A train operation dynamic visualization method, system, medium and device
By sorting and sliding the train operation data and station data, dynamic train operation data is generated, which solves the problems of data dispersion and lack of intuitiveness, and realizes data visualization and efficient operation and maintenance.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CRRC INDUSTRAIL ACADEMY (QINGDAO) CO LTD
- Filing Date
- 2025-06-23
- Publication Date
- 2026-07-14
AI Technical Summary
Train operation data is large and scattered. Existing tables and reports are not intuitive and cannot achieve comprehensive correlation analysis, leading to difficulties in operation and maintenance.
By acquiring train operation data and station data maps, sorting them along a set time series line, using time nodes as correlation parameters, and sliding along the station data line, train operation dynamics are generated and integrated into visualized data.
It enables intuitive visualization of train operation data, facilitating real-time monitoring of status and improving operation and maintenance efficiency.
Smart Images
Figure CN120681201B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of data processing, and in particular to a method, system, medium, and device for visualizing the dynamics of train operation. Background Technology
[0002] Data on train operation, energy consumption, and energy storage typically involves a very large volume of data. Maintenance personnel usually use Excel spreadsheets or platform reports to process this data. However, spreadsheet data is not intuitive, is time-consuming and labor-intensive to maintain, and the data from various aspects are relatively independent, making it impossible to achieve comprehensive correlation analysis. Summary of the Invention
[0003] The purpose of this application is to provide a method, system, computer-readable storage medium, and electronic device for visualizing train operation dynamics, which can realize the visualization of train operation data and facilitate users to grasp the train operation status in real time.
[0004] To address the aforementioned technical problems, this application provides a method for visualizing train operation dynamics, the specific technical solution of which is as follows:
[0005] Obtain train operation data and station data maps;
[0006] The train operation data is sorted along a set time series line, and the train operation unit data corresponding to each time node is used as the associated parameter of the time node on the time series line.
[0007] For each train line, the corresponding time sequence line is aligned with the station data line in the station data diagram, with the station as a fixed node and the time node as an active node.
[0008] Using the time information of the time node as a parameter, the time node is slid along the aligned station data line to obtain the running dynamics of a single train line; wherein, the sliding starts from the first station where the train begins to run along the train line, and is removed from the station data line when the train stops running.
[0009] By integrating the operational dynamics of all train lines, train operation dynamic data is rendered.
[0010] Optionally, before obtaining train operation data and station data maps, the following steps may also be taken:
[0011] Determine the location information of each train station;
[0012] The station data map is generated by scaling the distance between the train stations proportionally based on the location information.
[0013] Optionally, when generating the station data map by proportionally scaling the station spacing between the train stations based on the location information, the method further includes:
[0014] Train lines exceeding the screen width will be wound according to the set winding rules;
[0015] Substations and energy storage devices are marked on the station data map according to their actual location data; the substations and energy storage devices are used to indicate the corresponding status data of the train.
[0016] Optionally, the train operation data is sorted along a set time series line, and the train operation unit data corresponding to each time node is used as the association parameter of the time node on the time series line, including:
[0017] Obtain the train timetable and construct a time series line based on the train timetable;
[0018] The train operation data is divided into several train operation unit data based on a set duration; wherein each train operation unit data includes start and end time, current train number, next train number, direction of travel, station time data and arrival data;
[0019] On the time series line, several time node intervals will be obtained by using the set duration as the unit of division;
[0020] The train operation unit data is associated with the corresponding start and end times and arrival data to the time node intervals; each time node interval includes the current time node and a line segment extending to the next time node.
[0021] Optionally, for each train line, aligning the corresponding time series line with the station data line in the station data diagram, treating the station as a fixed node and the time node as an active node includes:
[0022] For each train line, the arrival time point in the time node is determined, and the time node containing the arrival time point is used as the reference time node and associated with the station in the station data map.
[0023] Other time nodes between the baseline time nodes are set sequentially between adjacent stations in the site data map according to their chronological order.
[0024] Optionally, using the time information of the time node as a parameter, sliding the time node along the aligned station data line to obtain the operational dynamics of a single train line includes:
[0025] Confirm the time interval information corresponding to the time node;
[0026] If the time interval information of all time nodes between adjacent stations matches the train running time between adjacent stations, remove all time nodes between adjacent stations.
[0027] Repeat the above steps until all time points except stations are removed from a single train line;
[0028] A sliding time point is set in a single train line, and all train operation unit data when the sliding time point slides along the single train line are used as the operation dynamics of the single train line; the operation dynamics include real-time train status data, traction substation, energy storage information and real-time energy consumption at any time.
[0029] Optionally, after integrating the operational dynamics of all train lines and rendering the train operation dynamics data, the following may also be included:
[0030] Obtain historical train operation data and historical station data maps;
[0031] Historical train operation dynamic data is rendered based on the historical train operation data and the historical station data map.
[0032] By integrating the historical site data map and the site data map, an overlapping site data map is obtained;
[0033] In the overlapping station data map, the train operation dynamic data is displayed in a first display mode and the historical train operation dynamic data is displayed in a second display mode;
[0034] By comparing the train operation dynamic data with the historical train operation dynamic data, dynamic change data of operation is generated.
[0035] This application also provides a train operation dynamic visualization system, including:
[0036] The data acquisition module is used to acquire train operation data and station data maps;
[0037] The data processing module is used to sort the train operation data along a set time series line, and on the time series line, the train operation unit data corresponding to each time node is used as the association parameter of the time node;
[0038] The data alignment module is used to align the corresponding time series line with the station data line in the station data diagram for each train line, treating the station as a fixed node and the time node as an active node.
[0039] The dynamic output module is used to slide the time node along the aligned station data line using the time information of the time node as a parameter to obtain the running dynamics of a single train line; wherein, the sliding starts from the first station where the train starts running along the train line and is removed from the station data line when the train stops running.
[0040] The dynamic rendering module is used to integrate the operational dynamics of all train lines and render the dynamic data of train operation.
[0041] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.
[0042] This application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method described above when it invokes the computer program in the memory.
[0043] This application provides a method for visualizing train operation dynamics, comprising: acquiring train operation data and station data maps; sorting the train operation data along a set time series line, and using the train operation unit data corresponding to each time node as the association parameter of the time node on the time series line; for each train line, aligning the corresponding time series line with the station data line in the station data map, using the station as a fixed node and the time node as an active node; using the time information of the time node as a parameter, sliding the time node along the aligned station data line to obtain the operation dynamics of a single train line; wherein, the sliding starts from the first station where the train begins to run along the train line and is removed from the station data line when the train stops running; integrating the operation dynamics of all train lines and rendering the train operation dynamic data.
[0044] After obtaining train operation data and station data maps, this application associates the train operation data with time series lines, and uses stations as fixed nodes and time nodes as active nodes to generate the operation dynamics of each train line. The train operation data is serialized and stored, and the data is correlated and analyzed according to the time series, which facilitates the output of train operation dynamic data to maintenance personnel and facilitates the visualization and analysis of train operation dynamic data.
[0045] This application also provides a train operation dynamic visualization system, a computer-readable storage medium, and an electronic device, which have the above-mentioned beneficial effects, and will not be elaborated here. Attached Figure Description
[0046] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.
[0047] Figure 1 A flowchart of the train operation dynamic visualization method provided in the embodiments of this application;
[0048] Figure 2 This is a schematic diagram of train operation dynamic data comparison provided in the embodiments of this application;
[0049] Figure 3 This is a schematic diagram of the train operation dynamic visualization system provided in the embodiments of this application;
[0050] Figure 4 This is a structural diagram of an electronic device provided in an embodiment of this application. Detailed Implementation
[0051] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0052] See Figure 1 , Figure 1 This is a flowchart of a train operation dynamic visualization method provided in an embodiment of this application. The method includes:
[0053] S101: Obtain train operation data and station data map;
[0054] S102: Sort the train operation data along a set time series line, and use the train operation unit data corresponding to each time node as the associated parameter of the time node on the time series line;
[0055] S103: For each train line, align the corresponding time sequence line with the station data line in the station data diagram, treat the station as a fixed node, and the time node as an active node;
[0056] S104: Using the time information of the time node as a parameter, slide the time node along the aligned station data line to obtain the running dynamics of a single train line; wherein, the sliding starts from the first station where the train begins to run along the train line, and is removed from the station data line when the train stops running.
[0057] S105: Integrates the operational dynamics of all train lines and renders the train operation dynamics data.
[0058] First, train operation data is acquired, such as train timetables, speed curves, switching stations, traction substations, energy storage, real-time energy consumption, and ledgers. The station data map can be generated in advance by determining the location information of each train station and proportionally scaling the distances between stations based on that location information.
[0059] Furthermore, when generating the station data map, train lines exceeding the screen width can be routed according to a set turning rule. Substations and energy storage devices are marked on the station data map based on their actual location data. Substations and energy storage devices are used to indicate the corresponding train status data.
[0060] Specifically, on a webpage, the width of the train line display element can be obtained using the `offsetWidth` property of JavaScript (a programming language). On a webpage, `window.innerWidth` can be used to get the width of the current browser window, which is then used as a measure of the screen width (mobile apps can also obtain the device screen width using corresponding methods). The obtained train line element width is compared with the screen width; if the line element width is greater than the screen width, then line wrapping is required.
[0061] When wrapping lines, you can do so by a fixed number of characters, such as wrapping every 10 characters. You can first split the train route text string according to this number of characters, and then insert the new line for display. Alternatively, you can wrap lines at specific stations or separators: if the train route text has some obvious station names as separators, you can use these separators as wrapping points to divide the route into multiple lines for display.
[0062] In another line wrapping method, line wrapping can be based on the actual distance. For example, a line of 1000 pixels represents an actual distance of 10km. If the starting station A is at position 0px, and station B is 2km from A, then station B is at position 200px. If station C is 6km from B, then station C is at position 800px. If station D is 5km from B, the first line is too large and has 200px remaining (representing 2km). Therefore, station C is positioned 300px (3km) in the second line.
[0063] When performing step S102, the aim is to construct the temporal relationship of train operation data by sorting along the time series line to associate the train operation unit data with time nodes.
[0064] One feasible implementation may include the following steps:
[0065] Step 1: Obtain the train timetable and construct a time series line based on the train timetable;
[0066] The second step is to divide the train operation data into several train operation unit data based on a set duration; wherein each train operation unit data includes start and end time, current train number, next train number, direction of travel, station time data and arrival data;
[0067] The third step is to obtain several time node intervals on the time series line, using the set duration as the unit of division;
[0068] Step 4: Associate the train operation unit data with the corresponding start and end times and arrival data to the time node intervals; each time node interval includes the current time node and the line segment extending to the next time node.
[0069] There are no restrictions on how train operation data is acquired. One feasible approach is to directly acquire multi-source heterogeneous fusion data. This multi-source heterogeneous fusion data includes five data sources: onboard sensor arrays (including inertial navigation, wheel and axle monitoring, and traction energy consumption modules), trackside detection base stations, signal system log servers, power monitoring systems, and passenger mobile terminal signaling data, enabling comprehensive perception of train operation status. Unlike traditional single data acquisition methods, when acquiring multi-source heterogeneous fusion data, an edge computing gateway can be introduced to preprocess the raw data, and FPGA chips can be used to achieve millisecond-level anomaly data annotation, reducing the transmission pressure on the cloud.
[0070] For example, if the data is obtained from a data file, relevant libraries in programming languages (such as Python) (such as pandas) can be used to read the timetable data from the file and load the data into a suitable data structure in memory (such as DataFrame, list, etc.) for convenient subsequent processing.
[0071] Based on the time information in the train timetable (including the arrival and departure times of each train), the corresponding time points are marked on the time axis to construct a time series line. This helps to correlate train operation data with time for subsequent analysis and processing.
[0072] A set duration is determined as the dividing line, for example, a duration of 10 minutes. Starting from the train timetable, the data is divided sequentially according to this set duration to obtain data for several train operation units.
[0073] Referring to Table 1, which is a train timetable provided in this application, it can be seen that trains have standard operating times. Furthermore, stations can be drawn in pixels based on the distance between stations. Therefore, when dragging and sliding the time point, the current position of the train can be calculated and displayed on each train line, such as which station it is located at or between two stations.
[0074] Table 1 Train Timetable
[0075]
[0076] Each train operation unit's data can include the following information:
[0077] Start and end times: These are the start and end times of the divided time period, determined by the set duration. For example, for the first unit of data, the start time might be the start time of the timetable, and the end time is the start time plus the set duration.
[0078] Current train number: The train number corresponding to this time period, which is extracted and determined based on the train number information in the timetable.
[0079] Next train: The train that follows the current train. It can be found by searching the timetable for subsequent train records.
[0080] Direction of travel: The direction of travel of the train (such as up or down) is determined from the relevant direction field in the timetable.
[0081] Station time data: This includes the arrival and departure times of trains at various stations. It is extracted from the station time information of the corresponding train in the timetable and covers the relevant station times within that time period.
[0082] Arrival data: Lists the names of all stations the train arrives at within this time period, organized based on the station names and arrival times in the station time data.
[0083] Using a set duration as the unit of division, the constructed time series line is divided sequentially from the start time into several time nodes. For example, if the set duration is 10 minutes and the start time is 6:00 AM, then the time nodes are 6:00, 6:10, 6:20, etc. These time nodes divide the time series into multiple intervals for subsequent association with train operation unit data. In other embodiments of this application, the division of time nodes does not necessarily have to be even.
[0084] For each train operation unit data point, its start and end times are used to determine which time interval on the time series it falls within. For example, if a train operation unit data point starts and ends at 6:05 and ends at 6:15, then it is associated with the interval consisting of the two time nodes 6:00 - 6:10 and 6:10 - 6:20.
[0085] At the same time, by combining the arrival data, we can see the stations the train arrived at within that time period, and further correlate it with the time node intervals. This facilitates subsequent analysis and display of the train's operation status on the timeline. For example, we can intuitively see the train's driving status, arrival status, and other information within the time node intervals.
[0086] In step S103, by aligning the time series line and the station data line, most time nodes on the time series line are blurred to form active nodes, making it easier for users to view.
[0087] Specifically, for each train line, the arrival time point in the time node is determined, and the time node containing the arrival time point is used as the reference time node and associated with the station in the station data map. Then, other time nodes between the reference time nodes are set sequentially between adjacent stations in the station data map according to the time order.
[0088] For each train line, the arrival time for each station is extracted from the timetable. The timetable typically records the arrival and departure times of each train at each station. These arrival times are marked on the constructed time series line. Time nodes are defined based on a set duration; for example, if the duration is 5 minutes, the time nodes on the time series line would be 06:00, 06:05, 06:10, 06:15, 06:20, 06:25, etc. It can be observed that the arrival times 06:00, 06:05, 06:10, 06:15, 06:20, and 06:25 all fall precisely on these time nodes. These time nodes containing the arrival times are used as base time nodes and associated with their corresponding stations. For example, the baseline time node 06:00 is associated with station A, 06:05 with station B, 06:10 with station C, 06:15 with station A, 06:20 with station B, and 06:25 with station C. This association can be stored in a dictionary or list for easier subsequent processing. Based on the associated baseline time nodes and the station order, baseline time node pairs between adjacent stations are determined. For example, station A (06:00) and station B (06:05) are one pair of adjacent baseline time nodes, station B (06:05) and station C (06:10) are another pair, and so on.
[0089] Between each pair of adjacent stations' base time nodes, other time nodes are set sequentially according to time order. Assuming a set duration of 5 minutes, there are no other intermediate time nodes between the base time node pairs of stations A (06:00) and B (06:05) because they are exactly one set duration apart. However, if the set duration is 3 minutes, the time nodes between 06:00 (station A) and 06:05 (station B) should be 06:00, 06:03, 06:06, etc. In this case, the time nodes 06:03 and 06:06 are filled between stations A and B. Corresponding time nodes can be inserted between adjacent base time nodes using methods such as looping or list generation.
[0090] These added time nodes are then sequentially placed between adjacent stations in the station data graph. The list of time nodes between adjacent stations in the station data graph is then updated, inserting the newly added time nodes to fully represent the time sequence of train operations.
[0091] Subsequently, using the time information of the time node as a parameter, the time node is slid along the aligned station data line to obtain the running dynamics of a single train line; wherein, the sliding starts from the first station where the train begins to run along the train line, and is removed from the station data line when the train stops running.
[0092] This step aims to establish the operational dynamics of a single train line, and specifically, it may include the following steps:
[0093] Step 1: Confirm the time interval information corresponding to the time node;
[0094] The second step is to remove all time nodes between adjacent stations if the time interval information of all time nodes between adjacent stations matches the train running time between adjacent stations.
[0095] Repeat the above steps until all time points except stations are removed from a single train line.
[0096] At this time, a sliding time point is set in a single train line, and all train operation unit data when the sliding time point slides along the single train line are used as the operation dynamics of the single train line; the operation dynamics include real-time train status data, traction substation, energy storage information and real-time energy consumption at any time.
[0097] First, it's essential to clarify the specific time range represented by each time point. Time interval information refers to the start and end times of each time point, which helps in the analysis and comparison of time periods in subsequent steps. For example, if a time point is marked "06:00," it's necessary to determine whether it refers to a specific instant or a time period (such as from 06:00 to 06:05).
[0098] If, between two adjacent train stations, the sum of the time intervals for all time points is exactly equal to the actual train travel time between those two stations, then these time points are considered redundant and can be removed. The purpose of this step is to eliminate unnecessary intermediate time points and simplify data representation.
[0099] Repeat steps one and two, continuously removing unnecessary intermediate time points, until only time points directly related to stations remain on a train line. This ensures that the dataset contains only key station information, facilitating subsequent analysis.
[0100] A sliding time point is defined, which can slide along the time axis of the train line. During the sliding process, data from all train operating units corresponding to that time point are collected. This data constitutes the operational dynamics of the train line. The operational dynamics not only include the real-time status of the train at any given moment (such as position and speed), but also encompass the status of the traction substation, the condition of the energy storage system, and real-time energy consumption information. This provides a detailed data foundation for monitoring and analyzing the operational efficiency and energy usage of the train line.
[0101] After obtaining train operation data and station data maps, this application embodiment associates the train operation data with time series lines, and uses stations as fixed nodes and time nodes as active nodes to generate the operation dynamics of each train line. The train operation data is serialized and stored, and the data is correlated and analyzed according to the time series, which facilitates the output of train operation dynamic data to maintenance personnel and facilitates the visualization and analysis of train operation dynamic data.
[0102] In one feasible implementation, after acquiring train operation data and station data maps, data preprocessing can be performed first. For example, a dynamic threshold adjustment algorithm can be used to set data filtering thresholds based on parameters such as the train's real-time location, operating period, and line load factor (e.g., increasing the vibration data threshold by 30% during peak hours). This allows for the filtering of train operation data based on the data filtering thresholds. Unlike traditional fixed threshold methods, setting dynamic data filtering thresholds can effectively preserve key data features under special operating conditions.
[0103] In addition, data cleaning can be performed. By calling a deep learning-based noise recognition model, corresponding data cleaning strategies can be adopted for different sensor features to achieve differentiated cleaning strategies. The following are some feasible exemplary operation methods:
[0104] An adaptive Kalman filter combined with wavelet transform is used to denoise the accelerometer sensor data.
[0105] A three-phase imbalance compensation algorithm is constructed based on power parameter data;
[0106] Implement a spatiotemporal continuity verification mechanism for passenger flow data;
[0107] Specifically, when using adaptive Kalman filtering combined with wavelet transform for denoising accelerometer data, the raw data sequence acquired by the accelerometer is collected. This data contains real acceleration information as well as various noises. A suitable wavelet function and decomposition scale are selected. Based on the characteristics and noise levels of the accelerometer data, the wavelet basis functions (such as Daubechies, Symlet, etc.) and decomposition levels are determined, typically through experimentation and experience to select the optimal parameter combination. Wavelet decomposition is performed on the raw data, decomposing the signal into approximation coefficients and detail coefficients at different scales. Approximation coefficients reflect the low-frequency components of the signal, while detail coefficients reflect high-frequency information at different scales, including the high-frequency components of the useful signal and noise. A dynamic model of the accelerometer data is established, including state equations and observation equations. The state equations describe the dynamic changes in acceleration, while the observation equations represent the relationship between the acceleration values observed by the sensor and the actual acceleration. The initial state and error covariance matrix of the Kalman filter are initially estimated. The noise statistical characteristics of the Kalman filter are adjusted using an adaptive algorithm. For example, residual information can be used to estimate process noise covariance and measurement noise covariance in real time, enabling filters to better adapt to changes in signal and noise.
[0108] The wavelet coefficients, preprocessed by wavelet transform, are used as input to the adaptive Kalman filter. During the iteration of the Kalman filter, the wavelet coefficients at each time step are filtered and estimated to remove the influence of noise.
[0109] After Kalman filtering, wavelet reconstruction is performed on the filtered coefficients to obtain the denoised acceleration signal.
[0110] When constructing a three-phase imbalance compensation algorithm based on power parameter data, it is possible to collect power parameter data such as three-phase voltage and current of the power system, including data under normal operation and data under three-phase imbalance conditions. The collected data is then analyzed to calculate three-phase imbalance indices, such as the ratio of negative-sequence voltage amplitude to positive-sequence voltage amplitude and zero-sequence current, to understand the degree and characteristics of the three-phase imbalance.
[0111] Based on the power system's operational requirements and relevant standards, determine the compensation target for three-phase imbalance, such as reducing the three-phase imbalance to below a certain specified threshold. Select an appropriate compensation strategy, such as using reactive power compensation, active filtering, or inter-phase power transfer methods to achieve three-phase imbalance compensation.
[0112] Based on the selected compensation strategy, a corresponding mathematical model is established. For example, for a reactive power compensation-based method, a control model for the reactive power compensation device is established to describe the relationship between the output of the compensation device and the three-phase imbalance. Power parameter data is used to identify and optimize the parameters of the compensation model. By minimizing the three-phase imbalance after compensation, key parameters in the model are determined, such as the capacity of the compensation device and control coefficients.
[0113] When designing a three-phase imbalance compensation algorithm, the current three-phase imbalance can be calculated based on real-time monitored three-phase power parameter data. The control signal of the compensation device can be determined according to the compensation model to achieve dynamic compensation of the three-phase imbalance.
[0114] Implement the algorithm in power system simulation software or on an actual power system test platform, and conduct simulation operation and testing.
[0115] When implementing a spatiotemporal continuity verification mechanism for passenger flow data, passenger flow data is first collected, including timestamps, locations (such as stations, stops, etc.), and the number of passengers entering and exiting the station. The data is then cleaned to remove obviously erroneous or missing records. Finally, the data is organized according to spatiotemporal dimensions, categorized and sorted based on time series and spatial location (such as different stations).
[0116] Analyze the temporal and spatial patterns of passenger flow to construct a spatiotemporal continuity model. One feasible implementation involves using a time-series forecasting model (such as ARIMA) to describe the trend of passenger flow over time, and employing spatial interpolation methods (such as Kriging interpolation) to reflect the spatial correlation of passenger flow between different stations. The model parameters are determined, and the model is trained and calibrated using historical passenger flow data to ensure it accurately reflects the spatiotemporal characteristics of passenger flow.
[0117] Subsequently, verification rules were set based on the spatiotemporal continuity model. For example, in the time dimension, passenger flow changes between adjacent time periods should not exceed a certain threshold; in the spatial dimension, passenger flow at adjacent stations should have a certain correlation and rationality. Criteria for judging data anomalies were set, such as judging a data point as an anomaly if its deviation from the value predicted by the spatiotemporal continuity model exceeds a certain range.
[0118] According to the verification rules, the spatiotemporal continuity of passenger flow data is verified one by one. Any data points with anomalies are marked and the anomalies are recorded. Various methods can be used to process the anomaly data, such as correcting the anomaly data based on a spatiotemporal continuity model, or interpolating or estimating data from surrounding stations or adjacent time periods to replace the anomaly data.
[0119] The above are just a few exemplary data cleaning methods provided in this application. Those skilled in the art can adopt similar or other data cleaning methods based on this application, and no specific limitations are made here.
[0120] In an optional implementation, historical train operation dynamic data and current train operation dynamic data can be compared to determine the data changes before and after train operation optimization, including but not limited to operating efficiency, substations, energy storage, and aggregated data. The specific process can be as follows:
[0121] The first step is to obtain historical train operation data and historical station data maps;
[0122] The second step is to render historical train operation dynamic data based on the historical train operation data and the historical station data map.
[0123] The third step is to integrate the historical site data map and the site data map to obtain the overlapping site data map.
[0124] Fourth step: In the overlapping station data map, display the train operation dynamic data in a first display mode and display the historical train operation dynamic data in a second display mode;
[0125] Step 5: Compare the train operation dynamic data with the historical train operation dynamic data to generate operation dynamic change data.
[0126] The historical site data map is matched with the current site data map to find sites common to both datasets, i.e., overlapping sites. Information on these overlapping sites is then integrated into a new data map, which includes the geographical location, name, and related attributes (such as the number of platforms, tracks, etc.) of the overlapping sites, forming the overlapping site data map. It is important to note that the overlapping site data map may include sites that only exist in the historical or current site data maps, i.e., abandoned or newly added sites.
[0127] Two different display methods are determined. For example, the first display method can use solid lines and bright colors (such as red) to display current train operation data, while the second display method can use dashed lines and lighter colors (such as gray) to display historical train operation data. Different display patterns can also be used to distinguish trains in different operation data. Based on the overlapping station data map, data visualization tools are used to implement the two display methods. The current train operation data and historical train operation data are plotted on the map according to the predetermined display methods, allowing users to intuitively distinguish between current and historical train operation status.
[0128] Data comparison algorithms (such as time series analysis and data deviation calculation) are used to compare current train operation dynamic data with historical train operation dynamic data. For example, the differences in train travel time and stopping time between the same stations are calculated.
[0129] Based on the comparison results, dynamic change data of train operation is generated. This data can be presented in the form of tables, charts or text reports to show the changing trends of train operation in different time periods, such as the shortening or lengthening of travel time, and the improvement or deterioration of delays.
[0130] In addition, it can also include changes in substations, energy storage, etc., for both train operation dynamic data and historical train operation dynamic data. The train section includes train traction energy consumption, train regenerative energy consumption, train auxiliary energy consumption, and train total energy consumption. The substation section includes forward and reverse power, current, and voltage. The summary section only needs to display the comparison data before and after optimization, including power transmission, total energy consumption, and energy saving rate.
[0131] See Figure 2 , Figure 2 This is a schematic diagram of train operation dynamic data comparison provided in the embodiments of this application. Figure 2 Different display patterns are used to distinguish trains in different operational dynamic data.
[0132] See Figure 3 , Figure 3 This is a schematic diagram of the train operation dynamic visualization system provided in an embodiment of this application. The system includes:
[0133] The data acquisition module is used to acquire train operation data and station data maps;
[0134] The data processing module is used to sort the train operation data along a set time series line, and on the time series line, the train operation unit data corresponding to each time node is used as the association parameter of the time node;
[0135] The data alignment module is used to align the corresponding time series line with the station data line in the station data diagram for each train line, treating the station as a fixed node and the time node as an active node.
[0136] The dynamic output module is used to slide the time node along the aligned station data line using the time information of the time node as a parameter to obtain the running dynamics of a single train line; wherein, the sliding starts from the first station where the train starts running along the train line and is removed from the station data line when the train stops running.
[0137] The dynamic rendering module is used to integrate the operational dynamics of all train lines and render the dynamic data of train operation.
[0138] Based on the above embodiments, as a preferred embodiment, it further includes:
[0139] The station data map generation module is used to determine the location information of each train station; and to generate the station data map by proportionally scaling the station spacing between the train stations based on the location information.
[0140] Based on the above embodiments, as a preferred embodiment, the site data map generation module further includes:
[0141] The data map processing unit is used to process train lines that exceed the screen width according to a set turning rule; and to mark substations and energy storage devices on the station data map according to their actual location data; the substations and the energy storage devices are used to indicate the corresponding status data of the train.
[0142] Based on the above embodiments, as a preferred embodiment, the data processing module is a unit for performing the following steps:
[0143] Obtain the train timetable and construct a time series line based on the train timetable;
[0144] The train operation data is divided into several train operation unit data based on a set duration; wherein each train operation unit data includes start and end time, current train number, next train number, direction of travel, station time data and arrival data;
[0145] On the time series line, several time node intervals will be obtained by using the set duration as the unit of division;
[0146] The train operation unit data is associated with the corresponding start and end times and arrival data to the time node intervals; each time node interval includes the current time node and a line segment extending to the next time node.
[0147] Based on the above embodiments, as a preferred embodiment, the data alignment module is a module for performing the following steps:
[0148] For each train line, the arrival time point in the time node is determined, and the time node containing the arrival time point is used as the reference time node and associated with the station in the station data map.
[0149] Other time nodes between the baseline time nodes are set sequentially between adjacent stations in the site data map according to their chronological order.
[0150] Based on the above embodiments, as a preferred embodiment, using the time information of the time node as a parameter, sliding the time node along the aligned station data line to obtain the operational dynamics of a single train line includes:
[0151] Confirm the time interval information corresponding to the time node;
[0152] If the time interval information of all time nodes between adjacent stations matches the train running time between adjacent stations, remove all time nodes between adjacent stations.
[0153] Repeat the above steps until all time points except stations are removed from a single train line;
[0154] A sliding time point is set in a single train line, and all train operation unit data when the sliding time point slides along the single train line are used as the operation dynamics of the single train line; the operation dynamics include real-time train status data, traction substation, energy storage information and real-time energy consumption at any time.
[0155] Based on the above embodiments, as a preferred embodiment, it further includes:
[0156] The data query module is used to obtain historical train operation data and historical station data maps; render historical train operation dynamic data based on the historical train operation data and the historical station data maps; integrate the historical station data maps and the station data maps to obtain overlapping station data maps; display the train operation dynamic data in a first display mode and the historical train operation dynamic data in a second display mode in the overlapping station data maps; and compare the train operation dynamic data and the historical train operation dynamic data to generate operation dynamic change data.
[0157] This application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method described in the above method embodiments.
[0158] It is understood that if the methods in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0159] The computer-readable storage medium provided in this embodiment includes the method mentioned above, and has the same effect.
[0160] This application also provides an electronic device, see [link to document]. Figure 4 The present application provides a structural diagram of an electronic device, such as... Figure 4 As shown, it may include a processor 1410 and a memory 1420.
[0161] The processor 1410 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 1410 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 1410 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 1410 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 1410 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.
[0162] The memory 1420 may include one or more computer-readable storage media, which may be non-transitory. The memory 1420 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 1420 is used to store at least the following computer program 1421, which, after being loaded and executed by the processor 1410, is capable of implementing the relevant steps in the methods executed by the electronic device side as disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 1420 may also include an operating system 1422 and data 1423, etc., and the storage method may be temporary storage or permanent storage. The operating system 1422 may include Windows, Linux, Android, etc.
[0163] In some embodiments, the electronic device may further include a display screen 1430, an input / output interface 1440, a communication interface 1450, a sensor 1460, a power supply 1470, and a communication bus 1480.
[0164] certainly, Figure 4 The structure of the electronic device shown does not constitute a limitation on the electronic device in the embodiments of this application. In practical applications, the electronic device may include more than [other components]. Figure 4 More or fewer components as shown, or combinations of certain components.
[0165] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. As the system provided in the embodiments corresponds to the method provided in the embodiments, the description is relatively simple; relevant parts can be found in the method section.
[0166] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of this application.
[0167] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
Claims
1. A method for visualizing the dynamics of train operation, characterized in that, include: Obtain train operation data and station data maps; The train operation data is sorted along a set time series line, and the train operation unit data corresponding to each time node is used as the associated parameter of the time node on the time series line. For each train line, the corresponding time sequence line is aligned with the station data line in the station data diagram, with the station as a fixed node and the time node as an active node. Using the time information of the time node as a parameter, the time node is slid along the aligned station data line to obtain the running dynamics of a single train line; wherein, the sliding starts from the first station where the train begins to run along the train line, and is removed from the station data line when the train stops running. By integrating the operational dynamics of all train lines, train operation dynamic data is rendered. Specifically, the train operation data is sorted along a predetermined time series line, and the train operation unit data corresponding to each time node is used as the associated parameter of that time node along the time series line, including: Obtain the train timetable and construct a time series line based on the train timetable; The train operation data is divided into several train operation unit data based on a set duration; wherein each train operation unit data includes start and end time, current train number, next train number, direction of travel, station time data and arrival data; On the time series line, several time node intervals will be obtained by using the set duration as the unit of division; The train operation unit data is associated with the corresponding start and end times and arrival data to the time node intervals; each time node interval includes the current time node and a line segment extending to the next time node; The process of using the time information of the time node as a parameter and sliding the time node along the aligned station data line to obtain the operational dynamics of a single train line includes: Confirm the time interval information corresponding to the time node; If the time interval information of all time nodes between adjacent stations matches the train running time between adjacent stations, remove all time nodes between adjacent stations. Repeat the above steps until all time points except stations are removed from a single train line; A sliding time point is set in a single train line, and all train operation unit data when the sliding time point slides along the single train line are used as the operation dynamics of the single train line; the operation dynamics include real-time train status data, traction substation, energy storage information and real-time energy consumption at any time.
2. The train operation dynamic visualization method according to claim 1, characterized in that, Before obtaining train operation data and station data maps, the following steps are also included: Determine the location information of each train station; The station data map is generated by scaling the distance between the train stations proportionally based on the location information.
3. The train operation dynamic visualization method according to claim 2, characterized in that, When generating the station data map by proportionally scaling the station spacing between the train stations based on the location information, the method further includes: Train lines exceeding the screen width will be wound according to the set winding rules; Substations and energy storage devices are marked on the station data map according to their actual location data; the substations and energy storage devices are used to indicate the corresponding status data of the train.
4. The train operation dynamic visualization method according to claim 1, characterized in that, For each train line, align the corresponding time series line with the station data line in the station data diagram, treating the station as a fixed node and the time node as an active node, including: For each train line, the arrival time point in the time node is determined, and the time node containing the arrival time point is used as the reference time node and associated with the station in the station data map. Other time nodes between the baseline time nodes are set sequentially between adjacent stations in the site data map according to their chronological order.
5. The train operation dynamic visualization method according to claim 1, characterized in that, After integrating the operational dynamics of all train lines and rendering the train operation dynamic data, it also includes: Obtain historical train operation data and historical station data maps; Historical train operation dynamic data is rendered based on the historical train operation data and the historical station data map. By integrating the historical site data map and the site data map, an overlapping site data map is obtained; In the overlapping station data map, the train operation dynamic data is displayed in a first display mode and the historical train operation dynamic data is displayed in a second display mode; By comparing the train operation dynamic data with the historical train operation dynamic data, dynamic change data of operation is generated.
6. A dynamic visualization system for train operation, characterized in that, include: The data acquisition module is used to acquire train operation data and station data maps; The data processing module is used to sort the train operation data along a set time series line, and on the time series line, the train operation unit data corresponding to each time node is used as the association parameter of the time node; The data alignment module is used to align the corresponding time series line with the station data line in the station data diagram for each train line, treating the station as a fixed node and the time node as an active node. The dynamic output module is used to slide the time node along the aligned station data line using the time information of the time node as a parameter to obtain the running dynamics of a single train line; wherein, the sliding starts from the first station where the train starts running along the train line and is removed from the station data line when the train stops running. The dynamic rendering module is used to integrate the operational dynamics of all train lines and render the train operation dynamic data. The data processing module is a unit for performing the following steps: Obtain the train timetable and construct a time series line based on the train timetable; The train operation data is divided into several train operation unit data based on a set duration; wherein each train operation unit data includes start and end time, current train number, next train number, direction of travel, station time data and arrival data; On the time series line, several time node intervals will be obtained by using the set duration as the unit of division; The train operation unit data is associated with the corresponding start and end times and arrival data to the time node intervals; each time node interval includes the current time node and a line segment extending to the next time node; The dynamic output module is a unit used to perform the following steps: Confirm the time interval information corresponding to the time node; If the time interval information of all time nodes between adjacent stations matches the train running time between adjacent stations, remove all time nodes between adjacent stations. Repeat the above steps until all time points except stations are removed from a single train line; A sliding time point is set in a single train line, and all train operation unit data when the sliding time point slides along the single train line are used as the operation dynamics of the single train line; the operation dynamics include real-time train status data, traction substation, energy storage information and real-time energy consumption at any time.
7. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the train operation dynamic visualization method as described in any one of claims 1 to 5 when executing the computer program.
8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the steps of the train operation dynamic visualization method as described in any one of claims 1 to 5.