Rail transit vehicle robot intelligent operation and maintenance digital twinborn model construction method

Abstract

The invention relates to the technical field of rail transit, in particular to a method for constructing a digital twinborn model for intelligent operation and maintenance of a rail transit vehicle robot. Comprising the following steps: constructing a rail transit vehicle big data platform; constructing a digital twin model; analyzing and predicting data; integrating the intelligent robot; continuously optimizing and updating; and displaying a graphical interface. According to the method for constructing the intelligent operation and maintenance digital twin model of the rail transit vehicle robot, the operation and maintenance efficiency and safety are improved, the maintenance cost is reduced, and comprehensive decision support and performance evaluation are provided for managers.

Description

Technical Field

[0001] The present invention relates to the field of rail transit technology, and in particular to a method for constructing a digital twin model of intelligent operation and maintenance of a rail transit vehicle robot. Background Art

[0002] With the acceleration of urbanization and the continuous growth of transportation demand, rail transit, as an important part of urban public transportation, has received increasing attention for its safety and operational efficiency. As the core component of the rail transit system, the operating status and performance of rail transit vehicles are directly related to the stability and reliability of the entire system. However, traditional vehicle operation and maintenance methods often rely on manual inspections and regular maintenance, which have problems such as low operation and maintenance efficiency, untimely fault detection, and high maintenance costs.

[0003] In order to solve these problems, in recent years, digital twin technology, as an emerging digital technology, has been widely used in industrial manufacturing, aerospace, smart cities and other fields. Digital twin technology builds a virtual model of the physical entity to achieve accurate mapping and real-time monitoring of the physical world, providing a new solution for operation and maintenance management. Applying digital twin technology to the field of rail transit vehicle operation and maintenance can achieve comprehensive monitoring of vehicle operating status, fault prediction and intelligent maintenance, improve operation and maintenance efficiency and safety, and reduce maintenance costs.

[0004] However, the application of digital twin technology in the field of rail transit vehicle operation and maintenance still faces some technical challenges. First, the structure of rail transit vehicles is complex and the operating environment is changeable. It is necessary to build a high-precision digital twin model to achieve accurate mapping and real-time monitoring of the vehicle's operating status. Secondly, the operation and maintenance tasks of rail transit vehicles are heavy and require efficient and intelligent operation and maintenance means to support. Traditional operation and maintenance methods often rely on manual inspections and regular maintenance, and there are problems such as low operation and maintenance efficiency and untimely fault detection. Summary of the invention

[0005] The present invention provides a method for constructing a digital twin model of rail transit vehicle robot intelligent operation and maintenance, which not only improves the operation and maintenance efficiency and safety, reduces maintenance costs, but also provides comprehensive decision-making support and performance evaluation for managers.

[0006] The technical solution adopted by the present invention is: a method for constructing a digital twin model of intelligent operation and maintenance of a rail transit vehicle robot, comprising the following steps:

[0007] S1: Use the Internet of Things technology to build a rail transit vehicle big data platform, which realizes real-time data collection of rail transit vehicle operation status information and vehicle surrounding environment based on information collection devices, and the information collection devices include vehicle control systems, environmental monitoring sensors and video image acquisition systems;

[0008] S2: Based on 3D modeling technology and simulation platform, build digital twin models of rail transit vehicles and their surrounding environment, realize accurate modeling of geometric models, physical models, rule models and behavioral models of physical entities, and dynamically display real-time data in the digital twin model through network technology and big data platform;

[0009] S3: Use machine learning and statistical methods to analyze rail transit vehicle operation data, predict vehicle maintenance needs and failure trends, and optimize maintenance plans and resource allocation;

[0010] S4: Integrate robotics technology to automatically inspect and repair rail transit vehicles through intelligent robots, and perform path planning and task scheduling based on digital twin models to achieve intelligent robot operation and maintenance;

[0011] S5: Continuously optimize and update the digital twin model based on real-time data and historical data to ensure that the model is highly consistent with the actual vehicle status;

[0012] S6: Displays the vehicle's operating status, maintenance requirements and fault trends through a graphical interface, supports managers' real-time monitoring and decision support for vehicle operation and maintenance, and supports multi-user concurrent access and data sharing.

[0013] As a further improvement of the present invention, the information collection device also includes a vehicle load sensor, a temperature sensor, a humidity sensor and a vibration sensor, which are used to collect the vehicle's load information, temperature information, humidity information and vibration information to comprehensively monitor the vehicle's operating status.

[0014] As a further improvement of the present invention, the digital twin model also includes detailed models of various components inside the vehicle, including the engine, braking system, suspension system, electrical system, and a model of the vehicle's surrounding environment, including tracks, platforms, and signal systems, to achieve full-scale simulation and monitoring.

[0015] As a further improvement of the present invention, the machine learning method includes support vector machines, random forests, and neural networks, which are used to predict vehicle maintenance needs and failure trends. The statistical method includes time series analysis and regression analysis, which are used to perform trend analysis and anomaly detection on vehicle operation data.

[0016] As a further improvement of the present invention, the intelligent robot has the functions of autonomous navigation, autonomous obstacle avoidance, autonomous identification and autonomous operation, and can perform inspection and maintenance tasks according to the instructions of the digital twin model. The path planning and task scheduling algorithms are based on the real-time location and status information of the vehicle, as well as the requirements and priorities of maintenance tasks.

[0017] As a further improvement of the present invention, the continuous optimization and updating include adjustment of model parameters, optimization of model structure, and improvement of model accuracy; the real-time data include vehicle operating status data, environmental monitoring data, and robot inspection data; and the historical data include vehicle maintenance records, fault records, and inspection records.

[0018] As a further improvement of the present invention, the graphical interface has rich interactive functions, supporting managers to visualize and operate vehicle operation and maintenance data, including data screening, data comparison, and data export functions, so as to improve operation and maintenance efficiency and decision-making accuracy.

[0019] Beneficial effects of the present invention: (1) Improving operation and maintenance efficiency and quality: The present invention constructs a digital twin model of rail transit vehicles and integrates intelligent robots for automatic inspection and maintenance. It can not only quickly respond to and handle vehicle failure problems, but also reduce the number and intensity of manual intervention, thereby greatly improving operation and maintenance efficiency and quality. The digital twin model can achieve continuous and comprehensive monitoring of vehicle status. Based on this, managers can predict and plan maintenance activities in advance, avoid unplanned downtime and maintenance, and ensure high availability and operational stability of rail transit vehicles.

[0020] (2) Strengthening safety management and risk control: This invention effectively enhances the safety management level of rail transit through high-precision digital twin technology and accurate prediction of vehicle operating status, maintenance requirements and fault trends. Operation and maintenance personnel can monitor the vehicle status in real time through a graphical interface, promptly identify potential safety hazards, and take preventive measures to reduce the probability of accidents. Intelligent analysis based on the digital twin model can help identify the root cause of the fault, provide more targeted maintenance suggestions, and fundamentally improve the safety performance of the vehicle.

[0021] (3) Reduce maintenance costs and optimize resource allocation: The present invention uses digital twin technology to perform intelligent operation and maintenance of rail transit vehicles, which can effectively monitor and predict the health status of vehicles, thereby realizing the transformation from the traditional time-based regular maintenance mode to the state-based on-demand maintenance mode. It can reduce unnecessary maintenance work, save maintenance costs, and ensure that maintenance work is carried out more timely and effectively, avoiding waste of resources caused by excessive or insufficient maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flow chart of the method for constructing a digital twin model of intelligent operation and maintenance of a rail transit vehicle robot of the present invention. DETAILED DESCRIPTION

[0023] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0024] The present invention provides a method for constructing a digital twin model of a rail transit vehicle robot intelligent operation and maintenance, comprising the following steps:

[0025] S1: Use the Internet of Things technology to build a rail transit vehicle big data platform, which realizes real-time data collection of rail transit vehicle operation status information and vehicle surrounding environment based on information collection devices, the information collection devices include vehicle control systems, environmental monitoring sensors and video image collection systems, the information collection devices also include vehicle load sensors, temperature sensors, humidity sensors and vibration sensors, which are used to collect vehicle load information, temperature information, humidity information and vibration information to comprehensively monitor the vehicle operation status;

[0026] S2: Based on 3D modeling technology and simulation platform, a digital twin model of rail transit vehicles and their surrounding environment is constructed to achieve accurate modeling of the geometric model, physical model, rule model and behavior model of physical entities, and real-time data is dynamically displayed in the digital twin model through network technology and big data platform. The digital twin model also includes detailed models of various components inside the vehicle, including the engine, braking system, suspension system, electrical system, and models of the vehicle's surrounding environment, including tracks, platforms, and signal systems, to achieve full-scale simulation and monitoring;

[0027] S3: Analyze the operation data of rail transit vehicles using machine learning methods and statistical methods, predict the maintenance needs and failure trends of vehicles, and optimize maintenance plans and resource allocation. The machine learning methods include support vector machines, random forests, and neural networks, which are used to predict the maintenance needs and failure trends of vehicles. The statistical methods include time series analysis and regression analysis, which are used to perform trend analysis and anomaly detection on the operation data of vehicles.

[0028] S4: Integrate robotics technology to automatically inspect and repair rail transit vehicles through intelligent robots, and perform path planning and task scheduling based on digital twin models to achieve intelligent robot operation and maintenance. The intelligent robots have autonomous navigation, autonomous obstacle avoidance, autonomous identification and autonomous operation functions, and can perform inspection and maintenance tasks according to the instructions of the digital twin model. The path planning and task scheduling algorithms are based on the real-time location and status information of the vehicle, as well as the requirements and priorities of maintenance tasks.

[0029] S5: Based on real-time data and historical data, the digital twin model is continuously optimized and updated to ensure that the model is highly consistent with the actual vehicle status. The continuous optimization and updating includes adjustment of model parameters, optimization of model structure, and improvement of model accuracy. The real-time data includes vehicle operation status data, environmental monitoring data, and robot inspection data. The historical data includes vehicle maintenance records, fault records, and repair records.

[0030] S6: The vehicle's operating status, maintenance requirements and fault trends are displayed through a graphical interface, supporting managers' real-time monitoring and decision support for vehicle operation and maintenance, and supporting multi-user concurrent access and data sharing. The graphical interface has rich interactive functions and supports managers' visual analysis and operation of vehicle operation and maintenance data, including data screening, data comparison, and data export functions, so as to improve operation and maintenance efficiency and decision-making accuracy.

[0031] Example:

[0032] A city rail transit company operates a busy subway line with multiple trains running on it. The environmental conditions for each train to run include tunnels, ground lines, and elevated lines. The average daily passenger flow of this subway line reaches 200,000. Due to the long line and the large number of vehicles, the traditional operation and maintenance methods can no longer meet the needs of efficient and timely maintenance. Frequent failures lead to low operating efficiency and reduced passenger satisfaction. Therefore, the method for constructing a digital twin model of intelligent operation and maintenance of rail transit vehicle robots in this application is adopted, and the specific implementation steps are as follows.

[0033] 1. Building a rail transit vehicle big data platform

[0034] Information collection device deployment: Vehicle control systems, environmental monitoring sensors, video image acquisition systems, as well as vehicle load sensors, temperature sensors, humidity sensors, and vibration sensors are installed on each train. These sensors are distributed in key parts of the train, such as the carriage, the bottom of the car, the wheels, etc., to comprehensively collect the train's operating status information and real-time data of the vehicle's surrounding environment.

[0035] Data collection and transmission: The data collected by the sensors are transmitted to the big data platform in real time through wireless communication technologies (such as 4G / 5G, Wi-Fi, etc.). The big data platform uses distributed storage and processing technology to ensure efficient storage and fast access to data.

[0036] 2. Building a digital twin model

[0037] 3D modeling: Use 3D modeling software (such as SolidWorks, AutoCAD, etc.) to build a geometric model of the train, including the car body, wheels, tracks, platforms, etc. At the same time, build detailed models of the internal components of the train, such as the engine, brake system, suspension system, and electrical system.

[0038] Physical model and rule model: Combine the physical characteristics and operation rules of the train, and build a physical model and a rule model through a simulation platform (such as ANSYS, MATLAB, etc.). The physical model is mainly used to simulate the dynamic behavior of the train, such as vibration, temperature distribution, etc.; the rule model is used to describe the control logic and behavior rules of the train.

[0039] Behavioral model: Build a behavioral model of the train through historical data and expert knowledge to simulate the operating status of the train under different environments and working conditions.

[0040] Dynamic data display: Use network technology (such as WebSocket) to dynamically display the real-time data of the big data platform in the digital twin model, so that managers can view the operating status and surrounding environment of the train in real time.

[0041] (III) Data analysis and prediction

[0042] Data preprocessing: Clean, denoise and format the large amount of collected data to ensure data quality and availability.

[0043] Machine learning methods: Support vector machines (SVM), random forests (RF) and neural networks (NN) are used to analyze train operation data and predict train maintenance needs and fault trends. For example, SVM is used to classify train vibration data, random forests are used to detect anomalies in temperature and humidity data, and neural networks are used to predict trends in vehicle load data.

[0044] Statistical methods: Use time series analysis (such as ARIMA model) and regression analysis (such as linear regression) to perform trend analysis and anomaly detection on train operation data. For example, use time series analysis to predict the load changes of trains in the future, and use regression analysis to find out the impact of temperature and humidity on train performance.

[0045] 4. Intelligent Robot Integration

[0046] Robot type selection: Select intelligent robots suitable for rail transit vehicle operation and maintenance, such as inspection robots with autonomous navigation and obstacle avoidance functions, and maintenance robots with autonomous identification and operation functions.

[0047] Path planning and task scheduling: Based on the real-time location and status information of the vehicle in the digital twin model, as well as the requirements and priorities of maintenance tasks, path planning algorithms (such as A* algorithm, Dijkstra algorithm) and task scheduling algorithms (such as genetic algorithm, heuristic algorithm) are used for path planning and task scheduling.

[0048] Automatic inspection and maintenance: The intelligent robot performs inspection tasks according to the instructions of the digital twin model, such as checking the wear of the wheels and detecting the temperature and humidity in the car. If a problem is found, the robot will automatically perform maintenance operations or generate a maintenance task order to notify the maintenance personnel to handle it.

[0049] (V) Continuous Optimization and Update

[0050] Data feedback: The data and maintenance records collected by the intelligent robot are fed back to the big data platform for data accumulation and analysis.

[0051] Model optimization: Based on the feedback data, the digital twin model is continuously optimized and updated using machine learning and statistical methods. For example, model parameters are adjusted to improve prediction accuracy and model structure is optimized to improve simulation efficiency.

[0052] Model verification: Regularly verify the digital twin model to ensure that it is highly consistent with the actual train status. Evaluate the accuracy and reliability of the model by comparing actual inspection and maintenance data with model prediction data.

[0053] (VI) Graphical interface display

[0054] Interface design: Design a user-friendly graphical interface to display the real-time operation status, maintenance requirements and fault trends of the train. The interface supports multi-user concurrent access and data sharing, ensuring that managers can view data anytime and anywhere.

[0055] Interactive functions: The interface has rich interactive functions, supporting data filtering, data comparison and data export. For example, you can select data for a specific time period by date range, compare the operating status of different trains, and export data for further analysis.

[0056] Decision support: An intelligent decision support system is integrated into the graphical interface to provide managers with real-time operation and maintenance suggestions and decision-making basis. For example, when a train is predicted to fail, the system will automatically prompt managers to take preventive measures to avoid train downtime.

[0057] Through the implementation of the above steps, a certain city subway system has realized the intelligent operation and maintenance of rail transit vehicles. The specific effects are as follows: (1) Improved operation and maintenance efficiency: Intelligent robots can quickly detect and handle faults, reducing the workload of manual inspections, and improving operation and maintenance efficiency by more than 30%. (2) Enhanced safety management level: The digital twin model can monitor the operating status of the train in real time, promptly detect potential safety hazards, and reduce the accident rate by 20%. (3) Reduced maintenance costs: The state-based on-demand maintenance model reduces unnecessary maintenance work and reduces maintenance costs by 15%. (4) Scientific management decisions: The graphical interface and intelligent decision support system provide managers with comprehensive operation and maintenance data and analysis results, making management decisions more scientific and accurate.

[0058] In summary, the method for constructing a digital twin model of intelligent operation and maintenance of rail transit vehicles provided by the present invention realizes comprehensive monitoring, intelligent operation and maintenance, and scientific management of rail transit vehicles through the integration of Internet of Things technology, three-dimensional modeling technology, simulation platform, machine learning method, and robotics technology, significantly improves the operation and maintenance efficiency and safety level, and reduces maintenance costs. The present invention has broad application prospects and practical value, and can be extended to other urban rail transit systems.

[0059] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a digital twin model for intelligent operation and maintenance of rail transit vehicle robots, characterized in that: The following steps are involved: S1: Use the Internet of Things technology to build a rail transit vehicle big data platform, which realizes real-time data collection of rail transit vehicle operation status information and vehicle surrounding environment based on information collection devices, and the information collection devices include vehicle control systems, environmental monitoring sensors and video image acquisition systems; S2: Based on 3D modeling technology and simulation platform, build digital twin models of rail transit vehicles and their surrounding environment, realize accurate modeling of geometric models, physical models, rule models and behavioral models of physical entities, and dynamically display real-time data in the digital twin model through network technology and big data platform; S3: Use machine learning and statistical methods to analyze rail transit vehicle operation data, predict vehicle maintenance needs and failure trends, and optimize maintenance plans and resource allocation; S4: Integrate robotics technology to automatically inspect and repair rail transit vehicles through intelligent robots, and perform path planning and task scheduling based on digital twin models to achieve intelligent robot operation and maintenance; S5: Continuously optimize and update the digital twin model based on real-time data and historical data to ensure that the model is highly consistent with the actual vehicle status; S6: Displays the vehicle's operating status, maintenance requirements and fault trends through a graphical interface, supports managers' real-time monitoring and decision support for vehicle operation and maintenance, and supports multi-user concurrent access and data sharing.

2. The method for constructing a digital twin model of intelligent operation and maintenance of a rail transit vehicle robot according to claim 1, characterized in that: The information collection device also includes a vehicle load sensor, a temperature sensor, a humidity sensor and a vibration sensor, which are used to collect the vehicle's load information, temperature information, humidity information and vibration information to comprehensively monitor the vehicle's operating status.

3. The method for constructing a digital twin model of intelligent operation and maintenance of a rail transit vehicle robot according to claim 1, characterized in that: The digital twin model also includes detailed models of the vehicle’s internal components, including the engine, braking system, suspension system, electrical system, and models of the vehicle’s surrounding environment, including tracks, platforms, and signal systems, to enable full-scale simulation and monitoring.

4. The method for constructing a digital twin model of intelligent operation and maintenance of a rail transit vehicle robot according to claim 1, characterized in that: The machine learning methods include support vector machines, random forests, and neural networks, which are used to predict vehicle maintenance needs and failure trends. The statistical methods include time series analysis and regression analysis, which are used to perform trend analysis and anomaly detection on vehicle operation data.

5. The method for constructing a digital twin model of intelligent operation and maintenance of a rail transit vehicle robot according to claim 1, characterized in that: The intelligent robot has the functions of autonomous navigation, autonomous obstacle avoidance, autonomous identification and autonomous operation, and can perform inspection and maintenance tasks according to the instructions of the digital twin model. The path planning and task scheduling algorithms are based on the real-time location and status information of the vehicle, as well as the needs and priorities of maintenance tasks.

6. The method for constructing a digital twin model of intelligent operation and maintenance of a rail transit vehicle robot according to claim 1, characterized in that: The continuous optimization and updating include adjustment of model parameters, optimization of model structure, and improvement of model accuracy; the real-time data include vehicle operation status data, environmental monitoring data, and robot inspection data; the historical data include vehicle maintenance records, fault records, and inspection records.

7. The method for constructing a digital twin model of intelligent operation and maintenance of a rail transit vehicle robot according to claim 1, characterized in that: The graphical interface has rich interactive functions, supporting managers to visualize and analyze vehicle operation and maintenance data, including data screening, data comparison, and data export functions, so as to improve operation and maintenance efficiency and decision-making accuracy.

Images