Unified management system for multi-source heterogeneous data of railway facilities

Abstract

The invention relates to the technical field of railway facility data management, in particular to a railway facility multi-source heterogeneous data unified management system which comprises a data acquisition module, a data quality evaluation module, a data standardization module, a data consistency verification module, a data analysis module and a fault diagnosis module. According to the system, original data of track detection, contact network detection and power supply monitoring systems are collected in real time, quality evaluation, standardization processing and consistency verification are carried out, the data are finally stored in a distributed database, and an equipment state evaluation report and fault early warning information are generated. According to the method, the problems of dispersity and heterogeneity of railway facility data can be effectively solved, the precision and reliability of data integration are improved, intelligent operation and maintenance management of data driving is realized, and the economical efficiency and stability of railway facility operation are improved.

Description

Technical Field

[0001] This invention relates to the field of railway facility data management technology, and more specifically, to a unified management system for multi-source heterogeneous data of railway facilities. Background Technology

[0002] With the continuous expansion of railway transportation, the monitoring and maintenance management of railway facilities (including tracks, overhead contact lines, power supply equipment, etc.) has become increasingly complex. Existing railway facility management systems typically rely on various independent detection systems, such as track detection systems, overhead contact line detection systems, and power supply monitoring systems. These systems collect and record different types of raw data, such as track geometric parameters, waveform data, voltage and current information, and equipment vibration status. Due to the differences in data formats, acquisition cycles, and storage structures used by each system, railway facility data exhibits significant dispersion and heterogeneity, making it difficult to form a unified monitoring and management view.

[0003] Currently, the processing and analysis of railway facility data still faces numerous challenges. On the one hand, the lack of standardized data interfaces and unified data models between various systems makes direct data integration and comparison difficult. On the other hand, the raw data contains a large amount of invalid, duplicate, or abnormal data, which, if not effectively cleaned and standardized, will directly affect the accuracy and reliability of subsequent analyses. Furthermore, there are shortcomings in the mixed storage of structured and unstructured data, version control, and historical traceability capabilities, making it difficult to achieve comprehensive, real-time, and traceable railway facility status assessments and fault early warnings.

[0004] Therefore, existing railway facility management technologies are insufficient to meet the needs of unified management, analysis, and application of multi-source heterogeneous data. The lack of a unified data integration platform not only restricts comprehensive monitoring of railway facility operation status but also limits the development of data-driven intelligent decision-making and early warning analysis. How to achieve efficient collection, standardized processing, unified storage, and centralized service of multi-source heterogeneous data has become a key technical problem that urgently needs to be solved in railway information management. Summary of the Invention

[0005] In view of this, the present invention proposes a unified management system for multi-source heterogeneous data of railway facilities, which aims to solve the problem that the current railway facility management lacks a unified data integration and processing platform, which makes it impossible to achieve efficient collection, standardization, unified storage and centralized service of multi-source heterogeneous data, thus restricting the realization of comprehensive monitoring, intelligent decision-making and early warning analysis.

[0006] This invention proposes a unified management system for multi-source heterogeneous data of railway facilities, comprising: The data acquisition module is configured to acquire raw data from the track inspection system, the overhead contact line inspection system, and the power supply monitoring system, and to perform real-time acquisition and preprocessing of the raw data to construct a unified raw dataset. The evaluation module is electrically connected to the data acquisition module. The evaluation module is configured to perform data validity analysis based on a unified dataset to determine whether the preliminary data integration conditions are met. The data standardization module is electrically connected to the evaluation module. The data standardization module is configured to perform format conversion and field mapping on the original data based on the target data model when the initial data integration conditions are met, so that it gradually approaches a unified standard format. The verification module is electrically connected to the data standardization module. The verification module is configured to continuously monitor the deviation between the standardized data and the target data model, and based on the deviation, determine whether the precise data integration conditions are met. If the precise data integration conditions are met, a data storage instruction is sent to store the data in the distributed database. The analysis module is electrically connected to the verification module. The analysis module is configured to perform in-depth data mining and trend analysis after data storage is completed, and generate equipment status assessment reports and fault warning information. The fault diagnosis module is electrically connected to the verification module and the analysis module. The fault diagnosis module is configured to monitor the actual storage status of the distributed database after the data storage instruction is sent. If the distributed database fails to successfully store data within a preset time or data is lost after storage, it is determined to be a data storage failure, and fault handling is performed according to the preset fault isolation and recovery strategy.

[0007] Furthermore, when the data acquisition module acquires raw data from the track inspection system, overhead contact line inspection system, and power supply monitoring system, it includes: The data acquisition module is also configured to acquire track geometry parameters, gauge, elevation, level, alignment, track vibration frequency, track surface roughness, and track material properties based on track detection sensors. The data acquisition module is also configured to acquire data on contact wire voltage, current, temperature, insulation resistance, waveform data, over-limit alarms, contact wire tension, contact wire wear degree, and contact wire ambient temperature based on the contact wire detection sensors. The data acquisition module is also configured to acquire data on suspension status, pantograph-catenary relationship, vibration data, aging of power supply equipment, and impedance of power supply lines based on power supply monitoring sensors.

[0008] Furthermore, the evaluation module is configured to perform data validity analysis based on the unified dataset to determine whether the initial data integration conditions are met, including: The evaluation module is also configured to extract track geometry parameters, overhead contact line voltage, and suspension status data, and compare the track geometry parameters with preset track safety thresholds to generate track parameter qualification marks. The evaluation module is also configured to compare the overhead contact line voltage with a preset voltage safety threshold to generate a voltage compliance mark; The evaluation module is also configured to compare the suspension status with a preset suspension status safety threshold to generate a suspension status pass mark; The evaluation module is also configured to aggregate track parameter pass flags, voltage pass flags, and suspension status pass flags based on configured AND logic rules. If the aggregation result is true, the evaluation module determines that the preliminary data integration conditions are met.

[0009] Furthermore, the data standardization module is configured to, when the initial data integration conditions are met, perform format conversion and field mapping on the original data based on the target data model, including: The data standardization module is also configured to define a uniform data format and field names based on the target data model; The data standardization module is also configured to use a format conversion algorithm to convert track geometry parameters, catenary voltage, and suspension status data into a format supported by the target data model; The data standardization module is also configured to establish the correspondence between the original data fields and the target data model fields for the field mapping algorithm, store the format-converted and field-mapped data in a temporary buffer, and verify the accuracy of the data conversion through a consistency check algorithm.

[0010] Furthermore, the verification module performs a precise data integration condition determination based on the deviation, including determining whether the precise data integration conditions are met: The verification module is also configured to calculate the relative deviation between the standardized orbital geometry parameters and the target data model; The verification module is also configured to calculate the relative deviation between the standardized contact network voltage and the target data model; The verification module is also configured to calculate the absolute deviation between the standardized suspension state and the target data model; The verification module is also configured to compare the relative deviation of the track geometry parameters with a preset track synchronization threshold to generate a track synchronization mark; The verification module is also configured to compare the relative deviation of the contact network voltage with a preset voltage synchronization threshold to generate a voltage synchronization mark; The verification module is also configured to compare the absolute deviation of the suspension state with a preset suspension state synchronization threshold to generate a suspension state synchronization mark. The verification module is also configured to aggregate track synchronization markers, voltage synchronization markers, and suspension state synchronization markers based on configured AND logic rules, wherein: If the aggregation result is true, then the conditions for precise data integration are met.

[0011] Furthermore, after data storage is complete, the analysis module performs in-depth data mining and trend analysis to generate equipment status assessment reports and fault early warning information, including: The analysis module is also configured to retrieve historical data on track geometry parameters, overhead contact line voltage, and suspension status based on a distributed database query interface; The analysis module is also configured to model the changing trends of orbital geometric parameters based on time series analysis algorithms to predict future orbital states; The analysis module is also configured to analyze the fluctuations in the overhead contact line voltage based on statistical analysis algorithms to identify potential abnormal patterns; The analysis module is also configured to classify historical records of suspended states based on machine learning algorithms to generate fault warning models.

[0012] Furthermore, the analysis module is also configured to combine track maintenance plans, power supply monitoring requirements, and overhead contact line maintenance strategies, and through optimization algorithms, determine the optimal equipment maintenance cycle, which includes the optimal maintenance time and maintenance priority, and issue adjustment instructions to the operation and maintenance management system.

[0013] Furthermore, when the fault diagnosis module determines that data storage has failed, it includes: The fault diagnosis module is also configured to disconnect the distributed database from the central processing unit, causing the data to roll back to a temporary buffer. The fault diagnosis module is also configured to perform internal fault diagnosis and isolation of the distributed database and generate fault reports; The fault diagnosis module is also configured to automatically or manually attempt to re-execute the data storage procedure based on the fault type.

[0014] Furthermore, the data acquisition module is also configured to transmit the raw data from the track inspection system, the overhead contact line inspection system, and the power supply monitoring system to the central processing unit via a high-speed communication interface, and to filter, denoise, and impute missing data in the data to construct a unified raw dataset.

[0015] Compared with existing technologies, the beneficial effects of this invention are as follows: By constructing a modular unified management system for multi-source heterogeneous data of railway facilities, it achieves closed-loop management of the entire process of data acquisition, integration, standardization, storage, analysis, and fault diagnosis, bringing about multiple beneficial effects. Firstly, in terms of data acquisition, the system's data acquisition module can simultaneously obtain raw data from the track inspection system, the overhead contact line inspection system, and the power supply monitoring system, and perform real-time acquisition and preliminary preprocessing of data from different sources and of different types, including data cleaning, anomaly marking, and preliminary standardization. By constructing a unified raw dataset, this module effectively solves the problems of independent operation of various systems, large differences in data formats, and severe information silos in existing technologies, providing a high-quality data foundation for subsequent data integration and analysis. Secondly, in terms of data validity analysis and standardization, the system uses an evaluation module to check the validity of the collected unified dataset, determining whether the data meets the preliminary integration conditions, ensuring that the data entering the standardization process has reliability and integrity. Based on this, the data standardization module performs format conversion, field mapping, and gradual normalization processing on data from different sources according to a preset target data model, gradually bringing the data closer to a unified standard format. This process not only eliminates structural differences between multi-source data but also ensures the comparability and fusion of data within the system, significantly improving data integration efficiency and reducing the need for manual intervention and error handling. Furthermore, regarding data verification and precise storage, the verification module continuously monitors the deviation between the standardized data and the target data model, making real-time judgments on the accuracy of data integration. When the data meets the conditions for precise integration, the system automatically generates data storage instructions, securely storing the data in a distributed database. Through the application of a distributed database, the system not only supports efficient storage of large-scale, multi-type data but also enables data version management, historical backtracking, and disaster recovery backup, ensuring data integrity, reliability, and traceability. This solves the problems of scattered data storage, lack of unified management, and difficulty in historical tracking in traditional railway management systems. Simultaneously, in terms of data analysis and intelligent operation and maintenance, the analysis module can perform in-depth data mining and trend analysis after data storage, generating equipment status assessment reports, abnormal alarm information, and fault warnings, providing a scientific basis for railway facility operation and maintenance management. This not only enhances the global visualization and monitoring capabilities of the track, catenary, and power supply system operating status but also enables data-driven predictive maintenance, reducing the risk of equipment failure and the probability of operational interruptions. Finally, regarding fault diagnosis and recovery, the fault diagnosis module monitors the storage status of the distributed database in real time. If data fails to be stored successfully or is lost within a preset time, the system will automatically determine it as a storage failure and handle it according to the preset fault isolation and recovery strategies to ensure the reliability and continuity of the data processing chain.This mechanism ensures the system's robustness and high availability in complex railway operating environments, enabling managers to confidently rely on the system for critical business decisions. Attached Figure Description

[0016] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A functional block diagram of a unified management system for multi-source heterogeneous data of railway facilities provided in an embodiment of the present invention; Figure 2 This is a flowchart of a unified management system for multi-source heterogeneous data of railway facilities, provided as an embodiment of the present invention. Detailed Implementation

[0017] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, embodiments and features in the embodiments of the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0018] like Figures 1-2 As shown in some embodiments of this application, this embodiment provides a unified management system for multi-source heterogeneous data of railway facilities, including: a data acquisition module, an evaluation module, a data standardization module, a verification module, an analysis module, and a fault diagnosis module.

[0019] Specifically, the data acquisition module is configured to acquire raw data from the track inspection system, the overhead contact line inspection system, and the power supply monitoring system, and to perform real-time acquisition and preprocessing of the raw data to construct a unified raw dataset.

[0020] Specifically, when the data acquisition module acquires raw data from the track detection system, catenary detection system, and power supply monitoring system, it includes: the data acquisition module is also configured to acquire track geometric parameters, gauge, elevation, level, alignment, track vibration frequency, track surface roughness, and track material properties based on track detection sensors; the data acquisition module is also configured to acquire catenary voltage, current, temperature, insulation resistance, waveform data, over-limit alarms, catenary tension, catenary wear degree, and catenary ambient temperature data based on catenary detection sensors; and the data acquisition module is also configured to acquire suspension status, pantograph-catenary relationship, vibration data, aging degree of power supply equipment, and power supply line impedance data based on power supply monitoring sensors.

[0021] Specifically, the data acquisition module is also configured to use a high-speed communication interface to transmit the raw data from the track inspection system, the overhead contact line inspection system, and the power supply monitoring system to the central processing unit, and to filter, denoise, and imput missing data in the data to build a unified raw dataset.

[0022] Understandably, the data acquisition module performs real-time acquisition, preprocessing, and unified management of data from the railway's multi-source heterogeneous detection system to achieve high-quality raw data integration. First, the data acquisition module can obtain raw data from the track inspection system, catenary inspection system, and power supply monitoring system, collecting key parameters through different types of sensors. For example, track inspection sensors collect track geometry parameters, gauge, elevation, level, alignment, track vibration frequency, track surface roughness, and track material properties; catenary inspection sensors collect voltage, current, temperature, insulation resistance, waveform data, over-limit alarms, catenary tension, wear level, and ambient temperature; power supply monitoring sensors collect information such as suspension status, pantograph-catenary relationship, vibration data, equipment aging level, and line impedance. This multi-dimensional, fine-grained data acquisition principle ensures comprehensive perception of the railway facility's operational status. Second, to ensure data availability and accuracy, the data acquisition module uses a high-speed communication interface to transmit raw data from each detection system to the central processing unit, achieving real-time data acquisition and centralized management. Simultaneously, the module preprocesses the collected data, including filtering, noise reduction, and missing data imputation, thereby eliminating sensor noise, filling in data gaps, and improving data integrity and accuracy. This processing principle ensures that data from different sources reach a unified quality standard before entering the subsequent integration and analysis stages. Finally, the data acquired and preprocessed in real time is constructed into a unified raw dataset, forming a unified data foundation that the system can identify and process. Through real-time acquisition and preprocessing of multi-source heterogeneous data, high-quality data fusion is achieved, providing a reliable foundation for subsequent standardized processing, accurate storage, and intelligent analysis. This also solves the problems of data fragmentation, inconsistent standards, and information silos in existing railway facility management.

[0023] Specifically, the evaluation module is electrically connected to the data acquisition module. The evaluation module is configured to perform data validity analysis based on a unified dataset to determine whether the preliminary data integration conditions are met.

[0024] Specifically, the evaluation module is configured to perform data validity analysis based on a unified dataset to determine whether the preliminary data integration conditions are met. This includes: the evaluation module is further configured to extract track geometric parameters, catenary voltage, and suspension status data, and compare the track geometric parameters with a preset track safety threshold to generate a track parameter qualification mark; the evaluation module is further configured to compare the catenary voltage with a preset voltage safety threshold to generate a voltage qualification mark; the evaluation module is further configured to compare the suspension status with a preset suspension status safety threshold to generate a suspension status qualification mark; and the evaluation module is further configured to aggregate the track parameter qualification mark, voltage qualification mark, and suspension status qualification mark based on a configured AND logic rule. If the aggregation result is true, the evaluation module determines that the preliminary data integration conditions are met.

[0025] Understandably, the evaluation module performs a systematic validity analysis on the multi-source heterogeneous data in the unified dataset to determine whether the data meets the initial data integration conditions, providing a reliable foundation for subsequent standardized processing, accurate storage, and analysis. First, the evaluation module is electrically connected to the data acquisition module, enabling real-time acquisition of key parameters in the unified dataset, including track geometry parameters, catenary voltage, and suspension status. These parameters represent core indicators of railway facility operation and are crucial for evaluating the operational status of the railway system and the reliability of the data. By analyzing these key parameters, the system can initially determine whether the data is complete and reasonable, providing the first quality control for subsequent integration. Specifically, when performing data validity analysis, the evaluation module first extracts track geometry parameters, including gauge, elevation, level, alignment, track vibration frequency, and track surface roughness, and compares them with preset track safety thresholds to generate track parameter qualification marks. Second, the module extracts catenary voltage data, compares the actual collected voltage values ​​with preset voltage safety thresholds to generate voltage qualification marks. Third, the module extracts suspension status data, compares the actual suspension status with preset suspension safety thresholds to generate suspension status qualification marks. By comparing these parameters with safety thresholds, the system can quickly identify potential data anomalies or acquisition deviations, ensuring that data entering the integration process meets safety and reliability requirements. Furthermore, based on multi-parameter analysis, the evaluation module further utilizes logical rules for data aggregation and judgment. Track parameter compliance markers, voltage compliance markers, and suspension status compliance markers are comprehensively evaluated using configured AND logical rules. When all markers are true, the unified dataset is deemed to meet the initial data integration conditions. This logical judgment mechanism ensures the consistency and reliability of multi-source data across different dimensions, preventing single anomalies from affecting the overall data integration effect. Finally, the evaluation module can be configured with scalable threshold parameters and logical rules to adapt to safety standards for different railway lines and facility conditions, making the system flexible and maintainable. Through the real-time analysis and judgment of this module, not only is preliminary quality control of multi-source heterogeneous data achieved, but it also provides reliable support for subsequent data standardization, precise integration, and intelligent analysis, significantly improving the railway facility management system's response capability to data anomalies and the overall operational safety.

[0026] Specifically, the data standardization module is electrically connected to the evaluation module. The data standardization module is configured to perform format conversion and field mapping on the original data based on the target data model when the initial data integration conditions are met, so that it gradually approaches a unified standard format.

[0027] Specifically, the data standardization module is configured to, when the initial data integration conditions are met, perform format conversion and field mapping on the original data based on the target data model. This includes: the data standardization module is also configured to define a unified data format and field names according to the target data model; the data standardization module is also configured to use a format conversion algorithm to convert track geometry parameters, catenary voltage, and suspension status data into a format supported by the target data model; the data standardization module is also configured to use a field mapping algorithm to establish a correspondence between the original data fields and the target data model fields, store the format-converted and field-mapped data in a temporary buffer, and verify the accuracy of the data conversion through a consistency check algorithm.

[0028] Understandably, the data standardization module performs unified format conversion and field mapping on multi-source heterogeneous data that meets the initial integration conditions, thereby gradually achieving data standardization and ensuring the data's integrability and processability within the system. First, the data standardization module is electrically connected to the evaluation module, enabling real-time acquisition of unified datasets deemed by the evaluation module to meet the initial integration conditions. Based on the target data model, the module defines a unified data format and field names, providing a unified standard for raw data from different sources and of different types, and providing a standardized foundation for subsequent data integration and analysis. Second, the data standardization module uses format conversion algorithms to convert raw data such as track geometry parameters, catenary voltage, and suspension status into standard formats supported by the target data model. For example, it unifies the units, precision, or data types of similar data from different detection systems, ensuring consistency in numerical representation, timestamp recording, and structured methods. This conversion ensures that multi-source heterogeneous data can be compared and processed under a unified data model, eliminating format differences between systems. Simultaneously, the data standardization module establishes a correspondence between raw data fields and target data model fields through field mapping algorithms, achieving data structure unification. Field mapping not only involves mapping simple field names but also data types, hierarchical structures, and relationships, enabling data to be gradually standardized from its original form to conform to the system's unified standards. Data after format conversion and field mapping is first stored in a temporary buffer for further processing. Finally, to ensure the accuracy of data standardization, the data standardization module is equipped with a consistency verification algorithm to validate the converted and mapped data, ensuring that the data content, structure, and values ​​remain consistent with the target model, avoiding data loss or errors during the standardization process. Through these technical principles, the data standardization module can achieve a smooth transition from multi-source heterogeneous data to a unified standard format, providing a high-quality data foundation for subsequent accurate data integration, storage, and intelligent analysis, significantly improving the data availability and analytical reliability of the railway facility management system.

[0029] Specifically, the verification module is electrically connected to the data standardization module. The verification module is configured to continuously monitor the deviation between the standardized data and the target data model, and based on the deviation, determine whether the conditions for accurate data integration are met. If the conditions are met, a data storage command is sent to store the data in the distributed database. Specifically, the verification module determines whether the precise data integration conditions are met based on the deviations. This includes: the verification module is further configured to calculate the relative deviation between the standardized track geometry parameters and the target data model; the verification module is further configured to calculate the relative deviation between the standardized contact wire voltage and the target data model; the verification module is further configured to calculate the absolute deviation between the standardized suspension state and the target data model; the verification module is further configured to compare the relative deviation of the track geometry parameters with a preset track synchronization threshold to generate a track synchronization mark; the verification module is further configured to compare the relative deviation of the contact wire voltage with a preset voltage synchronization threshold to generate a voltage synchronization mark; the verification module is further configured to compare the absolute deviation of the suspension state with a preset suspension state synchronization threshold to generate a suspension state synchronization mark; and the verification module is further configured to aggregate the track synchronization mark, voltage synchronization mark, and suspension state synchronization mark based on a configured AND logic rule, wherein: if the aggregation result is true, the precise data integration conditions are determined to be met.

[0030] Understandably, the verification module continuously monitors and analyzes the standardized multi-source heterogeneous data to determine whether the data meets the conditions for accurate integration, and securely stores the data in a distributed database when the conditions are met. First, the verification module is electrically connected to the data standardization module, enabling it to acquire standardized track geometry parameters, catenary voltage, and suspension status data in real time and compare them with the target data model to ensure high accuracy before entering the final storage and analysis stage. Second, the verification module achieves accurate judgment by calculating the deviations between various data types and the target data model. For track geometry parameters and catenary voltage, the module calculates their relative deviations; for suspension status, it calculates their absolute deviations. These deviation calculation methods quantify the differences between the standardized data and the target model, reflecting the degree of consistency of the data in terms of value and structure, thus providing a reliable basis for accurate data integration. Based on the deviation calculations, the verification module compares various deviations with preset synchronization thresholds. The relative deviation of track geometry parameters is compared with the track synchronization threshold to generate a track synchronization mark; the relative deviation of catenary voltage is compared with the voltage synchronization threshold to generate a voltage synchronization mark; and the absolute deviation of suspension status is compared with the suspension status synchronization threshold to generate a suspension status synchronization mark. These markers enable the system to quickly identify whether data meets the standards for precise integration, achieving high-precision control over the quality of multi-source heterogeneous data. Finally, the verification module uses logical rules for comprehensive judgment, aggregating track synchronization markers, voltage synchronization markers, and suspension status synchronization markers through configured AND logic rules. When all markers are true, the system determines that the data meets the conditions for precise data integration and automatically sends a data storage command, securely storing the data in a distributed database. This technical principle ensures the accuracy and consistency of multi-source heterogeneous data before it enters long-term storage and subsequent analysis, effectively improving data reliability and system operational security, and providing high-quality data support for intelligent management and predictive maintenance of railway facilities.

[0031] Specifically, the analysis module is electrically connected to the verification module. The analysis module is configured to perform in-depth data mining and trend analysis after the data is stored, and generate equipment status assessment reports and fault warning information. Specifically, after data storage is completed, the analysis module performs in-depth data mining and trend analysis to generate equipment status assessment reports and fault early warning information. This includes: the analysis module is also configured to obtain historical data on track geometric parameters, catenary voltage, and suspension status based on a distributed database query interface; the analysis module is also configured to model the changing trends of track geometric parameters based on time series analysis algorithms to predict future track status; the analysis module is also configured to analyze the fluctuations of catenary voltage based on statistical analysis algorithms to identify potential abnormal patterns; and the analysis module is also configured to classify historical records of suspension status based on machine learning algorithms to generate fault early warning models.

[0032] Specifically, the analysis module is also configured to combine track maintenance plans, power supply monitoring requirements, and overhead contact line maintenance strategies, and through optimization algorithms, determine the optimal equipment maintenance cycle, which includes the optimal maintenance time and maintenance priority, and issue adjustment instructions to the operation and maintenance management system.

[0033] Understandably, the analysis module performs in-depth mining and trend analysis on historical railway facility data in a distributed database to generate equipment status assessment reports, fault early warning information, and optimize equipment maintenance strategies. First, the analysis module is electrically connected to the verification module. After data storage, it can acquire standardized and accurately integrated data on track geometry parameters, catenary voltage, and suspension status in real time, serving as the basis for analysis. The module obtains historical data through a distributed database query interface, achieving comprehensive access to time-series data and providing reliable data support for trend analysis and anomaly detection. Specifically, the analysis module models the changing trends of track geometry parameters using time-series analysis algorithms to predict future track conditions and identify potential track anomalies or over-limit risks. Simultaneously, the module uses statistical analysis algorithms to analyze catenary voltage fluctuations, identifying possible abnormal patterns, such as voltage mutations or abnormal fluctuations, providing a basis for power supply safety monitoring. Furthermore, the analysis module employs machine learning algorithms to classify and recognize patterns in historical suspension status records, thereby establishing a fault early warning model that can predict potential equipment faults in advance, enabling proactive maintenance and risk prevention. Based on data analysis, the analysis module further integrates track maintenance plans, power supply monitoring requirements, and overhead contact line maintenance strategies. Through optimization algorithms, it calculates the optimal equipment maintenance cycle, including maintenance time and priority, and then issues maintenance adjustment instructions to the operation and maintenance management system. This step enables data-driven operation and maintenance decisions, ensuring that equipment maintenance aligns with actual operating conditions, optimizes resource utilization, and improves the safety and reliability of railway facilities.

[0034] Specifically, the fault diagnosis module is electrically connected to the verification module and the analysis module. The fault diagnosis module is configured to monitor the actual storage status of the distributed database after the data storage instruction is sent. If the distributed database fails to successfully store data within a preset time or data is lost after storage, it is determined to be a data storage failure, and fault handling is performed according to the preset fault isolation and recovery strategy.

[0035] Specifically, when the fault diagnosis module determines that data storage has failed, it includes: the fault diagnosis module is also configured to disconnect the distributed database from the central processing unit, causing the data to roll back to a temporary buffer; the fault diagnosis module is also configured to perform internal fault diagnosis and isolation on the distributed database and generate a fault report; the fault diagnosis module is also configured to automatically or manually attempt to re-execute the data storage process according to the fault type.

[0036] It is understandable that the fault diagnosis module enables real-time monitoring and fault handling of the distributed database's data storage process, thereby ensuring the reliable storage of multi-source heterogeneous data in railway facilities and the continuity of system operation. First, the fault diagnosis module is electrically connected to the verification and analysis modules, enabling real-time monitoring of the actual storage status of the distributed database after the data storage command is sent. This allows the system to determine whether data has been successfully written to the database and whether there has been any data loss or anomalies after storage. Through this monitoring mechanism, the system can detect storage faults immediately, preventing data loss from impacting subsequent analysis and decision-making. Second, when a data storage failure is detected, the fault diagnosis module performs multi-layered processing according to preset fault isolation and recovery strategies. First, the module disconnects the distributed database from the central processing unit, rolls the data back to a temporary buffer to ensure no loss of original data and provides a reliable data source for subsequent retries. Second, the module performs internal fault diagnosis and isolation processing on the distributed database, analyzes the cause of the fault, and generates a detailed fault report for maintenance personnel or the system to perform subsequent processing and improvements. Finally, depending on the fault type, the module automatically or manually attempts to re-execute the data storage process to ensure that data can be successfully written to the database, achieving the system's self-recovery capability.

[0037] As can be seen, the fault diagnosis module enables real-time monitoring of the distributed database storage status, fault isolation and diagnosis, and automatic recovery operations, thereby ensuring the integrity and reliability of multi-source heterogeneous railway data throughout the entire process of acquisition, integration, standardization, and analysis. This module not only improves the robustness of the data management system but also enhances its fault tolerance in the face of sudden storage failures, providing highly reliable data support for the intelligent management of railway facilities.

[0038] To enable those skilled in the art to fully understand and implement this invention, the specific implementation principle of this invention is further explained below in conjunction with a specific application scenario.

[0039] In the actual operation of a certain railway section, it is assumed that real-time monitoring and maintenance of track geometry parameters are required. First, track geometry parameters, including core data such as gauge, elevation, level, and alignment, are acquired through track detection sensors in the data acquisition module. Simultaneously, auxiliary information such as track vibration frequency, surface roughness, and material properties are also collected. This raw data is transmitted to the central processing unit via a high-speed communication interface. During this process, the central processing unit filters and denoises the data to eliminate noise interference and interpolates missing data, ultimately constructing a unified raw dataset and storing it in a temporary buffer.

[0040] Subsequently, the data quality assessment module extracts track geometry parameters from the temporary buffer and compares them with preset safety thresholds. For example, the track gauge data is compared with a preset track gauge safety range; if the track gauge is within the safety range, a qualified mark is generated; otherwise, a unqualified mark is generated. Similarly, parameters such as elevation, level, and alignment are also compared with their corresponding safety thresholds to generate corresponding qualified or unqualified marks. Based on the configured AND logic rules, the data quality assessment module aggregates the qualified marks of all key parameters. If the aggregation result is true, the preliminary data integration conditions are met, and the process proceeds to the next stage.

[0041] Once the initial data integration conditions are met, the data standardization module initiates data format conversion and field mapping operations. Based on the unified format defined by the target data model, the data standardization module converts the track geometry parameters into a standard format supported by the target data model using a format conversion algorithm. For example, it converts track gauge data from millimeters to meters and establishes the correspondence between the original data fields and the target data model fields using a field mapping algorithm, such as mapping the "track gauge" field to the "Track_Gauge" field in the target model. The converted data is stored in a temporary buffer, and the accuracy of the conversion is verified using a consistency check algorithm. If deviations exceed the allowable range, a feedback correction mechanism optimizes the conversion process, ensuring that the data gradually converges to the target format.

[0042] Next, the verification module performs a precise data integration condition determination on the standardized data. This module acquires the standardized track geometry parameters in real time and calculates their deviation from the target data model. For example, it calculates the relative deviation between the gauge data and the standard gauge value in the target model and compares this deviation with a preset gauge synchronization threshold. If the relative deviation is less than the synchronization threshold, a gauge synchronization marker is generated; similarly, corresponding synchronization markers are generated for parameters such as elevation, horizontality, and alignment. Based on the configured AND logic rules, the verification module performs an aggregation operation on all synchronization markers. If the aggregation result is true, the precise data integration condition is satisfied, and a data storage instruction is sent to store the data in the distributed database.

[0043] After data storage is complete, the analysis module retrieves historical data on track geometry parameters through a distributed database query interface and performs in-depth mining and trend analysis. For example, based on time series analysis algorithms, it models the trend of track gauge changes and predicts possible changes in track gauge over a future period. Simultaneously, statistical analysis algorithms are used to identify fluctuation patterns in high and low parameters to determine if potential anomalies exist. Furthermore, machine learning algorithms classify historical data on horizontal and azimuth, generating fault warning models. The analysis module then generates an equipment status assessment report from the prediction results, anomaly patterns, and fault warning information, displaying it to maintenance personnel through a visual interface for timely maintenance action.

[0044] If an anomaly occurs during data storage, the fault diagnosis module will initiate fault isolation and recovery strategies. For example, if the distributed database fails to successfully store data within a preset time, the fault diagnosis module will disconnect the distributed database from the central processing unit and roll back the data to a temporary buffer. Subsequently, the fault diagnosis module will perform internal fault diagnosis on the distributed database, generate a detailed fault report, and automatically or manually attempt to re-execute the data storage process based on the fault type to ensure data integrity.

[0045] As can be seen from the above steps, this invention acquires raw data through a data acquisition module and performs preprocessing, ensuring data integrity and reliability; it performs validity analysis on the data through a data quality assessment module, avoiding interference from invalid or abnormal data; it unifies data formats through a data standardization module, reducing the complexity of integrating multi-source heterogeneous data; it ensures the accuracy of data integration through a verification module, improving the quality of data storage; it enables in-depth data mining and trend analysis through an analysis module, providing a scientific basis for intelligent operation and maintenance of railway facilities; and it ensures the reliability of data storage through a fault diagnosis module, enhancing the system's fault tolerance. The modules interact electrically, forming a complete closed-loop management process. This achieves efficient acquisition, standardized processing, unified storage, and centralized service of multi-source heterogeneous data from railway facilities, solving the problem of difficulty in forming a unified monitoring and management view due to data dispersion and heterogeneity in existing technologies, while also improving the security, reliability, and intelligence level of data management.

[0046] In the above embodiments, by constructing a modular unified management system for multi-source heterogeneous railway facility data, a closed-loop management of the entire process—data acquisition, integration, standardization, storage, analysis, and fault diagnosis—was achieved, bringing numerous beneficial effects. Firstly, regarding data acquisition, the system's data acquisition module can simultaneously obtain raw data from the track inspection system, the overhead contact line inspection system, and the power supply monitoring system. It also performs real-time acquisition and preliminary preprocessing of data from different sources and of different types, including data cleaning, anomaly labeling, and preliminary standardization. By constructing a unified raw dataset, this module effectively solves the problems of independent operation of various systems, significant differences in data formats, and severe information silos in existing technologies, providing a high-quality data foundation for subsequent data integration and analysis. Secondly, regarding data validity analysis and standardization, the system uses an evaluation module to check the validity of the collected unified dataset, determining whether the data meets the preliminary integration conditions and ensuring the reliability and integrity of the data entering the standardization process. Based on this, the data standardization module performs format conversion, field mapping, and gradual normalization processing on data from different sources according to a preset target data model, gradually bringing the data closer to a unified standard format. This process not only eliminates structural differences between multi-source data but also ensures the comparability and fusion of data within the system, significantly improving data integration efficiency and reducing the need for manual intervention and error handling. Furthermore, regarding data verification and precise storage, the verification module continuously monitors the deviation between the standardized data and the target data model, making real-time judgments on the accuracy of data integration. When the data meets the conditions for precise integration, the system automatically generates data storage instructions, securely storing the data in a distributed database. Through the application of a distributed database, the system not only supports efficient storage of large-scale, multi-type data but also enables data version management, historical backtracking, and disaster recovery backup, ensuring data integrity, reliability, and traceability. This solves the problems of scattered data storage, lack of unified management, and difficulty in historical tracking in traditional railway management systems. Simultaneously, in terms of data analysis and intelligent operation and maintenance, the analysis module can perform in-depth data mining and trend analysis after data storage, generating equipment status assessment reports, abnormal alarm information, and fault warnings, providing a scientific basis for railway facility operation and maintenance management. This not only enhances the global visualization and monitoring capabilities of the track, catenary, and power supply system operating status but also enables data-driven predictive maintenance, reducing the risk of equipment failure and the probability of operational interruptions. Finally, regarding fault diagnosis and recovery, the fault diagnosis module monitors the storage status of the distributed database in real time. If data fails to be stored successfully or is lost within a preset time, the system automatically determines it as a storage failure and handles it according to the preset fault isolation and recovery strategies, ensuring the reliability and continuity of the data processing chain. This mechanism guarantees the robustness and high availability of the system in complex railway operating environments, allowing managers to confidently rely on the system for critical business decisions.

[0047] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program goods. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program goods embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0048] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program goods according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0049] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0050] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0051] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A unified management system for multi-source heterogeneous data of railway facilities, characterized in that, include: The data acquisition module is configured to acquire raw data from the track inspection system, the overhead contact line inspection system, and the power supply monitoring system, and to perform real-time acquisition and preprocessing of the raw data to construct a unified raw dataset. The evaluation module is electrically connected to the data acquisition module. The evaluation module is configured to perform data validity analysis based on a unified dataset to determine whether the preliminary data integration conditions are met. The data standardization module is electrically connected to the evaluation module. The data standardization module is configured to perform format conversion and field mapping on the original data based on the target data model when the initial data integration conditions are met, so that it gradually approaches a unified standard format. The verification module is electrically connected to the data standardization module. The verification module is configured to continuously monitor the deviation between the standardized data and the target data model, and based on the deviation, determine whether the precise data integration conditions are met. If the precise data integration conditions are met, a data storage instruction is sent to store the data in the distributed database. The analysis module is electrically connected to the verification module. The analysis module is configured to perform in-depth data mining and trend analysis after data storage is completed, and generate equipment status assessment reports and fault warning information. The fault diagnosis module is electrically connected to the verification module and the analysis module. The fault diagnosis module is configured to monitor the actual storage status of the distributed database after the data storage instruction is sent. If the distributed database fails to successfully store data within a preset time or data is lost after storage, it is determined to be a data storage failure, and fault handling is performed according to the preset fault isolation and recovery strategy.

2. The unified management system for multi-source heterogeneous data of railway facilities as described in claim 1, characterized in that, When the data acquisition module acquires raw data from the track inspection system, overhead contact line inspection system, and power supply monitoring system, it includes: The data acquisition module is also configured to acquire track geometry parameters, gauge, elevation, level, alignment, track vibration frequency, track surface roughness, and track material properties based on track detection sensors. The data acquisition module is also configured to acquire data on contact wire voltage, current, temperature, insulation resistance, waveform data, over-limit alarms, contact wire tension, contact wire wear degree, and contact wire ambient temperature based on the contact wire detection sensors. The data acquisition module is also configured to acquire data on suspension status, pantograph-catenary relationship, vibration data, aging of power supply equipment, and impedance of power supply lines based on power supply monitoring sensors.

3. The unified management system for multi-source heterogeneous data of railway facilities as described in claim 1, characterized in that, The evaluation module is configured to perform data validity analysis based on a unified dataset to determine whether the initial data integration conditions are met, including: The evaluation module is also configured to extract track geometry parameters, contact wire voltage and suspension status data, and compare the track geometry parameters with preset track safety thresholds to generate track parameter qualification marks; The evaluation module is also configured to compare the overhead contact line voltage with a preset voltage safety threshold to generate a voltage compliance mark; The evaluation module is also configured to compare the suspension status with a preset suspension status safety threshold to generate a suspension status pass mark; The evaluation module is also configured to aggregate track parameter pass flags, voltage pass flags, and suspension status pass flags based on configured AND logic rules. If the aggregation result is true, the evaluation module determines that the preliminary data integration conditions are met.

4. The unified management system for multi-source heterogeneous data of railway facilities as described in claim 1, characterized in that, The data standardization module is configured to, when the initial data integration conditions are met, perform format conversion and field mapping on the original data based on the target data model, including: The data standardization module is also configured to define a uniform data format and field names based on the target data model; The data standardization module is also configured to use a format conversion algorithm to convert track geometry parameters, catenary voltage, and suspension status data into a format supported by the target data model; The data standardization module is also configured to establish the correspondence between the original data fields and the target data model fields for the field mapping algorithm, store the format-converted and field-mapped data in a temporary buffer, and verify the accuracy of the data conversion through a consistency check algorithm.

5. The unified management system for multi-source heterogeneous data of railway facilities as described in claim 1, characterized in that, The verification module determines whether the conditions for accurate data integration are met based on the deviation. This includes: The verification module is also configured to calculate the relative deviation between the standardized orbital geometry parameters and the target data model; The verification module is also configured to calculate the relative deviation between the standardized contact network voltage and the target data model; The verification module is also configured to calculate the absolute deviation between the standardized suspension state and the target data model; The verification module is also configured to compare the relative deviation of the track geometry parameters with a preset track synchronization threshold to generate a track synchronization mark; The verification module is also configured to compare the relative deviation of the contact network voltage with a preset voltage synchronization threshold to generate a voltage synchronization mark; The verification module is also configured to compare the absolute deviation of the suspension state with a preset suspension state synchronization threshold to generate a suspension state synchronization mark. The verification module is also configured to aggregate track synchronization markers, voltage synchronization markers, and suspension state synchronization markers based on configured AND logic rules, wherein: If the aggregation result is true, then the conditions for precise data integration are met.

6. The unified management system for multi-source heterogeneous data of railway facilities as described in claim 1, characterized in that, After data storage is complete, the analysis module performs in-depth data mining and trend analysis to generate equipment status assessment reports and fault early warning information, including: The analysis module is also configured to retrieve historical data on track geometry parameters, overhead contact line voltage, and suspension status based on a distributed database query interface; The analysis module is also configured to model the changing trends of orbital geometric parameters based on time series analysis algorithms to predict future orbital states; The analysis module is also configured to analyze the fluctuations in the overhead contact line voltage based on statistical analysis algorithms to identify potential abnormal patterns; The analysis module is also configured to classify historical records of suspended states based on machine learning algorithms to generate fault warning models.

7. The unified management system for multi-source heterogeneous data of railway facilities as described in claim 6, characterized in that, The analysis module is also configured to combine track maintenance plans, power supply monitoring requirements, and overhead contact line maintenance strategies, and determine the optimal equipment maintenance cycle through optimization algorithms. The optimal equipment maintenance cycle includes the optimal maintenance time and maintenance priority, and the adjustment instructions are sent to the operation and maintenance management system.

8. The unified management system for multi-source heterogeneous data of railway facilities as described in claim 1, characterized in that, When the fault diagnosis module determines that data storage has failed, it includes: The fault diagnosis module is also configured to disconnect the distributed database from the central processing unit, causing the data to roll back to a temporary buffer. The fault diagnosis module is also configured to perform internal fault diagnosis and isolation of the distributed database and generate fault reports; The fault diagnosis module is also configured to automatically or manually attempt to re-execute the data storage procedure based on the fault type.

9. The unified management system for multi-source heterogeneous data of railway facilities as described in claim 2, characterized in that, The data acquisition module is also configured to transmit the raw data from the track inspection system, the overhead contact line inspection system, and the power supply monitoring system to the central processing unit via a high-speed communication interface, and to filter, denoise, and impute missing data in the data to construct a unified raw dataset.

Images