Intelligent monitoring and predicting system for rail transit equipment based on SNMP (Simple Network Management Protocol)

Abstract

The invention discloses an intelligent monitoring and predicting system for rail transit equipment based on an SNMP (Simple Network Management Protocol), which relates to the technical field of urban rail transit and comprises the rail transit equipment, a network transmission module and a central server, the rail transit equipment is a data source and provides multi-dimensional information, the network transmission module is used for establishing connection between the equipment and the central server, and the central server comprises a data acquisition module, a data processing module, a data storage module, a data prediction module, a topology drawing module and an information display module; scientific basis is provided for maintenance and management of the rail transit equipment, managers are helped to formulate reasonable maintenance plans in advance, excessive maintenance or insufficient maintenance is avoided, the maintenance cost is reduced, and the availability and reliability of the equipment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of urban rail transit, and in particular to a monitoring and prediction system for subway rail transit equipment. Background Art

[0002] With the rapid development of rail transit, ensuring its safe and efficient operation is crucial. Rail transit equipment is diverse, complex, and operates at high intensity for extended periods. Failure to promptly troubleshoot equipment failures can lead to serious safety incidents and operational delays.

[0003] Traditional rail transit equipment monitoring methods mainly rely on manual inspections and simple sensor monitoring, which can only obtain data of a single dimension of the equipment, cannot fully reflect the operating status of the equipment, and lack a global perception of the multi-dimensional operating status of the equipment.

[0004] Currently, subway equipment is diverse, with different manufacturers using different communication protocols. This makes data integration and unified management difficult, and there's a lack of effective data sharing and collaboration between systems, leading to high maintenance costs. Furthermore, existing systems can only monitor the current operating status of equipment, making it difficult to intelligently predict its operating status and identify potential faults.

[0005] In order to reduce communication protocols, lower design and implementation costs, and realize overall intelligent monitoring and prediction of rail transit equipment, an intelligent monitoring and prediction system for rail transit equipment based on SNMP protocol is urgently needed. Summary of the Invention

[0006] Based on this, it is necessary to provide an intelligent monitoring and prediction system for rail transit equipment based on the SNMP protocol to address the above technical problems.

[0007] The present invention provides a rail transit equipment intelligent monitoring and prediction system based on SNMP protocol, which includes rail transit equipment, a network transmission module and a central server; the rail transit equipment is used to work at each station and is the carrier of information.

[0008] The network transmission module is used to establish connections and information exchange between the central server and rail transit equipment.

[0009] The central server includes data acquisition, data processing, data storage, data prediction, topology drawing and information display modules.

[0010] Furthermore, the rail transit equipment includes platform doors (PSD), speakers, display screens, workstations and other stations, which are carriers of multi-dimensional information and send multi-dimensional data information such as the name, temperature, humidity, current and operating status of the equipment to the central server.

[0011] Furthermore, the network transmission module is used to establish a connection and information exchange between the central server and rail transit equipment. During the data information transmission process, SNMP encryption technology is used to ensure the security and integrity of the data.

[0012] Furthermore, the central server includes modules for data collection, data processing, data storage, data prediction, topology drawing and information display: The data acquisition module is used to obtain multi-dimensional data information such as the name, temperature, humidity, current and operating status of rail transit equipment; The data processing module is used to perform format conversion and division processing on the information set obtained by the data acquisition module; The data storage module is used to store the collected and processed multi-dimensional data information and status prediction information of rail transit equipment; The data prediction module is used to predict the operating status of the equipment within a period of time in the future; The topology drawing module is used to draw a topology map according to the distribution of rail transit equipment, and configure the drawn topology to be associated with the actual rail transit equipment; The information display module is used to display detailed information and real-time and predicted status of rail transit equipment.

[0013] Furthermore, the data acquisition module is used to obtain multi-dimensional data information such as the name, temperature, humidity, current and operating status of rail transit equipment, including: Establish a connection with rail transit equipment through the network transmission module, and different devices need to perform corresponding SNMP protocol configuration.

[0014] The SNMP protocol interface program sends requests to the specified device parameters at preset time intervals, parses the collected data according to the returned data format and the meaning of the device information, and realizes standardized data output.

[0015] Furthermore, the data processing module is used to convert and divide the format of the information set obtained by the data acquisition module, including: establishing an equipment information data set, classifying and indexing the acquired information such as temperature, humidity, current and operating status; according to a pre-defined range, marking the collected temperature into three intervals of low temperature, medium temperature and high temperature, marking the humidity into three intervals of low humidity, medium humidity and high humidity, and marking the current into three intervals of low current, medium current and high current.

[0016] Furthermore, the data storage module is used to store the collected and processed multi-dimensional data information and status prediction information of the rail transit equipment, including: the collected information data and the processed information data are stored in different tables of the distributed database respectively. The distributed storage architecture can improve the storage capacity and read and write efficiency of the data, and meet the storage needs of large amounts of data of rail transit equipment.

[0017] Recent information data is stored in high-speed storage media for quick query and analysis, while historical information data is stored in large-capacity, low-cost storage media for long-term data mining and analysis.

[0018] Furthermore, the data prediction module is used to predict the change trend of the operating status of the equipment in the future period, including: The HMM model is trained based on the historical data set of the data storage module, and the optimal prediction model is obtained through training and iteration.

[0019] The currently acquired multivariate equipment information is processed by the data module and input into the trained model, and combined with the Viterbi algorithm to predict the equipment's operating status change trend in the future.

[0020] By continuously learning and training historical data and real-time data, model parameters are optimized and prediction accuracy is improved.

[0021] Furthermore, the topology drawing module draws a topology map according to the distribution of rail transit equipment and configures the drawn topology to correspond to the actual rail transit equipment, including: Drag the corresponding device icon on the right side of the system interface to draw the device topology diagram according to the actual equipment situation on site.

[0022] Connect each graphic element according to the actual connection status of the on-site equipment, and configure the graphic elements in the interface to associate with the on-site equipment.

[0023] Furthermore, the information display module is used to display the real-time information and forecast information of rail transit equipment, including: The system reads the real-time information and predicted information of rail transit equipment stored in the data storage module in real time. When the mouse moves to a certain graphic element on the interface, the real-time information of the equipment and the predicted information for a period of time in the future are displayed.

[0024] When the real-time or predicted status of the equipment is normal operation, the element connection line will be displayed in green on the interface; when the real-time or predicted status of the equipment is a minor fault, the element connection line will be displayed in yellow; when the real-time or predicted status of the equipment is a serious fault, the element connection line will be displayed in red and the system will issue an alarm message; Compared to existing technologies, this invention provides an intelligent monitoring and prediction system for rail transit equipment based on the SNMP protocol. This system comprehensively and accurately reflects the operating status of equipment and intelligently integrates all equipment information, overcoming the limitations of traditional monitoring methods, which suffer from single data and complex protocols. It uses deep learning algorithms for intelligent analysis and prediction, predicting equipment operating status in advance, allowing operators to take maintenance measures with sufficient time. The system interface intuitively displays the connections between rail transit equipment, as well as detailed information, real-time status, and predicted status, providing strong support for equipment maintenance and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 The present invention is based on the SNMP protocol and is an intelligent monitoring and prediction system for rail transit equipment.

[0026] Figure 2 This is a diagram showing the original interface of an intelligent monitoring and prediction system for rail transit equipment based on the SNMP protocol according to an embodiment of the present invention.

[0027] Figure 3 This is a device topology interface display diagram drawn by a rail transit equipment intelligent monitoring and prediction system based on the SNMP protocol according to an embodiment of the present invention.

[0028] Figure 4 This is an interface display diagram of an intelligent monitoring and prediction system for rail transit equipment based on the SNMP protocol according to an embodiment of the present invention when the real-time and predicted status of the equipment is normal operation.

[0029] Figure 5 This is an interface display diagram of an intelligent monitoring and prediction system for rail transit equipment based on the SNMP protocol according to an embodiment of the present invention when the real-time or predicted status of the equipment is a minor fault.

[0030] Figure 6 This is an interface display diagram of an intelligent monitoring and prediction system for rail transit equipment based on the SNMP protocol according to an embodiment of the present invention when the real-time or predicted status of the equipment is a serious fault. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0032] See also Figures 1-6 , provides an intelligent monitoring and prediction system for rail transit equipment based on the SNMP protocol, which includes: rail transit equipment, network transmission module and central server.

[0033] Among them, rail transit equipment is a multi-dimensional information carrier, which is used to send multi-dimensional data information such as the name, temperature, humidity, current and operating status of the equipment to the central server.

[0034] In the description of this invention, rail transit equipment includes professional equipment such as ATS (Automatic Train Monitoring System), ISCS (Integrated Monitoring System), PSD (Platform Screen Door), ACS (Access Control System), as well as workstations and servers at the center and each station.

[0035] The network transmission module is used to establish a connection and information exchange between the central server and rail transit equipment. Data is transmitted to the central server through the network transmission module. During the data information transmission process, SNMP encryption technology is used to ensure data security and integrity.

[0036] In the description of the present invention, the network transmission module includes a switch, which is used to build a control center server and rail transit equipment to the communication backbone network.

[0037] The central server includes: a data acquisition module, a data processing module, a data storage module, a data prediction module, a topology drawing module and an information display module.

[0038] Among them, the data acquisition module is used to obtain multi-dimensional data information such as the name, temperature, humidity, current and operating status of rail transit equipment.

[0039] In the description of the present invention, the process of obtaining multi-dimensional data information of rail transit equipment includes: using the SNMP protocol interface program to send SNMP GETBULK requests to specified equipment parameters at preset time intervals, and professional equipment such as ATS (automatic train monitoring system), ISCS (integrated monitoring system), PSD (screen screen door), ACS (access control system) and servers and workstations reply to the central server with relevant equipment information according to the request parameters.

[0040] The interface program parses the collected data according to the returned data format and the meaning of the device information. If there is an obvious mismatch between the parsed data and the actual theoretical data, the program automatically discards the data to achieve standardized data output.

[0041] The data processing module is used to convert and divide the information set obtained by the data acquisition module.

[0042] In the description of the present invention, the process of converting and dividing the information set includes: establishing a device information data set, classifying and indexing the acquired information such as temperature, humidity, current and operating status.

[0043] The collected temperature is marked as low temperature, medium temperature and high temperature according to the pre-set temperature range; the humidity is marked as low humidity, medium humidity and high humidity according to the pre-set humidity range; the current is marked as low current, medium current and high current according to the pre-set current range.

[0044] The data storage module is used to store the collected and processed multi-dimensional data information and status prediction information of rail transit equipment.

[0045] In this description, the process of storing collected and processed multidimensional data and status prediction information about rail transit equipment in a data storage module includes: The system establishes a connection with a MySQL database and creates tables to store the corresponding device information. The interface then writes the collected and processed information features to the corresponding tables.

[0046] Specifically, the real-time collected information data is stored in the real-time monitoring information table of the distributed database, the processed information data is stored in the processed data information table of the distributed database, and the historical data is stored in the historical information data table. The distributed storage architecture can improve the storage capacity and read and write efficiency of the data, and meet the storage needs of large amounts of data for rail transit equipment.

[0047] Recent information data is stored in high-speed storage media for quick query and analysis, while historical information data is stored in large-capacity, low-cost storage media for long-term data mining and analysis.

[0048] The data prediction module is used to predict the changing trend of the equipment's operating status in the future.

[0049] In the description of the present invention, the method and process for predicting the changing trend of the operating status of the equipment in the future period includes: the data acquisition module collects the temperature of the track equipment at a fixed time interval ,humidity , and current and operating status , after being processed by the data processing module, an observation sequence is formed ,in is the number of observations, determined by the combination of temperature, humidity, and current. The device state set is represented by ,in is the number of device states. In this system, the devices are divided into three states: normal, minor fault, and major fault. The initial state probability distribution of the device ,in , indicating that at the initial moment it is in state The probability of the state transition matrix ,in , indicating that Always in the state Under the condition of Transfer to state The probability of observation. ,in, , indicating that Always in In this state, it is observed probability.

[0050] initialization 、 and , define the forward probability , its recursive formula is: , Defining backward probability , its recursive formula is: , calculate , which means Always in the state and Always in the state The posterior probability of .

[0051] Update Model parameters until convergence.

[0052] The acquired historical multi-device information is processed by the data module and input into the trained model, and the Viterbi algorithm is used to find the most likely current hidden state sequence. , recursive formula: , Indicates Always in the state And observed The maximum probability, Recording moments in On the path with maximum probability The state when. ,in is the maximum probability corresponding to the entire observation sequence, , It's the last moment status.

[0053] According to the most likely hidden sequence state obtained, combined with the state transfer matrix It can predict the changing trend of the equipment's operating status in the future. The status is ,but In state The probability is: ; By iterating this process, the state of the future is predicted. Historical data and real-time data are continuously learned and trained to optimize model parameters and improve prediction accuracy.

[0054] The topology drawing module is used to draw a topology map based on the actual distribution of rail transit equipment, and configure it to associate the drawn topology with the actual rail transit equipment.

[0055] In the description of the present invention, the topology diagram is drawn according to the distribution of rail transit equipment, and the configuration includes: like Figure 2 As shown, use the left button of the mouse to click the device icon on the right side of the system interface and hold down the left button to drag it to the interface on the left. Release the left button of the mouse to drop the icon. The icon dragged to the left interface must correspond to the actual equipment on site.

[0056] Connect the graphics elements in the left interface according to the actual connection between the on-site equipment. Move the mouse to the focus of the graphics element, hold down the left mouse button to draw lines to establish connections between the graphics elements.

[0057] Right-click the equipment element and enter the name and communication address of the equipment in the pop-up dialog box to associate the element with the actual rail transit equipment.

[0058] After drawing and configuring, click the Save button on the upper left corner of the system interface to save the drawn device topology diagram. Figure 3 The figure shows the completed track equipment topology diagram.

[0059] The information display module is used to display real-time information and forecast information of rail transit equipment.

[0060] In the description of the present invention, the information display module is used to display the real-time information and forecast information of rail transit equipment, including: like Figure 4 As shown, hover your mouse over the device you want to view information about. The interface displays detailed information about the device, including its name, temperature, humidity, operating status, and forecast information. When the connection line in the interface is green, the device is operating normally and will likely operate normally in the future.

[0061] like Figure 5As shown, when the connection line in the interface is yellow, it means that the equipment may be in a minor fault state at present or in the future. The equipment needs to be inspected to prevent the equipment failure from affecting subway operations.

[0062] like Figure 6 As shown, when the connection line in the interface is red, it means that the device is currently or will be in a fault state in the future. The system will record the time when the device fails and sound an alarm to remind maintenance personnel to deal with the equipment failure immediately.

[0063] In summary, the proposed SNMP-based intelligent monitoring and prediction system for rail transit equipment integrates multiple key modules, including data acquisition, data processing, data storage, data prediction, topology mapping, and information display. By innovatively utilizing the SNMP protocol to achieve standardized data collection and combining the HMM model and Viterbi algorithm to achieve highly accurate predictions of equipment operating status, this system overcomes many of the shortcomings of traditional rail transit equipment monitoring systems in terms of data acquisition, analysis, and application.

[0064] The present invention can not only grasp the operating status of rail transit equipment in real time, comprehensively and accurately, but also predict potential failures in advance, providing a scientific and reliable decision-making basis for equipment maintenance and management.

[0065] As described above, although the present invention has been shown and described with reference to certain preferred embodiments, it is not to be construed as limiting the invention itself, and various changes in form and details may be made thereto without departing from the spirit and scope of the invention as defined in the appended claims.

Claims

1. An intelligent monitoring and prediction system for rail transit equipment based on SNMP protocol, characterized in that: include: Rail transit equipment, network transmission modules and central servers: The rail transit equipment is used to operate at each station and is a carrier of information; The network transmission module is used to establish a connection and information exchange between the central server and rail transit equipment; The central server includes a data acquisition module, a data processing module, a data storage module, a data prediction module, a topology drawing and information display module.

2. The intelligent monitoring and prediction system for rail transit equipment based on the SNMP protocol according to claim 1, characterized in that: The data acquisition module is used to obtain multi-dimensional data information of rail transit equipment; The data processing module is used to convert and divide the multidimensional data information set obtained by the data acquisition module; The data storage module is used to store the collected and processed multi-dimensional data information of the device; The data prediction module is used to predict the state sequence of rail transit equipment in the future; The topology drawing module is used to draw a topology map according to the distribution of rail transit equipment, and configure the drawn topology to be associated with the actual rail transit equipment; The information display module is used to display detailed information and real-time predicted status of rail transit equipment.

3. The intelligent monitoring and prediction system for rail transit equipment based on SNMP protocol according to claim 2, characterized in that: The data acquisition module is used to obtain the name, temperature, humidity, current and operating status data information of rail transit equipment, including: Establish a connection with rail transit equipment through the network transmission module. Different devices need to be configured with the corresponding SNMP protocol. The SNMP protocol interface program sends SNMP GETBULK requests to the specified device parameters at preset time intervals. The automatic train monitoring system ATS, integrated monitoring system ISCS, platform shielded door PSD and access control system ACS devices and servers, and workstations reply to the central server with relevant device information based on the request parameters. The SNMP protocol interface program parses the collected data based on the returned data format and the meaning of the device information. If there is an obvious mismatch between the parsed data and the actual theoretical data, the program automatically discards the data.

4. The intelligent monitoring and prediction system for rail transit equipment based on SNMP protocol according to claim 2, characterized in that: The data processing module is used to convert and divide the information set obtained by the data acquisition module into a format, and the process includes: Establish a device information data set, classify and index the acquired temperature, humidity, current and operating status information; According to the pre-defined range, the collected temperature is marked as low temperature, medium temperature and high temperature; the humidity is marked as low humidity, medium humidity and high humidity; the current is marked as low current, medium current and high current.

5. The intelligent monitoring and prediction system for rail transit equipment based on SNMP protocol according to claim 2 is characterized in that: The data storage module is used to store the collected and processed multi-dimensional data information of the device, including: The system establishes a connection with the MySQL database and creates tables to store device information. The interface writes the collected and processed information features to the corresponding tables. Specifically, the real-time collected information data is stored in the real-time monitoring information table of the distributed database, the processed information data is stored in the processed data information table of the distributed database, and the historical data is stored in the historical information data table; Recent information data is stored in high-speed storage media, and historical information data is stored in large-capacity, low-cost storage media.

6. The intelligent monitoring and prediction system for rail transit equipment based on SNMP protocol according to claim 2, characterized in that: The data prediction module is used to predict the change trend of the operating status of the equipment in the future period, including: Train the HMM model based on the historical data set of the data storage module, and obtain the optimal prediction model through training and iteration; The currently acquired multi-device information is processed by the data module and input into the trained model, and the Viterbi algorithm is used to predict the operating status of the device in the future. By continuously learning and training historical data and real-time data, model parameters are optimized and prediction accuracy is improved.

7. The intelligent monitoring and prediction system for rail transit equipment based on SNMP protocol according to claim 2, characterized in that: The data prediction module is used to predict the change trend of the operating status of the equipment in the future period, including: Train the HMM model based on the historical data set of the data storage module, and obtain the optimal prediction model through training and iteration; The currently acquired multi-device information is processed by the data module and input into the trained model, and the Viterbi algorithm is used to predict the operating status of the device in the future. By continuously learning and training historical data and real-time data, the model parameters are optimized and the prediction accuracy is improved. ,humidity , current and operating status , after being processed by the data processing module, an observation sequence is formed ,in is the number of observations, determined by the combination of temperature, humidity and current; the device state set is expressed as ,in is the number of device states. In this system, devices are divided into three states: normal, minor fault, and major fault; Probability distribution of the device's initial state ,in , indicating that at the initial moment it is in state The probability of state transition matrix ,in , indicating that Always in the state Under the condition of probability; Observation probability matrix ,in, , indicating that Always in In this state, it is observed The probability of initialization 、 and , define the forward probability , its recursive formula is: ， Defining backward probability , its recursive formula is: ， calculate , which means Always in the state and Always in the state The posterior probability of Update Model parameters until convergence; The acquired historical multi-device information is processed by the data module and input into the trained model, and the Viterbi algorithm is used to find the most likely current hidden state sequence. , recursive formula: ， Indicates Always in the state And observed The maximum probability, Recording moments in On the path with maximum probability The state when ,in is the maximum probability corresponding to the entire observation sequence, , It's the last moment Status; According to the most likely hidden sequence state obtained, combined with the state transfer matrix Ability to predict the changing trend of the equipment's operating status in the future; knowing the current time The status is ,but In state The probability is: , predict the state of the future time by iterating this process; continuously learn and train historical data and real-time data to optimize model parameters.

8. The intelligent monitoring and prediction system for rail transit equipment based on SNMP protocol according to claim 2 is characterized in that: The topology drawing module draws a topology map according to the distribution of rail transit equipment and configures the topology drawn to be associated with the actual rail transit equipment, including: Drag the corresponding device icon on the right side of the system interface to draw the device topology diagram according to the actual device distribution on site; Establish connections between each device graphic element according to the actual connection status of the on-site equipment, and configure the graphic elements in the interface to associate with the on-site equipment.

9. The intelligent monitoring and prediction system for rail transit equipment based on SNMP protocol according to claim 2, characterized in that: The information display module is used to display detailed information and real-time and predicted status of rail transit equipment, including: The system reads the real-time information and forecast information of rail transit equipment stored in the data storage module in real time. When the mouse moves over a certain element on the interface, the real-time information of the equipment and the forecast information for a period of time in the future are displayed; When the real-time or predicted status of the equipment is normal operation, the graphic element connection line is displayed in green on the interface; when the real-time or predicted status of the equipment is a minor fault, the graphic element connection line is displayed in yellow; when the real-time or predicted status of the equipment is a serious fault, the graphic element connection line is displayed in red and the system issues an alarm message.

Images