: ; Let be the normalized distance between the traffic dynamic pressure and environmental safety dynamic pressure boundaries of road segment i. It is the normalization factor for the standard deviation of dynamic pressure, used to eliminate dimensional differences, and its dimensions are the same as those of the traffic dynamic pressure of the road segment;

[0099] S42. Further, the road segment coupling pressure factor is obtained, and the calculation formula for the road segment coupling pressure factor is as follows: ; Let i be the coupling pressure factor of road segment i. To take a positive function, The normalization coefficient is used to eliminate dimensional differences; the road segment coupling pressure factor is a dimensionless number that characterizes the degree to which the endogenous dynamics of traffic flow approach the exogenous boundary of the environment. The higher the value, the more severe the environment or the more intense the impact of traffic flow.

[0100] In this embodiment, the construction process of the vehicle car-following digital twin model in S5 is as follows: Obtain static topology data and static attribute data of the road network. The static topology data includes road segment length, number of road segments, and road segment connectivity. The static attribute data includes the free-flow speed of vehicles on each road segment and the saturated flow rate of each road segment. Construct a directed graph G(V,E), mapping road segment i to an edge. Map the intersection to nodes Each edge is assigned static road network attributes, and an independent instance is created for each vehicle based on its speed and actual position coordinates. The resulting vehicle-following digital twin model uses the intelligent driver model as its constitutive model.

[0101] In this embodiment, S5 further includes:

[0102] S51. Based on the road segment coupling pressure factor, the constitutive parameters of the vehicle following digital twin model are corrected. The constitutive parameters include the driver's reaction time and the vehicle's expected distance. The corrected values ​​for the driver's reaction time and the vehicle's expected distance are obtained. The formula for calculating the corrected value for the driver's reaction time is as follows:

[0103] ;

[0104] in, This is a correction value for driver reaction time. This serves as a baseline value for driver reaction time. This is the first correction factor;

[0105] S52, The formula for calculating the vehicle desired spacing correction value is as follows:

[0106] ;

[0107] in, This is the correction value for the desired vehicle spacing. This is the baseline value for the desired vehicle spacing. This is the second correction factor.

[0108] In this embodiment, step S6 includes the following specific steps:

[0109] S61. The upper limit of the dynamic capacity of the road segment is calculated based on the driver reaction time correction value and the vehicle expected spacing correction value. The calculation formula for the upper limit of the dynamic capacity of the road segment is as follows:

[0110] ;

[0111] in, Let i be the upper limit of the dynamic traffic capacity of road segment i. Let be the free-flow velocity of vehicles on road segment i;

[0112] S62, Future Time Period Internally, road segment density is updated based on the fluid continuity equation:

[0113] ;

[0114] in, The simulation time step for the vehicle-tracking digital twin model. For the updated time node The road segment density of road segment i Let i be the length of the road segment. Let i be the inflow rate of road segment i. Let i be the outflow rate of road segment i. ;

[0115] S63. The formula for predicting the free-flow speed of vehicles on a road segment in the future is: Simultaneously, the traffic flow of road sections in future periods is predicted using the following formula: Output the future road condition evolution trajectory sequence. .

[0116] In this embodiment, S7 includes:

[0117] S71. Based on energy dissipation theory, and using the road segment coupling compression factor and road condition evolution trajectory sequence, the road segment operation efficiency index is obtained, with the following formula:

[0118] ;

[0119] in, This represents the operational efficiency index of road segment i in the future time period. The turbulent dissipation energy flux of road segment i is calculated using the following formula: ;in, This is a normalization adjustment coefficient used to eliminate dimensions and ensure that the turbulent dissipation energy flux is a dimensionless number.

[0120] S72. When the road segment's operational efficiency index is lower than a preset efficiency threshold, it is determined to be an abnormal road segment, and the source of the abnormality is traced. If it is an environment-driven anomaly, then it is a flow-driven anomaly.

[0121] Example 2: This example proposes a full-road condition intelligent monitoring system based on big data simulation, such as... Figure 2 As shown, it includes: a data acquisition module, an endogenous traffic calculation module, an exogenous environment calculation module, a coupled pressure calculation module, a simulation correction module, a road condition evolution module, and an efficiency evaluation and source tracing module;

[0122] The data acquisition module is used to monitor vehicle speed, road segment label, road segment flow, road surface water film thickness, and atmospheric visibility in real time, and obtain the average speed and road segment density in the road segment space.

[0123] The endogenous traffic calculation module is used to calculate the traffic dynamic pressure of road segments, which represents the impact force of traffic flow, based on the average speed and density of road segments, and to calculate the congestion wave propagation speed between adjacent road segments to construct the traffic flow state vector of road segments.

[0124] The exogenous environment calculation module is used to obtain the effective adhesion coefficient of the road section based on the road surface water film thickness, further obtain the maximum safe speed of the road section, obtain the environmental safety dynamic pressure boundary of the road section based on the maximum safe speed of the road section, and construct the environmental safety boundary vector.

[0125] The coupled pressure calculation module is used to calculate the normalized distance between the traffic dynamic pressure of the road segment and the boundary of the environmental safety dynamic pressure of the road segment, and further obtain the road segment coupled pressure factor.

[0126] The simulation correction module is used to construct a vehicle car-following digital twin model and correct the constitutive parameters of the vehicle car-following digital twin model based on the road segment coupling pressure factor. The constitutive parameters include the driver's reaction time and the vehicle's expected distance. The module outputs the driver's reaction time correction value and the vehicle's expected distance correction value.

[0127] The road condition evolution module is used to calculate the upper limit of the dynamic traffic capacity of the road segment based on the driver reaction time correction value and the vehicle expected spacing correction value, and to predict the free flow speed of vehicles and the traffic flow of the road segment in future time periods, and output the road condition evolution trajectory sequence in future time periods.

[0128] The efficiency assessment and tracing module is used to obtain the road segment operation efficiency index based on the road segment coupling pressure factor and the road condition evolution trajectory sequence. When the road segment operation efficiency index is lower than the preset efficiency threshold, it is determined to be an abnormal road segment, and the abnormality of the abnormal road segment is traced.

[0129] The steps for implementing the corresponding functions of each parameter and each unit module in the intelligent monitoring system for all road conditions based on big data simulation of the present invention can be referred to the parameters and steps in the embodiment of the intelligent monitoring method for all road conditions based on big data simulation in Embodiment 1 above, and will not be repeated here.

[0130] Example 3: This example provides an electronic device, including a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the above-described intelligent monitoring method for all road conditions based on big data simulation by calling the computer program stored in the memory.

[0131] The electronic device can vary considerably depending on its configuration or performance. It may include one or more Central Processing Units (CPUs) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the intelligent road condition monitoring method based on big data simulation provided in the above-described embodiment. The electronic device may also include other components for implementing its functions; for example, it may have wired or wireless network interfaces and input / output interfaces for data input and output. Further details are omitted in this embodiment.

[0132] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this disclosure can be embodied in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, the invention can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.

[0133] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0134] This invention is described with reference to flowchart illustrations and block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and block diagrams, as well as combinations of blocks in the flowchart illustrations and block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0135] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and boxes Figure 1 The steps of the function specified in one or more boxes.

[0136] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

Claims

1. A method for intelligent monitoring of all road conditions based on big data simulation, characterized in that: Comprise the following specific steps: S1, real-time monitoring of vehicle speed, vehicle speed, road section label, road section flow, road section water film thickness and atmospheric visibility, get the road section space average speed and road section density; S2, based on the road section space average speed and road section density, calculate the road section traffic dynamic pressure, and calculate the congestion wave propagation speed between adjacent road sections, and construct the road section traffic flow state vector; S3, based on the road section water film thickness, the effective adhesion coefficient of the road section is obtained, and the maximum safe speed of the road section is further obtained, the road section environment safety dynamic pressure boundary is obtained based on the road section maximum safe speed, and the environment safety boundary vector is constructed; S4, calculate the normalized distance of road section traffic dynamic pressure and road section environment safety dynamic pressure boundary, and further obtain the road section coupling compression factor; S5, construct a vehicle following digital twin model, and correct the constitutive parameters of the vehicle following digital twin model based on the road section coupling compression factor, the constitutive parameters include driver reaction time and vehicle expected distance, output driver reaction time correction value and vehicle expected distance correction value; S6, based on the driver reaction time correction value and the vehicle expected distance correction value, the upper limit of the road section dynamic traffic capacity is calculated, and the road section vehicle free flow speed and the road section flow in the future period are predicted, and the road condition evolution trajectory sequence in the future period is output; S7, based on the road section coupling compression factor and the road condition evolution trajectory sequence, the road section operation efficiency index is obtained, when the road section operation efficiency index is lower than the preset efficiency threshold, it is judged as the efficiency abnormal road section, and the abnormal source of the efficiency abnormal road section is traced; The S3 comprises the following specific steps: S31, based on the road section water film thickness, the effective adhesion coefficient of the road section is obtained, and the calculation formula is: ； wherein, is the effective adhesion coefficient for road segment i, is the dry road surface friction coefficient, is the road surface texture influence factor; is the road surface water film thickness for road segment i; S32, calculate the maximum safe speed of the road section, the calculation formula is: ； wherein, is the maximum safe speed for link i, is the vehicle dynamics limit speed; is the atmospheric visibility for link i; S33, obtain the environmental safety dynamic pressure boundary of the road section, the formula is: ; wherein, is the environmental safety dynamic pressure boundary of the road section i, is the jam density constant; S34, constructing a segment environment safety boundary vector wherein, is the environment safety boundary vector for segment i; The S6 comprises the following specific steps: S61, based on the driver reaction time correction value and the vehicle expected distance correction value, the upper limit of the road section dynamic traffic capacity is calculated, and the calculation formula of the road section dynamic traffic capacity is: ； wherein, is the dynamic capacity upper limit for link i, is the free flow speed for vehicles on link i; is the vehicle desired spacing correction value, is the driver reaction time correction value; S62, in a future time period Within, update the link densities based on the fluid continuity equation: ； wherein, is a simulation time step for the vehicle car following digital twin model, is the updated time node is a road segment density of road segment i, is a road segment length of road segment i, is an inflow traffic volume of road segment i, is an outflow traffic volume of road segment i, ; S63, predicting the link vehicle free-flow speed in the future period, the formula is: ; predicting the link flow in the future period at the same time, the formula is: ; outputting the link state evolution trajectory sequence in the future period . 2.The all-terrain intelligent monitoring method based on big data simulation according to claim 1, characterized in that: The S1 comprises the following specific steps: S11, monitoring vehicle speed in real time , road segment label where the vehicle is located , road segment flow , road surface water film thickness of the road segment , and atmospheric visibility , wherein k is the vehicle index, i is the road segment index, and t is the time node index. S12, calculate the spatial average speed of each section by using harmonic mean, the calculation formula is: ; wherein, represents the spatial average speed of section i, is the number of vehicles in section i, is the vehicle set of section i; calculate the section density, the calculation formula is: ; wherein, is the density of section i. 3.The all-terrain intelligent monitoring method based on big data simulation according to claim 2, characterized in that: The S2 comprises the following specific steps: S21, based on the spatial average speed of the link and the link density, a link traffic dynamic pressure representing the traffic flow impact force is calculated, and the calculation formula is: wherein, is the traffic dynamic pressure of the link i; S22, calculate the congestion wave propagation speed between adjacent road sections, the calculation formula is: ； wherein, is the congestion wave propagation speed between road segment i and its adjacent road segment i+1, is the flow of road segment i, is the road segment density of road segment i+1; S23, constructing a road section traffic flow state vector based on the congestion wave propagation speed and the traffic dynamic pressure wherein, is the traffic flow state vector of the road section i. 4.The all-terrain intelligent monitoring method based on big data simulation according to claim 3, characterized in that: The S4 comprises the following specific steps: S41, calculate the normalized distance of the traffic dynamic pressure and the environmental safety dynamic pressure boundary of the road section, and the expression of the normalized distance is: is the normalized distance of the traffic dynamic pressure and the environmental safety dynamic pressure boundary of the road section i, is a dynamic pressure standard deviation normalization factor; S42, further obtain a link coupling compression factor, and a calculation formula of the link coupling compression factor is: is a coupling compression factor of a link i, is a taking positive function, is a normalization coefficient. 5.The all-terrain intelligent monitoring method based on big data simulation according to claim 4, characterized in that: The construction process of the vehicle following digital twin model in S5 is: acquiring road network static topology data and road network static attribute data, the road network static topology data including road segment length, road segment number and road segment connection relationship; the road network static attribute data including road segment vehicle free flow speed and road segment saturated flow; constructing a directed graph G(V, E), mapping road segment i as edge mapping intersection as node assigning road network static attribute to each edge, and creating independent instance for each vehicle according to vehicle speed and vehicle actual position coordinate, outputting vehicle following digital twin model, the vehicle following digital twin model taking intelligent driver model as constitutive model. 6.The all-terrain intelligent monitoring method based on big data simulation according to claim 5, characterized in that, The S5 further comprises: S51, based on the road section coupling compression factor, the constitutive parameters of the vehicle following digital twin model are corrected, the constitutive parameters include driver reaction time and vehicle expected distance, the driver reaction time correction value and the vehicle expected distance correction value are obtained, the calculation formula of the driver reaction time correction value is: ； wherein, is a driver reaction time reference value, is a first correction coefficient; The calculation formula of the vehicle expected distance correction value is: ； wherein is a vehicle desired distance reference value, is a second correction coefficient. 7.The all-terrain intelligent monitoring method based on big data simulation of claim 6, wherein, The S7 comprises: S71, based on the road section coupling compression factor and the road condition evolution trajectory sequence, the road section operation efficiency index is obtained, the formula is: ； wherein, is the operational performance index for link i for the future time period, is the turbulent dissipation energy flux for link i, calculated as: wherein, is a normalizing adjustment factor; S72, when the link operation performance index is lower than the preset performance threshold value, determining that the link is an abnormal performance link, performing abnormality tracing of the abnormal performance link, and if is an environment leading abnormality, otherwise, it is a flow leading abnormality.

8. An all-weather intelligent monitoring system based on big data simulation, which is implemented based on the all-weather intelligent monitoring method based on big data simulation according to any one of claims 1-7, characterized in that, The system comprises: data acquisition module, endogenous traffic calculation module, exogenous environment calculation module, coupling compression calculation module, simulation correction module, road condition evolution module and efficiency evaluation and tracing module; The data acquisition module is configured to monitor vehicle speed, road section label, road section flow, road section water film thickness, and atmospheric visibility in real time, to obtain a road section space average speed and a road section density; The endogenous traffic calculation module is configured to calculate a road section traffic dynamic pressure representing traffic flow impact force based on the road section space average speed and the road section density, to calculate a congestion wave propagation speed between adjacent road sections, and to construct a road section traffic flow state vector; The exogenous environment calculation module is configured to obtain a road section effective adhesion coefficient based on the road section water film thickness, to further obtain a road section maximum safe speed, to obtain a road section environment safety dynamic pressure boundary based on the road section maximum safe speed, and to construct an environment safety boundary vector; The coupling stress calculation module is configured to calculate a normalized distance between the road section traffic dynamic pressure and the road section environment safety dynamic pressure boundary, and to further obtain a road section coupling stress factor; The simulation correction module is configured to construct a vehicle car following digital twin model, to correct a constitutive parameter of the vehicle car following digital twin model based on the road section coupling stress factor, the constitutive parameter including a driver reaction time and a vehicle desired headway, to output a driver reaction time correction value and a vehicle desired headway correction value, and to output a road section dynamic traffic capacity upper limit based on the driver reaction time correction value and the vehicle desired headway correction value. The road condition evolution module is configured to calculate a road section dynamic traffic capacity upper limit based on the driver reaction time correction value and the vehicle desired headway correction value, to predict a road section vehicle free flow speed and a road section flow in a future time period, and to output a future time period road condition evolution trajectory sequence. The efficiency evaluation and tracing module is configured to obtain a road section operation efficiency index based on the road section coupling stress factor and the road condition evolution trajectory sequence, to determine a performance abnormal road section when the road section operation efficiency index is lower than a preset efficiency threshold, and to perform abnormal tracing on the performance abnormal road section.

Images