Rail transit vehicle robot intelligent operation and maintenance system based on digital twinning

Abstract

The invention relates to the technical field of rail transit, in particular to a rail transit vehicle robot intelligent operation and maintenance system based on digital twinning. The system is composed of a digital twin model construction module, a real-time monitoring and data analysis module, an intelligent decision and task planning module, a robot execution module and a feedback and optimization module. The invention provides a rail transit vehicle robot intelligent operation and maintenance system based on digital twinning, and aims to improve the operation and maintenance efficiency and safety of a rail transit vehicle, reduce the operation and maintenance cost and reduce the risk of manual operation through advanced data acquisition, analysis, modeling and robot control technologies.

Description

Technical Field

[0001] The present invention relates to the field of rail transit technology, and in particular to a rail transit vehicle robot intelligent operation and maintenance system based on digital twins. Background Art

[0002] With the rapid development of information technology and automation technology, the rail transit industry is also constantly seeking to improve its operating efficiency and service quality through technological innovation. In the traditional operation and maintenance model, the maintenance of rail transit vehicles mostly relies on manual work, which has the disadvantages of low efficiency, high cost, high safety risks and difficulty in timely detection of potential faults. In order to overcome these problems, in recent years, the application of digital twin technology and robotics technology has received more and more attention and practice.

[0003] Digital Twin is a technology that uses data collection, modeling, virtualization and other technical means to create a corresponding virtual model in the digital world. This virtual model can reflect the state and changes of the entity in real time, providing a new way for the operation, maintenance, analysis and optimization of the entity. In the operation and maintenance of rail transit vehicles, by building a digital twin model, real-time monitoring and analysis of the vehicle's operating status can be achieved, and faults can be discovered in time and preventive measures can be taken, greatly improving the vehicle's operation and maintenance efficiency and safety.

[0004] The wide application of robotics in manufacturing, services, medical and other fields has proven its significant advantages in improving work efficiency and reducing labor intensity. In the operation and maintenance of rail transit vehicles, the introduction of robots to perform maintenance tasks can not only reduce the uncertainty caused by manual operations, but also achieve higher-precision maintenance operations. For example, welding, spraying, assembly and other jobs that require high precision and stability, as well as inspections and other jobs that require long-term high efficiency, are all ideal application scenarios for robotics.

[0005] However, the existing rail transit vehicle operation and maintenance system based on digital twins and robots has some shortcomings: (1) Traditional data collection methods are difficult to achieve high-frequency and multi-dimensional data collection, resulting in insufficient real-time performance of the digital twin model and failure to accurately reflect the actual status of the vehicle. (2) Existing data analysis methods and fault prediction algorithms are not accurate in complex environments and variable working conditions, making it difficult to effectively identify potential faults. (3) In the existing operation and maintenance system, the intelligent decision-making and task planning modules lack flexibility and adaptability, and cannot dynamically adjust maintenance tasks based on real-time data analysis results. (4) Existing robots have problems with positioning errors and unstable execution when performing high-precision tasks, and cannot fully meet the maintenance needs of rail transit vehicles. (5) The existing operation and maintenance system lacks an effective feedback mechanism, resulting in unsatisfactory results in model optimization and decision optimization. Summary of the invention

[0006] The present invention proposes a rail transit vehicle robot intelligent operation and maintenance system based on digital twins, which aims to improve the operation and maintenance efficiency and safety of rail transit vehicles, reduce operation and maintenance costs, and reduce the risks of human operation through advanced data acquisition, analysis, modeling and robot control technology.

[0007] The technical solution adopted by the present invention is: a rail transit vehicle robot intelligent operation and maintenance system based on digital twin, which consists of a digital twin model construction module, a real-time monitoring and data analysis module, an intelligent decision-making and task planning module, a robot execution module, and a feedback and optimization module.

[0008] The digital twin model building module uses sensors and Internet of Things technology to collect real-time operation data of rail transit vehicles, including vehicle status and operating environment, and builds a digital twin model corresponding to the real vehicle through data analysis and modeling;

[0009] The real-time monitoring and data analysis module uses the digital twin model to monitor the vehicle's operating status in real time, analyze whether the vehicle has abnormalities or potential faults, and use machine learning algorithms to predict and diagnose faults;

[0010] The intelligent decision-making and task planning module intelligently decides whether maintenance operations are needed based on the results of real-time monitoring and data analysis, and plans corresponding maintenance tasks, including maintenance content, maintenance time and maintenance location;

[0011] The robot execution module uses the rail transit vehicle robot to perform specific maintenance operations, including welding, spraying, assembly, and inspection, according to the maintenance tasks output by the intelligent decision-making and task planning module;

[0012] The feedback and optimization module feeds back the execution results of the robot execution module to the digital twin model construction module to optimize the accuracy and reliability of the digital twin model. At the same time, the intelligent decision-making and task planning module is optimized according to the execution results to improve the overall performance of the system.

[0013] As a further improvement of the present invention, the digital twin model construction module includes a data acquisition unit, a data preprocessing unit and a model construction unit. The data acquisition unit is used to collect operation data of rail transit vehicles in real time, the data preprocessing unit is used to clean, convert and integrate the collected data, and the model construction unit is used to construct a digital twin model based on the preprocessed data.

[0014] As a further improvement of the present invention, the real-time monitoring and data analysis module includes a data receiving unit, a data analysis unit and a fault prediction unit. The data receiving unit is used to receive the real-time data output by the digital twin model construction module, the data analysis unit is used to perform in-depth mining and analysis on the real-time data, and the fault prediction unit is used to predict and diagnose vehicle faults using a machine learning algorithm.

[0015] As a further improvement of the present invention, the intelligent decision-making and task planning module includes a decision-making unit and a task planning unit. The decision-making unit is used to make an intelligent decision on whether maintenance operation is needed based on the output results of the data analysis unit and the fault prediction unit. The task planning unit is used to plan specific maintenance tasks, including maintenance content, maintenance time and maintenance location.

[0016] As a further improvement of the present invention, the robot execution module includes a robot control unit and a robot execution unit. The robot control unit is used to receive the maintenance tasks output by the task planning unit and control the robot to perform corresponding maintenance operations. The robot execution unit includes a welding robot, a spraying robot, an assembly robot and an inspection robot, which are used to perform specific maintenance tasks.

[0017] As a further improvement of the present invention, the welding robot includes a welding power supply, a welding gun and a multi-degree-of-freedom motion mechanism, the welding power supply is used to provide stable welding current and voltage, the welding gun is used to realize welding operations, and the multi-degree-of-freedom motion mechanism is used to realize the movement of the welding gun on a complex spatial trajectory.

[0018] As a further improvement of the present invention, the spraying robot includes a spray gun, a multi-degree-of-freedom motion mechanism and a sensing system. The spray gun is used to realize the spraying operation, the multi-degree-of-freedom motion mechanism is used to realize the movement of the spray gun on a complex spatial trajectory, and the sensing system is used to monitor the coating thickness and spraying quality during the spraying process in real time.

[0019] As a further improvement of the present invention, the assembly robot includes a clamping device, a multi-degree-of-freedom motion mechanism and a sensing system. The clamping device is used to clamp the workpiece to be assembled, the multi-degree-of-freedom motion mechanism is used to realize the movement of the clamping device on a complex spatial trajectory, and the sensing system is used to monitor the position and posture information during the assembly process in real time to achieve precise assembly.

[0020] As a further improvement of the present invention, the inspection robot includes a mobile platform, a multi-degree-of-freedom rotation mechanism and a camera system. The mobile platform is used to realize the autonomous movement of the robot on the rail transit vehicle, the multi-degree-of-freedom rotation mechanism is used to realize the rotation of the camera system at complex spatial angles, and the camera system is used to monitor the operating status and external environment of the vehicle in real time, providing real-time data support for the intelligent decision-making and task planning modules.

[0021] As a further improvement of the present invention, the feedback and optimization module includes an execution result receiving unit, a model optimization unit and a decision optimization unit. The execution result receiving unit is used to receive the execution result of the robot execution module, the model optimization unit is used to optimize the accuracy and reliability of the digital twin model according to the execution result, and the decision optimization unit is used to optimize the decision strategy and planning scheme of the intelligent decision-making and task planning module according to the execution result.

[0022] The beneficial effects of the present invention are as follows: (1) Improving operation and maintenance efficiency and accuracy: The present invention realizes real-time monitoring and status analysis of rail transit vehicles through digital twin technology, and can promptly detect vehicle abnormalities and potential faults. The robot execution module can efficiently and accurately complete various maintenance tasks, reducing the uncertainty and errors of manual operations, greatly improving operation and maintenance efficiency and accuracy. The intelligent decision-making and task planning module can dynamically adjust maintenance tasks according to real-time data analysis results, further optimizing the operation and maintenance process, and ensuring the timeliness and effectiveness of maintenance work.

[0023] (2) Reduce operation and maintenance costs and safety risks: The present invention uses robots for maintenance operations, which not only reduces labor costs, but also reduces the safety risks brought by human operations. Through fault prediction and diagnosis functions, the system can take preventive measures before a fault occurs, avoiding downtime and maintenance costs caused by the fault, thereby effectively reducing the overall operation and maintenance costs. In addition, the feedback and optimization module can continuously improve the performance of the system, reduce invalid or repeated maintenance, and further save resources and costs.

[0024] (3) Improving system reliability and adaptability: The present invention ensures the accuracy and real-time performance of the digital twin model through the data preprocessing unit and the model building unit, which can more realistically reflect the operating status of the vehicle. The feedback and optimization module continuously optimizes the digital twin model and the intelligent decision-making module according to the robot execution results, thereby improving the reliability and adaptability of the system. In particular, in complex working conditions and changing environments, the system can be quickly adjusted and optimized to ensure efficient and stable operation and maintenance effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a system block diagram of a rail transit vehicle robot intelligent operation and maintenance system based on digital twins of the present invention. DETAILED DESCRIPTION

[0026] 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.

[0027] The present invention provides a rail transit vehicle robot intelligent operation and maintenance system based on digital twin, which is characterized by being composed of a digital twin model construction module, a real-time monitoring and data analysis module, an intelligent decision-making and task planning module, a robot execution module, and a feedback and optimization module.

[0028] The digital twin model construction module in the present invention uses sensors and Internet of Things technology to collect the operation data of rail transit vehicles in real time, including vehicle status and operating environment, and constructs a digital twin model corresponding to the real vehicle through data analysis and modeling. The digital twin model construction module includes a data acquisition unit, a data preprocessing unit and a model construction unit. The data acquisition unit is used to collect the operation data of rail transit vehicles in real time, the data preprocessing unit is used to clean, convert and integrate the collected data, and the model construction unit is used to construct a digital twin model according to the preprocessed data;

[0029] The real-time monitoring and data analysis module in the present invention uses a digital twin model to monitor the running status of the vehicle in real time, analyze whether the vehicle has abnormalities or potential faults, and predict and diagnose faults using a machine learning algorithm. The real-time monitoring and data analysis module includes a data receiving unit, a data analysis unit, and a fault prediction unit. The data receiving unit is used to receive real-time data output by the digital twin model construction module, the data analysis unit is used to perform in-depth mining and analysis of real-time data, and the fault prediction unit is used to predict and diagnose vehicle faults using a machine learning algorithm.

[0030] The intelligent decision-making and task planning module in the present invention makes an intelligent decision whether maintenance operation is needed according to the results of real-time monitoring and data analysis, and plans corresponding maintenance tasks, including maintenance content, maintenance time and maintenance location. The intelligent decision-making and task planning module includes a decision-making unit and a task planning unit. The decision-making unit is used to make an intelligent decision whether maintenance operation is needed according to the output results of the data analysis unit and the fault prediction unit. The task planning unit is used to plan specific maintenance tasks, including maintenance content, maintenance time and maintenance location.

[0031] The robot execution module in the present invention utilizes the rail transit vehicle robot to perform specific maintenance operations, including welding, spraying, assembly, and inspection, according to the maintenance tasks output by the intelligent decision-making and task planning module. The robot execution module includes a robot control unit and a robot execution unit. The robot control unit is used to receive the maintenance tasks output by the task planning unit and control the robot to perform corresponding maintenance operations. The robot execution unit includes a welding robot, a spraying robot, an assembly robot, and an inspection robot, which are used to perform specific maintenance tasks.

[0032] The spraying robot includes a spray gun, a multi-degree-of-freedom motion mechanism and a sensor system. The spray gun is used to realize the spraying operation, the multi-degree-of-freedom motion mechanism is used to realize the movement of the spray gun on a complex spatial trajectory, and the sensor system is used to monitor the coating thickness and spraying quality in real time during the spraying process. The assembly robot includes a clamping device, a multi-degree-of-freedom motion mechanism and a sensor system. The clamping device is used to clamp the workpiece to be assembled, the multi-degree-of-freedom motion mechanism is used to realize the movement of the clamping device on a complex spatial trajectory, and the sensor system is used to monitor the position and posture information during the assembly process in real time to achieve precise assembly. The inspection robot includes a mobile platform, a multi-degree-of-freedom rotation mechanism and a camera system. The mobile platform is used to realize the autonomous movement of the robot on the rail transit vehicle, the multi-degree-of-freedom rotation mechanism is used to realize the rotation of the camera system at complex spatial angles, and the camera system is used to monitor the vehicle's operating status and external environment in real time, providing real-time data support for the intelligent decision-making and task planning modules. The welding robot includes a welding power supply, a welding gun and a multi-degree-of-freedom motion mechanism. The welding power supply is used to provide stable welding current and voltage, the welding gun is used to realize welding operations, and the multi-degree-of-freedom motion mechanism is used to realize the movement of the welding gun on a complex spatial trajectory.

[0033] In the present invention, the feedback and optimization module feeds back the execution results of the robot execution module to the digital twin model construction module, which is used to optimize the accuracy and reliability of the digital twin model. At the same time, the intelligent decision-making and task planning module is optimized according to the execution results to improve the overall performance of the system. The feedback and optimization module includes an execution result receiving unit, a model optimization unit and a decision optimization unit. The execution result receiving unit is used to receive the execution results of the robot execution module, the model optimization unit is used to optimize the accuracy and reliability of the digital twin model according to the execution results, and the decision optimization unit is used to optimize the decision strategy and planning scheme of the intelligent decision-making and task planning module according to the execution results.

[0034] Example:

[0035] The operator of a certain city's rail transit system is faced with the problem of a large number of vehicles, high maintenance costs and low efficiency. In order to improve the vehicle operation and maintenance efficiency and service quality, the company decided to adopt this invention - the rail transit vehicle robot intelligent operation and maintenance system based on digital twins to reduce the risk of human operation, improve the accuracy of fault prediction, and optimize the maintenance process.

[0036] System deployment and configuration:

[0037] 1. Digital twin model construction module

[0038] Data acquisition unit: Various sensors, such as vibration sensors, temperature sensors, humidity sensors, etc., are installed on the key components of each rail transit vehicle to monitor the working status of the vehicle in real time. At the same time, environmental monitoring sensors are arranged along the track to collect environmental information.

[0039] Data preprocessing unit: The data preprocessing unit is located in the local edge computing node, and cleans, converts and integrates the large amount of collected data to remove noise and outliers to ensure the quality of the data.

[0040] Model building unit: The model building unit is deployed in the cloud and uses preprocessed data to build a high-precision digital twin model. The model can reflect the vehicle's operating status and environmental changes in real time.

[0041] (II) Real-time monitoring and data analysis module

[0042] Data receiving unit: The data receiving unit receives real-time data from the digital twin model building module and transmits it to the data analysis unit and the fault prediction unit.

[0043] Data Analysis Unit: Uses big data analysis technology to conduct in-depth mining of vehicle operation data to identify potential problems and abnormal patterns.

[0044] Fault prediction unit: Uses machine learning algorithms, especially deep learning technology, to predict and diagnose vehicle faults and provide accurate fault warning information.

[0045] (III) Intelligent decision-making and task planning module:

[0046] Decision-making unit: Based on the output results of the data analysis unit and the fault prediction unit, it intelligently decides whether maintenance operations are required. If a potential fault is detected, the decision-making unit generates a maintenance instruction.

[0047] Task planning unit: According to the maintenance instructions, plan specific maintenance tasks, including maintenance content, maintenance time and maintenance location. The task planning unit will consider the current status of the vehicle, the availability of maintenance resources and the priority of the maintenance task to generate the optimal maintenance plan.

[0048] (IV) Robot execution module

[0049] Robot control unit: Receives maintenance tasks generated by the task planning unit and controls the robot to perform corresponding operations through wireless communication. The robot control unit can dynamically adjust the control strategy according to the complexity of the task and environmental changes.

[0050] Robot execution unit: including welding robots, spraying robots, assembly robots and inspection robots.

[0051] (1) Welding robot: Utilizes a multi-degree-of-freedom motion mechanism to perform high-precision welding operations at the vehicle's welding points. The welding power supply provides stable current and voltage to ensure welding quality. (2) Spraying robot: Through precise control of the spray gun, uniform spraying is performed on the vehicle surface. The multi-degree-of-freedom motion mechanism and sensor system ensure real-time monitoring of the spraying thickness and quality. (3) Assembly robot: Uses a clamping device and a multi-degree-of-freedom motion mechanism to complete high-precision assembly tasks in a small space. The sensor system monitors the position and posture information during the assembly process in real time to ensure assembly accuracy. (4) Inspection robot: Moves autonomously on the vehicle through a mobile platform. The multi-degree-of-freedom rotation mechanism and camera system monitor the vehicle's operating status and external environment in real time to provide support for fault diagnosis.

[0052] (V) Feedback and Optimization Module

[0053] Execution result receiving unit: collects the execution results of the robot execution module, including task completion status, operation time, operation quality and other information.

[0054] Model optimization unit: Optimize the accuracy and reliability of the digital twin model based on the execution results. For example, if the coating thickness of a certain spraying task does not meet the requirements, the model optimization unit will adjust the spraying parameters in the model.

[0055] Decision optimization unit: Optimizes the decision strategies and planning schemes of the intelligent decision and task planning modules based on the execution results. For example, if a certain inspection task finds more faults than expected, the decision optimization unit will adjust the frequency and path of the inspection task.

[0056] System operation process:

[0057] (I) Data collection and preprocessing: Sensors on rail transit vehicles collect vehicle operation data in real time, including vibration, temperature, humidity, etc. Local edge computing nodes clean, convert and integrate the collected data to ensure data quality. The preprocessed data is transmitted to the cloud for building a digital twin model.

[0058] (II) Construction of digital twin model: The cloud-based model construction unit updates and optimizes the digital twin model in real time based on the preprocessed data. The digital twin model can reflect the real-time status and operating environment of the vehicle.

[0059] (III) Real-time monitoring and data analysis: The data receiving unit receives the real-time data of the digital twin model and transmits it to the data analysis unit and the fault prediction unit. The data analysis unit conducts in-depth data mining to identify potential abnormal patterns. The fault prediction unit uses machine learning algorithms to predict possible faults and perform diagnosis.

[0060] (IV) Intelligent decision-making and task planning: The decision-making unit makes intelligent decisions on whether maintenance operations are required based on the results of data analysis and fault prediction. The task planning unit generates specific maintenance tasks, including maintenance content, maintenance time and maintenance location.

[0061] (V) Robot execution: The robot control unit receives the maintenance tasks output by the task planning unit and controls the corresponding robots to perform operations. Various robots complete maintenance tasks such as welding, spraying, assembly and inspection according to task requirements.

[0062] (VI) Feedback and optimization: The execution result receiving unit collects the execution results of the robot execution module. The model optimization unit optimizes the digital twin model according to the execution results to improve the accuracy and reliability of the model. The decision optimization unit optimizes the decision strategy and planning scheme of the maintenance task according to the execution results to improve the overall performance of the system.

[0063] Through the implementation of the above steps, the specific effects of the city are as follows: (1) Improved operation and maintenance efficiency: Through real-time monitoring and fault prediction of digital twin technology, the system can take preventive measures in time before a fault occurs, greatly reducing the downtime caused by the fault. The robot execution module can efficiently and accurately complete various maintenance tasks, reducing the time and error of manual operation. (2) Reduced operation and maintenance costs: Robots replace a large number of manual operations, reducing labor costs. Fault prediction and diagnosis functions reduce invalid or repeated maintenance and save maintenance costs. Continuous optimization of feedback and optimization modules further improves the economy of the system. (3) Improved operation and maintenance safety: Robots perform high-risk operations, reducing the safety risks brought by human operations. Real-time monitoring and fault prediction functions improve the safety of the system and ensure the normal operation of the vehicle. (4) Enhanced system reliability and adaptability: The data preprocessing unit and model optimization unit ensure the accuracy and real-time performance of the digital twin model. The decision optimization unit can dynamically adjust the maintenance strategy and planning scheme according to the execution results, improving the reliability and adaptability of the system.

[0064] In summary, the rail transit vehicle robot intelligent operation and maintenance system based on digital twins of the present invention has achieved remarkable results in practical applications, which not only improves the operation and maintenance efficiency and quality of rail transit vehicles, but also reduces the operation and maintenance costs and safety risks. The system realizes real-time monitoring and accurate prediction of vehicle operation status through digital twin technology, providing strong data support for intelligent decision-making. The efficient execution of the robot execution module further improves the completion efficiency and quality of operation and maintenance tasks. At the same time, the continuous optimization of the feedback and optimization module ensures the stability and reliability of the system, providing a strong guarantee for the safe operation of rail transit.

[0065] 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 rail transit vehicle robot intelligent operation and maintenance system based on digital twin, characterized in that: It consists of a digital twin model construction module, a real-time monitoring and data analysis module, an intelligent decision-making and task planning module, a robot execution module, and a feedback and optimization module. The digital twin model building module uses sensors and Internet of Things technology to collect real-time operation data of rail transit vehicles, including vehicle status and operating environment, and builds a digital twin model corresponding to the real vehicle through data analysis and modeling; The real-time monitoring and data analysis module uses the digital twin model to monitor the vehicle's operating status in real time, analyze whether the vehicle has abnormalities or potential faults, and use machine learning algorithms to predict and diagnose faults; The intelligent decision-making and task planning module intelligently decides whether maintenance operations are needed based on the results of real-time monitoring and data analysis, and plans corresponding maintenance tasks, including maintenance content, maintenance time and maintenance location; The robot execution module uses the rail transit vehicle robot to perform specific maintenance operations, including welding, spraying, assembly, and inspection, according to the maintenance tasks output by the intelligent decision-making and task planning module; The feedback and optimization module feeds back the execution results of the robot execution module to the digital twin model construction module to optimize the accuracy and reliability of the digital twin model. At the same time, the intelligent decision-making and task planning module is optimized according to the execution results to improve the overall performance of the system.

2. According to claim 1, a rail transit vehicle robot intelligent operation and maintenance system based on digital twins is characterized in that: The digital twin model construction module includes a data acquisition unit, a data preprocessing unit and a model construction unit. The data acquisition unit is used to collect the operation data of rail transit vehicles in real time. The data preprocessing unit is used to clean, convert and integrate the collected data. The model construction unit is used to build a digital twin model based on the preprocessed data.

3. According to claim 1, a rail transit vehicle robot intelligent operation and maintenance system based on digital twins is characterized in that: The real-time monitoring and data analysis module includes a data receiving unit, a data analysis unit and a fault prediction unit. The data receiving unit is used to receive the real-time data output by the digital twin model construction module. The data analysis unit is used to perform in-depth mining and analysis on the real-time data. The fault prediction unit is used to predict and diagnose vehicle faults using a machine learning algorithm.

4. According to claim 1, a rail transit vehicle robot intelligent operation and maintenance system based on digital twins is characterized in that: The intelligent decision-making and task planning module includes a decision-making unit and a task planning unit. The decision-making unit is used to make an intelligent decision on whether maintenance operation is required based on the output results of the data analysis unit and the fault prediction unit. The task planning unit is used to plan specific maintenance tasks, including maintenance content, maintenance time and maintenance location.

5. According to claim 1, a rail transit vehicle robot intelligent operation and maintenance system based on digital twins is characterized in that: The robot execution module includes a robot control unit and a robot execution unit. The robot control unit is used to receive the maintenance tasks output by the task planning unit and control the robot to perform corresponding maintenance operations. The robot execution unit includes a welding robot, a spraying robot, an assembly robot and an inspection robot, which are used to perform specific maintenance tasks.

6. According to claim 5, a rail transit vehicle robot intelligent operation and maintenance system based on digital twins is characterized in that: The welding robot comprises a welding power source, a welding gun and a multi-degree-of-freedom motion mechanism, wherein the welding power source is used to provide a stable welding current and voltage, the welding gun is used to realize the welding operation, and the multi-degree-of-freedom motion mechanism is used to realize the movement of the welding gun on a complex spatial trajectory.

7. The rail transit vehicle robot intelligent operation and maintenance system based on digital twin according to claim 5 is characterized in that: The spraying robot comprises a spray gun, a multi-degree-of-freedom motion mechanism and a sensor system. The spray gun is used to realize the spraying operation, the multi-degree-of-freedom motion mechanism is used to realize the movement of the spray gun on a complex spatial trajectory, and the sensor system is used to monitor the coating thickness and spraying quality in real time during the spraying process.

8. The rail transit vehicle robot intelligent operation and maintenance system based on digital twin according to claim 5 is characterized in that: The assembly robot includes a clamping device, a multi-degree-of-freedom motion mechanism and a sensor system. The clamping device is used to clamp the workpiece to be assembled, the multi-degree-of-freedom motion mechanism is used to realize the movement of the clamping device on a complex spatial trajectory, and the sensor system is used to monitor the position and posture information during the assembly process in real time to achieve precise assembly.

9. The rail transit vehicle robot intelligent operation and maintenance system based on digital twin according to claim 5 is characterized in that: The inspection robot includes a mobile platform, a multi-degree-of-freedom rotation mechanism and a camera system. The mobile platform is used to realize the autonomous movement of the robot on the rail transit vehicle. The multi-degree-of-freedom rotation mechanism is used to realize the rotation of the camera system at complex spatial angles. The camera system is used to monitor the vehicle's operating status and external environment in real time, and provide real-time data support for intelligent decision-making and task planning modules.

10. The rail transit vehicle robot intelligent operation and maintenance system based on digital twin according to claim 1, characterized in that: The feedback and optimization module includes an execution result receiving unit, a model optimization unit and a decision optimization unit. The execution result receiving unit is used to receive the execution result of the robot execution module, the model optimization unit is used to optimize the accuracy and reliability of the digital twin model according to the execution result, and the decision optimization unit is used to optimize the decision strategy and planning scheme of the intelligent decision-making and task planning module according to the execution result.

Images