Predictive maintenance system, predictive maintenance method, and predictive maintenance computer program

Abstract

An aspect relates to providing a predictive maintenance technique for managing relay service life of train onboard unit relay racks not equipped with operation count functionality. The predictive maintenance method includes collecting a set of onboard unit data including at least a set of command data indicating a set of commands output by a control computer to a set of relay racks to operate the set of relays, generating a command relay list, determining a relay operation count indicating a number of operations for each relay based on the command relay list and the set of command data, and determining a maintenance action for a first relay rack of the set of relay racks when the relay operation count for the first relay rack exceeds a predetermined threshold.

Description

[Technical Field]

[0001] The present disclosure relates to a predictive maintenance system, a predictive maintenance method, and a predictive maintenance computer program. [Background technology]

[0002] As rail systems have become increasingly sophisticated in recent years, the importance of reliably monitoring, collecting, and communicating information related to the operation of rail cars in a rail fleet has likewise increased. By analyzing the operational information collected from rail car systems, useful insights regarding the efficiency and safety of operations can be gained.

[0003] Previously, techniques have been considered for analyzing rail vehicle operational data to detect anomalies. As an example of a railway vehicle data anomaly technique, European Patent Application Publication No. 3988423 (Patent Document 1) discloses "a railway network, a server, a method, and a monitoring system for bimodal railway vehicles, wherein the monitoring system comprises: one or more bimodal railway vehicles of the railway network configured to operate on both electrified and non-electrified sections; one or more beacons located at respective wayside points and configured to broadcast beacon signals indicative of a transition from an electrified section of the railway network to a non-electrified section of the railway network, or vice versa; and a server configured to receive from the given bimodal railway vehicle one or both of a beacon signal received by the given bimodal railway vehicle from a given beacon and a location signal indicative of the position of the given bimodal railway vehicle on the railway network, wherein the server is further configured to determine whether the given beacon, the given bimodal railway vehicle, or a further bimodal railway vehicle is faulty from the received beacon signal and / or the received location signal." [Prior art documents] [Patent documents]

[0004] [Patent Document 1] European Patent Application Publication No. 3988423 Summary of the Invention [Problem to be solved by the invention]

[0005] In modern rail systems, trains are often equipped with on-board units (OBUs) to facilitate train communication and control operations. Typically, these OBUs include a relay rack, each having a plurality of relays, and a control computer that issues commands to the relays in the relay rack set to perform various train control operation functions. By way of example, a relay rack may include relays to monitor and collect sensor data, communicate with wayside devices, perform signaling operations, brake control, etc.

[0006] Each relay installed in a relay rack is associated with a service life. The service life of a relay can be expressed in terms of the estimated number of operations a given relay will perform before failure or replacement. Because unexpected relay failures may cause problems with train communications, signaling, braking, or other operational functions, it is desirable to track the number of operations of each relay to facilitate maintenance and replacement before the relay reaches the end of its service life. Accordingly, some relays are equipped with counters that track the number of times the relay has operated.

[0007] However, not all relays are equipped with an operation counting function. Limiting the use of relays to those with an operation counting function may limit the functionality of the relay and increase the relay installation costs. Patent Document 1 discloses a technique for distinguishing whether a communication failure with a wayside device is due to a fault in the railway vehicle or a fault in the wayside device, but does not consider or disclose a technique for performing predictive maintenance for OBU relays that are not equipped with an operation counting function.

[0008] It is therefore an object of the present disclosure to provide a predictive maintenance technique for managing relay service life in OBU relay racks that are not equipped with operation counting capabilities. [Means for solving the problem]

[0009] One representative example of the present disclosure relates to a predictive maintenance system for train-mounted units, the predictive maintenance system comprising: a train-mounted unit disposed on a train car; and a predictive maintenance device for determining a maintenance action for the train-mounted unit, wherein the train-mounted unit includes a set of relay racks each including a set of relays, and a control computer for outputting commands to operate the sets of relays in the set of relay racks, but does not include a relay operation count function for counting the number of operations of the sets of relays, and the predictive maintenance device includes at least a set of command data indicating a set of commands output by the control computer to the set of relay racks to operate the set of relays; a data collection unit for collecting the set of on-board unit data; a data management unit for generating a command relay list indicating a relationship between the set of commands and the set of relays operated for each command; a data analysis unit for determining a relay operation count indicating the number of operations for each relay in the set of relays based on the command relay list and the set of command data; and a maintenance management unit for determining a maintenance action for a first relay rack in the set of relay racks when the relay operation count of the first relay rack exceeds a predetermined threshold. [Effects of the Invention]

[0010] According to the present disclosure, it is possible to provide a predictive maintenance technique for managing the relay service life of an OBU relay rack that is not equipped with an operation counting function.

[0011] Problems, configurations, and advantages other than those mentioned above will become apparent from the following description of embodiments for carrying out the present invention. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 1 illustrates an exemplary computing architecture for implementing embodiments of the present disclosure. [Figure 2] FIG. 1 illustrates an example hardware configuration of a predictive maintenance system according to an embodiment of the present disclosure. [Figure 3] 1 is a flowchart illustrating a predictive maintenance method according to an embodiment of the present disclosure. [Figure 4] FIG. 10 illustrates a correspondence table according to an embodiment of the present disclosure. [Figure 5] FIG. 10 illustrates a list of command relays according to an embodiment of the present disclosure. [Figure 6] FIG. 10 illustrates a set of relay operation count data according to an embodiment of the present disclosure. [Figure 7] FIG. 10 illustrates a set of relay operation count threshold data according to an embodiment of the present disclosure. [Figure 8] FIG. 10 illustrates a rack error list according to an embodiment of the present disclosure. [Figure 9] FIG. 10 illustrates error count data according to an embodiment of the present disclosure. [Figure 10] FIG. 10 illustrates a set of relay rack usage data according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, embodiments of the present invention will be described with reference to the drawings. It should be noted that the embodiments described herein are not intended to limit the invention according to the claims, and it should be understood that each element and combination described with respect to the embodiments is not strictly necessary to realize aspects of the present invention.

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

[0015] The words "exemplary" and / or "example" are used herein to mean "serving as an example, instance, or illustration." Any aspect described herein as "exemplary" and / or "example" is not necessarily to be construed as preferred or advantageous over other aspects. Likewise, the term "aspects of the present disclosure" does not require that all aspects of the present disclosure include the discussed feature, advantage or mode of operation.

[0016] Further, many aspects are described in terms of sequences of actions to be performed by, for example, elements of a computing device. It will be appreciated that the various actions described herein can be performed by specific circuitry (e.g., an application-specific integrated circuit (ASIC)), by program instructions executed by one or more processors, or by a combination of both. In addition, a sequence of actions described herein can be considered to be entirely embodied in any form of computer-readable storage medium having stored thereon corresponding sets of computer instructions that, when executed, cause an associated processor to perform the functions described herein. Accordingly, various aspects of the present disclosure may be embodied in many different forms, all of which are contemplated to be within the scope of the claimed subject matter.

[0017] Hereinafter, detailed descriptions of embodiments of the present disclosure will be given with reference to the drawings.

[0018] Turning now to the drawings, Figure 1 illustrates a high-level block diagram of a computer system 100 for implementing various embodiments of the present disclosure, according to an embodiment. The mechanisms and apparatus of various embodiments disclosed herein apply equally to any suitable computing system. Major components of 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 communicatively coupled, directly or indirectly, for inter-component communication via memory bus 106, I / O bus 108, bus interface unit 109, and I / O bus interface unit 110.

[0019] Computer system 100 may include one or more general-purpose programmable central processing units (CPUs) 102A and 102B, collectively referred to herein as processors 102. In embodiments, computer system 100 may include multiple processors, although in particular embodiments, 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 on-board cache.

[0020] In embodiments, memory 104 may include random-access semiconductor memory, storage devices, or storage media (either volatile or nonvolatile) for storing or encoding data and programs. In particular embodiments, memory 104 represents the entire virtual memory of computer system 100 and may also include virtual memory of other computer systems coupled to computer system 100 or connected via a network. While memory 104 can be conceptually viewed as a single monolithic entity, in other embodiments, memory 104 is a more complex configuration, such as a hierarchy of caches and other memory devices. For example, memory may exist in the form of multiple levels of caches, and these caches may be further divided by function, such that one cache holds instructions and another cache holds non-instruction data used by one or more processors. Memory may also be distributed and associated with different CPUs or sets of CPUs, as in any of a variety of so-called non-uniform memory access (NUMA) computer architectures.

[0021] Memory 104 may store all or a portion of various programs, modules, and data structures for handling data transfers as discussed herein. For example, memory 104 may store predictive maintenance application 150. In an embodiment, predictive maintenance application 150 may include instructions or statements that execute on, or are interpreted by, processor 102 to perform functions as further described below. In certain embodiments, predictive maintenance application 150 is implemented in hardware via semiconductor devices, chips, logic gates, circuits, circuit cards, and / or other physical hardware devices instead of, or in addition to, a processor-based system. In embodiments, predictive maintenance application 150 may include data in addition to instructions or statements. In certain embodiments, cameras, sensors, or other data input devices (not shown) may be provided in direct communication with bus interface unit 109, processor 102, or other hardware of computer system 100. In such a configuration, the need for processor 102 to access memory 104 and predictive maintenance application 150 may be reduced.

[0022] Computer system 100 may include a bus interface unit 109 that handles communication between processor 102, memory 104, display system 124, and I / O bus interface unit 110. I / O bus interface unit 110 may be coupled to I / O bus 108 to transfer data to and from various I / O units. I / O bus interface unit 110 communicates through I / O bus 108 with multiple I / O interface units 112, 113, 114, and 115, also known as I / O processors (IOPs) or I / O adapters (IOAs). Display system 124 may include a display controller, display memory, or both. The display controller may provide video, audio, or both types of data to display device 126. Additionally, computer system 100 may include one or more sensors or other devices configured to collect and provide data to processor 102. By way of example, 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), motion sensors (e.g., collecting acceleration data, movement data), etc. Other types of sensors are possible. Display memory may be dedicated memory for buffering video data. Display system 124 may be coupled to a display device 126, such as a standalone display screen, a computer monitor, a television, or a tablet or mobile device display. In one embodiment, display device 126 may include one or more speakers for rendering audio. Alternatively, one or more speakers for rendering audio may be coupled to the I / O interface unit. In an alternative embodiment, one or more of the functions provided by display system 124 may be implemented on an integrated circuit that also includes processor 102. Additionally, one or more of the functions provided by bus interface unit 109 may be implemented on an integrated circuit that also includes processor 102.

[0023] The I / O interface unit supports communication with various storage and I / O devices. For example, the terminal interface unit 112 supports the attachment of one or more user I / O devices 116, which may include user output devices (such as a video display device, speakers, and / or a television) and user input devices (such as a keyboard, mouse, keypad, touchpad, trackball, buttons, light pen, or other pointing device). A user may use a user interface to manipulate the user input devices to provide input data and commands to the user I / O devices 116 and the computer system 100, and may 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 displayed on a display device, played through speakers, or printed via a printer.

[0024] Storage interface 113 supports the attachment of one or more disk drives or direct-access storage devices 117 (typically rotating magnetic disk drive storage devices, but can alternatively be other storage devices, including an array of disk drives configured to appear as a single large storage device to a host computer, or solid-state drives such as flash memory). In some embodiments, storage device 117 may be implemented via any type of secondary storage device. The contents of memory 104, or any portion thereof, may be stored in and retrieved from storage device 117 as needed. I / O device interface 114 provides an interface to any of a variety of other I / O devices, or other types of devices, such as printers or facsimile machines. Network interface 115 provides one or more communication paths from computer system 100 to other digital devices and computer systems; these communication paths may include, for example, one or more networks 130.

[0025] 1 depicts a particular bus structure providing direct communication paths between processor 102, memory 104, bus interface 109, display system 124, and I / O bus interface unit 110, in alternative embodiments, computer system 100 may include different buses or communication paths that may be arranged in any of a variety of configurations, such as point-to-point links in a hierarchical, star, or web configuration, multiple tiered buses, parallel or redundant paths, or any other suitable type of configuration. Furthermore, while I / O bus interface unit 110 and I / O bus 108 are depicted as single respective units, computer system 100 may actually encompass multiple I / O bus interface units 110 and / or multiple I / O buses 108. While multiple I / O interface units are depicted isolating I / O bus 108 from the various communication paths leading to the various I / O devices, in other embodiments, some or all of the I / O devices are directly connected to one or more system I / O buses.

[0026] In various embodiments, computer system 100 is a multi-user mainframe computer system, a single-user system, or a server computer, or similar device that has little or no direct user interface but receives requests from other computer systems (clients). In other embodiments, 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 FIG. 2, an exemplary hardware configuration of a rail vehicle data analysis system according to an embodiment of the present disclosure will be described.

[0028] 2 illustrates an exemplary hardware configuration of a predictive maintenance system 200 according to an embodiment of the present disclosure. The predictive maintenance system 200 relates to an information processing system configured to collect a set of on-board unit data from an on-board unit of a rail vehicle, generate a command relay list indicating a relationship between a set of commands and a relay that operates for each command based on the set of on-board unit data, determine a relay operation count indicating the number of operations for each relay, and determine a maintenance action for one or more relay racks based on at least the relay operation count.

[0029] 2 , a predictive maintenance system 200 according to an embodiment of the present disclosure includes a rail vehicle 210, a user terminal 220, a communication network 230, and a predictive maintenance device 240. In the predictive maintenance system 200, the rail vehicle 210, the user terminal 220, and the predictive maintenance device 240 may be communicatively connected via the communication network 230. Here, the communications network 230 may include a local area network (LAN) connection, the Internet, a wide area network (WAN) connection, a metropolitan area network (MAN) connection, and the like.

[0030] In an embodiment, rail vehicle 210 may include one or more rail cars, such as a train, coupled or connected to each other and moving on tracks extending along a path. Alternatively, the cars may not be mechanically connected to each other, but may communicate with each other to coordinate their movement and allow a group of cars to move together along a path in a coordinated manner. Rail vehicle 210 may be used in operations described as freight rail, passenger rail, high-speed rail, commuter rail, rail transit, subway, light rail, streetcar, trolley line, or tramtrain.

[0031] Railcar 210 may include one or more on-board units (OBUs) 215. Here, OBU 215 refers to devices installed on railcar 210 configured to perform various functions facilitating railcar communication and motion control operations. In an embodiment, OBU 215 may be configured to collect sets of on-board unit data characterizing the operation of OBU 215. In an embodiment, OBU 215 may transmit the sets of on-board unit data to a user terminal and / or predictive maintenance device 240 via communications network 230. In certain embodiments, OBU 215 may store the sets of on-board unit data in local storage (e.g., an SD card, a hard drive, etc.) for collection after operation of railcar 210 is completed. As shown in FIG. 2 , OBU 215 includes a control computer 216 and a set of relay racks 217.

[0032] Control computer 216 is a computing device configured to communicate with user terminals, predictive maintenance devices 240, wayside devices, and other external devices, and to issue commands to relays in relay rack set 217. The set of relay racks 217 includes structures that house a set of relays. Each relay rack (1, 2, n) in the set of relay racks 217 may include a set of relays. These relays may be electrically operated switches associated with one or more railcar functions configured to operate in response to specific commands from the control computer 216. By way of example, the set of relay racks 217 may include relays to monitor and collect sensor data, communicate with wayside devices, perform signaling operations, brake control, etc.

[0033] User terminal 220 is a device that can be used by a user (e.g., a client) of predictive maintenance device 240. In an embodiment, user terminal 220 may be used to request analysis by predictive maintenance device 240 of a set of on-board unit data collected from OBU 215 and to review the results of this analysis. By way of example, user terminal 220 may be implemented using a personal computer, a tablet computer, a smartphone, or other computing device.

[0034] Predictive maintenance device 240 is a device configured to collect and analyze sets of on-board unit data to manage the service life of each relay of a set of relays in set of relay racks 217 of OBU 215. In an embodiment, predictive maintenance device 240 may be implemented using computer system 100 shown in FIG. 1 as part of a distributed computing architecture. For example, the functionality of predictive maintenance device 240 may be implemented using one or more computing devices (e.g., computer system 100 shown in FIG. 1) that comprise a cloud infrastructure.

[0035] 2, predictive maintenance device 240 may include a data collection unit 242, a data management unit 244, a data analysis unit 246, a maintenance management unit 248, and a storage unit 250. In an embodiment, data collection unit 242, data management unit 244, data analysis unit 246, and maintenance management unit 248 may be implemented as software modules that make up predictive maintenance application 150 stored in memory 104 of computer system 100 shown in FIG. 1. In this manner, the functions of data collection unit 242, data management unit 244, data analysis unit 246, and maintenance management unit 248 may be performed by processor 102 of computer system 100 to implement the techniques of the present disclosure.

[0036] Data collection unit 242 is a functional unit for acquiring a set of on-board unit data for OBU 215 of railcar 210. The on-board unit data may include at least a set of command data indicating a set of commands output by control computer 216 to set of relay racks 217 to operate a set of relays. In an embodiment, data collection unit 242 may acquire the set of on-board unit data from user terminal 220. For example, a user of user terminal 220 may upload the set of on-board unit data to predictive maintenance device 240 via a graphical user interface provided by data collection unit 242. In an embodiment, data collection unit 242 may send a data collection request directly to railcar 210 to acquire the set of on-board unit data. In a particular embodiment, data collection unit 242 may acquire the set of on-board unit data collected from OBU 215 from a local storage device (e.g., an SD card, a hard drive, etc.) after operation of railcar 210 is completed.

[0037] Data management unit 244 is a functional unit for organizing and manipulating on-board unit data sets with other pre-arranged data to facilitate analysis. Data management unit 244 may generate a correspondence table showing the relationship between a particular train on-board unit, the set of relay racks included in the train on-board unit, and the set of relays in each relay rack in the set of relay racks. In an embodiment, data management unit 244 may generate a command relay list showing the relationship between a set of commands and the set of relays that operate for each command. Additionally, in an embodiment, data management unit 244 may generate a rack error list showing the relationship between error types and sets of relay racks. Data generated by data management unit 244 may be stored in storage unit 250.

[0038] Data analysis unit 246 is a functional unit for performing analysis on the set of on-board unit data and other intermediate data generated by the data management unit to determine information related to the service life of set of relay racks 217 of OBU 215. In an embodiment, data analysis unit 246 may determine a relay operation count indicating the number of operations for each relay in set of relay racks 217 based on the command relay list generated by data management unit 244 and the set of command data included in the on-board unit data. Additionally, in an embodiment, data analysis unit 246 may determine an error count indicating the number of errors for each rack in set of relay racks 217 and / or operation time data indicating the operation duration of set of relay racks 217 of OBU 215.

[0039] The maintenance management unit 248 is a functional unit for determining a maintenance action for one or more relay racks of the set of relay racks 217 based on the information about the service life of the set of relay racks 217 generated by the data analysis unit 246. In an embodiment, the maintenance management unit 248 may determine a maintenance action for a first relay rack of the set of relay racks 217 if the relay operation count, error count, or operation time of the first relay rack exceeds a predetermined threshold.

[0040] The storage unit 250 is a unit for storing various data and information used to implement aspects of the present disclosure. The storage unit 250 may include a collection of hard disk drives, solid-state drives, flash memory, cloud storage, and the like. As shown in FIG. 2 , the storage unit 250 may include a correspondence table, a command relay list, a rack error list, and a set of relay rack usage data. Details of the correspondence table, the command relay list, the rack error list, and the set of relay rack usage data will be described later, so a detailed description thereof will be omitted here. Furthermore, it should be noted that the contents of the storage unit 250 are not limited, and the storage unit 250 may include information other than the command relay list, the rack error list, and the set of relay rack usage data.

[0041] The predictive maintenance system 200 shown in FIG. 2 can provide a predictive maintenance technique for managing relay service life in OBU relay racks that are not equipped with operation counting capabilities.

[0042] Referring now to FIG. 3, a predictive maintenance method according to an embodiment of the present disclosure will be described.

[0043] 3 illustrates a predictive maintenance method 300 according to an embodiment of the present disclosure. The predictive maintenance method 300 is a method for determining a maintenance action for one or more relay racks of an OBU based on usage characteristics of the relay racks of the OBU. The predictive maintenance method 300 may be implemented by various functional units of the predictive maintenance device 240 shown in FIG. 2.

[0044] Initially, in step S305, the data collection unit 242 of the predictive maintenance device 240 acquires a set of on-board unit data. As described herein, the set of on-board unit data is a set of data characterizing the operation of a particular OBU (e.g., OBU 215 shown in FIG. 2 ) installed on a railcar. The set of on-board unit data may include at least a set of command data indicating a set of commands output by the control computer 216 of the OBU 215 to the set of relay racks 217 to operate the set of relays. Additionally, in embodiments, the set of on-board unit data may include a set of error data indicating the presence or absence of an error for each rack of the set of relay racks. Further, in embodiments, the set of on-board unit data may include a set of operating time data indicating the operating duration of the set of relay racks of the train on-board unit. In certain embodiments, the set of on-board unit data may include OBU identification information that identifies the origin of the set of on-board unit data.

[0045] In embodiments, data collection unit 242 may acquire the set of on-board unit data from user terminal 220. For example, a user of user terminal 220 may upload the set of on-board unit data to predictive maintenance device 240 via a graphical user interface provided by data collection unit 242. In embodiments, data collection unit 242 may send a data collection request directly to rail vehicle 210 to dynamically acquire the set of on-board unit data in real time. In certain embodiments, data collection unit 242 may acquire the set of on-board unit data collected from OBU 215 from a local storage device (e.g., an SD card, a hard drive, etc.) after operation of rail vehicle 210 is completed.

[0046] Next, in step S310, the data management unit 244 of the predictive maintenance device 240 generates a correspondence table indicating the relationship between a specific train on-board unit, a set of relay racks included in the train on-board unit, and a set of relays in each relay rack of the set of relay racks. The data management unit 244 may generate the correspondence table based on the set of on-board unit data and a previously prepared set of relay rack identification information. The set of relay rack identification information may include information such as a rack type indicating the type of relay rack, a rack serial number uniquely identifying a specific relay rack, and relay name information identifying a specific relay installed in the relay rack with a specific rack serial number. In an embodiment, the data management unit 244 may generate the correspondence table by associating a set of relay rack identification information with a specific OBU number based on the OBU identification information included in the set of on-board unit data. In this way, a correspondence table indicating the relationship between OBUs, relay racks, and relays for each railcar in the rail network can be established and maintained in the predictive maintenance device 240.

[0047] Next, in step S315, the data management unit 244 generates a command relay list indicating the relationship between the set of commands included in the in-vehicle unit data received in step S305 (e.g., the set of commands issued by the control computer 216 of the OBU 215) and the set of relays that operate for each command. In an embodiment, the data management unit 244 may generate the command relay list based on the set of in-vehicle unit data received in step S305 and the correspondence table generated in step S310. More specifically, the data management unit 244 determines, for each command in the set of commands, which relays listed in the correspondence table are configured to operate for that command, and generates a command relay list indicating the relays that operate for each command. In an embodiment, the data management unit 244 may determine which relays operate for which commands based on previously prepared specification information for each relay (e.g., a specification table provided by the manufacturer). In this way, a command relay list indicating which relays operate for each command in the set of commands included in the in-vehicle unit data collected from the OBU can be generated.

[0048] Next, in step S320, the data analysis unit 246 determines a relay operation count indicating the number of times each relay in the set of relays has operated based on the command relay list generated in step S315 and the set of command data included in the on-board unit data received in step S305. More specifically, the data analysis unit 246 may use the command relay list to determine, for each command in the set of command data, the relay that operates in response to that command and maintain a record indicating the number of times each relay has operated. These records for each relay may be summed to generate a set of relay operation count data indicating the relay operation count for each relay. In an embodiment, the relay operation count for each relay may be combined with previously generated sets of relay operation count data to maintain an accurate representation of the number of times each relay has operated throughout its service life. In this manner, the service life status of each relay in the set of relay racks in the OBU can be determined and managed with respect to the number of operations of each relay, even if the relay does not include an operation count function.

[0049] Next, in step S325, the data management unit 244 generates a rack error list indicating the relationship between the error type and the set of relay racks. In an embodiment, the data management unit 244 may generate the rack error list based on the set of error data included in the set of on-board unit data received in step S305. More specifically, the data management unit 244 may determine, for each error listed in the set of error data, which relay listed in the correspondence table is associated with that error, and generate a rack error list indicating each relay affected by that particular error type. In an embodiment, the data management unit 244 may determine which relays are associated with a particular error type based on previously prepared specifications information for each relay (e.g., a specifications table provided by the manufacturer). In this manner, a rack error list indicating which relays are affected by which error type can be generated.

[0050] Next, in step S330, the data analysis unit 246 determines an error count indicating the number of times an error has occurred for each relay rack in the set of relay racks based on the rack error list generated in step S325, the set of error data included in the on-board unit data received in step S305, and the correspondence table generated in step S310. More specifically, the data analysis unit 246 may use the rack error list to determine, for each error in the error data set, the relay associated with that error type, use the correspondence table to identify the specific relay rack (e.g., rack serial number) containing the affected relay, sum up the total number of errors that have occurred for each relay in each relay rack, and generate a set of error count data indicating the number of times an error has occurred for each relay rack in the set of relay racks. In an embodiment, the error count for each relay rack may be combined with previously generated sets of error count data to maintain an accurate representation of the number of errors that have occurred for each relay rack throughout its service life. In this manner, the service life status of each relay rack in the OBU can be determined and managed with respect to the number of errors that have occurred for each relay rack.

[0051] Next, in step S335, the maintenance management unit 248 determines a maintenance action for one or more relay racks of the set of relay racks. In an embodiment, the maintenance management unit 248 may determine a maintenance action for a particular relay rack (e.g., the first relay rack) if the relay operation count determined in step S320, the error count determined in S330, or the operation time included in the set of operation time data included in the set of on-board unit data acquired in step S305 exceeds a predetermined threshold. Here, a maintenance action refers to a process, operation, activity, or procedure for managing the particular relay rack. In an embodiment, the maintenance action may include performing an inspection of the particular relay rack, replacing one or more relays in the particular relay rack, or repairing one or more relays in the particular relay rack. In a particular embodiment, the maintenance action may be determined based on which of the relay operation count, the determined error count, or the operation time exceeds a predetermined threshold. For example, if the relay operation count and operation time for a particular relay rack do not exceed the predetermined threshold but the error count exceeds the predetermined threshold, the maintenance management unit 248 may decide to perform an inspection for the particular relay rack. Conversely, if the relay operation count and operation time exceed the predetermined threshold but the error count does not exceed the predetermined threshold, the maintenance management unit 248 may decide to perform a replacement operation for the particular relay rack.

[0052] Additionally, the term "predetermined threshold" herein refers to a criterion that defines a boundary for determining when a particular relay rack requires maintenance. In a particular embodiment, the predetermined threshold may include individual thresholds set for a relay operation count, an error count, and an operation time. Note that examples of the predetermined thresholds for the relay operation count, the error count, and the operation time will be described later, and therefore a description thereof will be omitted here.

[0053] In certain embodiments, the maintenance management unit 248 may calculate a total maintenance score indicating the likelihood that a first relay rack requires maintenance based on the relay operation count, error count, and operation time of a particular relay rack. Here, in certain embodiments, the total maintenance score may be calculated by normalizing the relay operation count, error count, and operation time and performing a weighted average. In certain embodiments, the total maintenance score may be calculated using a machine learning technique trained to identify relay racks requiring maintenance using training data including previously collected relay operation counts, error counts, and operation times. The total maintenance score may be expressed as a percentage value between 0 and 100%, with higher values ​​indicating a higher likelihood of requiring maintenance. The method used to calculate the total maintenance score is not particularly limited herein, and existing statistical or machine learning techniques may also be used.

[0054] In an embodiment, the maintenance management unit 248 may be configured to reset the relay operation count, error count, and operation time of a particular relay rack to zero after a maintenance action on the relay rack is completed. In this manner, the usage characteristics of a particular relay rack can be updated to reflect changes in the service life of the relay rack due to the performance of the maintenance action.

[0055] The predictive maintenance method 300 described above allows for the identification of relay racks having relays requiring maintenance, even when the relays do not include an operation counting function. Furthermore, the predictive maintenance method 300 can detect relay racks having relays requiring maintenance based not only on the number of operations performed, but also on information regarding the number of errors that have occurred for relays in each relay rack, taking into account the total operation duration of a particular relay rack. In this way, a more reliable representation of the current state of service life for relays in each relay rack can be obtained.

[0056] Next, with reference to FIG. 4, a correspondence table according to an embodiment of the present disclosure will be described.

[0057] 4 is a diagram illustrating a correspondence table 400 according to an embodiment of the present disclosure. As described herein, the correspondence table 400 is a data table showing relationships between train on-board units, sets of relay racks, and sets of relays. The correspondence table 400 may be generated by the data management unit 244 of the predictive maintenance device 240 based on the sets of on-board unit data and the sets of relay rack identification information and stored in the storage unit 250 shown in FIG. 2.

[0058] As shown in FIG. 4, the correspondence table 400 includes a railcar number 402 , an OBU number 404 , a rack type 406 , a rack serial number 408 , and a relay name 410 .

[0059] The railcar number 402 is a number that uniquely identifies a particular railcar. For example, the railcar number 402 may include "Train 1" and "Train 2" as numbers to identify particular railcars.

[0060] OBU number 404 is a number that uniquely identifies a specific OBU on a specific railcar. For example, OBU number 404 may include "OBU 1" and "OBU 2" as numbers that uniquely identify specific OBUs installed on a specific railcar.

[0061] The rack type 406 is information that identifies the type of a particular relay rack of a particular OBU. By way of example, the rack type 406 may include a TIU rack, an RLU rack, etc. The rack serial number 408 is information for uniquely identifying a specific relay rack included in a specific OBU. For example, the rack serial number 408 may include "TIU-001", "RLU-002", etc.

[0062] The relay name 410 is information for identifying a specific relay included in a specific relay rack of a specific OBU. For example, the relay name 410 may include "EB relay," "SB relay," "relay 2," etc.

[0063] 4, it is possible to determine the correspondence between OBUs, relay racks, and relays for each rail car on a rail network. As described herein, this correspondence table can be used to facilitate the generation of command relay lists, relay operation counts, and error counts used to define the current state of service life of a particular relay rack.

[0064] Next, referring to FIG. 5, a command relay list according to an embodiment of the present disclosure will be described.

[0065] 5 is a diagram illustrating a command relay list 500 according to an embodiment of the present disclosure. As described herein, the command relay list 500 is a data table that shows the relationship between a set of commands exemplified by a particular OBU and a set of relays that act on each command. The command relay list 500 may be generated by the data management unit 244 of the predictive maintenance device 240 based on a set of on-board unit data and stored in the storage unit 250 shown in FIG. 2.

[0066] As shown in FIG. 5, the command relay list 500 includes a set of commands 502 and information about an operating relay 504 . Set of commands 502 are commands issued by an OBU on a particular railcar to operate one or more relays in a set of relay racks. By way of example, the set of commands may include "Command 1" and "Command 2." The operating relay 504 indicates a specific relay that operates in response to a specific command. For example, according to the command relay list 500, "Relay 1," "Relay 2," and "Relay 3" operate in response to "Command 1," and "Relay 1" and "Relay 4" operate in response to "Command 2."

[0067] 5, it is possible to determine which relays in a particular relay rack will operate in response to which commands from the control computer 216 of the OBU 215. As described herein, this correspondence between the set of commands 502 and the operating relays 504 can be used to calculate the number of types each relay has operated, facilitating monitoring of the service life of the set of relay racks.

[0068] Next, with reference to FIG. 6, a set of relay operation count data according to an embodiment of the present disclosure will be described.

[0069] 6 illustrates a relay operation count data set 600 according to an embodiment of the present disclosure. As described herein, a relay operation count data set is a data table indicating the number of times one or more relays in a set of relay racks have operated. The relay operation count data set 600 may be generated by the data analysis unit 246 of the predictive maintenance device 240 based on the command relay list 500, the correspondence table 400, and the set of command data included in the set of on-board unit data collected from the OBU 215.

[0070] As shown in FIG. 6, the relay operation count data set 600 includes a railcar number 602 , an OBU number 604 , a rack type 606 , a rack serial number 608 , a relay name 610 , and a relay operation count 612 . The railcar number 602, OBU number 604, rack type 606, rack serial number 608, and relay name 610 substantially correspond to the railcar number 402, OBU number 404, rack type 406, rack serial number 408, and relay name 410 shown in the correspondence table 400, so detailed explanations thereof will be omitted here.

[0071] The relay operation count 612 is information indicating the number of times a particular relay has operated. For example, as shown in Figure 6, according to the relay operation count data set 600, the EB relay in relay rack "TIU-001" of "OBU 1" in "Train 1" has operated 1000 times, and the SB relay in relay rack "TIU-002" of "OBU 2" in "Train 2" has operated 1400 times.

[0072] Relay operation count data set 600 may maintain information regarding the number of times each relay in a particular relay rack in a particular OBU has operated. As described herein, this relay operation count data set 600 may be used to monitor the service life of relays in a relay rack and to facilitate determining maintenance actions for particular relays (e.g., relays near the end of their service life).

[0073] Referring now to FIG. 7, a set of relay operation count threshold data according to an embodiment of the present disclosure will be described.

[0074] As described herein, aspects of the present disclosure relate to determining a maintenance action for a particular relay rack (e.g., a first relay rack) when a relay operation count, error count, or operation time included in a set of operation time data for that relay rack exceeds a predetermined threshold. The predetermined threshold may be individually pre-set for each of the relay operation count, error count, and operation time. Accordingly, FIG. 7 illustrates a set 700 of relay operation count threshold data in accordance with an embodiment of the present disclosure.

[0075] 7, the relay operation count threshold data set 700 may include a railcar number 702, an OBU number 704, a rack type 706, a rack serial number 708, a relay name 710, a relay operation count 712, and a relay operation count threshold 714. The railcar number 702, OBU number 704, rack type 706, rack serial number 708, relay name 710, and relay operation count 712 substantially correspond to the railcar number 602, OBU number 604, rack type 606, rack serial number 608, relay name 610, and relay operation count 612 shown in the set of relay operation count data 600, and therefore a detailed description thereof will not be provided here.

[0076] The relay operation count threshold 714 is information indicating a particular relay operation count that defines a boundary for determining when a particular relay requires maintenance. The relay operation count threshold 714 may be defined individually for each relay in a set of relay racks. In embodiments, the relay operation count threshold may be determined based on estimated service life information provided in specifications information (e.g., a manufacturer's specifications table) for each relay. In particular embodiments, the relay operation count threshold may be determined based on historical usage data for each of the relays. As described herein, aspects of the disclosure relate to determining a maintenance action for a first relay when the relay operation count for that relay exceeds the corresponding relay operation count threshold. As an example, referring to FIG. 7 , the relay operation counter for the “SB Relay” associated with the relay rack having rack serial number “TIU-001” in OBU 1 is “12,000” and the relay operation count threshold for this relay is “10,000,” so this relay may be identified as a target for a maintenance action.

[0077] In this manner, the relay operation count threshold data set 700 can be used to determine maintenance action for the relay racks containing those relays when the relay operation count exceeds a predetermined relay operation count threshold.

[0078] Next, with reference to FIG. 8, a rack error list according to an embodiment of the present disclosure will be described.

[0079] 8 is a diagram illustrating a rack error list 800 according to an embodiment of the present disclosure. As described herein, the rack error list 800 is a data table showing the relationship between error types and sets of relay racks. The rack error list 800 may be generated by the data management unit 244 of the predictive maintenance device 240 based on a set of error data included in the set of on-board unit data and / or pre-prepared specifications information for each relay (e.g., a manufacturer's specifications table).

[0080] As shown in FIG. 8, the rack error list 800 includes information about the relay rack 802 and the error type 804 . Relay rack 802 indicates the type of relay rack included in a particular relay rack or in a particular OBU unit. By way of example, relay rack 802 may include information for relay rack types, such as "TIU rack" and "RLU rack." Error type 804 indicates a particular type of error associated with a particular relay rack or type of relay rack. For example, according to rack error list 800, a "TIU rack" is associated with "Error 1" and "Error 2," and an "RLU rack" is associated with "Error 3," "Error 4," and "Error 5."

[0081] 8, it is possible to maintain data defining which relays are affected by which types of errors. As described herein, this information can be used to determine the number of errors that have occurred for each relay in a set of relay racks.

[0082] Next, with reference to FIG. 9, a set of error count data according to an embodiment of the present disclosure will be described.

[0083] 9 illustrates a set of error count chambers 900 according to an embodiment of the present disclosure. As described herein, the set of error count data 900 may include a data table indicating the number of times an error has occurred for each relay rack in the set of relay racks. In an embodiment, the set of error count data may also include information indicating a defined error threshold for each relay rack. The set of error count data 900 may be generated by the data analysis unit 246 of the predictive maintenance device 240 based on the rack error list, correspondence table, and set of error data included in the on-board unit data.

[0084] As shown in FIG. 9, the set of error count data 900 may include a railcar number 902, an OBU number 904, a rack type 906, a rack serial number 908, a relay name 910, an error count 912, and an error count threshold 914. The railcar number 902, OBU number 904, rack type 906, rack serial number 908, and relay name 910 substantially correspond to the railcar number 702, OBU number 704, rack type 706, rack serial number 708, and relay name 710 shown in the set of relay operation count threshold data 700, and therefore a detailed description thereof will not be provided here.

[0085] The error count 912 is information indicating the number of times an error has occurred for a particular relay rack. For example, as shown in Figure 9, according to the error count data set 900, four errors have occurred for the "TIU rack" of "OBU 1" on "Train 1."

[0086] The error count threshold 914 is information indicating a particular error count that defines a boundary for determining when a particular relay rack requires maintenance. The error count threshold 914 may be defined individually for each relay rack in a set of relay racks. In embodiments, the error count threshold 914 may be determined based on estimated service life information provided in specifications information (e.g., a manufacturer's specifications table) for each relay in a particular relay rack. In particular embodiments, the error count threshold 914 may be determined based on historical usage data for each of the relays in a particular relay rack. As described herein, aspects of the disclosure relate to determining a maintenance action for a first relay rack when the error count for that relay rack exceeds the corresponding error count threshold. As an example, referring to FIG. 9 , the error count 012 for “TIU Rack” in OBU 2 of Train 2 is “31” and the relay operation count threshold for this relay is “30,” so this relay rack may be identified as a target for a maintenance action.

[0087] In this manner, the set of error count data 900 can be used to determine maintenance action for a relay rack when a number of errors exceeding a predetermined error count threshold occurs for that relay rack.

[0088] Next, with reference to FIG. 10, a set of relay rack usage data according to an embodiment of the present disclosure will be described.

[0089] 10 is a diagram illustrating a set of relay rack usage data 1000 according to an embodiment of the present disclosure. The set of relay rack usage data 1000 may include a data table including usage characteristics of a set of relay racks for one or more OBUs. In an embodiment, the set of relay rack usage data 1000 may be generated by summing the set of relay operation count threshold data 700, the set of error count data 900, and operation time data included in a set of OBU data received from a particular OBU.

[0090] 10 , a set of relay rack usage data 1000 may include a railcar number 1002, an OBU number 1004, a rack type 1006, a rack serial number 1008, a relay name 1010, a relay operation count 1012, a relay operation count threshold 1014, an error count 1016, an error threshold 1018, a rack operation time 1020, and a rack operation time threshold 1022. It should be noted that the railcar number 1002, the OBU number 1004, the rack type 1006, the rack serial number 1008, the relay name 1010, the relay operation count 1012, the relay operation count threshold 1014, the error count 1016, and the error threshold 1018 substantially correspond to those described with reference to FIGS. 6 , 7 , and 9 , and therefore a detailed description thereof will not be repeated here.

[0091] Rack operating hours 1020 is information that indicates the length of time (e.g., how many hours) each relay rack in a set of relay racks has been in operation. In an embodiment, each OBU may keep a record of the total number of hours that each of its relay racks has been in operation and include this information in the set of on-board unit data acquired by data collection unit 242. As an example, referring to FIG. 10, the relay rack associated with rack serial number RLU-001 in OBU 1 has been in operation for a total of 400 hours.

[0092] The rack operation time threshold 1022 is information indicating a particular rack operation time that defines a boundary for determining when a particular relay rack requires maintenance. The rack operation time threshold 1022 may be defined individually for each relay rack in a set of relay racks. In embodiments, the rack operation time threshold 1022 may be determined based on estimated service life information provided in the specifications information for each relay in a particular relay rack. In certain embodiments, the rack operation time threshold 1022 may be determined based on historical usage data for each of the relays in a particular relay rack.

[0093] As described herein, aspects of the disclosure relate to determining a maintenance action for a particular relay rack (e.g., a first relay rack) if a relay operation count, error count, or operation time included in a set of operation time data for that relay rack exceeds a predetermined threshold. Accordingly, in an embodiment, the maintenance management unit 248 may utilize the rack operation time thresholds 1022 to identify any relay racks whose relay operation count, error count, or operation time exceeds the corresponding threshold. As an example, as shown in FIG. 10 , the relay operation count and error count for a relay rack with rack serial number “TIU-002” in OBU 2 of train 2 do not exceed the corresponding thresholds, but the rack operation time of 41,000 hours exceeds the rack operation time threshold of 40,000 hours, so the maintenance management unit 248 may determine to perform a maintenance action for this relay rack.

[0094] In certain embodiments, after determining a maintenance action for a particular relay rack, the maintenance management unit 248 may generate a maintenance notification indicating the determined maintenance action, the relay rack on which the maintenance action should be performed, and a set of relay rack usage data 1000, and send it to the user terminal 220 for confirmation. In an embodiment, the maintenance management unit 248 may be configured to reset the relay operation count, error count, and operation time for a particular relay rack to zero in the set of relay rack usage data 1000 after a maintenance action on the relay rack is completed. In this manner, the usage characteristics of a particular relay rack can be updated to reflect changes in the service life of the relay rack due to the performance of the maintenance action.

[0095] According to the set of relay rack usage data 1000, information regarding various usage characteristics for each relay in each relay rack of a set of relay racks for one or more OBUs can be maintained. Further, as described herein, this set of relay rack usage data 1000 can be used to facilitate identification of a specific relay rack for which maintenance action should be performed, taking into account usage characteristics and estimated service life. Note that in addition to the information shown in FIG. 10 , the set of relay rack usage data 1000 may include additional information regarding the set of relays and usage characteristics of the set of relay racks. For example, in an embodiment, the set of relay rack usage data 1000 may include a maintenance score calculated for each relay rack based on a relay operation count, an error count, and operation time.

[0096] As described herein, aspects of the present disclosure relate to providing predictive maintenance techniques for managing relay service life in OBU relay racks that are not equipped with operation counting capabilities. More particularly, aspects of the present disclosure relate to determining the number of times each relay in one or more relay racks in an OBU has operated based on command data received from the OBU and a command relay list indicating the relationship between specific commands and specific relays. In this manner, it is possible to identify relay racks that have operated a number of times above a threshold as targets for maintenance action.

[0097] Predictive maintenance techniques according to aspects of the present disclosure can detect relay racks that have relays requiring maintenance not only based on the number of operations performed, but also based on information about the number of errors that have occurred for the relays in each relay rack and the total operation duration of a particular relay rack. In this way, a more reliable representation of the current state of service life of the relays in each relay rack can be obtained. Additionally, the maintenance action to be taken for a particular relay rack may be determined according to whether the relay operation count, error count, or operation time exceeds a threshold, thus allowing for the selection of a maintenance action specifically tailored to the operating state of the relay rack. Furthermore, it should be noted that in a configuration in which railcar 210 and predictive maintenance device 240 are configured for direct communication over communication network 230, data collection unit 242 may send data collection requests directly to railcar 210 to dynamically acquire sets of on-board unit data. In this manner, the service life of the relays in each relay track can be monitored in real time, and maintenance actions for the relay racks can be quickly determined while railcar 210 is in operation, without having to wait for railcar 210 to arrive at a depot.

[0098] In this manner, embodiments of the present disclosure may provide a predictive maintenance technique for managing relay service life in OBU relay racks that are not equipped with operation counting functionality, thereby promoting the safety and efficiency of rail vehicle operation.

[0099] As described herein, the present disclosure relates to the following embodiments:

[0100] (Aspect 1) 1. A predictive maintenance system for a train on-board unit, the predictive maintenance system comprising: a train-mounted unit disposed on a train; a predictive maintenance device for determining a maintenance action for the train-mounted unit; The train-mounted unit is a set of relay racks each containing a set of relays; a control computer for outputting commands to operate the set of relays in the set of relay racks; does not include a relay operation counting function for counting the number of operations of the set of relays; the predictive maintenance device: a data collection unit for collecting a set of on-board unit data including at least a set of command data indicative of a set of commands output by the control computer to the set of relay racks to operate the set of relays; a data management unit for generating a command relay list indicating a relationship between the set of commands and the set of relays operating for each command; a data analysis unit for determining a relay operation count indicative of the number of operations for each relay of the set of relays based on the command relay list and the set of command data; a maintenance management unit for determining a maintenance action for a first relay rack in the set of relay racks when the relay operation count for the first relay rack exceeds a predetermined threshold.

[0101] (Aspect 2) 2. The predictive maintenance system of claim 1, wherein the set of on-board unit data comprises: a set of error data indicating the presence or absence of an error for each rack in the set of relay racks; and an operating time indicating an operating duration of the set of relay racks of the train-mounted unit.

[0102] (Aspect 3) 3. The predictive maintenance system of claim 2, wherein the data management unit: generating a correspondence table indicating a relationship between the train on-board units, the set of relay racks, and the set of relays based on the set of on-board unit data and the set of relay rack identification information; generating a command relay list based on the set of on-board unit data; A predictive maintenance system that determines a relay operation count based on a command relay list, a command data set, and a correspondence table.

[0103] (Aspect 4) 4. The predictive maintenance system of claim 3, further comprising: The data management unit generating a rack error list indicating a relationship between an error type and a set of relay racks based on the set of error data; The data analysis unit A predictive maintenance system that uses a rack error list, a set of error data, and a correspondence table to determine an error count indicating the number of errors for each rack in a set of relay racks.

[0104] (Aspect 5) 5. The predictive maintenance system of claim 4, wherein the maintenance management unit: A predictive maintenance system that determines a maintenance action for the first relay rack when a relay actuation count, an error count, or an actuation time for the first relay rack exceeds a predetermined threshold.

[0105] (Aspect 6) 5. The predictive maintenance system of claim 4, wherein the maintenance management unit: calculating a total maintenance score indicating a likelihood that the first relay rack requires maintenance based on the relay operation count, the error count, and the operation time of the first relay rack; A predictive maintenance system that determines a maintenance action for the first relay rack when the relay operation count exceeds a predetermined maintenance score threshold.

[0106] (Aspect 7) The predictive maintenance system according to any one of aspects 4 to 6, wherein the maintenance management unit: The predictive maintenance system resets the relay operation count, error count, and operation time of the first relay rack to zero after the maintenance action on the first relay rack is completed.

[0107] The present invention may be a system, a method, or a computer program product, or a combination thereof. The computer program product may include a computer-readable storage medium (or media) having computer-readable program instructions that cause a processor to implement aspects of the present invention.

[0108] A computer-readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. The computer-readable storage medium can be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. A non-exclusive list of more specific examples of computer-readable storage media includes portable computer diskettes, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), static random access memories (SRAMs), portable compact disc read-only memories (CD-ROMs), digital versatile discs (DVDs), memory sticks, floppy disks, mechanically encoded devices such as punch cards or ridge-in-groove structures with instructions recorded thereon, and any suitable combination of the above. Computer-readable storage medium, as used herein, is not to be construed as being a transitory signal per se, such as radio frequency or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., light pulses through fiber optic cable), or electrical signals transmitted through wires.

[0109] Aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0110] Computer-readable program instructions may be provided to a processor of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus to manufacture a machine, whereby the instructions, executing via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams. These computer-readable program instructions may also be stored on a computer-readable storage medium and can direct a computer, programmable data processing apparatus, and / or other device to function in a particular manner, whereby the computer-readable storage medium having instructions stored thereon includes an article of manufacture containing instructions that implement aspects of the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams.

[0111] The computer-readable program instructions may also be loaded into a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus, or other device to create a computer-implemented process, whereby the instructions executing on the computer, other programmable apparatus, or other device implement the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams.

[0112] The flowcharts and block diagrams in the figures 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 flowcharts or block diagrams may represent a module, segment, or portion of instructions, including one or more executable instructions that implement the specified logical function. In some alternative implementations, the functions shown in the blocks may occur in an order other than that shown in the figures. For example, two blocks shown in succession may in fact be executed substantially concurrently, or the blocks may even be executed in the reverse order, depending on the functionality involved. It is also noted that each block of the block diagrams and / or flowchart diagrams, and combinations of blocks in the block diagrams and / or flowchart diagrams, may be realized by a special-purpose hardware-based system that performs the specified function or operation, or may embody a combination of special-purpose hardware and computer instructions.

[0113] While the foregoing is directed to exemplary embodiments, other and further embodiments of the present invention may be devised without departing from the basic scope of the invention, the scope of which is determined by the following claims. The description of various embodiments of the present disclosure has been presented for purposes of illustration and is not intended to be exhaustive or limiting to 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 described embodiments. The terminology used herein has been selected to explain the principles of the embodiments, practical applications, or technical improvements over technologies found in the marketplace, or to enable others skilled in the art to understand the embodiments disclosed herein.

[0114] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of various embodiments. As used herein, the singular forms "a," "an," and "the" are intended to include the plural unless the context clearly dictates otherwise. "A set of," "A group of," "A group of," and the like are intended to include one or more. Furthermore, it will be understood that the terms "comprise" and / or "comprising," as used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. In the foregoing detailed description of exemplary embodiments of various embodiments, reference has been made to the accompanying drawings (where like numerals represent like elements), which form a part of this disclosure, and in which are shown, by way of illustration, specific exemplary embodiments in which various embodiments may be practiced. These embodiments have been described in sufficient detail to enable those skilled in the art to practice the disclosure, but other embodiments may be utilized, and changes may be made without departing from the scope of the various embodiments. In the above description, numerous specific details are set forth to provide a thorough understanding of various embodiments. However, various embodiments may be practiced without these specific details. In other instances, well-known circuits, structures, and techniques have not been shown in detail so as not to obscure the embodiments. [Explanation of symbols]

[0115] 200: Predictive maintenance system 210:Railway vehicles 215: In-vehicle unit 216: Control computer 217: Relay rack set 220: User terminal 230:Communication Network 240: Predictive maintenance devices 242: Data collection unit 244: Data Management Unit 246: Data Analysis Unit 248: Maintenance Management Unit 250: Storage unit

Claims

1. 1. A predictive maintenance system for a train on-board unit, the predictive maintenance system comprising: a train-mounted unit disposed on a train; a predictive maintenance device for determining a maintenance action for the train-mounted unit; The train-mounted unit is a set of relay racks each containing a set of relays; a control computer for outputting commands to operate the set of relays in the set of relay racks; does not include a relay operation counting function for counting the number of operations of the set of relays; the predictive maintenance device: a data collection unit for collecting a set of on-board unit data including at least a set of command data indicative of a set of commands output by the control computer to the set of relay racks to operate the set of relays; a data management unit for generating a command relay list indicating a relationship between the set of commands and the set of relays operating for each command; a data analysis unit for determining a relay operation count indicative of the number of operations for each relay of the set of relays based on the command relay list and the set of command data; a maintenance management unit for determining a maintenance action for a first relay rack in the set of relay racks when the relay operation count for the first relay rack exceeds a predetermined threshold.

2. The set of on-board unit data comprises: a set of error data indicating the presence or absence of an error for each rack of the set of relay racks; an operating time indicating the operating duration of the set of relay racks of the train-mounted unit; The predictive maintenance system of claim 1 further comprising:

3. The data management unit generating a correspondence table indicating a relationship between the train on-board units, the set of relay racks, and the set of relays based on the set of on-board unit data and the set of relay rack identification information; generating the command relay list based on the set of in-vehicle unit data; determining the relay operation count based on the command relay list, the command data set, and the correspondence table; The predictive maintenance system of claim 2 .

4. The data management unit generating a rack error list indicating a relationship between an error type and the set of relay racks based on the set of error data; The data analysis unit determining an error count indicating the number of errors for each rack of the set of relay racks using the rack error list, the set of error data, and the correspondence table; The predictive maintenance system of claim 3 .

5. The maintenance management unit: determining a maintenance action for the first relay rack when the relay operation count, the error count, or the operation time of the first relay rack exceeds a predetermined threshold; The predictive maintenance system of claim 4 .

6. The maintenance management unit: calculating a total maintenance score indicating a likelihood that the first relay rack requires maintenance based on the relay operation count, the error count, and the operation time of the first relay rack; determining the maintenance action for the first relay rack if the relay operation count exceeds a predetermined maintenance score threshold; The predictive maintenance system of claim 4 .

7. The maintenance management unit: resetting the relay operation count, the error count, and the operation time of the first relay rack to zero after the maintenance action on the first relay rack is completed; The predictive maintenance system of claim 4 .

8. 1. A predictive maintenance method for a train-mounted unit, the train-mounted unit comprising: a set of relay racks each containing a set of relays; a control computer for outputting commands to operate the set of relays in the set of relay racks; does not include a relay operation counting function for counting the number of operations of the set of relays; The predictive maintenance method comprises: collecting a set of on-board unit data from the train on-board units; a set of command data indicating a set of commands to be output by the control computer to the set of relay racks to operate the set of relays; a set of error data indicating the presence or absence of an error for each rack of the set of relay racks; collecting a set of on-board unit data including an operation time indicating an operation duration of the set of relay racks of the train on-board unit; generating a correspondence table indicating a relationship between the train on-board units, the set of relay racks, and the set of relays based on the set of on-board unit data and the set of relay rack identification information; generating a command relay list indicating a relationship between the set of commands and the set of relays that operate for each command based on the set of on-board unit data; determining a relay operation count indicating the number of operations for each relay of the set of relay racks based on the command relay list, the set of command data, and the correspondence table; generating a rack error list indicating a relationship between an error type and the set of relay racks based on the set of error data; determining an error count indicating the number of errors for each rack of the set of relay racks using the rack error list, the set of error data, and the correspondence table; determining a maintenance action for a first relay rack of the set of relay racks when the relay operation count, the error count, or the operation time of the first relay rack exceeds a predetermined threshold.

9. calculating a total maintenance score indicating a likelihood that the first relay rack requires maintenance based on the relay operation count, the error count, and the operation time of the first relay rack; determining the maintenance action for the first relay rack if the relay operation count exceeds a predetermined maintenance score threshold; 10. The predictive maintenance method of claim 8, further comprising:

10. resetting the relay operation count, the error count, and the operation time of the first relay rack to zero after the maintenance action on the first relay rack is completed; 10. The predictive maintenance method of claim 8, further comprising:

11. 1. A predictive maintenance computer program for a train on-board unit, the train on-board unit comprising: a set of relay racks each containing a set of relays; a control computer for outputting commands to operate the set of relays in the set of relay racks; does not include a relay operation counting function for counting the number of operations of the set of relays; The predictive maintenance computer program includes a computer-readable storage medium having embedded thereon program instructions, the computer-readable storage medium being non-transitory in nature, the program instructions being executable by a processor to cause the processor to perform a method, the method comprising: collecting a set of on-board unit data from the train on-board units; a set of command data indicating a set of commands to be output by the control computer to the set of relay racks to operate the set of relays; a set of error data indicating the presence or absence of an error for each rack of the set of relay racks; collecting a set of on-board unit data including an operation time indicating an operation duration of the set of relay racks of the train on-board unit; generating a correspondence table indicating a relationship between the train on-board units, the set of relay racks, and the set of relays based on the set of on-board unit data and the set of relay rack identification information; generating a command relay list indicating a relationship between the set of commands and the set of relays that operate for each command based on the set of on-board unit data; determining a relay operation count indicating the number of operations for each relay of the set of relay racks based on the command relay list, the set of command data, and the correspondence table; generating a rack error list indicating a relationship between an error type and the set of relay racks based on the set of error data; determining an error count indicating the number of errors for each rack of the set of relay racks using the rack error list, the set of error data, and the correspondence table; determining a maintenance action for a first relay rack of the set of relay racks when the relay operation count, the error count, or the operation time of the first relay rack exceeds a predetermined threshold.

Images