Signal system fault analysis method and device based on knowledge graph

Abstract

The present invention provides a signal system fault analysis method and device based on a knowledge graph. The method includes: determining the centralized station corresponding to each train based on the current position of each train running on the line and the communication range of each centralized station on the line; when a first faulty device exists on any train at the current moment, retrieving the equipment of the centralized station connected to the first faulty device from the knowledge graph based on the centralized station corresponding to the any train; when a second faulty device exists among the retrieved equipment of the centralized station, determining that the first faulty device and the second faulty device have an associated relationship. The present invention converts the time relationship into a spatial distance relationship by corresponding the train and the centralized station at a certain moment through the positional relationship, thereby reducing the complexity of fault troubleshooting, thereby reducing the time of fault troubleshooting and improving the accuracy of fault analysis.

Description

Technical Field

[0001] The present invention relates to the field of rail transit technology, and in particular to a signal system fault analysis method and device based on a knowledge graph. Background Art

[0002] Urban rail transit signaling systems are highly automated command systems. As operations become more refined, the types of associated equipment are becoming increasingly diverse, placing higher demands on system operation and maintenance capabilities. Fault location is a crucial step in signaling system maintenance. When a fault occurs, the faulty device must be quickly located and addressed.

[0003] Signal system operations and maintenance can be analyzed using knowledge graphs. A knowledge graph is a tool built on a graph database of nodes and relationships that is well-suited to various fault analysis areas. Because the various components of a signal system are interrelated, knowledge graphs typically address this type of problem by adding connections. For example, consider the connection between a centralized station's ground safety system and its ground-based automatic train monitoring system. Because the distance between the two signal subsystems is fixed, the connection between a centralized station's ground safety system and its automatic train monitoring system is static, and the number of such connections is typically small.

[0004] When it comes to related failures between trains and ground equipment, the situation becomes more complex. This is because the connection between trains and ground safety systems or ground train monitoring systems is dynamic. At one moment, a train is connected to the ground system of centralized station A, and at the next moment, it is connected to the ground system of centralized station B. With many trains operating simultaneously, each train may be connected to the ground systems of multiple centralized stations, and each centralized station's ground system may be connected to multiple trains. The number of centralized stations generally ranges from 3 to 10, and the number of trains ranges from 50 to 100. The more centralized stations and trains there are, the more complex the situation becomes. The complexity increases further if cross-line train operations are considered.

[0005] Existing fault analysis techniques based on knowledge graphs add time filtering to each fault. This involves determining whether other faults occurred within a specified timeframe. If so, each fault is correlated with other faults that occurred within that specified timeframe. Correlations between these correlated faults are then used for troubleshooting. Existing fault analysis methods use time filtering to consume significant computing resources and take a long time. Furthermore, correlated fault analysis is inaccurate, making troubleshooting difficult. Summary of the Invention

[0006] The present invention provides a signal system fault analysis method and device based on knowledge graph, which is used to solve the defects of the fault analysis method in the prior art, such as high resource consumption, low efficiency and inaccuracy, thereby reducing the resource consumption of fault analysis and improving the efficiency and accuracy of fault analysis.

[0007] The present invention provides a signal system fault analysis method based on knowledge graph, comprising:

[0008] Determine the central station corresponding to each train according to the current position of each train running on the line and the communication range of each central station on the line;

[0009] In the case that a first faulty device exists on any train at the current moment, the device of the centralized station connected to the first faulty device is retrieved from the knowledge graph according to the centralized station corresponding to the any train;

[0010] In the case that there is a second faulty device among the retrieved devices of the centralized station, it is determined that there is an association relationship between the first faulty device and the second faulty device.

[0011] According to a signal system fault analysis method based on a knowledge graph provided by the present invention, the step of retrieving the device of the centralized station connected to the first faulty device from the knowledge graph according to the centralized station corresponding to any train includes:

[0012] According to the subsystem of the centralized station corresponding to any one of the trains, the devices of the subsystem connected to the first faulty device are retrieved from the knowledge graph.

[0013] According to a signal system fault analysis method based on a knowledge graph provided by the present invention, when there is a second faulty device among the retrieved devices of the centralized station, after the step of determining that there is an association relationship between the first faulty device and the second faulty device, the method further includes:

[0014] If the second faulty device does not exist in the retrieved devices of the centralized station, determining that the fault type of the first faulty device is a first type of fault;

[0015] In the case that there is a second faulty device among the retrieved devices of the centralized station, determining that the fault types of the first faulty device and the second faulty device having an associated relationship are second type faults;

[0016] In a case where any second faulty device has no association relationship with the first faulty devices of all trains, determining that the fault type of the any second faulty device is the first type of fault;

[0017] The fault type of the first faulty device and the fault type of the second faulty device are displayed.

[0018] According to a signal system fault analysis method based on a knowledge graph provided by the present invention, before the step of searching the knowledge graph for devices at the centralized station connected to the first faulty device on any train at the current moment, the method further includes:

[0019] If a device on any train fails at the previous moment and returns to normal at the current moment, the device will be regarded as the first failed device at the current moment.

[0020] According to a signal system fault analysis method based on a knowledge graph provided by the present invention, when there is a second faulty device among the retrieved devices of the centralized station, after the step of determining that there is an association relationship between the first faulty device and the second faulty device, the method further includes:

[0021] When the number of the first faulty devices associated with any second faulty device within a first preset time period is greater than a first preset threshold, it is determined that the second faulty device is faulty.

[0022] According to a signal system fault analysis method based on a knowledge graph provided by the present invention, when there is a second faulty device among the retrieved devices of the centralized station, after the step of determining that there is an association relationship between the first faulty device and the second faulty device, the method further includes:

[0023] If the number of the second faulty devices associated with any first faulty device within a second preset time period is greater than a second preset threshold, it is determined that the first faulty device is faulty.

[0024] The present invention also provides a signal system fault analysis device based on a knowledge graph, comprising:

[0025] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the program, it implements any of the above-described signal system fault analysis methods based on knowledge graphs.

[0026] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described signal system fault analysis methods based on knowledge graphs.

[0027] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-described signal system fault analysis methods based on knowledge graphs. The signal system fault analysis method based on knowledge graphs provided by the present invention improves the accuracy of the associated fault analysis and thus improves the speed of fault detection by associating a train that has a fault at a certain moment with its corresponding centralized station, searching the knowledge graph for a second fault device in the centralized station that has a connection relationship with the first fault device, and determining that it has an associated relationship with the first fault device; by corresponding the train at a certain moment with the centralized station through a positional relationship, the time relationship is converted into a spatial distance relationship, thereby reducing the complexity of fault detection, thereby reducing the time of fault detection and improving the accuracy of fault analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0029] Figure 1 This is one of the flow charts of the signal system fault analysis method based on knowledge graph provided by the present invention;

[0030] Figure 2 This is the second flow chart of the signal system fault analysis method based on knowledge graph provided by the present invention;

[0031] Figure 3 It is a structural diagram of the signal system fault analysis device based on knowledge graph provided by the present invention;

[0032] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0033] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0034] The following combination Figure 1-Figure 2 The present invention describes a signal system fault analysis method based on a knowledge graph, which includes:

[0035] Step 101, determining the central station corresponding to each train based on the current position of each train running on the line and the communication range of each central station on the line;

[0036] Multiple centralized stations are arranged in sequence along the line. Each centralized station has its corresponding communication range on the line, and the communication range of multiple centralized stations covers the entire line.

[0037] When a train reaches a specific location on the line at a certain moment, it is determined that the location is within the communication range of a certain centralized station, and the train is matched with the centralized station at this moment.

[0038] For example, the starting position of the line is 0km, the ending position of the line is 20km, and the communication radius of each centralized station is 10km. There are two centralized stations, centralized station A and centralized station B, in this section of the line. The communication range of centralized station A covers the line from 0 to 10km, and the communication range of centralized station B covers the line from 10 to 20km. If the train is currently at a position of 5km in the line, the train is in the communication range of centralized station A, corresponding to centralized station A; if the train is currently at a position of 12km in the line, the train is in the communication range of centralized station B, corresponding to centralized station B.

[0039] Step 102: If a first faulty device exists on any train at the current moment, retrieve the device of the centralized station connected to the first faulty device from the knowledge graph according to the centralized station corresponding to the train;

[0040] The first faulty device is a train device, which includes devices on the train that need to be connected to the centralized station, such as communication equipment for connecting to the ground safety subsystem; and also includes devices that do not need to communicate with the centralized station, such as the train's automatic protection subsystem.

[0041] The train has a first faulty device at the current moment, that is, a device on the train is in a faulty state at the current moment, and the fault of the train needs to be checked.

[0042] If the first faulty device is a device on the train that needs to be connected to the central station, when the first faulty device detects a fault, it may be caused by its own fault or by the equipment at the central station to which it is connected. Therefore, when troubleshooting the fault, it is necessary to also troubleshoot the equipment at the central station to which it is connected.

[0043] When it is detected that any train has a first faulty device at any moment, the centralized station corresponding to the train at this moment is determined based on the train's location at this moment, and the equipment of the centralized station that has a connection relationship with the first faulty device is retrieved from the knowledge graph.

[0044] Among them, the association relationship between each node of the knowledge graph is set according to the centralized station division method of the signal system. The nodes in the knowledge graph include nodes representing train equipment and nodes representing equipment at centralized stations. If there is a connection relationship between a certain train equipment and a certain centralized station equipment, the corresponding two nodes in the knowledge graph are connected by a line segment.

[0045] The knowledge graph can integrate data from multiple consecutive moments into a set of data, and determine the correlation between faults between trains and between trains and equipment in centralized stations based on the correlation between the positions of trains.

[0046] By using the existing knowledge content of the signal system to construct the association relationship of the knowledge graph, the processing mode of the signal system can be better continued when performing fault retrieval through the knowledge graph, and the analysis ability of related faults is improved with less additional investment. It is easy to use and economical.

[0047] Step 103: If there is a second faulty device among the retrieved devices of the centralized station, determine whether there is an association relationship between the first faulty device and the second faulty device.

[0048] The equipment in the centralized station includes equipment that needs to be connected to the train and equipment that does not need to be connected to the train. The second faulty equipment refers to equipment that has a fault in the centralized station.

[0049] If there is a second faulty device among the devices of the centralized station retrieved through the knowledge graph, then the second faulty device is a device that needs to be connected to the train. At this time, it is determined that there is an association relationship between the second faulty device and the first faulty device.

[0050] That is, the failures of the first faulty device and the second faulty device may be caused by the first faulty device and / or the second faulty device. When troubleshooting, it is necessary to troubleshoot the first faulty device and the second faulty device at the same time.

[0051] The signal system fault analysis method based on the knowledge graph of the present invention improves the accuracy of the associated fault analysis and thus improves the speed of fault detection by associating a train that has a fault at a certain moment with its corresponding centralized station, searching the knowledge graph for a second fault device in the centralized station that has a connection relationship with the first fault device, and determining that it has an associated relationship with the first fault device; by making the train at a certain moment correspond to the centralized station through a positional relationship, the time relationship is converted into a spatial distance relationship, thereby reducing the complexity of fault detection, thereby reducing the time of fault detection and improving the accuracy of fault analysis.

[0052] In the signal system fault analysis method based on the knowledge graph of the present invention, the step of retrieving the device of the centralized station connected to the first faulty device from the knowledge graph according to the centralized station corresponding to any one of the trains includes:

[0053] According to the subsystem of the centralized station corresponding to any one of the trains, the devices of the subsystem connected to the first faulty device are retrieved from the knowledge graph.

[0054] In the knowledge graph, the centralized station includes multiple subsystems, each of which includes different equipment, some of which need to be connected to the train, while some do not.

[0055] Optionally, the subsystem includes a ground safety subsystem and a ground train automatic supervision subsystem.

[0056] When a train has a first faulty device at a certain moment, the train's position at that moment can be optionally determined through the train timetable, and then the central station corresponding to the train at that moment can be determined, and the second faulty device connected to the first faulty device can be retrieved in the knowledge graph corresponding to the central station according to the logic of central station-subsystem-device.

[0057] In the signal system fault analysis method based on the knowledge graph of the present invention, after the step of determining that there is an association relationship between the first faulty device and the second faulty device when there is a second faulty device among the retrieved devices of the centralized station, the method further includes:

[0058] If the second faulty device does not exist in the retrieved devices of the centralized station, determining that the fault type of the first faulty device is a first type of fault;

[0059] The first type of fault is a single fault, which means that the fault occurs in the device itself rather than being caused by faults of other devices associated with it.

[0060] There is no second faulty device among the retrieved centralized station devices, that is, there is no centralized station device that is connected to the first faulty device. At this time, it is determined that the fault of the first faulty device is caused by the device itself, and the fault can be solved by checking the first faulty device.

[0061] In the case that there is a second faulty device among the retrieved devices of the centralized station, determining that the fault types of the first faulty device and the second faulty device having an associated relationship are second type faults;

[0062] The second type of fault is an associated fault, which means that the fault may be caused by the first faulty device and / or a second faulty device connected to the first faulty device.

[0063] There is a second faulty device among the retrieved centralized station devices, that is, there is a centralized station device connected to the first faulty device in the centralized station. At this time, when troubleshooting, it is necessary to troubleshoot the first faulty device and the second faulty device.

[0064] In a case where any second faulty device has no association relationship with the first faulty devices of all trains, determining that the fault type of the any second faulty device is the first type of fault;

[0065] If a second faulty device is not associated with any first faulty device on any train, it indicates that the second faulty device is a device in the central station that does not need to be connected to the train and its fault is caused by itself. Therefore, the fault type of the faulty device is determined to be a first-class fault. During troubleshooting, the fault can be resolved by troubleshooting the second faulty device.

[0066] The fault type of the first faulty device and the fault type of the second faulty device are displayed.

[0067] Optionally, the first type of fault and the second type of fault are displayed and marked in the signal system by different colors.

[0068] If the fault type of a first faulty device is a second-class fault and the fault is caused by itself, then before the fault is resolved, for each centralized station it passes through, the second faulty device connected to it will be displayed as a faulty state, increasing the difficulty of fault detection and resolution.

[0069] Therefore, when troubleshooting, priority is given to troubleshooting and resolving the first faulty device and the second faulty device whose fault type is the second type of fault.

[0070] In the signal system fault analysis method based on the knowledge graph of the present invention, before the step of searching the knowledge graph for the equipment of the centralized station connected to the first faulty equipment in any train at the current moment, based on the centralized station corresponding to the train, the method further includes:

[0071] If a device on any train fails at the previous moment and returns to normal at the current moment, the device will be regarded as the first failed device at the current moment.

[0072] During the time period of the current moment, if a device on the train experienced a fault at the previous moment and has returned to normal at the current moment, this device is still considered the first faulty device at this moment. The knowledge graph is searched to see if there is a second faulty device associated with it among the devices at the centralized station. If not, the fault type of the first faulty device is determined to be a Class I fault at this moment. The length of the time period is determined based on experience and actual needs.

[0073] The first type of fault has a lower priority. At the next moment, if the device is still in normal condition, it will no longer be considered as the first fault device. The fault display of the fault will be eliminated and the fault will be automatically eliminated.

[0074] Since the type of fault is determined by the connection relationship between the first faulty device on the train at each moment and the second faulty device at the centralized station, by dividing the time period, the train equipment that has returned to normal at the current moment within the time period is still retrieved in the knowledge graph as the first faulty device, which can improve the accuracy of fault detection to a certain extent.

[0075] In the signal system fault analysis method based on the knowledge graph of the present invention, after the step of determining that there is an association relationship between the first faulty device and the second faulty device when there is a second faulty device among the retrieved devices of the centralized station, the method further includes:

[0076] When the number of the first faulty devices associated with any second faulty device within a first preset time period is greater than a first preset threshold, it is determined that the second faulty device is faulty.

[0077] The first preset duration and the first preset threshold are both determined through experience. The first preset duration includes one or more moments.

[0078] Optionally, when the number of trains passing through the centralized station at the same time is small, the first preset time length includes multiple moments, and the number of first fault devices associated with a second fault device in multiple moments is counted. When the number is large, the second fault device is determined to be the actual fault device, and the fault of the first fault device associated with it is caused by the fault of the second fault device.

[0079] When a large number of trains pass through the centralized station at the same time, the first preset time length may be one time.

[0080] In the signal system fault analysis method based on the knowledge graph of the present invention, after the step of determining that there is an association relationship between the first faulty device and the second faulty device when there is a second faulty device among the retrieved devices of the centralized station, the method further includes:

[0081] If the number of the second faulty devices associated with any first faulty device within a second preset time period is greater than a second preset threshold, it is determined that the first faulty device is faulty.

[0082] The second preset duration and the second preset threshold are determined through experience. The second preset duration includes several moments.

[0083] Optionally, when the second preset time length includes multiple moments, the train passes through different centralized stations at different moments. When the first faulty device of the train passes through multiple centralized stations and has a second type of fault with the second faulty devices in multiple centralized stations, the first faulty device is determined to be the actual faulty device. Fixing the fault of the first faulty device can quickly eliminate the fault display of a series of second faulty devices related to it.

[0084] The following combination Figure 2 A specific embodiment is introduced.

[0085] First, the centralized stations are divided according to the equipment location and the kilometer mark. When a train reaches a kilometer mark at a certain moment, it enters the communication range of the centralized station corresponding to the kilometer mark and connects with the equipment corresponding to the centralized station.

[0086] The communication kilometer mark range of centralized station A is 0 to 10km. Centralized station A has ground safety subsystem equipment a-1 and a-2, and ground train automatic supervision subsystem equipment a-7 and a-8. Among them, a-1 and a-7 connect trains within the communication range of centralized station A, and a-2 and a-8 are other operating equipment of the ground safety subsystem and the ground train automatic supervision subsystem.

[0087] The communication kilometer range of centralized station B is 10 to 20 km. Centralized station B has ground safety subsystem equipment b-1 and b-2, and ground train automatic supervision subsystem equipment b-7 and b-8. Among them, b-1 and b-7 connect trains within the communication range of centralized station B, and b-2 and b-8 are other operating equipment of the ground safety subsystem and the ground train automatic supervision subsystem.

[0088] Train 1, Train 2 and Train 3 move within the kilometer mark range of 0 to 50 km.

[0089] All trains are equipped with equipment TN1, TN7 and TN9. TN1 is connected to the ground safety subsystem, TN7 is connected to the ground train automatic supervision subsystem, and TN9 is the train automatic driving and automatic protection subsystem.

[0090] Where n represents the train number. For example, the device used by train 1 to connect to the ground safety subsystem is t11, the device used to connect to the ground train automatic supervision subsystem is t17, and the device used to connect to the train automatic driving and automatic protection subsystem is t19.

[0091] When troubleshooting, only the fault correlation between the train, ground safety subsystem, and ground train automatic supervision subsystem is considered, and other fault correlations are not considered, such as the situation where the communication field strength causes multiple trains to have the same fault at certain kilometer marker locations.

[0092] In the knowledge graph, faults are searched by time slices. For example, at four moments in the same time period, Train 1, Train 2, and Train 3 were located at different positions and some faults occurred.

[0093] At time 1, train 1 is at 1 km and breaks down at t11; train 2 is at 19 km and breaks down at t21; train 3 is at 15 km and breaks down at t39; and b-1 breaks down.

[0094] That is, the faulty devices at time 1 include t11, t21, t39, and b-1.

[0095] The fault points are mapped to the location correspondence table, that is, divided according to the centralized station. Train 1 is located at 1 km and mapped to centralized station A; train 2 is located at 19 km and mapped to centralized station B; train 3 is located at 15 km and mapped to centralized station B, and b-1 is located at centralized station B.

[0096] For the first faulty device t11, it is associated with centralized station A. At this time, centralized station A does not have any faulty devices connected to t11. Therefore, during the knowledge graph search, it is considered that centralized station A associated with the first faulty device t11 has no connected device fault, and the first faulty device t11 is considered to be a first-class fault.

[0097] For the first faulty device t21, it is associated with the centralized station B. During the knowledge graph search, the second faulty device b-1 at the centralized station is found. At the same time, it is determined that b-1 and the train can be connected to t21 when they are located at the centralized station B. Therefore, the first faulty device t21 and the second faulty device b-1 are considered to have an association relationship, and the first faulty device t21 and the second faulty device b-1 are second-type faults.

[0098] For the first faulty device t39, it is associated with the centralized station B. During the knowledge graph search, the second faulty device b-1 at the centralized station is found, but b-1 and the train are not connected to t39 when they are at the centralized station B. Therefore, the first faulty device t39 is considered to be a first-class fault.

[0099] When the fault is resolved, priority is given to troubleshooting the second type of fault, that is, first faulty device t21 and first faulty device b-1.

[0100] At time 2, train 1 is at 6 km, recovered at t11, and failed at t17; train 2 is at 9 km, recovered at t21; train 3 is at 7 km, and failed at t39; a-7 failed, b-1 failed.

[0101] That is, the faulty devices at time 2 include t17, t39, a-7, and b-1, while t11 and t21 recover. Since t11 and t21 were faulty devices at time 1, and time 1 and time 2 belong to the same time period, at time 2, t11 and t21 are still considered the first faulty devices.

[0102] According to the centralized station division, train 1 is located at 6km and mapped to centralized station A; train 2 is located at 0km and mapped to centralized station B; train 3 is located at 7km and mapped to centralized station B, a-7 is located at centralized station A, and b-1 is located at centralized station B.

[0103] For the first faulty device t17, it is associated with the centralized station A. During the knowledge graph search, the second faulty device a-7 is found. When the train is at the centralized station A, a-7 can be connected to t17. Therefore, it is determined that the first faulty device t17 and the second faulty device a-7 are second-type faults.

[0104] For the first faulty device t39, it is associated with the centralized station A. During the knowledge graph search, the second faulty device a-7 is found, but a-7 and the train are not connected to t39 when they are located at the centralized station A. Therefore, the first faulty device t39 is considered to be a second-type fault.

[0105] For the second faulty device a-7, it is located at the centralized station A. For trains 1, 2, and 3 associated with the centralized station, there is an association with the first faulty device t17 of train 1. Therefore, it is determined that the second faulty device a-7 and the first faulty device t17 are second-type faults and need to be eliminated first.

[0106] For the second faulty device b-1, it is located at the centralized station B. If there is no train at the associated centralized station, it is considered that the second faulty device b-1 is a first type fault.

[0107] For the first faulty device t11 in the time period at that moment, it is associated with centralized station A. During the knowledge graph search, the second faulty device a-7 is found. At the same time, it is determined that a-7 and the train are not connected to t11 when they are located at centralized station A. Therefore, the first faulty device t11 is considered to be a first-class fault.

[0108] For the first faulty device t21 within the time period of this moment, it is associated with centralized station A. During the knowledge graph search, the second faulty device a-7 is found. At the same time, it is determined that a-7 and the train are not connected to t21 when they are located at centralized station A. Therefore, the second faulty device t21 is considered to be a first-class fault.

[0109] At time 3, train 1 is at 9 km and breaks down at t17; train 2 is at 22 km and breaks down at t27; train 3 is at 1 km and breaks down at t39; b-7 breaks down and b-8 breaks down.

[0110] That is, the faulty devices at time 3 include t17, t27, t39, b-7, and b-8.

[0111] According to the centralized station division, train 1 is mapped to centralized station A, train 2 is located at 22km, neither at centralized station A nor at centralized station B, train 3 is located at 1km and mapped to centralized station A, b-7 is located at centralized station B, and b-8 is located at centralized station B.

[0112] For the first faulty device t17, it is associated with centralized station A. During the knowledge graph search, if centralized station A has no fault, the first faulty device t17 is considered to be a first-class fault.

[0113] For the first faulty device t27, it is neither associated with the centralized station A nor the centralized station B. Therefore, during the knowledge graph search, the first faulty device t27 is considered to be a first-type fault.

[0114] For the first faulty device t39, it is associated with centralized station A. When searching the knowledge graph, centralized station A has no fault, so the first faulty device t39 is considered to be a first-class fault.

[0115] For the second faulty device b-7, it is located at the centralized station B. There is no train associated with the centralized station B. Therefore, it is considered that the second faulty device b-7 is a first type of fault.

[0116] For the second faulty device b-8, it is located at the centralized station B. There is no train associated with the centralized station B and no connection is possible. Therefore, the fault b-8 is considered to be a first-type fault.

[0117] At time 4, all devices are normal, so the knowledge graph does not retrieve the association relationship of the fault.

[0118] In the knowledge graph, when searching for related faults, priority is given to troubleshooting faulty equipment with related fault types of second-class faults. Therefore, at time 3, after the second-class faults are troubleshooted, no second-class faults will occur again; at time 4, all faults are troubleshooted and all equipment is in normal condition.

[0119] The signal system fault analysis device based on the knowledge graph provided by the present invention is described below. The signal system fault analysis device based on the knowledge graph described below and the signal system fault analysis method based on the knowledge graph described above can be referenced to each other.

[0120] like Figure 3 As shown, the apparatus includes a division module 301, a retrieval module 302 and an analysis module 303, wherein:

[0121] A division module 301 is configured to determine a centralized station corresponding to each train based on the current position of each train running on the line and the communication range of each centralized station on the line;

[0122] Multiple centralized stations are arranged in sequence along the line. Each centralized station has its corresponding communication range on the line, and the communication range of multiple centralized stations covers the entire line.

[0123] When a train reaches a specific location on the line at a certain moment, it is determined that the location is within the communication range of a certain centralized station, and the train is matched with the centralized station at this moment.

[0124] For example, the starting position of the line is 0km, the ending position of the line is 20km, and the communication radius of each centralized station is 10km. There are two centralized stations, centralized station A and centralized station B, in this section of the line. The communication range of centralized station A covers the line from 0 to 10km, and the communication range of centralized station B covers the line from 10 to 20km. If the train is currently at a position of 5km in the line, the train is in the communication range of centralized station A, corresponding to centralized station A; if the train is currently at a position of 12km in the line, the train is in the communication range of centralized station B, corresponding to centralized station B.

[0125] A retrieval module 302 is configured to, when a first faulty device exists on any train at a current moment, retrieve, from a knowledge graph, devices at the centralized station corresponding to the train that are connected to the first faulty device;

[0126] The first faulty device is a train device, which includes devices on the train that need to be connected to the centralized station, such as communication equipment for connecting to the ground safety subsystem; and also includes devices that do not need to communicate with the centralized station, such as the train's automatic protection subsystem.

[0127] The train has a first faulty device at the current moment, that is, a device on the train is in a faulty state at the current moment, and the fault of the train needs to be checked.

[0128] If the first faulty device is a device on the train that needs to be connected to the central station, when the first faulty device detects a fault, it may be caused by its own fault or by the equipment at the central station to which it is connected. Therefore, when troubleshooting the fault, it is necessary to also troubleshoot the equipment at the central station to which it is connected.

[0129] When it is detected that any train has a first faulty device at any moment, the centralized station corresponding to the train at this moment is determined based on the train's location at this moment, and the equipment of the centralized station that has a connection relationship with the first faulty device is retrieved from the knowledge graph.

[0130] Among them, the association relationship between each node of the knowledge graph is set according to the centralized station division method of the signal system. The nodes in the knowledge graph include nodes representing train equipment and nodes representing equipment at centralized stations. If there is a connection relationship between a certain train equipment and a certain centralized station equipment, the corresponding two nodes in the knowledge graph are connected by a line segment.

[0131] The knowledge graph can integrate data from multiple consecutive moments into a set of data, and determine the correlation between faults between trains and between trains and equipment in centralized stations based on the correlation between the positions of trains.

[0132] By using the existing knowledge content of the signal system to construct the association relationship of the knowledge graph, the processing mode of the signal system can be better continued when performing fault retrieval through the knowledge graph, and the analysis ability of related faults is improved with less additional investment. It is easy to use and economical.

[0133] The analyzing module 303 is configured to determine whether there is an association relationship between the first faulty device and the second faulty device when there is a second faulty device among the retrieved devices of the centralized station.

[0134] The equipment in the centralized station includes equipment that needs to be connected to the train and equipment that does not need to be connected to the train. The second faulty equipment refers to equipment that has a fault in the centralized station.

[0135] If there is a second faulty device among the devices of the centralized station retrieved through the knowledge graph, then the second faulty device is a device that needs to be connected to the train. At this time, it is determined that there is an association relationship between the second faulty device and the first faulty device.

[0136] That is, the failures of the first faulty device and the second faulty device may be caused by the first faulty device and / or the second faulty device. When troubleshooting, it is necessary to troubleshoot the first faulty device and the second faulty device at the same time.

[0137] The signal system fault analysis method based on the knowledge graph of the present invention associates a train that fails at a certain moment with its corresponding centralized station, retrieves a second fault device in the centralized station that has a connection relationship with the first fault device in the knowledge graph, and determines that it has an association relationship with the first fault device, thereby improving the accuracy of the associated fault analysis and thus improving the speed of fault detection; by making the train at a certain moment correspond to the centralized station through a positional relationship, the time relationship is converted into a spatial distance relationship, thereby reducing the complexity of fault detection and thus reducing the time of fault detection.

[0138] Figure 4 An example of a physical structure diagram of an electronic device is shown below. Figure 4As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 840, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other via the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute a signal system fault analysis method based on a knowledge graph, the method comprising: determining the centralized station corresponding to each train according to the current position of each train running on the line and the communication range of each centralized station on the line; in the case where a first faulty device exists on any train at the current moment, retrieving the device of the centralized station connected to the first faulty device from the knowledge graph according to the centralized station corresponding to any train; in the case where a second faulty device exists among the retrieved devices of the centralized station, determining that the first faulty device and the second faulty device have an associated relationship.

[0139] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0140] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the signal system fault analysis method based on the knowledge graph provided by the above methods, the method including: determining the centralized station corresponding to each train according to the position of each train running on the line at the current moment and the communication range of each centralized station on the line; in the case that any train has a first faulty device at the current moment, retrieving the equipment of the centralized station connected to the first faulty device from the knowledge graph according to the centralized station corresponding to any train; in the case that a second faulty device exists among the retrieved equipment of the centralized station, determining that the first faulty device and the second faulty device have an association relationship.

[0141] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the signal system fault analysis method based on the knowledge graph provided by the above-mentioned methods, the method comprising: determining the centralized station corresponding to each train according to the position of each train running on the line at the current moment and the communication range of each centralized station on the line; in the case that any train has a first faulty device at the current moment, retrieving the equipment of the centralized station connected to the first faulty device from the knowledge graph according to the centralized station corresponding to any train; in the case that a second faulty device exists among the retrieved equipment of the centralized station, determining that the first faulty device and the second faulty device have an association relationship.

[0142] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0143] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0144] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A signal system fault analysis method based on knowledge graph, characterized in that: include: Determine the central station corresponding to each train according to the current position of each train running on the line and the communication range of each central station on the line; In the case that a first faulty device exists on any train at the current moment, the device of the centralized station connected to the first faulty device is retrieved from the knowledge graph according to the centralized station corresponding to the any train; In the case that a second faulty device exists among the retrieved devices of the centralized station, determining that there is an association relationship between the first faulty device and the second faulty device; After the step of determining that there is an association relationship between the first faulty device and the second faulty device when there is a second faulty device among the retrieved devices of the centralized station, the method further includes: If the number of the first faulty devices associated with any second faulty device within a first preset time period is greater than a first preset threshold, determining that the second faulty device is faulty; If the number of the second faulty devices associated with any first faulty device within a second preset time period is greater than a second preset threshold, it is determined that the first faulty device is faulty.

2. The signal system fault analysis method based on knowledge graph according to claim 1 is characterized in that: The step of retrieving the device of the centralized station connected to the first faulty device from the knowledge graph according to the centralized station corresponding to any one of the trains includes: According to the subsystem of the centralized station corresponding to any one of the trains, the devices of the subsystem connected to the first faulty device are retrieved from the knowledge graph.

3. The signal system fault analysis method based on knowledge graph according to claim 1 is characterized in that: After the step of determining that there is an association relationship between the first faulty device and the second faulty device when there is a second faulty device among the retrieved devices of the centralized station, the method further includes: If the second faulty device does not exist in the retrieved devices of the centralized station, determining that the fault type of the first faulty device is a first type of fault; In the case that there is a second faulty device among the retrieved devices of the centralized station, determining that the fault types of the first faulty device and the second faulty device having an associated relationship are second type faults; In a case where any second faulty device has no association relationship with the first faulty devices of all trains, determining that the fault type of the any second faulty device is the first type of fault; The fault type of the first faulty device and the fault type of the second faulty device are displayed.

4. The signal system fault analysis method based on knowledge graph according to claim 1 is characterized in that: Before the step of searching, from a knowledge graph, a device of the centralized station connected to the first faulty device in a case where the first faulty device exists on any train at the current moment, according to the centralized station corresponding to the any train, the method further includes: If a device on any train fails at the previous moment and returns to normal at the current moment, the device will be regarded as the first failed device at the current moment.

5. A signal system fault analysis device based on knowledge graph, characterized in that: include: A division module is used to determine the central station corresponding to each train according to the current position of each train running on the line and the communication range of each central station on the line; A retrieval module is configured to, when a first faulty device exists on any train at a current moment, retrieve, from a knowledge graph, devices at the centralized station connected to the first faulty device based on the centralized station corresponding to the train; an analyzing module, configured to determine, when a second faulty device exists among the retrieved devices of the centralized station, that the first faulty device and the second faulty device are associated with each other; In the case that there is a second faulty device among the retrieved devices of the centralized station, after the step of determining that there is an association relationship between the first faulty device and the second faulty device, the method further includes: If the number of the first faulty devices associated with any second faulty device within a first preset time period is greater than a first preset threshold, determining that the second faulty device is faulty; If the number of the second faulty devices associated with any first faulty device within a second preset time period is greater than a second preset threshold, it is determined that the first faulty device is faulty.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the signal system fault analysis method based on the knowledge graph as described in any one of claims 1 to 4 is implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the signal system fault analysis method based on the knowledge graph as described in any one of claims 1 to 4 is implemented.

8. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the signal system fault analysis method based on the knowledge graph as described in any one of claims 1 to 4 is implemented.

Images