Railway vehicle data analysis method, railway vehicle data analysis device, and railway vehicle data analysis computer program

Abstract

Aspects relate to providing rail vehicle data analysis techniques for facilitating detection of rail vehicle stopping accuracy degradation and providing insight into potential causes of the stopping accuracy degradation for a particular rail vehicle. The rail vehicle data analysis method includes obtaining a set of rail vehicle operating data, identifying a set of rail vehicle stopping accuracy values, determining a set of anomalous stopping accuracy values, defining a set of analysis variables that may affect the rail vehicle stopping accuracy, defining a set of analysis functions for identifying the set of analysis variables, extracting data corresponding to a time frame including the set of analysis variables, identifying a set of feature values ​​indicative of potential causes of the anomalous set of stopping accuracy values, and generating a set of output data indicative of the set of feature values ​​for each rail vehicle.

Description

Technical Field

[0001] The present disclosure relates to a railway vehicle data analysis method, a railway vehicle data analysis device, and a railway vehicle data analysis computer program.

Background Art

[0002] In recent years, with the advancement of railway systems, the importance of reliably monitoring, collecting, and transmitting information related to the operation of railway vehicles in a railway vehicle formation has also increased similarly. By analyzing the operation information collected from the railway vehicle system, useful insights regarding operation efficiency and safety can be obtained.

[0003] Conventionally, techniques for analyzing the operation data of railway vehicles to detect abnormalities have been considered. As an example of an abnormal technique for railway vehicle data, Japanese Patent Application Laid-Open No. 2006-117190 (Patent Document 1) discloses that "the object of the present invention is to provide an ATC data analysis system capable of automatically executing analysis processes such as abnormality detection of railway vehicles using ATC data. An ATC analysis device (21) using a database (200) for storing ATC data including ATC chart data transmitted from an ATC device mounted on a railway vehicle is disclosed. The ATC analysis device 21 executes data analysis software for implementing analysis functions including a railway vehicle abnormality detection function, a deceleration measurement function, and a slip / skid detection function using the ATC data."

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] Stopping accuracy is one of the key indicators of operational efficiency in automatic train operation (ATO) systems. Typically, in ATO systems, train stopping control is performed manually, stopping the train at designated locations such as boarding / alighting areas at railway stations. Poor stopping accuracy can cause the train to overshoot or undershoot the designated stopping position, potentially hindering passenger movement and leading to safety concerns.

[0006] The stopping accuracy of a train can be affected by a number of factors, including braking performance, friction, weather conditions, voltage, and train approach speed. Therefore, in order to maintain operational efficiency and safety, it is desirable to detect deterioration in stopping accuracy and diagnose the potential causes of any detected deterioration.

[0007] Patent Document 1 describes analyzing automatic train control (ATC) data to determine the train's speed and emergency brake While technologies have been disclosed for automatically detecting anomalies based on usage patterns, technologies for detecting deterioration in stopping accuracy and technologies for diagnosing the potential causes of any detected deterioration in stopping accuracy have not been considered or provided. As a result, train operators are required to use a trial-and-error approach to estimate the causes of deterioration in the stopping accuracy of railway vehicle systems.

[0008] Therefore, the purpose of this disclosure is to provide a railway vehicle data analysis technique that facilitates the detection of deterioration in the stopping accuracy of railway vehicles and provides insights into the potential causes of deterioration in the stopping accuracy of specific railway vehicles. [Means for solving the problem]

[0009] One representative example of the present disclosure is a railway vehicle data analysis method, comprising: acquiring a set of railway vehicle operation data relating to the operation of a railway vehicle; identifying a first subset of railway vehicle operation data containing a set of railway vehicle stopping accuracy values ​​from the set of railway vehicle operation data using a set of stopping accuracy conditions; determining a second subset of railway vehicle operation data containing a set of abnormal stopping accuracy values ​​from the first subset of railway vehicle operation data using a predetermined stopping accuracy threshold; defining a set of analytical variables related to operational events that may affect the stopping accuracy of a railway vehicle; defining a set of analytical functions for identifying a set of analytical variables in the second subset of railway vehicle operation data; extracting a third subset of railway vehicle operation data corresponding to a time frame containing a set of analytical variables from the second subset of railway vehicle operation data using the set of analytical functions; identifying a set of feature values ​​indicating the potential cause of the set of abnormal stopping accuracy values ​​from the third subset of railway vehicle operation data using statistical analysis techniques; and generating a set of output data showing the set of feature values ​​associated with the set of railway vehicle operation data. [Effects of the Invention]

[0010] According to this disclosure, it is possible to provide a railway vehicle data analysis technique that facilitates the detection of deterioration in the stopping accuracy of railway vehicles and provides insights into the potential causes of deterioration in the stopping accuracy of specific railway vehicles.

[0011] Any issues, configurations, and effects other than those described above will become clear from the following description of embodiments for carrying out the present invention. [Brief explanation of the drawing]

[0012] [Figure 1] Figure 1 shows an exemplary computing architecture for implementing embodiments of the present disclosure. [Figure 2]Figure 2 shows an exemplary hardware configuration of a railway vehicle data analysis system according to an embodiment of the present disclosure. [Figure 3] Figure 3 is a flowchart showing a railway vehicle data analysis method according to an embodiment of the present disclosure. [Figure 4] Figure 4 shows an analysis variable table for storing a set of analysis variables according to an embodiment of the present disclosure. [Figure 5] Figure 5 shows an analytic function table for storing a set of analytic functions according to an embodiment of the present disclosure. [Figure 6] Figure 6 shows a composite analysis function table for storing a set of composite analysis functions according to an embodiment of the present disclosure. [Figure 7] Figure 7 shows a stop accuracy condition table for storing a set of stop accuracy conditions according to an embodiment of the present disclosure. [Figure 8] Figure 8 shows the configuration of a first subset of railway vehicle operation data according to an embodiment of the present disclosure. [Figure 9] Figure 9 shows the configuration of a second subset of railway vehicle operation data according to an embodiment of the present disclosure. [Figure 10] Figure 10 shows the configuration of the output data set according to an embodiment of the present disclosure. [Modes for carrying out the invention]

[0013] Embodiments of the present invention will be described herein with reference to the drawings. It should be noted that the embodiments described herein are not intended to limit the present invention in accordance with the claims, and it should be understood that each element and combination thereof described in relation to the embodiments is not strictly necessary to carry out aspects of the present invention.

[0014] In the following description and the related drawings, various aspects are disclosed. Alternative aspects can be devised without departing from the scope of the present disclosure. Additionally, well-known elements of the present disclosure are not described in detail or are omitted so as not to obscure the relevant details of the present disclosure.

[0015] As used herein, the terms “exemplary” and / or “example” are used to mean “serving as an example, instance, or illustration.” Any aspect described herein as “exemplary” and / or “example” should not necessarily be construed as being more preferred or beneficial than other aspects. Similarly, the term “aspect of the present disclosure” does not require that all aspects of the present disclosure include the recited features, advantages, or characteristics.

[0016] Furthermore, for example, with respect to the order of actions performed by elements of a computing device, many aspects are described. It will be appreciated that the various actions described herein can be performed by a specific circuit (e.g., an application specific integrated circuit (ASIC)), program instructions executed by one or more processors, or a combination of both. Additionally, the order of actions described herein can be embodied as a whole within any form of computer-readable storage medium that stores a corresponding set of computer instructions that, when executed, cause the associated processor to perform the functions described herein. Thus, the various aspects of the present disclosure may be embodied in many different forms, all of which are intended to be within the scope of the subject matter recited in the claims.

[0017] In this specification, a detailed description of embodiments of the present disclosure is described with reference to the drawings.

[0018] Next, referring to the drawings, Figure 1 shows a schematic block diagram of a computer system 100 according to an embodiment for carrying out various embodiments of the present disclosure. The mechanisms and apparatus of the various embodiments disclosed herein are equally applicable to any suitable computing system. The main components of the computer system 100 include one or more processors 102, memory 104, terminal interface 112, storage interface 113, I / O (input / output) device interface 114, and network interface 115, all of which are communicably coupled, directly or indirectly, for intercomponent communication via a memory bus 106, an I / O bus 108, a bus interface unit 109, and an I / O bus interface unit 110.

[0019] The computer system 100 may include one or more general-purpose programmable central processing units (CPUs) 102A and 102B, which are generally referred to herein as processors 102. In embodiments, the computer system 100 may include multiple processors, but in certain embodiments, the computer system 100 may, alternatively, be a single CPU system. Each processor 102 executes instructions stored in memory 104 and may include one or more levels of onboard cache.

[0020] In some embodiments, memory 104 may include random-access semiconductor memory, storage devices, or storage media (either volatile or non-volatile) for storing or encoding data and programs. In certain embodiments, memory 104 may represent the entire virtual memory of computer system 100 and further include virtual memory of other computer systems coupled to or connected to computer system 100 via a network. Conceptually, memory 104 can be viewed as a single monolithic entity, but in other embodiments, memory 104 has a more complex configuration, such as a hierarchy of caches and other memory elements. For example, memory may reside in multiple levels of caches, which may be further divided functionally, so that one cache holds instructions and another holds data other than instructions used by the processor. Memory may also be distributed and associated with different CPUs or sets of CPUs, as is known in any architecture among various so-called heterogeneous memory access (NUMA) computer architectures.

[0021] Memory 104 may store all or part of various programs, modules, and data structures for processing the data transfers described herein. For example, memory 104 may store a railway vehicle data analysis application 150. In embodiments, the railway vehicle data analysis application 150 may include instructions or statements executed on processor 102, or instructions or statements interpreted by instructions or statements executed on processor 102 to perform functions as described later. In certain embodiments, the railway vehicle data analysis application 150 is implemented in hardware via semiconductor devices, chips, logic gates, circuits, circuit cards, and / or other physical hardware devices, either in place of or in addition to a processor-based system. In embodiments, the railway vehicle data analysis application 150 may include data in addition to instructions or statements. In certain embodiments, a camera, sensor, or other data input device (not shown) may be provided in direct communication with the bus interface unit 109 of the computer system 100, the processor 102, or other hardware. In such a configuration, the need for the processor 102 to access the memory 104 and the railway vehicle data analysis application 150 can be reduced.

[0022] The computer system 100 may include a bus interface unit 109 that handles communication between a processor 102, memory 104, a display system 124, and an I / O bus interface unit 110. The I / O bus interface unit 110 may be coupled with an I / O bus 108 to transfer data to and from various I / O units. The I / O bus interface unit 110 communicates with several I / O interface units 112, 113, 114, and 115, also known as I / O processors (IOPs) or I / O adapters (IOAs), via the I / O bus 108. The display system 124 may include a display controller, display memory, or both. The display controller may provide data of the type video, audio, or both to a display device 126. Furthermore, the computer system 100 may include one or more sensors or other devices configured to collect data and provide it to the processor 102. For example, the computer system 100 may include biometric sensors (e.g., collecting heart rate data, stress level data), environmental sensors (e.g., collecting humidity data, temperature data, pressure data), or motion sensors (e.g., collecting acceleration data, motion data). Other types of sensors are also possible. The display memory may be dedicated memory for buffering video data. The display system 124 may be coupled with a display device 126 such as a standalone display screen, a computer monitor, a television, or a tablet or a handheld device display. In one embodiment, the display device 126 may include one or more speakers for rendering sound. Alternatively, one or more speakers for rendering sound may be coupled with an I / O interface unit. In an alternative embodiment, one or more of the functions provided by the display system 124 may be incorporated into an integrated circuit that also includes a processor 102. In addition, one or more of the functions provided by the bus interface unit 109 may be incorporated into an integrated circuit that also includes a processor 102.

[0023] The I / O interface unit supports communication with various storage devices and I / O devices. For example, the terminal interface unit 112 supports the connection of one or more user I / O devices 116, which may include user output devices (such as video display devices, speakers, and / or television receivers) and user input devices (such as keyboards, mice, keypads, touchpads, trackballs, buttons, optical pens, or other pointing devices). The user may use the user interface to operate the user input devices to provide input data and commands to the user I / O devices 116 and the computer system 100, and may also receive output data via the user output devices. For example, the user interface may be presented via the user I / O devices 116, such as by displaying on a display device, playing through speakers, or printing on a printer.

[0024] The storage interface 113 supports the connection of one or more disk drives or direct-access storage devices 117 (typically magnetic disk drive storage devices that rotate, but alternatively, other storage devices including disk drives configured to appear as a single mass storage device to the host computer, or arrays of solid-state drives such as flash memory). In some embodiments, the storage device 117 may be implemented by any type of secondary storage device. The contents of memory 104, or any part thereof, may be stored in the storage device 117 and retrieved from the storage device 117 as needed. The I / O device interface 114 provides an interface to various other I / O devices or other types of devices such as printers or fax machines. The network interface 115 provides one or more communication paths from the computer system 100 to other digital devices and computer systems, and these communication paths may include, for example, one or more networks 130.

[0025] The computer system 100 shown in Figure 1 illustrates a specific bus structure that provides direct communication paths between the processor 102, memory 104, bus interface 109, display system 124, and I / O bus interface unit 110. However, in alternative embodiments, the computer system 100 may include different buses or communication paths that can be configured in any of various forms, such as hierarchical, star-shaped, or web-shaped configurations, multiple hierarchical buses, parallel and redundant paths, or point-to-point links in any other suitable type of configuration. Furthermore, although the I / O bus interface unit 110 and the I / O bus 108 are shown as separate units, the computer system 100 may actually include multiple I / O bus interface units 110 and / or multiple I / O buses 108. While multiple I / O interface units are shown that isolate the I / O bus 108 from various communication paths running to various I / O devices, in other embodiments, some or all of its I / O devices may be directly connected to one or more system I / O buses.

[0026] In various embodiments, the computer system 100 is a multi-user mainframe computer system, a single-user system, or a server computer, or a similar device with little or no direct user interface, but which receives requests from other computer systems (clients). In other embodiments, the computer system 100 may be implemented as a desktop computer, a portable computer, a laptop or notebook computer, a tablet computer, a pocket computer, a telephone, a smartphone, or any other suitable type of electronic device.

[0027] Next, with reference to Figure 2, an exemplary hardware configuration of a railway vehicle data analysis system according to an embodiment of the present disclosure will be described.

[0028] Figure 2 shows an exemplary hardware configuration of a railway vehicle data analysis system 200 according to an embodiment of the present disclosure. The railway vehicle data analysis system 200 relates to an information processing system configured to collect a set of railway vehicle operation data relating to the operation of railway vehicles, to identify data for analysis relating to the stopping accuracy of railway vehicles, to set analysis parameters, and to perform analysis to identify potential causes of deterioration in the stopping accuracy of railway vehicles.

[0029] As shown in Figure 2, the railway vehicle data analysis system 200 according to an embodiment of the present disclosure includes a railway vehicle 210, a user terminal 220, a communication network 230, and a railway vehicle data analysis device 240. In the railway vehicle data analysis system 200, the railway vehicle 210, the user terminal 220, and the railway vehicle data analysis device 240 can be communicated together via the communication network 230. Here, the communication network 230 may include a local area network (LAN) connection, the internet, a wide area network (WAN) connection, or a metropolitan area network (MAN) connection.

[0030] In embodiments, the railway vehicle 210 may include one or more railway vehicles, such as a train mechanically coupled or connected to run along a track extending along a route. Alternatively, the railway vehicles may not be mechanically coupled but may communicate with each other so that the vehicles coordinate their movements and the group of vehicles move in coordination along the route. The railway vehicle 210 may be used in operations described as freight rail, passenger rail, high-speed rail, commuter rail, rail transport, subway, light rail, tram, tram route, or rail-tram vehicle. In embodiments, the railway vehicle 210 may be configured to record a set of railway vehicle operation data that characterizes its operation and performance. This railway vehicle operation data may be transmitted periodically or in real time to a user terminal 220 and a railway vehicle data analysis device 240 via a communication network 230, or it may be stored in the railway vehicle 210's local storage device so that it is manually collected after the operation is complete.

[0031] The user terminal 220 is a device available to users (e.g., clients) of the railway vehicle data analysis device 240. In embodiments, the user terminal 220 may be used to request analysis of a set of railway vehicle operation data recorded for a railway vehicle 210 by the railway vehicle data analysis device 240 and to determine the results of this analysis. Furthermore, in embodiments, the user terminal may be used to allow the user to define a set of analysis variables and / or analysis functions for analyzing the railway vehicle operation data. For example, the user terminal 220 may be implemented using a personal computer, tablet computer, smartphone, or other computing device.

[0032] The railway vehicle data analysis device 240 is configured to analyze a set of railway vehicle operation data to detect deterioration in the stopping accuracy of the railway vehicle 210 and to identify the potential causes of the deterioration in stopping accuracy. In an embodiment, the railway vehicle data analysis device 240 may be implemented using the computer system 100 shown in Figure 1 as part of a distributed computing architecture. For example, the functions of the railway vehicle data analysis device 240 may be implemented using one or more computing devices (e.g., computer system 100) that constitute a cloud infrastructure.

[0033] As shown in Figure 2, the railway vehicle data analysis device 240 may include a data acquisition unit 242, an analysis data extraction unit 244, an analysis management unit 246, and an analysis unit 248. In this embodiment, the data acquisition unit 242, the analysis data extraction unit 244, the analysis management unit 246, and the analysis unit 248 may be implemented as software modules constituting a railway vehicle data analysis application 150 stored in the memory 104 of the computer system 100 shown in Figure 1. Thus, the functions of the data acquisition unit 242, the analysis data extraction unit 244, the analysis management unit 246, and the analysis unit 248 are executed by the processor 102 of the computer system 100, thereby realizing the technology of this disclosure.

[0034] The data acquisition unit 242 is a functional unit for acquiring a set of railway vehicle operation data from the railway vehicle 210. In an embodiment, the data acquisition unit 242 may acquire a set of railway vehicle operation data from a user terminal 220. For example, a user of the user terminal 220 can upload a set of railway vehicle operation data to the railway vehicle data analysis device 240 via a graphical user interface provided by the data acquisition unit 242. In an embodiment, the data acquisition unit 242 may directly send a data acquisition request to the railway vehicle 210 in order to acquire a set of railway vehicle operation data. Alternatively, in a particular embodiment, the railway vehicle 210 may be configured to automatically upload a set of railway vehicle operation data to the data acquisition unit 242. This automatic data upload may be performed at regular time intervals, such as after the occurrence of a specific event (e.g., the departure or arrival of the railway vehicle 210 from a specific location) or in response to the collection of a certain amount of data.

[0035] The analysis data extraction unit 244 is a functional unit that extracts a set of analysis data to be analyzed from the set of railway vehicle operation data acquired by the data acquisition unit 242. In this embodiment, the analysis data extraction unit 244 can use a set of stopping accuracy conditions to identify a first subset of railway vehicle operation data from the set of railway vehicle operation data that includes a set of stopping accuracy values ​​for the railway vehicle 210, and use a predetermined stopping accuracy threshold to determine a second subset of railway vehicle operation data from the first subset of railway vehicle operation data that includes a set of abnormal stopping accuracy values. This second subset of railway vehicle operation data can be used as a set of analysis data.

[0036] The analysis management unit 246 is a functional unit for setting parameters to facilitate the analysis of the set of analysis data extracted by the analysis data extraction unit 244. In the embodiment, the analysis management unit can define a set of analysis variables related to operational events that may affect the stopping accuracy of the railway vehicle 210, and a set of analysis functions for identifying the set of analysis variables within a second subset of the railway vehicle operational data. In the embodiment, the set of analysis variables and the set of analysis functions can be specified based on user input (for example, user input received from a user on the user terminal 220).

[0037] The analysis unit 248 is a functional unit for performing analysis on a set of analysis data (e.g., a second subset of railway vehicle operation data) using parameters (e.g., analysis variables and analysis functions) set by the analysis management unit 246. In this embodiment, the analysis unit 248 can use a set of analysis functions to extract a third subset of railway vehicle operation data from the second subset of railway vehicle operation data that corresponds to a time frame containing a set of analysis variables, use statistical analysis techniques to identify a set of feature values ​​from the third subset of railway vehicle operation data that indicate the potential cause of a set of abnormal stopping accuracy values, and generate a set of output data that shows the set of feature values ​​in relation to the set of railway vehicle operation data. The analysis unit 248 can then provide the set of output data to the user terminal 220.

[0038] According to the railway vehicle data analysis device 240 shown in Figure 2, it is possible to provide railway vehicle data analysis technology that facilitates the detection of deterioration in the stopping accuracy of railway vehicles and provides insights into the potential causes of deterioration in the stopping accuracy of a particular railway vehicle.

[0039] Next, with reference to Figure 3, a railway vehicle data analysis method according to an embodiment of this disclosure will be described.

[0040] Figure 3 shows a railway vehicle data analysis method 300 according to an embodiment of the present disclosure. The railway vehicle data analysis method 300 is a method for analyzing a set of railway vehicle operation data to detect deterioration in the stopping accuracy of a railway vehicle and for identifying the potential causes of said deterioration in stopping accuracy. The railway vehicle data analysis method 300 can be performed by various functional units of the railway vehicle data analysis device 240 shown in Figure 2.

[0041] First, in step S305, the data acquisition unit 242 acquires a set of railway vehicle operation data relating to the operation of the railway vehicle. The set of railway vehicle operation data may be a collection of structured information characterizing the operation of the railway vehicle. For example, the set of railway vehicle operation data may include information on speed, acceleration, brake usage, electrical parameters, stopping accuracy, signals, departure and arrival times, route, and other parameters related to the operation of the railway vehicle. In a particular embodiment, the set of railway vehicle operation data may include a set of time-series operation records, including at least the speed value of the railway vehicle at a particular time while traveling along the route, the stopping accuracy value of the railway vehicle at a particular time while traveling along the route, and the next station tag where the railway vehicle is scheduled to stop on the route. In a particular embodiment, the railway vehicle operation data The set may also be ATC (Automatic Train Control) data.

[0042] In one embodiment, the data acquisition unit 242 may acquire a set of railway vehicle operation data from the user terminal 220. For example, the user of the user terminal 220 shown in Figure 2 may upload the set of railway vehicle operation data to the railway vehicle data analysis device 240 via a graphical user interface provided by the data acquisition unit 242. In another embodiment, the data acquisition unit 242 may directly send a data acquisition request to the railway vehicle 210 to acquire a set of railway vehicle operation data. Alternatively, in one particular embodiment, the railway vehicle 210 may be configured to automatically upload the set of railway vehicle operation data to the data acquisition unit 242. This automatic data upload may be performed at regular time intervals, such as after a specific event occurs (e.g., the departure or arrival of the railway vehicle 210 from a specific location) or in response to the collection of a certain amount of data.

[0043] Next, in step S310, the analysis data extraction unit 244 identifies a first subset of railway vehicle operation data from the set of railway vehicle operation data acquired in step S305, which includes a set of stopping accuracy values ​​for that railway vehicle. As described herein, the set of stopping accuracy values ​​is one or more numerical values ​​indicating the accuracy with which the railway vehicle stops (e.g., its speed becomes zero) at a specified stopping position. In embodiments, the set of stopping accuracy values ​​may include distance values ​​indicating how far the railway vehicle stopped from the specified stopping position. A negative distance value may indicate that the railway vehicle stopped before reaching the specified stopping position (e.g., the railway vehicle undershot the stopping position), a zero value may indicate that the railway vehicle stopped exactly at the specified stopping position, and a positive distance value may indicate that the railway vehicle went beyond the specified stopping position (e.g., the railway vehicle overshot the stopping position). In embodiments, the analysis data extraction unit 244 can identify one or more stopping accuracy values ​​for each of a plurality of predetermined stops for each railway vehicle along the route, and aggregate the identified stopping accuracy values ​​as a first subset of railway vehicle operation data.

[0044] In general, the stopping accuracy values ​​of a railway vehicle can be calculated continuously in real time while the railway vehicle is in operation and stored as a time-series record. For example, records of stopping accuracy values ​​may be calculated and recorded at regular time intervals of approximately several hundred milliseconds. Furthermore, aspects of this disclosure relate to the recognition that the calculated stopping accuracy values ​​may be delayed relative to the actual movement of the railway vehicle due to the time required for sensor data collection and stopping accuracy calculation processing. Therefore, the calculation and generation of stopping accuracy records may continue for several time intervals even after the railway vehicle has actually stopped at a designated stopping position. As a result, the stopping accuracy record that most accurately represents the distance between the railway vehicle and the designated stopping position may not be the stopping accuracy record corresponding to the time the railway vehicle actually stopped, but rather a stopping accuracy record from several hours after the railway vehicle stopped.

[0045] Therefore, from the above perspective, aspects of this disclosure relate to the use of a set of stopping accuracy conditions to identify a set of stopping accuracy values ​​for a railway vehicle. Here, the set of stopping accuracy values ​​may include one or more stopping accuracy values ​​that most accurately represent the distance of the railway vehicle to a particular stopping position. The stopping accuracy conditions refer to requirements that can be used to identify a stopping accuracy record that most accurately represents the stopping accuracy of the railway vehicle to a particular stopping position. An example of stopping accuracy conditions will be described later with respect to Figure 7, and therefore will not be explained here.

[0046] In this embodiment, the analysis data extraction unit 244 extracts from the set of time-series driving records a first time-series driving record in which the speed value of the railway vehicle is zero, a time-series driving record in which the speed value of the railway vehicle is not zero in the immediately preceding time-series driving record, and the immediately following time-series driving record TimelineA set of stopping accuracy values ​​for a railway vehicle may be identified by identifying time-series operating records in which the speed value of the railway vehicle is zero, and time-series operating records in which the next station tag changes in the immediately following time-series operating record. In this way, the analysis data extraction unit 244 can identify stopping accuracy values ​​corresponding to the time when the railway vehicle has traveled at a certain speed, stopped, remains stationary, and has not started moving toward the next station on the route. Subsequently, the analysis data extraction unit 244 may extract, as a first subset of the railway vehicle operating data, the next station tag from the first time-series operating record and the stopping accuracy values ​​from a second time-series operating record that is a predetermined number of records after the first time-series operating record. This predetermined number of records may be determined based on the time-series record calculation time (i.e., the time required for the stopping accuracy values ​​to be calculated and the corresponding records to be created). In this way, the analysis data extraction unit 244 can identify a stopping accuracy value corresponding to the time after the generation of a stopping accuracy value record for a specific designated stopping position is completed. Therefore, it is possible to select the stopping accuracy record that most accurately represents the stopping accuracy of the railway vehicle for a specific stopping position, taking into account the time delay in record generation.

[0047] Next, in step S315, the analysis data extraction unit 244 determines a second subset of railway vehicle operation data from the first subset of railway vehicle operation data identified in step S310, which includes a set of abnormal stopping accuracy values. Here, the set of abnormal stopping accuracy values ​​may include stopping accuracy values ​​that indicate a potential error in the stopping ability of the railway vehicle. The set of abnormal stopping accuracy values ​​can be determined using a predetermined stopping accuracy threshold. In an embodiment, the stopping accuracy threshold may indicate an acceptable range of stopping accuracy values ​​(e.g., -100cm to +100cm). Thus, the analysis data extraction unit 244 can determine a second subset of railway vehicle operation data from the first subset of railway vehicle operation data, which includes time-series operation records having stopping accuracy values ​​that do not fall within the range defined by the stopping accuracy threshold. In addition to the set of abnormal stopping accuracy values, the second subset of railway vehicle operation data also includes operation parameters for the railway vehicle (time-series speed information, and brake It should be noted that this includes usage information, etc. In the embodiment, a second subset of railway vehicle operation data may be sent to a nested space for analysis. This nested space may be a logical space configured for the temporary storage and analysis of railway vehicle operation data.

[0048] Next, in step S320, the analysis management unit 246 may define a set of analysis variables related to operational events that may affect the stopping accuracy of the railway vehicle. The set of analysis variables refers to specific parameters within the set of railway vehicle operation data that are related to operational events that may affect the stopping accuracy of the railway vehicle. Here, operational events refer to any state, incident, action, or situation that occurs during the operation of the railway vehicle. For example, the analysis variables may include slip variables related to operational events in which the wheels of the railway vehicle slip on the rails, velocity variables related to the speed of the railway vehicle, and acceleration variables related to the acceleration of the railway vehicle. The set of analysis variables may be used by the analysis function described later to identify the presence of operational events that may affect the stopping accuracy of the railway vehicle.

[0049] In some embodiments, the analysis management unit 246 may define a set of analysis variables based on user input (for example, the user of the user terminal 220 shown in Figure 2). For example, the user may define a set of analysis variables based on variables that are thought to have an effect on the stopping accuracy of the railway vehicle. In certain embodiments, the analysis management unit 246 may define a set of analysis variables that includes all or some of the parameters defined in the railway vehicle operation data. An example of a set of analysis variables will be described later with respect to Figure 4, and therefore will not be explained here.

[0050] Next, in step S325, the analysis management unit 246 may define a set of analysis functions. The set of analysis functions refers to logical functions for identifying a set of analysis variables defined in step S320 within a second subset of railway vehicle operation data. For example, the set of analysis functions may include a slip function for identifying slip variables within the second subset of railway vehicle operation data, or a velocity function for identifying data corresponding to the time a railway vehicle traveled at a certain speed. In a particular embodiment, the analysis management unit 246 may define a composite analysis function that includes a first analysis function for identifying a first analysis variable in a set of analysis variables within a second subset of railway vehicle operation data, and a second analysis function for identifying a second analysis variable in a set of analysis variables within a second subset of railway vehicle operation data. Examples of sets of analysis functions and composite analysis functions will be described later with respect to Figures 5 and 6, and will therefore not be explained here.

[0051] Next, in step S330, the analysis unit 248 uses the set of analysis functions defined in step S325 to extract a third subset of railway vehicle operation data from a second subset of railway vehicle operation data that corresponds to a predetermined time frame containing a set of analysis variables. As an example, the analysis unit 248 may extract a portion of the second subset of railway vehicle operation data that corresponds to a time frame from 30 seconds before to 10 seconds after the occurrence of an operation event corresponding to a particular analysis variable. In this way, by determining railway vehicle operation data that includes abnormal stopping accuracy values ​​(a second subset), and extracting the portion of this railway vehicle operation data corresponding to the period in which specific operating events that may affect stopping accuracy occurred (a third subset), it becomes easier to analyze the potential causes of abnormal stopping accuracy values.

[0052] Next, in step S335, the analysis unit 248 uses statistical analysis techniques to identify a set of feature values ​​from a third subset of railway vehicle operation data that indicate the potential cause of the set of abnormal stopping accuracy values. In embodiments, the analysis unit 248 may use statistical analysis techniques to identify parameters associated with values ​​classified as statistical outliers. In embodiments, the analysis unit 248 may identify the maximum values ​​of one or more predetermined parameters from within the third subset of railway vehicle operation data as a set of feature values. For example, the analysis unit 248 may identify the maximum speed value and the maximum brake voltage value for a railway vehicle within the third subset of railway vehicle operation data as a set of feature values. In embodiments, this analysis may be performed in nested space.

[0053] Next, in step S340, the analysis unit 248 may generate a set of output data showing a set of feature values ​​associated with a set of railway vehicle operation data. In some embodiments, the analysis unit may visually highlight the feature values ​​for each set of railway vehicle operation data in the set of output data. Furthermore, in certain embodiments, the analysis unit may determine candidate causes for a set of abnormal stopping accuracy values ​​based on the set of feature values ​​and include these candidate causes in the set of output data. The analysis unit can output the set of output data to the user terminal 220 via the communication network 230. An example of the set of output data will be described later with respect to Figure 12, so its description is omitted here.

[0054] According to the railway vehicle data analysis method 300 shown in Figure 3, by using a set of stopping accuracy conditions, it is possible to consider the time delay in record generation and identify a first subset of railway vehicle operation data that includes stopping accuracy records that most accurately represent the stopping accuracy of the railway vehicle for a specific stopping position. Furthermore, by using an analysis function to analyze a second subset of railway vehicle operation data with abnormal stopping accuracy values, it is possible to extract a third subset of railway vehicle operation data that includes the occurrence of operational events that may affect stopping accuracy. Furthermore, by analyzing the third subset of railway vehicle operation data with statistical analysis techniques, it is possible to determine feature values ​​that indicate the potential causes of abnormal stopping accuracy values. In this way, it is possible to provide railway vehicle data analysis technology that facilitates the detection of deterioration in the stopping accuracy of railway vehicles and provides insights into the potential causes of deterioration in the stopping accuracy of specific railway vehicles.

[0055] Next, with reference to Figure 4, the set of analytical variables according to the embodiment of this disclosure will be described.

[0056] Figure 4 shows an analysis variable table 400 for storing a set of analysis variables according to an embodiment of the present disclosure. As shown in Figure 4, the analysis variable table 400 may include a variable number 402, a variable name 404, a variable source address 406, a variable destination address 408, a conversion data 410, a memo 412, and a creator 414. Variable number 402 represents a unique identifier for each analytical variable in the analytical variable table 400.

[0057] Variable name 404 indicates the name of a specific analysis variable. As described herein, the analysis variables in embodiments of this disclosure refer to specific parameters within a set of railway vehicle operation data that relate to operational events that may affect the stopping accuracy of the railway vehicle. For example, as shown in Figure 4, the analysis variables include a slip variable relating to the wheels of the railway vehicle sliding on the rails, a velocity variable relating to the speed of the railway vehicle, an acceleration variable relating to the acceleration of the railway vehicle, an overstop variable relating to the railway vehicle overshooting the stopping position, and an emergency by the railway vehicle. brake Emergency related to usage brake Variables, and the voltage supplied to the railway vehicle (for example, the voltage of the railway vehicle) brake It may include voltage variables related to the voltage supplied to it. As described herein, the analysis variables specified by variable name 404 may be used by the analysis functions described later to identify the presence of operational events that may affect the stopping accuracy of the railway vehicle. In embodiments, a user (for example, a user of user terminal 220 shown in Figure 2) may specify the analysis variables in the analysis variable table 400 based on variables that are thought to affect the stopping accuracy of the railway vehicle. In embodiments, the analysis variable table 400 may be structured to include all or some of the parameters defined in the railway vehicle operation data.

[0058] The variable source address 406 is information that defines the source location of a particular analysis variable within a data file containing a set of railway vehicle operation data. For example, if the data file containing the set of railway vehicle operation data is formatted as a proprietary data file (e.g., a PCF file, a CSV file, or another tabular data format), the variable source address 406 can specify the row and column of the table within the data file that contains the particular analysis variable. The variable destination address 408 is information that defines the destination location of a particular analysis variable, which will be stored within the data file containing the set of railway vehicle operation data after a number base conversion (such as from binary to decimal) or other preprocessing is complete.

[0059] The conversion data 410 is information for specifying the number base conversion to be applied to a particular analytic variable. For example, the conversion data may indicate numerical conversions from binary to decimal, from binary to hexadecimal, or from hexadecimal to decimal.

[0060] Memo 412 contains information to indicate the purpose of a particular analytical variable. Creator 414 indicates the user who defined the specific analysis variable.

[0061] Next, with reference to Figure 5, the set of analytical functions according to the embodiments of this disclosure will be described.

[0062] Figure 5 shows an analytic function table 500 for storing a set of analytic functions according to embodiments of the present disclosure. As shown in Figure 5, the analytic function table 500 may include a function number 502, a function name 504, a function variable 506, a function operator 508, a bit change value (before) 510, a bit change value (after) 512, a range value (lower limit) 514, a range value (upper limit) 516, a memo 518, and an author 520.

[0063] Function number 502 represents a unique identifier for each analytical function in the analytical function table 500.

[0064] The function name 504 indicates the name of a specific analysis function. As described herein, a set of analysis functions is a set of logical functions for identifying a set of analysis variables in the analysis variable table 400 shown in Figure 4 within the railway vehicle operation data (a second subset of the railway vehicle operation data). For example, as shown in Figure 5, a set of analysis functions may include a slip function for identifying slip variables within the second subset of the railway vehicle operation data, or a speed function for identifying data corresponding to the time a railway vehicle traveled at a certain speed. Multiple analysis functions can be defined for a particular analysis variable. For example, the analysis variable table 400 may include a first speed function for identifying railway vehicles traveling at speeds of 60 kilometers per hour or more, and a second speed function for identifying railway vehicles traveling at speeds of 20 to 60 kilometers per hour. In this embodiment, a user (for example, the user of user terminal 220 shown in Figure 2) can specify an analysis function in the analysis function table 500 based on a variable (driving event) that they want to identify within the set of vehicle driving data.

[0065] Function variable 506 indicates an analytical variable that is computed (i.e., identified) by a particular analytical function. For example, function variable 506 may include slip, speed, or emergency brake usage.

[0066] The function operator 508 indicates a state that is specified with respect to a particular analytic variable. For example, as shown in Figure 5, the function operator 508 may include “change,” “greater than or equal to,” “less than or equal to,” or “between.” As an example, a “slip function” with a “change” function operator may be configured to specify any change in the binary bits that indicate the presence or absence of slip in a railway vehicle.

[0067] The bit change value (before) 510 indicates the initial state of a specific bit corresponding to a particular function variable 506 before the change, and the bit change value (after) 512 indicates the final state of a specific bit corresponding to a particular function variable 506 after the change. The bit change value (before) 510 and the bit change value (after) 512 can be used, for example, to monitor changes in binary bits indicating the presence or absence of slip in a railway vehicle.

[0068] The lower limit range value 514 indicates the lower limit of the numerical range of a specific bit corresponding to a particular function variable 506, and the upper limit range value 516 indicates the upper limit of the numerical range of a specific bit corresponding to a particular function variable 506. The lower limit range value 514 and the upper limit range value 516 can be used to monitor railway values ​​associated with a function variable 506 that satisfy a specific numerical range, such as railway vehicles traveling at 60 kilometers per hour or more, or railway vehicles traveling at 20 to 60 kilometers per hour.

[0069] Note 518 contains information to indicate the purpose of a particular analytical function. Creator 520 indicates the user who defined a specific analysis function.

[0070] Next, with reference to Figure 6, the set of composite analysis functions according to the embodiments of this disclosure will be described.

[0071] Figure 6 shows a composite analytic function table 600 for storing a set of composite analytic functions according to an embodiment of the present disclosure. As shown in Figure 6, the composite analytic function table 600 may include a composite analytic function name 602, a composite analytic function logic 604, a memo 606, and an author 608.

[0072] As described herein, in certain embodiments, in addition to the set of analytical functions described above with reference to Figure 5, a set of composite analytical functions may be used to identify a set of analytical variables in railway vehicle operation data. For example, a composite analytical function may be defined as including a first analytical function for identifying a first analytical variable in a set of analytical variables in a second subset of railway vehicle operation data, and a second analytical function for identifying a second analytical variable in a set of analytical variables in railway vehicle operation data. The composite analytical function can be used to identify more detailed operational events in the set of railway vehicle operation data.

[0073] The composite analysis function name 602 indicates the name of a specific composite analysis function. For example, composite analysis function name 602 could include, for example, "fast slip" or "fast and overstop".

[0074] The composite analysis function logic 604 represents the logic for performing a particular composite analysis function. In embodiments, the composite analysis function logic 604 can be specified in terms of the individual analysis functions it includes. For example, the composite analysis function logic 604 may include a “slip function and velocity function (60+)”. This “high-speed slip” function can be used to identify a slip event in a railway vehicle traveling at a speed greater than 60 kilometers per hour. As another example, a “high-speed and overstop” function, defined by “velocity function (60+) and overstop”, can be used to identify an overstop event in a railway vehicle traveling at a speed greater than 60 kilometers per hour.

[0075] Note 606 contains information to indicate the purpose of a particular composite analytic function. Creator 608 indicates the user who defined a specific composite analysis function.

[0076] Next, with reference to Figure 7, the set of stopping accuracy conditions according to the embodiment of this disclosure will be described.

[0077] Figure 7 shows a stop accuracy condition table 700 for storing a set of stop accuracy conditions according to an embodiment of the present disclosure. As described herein, aspects of the present disclosure relate to using a set of stop accuracy conditions to identify a set of railway vehicle stop accuracy values ​​that most accurately represent the distance of a railway vehicle to a particular stopping position, taking into account the delay in time stop accuracy record generation. Accordingly, the stop accuracy condition table 700 shown in Figure 7 shows an example of stop accuracy conditions that can be used to identify a set of stop accuracy values. It should be noted that the stop accuracy conditions shown in Figure 7 are merely examples, and the stop accuracy conditions used to identify a set of railway vehicle stop accuracy values ​​are not particularly limited herein, so that any stop accuracy conditions or logic that can reliably determine a set of stop accuracy values ​​that represent the distance of a railway vehicle to a particular stopping position may be used.

[0078] As shown in Figure 7, the stop accuracy condition table 700 may include stop accuracy conditions 715 for identifying a specific record n ​​from a set of time-series driving records to be included in a first subset of railway vehicle driving data containing a set of stop accuracy values, and recording actions 720 for indicating information to be recorded when a specific record n ​​that satisfies the stop accuracy conditions 715 is identified.

[0079] In this embodiment, the stopping accuracy condition 715 includes a first condition specifying that the speed value of the railway vehicle is zero in a particular first time-series driving record n, a second condition specifying that the speed value of the railway vehicle is not zero in the previous time-series driving record n-1, and the immediately following condition TimelineThis may include a third condition specifying that the vehicle's speed is zero in the n+1 driving record, and a fourth condition specifying that the next station tag in the immediately following n+1 time-series driving record is not the same as the next station tag in the first n time-series driving record. By identifying the first n time-series driving record that satisfies these conditions, it is possible to identify the stop precision value corresponding to the time when the vehicle has traveled at a certain speed, come to a stop, remains stationary, and has not yet started traveling toward the next station on its route (for example, the last n time-series driving record before the vehicle starts traveling toward the next station on its route).

[0080] Once a first time-series driving record n ​​that satisfies the stop accuracy condition 715 is obtained, the action specified in the recording action 720 may be executed. In an embodiment, the recording action 720 may specify that the first time-series driving record n ​​and the stop accuracy value from a second time-series driving record that is a predetermined number of records x later than the first time-series driving record are extracted and recorded as a first subset of railway vehicle driving data. The value of x can be determined based on the average delay time in the calculation and generation of the time-series records. For example, if the stop accuracy calculation takes 400 milliseconds and time-series driving records are made at 100-millisecond intervals, the value of x can be specified as "4". As a result, the time-series driving record that is 4 records later than the first time-series driving record n ​​(corresponding to the time when 400 milliseconds have elapsed since the train reached a stop and the stop accuracy calculation has been completed) is identified as the second time-series driving record. In this way, it is possible to identify the stopping accuracy value corresponding to the time after the generation of the stopping accuracy value record for a specific designated stopping position is completed. Therefore, taking into account the time delay in record generation, it becomes possible to select the stopping accuracy record that most accurately represents the stopping accuracy of the railway vehicle for a specific stopping position.

[0081] Next, with reference to Figure 8, a first subset of railway vehicle operation data according to an embodiment of the present disclosure will be described.

[0082] Figure 8 shows the configuration of a first subset of railway vehicle operation data 800 according to an embodiment of the present disclosure. As described herein, the first subset of railway vehicle operation data 800 is a subset of railway vehicle operation data that includes at least a set of stop accuracy values. As shown in Figure 8, the first subset of railway vehicle operation data 800 may include record number 802, railway vehicle number 804, data file name 806, record time 808, stop accuracy value 810, and station code 812.

[0083] Record number 802 is a number that uniquely identifies a specific data record within the first subset of railway vehicle operation data 800. Railway vehicle number 804 is a number that uniquely identifies a specific railway vehicle.

[0084] The data file name 806 is a file name used to identify the data file containing railway vehicle operation data for a specific railway vehicle. Record time 808 indicates the date and time when a specific data file was recorded.

[0085] The stopping accuracy value 810 represents the stopping accuracy value identified from each set of railway vehicle operation data (e.g., each data file). As shown in Figure 8, the set of stopping accuracy values ​​810 may include normal stopping accuracy values, as well as abnormal stopping accuracy values ​​(shown in bold in Figure 8) that do not meet a predetermined stopping accuracy threshold.

[0086] Station code 812 represents the station code corresponding to the identified set of stopping precision values ​​810. That is, referring to Figure 8, each of the stopping precision values ​​810 was identified for the station code "Tokyo".

[0087] Next, with reference to Figure 9, a second subset of railway vehicle operation data according to an embodiment of the present disclosure will be described.

[0088] Figure 9 shows the configuration of a second subset of railway vehicle operation data 900 according to an embodiment of the present disclosure. As described herein, the second subset of railway vehicle operation data 900 is a subset of the first subset of railway vehicle operation data that includes at least a set of abnormal stopping accuracy values. As shown in Figure 9, the second subset of railway vehicle operation data 900 may include record number 902, data file name 904, and stopping accuracy value 906.

[0089] Record number 902 is a number that uniquely identifies a specific data record within the second subset of railway vehicle operation data 900.

[0090] The data file name 904 is a file name used to identify the data file containing railway vehicle operation data for a specific railway vehicle.

[0091] The stopping accuracy values ​​906 represent a set of abnormal stopping accuracy values ​​determined from a first subset of railway vehicle operation data. As described herein, in embodiments, the set of abnormal stopping accuracy values ​​may be stopping accuracy values ​​within the first subset of railway vehicle operation data that do not fall within the range of acceptable stopping accuracy values ​​specified by the stopping accuracy threshold. For example, if the stopping accuracy threshold specifies a range of -100 centimeters to 100 centimeters, stopping accuracy values ​​150, 300, -200, 350, 230, and 400 may be identified as abnormal stopping accuracy values.

[0092] Next, with reference to Figure 10, the set of output data according to the embodiment of this disclosure will be described.

[0093] Figure 10 shows the configuration of a set of output data 1000 according to an embodiment of the present disclosure. As described herein, the set of output data 1000 is a set of data that includes a set of feature values ​​indicating the potential cause of a set of abnormal stop accuracy values, along with a set of railway vehicle operation data. As shown in Figure 10, the set of output data 1000 may include a record number 1002, a railway vehicle number 1004, a data file name 1006, a time 1008, a first feature value 1010, and a second feature value 1012.

[0094] Record number 1002 is a number that uniquely identifies a specific data record within the set of output data 1000.

[0095] Railway vehicle number 1004 is a number that uniquely identifies a specific railway vehicle.

[0096] The data file name 1006 is a file name used to identify the data file containing railway vehicle operation data for a specific railway vehicle. The time 1008 indicates the date and time when the specific data file was recorded.

[0097] The first feature value 1010 and the second feature value 1012 are values ​​corresponding to specific parameters related to the potential cause of an abnormal set of stopping accuracy values. In embodiments, the first feature value 1010 and the second feature value 1012 may be the maximum values ​​of predetermined parameters present in a set of railway vehicle operation data. In embodiments, the first feature value 1010 and the second feature value 1012 may be identified using statistical analysis techniques to identify parameters related to values ​​classified as statistical outliers. For example, the first feature value 1010 may be the maximum speed value of a railway vehicle in a third subset of railway vehicle operation data, and the second feature value 1012 may be the maximum brake voltage value of a railway vehicle in a third subset of railway vehicle operation data.

[0098] In some embodiments, one or more feature values ​​within the output data set may be visually highlighted. For example, in a particular embodiment, feature values ​​that do not meet the specified normal operating range threshold for the corresponding parameter may be bolded, highlighted, displayed in a different color, or otherwise visually highlighted. As an example, referring to Figure 10, the voltage values ​​"10 volts" and "20 volts" do not meet the normal operating range threshold of "80 volts to 300 volts" and may be visually highlighted in bold font. Similarly, the speed value "1 kilometer per hour" does not meet the normal operating range threshold of "30 kilometers per hour to 80 kilometers per hour" and may also be visually highlighted in bold font.

[0099] Furthermore, in certain embodiments, the analysis unit 248 may be configured to analyze a set of feature values ​​to determine candidate causes for abnormal stopping accuracy values ​​corresponding to specific feature values, and to include these candidate causes in the set of input data. In embodiments, determining candidate causes may involve using a lookup table that shows candidate causes for deterioration in stopping accuracy for a given feature value. For example, using a lookup table, the analysis unit 248 may determine that feature values ​​for speed parameters below a threshold of the normal operating range are candidate causes for deterioration in stopping accuracy. braking It can be determined that this is related to "excessive deceleration during distance." This determined candidate cause 1014 can be added to the set of output data in the form of related metadata or callouts indicating the corresponding feature values.

[0100] As described herein, aspects of this disclosure relate to railway vehicle data analysis techniques for facilitating the detection of deterioration in the stopping accuracy of railway vehicles by analyzing the stopping accuracy values ​​of railway vehicles. However, as described herein, due to the time required for sensor data acquisition and stop accuracy calculation, the calculated stop accuracy values ​​may lag behind the actual movement of the railway vehicle. Therefore, the calculation and generation of stop accuracy records may continue for several time intervals after the railway vehicle has actually stopped at the designated stopping position. As a result, the stop accuracy record that most accurately represents the distance between the railway vehicle and the designated stopping position is not the stop accuracy record corresponding to the time the railway vehicle actually stopped, making it difficult to confirm a reliable stop accuracy value for stopping accuracy evaluation.

[0101] Therefore, from the above perspective, aspects of the present disclosure relate to using a set of stopping accuracy conditions to identify a set of stopping accuracy values ​​for a railway vehicle. By using a set of stopping accuracy conditions, it becomes possible to take into account time delays in record generation and to identify a first subset of railway vehicle operation data, which includes stopping accuracy records that most accurately represent the stopping accuracy of the railway vehicle for a particular stopping position.

[0102] Furthermore, by using a set of analytical functions to analyze a second subset of railway vehicle operation data containing abnormal stopping accuracy values ​​identified from a first subset of railway vehicle operation data, it becomes possible to extract a third subset of railway vehicle operation data containing the occurrence of operational events that may affect the stopping accuracy of railway vehicles. These operational events may include, for example, the use of emergency brakes, slip events, or speeds exceeding the normal operating range. In this way, it becomes possible to pinpoint the portion of railway vehicle operation data in which operational events that ultimately worsened stopping accuracy occurred.

[0103] Furthermore, by analyzing a third subset of railway vehicle operation data using statistical analysis techniques, it is possible to identify feature values ​​that indicate potential causes of abnormal stopping accuracy values. These feature values ​​may correspond to parameters related to the deterioration of stopping accuracy, such as abnormal values ​​of speed or voltage. Based on these feature values, candidate causes of the deterioration of railway vehicle stopping accuracy can be identified.

[0104] Thus, according to the embodiments of this disclosure, it is possible to provide a railway vehicle data analysis technique that facilitates the detection of deterioration in the stopping accuracy of railway vehicles and provides insights into the potential causes of deterioration in the stopping accuracy of a particular railway vehicle.

[0105] As described herein, this disclosure relates to the following embodiments.

[0106] (Aspect 1) A method for analyzing railway vehicle data, To obtain a set of railway vehicle operation data related to the operation of railway vehicles, From a set of railway vehicle operation data using a set of stopping accuracy conditions, identify a first subset of railway vehicle operation data that includes a set of railway vehicle stopping accuracy values, Using a predetermined stopping accuracy threshold, a second subset of railway vehicle operation data containing a set of abnormal stopping accuracy values ​​is determined from a first subset of railway vehicle operation data. To define a set of analytical variables related to operational events that may affect the stopping accuracy of railway vehicles, To define a set of analytical functions for identifying a set of analytical variables within a second subset of railway vehicle operation data, Using a set of analytical functions, a third subset of railway vehicle operation data is extracted from a second subset of railway vehicle operation data, corresponding to a time frame containing a set of analytical variables. Using statistical analysis techniques, we identify a set of feature values ​​from a third subset of railway vehicle operation data that indicate the potential causes of an abnormal set of stopping accuracy values, To generate a set of output data that shows a set of feature values ​​associated with a set of railway vehicle operation data, A method for analyzing railway vehicle data, including the analysis of railway vehicle data.

[0107] (Aspect 2) The set of railway vehicle operation data includes a set of time-series operation records, and the set of time-series operation records includes at least, The speed value of a railway vehicle at a specific time while traveling along a route, The stopping accuracy value of a railway vehicle at a specific time while traveling along a route, Next station tag indicating the next station on the route where the train is scheduled to stop, A railway vehicle data analysis method according to Embodiment 1, including the above.

[0108] (Aspect 3) Identifying the first subset of railway vehicle operation data is Identifying a first time-series operation record from a set of time-series operation records, wherein in the first time-series operation record, The speed value of the railway vehicle is zero. The speed value of the railway vehicle was greater than zero in the previous time-series operating record. Immediately after Timeline In the driving record, the speed value of the railway vehicle is zero. The next station tag is different from the next station tag of the time-series train record immediately following the aforementioned. Identifying and As a first subset of railway vehicle operation data, the next station tag is extracted from the first time-series operation record, and the stop accuracy value is extracted from the second time-series operation record that is a predetermined number of records later than the first time-series operation record. The railway vehicle data analysis method according to embodiment 2, including the method described in embodiment 2.

[0109] (Aspect 4) The predetermined number of records after the first time-series operation record is determined based on the time-series record calculation time, according to the railway vehicle data analysis method described in Embodiment 3.

[0110] (Appendix 5) The set of analysis variables is slip, velocity, acceleration, overstop, and emergency. brake A railway vehicle data analysis method according to any one of embodiments 1 to 4, selected from the group consisting of the use of the following.

[0111] (Aspect 6) Defining a set of analytical functions is Define a composite analytical function that includes a first analytical function for identifying a first analytical variable in a set of analytical variables within a second subset of railway vehicle operation data, and a second analytical function for identifying a second analytical variable in a set of analytical variables within a second subset of railway vehicle operation data. A railway vehicle data analysis method according to any one of embodiments 1 to 5, further including the above.

[0112] (Aspect 7) A railway vehicle data analysis method according to any one of embodiments 1 to 6, further comprising visually highlighting feature values ​​for each set of railway vehicle operation data in the output data set.

[0113] (Pattern 8) Based on the set of feature values, determine the possible causes of an abnormal set of stopping accuracy values, The potential cause should be included in the output data set, A railway vehicle data analysis method according to any one of embodiments 1 to 7, further comprising the above.

[0114] (Aspect 9) A railway vehicle data analysis device, A data acquisition unit configured to acquire a set of railway vehicle operation data related to the operation of railway vehicles, This is an analysis data extraction unit, From a set of railway vehicle operation data using a set of stopping accuracy conditions, identify a first subset of railway vehicle operation data that includes a set of railway vehicle stopping accuracy values. Using a predetermined stopping accuracy threshold, a second subset of railway vehicle operation data containing a set of abnormal stopping accuracy values ​​is determined from a first subset of railway vehicle operation data. The analysis data extraction unit is configured as follows, Analysis management unit, Define a set of analytical variables related to operational events that may affect the stopping accuracy of railway vehicles. Define a set of analytical functions to identify a set of analytical variables within a second subset of railway vehicle operation data. The analysis management unit is configured as follows: It is an analysis unit, Using a set of analytical functions, a third subset of railway vehicle operation data is extracted from a second subset of railway vehicle operation data, corresponding to a time frame containing a set of analytical variables. Using statistical analysis techniques, a third subset of railway vehicle operation data was identified to identify a set of feature values ​​that indicate the potential cause of an abnormal set of stopping accuracy values. Generates a set of output data that shows a set of feature values ​​associated with a set of railway vehicle operation data. The analysis unit is configured as follows: A railway vehicle data analysis device equipped with the following features.

[0115] (Aspect 10) A computer program for analyzing railway vehicle data, comprising a computer-readable storage medium that embodies program instructions, wherein the computer-readable storage medium is not a primary signal in itself, and the program instructions are executable by a processor, and the processor... The acquisition of a set of railway vehicle operation data related to the operation of a railway vehicle, wherein the set of railway vehicle operation data includes the speed value of the railway vehicle at a specific time while traveling along the route, the stopping accuracy value of the railway vehicle at a specific time while traveling along the route, and a next station tag indicating the next station on the route where the railway vehicle is scheduled to stop. To identify a first subset of railway vehicle operation data that includes a set of railway vehicle stopping accuracy values ​​from a set of railway vehicle operation data that uses a set of stopping accuracy conditions, Identifying a first time-series operation record from a set of time-series operation records, wherein in the first time-series operation record, The speed value of the railway vehicle is zero. The speed value of the railway vehicle was greater than zero in the previous time-series operating record. Immediately after Timeline In the driving record, the speed value of the railway vehicle is zero. The next station tag is different from the next station tag of the time-series train record immediately following the aforementioned. Identifying and As a first subset of railway vehicle operation data, the next station tag is extracted from the first time-series operation record, and the stop accuracy value is extracted from the second time-series operation record that is a predetermined number of records later than the first time-series operation record. By doing so, to identify, Using a predetermined stopping accuracy threshold, a second subset of railway vehicle operation data containing a set of abnormal stopping accuracy values ​​is determined from a first subset of railway vehicle operation data. To define a set of analytical variables related to operational events that may affect the stopping accuracy of railway vehicles, To define a set of analytical functions for identifying a set of analytical variables within a second subset of railway vehicle operation data, Using a set of analytical functions, a third subset of railway vehicle operation data is extracted from a second subset of railway vehicle operation data, corresponding to a time frame containing a set of analytical variables. Using statistical analysis techniques, we identify a set of feature values ​​from a third subset of railway vehicle operation data that indicate the potential causes of an abnormal set of stopping accuracy values, To generate a set of output data that shows a set of feature values ​​associated with a set of railway vehicle operation data, A computer program for analyzing railway vehicle data, including methods for performing such actions.

[0116] (Aspect 11) A railway vehicle data analysis system, Railway vehicles and, User terminal and Railway vehicle data analysis device, The railway vehicle data analysis device is equipped with the following features: A data acquisition unit configured to acquire a set of railway vehicle operation data related to the operation of railway vehicles, This is an analysis data extraction unit, From a set of railway vehicle operation data using a set of stopping accuracy conditions, identify a first subset of railway vehicle operation data that includes a set of railway vehicle stopping accuracy values. Using a predetermined stopping accuracy threshold, a second subset of railway vehicle operation data containing a set of abnormal stopping accuracy values ​​is determined from a first subset of railway vehicle operation data. The analysis data extraction unit is configured as follows, Analysis management unit, Define a set of analytical variables related to operational events that may affect the stopping accuracy of railway vehicles. Define a set of analytical functions to identify a set of analytical variables within a second subset of railway vehicle operation data. The analysis management unit is configured as follows: It is an analysis unit, Using a set of analytical functions, a third subset of railway vehicle operation data is extracted from a second subset of railway vehicle operation data, corresponding to a time frame containing a set of analytical variables. Using statistical analysis techniques, a third subset of railway vehicle operation data was identified to identify a set of feature values ​​that indicate the potential cause of an abnormal set of stopping accuracy values. It generates a set of output data representing a set of railway vehicle operation data and a set of associated feature values, and outputs this set of output data to the user terminal. The analysis unit is configured as follows: A railway vehicle data analysis system equipped with the following features.

[0117] The present invention may also be a system, method, and / or a computer program product. This computer program product may include a computer-readable storage medium having computer-readable program instructions for causing a processor to carry out aspects of the present invention.

[0118] A computer-readable storage medium can be a tangible device capable of holding and storing instructions used by an instruction execution device. A computer-readable storage medium may, but is not limited to, electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the above. A non-exhaustive list of more specific examples of computer-readable storage media includes portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disks (DVDs), memory sticks, floppy disks, mechanical encryption devices such as punched cards or grooved raised structures on which instructions are recorded, and any suitable combination of the above. As used herein, a computer-readable storage medium should not be interpreted as a primary signal such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses passing through optical fiber cables), or electrical signals transmitted by wires.

[0119] Aspects of the present invention will be described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It will be understood that each block in the flowcharts and / or block diagrams, as well as any combination of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0120] The computer-readable program instructions described above may be provided to a processor of a general-purpose computer, a dedicated computer, or another programmable data processing device for manufacturing a machine, so as to create a means for instructions executed via the processor of a computer or other programmable data processing device to perform functions / operations explicitly shown in the blocks of a flowchart and / or block diagram. These computer-readable program instructions may also be stored in a computer-readable storage medium that can be made to function in a particular way for computers, programmable data processing devices, and / or other devices, such that the computer-readable storage medium storing the instructions comprises a product containing instructions that perform the modes of functions / operations explicitly shown in the blocks of a flowchart and / or block diagram.

[0121] The computer-readable program instructions described above may be further loaded onto a computer, other programmable device, or other device so that the instructions executed on the computer, other programmable device, or other device perform the functions / operations explicitly shown in the blocks of the flowchart and / or block diagram, so that a series of operation steps are executed on the computer, other programmable device, or other device to create a computer-executed process.

[0122] The flowcharts and block diagrams in the drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, segment, or portion of instructions containing one or more executable instructions for performing a specialized logical function. In some alternative implementations, the functions described in the blocks may occur in an order different from the order shown in the drawings. For example, two blocks shown consecutively may actually be executed almost simultaneously, or the blocks may be executed in reverse order, depending on the functions they relate to. It will also be recognized that each block in the block diagrams and / or flowcharts, as well as combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a system based on specialized hardware that performs a specialized function or operation, or a combination of specialized hardware and computer instructions.

[0123] While the foregoing relates to exemplary embodiments of the present invention, other further embodiments of the present invention may be conceived without departing from the basic scope of the invention, the scope of which will be determined by the claims set forth below. Although the descriptions of the various embodiments of this disclosure are provided for illustrative purposes, they are not intended to be exhaustive or to limit the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the embodiments described. The terms used herein have been chosen to describe the principles of the embodiments, the practical application or improvement of existing technologies, or to enable those skilled in the art to understand the embodiments disclosed herein.

[0124] The terms used herein are for the sole purpose of describing specific embodiments and are not intended to limit the various embodiments. Where used herein, unless the context explicitly indicates otherwise, the singular forms "a," "an," and "the" are intended to include the plural forms as well. "Sets," "groups," "bundles," etc., are intended to include one or more. Furthermore, where used herein, the terms "include" and / or "include" indicate the presence of the described features, numbers, steps, actions, elements, and / or components, but it will be understood that they do not exclude the presence or addition of one or more other features, numbers, steps, actions, elements, components, and / or groups thereof. In the above detailed descriptions of exemplary embodiments of various embodiments, attached drawings forming those parts (similar numbers indicate similar elements) have been referred to, but only specific exemplary embodiments are shown as examples, and various embodiments are possible. While the embodiments described above have been explained in sufficient detail to enable those skilled in the art to practice them, other embodiments are also available, and logical, mechanical, electrical, and other modifications may be made, provided they do not deviate from the scope of the various embodiments. Numerous specific details have been included in the above description to facilitate a full understanding of the various embodiments. However, the various embodiments may be practiced without these specific details. In other instances, well-known circuits, structures, and techniques are not shown in detail to avoid obscuring the embodiments. [Explanation of Symbols]

[0125] 200 Railway Vehicle Data Analysis System 210 Railway Vehicles 220 user terminals 230 Communication Networks 240 Railway Vehicle Data Analysis Device 242 Data Acquisition Unit 244 Analysis Data Extraction Unit 246 Analysis Management Unit 248 Analysis Units

Claims

1. A method for analyzing railway vehicle data, To obtain a set of railway vehicle operation data related to the operation of railway vehicles, Using a set of stopping accuracy conditions, a first subset of railway vehicle operation data is identified from the set of railway vehicle operation data that includes a set of stopping accuracy values ​​that most accurately represent the stopping accuracy of the railway vehicle with respect to a specific stopping position. Using a predetermined stopping accuracy threshold, a second subset of railway vehicle operation data containing a set of abnormal stopping accuracy values ​​is determined from the first subset of the railway vehicle operation data. To define a set of analytical variables related to operational events that may affect the stopping accuracy of the aforementioned railway vehicle, Define a set of analytical functions for identifying the set of analytical variables within the second subset of the aforementioned railway vehicle operation data, Using the set of analysis functions, the second subset of the railway vehicle operation data is used to determine the time frame corresponding to the set of analysis variables. Extracting a third subset of railway vehicle operation data, Using statistical analysis techniques to identify parameters associated with values ​​classified as statistical outliers, a set of feature values ​​is identified from the third subset of the railway vehicle operation data, which are values ​​corresponding to specific parameters related to the potential cause of the abnormal set of stopping accuracy values. To generate a set of output data that shows the set of feature values ​​associated with the set of railway vehicle operation data, A method for analyzing railway vehicle data, including the analysis of railway vehicle data.

2. The aforementioned set of railway vehicle operation data includes a set of time-series operation records, and the aforementioned set of time-series operation records is The speed value of the railway vehicle at a specific time while traveling along the route, The stopping accuracy value of the railway vehicle at a specific time while traveling along the aforementioned route, A next station tag indicating the next station on the route where the aforementioned railway vehicle is scheduled to stop, A railway vehicle data analysis method according to claim 1, comprising at least the following:

3. Identifying the first subset of the aforementioned railway vehicle operation data is: To identify a first time-series operation record from the set of time-series operation records, wherein in the first time-series operation record, The speed value of the aforementioned railway vehicle is zero. The speed value of the aforementioned railway vehicle is greater than zero in the previous time-series operation record. In the immediately following time-series driving record, the speed value of the railway vehicle is zero. The aforementioned next station tag is different from the aforementioned next station tag of the time-series operation record immediately following it. The following conditions are met: As a first subset of the railway vehicle operation data, the next station tag from the first time-series operation record and the stop accuracy value from a second time-series operation record that is a predetermined number of records later than the first time-series operation record are extracted. The railway vehicle data analysis method according to claim 2, including the method described in claim 2.

4. The railway vehicle data analysis method according to claim 3, wherein the predetermined number of records after the first time-series operation record is based on the time-series record calculation time.

5. The railway vehicle data analysis method according to claim 1, wherein the set of analysis variables is selected from the group consisting of slip, speed, acceleration, overstop, and use of emergency brakes.

6. Defining the aforementioned set of analytical functions means that Define a composite analysis function that includes a first analysis function for identifying a first analysis variable in the set of analysis variables within the second subset of the railway vehicle operation data, and a second analysis function for identifying a second analysis variable in the set of analysis variables within the second subset of the railway vehicle operation data. The railway vehicle data analysis method according to claim 1, further comprising:

7. The railway vehicle data analysis method according to claim 1, further comprising visually highlighting, in the set of output data, feature values ​​from the set of feature values ​​that do not meet the threshold for the normal operating range.

8. Based on the set of feature values, a candidate cause for the set of abnormal stopping accuracy values ​​is determined, The set of output data includes the candidate cause, The railway vehicle data analysis method according to claim 1, further comprising:

9. A railway vehicle data analysis device, A data acquisition unit configured to acquire a set of railway vehicle operation data related to the operation of railway vehicles, This is an analysis data extraction unit, Using a set of stopping accuracy conditions, a first subset of the railway vehicle operation data is identified from the set of railway vehicle operation data, which includes a set of stopping accuracy values ​​that most accurately represent the stopping accuracy of the railway vehicle with respect to a specific stopping position. Using a predetermined stopping accuracy threshold, a second subset of railway vehicle operation data is determined from the first subset of railway vehicle operation data, which includes a set of abnormal stopping accuracy values. The analysis data extraction unit is configured as follows, Analysis management unit, A set of analytical variables related to operational events that may affect the stopping accuracy of the aforementioned railway vehicle is defined, Define a set of analytical functions for identifying the set of analytical variables within the second subset of the aforementioned railway vehicle operation data. The analysis management unit is configured as follows: It is an analysis unit, Using the set of analysis functions, a third subset of the railway vehicle operation data is extracted from the second subset of the railway vehicle operation data, corresponding to a time frame containing the set of analysis variables. Using statistical analysis techniques to identify parameters associated with values ​​classified as statistical outliers, a set of feature values ​​is identified from the third subset of the railway vehicle operation data, which are values ​​corresponding to specific parameters related to the potential causes of the set of abnormal stopping accuracy values. A set of output data is generated that shows the set of feature values ​​associated with the set of railway vehicle operation data. The analysis unit is configured as follows: A railway vehicle data analysis device equipped with the following features.

10. A computer program for analyzing railway vehicle data, comprising program instructions, wherein the program instructions are executable by a processor, and the processor, Obtaining a set of railway vehicle operation data related to the operation of a railway vehicle, wherein the set of railway vehicle operation data includes the speed value of the railway vehicle at a specific time while traveling along the route, the stopping accuracy value of the railway vehicle at a specific time while traveling along the route, and a next station tag indicating the next station on which the railway vehicle is scheduled to stop along the route. Identifying a first subset of the railway vehicle operation data from the set of railway vehicle operation data, which includes a set of stopping accuracy values ​​that most accurately represent the stopping accuracy of the railway vehicle with respect to a specific stopping position, using a set of stopping accuracy conditions, wherein identifying the first subset is: Identifying a first time-series operation record from a set of time-series operation records, wherein in the first time-series operation record, The speed value of the aforementioned railway vehicle is zero. The speed value of the aforementioned railway vehicle is greater than zero in the previous time-series operation record. In the immediately following time-series driving record, the speed value of the railway vehicle is zero. The aforementioned next station tag is different from the aforementioned next station tag of the time-series operation record immediately following it. The following conditions are met: As a first subset of the railway vehicle operation data, the next station tag from the first time-series operation record and the stop accuracy value from a second time-series operation record that is a predetermined number of records later than the first time-series operation record are extracted. Identifying by, Using a predetermined stopping accuracy threshold, a second subset of the railway vehicle operation data is determined from the first subset of the railway vehicle operation data, which includes a set of abnormal stopping accuracy values. To define a set of analytical variables related to operational events that may affect the stopping accuracy of the aforementioned railway vehicle, Define a set of analytical functions for identifying the set of analytical variables within the second subset of the aforementioned railway vehicle operation data, Using the set of analysis functions, a third subset of the railway vehicle operation data corresponding to a time frame containing the set of analysis variables is extracted from the second subset of the railway vehicle operation data. Using statistical analysis techniques to identify parameters associated with values ​​classified as statistical outliers, a set of feature values ​​is identified from the third subset of the railway vehicle operation data, which are values ​​corresponding to specific parameters related to the potential cause of the set of abnormal stopping accuracy values. To generate a set of output data that shows the set of feature values ​​associated with the set of railway vehicle operation data, A computer program for analyzing railway vehicle data, including methods for performing such actions.

Images