Railway vehicle-mounted ATP intelligent operation and maintenance system based on multi-source data fusion

Abstract

The invention discloses a railway vehicle-mounted ATP intelligent operation and maintenance system based on multi-source data fusion, and particularly relates to the technical field of high-speed railway signal system operation and maintenance, and the system comprises a data collection layer which is used for collecting data related to a railway vehicle-mounted ATP from a plurality of different data sources in real time; the data transmission layer adopts a reliable communication protocol to ensure that the data acquired from the data acquisition layer can be stably transmitted to the subsequent processing layer in real time; the data processing layer is used for cleaning, converting and fusing the transmitted data so as to improve the consistency and availability of the data; the intelligent analysis layer is used for carrying out intelligent analysis on the fused data; and the application layer provides a visual interface for operation and maintenance personnel and displays the analysis result and the operation and maintenance suggestions obtained by the intelligent analysis layer. According to the railway vehicle-mounted ATP intelligent operation and maintenance system based on multi-source data fusion, the ATP operation and maintenance efficiency can be remarkably improved, the operation and maintenance cost is reduced, and safe and smooth railway transportation is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of operation and maintenance of high-speed railway signal systems, and particularly relates to a railway vehicle-mounted ATP intelligent operation and maintenance system based on multi-source data fusion. Background Art

[0002] In the modern railway transportation system, the Automatic Train Protection (ATP) system, as a core technical equipment for ensuring train operation safety, plays a crucial role. With the rapid development of railway transportation towards high speed, heavy haul, and high density, higher requirements are put forward for the reliability, stability, and safety of the ATP system. The ATP system monitors the train operation status in real time, such as key information like speed and position, and compares it with the preset safety standards. Once an abnormality is detected, it quickly takes measures such as braking, thus effectively avoiding serious accidents such as train overspeed and rear-end collisions, laying a solid foundation for the safe and stable operation of railway transportation.

[0003] Traditional railway ATP operation and maintenance mainly rely on manual inspections and simple data analysis, with low efficiency and difficulty in comprehensively and timely discovering potential fault hazards. With the continuous advancement of railway informatization construction, a large amount of data related to the ATP system has been generated and collected, including equipment operation status data, fault alarm data, train operation trajectory data, etc.; these multi-source data contain rich equipment health status and operation behavior information, but due to diverse data sources, different formats, and complex structures, how to effectively fuse and analyze them has become a key issue in improving ATP operation and maintenance efficiency and safety.

[0004] In terms of data acquisition and transmission, China has established a relatively complete railway information acquisition network that can obtain various types of train operation data in real time. However, there are still some deficiencies and gaps in current domestic and foreign research: on the one hand, in multi-source data fusion, the data formats, semantics, and time scales between different data sources vary greatly, resulting in high data fusion difficulty. Existing fusion algorithms still have certain limitations in processing complex data and are difficult to fully explore the potential connections between data; on the other hand, in intelligent analysis technology, although machine learning and deep learning algorithms have achieved certain application results, the interpretability of the models is poor and it is difficult to provide intuitive guidance in actual operation and maintenance decisions; in addition, for the special application scenarios of railway vehicle-mounted ATP systems, such as data processing and analysis in environments with high speed operation and strong electromagnetic interference, existing research is not deep enough and more effective solutions need to be further explored. Therefore, a railway vehicle-mounted ATP intelligent operation and maintenance system based on multi-source data fusion is needed. Summary of the Invention

[0005] The main object of the present invention is to provide a railway vehicle-mounted ATP intelligent operation and maintenance system based on multi-source data fusion, which can effectively solve the problems of high difficulty in data fusion and poor interpretability of models.

[0006] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0007] A railway vehicle-mounted ATP intelligent operation and maintenance system based on multi-source data fusion, comprising:

[0008] A data acquisition layer for real-time collecting data related to railway vehicle-mounted ATP from multiple different data sources, and the data sources include but are not limited to equipment operation status data, fault alarm data, train operation track data, speed sensor data, position sensor data, and communication data;

[0009] A data transmission layer that uses a reliable communication protocol to ensure that the data obtained from the data acquisition layer can be transmitted to the subsequent processing layer in real time and stably;

[0010] A data processing layer for cleaning, transforming, and fusing the transmitted data to improve the consistency and availability of the data; wherein, the data fusion processing includes data layer fusion, feature layer fusion, and decision layer fusion, and corresponding fusion algorithms are adopted according to the data characteristics and requirements of different levels, including Kalman filtering, principal component analysis PCA, and D-S evidence theory;

[0011] An intelligent analysis layer that uses advanced technologies such as big data analysis, machine learning, and artificial intelligence to perform intelligent analysis on the fused data, including fault diagnosis, predictive maintenance, and equipment status monitoring, to provide operation and maintenance decision support;

[0012] An application layer that provides an intuitive interface for operation and maintenance personnel to display the analysis results and operation and maintenance suggestions obtained by the intelligent analysis layer, including but not limited to information on equipment fault warning, maintenance plan optimization, and operation and maintenance efficiency improvement.

[0013] Preferably, the data acquisition layer collects the real-time speed and position data of the train, as well as the operation status data of the ATP equipment, with high precision and high frequency through devices such as vehicle-mounted sensors, balises, and satellite positioning systems.

[0014] Preferably, the data processing layer uses a distributed file system HDFS and a columnar storage database HBase to store and process a large amount of ATP operation and maintenance data to ensure the security and reliability of the data.

[0015] Preferably, the intelligent analysis layer constructs a variety of intelligent analysis models, including but not limited to fault diagnosis models and predictive maintenance models, for deeply mining and analyzing the fused data to improve the accuracy of fault diagnosis and operation and maintenance efficiency.

[0016] Preferably, the data acquisition layer further includes an environmental monitoring data acquisition module for collecting and monitoring environmental factors and determining the impact of environmental factors on the performance of the ATP system.

[0017] Preferably, the intelligent analysis layer further includes a fault warning model for predicting possible faults of equipment based on real-time data and sending warning information to operation and maintenance personnel. The intelligent analysis layer of the system adopts deep learning technology to improve the analysis ability for complex problems and can continuously optimize the prediction model according to historical data. The intelligent analysis layer also includes a trend analysis model for analyzing the change trends of historical data and real-time data to help operation and maintenance personnel with long-term planning and decision-making.

[0018] Preferably, the application layer includes a data visualization function to display various key data indicators, such as equipment operation status, fault alarm information, and operation and maintenance efficiency, in a graphical interface, facilitating analysis and decision-making by operation and maintenance personnel.

[0019] Preferably, the system supports interface docking with other railway operation and maintenance management systems, enabling data sharing and collaborative operations to improve the overall operation and maintenance efficiency of the railway system.

[0020] Preferably, the data transmission layer adopts a communication technology based on the 5G network to ensure the high efficiency and low latency of data transmission.

[0021] Compared with the prior art, the present invention has the following beneficial effects:

[0022] 1. The operation and maintenance efficiency of ATP can be significantly improved through this system, realizing the transformation from passive operation and maintenance to active operation and maintenance and reducing operation and maintenance costs.

[0023] 2. The safety and reliability of the ATP system are enhanced through this system, potential faults are discovered and processed in a timely manner, accident risks are reduced, and the safe and unobstructed railway transportation is guaranteed.

[0024] 3. The intelligent upgrade of railway operation and maintenance management is promoted through this system, the overall service level of railway transportation is improved, and the requirements for future railway development are met. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 is the overall flowchart of the present invention; DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] In order to make the technical means, creative features, achieved purposes, and functions of the present invention easy to understand, the present invention will be further described below in conjunction with specific embodiments.

[0027] Such as Figure 1As shown in the figure, a railway vehicle-mounted ATP intelligent operation and maintenance system based on multi-source data fusion includes:

[0028] A data acquisition layer for real-time collecting data related to railway vehicle-mounted ATP from multiple different data sources, where the data sources include but are not limited to equipment operation status data, fault alarm data, train operation trajectory data, speed sensor data, position sensor data, and communication data;

[0029] A data transmission layer that uses a reliable communication protocol to ensure that the data obtained from the data acquisition layer can be transmitted to the subsequent processing layer in real time and stably;

[0030] A data processing layer for cleaning, transforming, and fusing the transmitted data to improve data consistency and availability; among them, data fusion processing includes data layer fusion, feature layer fusion, and decision layer fusion, and corresponding fusion algorithms are adopted according to the data characteristics and requirements at different levels, including Kalman filtering, principal component analysis PCA, and D-S evidence theory;

[0031] An intelligent analysis layer that uses advanced technologies such as big data analysis, machine learning, and artificial intelligence to perform intelligent analysis on the fused data, including fault diagnosis, predictive maintenance, and equipment status monitoring, to provide operation and maintenance decision-making support;

[0032] An application layer that provides an intuitive interface for operation and maintenance personnel to display the analysis results and operation and maintenance suggestions obtained by the intelligent analysis layer, including but not limited to information on equipment fault early warning, maintenance plan optimization, and operation and maintenance efficiency improvement.

[0033] The railway vehicle-mounted ATP system, as the core safety equipment of the train operation control system, mainly consists of multiple subsystems such as an on-vehicle host, a wireless transmission unit, a transponder information receiving unit, a track circuit information reader (TCR), a speed measurement and distance measurement unit, a man-machine interface unit (DMI), a train interface unit (TIU), and a judicial record unit (JRU). These subsystems cooperate with each other to jointly ensure the safe operation of the train;

[0034] The multi-source data fusion technology can integrate various data from different sensors and different systems, eliminate redundancy and contradictions between data, and thus obtain more comprehensive and accurate information. Applying it to the field of railway ATP operation and maintenance can realize an all-round and in-depth perception of the ATP system status. The intelligent analysis technology, with the help of advanced algorithms such as big data analysis, machine learning, and artificial intelligence, can mine potential laws and characteristics from a large amount of data, realize early warning, accurate diagnosis, and intelligent prediction of ATP equipment faults, and provide a scientific basis for operation and maintenance decision-making;

[0035] Foreign data fusion technology consists of various fusion algorithms and frameworks. For example, the fusion method based on Bayesian network can comprehensively consider the uncertainties of different data sources and achieve effective information fusion through probability reasoning. The distributed data fusion architecture utilizes cloud computing and edge computing technologies to distribute data processing tasks to each node, improving the efficiency and real-time performance of data processing. In intelligent analysis technology, machine learning and deep learning algorithms are widely used. For example, neural networks are used for equipment fault diagnosis. Through learning a large amount of historical fault data, the model can accurately identify the types and causes of faults. Time series analysis algorithms are used to predict the changing trends of equipment performance, providing a basis for preventive maintenance.

[0036] Domestic data fusion technology is a multi-modal data fusion algorithm based on deep learning, which can simultaneously process various types of data such as images, texts, and numerical values, improving the accuracy of fault diagnosis. The fault prediction model optimized by genetic algorithm improves the accuracy and reliability of prediction through optimizing model parameters.

[0037] The overall architecture of the multi-source data fusion and intelligent analysis system for railway vehicle-mounted ATP operation and maintenance includes a data acquisition layer, a data transmission layer, a data processing layer, a data analysis layer, and an application layer. In the data acquisition layer, efficient acquisition and preprocessing of multi-source data are realized. The data transmission layer adopts a reliable communication protocol to ensure real-time data transmission. The data processing layer completes data cleaning, transformation, and fusion. The data analysis layer uses intelligent analysis technology for fault diagnosis and prediction. The application layer provides an intuitive interface for operation and maintenance personnel to display analysis results and operation and maintenance suggestions. Based on the cloud computing platform, the deployment and operation of the system are realized, improving the scalability and performance of the system to meet the needs of future railway development. The system also includes a data quality assessment and improvement module, which is used to assess the quality of the collected data and perform preprocessing and improvement on the problems existing in the data to improve the availability and consistency of the data. The system has a multi-user permission management function, and operation and maintenance personnel can access different data and functions according to their permission levels to improve the security and manageability of the system. The system supports interface docking with other railway operation and maintenance management systems, enabling data sharing and collaborative operation, and improving the overall operation and maintenance efficiency of the railway system.

[0038] The data acquisition layer collects the real-time speed and position data of the train and the operation status data of ATP equipment with high precision and high frequency through devices such as on-vehicle sensors, transponders, and satellite positioning systems. The data acquisition layer also includes an environmental monitoring data acquisition module, which is used to collect and monitor environmental factors to determine the impact of environmental factors on the performance of the ATP system.

[0039] The data processing layer adopts the distributed file system HDFS and the columnar storage database HBase to store and process massive ATP operation and maintenance data, ensuring the security and reliability of the data.

[0040] The distributed file system HDFS (Hadoop Distributed File System) is one of the core components of Hadoop. As the bottom-layer distributed storage service, it aims to solve the big data storage problem and provides the required scalability for storing and processing ultra-large-scale data. By using multiple computers to store files and providing a unified access interface, HDFS enables users to use the distributed file system just like accessing an ordinary file system. The columnar storage database HBase is a sub-project of the Apache Hadoop project, with core features such as high reliability, high performance, column-oriented, and scalability. It can efficiently process large-scale data sets and meet the data storage and access requirements of various application scenarios.

[0041] The intelligent analysis layer constructs various intelligent analysis models, including but not limited to the fault diagnosis model and the predictive maintenance model, to deeply mine and analyze the fused data, improving the accuracy of fault diagnosis and the operation and maintenance efficiency.

[0042] The intelligent analysis layer further includes a fault warning model to predict possible faults of the device based on real-time data and send warning messages to the operation and maintenance personnel. The intelligent analysis layer of the system adopts deep learning technology to improve the analysis ability for complex problems and can continuously optimize the prediction model according to historical data. The intelligent analysis layer also includes a trend analysis model to analyze the change trends of historical data and real-time data, helping the operation and maintenance personnel with long-term planning and decision-making.

[0043] The application layer includes a data visualization function to display various key data indicators, such as the device operation status, fault alarm information, and operation and maintenance efficiency, in a graphical interface, facilitating the operation and maintenance personnel to make analysis and decisions.

[0044] The data transmission layer adopts the communication technology based on the 5G network to ensure the high efficiency and low latency of data transmission.

[0045] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification only illustrates the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A railway vehicle-mounted ATP intelligent operation and maintenance system based on multi-source data fusion, characterized in that Including: A data acquisition layer for real-time collecting data related to on-railway vehicle ATP from multiple different data sources, where the data sources include but are not limited to equipment operation status data, fault alarm data, train operation trajectory data, speed sensor data, position sensor data, and communication data; A data transmission layer that uses a reliable communication protocol to ensure that the data obtained from the data acquisition layer can be transmitted to the subsequent processing layer in real time and stably; A data processing layer for cleaning, transforming, and fusing the transmitted data to improve data consistency and availability; among them, data fusion processing includes data layer fusion, feature layer fusion, and decision layer fusion, and corresponding fusion algorithms are adopted according to the data characteristics and requirements at different levels, including Kalman filtering, principal component analysis PCA, and D-S evidence theory; An intelligent analysis layer that uses advanced technologies such as big data analysis, machine learning, and artificial intelligence to perform intelligent analysis on the fused data, including fault diagnosis, predictive maintenance, and equipment status monitoring, to provide operation and maintenance decision support; An application layer that provides an intuitive interface for operation and maintenance personnel to display the analysis results and operation and maintenance suggestions obtained by the intelligent analysis layer, including but not limited to information on equipment fault warning, maintenance plan optimization, and operation and maintenance efficiency improvement.

2. The railway vehicle-mounted ATP intelligent operation and maintenance system based on multi-source data fusion according to claim 1, wherein: The data acquisition layer collects the real-time speed and position data of the train, as well as the operation status data of the ATP equipment, with high precision and high frequency through devices such as on-vehicle sensors, transponders, and satellite positioning systems.

3. The intelligent operation and maintenance system of railway vehicle-mounted ATP based on multi-source data fusion according to claim 1, characterized in that: The data processing layer adopts a distributed file system HDFS and a columnar storage database HBase for storing and processing massive amounts of ATP operation and maintenance data to ensure data security and reliability.

4. An intelligent operation and maintenance system for railway vehicle-borne ATP based on multi-source data fusion according to claim 1, characterized in that: The intelligent analysis layer constructs various intelligent analysis models, including but not limited to fault diagnosis models and predictive maintenance models, for deeply mining and analyzing the fused data to improve the accuracy of fault diagnosis and operation and maintenance efficiency.

5. The intelligent operation and maintenance system for railway vehicle-mounted ATP based on multi-source data fusion according to claim 1, characterized in that: The data acquisition layer further includes an environmental monitoring data acquisition module for collecting and monitoring environmental factors to determine the impact of environmental factors on the performance of the ATP system.

6. The railway vehicle-mounted ATP intelligent operation and maintenance system based on multi-source data fusion according to claim 1, wherein: The intelligent analysis layer further includes a fault warning model for predicting possible faults of equipment based on real-time data and sending warning information to operation and maintenance personnel. The intelligent analysis layer of the system adopts deep learning technology to improve the analysis ability for complex problems and can continuously optimize the prediction model according to historical data. The intelligent analysis layer also includes a trend analysis model for analyzing the change trends of historical data and real-time data to help operation and maintenance personnel make long-term plans and decisions.

7. The intelligent operation and maintenance system for railway vehicle-mounted ATP based on multi-source data fusion according to claim 1, characterized in that: The application layer includes a data visualization function to display various key data indicators, such as equipment operation status, fault alarm information, and operation and maintenance efficiency, in a graphical interface to facilitate operation and maintenance personnel to make analysis and decisions.

8. The railway vehicle-mounted ATP intelligent operation and maintenance system based on multi-source data fusion according to claim 1, characterized in that: The data transmission layer adopts a communication technology based on the 5G network to ensure the high efficiency and low latency of data transmission.

Images