A digital twin modeling method and system for urban rail transit system

Abstract

The present invention provides a digital twin modeling method and system for an urban rail transit system. The digital twin modeling method for an urban rail transit system includes the following steps: S1, using the Internet of Things technology to build a big data platform for the urban rail transit system; S2, realizing accurate modeling of the physical entities of the urban rail transit system; S3, using machine learning methods and statistical methods to predict passenger flow in urban rail transit; S4, based on real-time data, presenting the spatiotemporal distribution state of passenger flow and vehicle flow in the urban rail transit system in real time, and simulating its evolution in the subway system, thereby predicting short-term passenger flow, and continuously optimizing the model using the real-time data of the system. The digital twin modeling method and system for an urban rail transit system provided by the present invention facilitate managers to clearly grasp the real-time operating status of the urban rail transit system, and provide a reference for the operation planning of trains and the guidance of passenger flow in the system.

Description

Technical Field

[0001] The present invention relates to the field of smart city rail transit technology and digital modeling technology, and more specifically, to a digital twin modeling method and system for an urban rail transit system. Background Art

[0002] With the development of the urban rail transit industry and the increase in the number of passengers, passenger flow management in urban rail transit systems has become an important issue in the construction of smart cities. How to quickly and efficiently dispatch to restore the normal operation of the system after an emergency has become an urgent problem to be solved in the current urban rail transit field.

[0003] Traditional simulation methods cannot effectively deal with the real-time nature of the problem, nor can they control the physical space based on the predicted situation. Artificial intelligence technologies represented by long short-term memory neural networks and recurrent neural networks are also unable to effectively predict the problem.

[0004] Digital twin technology can well integrate emerging technologies such as the Internet of Things, big data, and artificial intelligence. By building a digital mapping system of the real physical environment, it can serve the physical environment to a great extent, making it more intelligent, digital, and controllable.

[0005] Therefore, it is necessary to provide a digital twin modeling method and system for an urban rail transit system to solve the above technical problems. Summary of the invention

[0006] Purpose of the invention: In order to solve the problems of how to quickly and efficiently dispatch to restore the normal operation of the system after an emergency occurs in the current urban rail transit system, as well as the spatiotemporal distribution of vehicle and passenger flows during the interruption recovery process, the present invention provides a digital twin modeling method and system for an urban rail transit system.

[0007] To solve the above problems, the urban rail transit system digital twin modeling method provided by the present invention comprises the following steps:

[0008] Step S1, using the Internet of Things technology to build a digital urban rail transit system, based on the information collection device to realize the collection of the running status information of the urban rail transit system trains and the temporal and spatial distribution status information of the passengers in the system, and based on Hadoop to build a big data platform for the urban rail transit system to realize the storage and analysis of the collected information;

[0009] Step S2, building a digital twin model of the urban rail transit system based on Unity3D, SketchUp and .HET platform, etc., to achieve accurate modeling of the geometric model, physical model, rule model and behavior model of the physical entity of the urban rail transit system, and dynamically display the real-time information of vehicle flow and passenger flow in the digital twin model of the urban rail transit system through network technology and big data platform;

[0010] Step S3, the urban rail transit system digital twin model uses machine learning methods and statistical methods to predict the passenger flow in and out of each station in the urban rail transit;

[0011] Step S4: the urban rail transit system digital twin model has two operating modes:

[0012] Mode 1 is the twin monitoring mode, in which the temporal and spatial distribution of passenger and vehicle flows in the current urban rail transit system is presented in real time based on real-time data;

[0013] Mode 2 is the twin prediction mode, in which the system simulates its evolution in the subway system to predict short-term passenger flow and driving status, while using the system's real-time data to continuously optimize the model.

[0014] Furthermore, in step S1, the information collection device includes a subway train control system, a subway gate and a video image collection system, etc., and the collection of urban rail transit system information includes train operation status information and spatial and temporal distribution status information of passengers in the system.

[0015] Furthermore, in step S1, the collection of the train's running status information includes the train's real-time position, the train's running speed, and load information.

[0016] Furthermore, in step S1, the collection of the spatiotemporal distribution status information of passengers in the system includes the passenger's identity information, entry station name, entry time, exit station name, exit time, and the passenger's intermittent tracking and positioning information.

[0017] Furthermore, the steps of constructing the digital twin virtual model in step S2 are:

[0018] Step S21, constructing a geometric model, the specific process includes:

[0019] Use 3D modeling software to carry out refined 3D virtual modeling of different facilities in the urban rail transit system, and describe their geometric parameters (such as shape, size, position, etc.) and relationships (such as assembly relationships) in detail, so that they have good temporal and spatial consistency with the physical entities of the system facilities. At the same time, rendering of the detail level can make the geometric model visually closer to the physical entity, which can be used as the basic element for constructing the digital twin geometric model at the station level of the urban rail transit system;

[0020] Import the geometric model of urban rail transit facilities built based on 3D modeling software into Unity3D, set the position and assembly relationship of different facility models in the urban rail transit system, and complete the construction of the geometric model of the station level of the digital twin of the urban rail transit system;

[0021] Step S22, constructing a physical model, the specific process includes:

[0022] Based on the .NET platform and using object-oriented programming ideas, the physical properties, constraints, characteristics and other information of different facilities in the urban rail transit system and their mutual constraints are abstracted, and then integrated with the geometric model to complete the construction of the physical model.

[0023] Step S23, constructing a rule model, the specific process includes:

[0024] Describe the real-time response and behavior (such as evolutionary behavior over time, dynamic functional behavior, performance degradation behavior, etc.) of physical models at different granularities and spatial scales under the external environment and interference at different time scales, as well as the internal operating mechanism;

[0025] Use recurrent neural networks to build a passenger flow rule model for urban rail transit systems; build a vehicle flow rule model based on data such as train operation planning in urban rail transit systems;

[0026] Step S24, constructing a behavior model, the specific process includes:

[0027] According to historical data and effective path selection methods, a passenger flow allocation model based on random effect theory is established to calculate the dynamic selection ratio of passenger flow to each path;

[0028] The above model is continuously optimized and improved using the intermittent position information of passengers collected by the image acquisition system.

[0029] Furthermore, in step S24, the temporal and spatial distribution status information of the passengers including the passenger identification information and the intermittent tracking and positioning information of the passengers collected in step S1 is tracked to realize automatic updating of the passenger information to ensure the accuracy of the data.

[0030] Furthermore, in step S3, by analyzing the travel statistics of passengers with clear accounts and the distribution statistics of the destinations of passengers in subway stations based on machine learning and statistical methods, the travel of passengers in the next hour is judged as the basis for the train operation scheduling of the urban rail transit system, and the train operation diagram is planned in advance based on this basis.

[0031] Furthermore, in step S4, the two operation modes of the digital twin model of the urban rail transit system are constructed as follows:

[0032] Step S41, the twin monitoring mode is based on the digital twin system of the urban rail transit system constructed in step 2, and the real-time data such as subway card swiping data, subway video monitoring data, subway WIFI probe data and the urban rail transit system network model are integrated to present the distribution status of passenger flow in the digital twin model;

[0033] Step S42, the twin prediction mode goes a step further on the basis of the twin monitoring mode, integrating real-time data with historical data, and based on this, predicts the behavioral changes of the inbound passenger flow and the in-station passenger flow at each subway station in the urban rail transit system, thereby predicting the spatiotemporal distribution status of the passenger flow in the urban rail transit system in the short term.

[0034] Furthermore, a digital twin modeling system for an urban rail transit system is characterized by comprising:

[0035] An information collection system, the information collection system comprising an urban rail transit system spatiotemporal information collection module and a passenger information collection module;

[0036] A model definition system, wherein the model definition system is configured to perform abstract analysis on the urban rail transit system digital twin virtual model and construct a virtual entity organically composed of a geometric model, a physical model, a rule model, and a behavior model;

[0037] An analysis and planning system, the analysis and planning system includes an information storage module, an information analysis module and an instruction generation module.

[0038] Furthermore, the analysis and planning system also includes an information verification module, which is used to compare the information collected in the information collection system with the information analyzed by the information analysis module. If they are consistent, the instruction is manually confirmed and sent to the corresponding part. If they are inconsistent, the updated information is analyzed again by the information analysis module. The above steps are repeated until the information collected in the information collection system and the information analyzed by the information analysis module are consistent.

[0039] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0040] The present invention accurately constructs a digital twin model of the urban rail transit system based on the physical entity of the urban rail transit system, and collects data through various information collection devices, so that the real-time status of the urban rail transit system can be intuitively displayed on the local terminal through its digital twin model, which makes it easier for urban rail transit system managers to clearly grasp the real-time operating status of the urban rail transit system and provide a reference for the operation planning of trains and the guidance of passenger flow in the urban rail transit system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic diagram of the principle of an implementation example of the present invention;

[0042] Figure 2 This is a system architecture diagram of the urban rail transit system digital twin modeling method of the present invention;

[0043] Figure 3 This is a system architecture diagram of the urban rail transit system digital twin modeling system of the present invention. DETAILED DESCRIPTION

[0044] The drawings are for illustrative purposes only and should not be construed as limiting the present patent;

[0045] The technical solution of the present invention is further described below in conjunction with the accompanying drawings.

[0046] Please refer to Figure 1 , Figure 2 and Figure 3 ,in, Figure 1 It is a schematic diagram of the principle of an implementation example of the present invention; Figure 2 This is a system architecture diagram of the urban rail transit system digital twin modeling method of the present invention; Figure 3 The system architecture diagram of the urban rail transit system digital twin modeling system of the present invention. The urban rail transit system digital twin modeling method and system thereof include the following steps:

[0047] Step S1, using the Internet of Things technology to build a digital urban rail transit system, collecting the running status information of the urban rail transit system trains and the temporal and spatial distribution status information of passengers in the system based on the information collection device, and building a big data platform for the urban rail transit system based on Hadoop to store and analyze the collected information;

[0048] Step S2, building a digital twin model of the urban rail transit system based on Unity3D, SketchUp and .HET platform, etc., to achieve accurate modeling of the geometric model, physical model, rule model and behavior model of the physical entity of the urban rail transit system, and dynamically display the real-time information of vehicle flow and passenger flow in the digital twin model of the urban rail transit system through network technology and big data platform;

[0049] Step S3, the urban rail transit system digital twin model uses machine learning methods and statistical methods to predict the passenger flow in and out of each station in the urban rail transit;

[0050] Step S4: the urban rail transit system digital twin model has two operating modes:

[0051] Mode 1 is the twin monitoring mode, in which the temporal and spatial distribution of passenger and vehicle flows in the current urban rail transit system is presented in real time based on real-time data;

[0052] Mode 2 is the twin prediction mode, in which the system simulates its evolution in the subway system to predict short-term passenger flow and driving status, while using the system's real-time data to continuously optimize the model.

[0053] In step S1, information of the urban rail transit system is collected through the subway train control system, subway gate machine and video image acquisition system, and these devices are connected to the big data platform to integrate the information and establish the data foundation of the digital twin of the urban rail transit system.

[0054] In step S1, the information collection device includes a subway train control system, a subway gate, and a video image collection system, etc. The information collected from the urban rail transit system includes the running status information of the train and the temporal and spatial distribution status information of the passengers in the system.

[0055] In step S1, the collection of the train's running status information includes the train's real-time position, the train's running speed, and load information.

[0056] In step S1, the collection of the temporal and spatial distribution status information of passengers in the system includes the passenger's identity information, entry station name, entry time, exit station name, exit time, and the passenger's intermittent tracking and positioning information.

[0057] In step S2, the steps of constructing a digital twin virtual model are:

[0058] Step S21, constructing a geometric model, the specific process includes:

[0059] Use 3D modeling software to carry out refined 3D virtual modeling of different facilities in the urban rail transit system, and describe their geometric parameters (such as shape, size, position, etc.) and relationships (such as assembly relationships) in detail, so that they have good temporal and spatial consistency with the physical entities of the system facilities. At the same time, rendering of the detail level can make the geometric model visually closer to the physical entity, which can be used as the basic element for constructing the digital twin geometric model at the station level of the urban rail transit system;

[0060] Import the geometric model of urban rail transit facilities built based on 3D modeling software into Unity3D, set the position and assembly relationship of different facility models in the urban rail transit system, and complete the construction of the geometric model of the station level of the digital twin of the urban rail transit system;

[0061] Step S22, constructing a physical model, the specific process includes:

[0062] Based on the .NET platform and using object-oriented programming ideas, the physical properties, constraints, characteristics and other information of different facilities in the urban rail transit system and their mutual constraints are abstracted, and then integrated with the geometric model to complete the construction of the physical model.

[0063] Step S23, constructing a rule model, the specific process includes:

[0064] Describe the real-time response and behavior (such as evolutionary behavior over time, dynamic functional behavior, performance degradation behavior, etc.) of physical models at different granularities and spatial scales under the external environment and interference at different time scales, as well as the internal operating mechanism;

[0065] Use recurrent neural networks to build a passenger flow rule model for urban rail transit systems; build a vehicle flow rule model based on data such as train operation planning in urban rail transit systems;

[0066] Step S24, constructing a behavior model, the specific process includes:

[0067] According to historical data and effective path selection methods, a passenger flow allocation model based on random effect theory is established to calculate the dynamic selection ratio of passenger flow to each path;

[0068] The above model is continuously optimized and improved using the intermittent position information of passengers collected by the image acquisition system.

[0069] In step S24, the passenger's time-space distribution status information including the passenger's identity information and the passenger's intermittent tracking and positioning information collected in step S1 is tracked to achieve automatic update of passenger information to ensure data accuracy.

[0070] In step S3, by analyzing the travel statistics of passengers with clear accounts and the distribution statistics of the destinations of passengers in subway stations based on machine learning and statistical methods, the travel of passengers in the next hour is judged as the basis for the train operation scheduling of the urban rail transit system, and the train operation diagram is planned in advance based on this basis.

[0071] The train operation diagram can be sent through the service terminal to facilitate the issuance and acquisition of dispatching instructions.

[0072] In step S4, the two operation modes of the digital twin model of the urban rail transit system are constructed as follows:

[0073] Step S41, the twin monitoring mode is based on the digital twin system of the urban rail transit system constructed in step 2, and the real-time data such as subway card swiping data, subway video monitoring data, subway WIFI probe data and the urban rail transit system network model are integrated to present the distribution status of passenger flow in the digital twin model;

[0074] Step S42, the twin prediction mode goes a step further on the basis of the twin monitoring mode, integrating real-time data with historical data, and based on this, predicts the behavioral changes of the inbound passenger flow and the in-station passenger flow at each subway station in the urban rail transit system, thereby predicting the spatiotemporal distribution status of the passenger flow in the urban rail transit system in the short term.

[0075] A digital twin modeling system for an urban rail transit system, comprising:

[0076] An information collection system, the information collection system comprising an urban rail transit system spatiotemporal information collection module and a passenger information collection module;

[0077] A model definition system, wherein the model definition system is configured to perform abstract analysis on the urban rail transit system digital twin virtual model and construct a virtual entity organically composed of a geometric model, a physical model, a rule model, and a behavior model;

[0078] An analysis and planning system, the analysis and planning system includes an information storage module, an information analysis module and an instruction generation module.

[0079] The analysis and planning system also includes an information verification module, which is used to compare the information collected in the information collection system with the information analyzed by the information analysis module. If they are consistent, the instruction is manually confirmed and sent to the corresponding part. If they are inconsistent, the updated information is analyzed again by the information analysis module. The above steps are repeated until the information collected in the information collection system and the information analyzed by the information analysis module are consistent.

Claims

1. A digital twin modeling method for an urban rail transit system, characterized in that: The method comprises the following steps: Step S1, using the Internet of Things technology to build a digital urban rail transit system, based on the information collection device to realize the collection of the running status information of the urban rail transit system trains and the temporal and spatial distribution status information of the passengers in the system, and based on Hadoop to build a big data platform for the urban rail transit system to realize the storage and analysis of the collected information; Step S2, building a digital twin model of the urban rail transit system based on Unity3D, SketchUp and .HET platform, realizing accurate modeling of the geometric model, physical model, rule model and behavior model of the physical entity of the urban rail transit system, and dynamically displaying the real-time information of vehicle flow and passenger flow in the digital twin model of the urban rail transit system through network technology and big data platform; The specific process of building a rule model includes: describing the external environment and interference of physical models at different granularities and spatial scales at different time scales, as well as the real-time response and behavior generated by the joint action of the internal operating mechanism; using recurrent neural networks to build a passenger flow rule model for the urban rail transit system; building a traffic flow rule model based on the operation planning data of trains in the urban rail transit system; The specific process of constructing the behavior model includes: establishing a passenger flow allocation model based on random effect theory according to historical data and effective path selection methods, and calculating the dynamic selection ratio of passenger flow for each path; continuously optimizing and improving the above model using the intermittent position information of passengers collected by the image acquisition system; Step S3, the urban rail transit system digital twin model uses machine learning methods and statistical methods to predict the passenger flow in and out of each station in the urban rail transit; Step S4: the urban rail transit system digital twin model has two operation modes, including: Mode 1 is the twin monitoring mode, in which the temporal and spatial distribution of passenger and vehicle flows in the current urban rail transit system is presented in real time based on real-time data; Mode 2 is the twin prediction mode, in which the system simulates its evolution in the subway system to predict short-term passenger flow and driving status, while using the system's real-time data to continuously optimize the model.

2. The urban rail transit system digital twin modeling method according to claim 1 is characterized in that: In step S1, the information collection device includes a subway train control system, a subway gate and a video image collection system, and the collection of urban rail transit system information includes train operation status information and spatial and temporal distribution status information of passengers in the system.

3. The urban rail transit system digital twin modeling method according to claim 1 is characterized in that: In step S1, the collection of the train's running status information includes the train's real-time position, the train's running speed, and load information.

4. The urban rail transit system digital twin modeling method according to claim 1 is characterized in that: In step S1, the collection of the temporal and spatial distribution status information of passengers in the system includes the passenger's identity information, entry station name, entry time, exit station name, exit time, and the passenger's intermittent tracking and positioning information.

5. The urban rail transit system digital twin modeling method according to claim 1, characterized in that: In the step S2, the specific process of constructing the geometric model includes: using 3D modeling software to perform refined 3D virtual modeling of different facilities in the urban rail transit system, describing their geometric parameters and assembly relationships in detail, so that they have good spatiotemporal consistency with the physical entities of the system facilities, and rendering the detail levels can make the geometric model visually closer to the physical entity, which can be used as the basic element for constructing the digital twin geometric model of the urban rail transit system station level; importing the urban rail transit facility geometric model constructed based on the 3D modeling software into Unity3D, and then setting the positions and assembly relationships of different facility models in the urban rail transit system to complete the construction of the digital twin station-level geometric model of the urban rail transit system. The specific process of constructing the physical model includes: based on the .NET platform, using object-oriented programming ideas, abstracting the physical properties, constraints and feature information of different facilities in the urban rail transit system and their mutual constraint information, and then integrating them with the geometric model to complete the construction of the physical model.

6. The urban rail transit system digital twin modeling method according to claim 1, characterized in that: According to the temporal and spatial distribution status information of the passengers including the identity information of the passengers and the intermittent tracking and positioning information of the passengers collected in the step S1, the passenger information is tracked to realize automatic updating of the passenger information so as to ensure the accuracy of the data.

7. The urban rail transit system digital twin modeling method according to claim 1 is characterized in that: In step S3, by analyzing the travel statistics of passengers with clear accounts and the distribution statistics of the destinations of passengers in subway stations based on machine learning and statistical methods, the travel of passengers in the next hour is judged as the basis for the train operation scheduling of the urban rail transit system, and the train operation diagram is planned in advance based on this basis.

8. The urban rail transit system digital twin modeling method according to claim 1 is characterized in that: In step S4, the two operation modes of the digital twin model of the urban rail transit system are constructed as follows: Step S41, the twin monitoring mode is based on the urban rail transit system digital twin system constructed in step 2, and the subway card swiping data, subway video surveillance data, subway WIFI probe data and the urban rail transit system network model are integrated to present the distribution status of passenger flow in the digital twin model; Step S42, the twin prediction mode goes a step further on the basis of the twin monitoring mode, integrating real-time data with historical data, and based on this, predicts the behavioral changes of the inbound passenger flow and the in-station passenger flow at each subway station in the urban rail transit system, thereby predicting the spatiotemporal distribution status of the passenger flow in the urban rail transit system in the short term.

9. A digital twin modeling system for an urban rail transit system for implementing the method of claim 1, characterized in that: The system includes: An information collection subsystem, the information collection subsystem comprising an urban rail transit system spatiotemporal information collection module and a passenger information collection module; A model definition subsystem, wherein the model definition subsystem is configured to perform abstract analysis on the digital twin virtual model of the urban rail transit system and construct a virtual entity organically composed of a geometric model, a physical model, a rule model, and a behavior model; The analysis and planning subsystem includes an information storage module, an information analysis module and an instruction generation module.

10. The urban rail transit system digital twin modeling system according to claim 9, characterized in that: The analysis and planning subsystem also includes an information verification module, which is used to compare the information collected by the information collection subsystem with the information analyzed by the information analysis module. If they are consistent, the instruction is manually confirmed and sent to the corresponding part. If they are inconsistent, the updated information is analyzed again by the information analysis module. The above steps are repeated until the information collected by the information collection subsystem and the information analyzed by the information analysis module are consistent.

Images