Subway equipment alarm system based on operation parameter analysis

Abstract

The invention discloses a subway equipment alarm system based on operation parameter analysis. The system comprises a server and a client, wherein the server is composed of a data cleaning / classifying module, a rule engine anomaly sensing module, an algorithm analysis module and a data storage module, and the client is composed of a visual display and interaction module. The system has the characteristics of high real-time performance, high intelligence, full-process tracking, reduced maintenance cost and the like; by identifying the potential fault in advance, the equipment damage risk is reduced, the service life of the equipment is prolonged, and the fault detection efficiency is improved. It is ensured that exceptions of different degrees can be responded in a targeted mode, and resource allocation is optimized; an artificial intelligence algorithm and historical data are combined to optimize alarm rules, so that false alarms and missing alarms are remarkably reduced; closed-loop management from alarm triggering to problem solving is supported, and it is ensured that equipment faults are thoroughly processed.

Description

Technical Field

[0001] The invention relates to the field of rail transit equipment safety monitoring, and in particular to a subway equipment alarm system based on operation parameter analysis. Background Art

[0002] As the scale of rail transit systems continues to expand, the types and quantity of subway equipment have increased significantly, and their operating conditions play a vital role in the safety and efficient operation of subways. However, the traditional operation and maintenance model mainly relies on manual inspections and regular maintenance, which is inefficient, difficult to detect potential faults in a timely manner, and the maintenance cost remains high. In addition, the existing system has the following shortcomings: 1. Isolated data collection: There is a lack of coordination between subway equipment subsystems (subsystems include transmission system, public telephone system, private telephone system, broadcasting system, clock system, video surveillance system, passenger information system, centralized recording system, and power supply system). Data collection independence is poor, forming an "information island" and limiting the overall perception of the equipment status.

[0003] 2. Response delay: The alarm is triggered with a delay after a fault occurs, making it difficult to take effective response measures in a timely manner.

[0004] 3. Lack of preventive optimization: The existing system lacks trend analysis and alarm rule optimization based on historical data, making it difficult to effectively prevent equipment failures. Summary of the invention

[0005] In view of the problems existing in the above-mentioned prior art, the present invention provides a subway equipment alarm system based on operation parameter analysis. This system is used for intelligent subway equipment, and performs real-time analysis based on the operation parameters reported by the subway equipment subsystem, and combines historical trend data with artificial intelligence algorithms to quickly identify abnormal conditions, significantly improving the safety assurance capability of subway equipment.

[0006] The technical solution adopted by the present invention is: a subway equipment alarm system based on operation parameter analysis includes a server composed of a data cleaning / classification module, a rule engine abnormality perception module, an algorithm analysis module, and a data storage module, and a client composed of a visualization display and interaction module; the server is bidirectionally connected to the client; the server is connected to the subway equipment subsystem and contains a data processing program; the data cleaning / classification module is connected to the rule engine abnormality perception module, the rule engine abnormality perception module is connected to the algorithm analysis module, and the algorithm analysis module is connected to the data storage module.

[0007] The data processing program flow performs the following operations: 1. The subway equipment subsystem uploads the equipment operation parameter data to the data cleaning / classification module for processing to ensure the accuracy and reliability of subsequent analysis.

[0008] 2. The processed equipment operation parameter data is then passed to the rule engine anomaly perception module.

[0009] 3. The rule engine anomaly perception module customizes different rules and issues alarms based on different device operating parameters.

[0010] 4. If the rule engine abnormality perception module determines that the equipment operation parameter data triggers the alarm rule, an alarm prompt will be immediately generated in the client's visual display and interaction module.

[0011] 5. If the rule engine abnormality perception module determines that the equipment operation parameter data does not trigger the alarm rule, the equipment operation parameter data is passed to the algorithm analysis module.

[0012] 6. The algorithm analysis module combines artificial intelligence algorithms to further analyze the potential anomalies marked by the rule engine on the equipment operation parameter data uploaded by the subway equipment subsystem to identify whether the abnormal algorithm is hit and determine the trend or complexity of the anomaly.

[0013] 7. If the algorithm analysis module determines that the equipment operation parameter data uploaded by the subway equipment subsystem is abnormal in trend or complexity, it returns to step 4, and the client's visualization display and interaction module generates an alarm prompt.

[0014] 8. If the algorithm analysis module determines that the equipment operation parameter data uploaded by the subway equipment subsystem is not abnormal in trend or complexity, the equipment operation parameter data uploaded by the subway equipment subsystem is saved in the data storage module.

[0015] The beneficial effects produced by the present invention are: 1. This system has strong real-time performance. The operating parameter data of the subway equipment subsystem equipment is reported in real time and responds within seconds, which improves the efficiency of fault detection.

[0016] 2. High intelligence: Combining artificial intelligence algorithms with historical data to optimize alarm rules, significantly reducing false alarms and missed alarms.

[0017] 3. Reduce maintenance costs: By identifying potential failures in advance, the risk of equipment damage is reduced and the service life of the equipment is extended. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a block diagram of the system composition of the present invention; Figure 2 The data processing flow chart of the system of the present invention. DETAILED DESCRIPTION

[0019] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0020] Reference Figure 1 The system includes a server consisting of a data cleaning / classification module, a rule engine anomaly perception module, an algorithm analysis module, and a data storage module, and a client consisting of a visualization display and interaction module; the server is bidirectionally connected to the client; the server is connected to the subway equipment subsystem and contains a data processing program; the data cleaning / classification module is connected to the rule engine anomaly perception module, the rule engine anomaly perception module is connected to the algorithm analysis module, and the algorithm analysis module is connected to the data storage module.

[0021] The data processing procedure of this system performs the following operations: 1. The subway equipment subsystem uploads the equipment operation parameter data to the data cleaning / classification module for processing to ensure the accuracy and reliability of subsequent analysis. Cleaning processing includes filtering invalid data, removing duplicate data, and completing time series data; classification processing is to classify different types of data according to the set rules and sort out the data that needs to be processed later.

[0022] 2. The processed equipment operation parameter data is then passed to the rule engine anomaly perception module.

[0023] 3. The rule engine anomaly perception module customizes different rules and issues alarms based on different device operating parameters.

[0024] 4. If the rule engine abnormality perception module determines that the equipment operation parameter data triggers the alarm rule, an alarm prompt will be immediately generated in the client's visual display and interaction module.

[0025] 5. If the rule engine abnormality perception module determines that the equipment operation parameter data does not trigger the alarm rule, the equipment operation parameter data is passed to the algorithm analysis module.

[0026] 6. The algorithm analysis module combines artificial intelligence algorithms to further analyze the potential anomalies marked by the rule engine on the equipment operation parameter data uploaded by the subway equipment subsystem to identify whether the abnormal algorithm is hit and determine the trend or complexity of the anomaly.

[0027] 7. If the algorithm analysis module determines that the equipment operation parameter data uploaded by the subway equipment subsystem is abnormal in trend or complexity, it returns to step 4, and the client's visualization display and interaction module generates an alarm prompt.

[0028] 8. If the algorithm analysis module determines that the equipment operation parameter data uploaded by the subway equipment subsystem is not abnormal in trend or complexity, the equipment operation parameter data uploaded by the subway equipment subsystem is saved to the data storage module for query.

[0029] The stored data includes: all equipment operating parameters, analysis results, alarm records, historical data trends and other basic data reported by the subway equipment subsystem.

[0030] Commonly used classification algorithms include identifying abnormality types (transient abnormalities, continuous abnormalities, etc.). Common prediction algorithms include predicting possible equipment failure trends based on historical data (such as LSTM deep learning models). Input abnormal events marked by the rule engine, and combine historical data with real-time data to determine the abnormality type.

[0031] The operation and maintenance personnel can observe the alarm data of the subway equipment subsystem in real time through the visual display and interaction module at the terminal, which is convenient for the management and maintenance personnel to deal with equipment problems more promptly. In addition, the visual display and interaction module can also perform visual management of basic data, such as: lines, stations, subway equipment subsystems, computer rooms, cabinets and other data, and can also display the operation status of subway equipment subsystems, real-time alarm information and alarm history data trends.

Claims

1. A subway equipment alarm system based on operation parameter analysis, characterized in that: The system includes a server consisting of a data cleaning / classification module, a rule engine anomaly perception module, an algorithm analysis module, and a data storage module, and a client consisting of a visualization display and interaction module; The server is bidirectionally connected to the client; the server is connected to the subway equipment subsystem and contains a data processing program; the data cleaning / classification module is connected to the rule engine anomaly perception module, the rule engine anomaly perception module is connected to the algorithm analysis module, and the algorithm analysis module is connected to the data storage module.

2. A subway equipment alarm system based on operation parameter analysis according to claim 1, characterized in that: The data processing program flow performs the following operations:

1. The subway equipment subsystem uploads the equipment operation parameter data to the data cleaning / classification module for processing to ensure the accuracy and reliability of subsequent analysis; 2. The processed equipment operation parameter data is then passed to the rule engine anomaly perception module; 3. The rule engine anomaly perception module customizes different rules based on different equipment operating parameters to issue alarms; 4. If the rule engine abnormality perception module determines that the equipment operation parameter data triggers the alarm rule, an alarm prompt will be immediately generated in the client's visual display and interaction module; 5. If the rule engine abnormality perception module determines that the equipment operation parameter data does not trigger the alarm rule, the equipment operation parameter data is passed to the algorithm analysis module; 6. The algorithm analysis module combines artificial intelligence algorithms to further analyze the potential anomalies marked by the rule engine on the equipment operation parameter data uploaded by the subway equipment subsystem to identify whether the abnormal algorithm is hit and determine the trend or complexity anomalies; 7. If the algorithm analysis module determines that the equipment operation parameter data uploaded by the subway equipment subsystem is abnormal in trend or complexity, it returns to step 4, and the client's visualization display and interaction module generates an alarm prompt; 8. If the algorithm analysis module determines that the equipment operation parameter data uploaded by the subway equipment subsystem is not abnormal in trend or complexity, the equipment operation parameter data uploaded by the subway equipment subsystem is saved to the data storage module for query.

Images