Intelligent and efficient railway signal centralized monitoring and maintenance system

Abstract

The invention is suitable for the technical field of railway safety, and provides an intelligent and efficient railway signal centralized monitoring and maintenance system, a maintenance platform comprises a three-level networking architecture, and the three-level networking architecture comprises a national railway group level monitoring operation and maintenance subsystem, a bureau group company level monitoring operation and maintenance subsystem and a station level monitoring operation and maintenance subsystem. The national railway group level monitoring operation and maintenance subsystem deploys an active-active data center; the bureau group company-level monitoring operation and maintenance subsystem is configured with a dual-computer hot standby server cluster and comprises an acquisition and analysis unit, an application server and a database server; the station-level monitoring operation and maintenance subsystem is integrated with an edge computing node; the three stages are interconnected through a data communication network; according to the comprehensive maintenance platform of the railway signal centralized monitoring system, an integrated, intelligent and efficient operation and maintenance management system is constructed, comprehensive monitoring and precise maintenance of the railway signal system are achieved through the functions of real-time monitoring, fault early warning, intelligent diagnosis, decision support and the like, safe and stable operation of the railway signal system is ensured, and the service life of the railway signal system is prolonged. And the overall efficiency and service quality of railway operation are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of railway safety, and in particular relates to an intelligent and efficient railway signal centralized monitoring and maintenance system. Background Art

[0002] Railway signaling equipment is a core facility for ensuring operational safety, and its operational status directly impacts the efficiency and safety of railway transportation. Traditional monitoring systems suffer from limited monitoring methods, delayed fault warnings, low data processing efficiency, and high maintenance costs, making them unable to meet the demands of modern railways for efficient and intelligent operation and maintenance. Therefore, the development of a comprehensive monitoring and maintenance system integrating real-time monitoring, intelligent diagnosis, and remote maintenance is of great significance. The existing Centralized Railway Signal Monitoring (CSM) system is a comprehensive monitoring platform for railway signaling equipment maintenance. It plays a vital role in monitoring the operational status of signaling equipment, identifying potential hazards, strengthening the management of signaling equipment interfaces, analyzing faults, and providing on-site repair guidance. It is an indispensable tool for railway signaling maintenance personnel. However, existing intelligent and efficient centralized railway signaling monitoring and maintenance systems lack a multi-level alarm mechanism, unable to prioritize fault severity and ensure that critical hazards are addressed first. Without a multi-level alarm mechanism, the system cannot quickly prioritize faults. This can lead to maintenance personnel spending more time screening and determining the severity of faults, delaying the resolution of critical faults. The extension of fault handling time will directly affect the overall efficiency of the railway signal system, which may lead to longer train running intervals and reduce railway transportation capacity. To solve the above problems, it is necessary to design an intelligent and efficient railway signal centralized monitoring and maintenance system. Summary of the Invention

[0003] The present invention provides an intelligent and efficient railway signal centralized monitoring and maintenance system, aiming to solve the problem that the current railway signal centralized monitoring and maintenance system has no multi-level alarm mechanism and the system cannot quickly distinguish the severity of faults.

[0004] The present invention is implemented as follows: an intelligent and efficient railway signal centralized monitoring and maintenance system includes a three-level monitoring architecture, which includes a national railway group-level monitoring and operation subsystem, a bureau group company-level monitoring and operation subsystem, and a station-level monitoring and operation subsystem. The national railway group-level monitoring and operation subsystem deploys a dual-active data center; the bureau group company-level monitoring and operation subsystem is configured with a dual-machine hot standby server cluster, including communication front-end, application and database servers; the station-level monitoring and operation subsystem integrates edge computing nodes; the three levels are interconnected through a dual-route redundant wide area network; Intelligent monitoring and early warning module: uses LSTM neural network to predict equipment failures; Efficient data processing and storage module: Based on Hadoop distributed architecture, supports PB-level data storage; Innovative network access module: deploying optical acquisition units at the station level to enable non-intrusive monitoring of service optical signals; Full-stack diagnostic engine: Synchronously collects data from the physical layer (BMC), virtualization layer (Hypervisor), transport layer (optical channel), and device layer (serial port); Intelligent maintenance center: integrated configuration version comparison, multi-dimensional traffic analysis, and electronic drawing intelligent verification tools.

[0005] Preferably, the spectroscopic collection unit comprises a three-column optical splitter group, specifically an IN / OUT / MONITOR interface, with a splitting ratio of 1:9, and the monitoring channel accounts for 10%; The MONITOR port is connected to the data link monitoring unit via an ultra-low optical attenuation link (attenuation ≤ 0.5dB); FE board integration of data link monitoring unit: Optical power sensor, optical power sensor sampling frequency ≥ 1Hz, accuracy ±0.1dBm; Transport layer protocol parsing chip, which supports TCP / UDP / ICMP protocol decompression and has a processing rate of ≥10Gbps; Output channel traffic matrix, packet loss rate curve and protocol distribution heat map. Preferably, the intelligent monitoring and early warning module includes an adaptive threshold adjustment unit, a multi-source data fusion unit and an early warning push unit. The adaptive threshold adjustment unit is based on the dynamic calculation of historical data. Calculate the threshold interval; the multi-source data fusion unit integrates multi-dimensional data such as the computer interlocking system status, train control center system status, CTC system status, power panel equipment status, track circuit system status, and switch gap system status; the early warning push unit pushes the fault level (emergency / important / general) to the mobile phone APP, work area terminal, and dispatching large screen in a graded manner.

[0006] Preferably, the efficient data processing and storage module includes: Real-time stream processing unit: uses the Flink engine to process data streams, with window calculation latency ≤ 50ms; Data hierarchical storage unit: Hot data is stored on SSD (retained for 30 days); Warm data is stored on SAS hard disks (retained for 1 year); Cold data is archived to Blu-ray storage (retention for 10 years); Data quality verification unit: ensures data credibility through regular expression matching, range detection, and correlation verification; Traffic tracing engine of the intelligent maintenance center: Generate TOP10 traffic rankings based on session / IP / protocol / port; When a single IP traffic surge exceeds 80% of the baseline value, it is marked as abnormal and automatically associated with NetFlow data to generate a tracing report.

[0007] Preferably, the remote management and maintenance module includes: AR remote assistance unit: Overlays fault location marks and operation instructions through Hololens glasses; Automated test unit: built-in 200+ test cases (including ZPW-2000 track circuit calibration test); Maintenance knowledge base unit: integrates 5,000+ fault cases and supports natural language queries; The system deploys a fault event tree generation algorithm: Input: BMC alarms, virtual machine events, and optical channel anomaly time series data; Output: Root cause path chain (confidence > 95%), such as "optical power attenuation → channel packet loss → station-machine communication timeout".

[0008] Preferably, the innovative network access module further includes: 5G private network unit: uses URLLC slicing (air interface latency ≤ 1ms) to transmit vehicle monitoring data; Network self-healing unit: When the optical fiber is broken, it automatically switches to the microwave link (switching time ≤ 200ms); The spectroscopic acquisition unit is equipped with a dual-channel optical power compensation module: Automatic switching when the optical power difference between the main and backup channels is greater than 3dB; There is zero service interruption during the switching process (using optical switch devices, response time ≤ 10ms).

[0009] Preferably, the transport layer protocol parsing module has a built-in railway-specific protocol feature library, and the electronic drawing version management compares the station version with the drawing library through MD5 hash value; when the verification fails, the drawing editing permission is frozen and a version conflict alarm is pushed to the responsible person's terminal.

[0010] Preferably, it also includes fine-grained permission management, an operation audit unit, and a system self-check engine. The operation audit unit records user login IP, operation instructions, and impact scope, with a storage period of ≥5 years; the system self-check engine scans hardware health (such as disk bad sectors, memory ECC errors) daily and triggers BMC out-of-band alarms in case of abnormalities.

[0011] Preferably, the method further includes monitoring the communication status of the interface with the third-party system: CTC interface: RS422 serial port, synchronized train scheduling plan based on TL1 protocol; Intelligent power panel interface: RS422 serial port, obtains the power panel status through IEC 61850 protocol; Protocol conversion gateway: supports Modbus RTU / TCP and IEC 60870-5-104 protocol conversion; The station-level monitoring and operation subsystem deployment: Edge intelligent terminal: equipped with an AI chip (computing power ≥ 4TOPS) to analyze the turnout current waveform in real time; Self-organizing network communication unit: adopts LoRa+Mesh hybrid networking, with a coverage radius of ≥5km.

[0012] Preferably, the disaster recovery linkage mechanism: When the BMC reports a server downtime, the virtual machine is automatically migrated (migration time ≤ 30 seconds); Mark the faulty device as a red flashing icon in the topology map; Generate migration reports (including resource allocation diagrams and performance impact assessments); The full-stack diagnostic engine is linked to the digital twin and constructs a three-dimensional model of the traffic light to simulate lightning strike / electromagnetic interference failure scenarios; it also outputs an alarm indicating deviations between virtual sensor data and actual monitoring values.

[0013] Compared with related technologies, the intelligent and efficient railway signal centralized monitoring and maintenance system provided by the present invention has the following beneficial effects: The railway signal centralized monitoring and maintenance system proposed in this application improves operation and maintenance efficiency and reliability through a three-level disaster recovery architecture and redundant design. The National Railway Group-level active-active data center, the bureau group company-level dual-machine hot standby cluster, the dual-route wide area network, and the network self-healing function ensure high system availability, with service interruption time approaching zero. The comprehensive maintenance platform for the railway signal centralized monitoring system can build an integrated, intelligent, and efficient operation and maintenance management system. Through real-time monitoring, fault warning, intelligent diagnosis, decision support, and other functions, it can achieve comprehensive monitoring and precise maintenance of the railway signal system, ensure the safe and stable operation of the railway signal system, and improve the overall efficiency and service quality of railway operations.

[0014] Equipment fault prediction is achieved through an LSTM neural network. Multi-source data fusion (such as interlocking status, track circuit voltage, and turnout images) improves fault location accuracy, shifting from passive response to proactive prevention. A full-stack diagnostic engine simultaneously collects data from the physical, virtualization, transport, and device layers. Integrating digital twin technology to build a 3D simulation model supports fault scenario simulation and virtual-to-actual data comparison, enhancing complex fault troubleshooting capabilities. A built-in railway-specific protocol feature library supports conversion between multiple industrial protocols, ensuring compatibility between legacy equipment and new sensors, reducing system upgrade costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a schematic diagram of the four-layer dynamic alarm thresholds of the full-stack diagnostic engine of the present invention; Figure 2 This is a schematic diagram of a railway-specific protocol feature library built into the transport layer protocol parsing module of the present invention; Figure 3 This is a schematic diagram of the fine-grained rights management of the present invention; Figure 4 Schematic diagram of the hierarchical structure of the CSM system of the present invention; Figure 5 Schematic diagram of the three-layer functional structure of the system of the present invention; Figure 6 Schematic diagram of the system software architecture of the present invention. DETAILED DESCRIPTION

[0016] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of the application are only for the purpose of describing specific embodiments and are not intended to limit this application. The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0017] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0018] The preferred embodiment of the intelligent and efficient railway signal centralized monitoring and maintenance system provided by the present invention is as follows: Figures 1 to 6 As shown: An intelligent and efficient centralized railway signal monitoring and maintenance system includes a three-level monitoring architecture, which includes a national railway group-level monitoring and operation subsystem, a bureau group-level monitoring and operation subsystem, and a station-depot-level monitoring and operation subsystem. The national railway group-level monitoring and operation subsystem deploys a dual-active data center; the bureau group-level monitoring and operation subsystem is equipped with a dual-machine hot standby server cluster, including communication front-end, application, and database servers; the station-depot-level monitoring and operation subsystem integrates edge computing nodes; and the three levels are interconnected via a dual-route redundant wide area network. Intelligent monitoring and early warning module: uses LSTM neural network to predict equipment failures; Efficient data processing and storage module: Based on Hadoop distributed architecture, supports PB-level data storage; Innovative network access module: deploying optical acquisition units at the station level to enable non-intrusive monitoring of service optical signals; Full-stack diagnostic engine: Synchronously collects data from the physical layer (BMC), virtualization layer (Hypervisor), transport layer (optical channel), and device layer (serial port); Intelligent maintenance center: integrated configuration version comparison, multi-dimensional traffic analysis, and electronic drawing intelligent verification tools.

[0019] The spectroscopic acquisition unit includes a three-column optical splitter group, specifically IN / OUT / MONITOR interfaces, with a splitting ratio of 1:9, and the monitoring channel accounts for 10%; The MONITOR port is connected to the data link monitoring unit via an ultra-low optical attenuation link (attenuation ≤ 0.5dB); FE board integration of data link monitoring unit: Optical power sensor, optical power sensor sampling frequency ≥ 1Hz, accuracy ±0.1dBm; Transport layer protocol parsing chip, which supports TCP / UDP / ICMP protocol decompression and has a processing rate of ≥10Gbps; Output channel traffic matrix, packet loss rate curve, and protocol distribution heat map.

[0020] The intelligent monitoring and early warning module includes an adaptive threshold adjustment unit, a multi-source data fusion unit and an early warning push unit. The adaptive threshold adjustment unit dynamically calculates the threshold interval based on historical data; the multi-source data fusion unit integrates multi-dimensional data such as the computer interlocking system status, the train control center system status, the CTC system status, the power supply panel equipment status, the track circuit system status, and the switch gap system status; the early warning push unit pushes faults to mobile phone apps, work area terminals, and dispatching screens in a hierarchical manner according to the fault level (emergency / important / general).

[0021] Efficient data processing and storage modules include: Real-time stream processing unit: uses the Flink engine to process data streams, with window calculation latency ≤ 50ms; Data hierarchical storage unit: Hot data is stored on SSD (retained for 30 days); Warm data is stored on SAS hard disks (retained for 1 year); Cold data is archived to Blu-ray storage (retention for 10 years); Data quality verification unit: ensures data credibility through regular expression matching, range detection, and correlation verification; Traffic tracing engine of the intelligent maintenance center: Generate TOP10 traffic rankings based on session / IP / protocol / port; When a single IP traffic surge exceeds 80% of the baseline value, it is marked as abnormal and automatically associated with NetFlow data to generate a tracing report.

[0022] The remote management and maintenance module includes: AR remote assistance unit: Overlays fault location marks and operation instructions through Hololens glasses; Automated test unit: built-in 200+ test cases (including ZPW-2000 track circuit calibration test); Maintenance knowledge base unit: integrates 5,000+ fault cases and supports natural language queries; System deployment fault event tree generation algorithm: Input: BMC alarms, virtual machine events, and optical channel anomaly time series data; Output: Root cause path chain (confidence > 95%), such as "optical power attenuation → channel packet loss → station-machine communication timeout".

[0023] The innovative network access module also includes: 5G private network unit: uses URLLC slicing (air interface latency ≤ 1ms) to transmit vehicle monitoring data; Network self-healing unit: When the optical fiber is broken, it automatically switches to the microwave link (switching time ≤ 200ms); The spectroscopic acquisition unit is equipped with a dual-channel optical power compensation module: Automatic switching when the optical power difference between the main and backup channels is greater than 3dB; There is zero service interruption during the switching process (using optical switch devices, response time ≤ 10ms).

[0024] The transport layer protocol parsing module has a built-in railway-specific protocol feature library. The electronic drawing version management compares the station version with the drawing library through MD5 hash value. If the verification fails, the drawing editing permission is frozen and a version conflict alarm is pushed to the responsible person's terminal.

[0025] It also includes fine-grained permission management, an operation audit unit, and a system self-check engine. The operation audit unit records user login IP, operation instructions, and impact scope, with a storage period of ≥5 years; the system self-check engine scans hardware health (such as disk bad sectors and memory ECC errors) daily and triggers BMC out-of-band alarms in case of abnormalities.

[0026] Also includes third-party system interfaces: CTC interface: synchronizes train scheduling based on TL1 protocol; Power supply system interface: obtain the power supply screen status through the IEC 61850 protocol; Protocol conversion gateway: supports Modbus RTU / TCP and IEC 60870-5-104 protocol conversion; The monitoring and operation system is responsible for monitoring the interface communication status between the signal centralized monitoring system and these third-party systems. The monitoring methods include SNMP collection of RJ45 type interfaces, serial port mirroring to obtain serial port RS422 communication status, and splitter channel data collection and analysis to obtain fiber optic data network channel status.

[0027] Deployment of station-level monitoring and operation subsystem: Edge intelligent terminal: equipped with an AI chip (computing power ≥ 4TOPS) to analyze the turnout current waveform in real time; Self-organizing network communication unit: adopts LoRa+Mesh hybrid networking, with a coverage radius of ≥5km.

[0028] Disaster recovery linkage mechanism: When the BMC reports a server downtime, the virtual machine is automatically migrated (migration time ≤ 30 seconds); Mark the faulty device as a red flashing icon in the topology map; Generate migration reports (including resource allocation diagrams and performance impact assessments); The full-stack diagnostic engine links with the digital twin and builds a three-dimensional model of the traffic light to simulate lightning strike / electromagnetic interference failure scenarios; it also outputs alarms for deviations between virtual sensor data and actual monitoring values.

[0029] In this embodiment, the China Railway Group-level monitoring and operation and maintenance subsystem deploys active-active data centers to achieve load balancing and seamless failover, ensuring business continuity. An integrated big data analysis platform provides macro-level analysis of global equipment status, fault trends, and operation and maintenance efficiency. This supports cross-bureau and group company data sharing and collaborative decision-making, optimizing resource scheduling across the national railway network.

[0030] The bureau's corporate-level monitoring and operations subsystem is equipped with a dual-server hot-standby server cluster, including a redundant communication front-end server, an application server with load balancing, and a database server with master-slave synchronization. This subsystem provides centralized regional equipment monitoring, intelligent diagnosis, maintenance task allocation, and emergency command. It is interconnected with station-level systems via a dual-route redundant wide area network to ensure reliable data transmission.

[0031] The station-level monitoring and maintenance subsystem integrates edge computing nodes, deployed at the station level, to perform data preprocessing, local decision-making, and privacy data filtering. Equipped with an AI chip (computing power ≥ 4TOPS), it supports real-time analysis of key parameters such as turnout current waveforms and track circuit phases. Through a self-organizing communication unit (LoRa + Mesh hybrid networking), it covers equipment in remote areas, ensuring comprehensive monitoring.

[0032] In this embodiment, an LSTM neural network uses historical data to train models for fault prediction and precise early warning, enabling early prediction of equipment failures (such as track circuit failures and switch jams). This transforms passive responses into proactive prevention, reducing unplanned downtime. Adaptive threshold adjustment dynamically calculates equipment parameter thresholds (such as voltage and temperature), avoiding false alarms or missed alarms caused by fixed thresholds and improving early warning accuracy. Multi-source data fusion integrates multi-dimensional data, including computer interlocking system status, train control center system status, CTC system status, power supply panel equipment status, track circuit system status, and switch gap system status, enabling rapid identification of fault root causes (e.g., detecting switch gap violations through image recognition and mechanical jams through current waveform analysis).

[0033] The intelligent maintenance center automatically detects device configuration changes, preventing human error or illegal modification and ensuring system consistency. Intelligent verification of electronic drawings compares drawings and station versions using MD5 hash values, preventing construction accidents caused by drawing errors. The traffic tracing engine quickly locates abnormal traffic (such as an 80% sudden increase in traffic from a single IP address) and generates tracing reports based on NetFlow data, assisting in network attack and troubleshooting.

[0034] A three-level monitoring architecture and redundant design ensure high system reliability and disaster recovery capabilities. The active-active data center (at the China Railway Corporation level) ensures zero service interruption. If the primary center fails, the backup center seamlessly takes over, ensuring uninterrupted global monitoring. A dual-machine hot standby server cluster (at the bureau group company level) features redundant deployment of communication front-end, application, and database servers to avoid single points of failure. The dual-route redundant WAN links are physically isolated, with automatic failover (≤50ms) in the event of a failure, ensuring data transmission reliability. Network self-healing and optical acquisition redundancy combine to automatically switch to microwave links in the event of fiber breaks, with a failover time of ≤200ms, ensuring zero service interruption and adapting to the complex environment along the railway. The optical acquisition unit features dual-channel compensation, with automatic failover (≤10ms) when the optical power difference between the primary and backup channels exceeds 3dB, ensuring monitoring continuity. A disaster recovery linkage mechanism ensures that when the BMC reports a server downtime, virtual machines are migrated to healthy nodes within 30 seconds, ensuring business continuity. Faulty devices are indicated by a flashing red light on the topology map, helping operations personnel quickly locate the problem.

[0035] Real-time stream processing and tiered storage optimize data processing and storage efficiency. By using the Flink engine, window computing latency is ≤50ms, supporting real-time alerts (such as a transient track circuit short circuit) and trend analysis (such as a slow temperature rise in equipment). Tiered data storage allows for 30 days of frequently accessed data, supporting low-latency queries (such as fault history backtracking). One year of data is stored for trend analysis and auditing. Historical data spanning more than 10 years can be archived to meet compliance requirements (such as accident investigations). Regular expressions, range checks, and correlation verification (such as consistency checks between interlocking relationships and track circuit occupancy status) ensure data credibility and prevent misjudgments caused by dirty data.

[0036] AR remote assistance enhances remote collaboration and automation capabilities. By overlaying fault location markers and operational instructions through HoloLens, experts can remotely guide on-site personnel, reducing travel costs and shortening fault repair time (e.g., providing guidance on disassembly and assembly of complex equipment). Over 200 built-in test cases, covering scenarios such as ZPW-2000 track circuit calibration and adjustment testing, automatically generate test reports, and improve acceptance efficiency. A knowledge base of over 5,000 fault cases supports natural language queries (e.g., inputting "no indication for turnout") to quickly recommend solutions and spare parts lists.

[0037] Build a 3D model of a signal light, simulate lightning strike / electromagnetic interference scenarios, and generate alarms indicating deviations between virtual sensor data and actual monitoring values, assisting in the verification of new equipment. Open APIs support integration with third-party systems such as CTC and power supply systems (e.g., synchronizing train scheduling plans via the TL1 protocol), enabling cross-system collaboration. A protocol conversion gateway supports interoperability between Modbus RTU / TCP and IEC60870-5-104 protocols, ensuring compatibility between legacy equipment and new sensors, reducing upgrade costs.

[0038] The railway signal centralized monitoring and maintenance system of this application improves operation and maintenance efficiency and reliability through a three-level disaster recovery architecture and redundant design. The national railway group-level active-active data center, the bureau group company-level dual-machine hot standby cluster, the dual-route wide area network and the network self-healing function (such as automatic switching of microwave links in case of optical fiber breakage) ensure the high availability of the system, and the service interruption time is close to zero.

[0039] Equipment fault prediction is achieved through LSTM neural networks, and multi-source data fusion (such as interlocking status, track circuit voltage, and turnout images) is combined to improve fault location accuracy, achieving a shift from passive response to active prevention.

[0040] The full-stack diagnostic engine simultaneously collects data from the physical, virtualization, transport, and device layers, leveraging digital twin technology to build a 3D simulation model. This supports fault scenario simulation and virtual-to-actual data comparison, enhancing complex troubleshooting capabilities. A built-in railway-specific protocol feature library supports conversion between multiple industrial protocols (such as Modbus and IEC 60870-5-104), enabling compatibility between legacy equipment and new sensors, reducing system upgrade costs.

[0041] AR remote assistance (HoloLens glasses) enables expert remote guidance of on-site operations. The automated testing unit includes over 200 built-in test cases, and the intelligent maintenance center automatically generates configuration change reports, reducing manual intervention and improving O&M efficiency. The traffic tracing engine flags abnormal traffic in real time, and the root cause analysis algorithm (e.g., "optical power attenuation → channel packet loss → station-to-machine communication timeout") outputs a fault path chain with a confidence level greater than 95%, shortening mean time to repair (MTTR).

[0042] Real-time stream processing and tiered storage optimize data processing and storage. The Flink engine achieves 50ms-level low-latency data stream processing and supports real-time alerts. Tiered data storage (SSD / SAS / Blu-ray) categorizes and stores data by popularity, balancing query efficiency and cost. Regular expressions, range checks, and correlation verification (such as consistency checks on interlocking relationships and track circuit status) ensure data credibility and avoid misjudgments caused by dirty data. This reduces manual inspections and downtime losses (for example, predicting track circuit failures in advance to avoid train delays). Automated testing and remote collaboration reduce operation and maintenance costs. Fine-grained permission management and operation auditing (recording user login IP addresses and operation instructions, with a storage period of ≥5 years) prevent illegal operations. The system self-check engine scans hardware health daily and triggers BMC alerts in the event of anomalies to ensure system security.

[0043] It is worth noting that the circuits, electronic components and modules involved in the present invention are all existing technologies and can be fully implemented by those skilled in the art. Needless to say, the content protected by the present invention does not involve improvements to software and methods.

[0044] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be in the form of telecommunications or other forms.

[0045] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the scope of protection of the invention. Obviously, the embodiments described are only some embodiments of the present invention, rather than all embodiments. Based on these embodiments, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in this field can still combine, add, delete or make other adjustments to the features in the various embodiments of the present invention according to the circumstances without conflict, without making creative work, so as to obtain different other technical solutions that do not deviate from the concept of the present invention in essence, and these technical solutions also fall within the scope of protection of the present invention.

Claims

1. An intelligent and efficient railway signal centralized monitoring and maintenance system, characterized by: It includes a three-level monitoring architecture, which includes a national railway group-level monitoring and operation subsystem, a bureau group company-level monitoring and operation subsystem, and a station-level monitoring and operation subsystem. The national railway group-level monitoring and operation subsystem deploys a dual-active data center; the bureau group company-level monitoring and operation subsystem is configured with a dual-machine hot standby server cluster, including collection and analysis units, application servers, and database servers; the station-level monitoring and operation subsystem integrates edge computing nodes; the three levels are interconnected through a dual-redundant data communication network; Intelligent monitoring and early warning module: uses LSTM neural network to predict equipment failures; Efficient data processing and storage module: Based on Hadoop distributed architecture, supports PB-level data storage; Innovative network access module: deploying optical acquisition units at the station level to enable non-intrusive monitoring of service optical signals; Full-stack diagnostic engine: Synchronously collects data from the physical layer (BMC), virtualization layer (Hypervisor), transport layer (optical channel), and device layer (serial port); Intelligent maintenance center: integrated configuration version comparison, multi-dimensional traffic analysis, and electronic drawing intelligent verification tools.

2. The intelligent and efficient railway signal centralized monitoring and maintenance system according to claim 1 is characterized in that: The spectroscopic acquisition unit includes a three-column optical splitter group, specifically IN / OUT / MONITOR interfaces, with a splitting ratio of 1:9, and the monitoring channel accounts for 10%; The MONITOR port is connected to the data link monitoring unit via an ultra-low optical attenuation link (attenuation ≤ 0.5dB); FE board integration of data link monitoring unit: Optical power sensor, optical power sensor sampling frequency ≥ 1Hz, accuracy ±0.1dBm; Transport layer protocol parsing chip, which supports TCP / UDP / ICMP protocol decompression and has a processing rate of ≥10Gbps; Output channel traffic matrix, packet loss rate curve, and protocol distribution heat map.

3. The intelligent and efficient railway signal centralized monitoring and maintenance system according to claim 1 is characterized in that: The intelligent monitoring and early warning module includes an adaptive threshold adjustment unit, a multi-source data fusion unit and an early warning push unit. The adaptive threshold adjustment unit dynamically calculates the threshold interval based on historical data; the multi-source data fusion unit integrates multi-dimensional data such as the computer interlocking system status, the train control center system status, the CTC system status, the power supply panel equipment status, the track circuit system status, and the switch gap system status; the early warning push unit pushes faults to mobile phone APP, work area terminals, and dispatching large screens in a hierarchical manner according to the fault level (emergency / important / general).

4. The intelligent and efficient railway signal centralized monitoring and maintenance system according to claim 1 is characterized in that: The efficient data processing and storage module includes: Real-time stream processing unit: uses the Flink engine to process data streams, with window calculation latency ≤ 50ms; Data hierarchical storage unit: Hot data is stored on SSD (retained for 30 days); Warm data is stored on SAS hard disks (retained for 1 year); Cold data is archived to Blu-ray storage (retention for 10 years); Data quality verification unit: ensures data credibility through regular expression matching, range detection, and correlation verification; Traffic tracing engine of the intelligent maintenance center: Generate TOP10 traffic rankings based on session / IP / protocol / port; When a single IP traffic surge exceeds 80% of the baseline value, it is marked as abnormal and automatically associated with NetFlow data to generate a tracing report.

5. The intelligent and efficient railway signal centralized monitoring and maintenance system according to claim 1 is characterized in that: The remote management and maintenance module includes: AR remote assistance unit: Overlays fault location marks and operation instructions through Hololens glasses; Automated test unit: built-in 200+ test cases (including ZPW-2000 track circuit calibration test); Maintenance knowledge base unit: integrates 5,000+ fault cases and supports natural language queries; The system deploys a fault event tree generation algorithm: Input: BMC alarms, virtual machine events, and optical channel anomaly time series data; Output: Root cause path chain (confidence level > 95%), such as "optical power attenuation → channel packet loss → station-machine communication timeout." 6. The intelligent and efficient railway signal centralized monitoring and maintenance system according to claim 1 is characterized in that: The innovative network access module also includes: 5G private network unit: uses URLLC slicing (air interface latency ≤ 1ms) to transmit vehicle monitoring data; Network self-healing unit: When the optical fiber is broken, it automatically switches to the microwave link (switching time ≤ 200ms); The spectroscopic acquisition unit is equipped with a dual-channel optical power compensation module: Automatic switching when the optical power difference between the main and backup channels is greater than 3dB; There is zero service interruption during the switching process (using optical switch devices, response time ≤ 10ms).

7. The intelligent and efficient railway signal centralized monitoring and maintenance system according to claim 2, characterized in that: The transport layer protocol parsing module has a built-in railway-specific protocol feature library, and the electronic drawing version management compares the station version with the drawing library through MD5 hash value; when the verification fails, the drawing editing permission is frozen and a version conflict alarm is pushed to the responsible person's terminal.

8. The intelligent and efficient railway signal centralized monitoring and maintenance system according to claim 1 is characterized in that: It also includes fine-grained permission management, an operation audit unit, and a system self-check engine. The operation audit unit records user login IP, operation instructions, and impact scope, with a storage period of ≥5 years; the system self-check engine scans hardware health (such as disk bad sectors and memory ECC errors) daily and triggers BMC out-of-band alarms in case of abnormalities.

9. The intelligent and efficient railway signal centralized monitoring and maintenance system according to claim 1, characterized in that: Also includes the interface status with third-party systems: CTC interface: RS422 serial port, synchronized train scheduling plan based on TL1 protocol; Power supply system interface: obtain the power supply screen status through the IEC 61850 protocol; Protocol conversion gateway: supports Modbus RTU / TCP and IEC 60870-5-104 protocol conversion; The station-level monitoring and operation subsystem deployment: Edge intelligent terminal: equipped with an AI chip (computing power ≥ 4TOPS) to analyze the turnout current waveform in real time; Self-organizing network communication unit: adopts LoRa+Mesh hybrid networking, with a coverage radius of ≥5km.

10. The intelligent and efficient railway signal centralized monitoring and maintenance system according to claim 1, characterized in that: The disaster recovery linkage mechanism: When the BMC reports a server downtime, the virtual machine is automatically migrated (migration time ≤ 30 seconds); Mark the faulty device as a red flashing icon in the topology map; Generate migration reports (including resource allocation diagrams and performance impact assessments); The full-stack diagnostic engine is linked to the digital twin and constructs a three-dimensional model of the traffic light to simulate lightning strike / electromagnetic interference failure scenarios; it also outputs an alarm indicating deviations between virtual sensor data and actual monitoring values.

Images