Railway signal operation and maintenance management system based on large model and multi-source data fusion

Abstract

The invention discloses a railway signal operation and maintenance management system based on large model and multi-source data fusion, and particularly relates to the technical field of railway signal operation and maintenance, and the system comprises a large model processing module which can process data based on a deep learning algorithm; the multi-source data fusion module is used for fusing data from different sources; the operation and maintenance management decision module is used for outputting according to the large model processing module and the multi-source data fusion module; and the application module provides a visual interface for operation and maintenance personnel and improves the operation and maintenance efficiency and safety. Through real-time data analysis and prediction, potential faults can be found and processed in time, the operation and maintenance efficiency is improved, scientific decision support is provided for operation and maintenance personnel based on a deep learning algorithm and a multi-source data fusion technology, the equipment operation state and fault early warning information are visually displayed through a visual interface, and the operation and maintenance efficiency is improved. Operation and maintenance personnel are helped to quickly respond and process faults, and the safety is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of railway signal operation and maintenance, and particularly to a railway signal operation and maintenance management system based on the integration of large models and multi-source data. Background Art

[0002] The railway signal system is a key component to ensure the safe and efficient operation of railway transportation. However, with the continuous expansion of the railway network and the continuous increase in train operation speed, the operation and maintenance management of the railway signal system faces unprecedented challenges. Traditional operation and maintenance management methods often rely on manual inspections and experience judgments, relying 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 relevant data 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, it is impossible to effectively fuse and analyze them, resulting in low operation and maintenance efficiency. Therefore, it is particularly important to develop a railway signal operation and maintenance management system based on the integration of large models and multi-source data. Summary of the Invention

[0003] The main object of the present invention is to provide a railway signal operation and maintenance management system based on the integration of large models and multi-source data, which can effectively solve the problem of low operation and maintenance efficiency caused by the inability to effectively fuse and analyze the data.

[0004] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0005] A railway signal operation and maintenance management system based on the integration of large models and multi-source data, comprising:

[0006] A large model processing module for receiving and analyzing historical data, real-time operation data, and external environment data of the railway signal system. The large model processing module can process the data based on deep learning algorithms to predict the operation status and potential faults of the railway signal system;

[0007] A multi-source data fusion module for fusing data from different sources, including but not limited to sensor data, video surveillance data, weather data, and train operation plan data of the railway signal system. The multi-source data fusion module can extract and integrate key information from each data source to form a unified operation and maintenance management data set;

[0008] An operation and maintenance management decision-making module for generating operation and maintenance management decisions for the railway signal system according to the outputs of the large model processing module and the multi-source data fusion module. The decisions include but are not limited to fault early warning, maintenance plan formulation, and emergency response strategy formulation;

[0009] An application module provides a visual interface for operation and maintenance personnel, intuitively displaying key information such as the operating status of various devices, fault warnings, equipment health status, and operation and maintenance efficiency, helping operation and maintenance personnel quickly make judgments and decisions, and improving operation and maintenance efficiency and safety.

[0010] Preferably, the large model processing module includes a data preprocessing sub-module and a feature extraction sub-module. The data preprocessing sub-module is used to clean, format convert, and normalize the received raw data to improve data quality and analysis efficiency. The feature extraction sub-module is used to extract features related to the operating status of the railway signal system from the preprocessed data. The features include but are not limited to signal response time, failure rate, and external environmental factors.

[0011] Preferably, the multi-source data fusion module includes a data matching sub-module and a data fusion algorithm sub-module.

[0012] Preferably, the data matching sub-module is used to synchronize the time and match the space of data from different sources to ensure the consistency and accuracy of the data. The data fusion algorithm sub-module uses the Kalman filter and D-S evidence theory fusion algorithm to fuse the matched data to extract key information useful for operation and maintenance management decisions.

[0013] Preferably, the operation and maintenance management decision module includes a fault warning sub-module, a maintenance plan formulation sub-module, and an emergency response strategy formulation sub-module.

[0014] Preferably, the fault warning sub-module is used to judge whether there are potential faults in the railway signal system according to the output of the large model processing module and generate fault warning information. The maintenance plan formulation sub-module is used to formulate a maintenance plan according to the fault warning information and the system's historical maintenance records. The maintenance plan includes but is not limited to maintenance time, maintenance content, and maintenance personnel arrangement. The emergency response strategy formulation sub-module is used to quickly generate an emergency response strategy when a fault occurs in the railway signal system to minimize the impact of the fault on railway transportation.

[0015] Preferably, the application module includes a user switching unit, which is used to display the results of operation and maintenance management decisions, receive user input, and provide system configuration and parameter adjustment functions.

[0016] Compared with the prior art, the present invention has the following beneficial effects:

[0017] 1. Through real-time data analysis and prediction, the present invention can timely discover and handle potential faults, reduce the impact of system faults on railway transportation, and improve operation and maintenance efficiency.

[0018] 2. The present invention provides scientific decision-making support for operation and maintenance personnel through deep learning algorithms and multi-source data fusion technology, enhancing the scientific nature of decision-making.

[0019] 3. The present invention visually displays the operation status of equipment and fault warning information through a visualization interface, helping operation and maintenance personnel quickly respond to and handle faults, ensuring the safety of railway transportation, and enhancing safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is the overall flowchart of the present invention; DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] To make the technical means, creative features, achieved purposes, and effects of the present invention easy to understand, the present invention will be further described below in conjunction with specific embodiments.

[0022] As Figure 1 shown, a railway signal operation and maintenance management system based on a large model and multi-source data fusion includes:

[0023] A large model processing module for receiving and analyzing historical data, real-time operation data, and external environment data of the railway signal system. The large model processing module can process the data based on deep learning algorithms to predict the operation status and potential faults of the railway signal system;

[0024] A multi-source data fusion module for fusing and processing data from different sources. The data includes but is not limited to sensor data, video surveillance data, weather data, and train operation plan data of the railway signal system. The multi-source data fusion module can extract and integrate key information from each data source to form a unified operation and maintenance management data set;

[0025] An operation and maintenance management decision-making module for generating operation and maintenance management decisions for the railway signal system based on the outputs of the large model processing module and the multi-source data fusion module. The decisions include but are not limited to fault warning, maintenance plan formulation, and emergency response strategy formulation;

[0026] An application module provides a visualization interface for operation and maintenance personnel, visually displaying key information such as the operation status of various devices, fault warnings, equipment health status, and operation and maintenance efficiency, helping operation and maintenance personnel quickly make judgments and decisions, and improving operation and maintenance efficiency and safety.

[0027] The large model processing module includes a data preprocessing sub-module and a feature extraction sub-module. The data preprocessing sub-module is used to clean, format convert, and normalize the received raw data to improve data quality and analysis efficiency. The feature extraction sub-module is used to extract features related to the operation status of the railway signal system from the preprocessed data. The features include but are not limited to signal response time, failure rate, and external environment factors.

[0028] Preprocess and extract features from various fault data, such as equipment operation status data, sensor data, communication data, and historical fault data, and convert them into input feature vectors that can be processed by a neural network. Then, input these feature vectors into the neural network. Through the forward propagation algorithm, calculate the output result of the network. As a powerful artificial intelligence technology, the neural network is based on the simulation of biological neural networks. By constructing a large number of neurons and complex connection weights, a highly complex non-linear model is formed. The neural network can learn and train on a large amount of historical fault data. During the training process, by comparing the difference between the actual output and the expected output of the network, use the backpropagation algorithm to continuously adjust the connection weights of the network, so that the network can gradually learn the features and rules in the fault data. When new fault data is input, the neural network can quickly and accurately judge the fault type and cause based on the learned knowledge. When dealing with hardware faults, the neural network can judge which hardware component has failed according to the changes in operating parameters such as the temperature, current, and voltage of the equipment, as well as the abnormal signals feedback by the sensors, such as the damage of a certain chip on the circuit board, the failure of a certain sensor, etc. When facing software faults, the neural network can judge whether there are problems such as program vulnerabilities and data errors by analyzing software operation logs, data transmission anomalies, etc.;

[0029] The expert system is an intelligent system built based on the knowledge and experience of domain experts. The inference engine is the core of the expert system. It uses the knowledge in the knowledge base to perform logical reasoning through inference algorithms according to the input fault information, so as to draw a fault diagnosis conclusion. The expert system first receives fault information from various monitoring devices and sensors. Then, the inference engine searches and matches in the knowledge base according to this information. If it finds knowledge that matches a certain fault mode, it can give a fault diagnosis conclusion and repair suggestions according to the corresponding fault cause and solution. If the abnormal train speed is detected, the expert system will judge the possible fault causes through inference based on the knowledge about speed sensor faults, speed measurement module faults, and related software algorithm errors in the knowledge base, and provide corresponding troubleshooting and repair methods.

[0030] The multi-source data fusion module includes a data matching sub-module and a data fusion algorithm sub-module.

[0031] The data matching sub-module is used to synchronize the time and match the space of data from different sources to ensure the consistency and accuracy of the data; the data fusion algorithm sub-module uses the Kalman filter and D-S evidence theory fusion algorithm to fuse the matched data to extract key information useful for operation and maintenance management decisions.

[0032] Kalman filtering is an efficient recursive filtering algorithm. Based on the assumptions of a linear system and unbiased estimation conforming to the Gaussian distribution, it features high computational efficiency and strong real-time performance. During the operation of a train, information such as the train's speed and position needs to be updated in real time and accurately estimated. Kalman filtering can, according to the state equation and observation equation of the system, perform real-time estimation and prediction on parameters such as the train's position and speed. For example, in train speed estimation, by fusing the measurement data from speed sensors and the prediction data from the train motion model, Kalman filtering can effectively reduce the impact of measurement noise and provide a more accurate speed estimation value;

[0033] D-S evidence theory is an uncertainty reasoning method, with the core content being "evidence" and "combination". In the fault diagnosis during the operation and maintenance of railway signals, D-S evidence theory can use the fault information from different sensors and different monitoring systems as evidence, and through the basic probability assignment function and combination rules, reason and judge the fault type and cause. For example, when a device fails, information may be received from various aspects such as the device operation status monitoring system and the sensor alarm system. This information may be uncertain and conflicting. D-S evidence theory can effectively process this uncertain information, fuse different evidences, and draw a more reliable fault diagnosis conclusion. It does not require prior probabilities and can directly handle unknown states, having strong advantages in dealing with multi-source uncertain information.

[0034] The operation and maintenance management decision-making module includes a fault warning sub-module, a maintenance plan formulation sub-module, and an emergency response strategy formulation sub-module. The fault warning sub-module is used to judge whether there are potential faults in the railway signal system according to the output of the large model processing module and generate fault warning information. The maintenance plan formulation sub-module is used to formulate a maintenance plan according to the fault warning information and the system's historical maintenance records. The maintenance plan includes but is not limited to maintenance time, maintenance content, and maintenance personnel arrangement. The emergency response strategy formulation sub-module is used to quickly generate an emergency response strategy when a fault occurs in the railway signal system to minimize the impact of the fault on railway transportation.

[0035] The application module includes a user switching unit, which is used to display the operation and maintenance management decision-making results, receive user input, and provide system configuration and parameter adjustment functions.

[0036] Provide a visual interface for operation and maintenance personnel, intuitively display key information such as the operation status of various devices, fault warnings, device health status, and operation and maintenance efficiency, help operation and maintenance personnel make quick judgments and decisions, and improve operation and maintenance efficiency and safety.

[0037] The foregoing has shown and described 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, and what is described in the above embodiments and the specification is only to illustrate 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 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 signal operation and maintenance management system based on the integration of large models and multi-source data, characterized in that Including: A large model processing module, which is used to receive and analyze the historical data, real-time operation data and external environment data of the railway signal system. The large model processing module can process the data based on deep learning algorithms to predict the operation status and potential faults of the railway signal system; A multi-source data fusion module, which is used to fuse and process data from different sources. The data includes but is not limited to sensor data, video surveillance data, weather data and train operation plan data of the railway signal system. The multi-source data fusion module can extract and integrate key information from each data source to form a unified operation and maintenance management data set; An operation and maintenance management decision-making module, which is used to generate operation and maintenance management decisions for the railway signal system according to the outputs of the large model processing module and the multi-source data fusion module. The decisions include but are not limited to fault warning, maintenance plan formulation and emergency response strategy formulation; An application module, which provides a visual interface for operation and maintenance personnel to intuitively display key information such as the operation status of various devices, fault warnings, device health status, and operation and maintenance efficiency, helping operation and maintenance personnel to quickly make judgments and decisions, and improving operation and maintenance efficiency and safety.

2. The railway signal operation and maintenance management system based on the integration of large models and multi-source data according to claim 1, wherein: The large model processing module includes a data preprocessing sub-module and a feature extraction sub-module. The data preprocessing sub-module is used to clean, format convert and normalize the received raw data to improve data quality and analysis efficiency. The feature extraction sub-module is used to extract features related to the operation status of the railway signal system from the preprocessed data. The features include but are not limited to signal response time, failure rate and external environment factors.

3. The railway signal operation and maintenance management system based on the integration of large models and multi-source data according to claim 2, characterized in that: The multi-source data fusion module includes a data matching sub-module and a data fusion algorithm sub-module.

4. The railway signal operation and maintenance management system based on the fusion of large models and multi-source data according to claim 3, characterized in that: The data matching sub-module is used to synchronize the time and match the space of data from different sources to ensure the consistency and accuracy of the data. The data fusion algorithm sub-module uses the Kalman filter and D-S evidence theory fusion algorithm to fuse the matched data to extract key information useful for operation and maintenance management decision-making.

5. The railway signal operation and maintenance management system based on the integration of large models and multi-source data according to claim 4, characterized in that: The operation and maintenance management decision-making module includes a fault warning sub-module, a maintenance plan formulation sub-module and an emergency response strategy formulation sub-module.

6. The railway signal operation and maintenance management system based on the integration of large models and multi-source data according to claim 5, characterized in that: The fault warning sub-module is used to judge whether there are potential faults in the railway signal system according to the output of the large model processing module and generate fault warning information. The maintenance plan formulation sub-module is used to formulate a maintenance plan according to the fault warning information and the system's historical maintenance records. The maintenance plan includes but is not limited to maintenance time, maintenance content and maintenance personnel arrangement. The emergency response strategy formulation sub-module is used to quickly generate an emergency response strategy when a fault occurs in the railway signal system to minimize the impact of the fault on railway transportation.

7. The railway signal operation and maintenance management system based on the fusion of large models and multi-source data according to claim 1, characterized in that: The application module includes a user interaction unit, which is used to display the results of operation and maintenance management decisions, receive user inputs, and provide system configuration and parameter adjustment functions.

Images