Method and system for intelligent management of line rain and snow mode

Abstract

The application discloses a kind of methods and systems for intelligently managing line snow mode, the method includes: setting up snow mode intelligent management component on the gateway server of train automatic monitoring system, periodically execute: obtain meteorological data and train real-time operation data and other multi-source data;Accordingly, the current environment perception limited index of each section and the current environment perception limited index of each train are calculated;Integrate current index, preset surrounding geographical type index and historical limited index obtained by analyzing historical data, respectively calculate the overall limited level of each section and the overall limited level of each train;According to the overall limited level of section, automatically control section temporary speed limit, according to the overall limited level of train, automatically adjust train traction or braking force.Compared with prior art, the application realizes the automatic, predictive and accurate management of line snow mode by fusing multi-source perception data and using intelligent decision mechanism based on section and train.

Description

Technical Field

[0001] This invention relates to the field of automatic control technology for rail transit trains, and in particular to a method and system for intelligently managing rain and snow patterns on railway lines. Background Technology

[0002] In the rail transit sector, fully automated operation systems, with their unmanned operation, high scheduling precision, and efficient operation capabilities, have become the core direction of modern urban rail transit development. In urban rail fully automated operation systems, severe weather or sudden changes in track environment can cause a decrease in the rail surface adhesion coefficient, potentially leading to train slippage and serious threats to operational safety. To address this, existing signaling systems employ intelligent protection by triggering rain and snow modes. Currently, various signaling system suppliers have proposed multiple technical solutions for implementing this mode, striving to evolve from traditional manual experience-based judgment to automated and precise proactive protection.

[0003] A search revealed several patent publications: Chinese Patent Publication No. CN118790317A discloses a method, device, and equipment for setting rain and snow modes based on a track controller. By receiving rain and snow mode commands from the ATS (Automatic Train Protection System), the track controller sends rain and snow mode information to trains within the target track section and trains about to enter that section, achieving precise regional control. Chinese Patent Publication No. CN118810867A discloses a method, device, electronic equipment, and storage medium for controlling train rain and snow modes. By identifying the track section corresponding to the rain and snow warning signal and overriding the control commands, regional rain and snow driving control is achieved. Chinese Patent Publication No. CN119659716A discloses a method and device for adjusting train operation in rain and snow modes. By predicting train operation plans using multi-level driving parameters and an operation adjustment model, intelligent optimization of the train schedule is achieved in rain and snow modes. Chinese Patent Publication No. CN113734233A discloses a train control method and system for non-stop switching between rain and snow modes. This method controls the train to operate under preset traction and braking forces, and switches to rain and snow mode when conditions are met, achieving a smooth switching during operation. Chinese Patent Publication No. CN119329578A discloses a protection method, device, equipment, and medium for a virtual train formation rain and snow mode system. It proposes a dynamic disassembly and spacing adjustment mechanism for virtual train formations under rain and snow mode, achieving coordinated safety control of train groups in adverse weather conditions.

[0004] However, existing technologies have the following drawbacks: 1. The perception of rain and snow signals is relatively limited. It usually relies on operators visually observing the weather conditions or only using the slippery status collected by the vehicle as the basis for decision-making, resulting in delayed response and a high misjudgment rate.

[0005] 2. The system uses a total static threshold mechanism for judging train slippage, without differentiating based on the characteristics of different sections (such as rail material, wear, and section environment) and train characteristics (such as track entry time).

[0006] 3. Failed to identify the risks to the surrounding environment caused by train skidding based on geographical information of the line, and failed to formulate corresponding early warning prompts and measures.

[0007] 4. The lack of a long-term predictive model makes it impossible to identify in advance situations where sections and trains are restricted, which can have a significant impact on the day's operational plan and cause operational chaos when restrictions occur.

[0008] 5. Failure to effectively leverage the value of historical data.

[0009] Therefore, how to achieve intelligent management of rain and snow modes that can accurately judge and control the characteristics of the section and the attributes of the train is a technical problem that needs to be solved. Summary of the Invention

[0010] The purpose of this invention is to overcome the defects of the prior art by providing a method and system for intelligent management of rain and snow modes of power lines.

[0011] The objective of this invention can be achieved through the following technical solutions: According to a first aspect of the present invention, a method for intelligently managing rain and snow modes of power lines is provided, the method comprising: Acquire multi-source data, including meteorological data from external weather systems and real-time train operation data from onboard controllers; Based on the multi-source data, calculate the current segment environmental perception limitation index (CSERI) and the current train environmental perception limitation index (CTERI) for each segment and each train in the line. Based on the current segment environmental perception restricted index CSERI, the preset segment surrounding geographical type index CGTI, and the segment historical restricted index HIS_s obtained by analyzing historical data, the overall restricted level of each segment is calculated, and according to the overall restricted level of the segment, instructions are automatically sent to the line controller to perform temporary speed limit control on the corresponding segment. Based on the current train environmental perception restriction index CTERI, the surrounding geographical type index CGTI of its section, and the historical train restriction index HIS_t obtained by analyzing historical data, the overall train restriction level of each train is calculated; and according to the overall train restriction level, instructions are automatically sent to the on-board controller to perform traction or braking force adjustment control on the corresponding train.

[0012] As a preferred technical solution, the multi-source data also includes parameters such as rail surface friction, rotational speed, temperature, and environmental conditions around the train, collected by sensors installed on the wheels or rails; the meteorological data includes real-time weather data and forecasted weather data for future periods.

[0013] As a preferred technical solution, the calculation expression for the Current Segment Environmental Sensing Limitation Index (CSERI) is as follows: , Among them, CWRI is the current weather-limited index, which maps meteorological data to an index from 1 to 100 through a preset mapping model; CSRI is the current section environmental-limited index, which compares the parameters collected by the sensor with the preset section environmental benchmark parameters and maps them to an index from 1 to 100 according to the degree of deviation through a preset mapping model; W1 and W2 are weighting coefficients, and W1 + W2 = 100%.

[0014] As a preferred technical solution, the calculation expression for the Current Train Environment Perception Limitation Index (CTERI) is as follows: , Among them, CSERI is the current segment environmental perception limitation index of the section where the train is located; CTRI is the current train perception limitation index, which is mapped to an index from 1 to 100 by comparing the real-time train operation data with the preset train normal operation benchmark parameters and mapping the parameter abnormality to an index from 1 to 100 through a mapping model; W3 and W4 are weighting coefficients, and W3 + W4 = 100%.

[0015] As a preferred technical solution, the overall restricted level of the section is determined as follows: Calculate the overall restricted index QL1 of the first segment and the overall restricted index QL2 of the second segment, and take the larger value of the two as the overall restricted level of the segment; The QL1 is determined by: counting the total number of trains that slip and spin within a preset time and a preset continuous length area, comparing the total number with a preset restricted level threshold, and taking the value corresponding to the highest restricted level reached as QL1. The calculation method for QL2 is as follows: , Wherein, CSERI is the current segment environmental perception restriction index of the section where the train is located; CGTI is the surrounding geographical type index of the current segment; HIS_s is the historical restriction index of the segment; ZW1, ZW2 and ZW3 are weighting coefficients, and ZW1 + ZW2 + ZW3 = 100%.

[0016] As a preferred technical solution, the method for determining the overall train limitation level is as follows: Calculate the first overall train restriction index TL1 and the second overall train restriction index TL2, and take the larger of the two as the overall train restriction level; The method for determining TL1 is as follows: the total length of the section where the train slips and spins within a preset time period is counted, and the total length is compared with a preset train restriction level threshold. TL1 is the value corresponding to the highest restriction level reached. The calculation method for TL2 is as follows: , Wherein, CTERI is the current train environment perception restriction index; CGTI is the geographical type index of the surrounding area of ​​the section in which it is located; HIS_t is the train historical restriction index; ZW4, ZW5 and ZW6 are weighting coefficients, and ZW4 + ZW5 + ZW6 = 100%.

[0017] As a preferred technical solution, the calculation method for the Geographic Type Index (CGTI) of the surrounding area is as follows: , CGI is the current passenger flow index, which is obtained by comparing real-time passenger flow data with the passenger flow benchmark value in the rain and snow mode basic information database and using a mapping model based on the degree to which the passenger flow exceeds the benchmark value; GPI is a preset surrounding geographical protection index that characterizes the level of physical protection facilities; W5 and W6 are weighting coefficients, and W5 + W6 = 100%.

[0018] As a preferred technical solution, the section historical restriction index and the train historical restriction index are obtained through the following process: Obtain historical section dynamic information, historical train dynamic information, basic section information, and basic train information from the rain and snow mode basic information database; The acquired information is used periodically to train a pre-built neural network model to generate an optimized prediction model; Before the start of daily operations, the prediction model is used to predict and output the historical restriction index of each section and the historical restriction index of each train based on the operation plan for the next day.

[0019] As a preferred technical solution, the method further includes an early warning step: before the start of operation on the same day, based on the predicted historical restriction index of the section and the historical restriction index of the train, it is determined whether there are sections or trains that meet the restriction conditions in the future operation period, and an early warning message is sent to the user interface for proactive prompting.

[0020] According to a second aspect of the present invention, a system for implementing the method is provided, the system comprising: The database equipment of the train automatic monitoring system includes a basic information database for rain and snow patterns; The train control system gateway server has a rain and snow mode intelligent management component deployed on it, the component including: The data interface and service module is responsible for reading and writing data to the rain and snow mode basic information database and communicating with external weather systems and vehicle controllers. The environmental perception module acquires multi-source data through the data interface and service module, and calculates the environmental perception limitation index of the section and the train. The main logic module obtains the calculation results of the environmental perception module, the preset geographical type index of the surrounding area of ​​the section, and the historical restriction index of the section and train obtained by analyzing historical data. It calculates the overall restriction level of the section and train, and generates control commands to be sent to the line controller and the on-board controller through the data interface and service module.

[0021] As a preferred technical solution, the system further includes: The surrounding geography module obtains passenger flow data and basic geographic information through the data interface and service module, and calculates the surrounding geography type index of each segment. The historical information analysis module obtains historical data through the data interface and service module, trains and predicts through machine learning models, and generates the section historical restriction index and the train historical restriction index. The central workstation provides a human-computer interaction interface, receives data from the rain and snow mode intelligent management component, and displays it visually to the user.

[0022] As a preferred technical solution, the rain and snow mode basic information database includes: The route information table stores the configuration information for the entire line, including the total number of sections, the total number of trains, the thresholds under different overall restriction levels, and the calculation formulas for calculating various restriction indices. The basic segment information table is used to store the static attributes of each segment, including segment identifier, segment length, kilometer marker location information, segment threshold under different restriction levels, and surrounding geographical protection index; The basic train information table stores the static attributes of each train, including train identification, length, vehicle condition information, and train thresholds under different restriction levels. The daily section dynamic information table and the daily train dynamic information table are used to periodically record and update the real-time status data of each section and each train during operation, calculate the current and predicted perception limitation index, and the overall limitation level determined by the main logic module. The historical section dynamic information table and the historical train dynamic information table are used to store dynamic information data of the days that have ended their operation, providing a historical data foundation for the historical information analysis module to conduct model training and prediction.

[0023] Compared with the prior art, the present invention has the following advantages: 1. This invention constructs a unified basic information database and automatically calculates the perception index and overall limitation level for each section and each train based on multi-source data. This enables differentiated and precise control and automated operation of sections and trains under rain and snow conditions, effectively improving operational safety and decision-making efficiency.

[0024] 2. This invention introduces a multi-sensing mechanism, which integrates meteorological data, high-precision sensor data and train control data to construct a comprehensive environmental perception constraint index system, thereby improving the accuracy of early warning and decision-making.

[0025] 3. This invention provides differentiated processing for each section and each train, improving the accurate positioning of the restricted status of sections or trains, thereby effectively improving the efficiency of line management and operation.

[0026] 4. Based on the geographical information around the line, this invention can identify and differentiate high-risk sections, thereby achieving refined prevention and control of safety risks and improving the protection level of key areas.

[0027] 5. This invention establishes a historical data model and performs periodic training and prediction, giving the system the ability to predict over a long time scale, enabling operators to anticipate risks and adjust plans in advance, thereby mitigating the impact of section or train restrictions on line operation. Attached Figure Description

[0028] Figure 1 This is a schematic diagram of the system structure of the present invention; Figure 2 This is a diagram showing the internal module division of the intelligent management component of the present invention; Figure 3 This is a flowchart of the method of the present invention; Detailed Implementation

[0029] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] Example 1: This invention provides an automatic train monitoring system for intelligent management of rain and snow modes on railway lines, such as... Figure 1As shown, this system is implemented through software upgrades and functional expansion based on the hardware of the traditional Automatic Train Monitoring System (ATS) and Automatic Train Control System (ATC).

[0031] The hardware architecture of the system includes: ATS Subsystem: Includes ATS database, ATC gateway server, central server and central workstation; ATC subsystem: includes line controller LC and vehicle controller CC; External systems: including weather systems and passenger flow systems.

[0032] This system adds a rain and snow mode intelligent management component to the existing ATC gateway server and establishes a basic information database for rain and snow modes in the ATS database, such as... Figure 2 As shown, the internal logical modules of the rain and snow mode intelligent management component are specifically divided as follows: Data Interface and Service Module: Serving as the unified entry point for data access, it performs all operations on the rain and snow mode basic information database through the dedicated database interface (such as OCCI) provided by the database vendor, and is responsible for the backup and initialization of dynamic data tables after the operation ends.

[0033] Environmental perception module: Periodically communicates with the on-board controller CC through the ATC gateway to obtain real-time train data, including train position, traction, braking force, etc., obtains weather data through the meteorological interface, and calculates the current weather-limited index CWRI, the predicted weather-limited index curve PWRI, the current section environmental-limited index CSRI, the current section environmental perception-limited index CSERI, the current train perception-limited index CTRI, and the current train environmental perception-limited index CTERI.

[0034] Surrounding Geographic Module: Periodically obtains passenger flow data through the passenger flow system interface and calculates the current passenger flow index (CGI), the predicted passenger flow index curve (PGI), and the current surrounding geographic type index (CGTI).

[0035] Historical information analysis module: Loads, runs, and periodically trains a deep temporal prediction model to calculate the historical constraint index of sections and trains; the model is a Long Short-Term Memory Network (LSTM), a Temporal Convolutional Network (TCN), or a Transformer model.

[0036] Main logic module: Calculates the overall restriction index QL1 and QL2 of the first and second sections, as well as the overall restriction index TL1 and TL2 of the first and second trains, and determines the final overall restriction level accordingly. It then triggers control commands to set temporary speed limits for the line controller LC and adjust traction / braking for the onboard controller CC, and sends display and warning information to the central workstation.

[0037] The ATS database contains a dedicated rain and snow pattern information database to store all relevant data, which includes the following core data tables: Line Information Table: Stores the global configuration of the entire line, such as the total number of sections, the total number of trains, the thresholds under different overall restriction levels (total length of sections where slippage occurs within a certain length area, total number of trains where slippage occurs within a certain length area), and formulas for calculating various indices, including the current section environmental perception restriction index formula, the current train environmental perception restriction index formula, the surrounding geographical type index formula, the overall section restriction index formula, and the overall train restriction index formula.

[0038] Basic Section Information Table: Stores the static attributes of each section, including section identifier, section length, kilometer marker, threshold information under different restriction levels (such as temporary speed limit and the number of trains that slip and slide within a unit of time), environmental perception index benchmark value, surrounding geographical passenger flow benchmark value, and surrounding geographical protection index.

[0039] Basic Train Information Table: Stores the static attributes of each train, including train identification, train length, overall vehicle condition, and threshold information under different restriction levels, such as preset traction force, preset braking force, train slippage time, and the baseline probability of the train being affected by the environment.

[0040] Daily Section Dynamic Information Table: Used to record and update the dynamic information of the section in real time during the operation day, including section identifier, current time, whether there is a train, current environmental perception restriction index, predicted environmental perception restriction index curve, current surrounding geographical type index, predicted surrounding geographical type index curve, historical restriction index, and overall restriction level.

[0041] Daily Train Dynamic Information Sheet: Used to record and update train dynamic information in real time during the operating day, including train identification, current time, current train location, current train traction force, current train braking force, current train perception limitation index, predicted train perception limitation index curve, historical limitation index, and overall limitation level.

[0042] Historical Section Dynamic Information Table and Historical Train Dynamic Information Table: Used to store dynamic information for historical operating days.

[0043] The software functionality of the central workstation of this invention has been expanded based on the existing foundation, specifically including: (1) The station layout map can be modified from the original single setting of whether or not a rain / snow mode is set to different display effects based on the overall restriction level of the specific train. For example, the icon color can be changed from light to dark to indicate the restriction level from low to high. Similarly, it can be displayed with different display effects based on the overall restriction level of the specific section. (2) Users can actively view the restricted status of all sections through the operation menu items, and access the main logic module of the intelligent management component through the central server to query the historical, current and predicted information of all sections. A detailed list of information (including section name, start time, end time, etc.) is displayed to the user in a pop-up window, using different colors to distinguish historical, current and predicted information, and supporting filtering by name or start and end time. Selecting a specific section name will pop up a time-restriction level curve to display the detailed restricted information of that section; (3) Users can directly operate on the station map to query detailed information for a specified section. The pop-up window contains the historical, current and forecast information of the restricted section. (4) Users can actively view the restricted status of all trains through the operation menu items, access the main logic module of the intelligent management component through the central server, query the historical information, current information and forecast information of all sections, and display detailed list information (including train name, start time, end time, etc.) to users in the pop-up window. Different colors are used to distinguish historical information, current information and forecast information. It supports filtering display by name or start and end time. When a specific train name is selected, a time-restriction level curve will pop up to display the detailed restricted information of the train. (5) Users can directly operate the detailed information of a specified train on the station map. The pop-up window contains the historical, current and forecast information of the train's restrictions. (6) Expand the ability to adjust existing thresholds. All thresholds in the basic information database of this technical solution can be queried and adjusted on the workstation.

[0044] The system of this invention, based on the existing Automatic Train Monitoring System (ATS) and Automatic Train Control System (ATC) hardware architecture, adds an intelligent management component for rain and snow modes that integrates environmental perception, geographical risk assessment, historical data analysis, and intelligent decision-making modules, and creates a dedicated basic information database for rain and snow modes. Through multi-system data interoperability and functional collaboration, it realizes intelligent early warning, dynamic control, and continuous optimization of rain and snow modes for the railway line.

[0045] Example 2: like Figure 3 The diagram shows the execution flow of the method of the present invention, which is completed collaboratively by multiple modules within the rain and snow mode intelligent management component.

[0046] Before the start of each day's operations, the system automatically performs the following operations: Historical Prediction: The historical information analysis module loads a prediction model trained from historical data. This model takes the basic information and time of each segment for the next day as input, calculates the historical restriction index of each segment at each time point, and stores it in the segment dynamic information table for the day. It also takes the basic information and operation plan of each train for the next day as input, calculates the historical restriction index of each train at each time point, and stores it in the train dynamic information table for the day.

[0047] Fifteen minutes before the start of operations, the main logic module reads the forecast information from the daily dynamic information table and uses simulation calculations to determine whether any sections or trains will meet the restricted conditions during the future operating period. If so, it immediately displays the warning and alerts to the dispatcher on the central workstation via the central server.

[0048] During the day's operation, the system executes the following process in a fixed cycle: The environmental perception module periodically reads real-time data of all trains from the on-board controller CC through the ATC gateway, including the current train position, current train traction force, current train braking force, speed, etc., and stores it in the train dynamic information table for the day. At the same time, based on the train position, it calculates whether there is a train in each section and stores it in the section dynamic information table for the day. This module periodically reads real-time weather data for all areas along the route via a meteorological interface and calculates the Current Weather Restricted Index (CWRI, ranging from 1 to 100, with higher values ​​indicating greater restriction) for each segment. Simultaneously, it acquires weather forecast data, calculates the Predicted Weather Restricted Index (PWRI, which can be predicted hourly), and connects these to form a Predicted Weather Restricted Index curve. For lines equipped with high-precision sensors, this module monitors parameters such as friction, rotational speed, and temperature between the wheels and the rails in real time, as well as environmental conditions around the train, such as humidity, temperature, wind speed, and wind direction. It compares these parameters with baseline normal parameters and calculates the Current Section Restricted Index (CSRI, ranging from 1 to 100, with higher values ​​indicating greater restriction) for each section. According to the formula W1+W2=100% calculates the Current Section Environmental Restricted Index (CSERI) for each section. By replacing CWRI with PWRI for each hour, the predicted section environmental restricted index for each hour can be calculated. These indices are then connected to form a curve, which is stored in the section dynamic information table for the day through the data interface and service module. Finally, the module queries the Current Train Restricted Index (CSERI) of the current section based on the train's location, assesses the Current Train Restricted Index (CTRI, ranging from 1 to 100, with higher values ​​indicating greater restriction), and then applies the formula... W3 + W4 = 100%, calculate the Current Train Environmental Restricted Index (CTERI), generate a predicted CTERI curve based on the operation plan, and store it in the train dynamic information table for the day.

[0049] The surrounding geography module periodically reads real-time passenger flow data and predicted passenger flow curves for all areas of the route through the passenger flow system interface. After being decomposed by section, it is compared with the surrounding geography passenger flow benchmark value in the basic section information table to calculate the current passenger flow index CGI and the predicted passenger flow index PGI curve. Combining the static surrounding geographical protection index (GPI) read from the basic section information table (derived from platform screen doors, gap protection systems, and section protection airtight partition doors, etc.), according to the formula... W5 + W6 = 100%, calculate the current surrounding geographic type index CGTI for each segment, replace the segment CGI with GPI, and calculate the predicted surrounding geographic type index for each segment. Then connect these indices together to form a curve, and store it in the segment dynamic information table for the day through the data interface and service module.

[0050] The main logic module periodically reads the latest data from all base tables and dynamic tables; For a given section: The overall restricted index QL1 for the first section is calculated based on whether the total number of slipping trains in a preset area within a preset time exceeds a threshold. For example, if the current number of slipping trains is 3, and the thresholds for restricted levels 1, 2, and 3 are 2, 3, and 4 respectively, then the restricted level for the section is 2. This value is denoted as QL1; using the formula... ZW1 + ZW2 + ZW3 = 100%, calculate the overall restricted index QL2 for the second section; take the larger value of QL1 and QL2 as the overall restricted level for this section. If the level is non-zero, retrieve the corresponding temporary speed limit value from the basic section information table, set the temporary speed limit for this section through the line controller LC, and issue an alarm at the central workstation.

[0051] For the train: The overall train restriction index TL1 is calculated based on whether the total length of the slippage sections exceeds a threshold within a preset time. For example, if the current number of slippage sections is 3, with a total length of 5.5 kilometers, and the thresholds for restriction levels 1, 2, and 3 are 2 kilometers, 4 kilometers, and 6 kilometers respectively, then the train restriction level is 2, and this value is recorded as TL1; using the formula... ZW4 + ZW5 + ZW6 = 100%; take the larger value of TL1 and TL2 as the overall restricted level of the train. If the level is not zero, take the corresponding preset traction force and braking force values ​​from the basic train information table, adjust them through the train's onboard controller CC, and issue an alarm at the central workstation.

[0052] Fifteen minutes after the end of each day's operations, the data interface and service module automatically backs up the day's section and train dynamic information tables to the historical section dynamic information table and the historical train dynamic information table, respectively, and then clears the table for the day to prepare for the next day's operations. During normal operation, every 30 days, 45 minutes after the end of the day's operations, the historical information analysis module, based on a pre-set basic neural network model (an offline model trained using years of operational data from all urban rail lines collected by the supplier and operator), gathers all existing information from the basic information database of this line. This information is then organized and standardized into structured, multi-dimensional feature vectors, which serve as the input layer of the neural network. This data undergoes forward propagation and feature learning through a complex network structure containing multiple hidden layers. Incremental optimization and fine-tuning based on the backpropagation algorithm optimizes the model parameters, ultimately resulting in a prediction model optimized for the current line environment and operational characteristics. The optimized model is saved to the local hard drive for subsequent prediction tasks. Depending on project needs, section and train information can be aggregated and trained into a single large model, or section and train information can be trained separately into two large models: a section large model and a train large model. As a preferred embodiment, the neural network model employs deep learning models suitable for processing time-series data and possessing powerful feature extraction capabilities, such as Long Short-Term Memory (LSTM), Temporal Convolutional Network (TCN), or Transformer.

[0053] The central workstation provides users with a comprehensive query and intervention interface: on the workstation map, the color of the section and train icons changes dynamically from light to dark according to their overall restriction level; users can query detailed historical, current and predicted restriction information for any section or train through the menu, which is displayed in the form of a list and a time-restriction level curve; all threshold parameters and weight coefficients in the basic information database can be queried and adjusted on the workstation.

[0054] The method of this invention constructs a basic information database of rain and snow patterns, collects multi-source environmental and operational data in real time and quantifies them into a limitation index, and combines the decision-making logic of section / train dimensions to achieve early warning and real-time control. It automatically calculates and dynamically adjusts the rain and snow limitation levels of each section and each train, realizing precise and intelligent control of temporary speed limits on the line and train traction braking, thereby improving operational safety and efficiency under severe weather conditions.

[0055] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for intelligently managing rain and snow modes on power lines, characterized in that, The method includes: Acquire multi-source data, including meteorological data from external weather systems and real-time train operation data from onboard controllers; Based on the multi-source data, calculate the current segment environmental perception limitation index (CSERI) and the current train environmental perception limitation index (CTERI) for each segment and each train in the line. The calculation expression for the current train environment perception limitation index (CTERI) is as follows: ， Wherein, CSERI is the current segment environmental perception limitation index of the section where the train is located, and CTRI is the current train perception limitation index. By comparing the real-time train operation data with the preset train normal operation benchmark parameters, the parameters are mapped to an index from 1 to 100 through a mapping model according to the degree of parameter anomaly. W3 and W4 are weighting coefficients, and W3 + W4 = 100%. Based on the current segment environmental perception restricted index CSERI, the preset segment surrounding geographical type index CGTI, and the segment historical restricted index HIS_s obtained by analyzing historical data, the overall restricted level of each segment is calculated; and according to the overall restricted level of the segment, instructions are automatically sent to the line controller to perform temporary speed limit control on the corresponding segment. The calculation method for the Geographic Type Index (CGTI) of the surrounding area of ​​the section is as follows: ， CGI is the current passenger flow index, which is obtained by comparing real-time passenger flow data with the passenger flow benchmark value in the rain and snow mode basic information database and using a mapping model based on the degree to which the passenger flow exceeds the benchmark value. GPI is a preset surrounding geographical protection index that characterizes the level of physical protection facilities. W5 and W6 are weighting coefficients, and W5 + W6 = 100%. The method for determining the overall restricted level of the section is as follows: Calculate the overall restricted index QL1 of the first segment and the overall restricted index QL2 of the second segment, and take the larger value of the two as the overall restricted level of the segment; The QL1 is determined by: counting the total number of trains that slip and spin within a preset time and a preset continuous length area, comparing the total number with a preset restricted level threshold, and taking the value corresponding to the highest restricted level reached as QL1. The calculation method for QL2 is as follows: ， Wherein, CSERI is the current segment environmental perception restriction index of the section where the train is located, CGTI is the surrounding geographical type index of the current segment, HIS_s is the historical restriction index of the segment, ZW1, ZW2 and ZW3 are weighting coefficients, and ZW1 + ZW2 + ZW3 = 100%; Based on the current train environmental perception restriction index CTERI, the surrounding geographical type index CGTI of its section, and the historical train restriction index HIS_t obtained by analyzing historical data, the overall train restriction level of each train is calculated; and according to the overall train restriction level, instructions are automatically sent to the on-board controller to perform traction or braking force adjustment control on the corresponding train.

2. The method for intelligently managing rain and snow modes of power lines according to claim 1, characterized in that, The multi-source data also includes parameters such as rail surface friction, rotational speed, temperature, and environmental conditions around the train, collected by sensors installed on the wheels or rails; the meteorological data includes real-time weather data and forecasted weather data for future periods.

3. The method for intelligently managing rain and snow modes of power lines according to claim 1, characterized in that, The calculation expression for the Current Segment Environmental Sensing Limitation Index (CSERI) is as follows: ， Wherein, CWRI is the current weather-limited index, which maps meteorological data to an index from 1 to 100 through a preset mapping model; CSRI is the current section environmental-limited index, which compares the parameters collected by the sensor with the preset section environmental baseline parameters and maps them to an index from 1 to 100 according to the degree of deviation through the mapping model; W1 and W2 are weighting coefficients, and W1 + W2 = 100%.

4. The method for intelligently managing rain and snow modes of power lines according to claim 1, characterized in that, The method for determining the overall train limitation level is as follows: Calculate the first overall train restriction index TL1 and the second overall train restriction index TL2, and take the larger of the two as the overall train restriction level; The method for determining TL1 is as follows: the total length of the section where the train slips and spins within a preset time period is counted, and the total length is compared with a preset train restriction level threshold. TL1 is the value corresponding to the highest restriction level reached. The calculation method for TL2 is as follows: ， Wherein, CTERI is the current train environment perception restriction index; CGTI is the geographical type index of the section surrounding the train; HIS_t is the train historical restriction index; ZW4, ZW5 and ZW6 are weighting coefficients, and ZW4 + ZW5 + ZW6 = 100%.

5. The method for intelligently managing rain and snow modes of power lines according to claim 1, characterized in that, The historical restriction index of the section and the historical restriction index of the train are obtained through the following process: Obtain historical section dynamic information, historical train dynamic information, basic section information, and basic train information from the rain and snow mode basic information database; The acquired information is used periodically to train a pre-built neural network model to generate an optimized prediction model. Before the start of daily operations, the prediction model is used to predict and output the historical restriction index of each section and the historical restriction index of each train based on the operation plan for the next day.

6. The method for intelligently managing rain and snow modes of power lines according to claim 1, characterized in that, The method also includes an early warning step: before the start of operation on the same day, based on the predicted historical restriction index of the section and the historical restriction index of the train, it is determined whether there are sections or trains that meet the restriction conditions during the future operation period, and an early warning message is sent to the user interface to provide an active reminder.

7. A system for implementing the method according to any one of claims 1-6, characterized in that, The system includes: The database equipment of the train automatic monitoring system includes a basic information database for rain and snow patterns; The train control system gateway server has a rain and snow mode intelligent management component deployed on it, the component including: The data interface and service module is responsible for reading and writing data to the rain and snow mode basic information database and communicating with external weather systems and vehicle controllers. The environmental perception module acquires multi-source data through the data interface and service module, and calculates the environmental perception limitation index of the section and the train. The main logic module obtains the calculation results of the environmental perception module, the preset geographical type index of the surrounding area of ​​the section, and the historical restriction index of the section and train obtained by analyzing historical data. It calculates the overall restriction level of the section and train, and generates control commands to be sent to the line controller and the on-board controller through the data interface and service module.

8. The system according to claim 7, characterized in that, The system also includes: The surrounding geography module obtains passenger flow data and basic geographic information through the data interface and service module, and calculates the surrounding geography type index of each segment. The historical information analysis module obtains historical data through the data interface and service module, trains and predicts through machine learning models, and generates the section historical restriction index and the train historical restriction index. The central workstation provides a human-computer interaction interface, receives data from the rain and snow mode intelligent management component, and displays it visually to the user.

9. The system according to claim 7, characterized in that, The rain and snow mode basic information database includes: The route information table stores the configuration information for the entire line, including the total number of sections, the total number of trains, the thresholds under different overall restriction levels, and the calculation formulas for calculating various restriction indices. The basic segment information table is used to store the static attributes of each segment, including segment identifier, segment length, kilometer marker location information, segment threshold under different restriction levels, and surrounding geographical protection index; The basic train information table stores the static attributes of each train, including train identification, length, vehicle condition information, and train thresholds under different restriction levels. The daily section dynamic information table and the daily train dynamic information table are used to periodically record and update the real-time status data of each section and each train during operation, calculate the current and predicted perception limitation index, and the overall limitation level determined by the main logic module. The historical section dynamic information table and the historical train dynamic information table are used to store dynamic information data of the days that have ended their operation, providing a historical data foundation for the historical information analysis module to conduct model training and prediction.

Images