Title of the invention: track monitoring system, track monitoring device, track monitoring method, and non-temporary computer-readable medium.
Technical field
[0001]
　The present disclosure relates to track monitoring systems, track monitoring devices, track monitoring methods, and non-transitory computer-readable media.
Background technology
[0002]
　Conventionally, track abnormality detection is often performed manually. For example, a worker visually monitors the occurrence of a landslide, the invasion of animals, humans, etc. into a high-speed track or the like. However, when a track abnormality is detected manually, it takes a lot of cost and time, and the detection and countermeasures of the abnormality may be delayed.
　Further, conventionally, the running state of a train on a railroad track has been controlled by an axle counter laid on the railroad track. However, there is a problem that the axle counter is reset due to the influence of a power failure or communication interruption.
　Therefore, recently, a system for monitoring an abnormality of a railroad track and a running state of a train on the railroad track by using an optical fiber has been proposed (for example, Patent Documents 1 to 3).
[0003]
　In the techniques described in Patent Documents 1 and 2, an optical fiber is laid along the line, and a train on the line is detected by frequency-analyzing the scattered light in the optical fiber. At this time, particularly in the region where the train is desired to be detected, a multiple loop is formed so as to surround the region to improve the detection sensitivity by the optical fiber.
[0004]
　In the technique described in Patent Document 3, an optical fiber is laid along a railroad track, and an abnormality (for example, rockfall, landslide, etc.) of the railroad track and a running state of a train on the railroad track are detected through an acoustic signal induced in the optical fiber. It is being detected.
Prior art literature
Patent documents
[0005]
Patent Document 1: Japanese Patent Application Laid-Open No. 2018-114790
Patent Document 2: Japanese Patent Application Laid-Open No. 2018-114792
Patent Document 3: Japanese Patent Application Laid-Open No. 2018-504603
Outline of the invention
Problems to be solved by the invention
[0006]
　However, the techniques described in Patent Documents 1 and 2 are merely techniques in which the detection sensitivity by the optical fiber is improved by forming multiple loops so as to surround the region where the train is desired to be detected in order to detect the train on the track. No.
[0007]
　Further, in the technique described in Patent Document 3, abnormality detection of a line is performed by monitoring an acoustic signal when a strong stress is applied to an optical fiber.
　Therefore, although it is possible to detect an extreme state such as a rock fall on a railroad track or a landslide, there is a problem that it is difficult to detect a state that hardly affects the stress on the optical fiber.
[0008]
　On the other hand, in recent years, with the development of IoT (Internet of Things) and the like, there is an increasing demand for detecting various environmental changes of railway tracks. However, there is a high possibility that changes in the environment of the line will not appear in the remarkable changes in the stress on the optical fiber.
[0009]
　Further, in the technique described in Patent Document 3, the running state of the train on the track is detected by monitoring the acoustic signal. Therefore, there is a problem that it is difficult to detect a state in which the train is not running and the train is stopped.
[0010]
　Therefore, an object of the present disclosure is a track monitoring system, a track monitoring device, and a track monitoring capable of solving any of the above-mentioned problems and detecting either an abnormal state of a track or a running state of a train on a track with high accuracy. The method is to provide a non-temporary computer-readable medium.
Means to solve problems
[0011]
　The line monitoring system according to one aspect is based
　on a cable including a communication optical fiber laid on the line,
　a receiving unit that receives an optical signal from at least one communication optical fiber included in the cable, and the
　optical signal. A detection unit that detects a pattern according to the state of the line and detects an abnormal state of the line based on the detected pattern according to the state of the line
　.
[0012]
　The line monitoring device according to one embodiment
　has a receiving unit that receives an optical signal from at least one communication optical fiber included in a cable laid on the
　line, and a pattern according to the state of the line based on the optical signal.
　Is provided , and a detection unit for detecting an abnormal state of the line based on a pattern corresponding to the detected state of the line is provided.
[0013]
　The line monitoring method according to one aspect is a line monitoring method using a
　line monitoring device
　, in which an optical signal is received from at least one communication optical fiber included in a cable laid on the line,
　and based on the optical signal, the line monitoring method is performed . A pattern corresponding to the state of the line is detected, and an abnormal state of the line is detected based on the detected pattern according to the state of the line.
[0014]
　The non-temporary computer-readable medium according to one aspect
　is the
　line
　, based on the procedure of receiving an optical signal from at least one communication optical fiber included in a cable laid on the line, and the optical signal.
　A non-temporary computer that stores a procedure for detecting a pattern according to the state of the track and detecting an abnormal state of the track based on the detected pattern according to the state of the track, and a program for executing the procedure. It is a readable medium.
The invention's effect
[0015]
　According to the above aspect, the effect that the abnormal state of the line can be detected with high accuracy can be obtained.
A brief description of the drawing
[0016]
[Fig. 1] Fig. 1 is a diagram showing an example of a configuration of a track monitoring system according to an embodiment.
FIG. 2 is a diagram showing an example of a configuration of a track monitoring system according to an embodiment.
FIG. 3 is a diagram showing an example of a pattern according to a track state used in the method A1 in the track monitoring system according to the embodiment.
FIG. 4 is a diagram showing an example of a pattern according to a track state used in the method A1 in the track monitoring system according to the embodiment.
FIG. 5 is a diagram showing an example of machine learning by the method A3 in the track monitoring system according to the embodiment.
[Fig. 6] Fig. 6 is a diagram showing an example of abnormality level information according to the embodiment.
FIG. 7 is a diagram showing an example of a pattern according to a running state of a train on a railroad track, which is used in the method B1 in the railroad track monitoring system according to the embodiment.
FIG. 8 is a diagram showing an example of a pattern according to a running state of a train on a railroad track, which is used in the method B1 in the railroad track monitoring system according to the embodiment.
FIG. 9 is a diagram showing an example of a pattern according to a running state of a train on a railroad track, which is used in the method B1 in the railroad track monitoring system according to the embodiment.
FIG. 10 is a diagram showing an example of a pattern according to a running state of a train on a railroad track, which is used in the method B1 in the railroad track monitoring system according to the embodiment.
FIG. 11 is a diagram showing an example of a pattern according to a running state of a train on a railroad track, which is used in the method B1 in the railroad track monitoring system according to the embodiment.
FIG. 12 is a diagram showing an example of machine learning by method B3 in the track monitoring system according to the embodiment.
FIG. 13 is a diagram showing an example of a pattern according to a state of a train on a track, which is used in the method C1 in the track monitoring system according to the embodiment.
FIG. 14 is a diagram showing an example of a pattern according to a state of a train on a track, which is used in the method C1 in the track monitoring system according to the embodiment.
FIG. 15 is a diagram showing an example of a pattern according to a state of a train on a track, which is used in the method C2 in the track monitoring system according to the embodiment.
FIG. 16 is a diagram showing an example of train information according to an embodiment.
FIG. 17 is a diagram showing an example of an application that can be realized based on an abnormal state of a railroad track and a train detected by a detection unit according to the embodiment.
FIG. 18 is a block diagram showing an example of a hardware configuration of a computer that realizes the line monitoring device according to the embodiment.
FIG. 19 is a flow chart showing an example of an operation flow of the track monitoring system according to the embodiment.
FIG. 20 is a diagram showing an example of a track monitoring system according to another embodiment.
FIG. 21 is a diagram showing another example of a track monitoring system according to another embodiment.
FIG. 22 is a diagram showing an example of arrangement of a fiber sensing unit in a line monitoring system according to another embodiment.
FIG. 23 is a diagram showing another example of arrangement of a fiber sensing unit in a line monitoring system according to another embodiment.
FIG. 24 is a diagram showing still another example of the arrangement of the fiber sensing unit in the line monitoring system according to another embodiment.
FIG. 25 is a diagram showing still another example of the arrangement of the fiber sensing unit in the line monitoring system according to another embodiment.
FIG. 26 is a diagram showing an example of the operation of the fiber sensing unit when the optical fiber cable is broken in the line monitoring system of FIG. 22.
FIG. 27 is a diagram showing an example of the operation of the fiber sensing unit when the optical fiber cable is broken in the line monitoring system of FIG. 23.
FIG. 28 is a diagram showing an example of the operation of the fiber sensing unit when the optical fiber cable is broken in the line monitoring system of FIG. 25.
Forms for carrying out the invention
[0017]
　Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

　First, the configuration of the track monitoring system according to the present embodiment will be described with reference to FIGS. 1 and 2.
[0018]
　As shown in FIG. 1, the line monitoring system according to the present embodiment detects an abnormal state of the line 10, and includes an optical fiber cable 20 and a line monitoring device 33. Further, as shown in FIG. 2, the track monitoring system according to the present embodiment also detects the running state of the train on the track 10.
[0019]
　The optical fiber cable 20 is laid along the line 10. In FIG. 1, the optical fiber cable 20 is laid under the line 10, but the present invention is not limited to this, and the optical fiber cable 20 may be laid on the side of the line 10. Further, at this time, at the position where the state of the line 10 is particularly desired to be detected, the optical fiber cable 20 may be densely installed, for example, by laying the optical fiber cable 20 while forming a loop. As a result, the detection rate of abnormalities on the track 10 can be improved, and the accuracy of detecting the running state of the train on the track 10 can be improved.
　The optical fiber cable 20 is a cable configured by covering one or more communication optical fibers, and one end thereof is routed inside the communication carrier station building 30.
[0020]
　The track monitoring system according to the present embodiment uses an optical fiber sensing technique using an optical fiber as a sensor to detect an abnormal state of the track 10 and a running state of a train on the track 10.
　Specifically, inside the communication carrier station building 30, pulsed light is incident on the communication optical fiber included in the optical fiber cable 20. Then, as the pulsed light is transmitted through the communication optical fiber in the direction of the line 10, backscattered light is generated for each transmission distance. This backscattered light returns to the inside of the communication carrier station building 30 via the same communication optical fiber.
[0021]
　Here, the track 10 vibrates when a train runs or a landslide occurs, and the vibration of the track 10 is transmitted to the communication optical fiber. Further, the temperature of the line 10 rises when a fire or the like occurs, and the temperature change of the line 10 is also transmitted to the communication optical fiber. Further, the line 10 generates an abnormal noise when an abnormality or the like of the line 10 occurs, and the change in sound is also transmitted to the communication optical fiber. Therefore, in the optical fiber for communication, the pattern in which the vibration, temperature, and sound of the line 10 are transmitted is the state of the line 10 (for example, the presence or absence of landslides and rockfalls, the presence or absence of invasion of animals, humans, etc., and the presence or absence of fire. Whether or not an earthquake has occurred, whether or not railroad tracks 10 or trains have been damaged, whether or not abnormal noise has occurred, whether or not strong winds (including typhoons and tornadoes) have occurred, whether or not flood damage has occurred, etc. It differs depending on the running state of the train on the track 10 (for example, type, position, speed, acceleration / deceleration, etc.) and the abnormal state of the train on the track 10 (for example, damage, deterioration, etc.).
[0022]
　Therefore, the backscattered light returning to the inside of the communication carrier station building 30 depends on the pattern according to the state of the line 10, the pattern according to the running state of the train on the line 10, and the state of the train on the line 10. Patterns are included. In the example of FIG. 1, the backscattered light returning to the inside of the communication carrier station building 30 has a pattern according to the state of various positions of the line 10, a pattern according to the running state of the train on the line 10, and a pattern. A pattern corresponding to the state of the train on the track 10 is included.
[0023]
　The line monitoring system according to the present embodiment utilizes the fact that the backscattered light returning to the inside of the communication carrier station building 30 includes a pattern corresponding to the state of the line 10, and the abnormal state of the line 10 is used. (For example, landslides and rockfalls, invasion of animals and humans, fires, earthquakes, damage to railroad tracks 10 and trains, abnormal noises, strong winds, floods, etc.) be.
　Further, the track monitoring system according to the present embodiment utilizes the fact that the backscattered light returning to the inside of the communication carrier station building 30 includes a pattern corresponding to the running state of the train on the track 10. It detects the running state of the train on the track 10 (for example, type, position, speed, acceleration / deceleration, etc.).
　Further, the track monitoring system according to the present embodiment utilizes the fact that the backscattered light returning to the inside of the communication carrier station building 30 includes a pattern according to the state of the train on the track 10. It detects an abnormal state of a train (for example, damage, deterioration, etc.) in the above.
[0024]
　Here, the above-mentioned line monitoring device 33 is provided inside the communication carrier station building 30. The track monitoring device 33 is equipment newly installed for the realization of the present embodiment.
[0025]
　The line monitoring device 33 is a device having a function as an optical fiber sensing device and also having a function of detecting the state of the line 10. Specifically, the line monitoring device 33 includes a fiber sensing unit 331 and a detection unit 332. The fiber sensing unit 331 is an example of a receiving unit.
[0026]
　The fiber sensing unit 331 incidents pulsed light on at least one communication optical fiber included in the optical fiber cable 20. This pulsed light is transmitted in the direction of the line 10. Further, the fiber sensing unit 331 receives backscattered light with respect to the pulsed light from the same communication optical fiber as the communication optical fiber in which the pulsed light is incident. This backscattered light is received from the direction of the line 10.
[0027]
　At this time, as described above, the backscattered light received by the fiber sensing unit 331 has a pattern according to the state of the line 10, a pattern according to the running state of the train on the line 10, and the state of the train on the line 10. Includes patterns according to. Further, in the example of FIG. 1, the fiber sensing unit 331 receives the backscattered light generated at various positions of the line 10 in time series.
[0028]
　Therefore, when the fiber sensing unit 331 receives the backscattered light, it first identifies the position of the line 10 where the backscattered light is generated. Further, the fiber sensing unit 331 detects the vibration state, the temperature state, the sound state, and the like at the specified position.
　Then, the detection unit 332 detects a pattern according to the state of the specified position of the line 10 based on the processing result of the backscattered light by the fiber sensing unit 331, and based on the detected pattern, the line. The abnormal state of 10 specified positions is detected. Further, the detection unit 332 detects a pattern according to the running state of the train on the track 10 based on the processing result of the backscattered light by the fiber sensing unit 331, and based on the detected pattern, the detection unit 332 of the train on the track 10. Detect the running condition. Further, the detection unit 332 detects a pattern according to the state of the train on the track 10 based on the processing result of the backscattered light by the fiber sensing unit 331, and based on the detected pattern, the abnormality of the train on the track 10 Detect the condition.
[0029]
　Therefore, in the following, first, when the fiber sensing unit 331 receives the backscattered light, a method of specifying the position where the backscattered light is generated will be described.
[0030]
　In the present embodiment, the fiber sensing unit 331 scatters backscattered based on the time difference between the time when the pulsed light is incident on the optical fiber for communication and the time when the backscattered light is received from the same optical fiber for communication. Identify the location where the light was generated. At this time, the fiber sensing unit 331 specifies the generation position so that the smaller the time difference is, the closer it is to the fiber sensing unit 331.
[0031]
　Subsequently, a method of detecting an abnormal state of the line 10 in the detection unit 332 will be described below.
(A1) Method A1
　First, a method A1 for detecting an abnormal state of the line 10 will be described with reference to FIGS. 3 and 4. 3 and 4 show vibration data (horizontal axis is time, vertical axis is vibration intensity) of the track 10 when a train passes through a specific position of the track 10. Further, FIG. 3 shows vibration data of the normal line 10, and FIG. 4 shows vibration data of the line 10 in which an abnormality such as deterioration has occurred over time.
[0032]
　The fiber sensing unit 331 performs a process of identifying the position of the line 10 where the backscattered light received from the communication optical fiber is generated. Further, the fiber sensing unit 331 detects the backward scattered light by a distributed acoustic sensor, a distributed vibration sensor, a distributed temperature sensor, or the like. , Performs a process of detecting a vibration state, a temperature state, a sound state, and the like at a specified position of the line 10.
[0033]
　Therefore, the detection unit 332 detects the pattern according to the state of the line 10 based on the processing result of the backscattered light by the fiber sensing unit 331. At this time, the detection unit 332 can detect the dynamic fluctuation pattern of the vibration by detecting, for example, the strength of the vibration generated on the line 10, the vibration position, the transition of the fluctuation of the frequency, and the like. Become. Further, the detection unit 332 detects the complex unique pattern of the line 10 by also detecting the dynamic fluctuation pattern of the sound and the temperature generated on the line 10, and detects the deterioration state with higher accuracy. Is possible. Here, specifically, the vibration data of the line 10 as shown in FIGS. 3 and 4 is detected.
　As shown in FIGS. 3 and 4, the vibration data of the line 10 has a dynamic vibration pattern that differs depending on the abnormal state of the line 10. Specifically, the vibration data of the line 10 in which the abnormality has occurred (FIG. 4) has a larger amplitude of the vibration intensity than the vibration data of the normal line 10 (FIG. 3).
[0034]
　Therefore, when detecting the abnormal state of the line 10, the detection unit 332 first detects the vibration data of the line 10 (for example, FIGS. 3 and 4). Subsequently, the detection unit 332 detects the abnormal state of the line 10 based on the amplitude of the vibration intensity in the vibration data of the line 10.
[0035]
(A2) Method A2
　Subsequently, a method A2 for detecting an abnormal state of the line 10 will be described.
　In the method A2, the detection unit 332 holds a correspondence table in which the pattern corresponding to the state of the line 10 and the state of the line 10 are associated with each other. Therefore, when detecting the abnormal state of the line 10, the detection unit 332 first detects the pattern according to the state of the line 10. Subsequently, the detection unit 332 uses the above-mentioned correspondence table to specify the state of the line 10 corresponding to the pattern corresponding to the state of the line 10 detected above, so that the line 10 is in an abnormal state. Judge whether or not.
[0036]
(A3) Method A3
　Subsequently, a method A3 for detecting an abnormal state of the line 10 will be described.
　In the method A3, the detection unit 332 machine-learns a pattern according to the state of the line 10 (for example, deep learning), and uses the learning result of the machine learning (initial learning model) to determine the abnormal state of the line 10. To detect.
[0037]
　First, the machine learning method in the method A3 will be described with reference to FIG. Here, a method of learning a pattern in which the distance from the fiber sensing unit 331 is xx [km], yy [km], and zz [km] on the line 10 as teacher data will be described.
　As shown in FIG. 5, the detection unit 332 inputs teacher data which is abnormality level information indicating the degree of abnormality at three locations of the line 10 and a pattern corresponding to the state of the three locations (steps S1 and S2). ). FIG. 6 shows an example of abnormality level information that serves as teacher data. In FIG. 6, the larger the value of the abnormality level, the more the degree of abnormality is progressing. Further, the abnormality level information is held by the detection unit 332.
[0038]
　Subsequently, the detection unit 332 matches and classifies the two (step S3), and performs supervised learning (step S4). As a result, an initial learning model is obtained (step S5). This initial learning model is a model in which the state of the line 10 is output when a pattern corresponding to the state of the line 10 is input.
[0039]
　Subsequently, a method of detecting an abnormal state of the line 10 in the method A3 will be described.
　When detecting the abnormal state of the line 10, the detection unit 332 first detects a pattern according to the state of the line 10. Subsequently, the detection unit 332 inputs the pattern to the initial learning model. As a result, the detection unit 332 obtains the state of the line 10 as the output result of the initial learning model, and therefore determines whether or not the line 10 is in an abnormal state.
[0040]
　Subsequently, a method of detecting the running state of the train on the track 10 by the detection unit 332 will be described below.
(B1) Method B1
　First, a method B1 for detecting a running state of a train on a track 10 will be described with reference to FIGS. 7 to 11. 7 to 11 are diagrams showing an example of a pattern according to a running state of a train on the track 10.
　The detection unit 332 detects a pattern according to the running state of the train on the track 10 based on the processing result by the fiber sensing unit 331. Specifically, as shown in FIGS. 7 to 11, a pattern corresponding to the running state of the train on the track 10 is detected.
[0041]
　Hereinafter, the patterns according to the running state of the train on the track 10 shown in FIGS. 7 to 11 will be described in detail. The patterns themselves are the same in FIGS. 7 to 11.
　In FIGS. 7 to 11, the horizontal axis represents the distance from the fiber sensing unit 331, and the vertical axis represents the passage of time. When the train is running and the vibration of the train is detected by the fiber sensing unit 331, the running of the train is indicated by a line on the graph. For example, the fact that a train is traveling over time is represented by a single line diagonally on the graph. Hereinafter, this line is referred to as a "detection information line". Based on the line of detection information, it is possible to detect the traveling direction, traveling speed, acceleration / deceleration, number of traveling units, traveling interval, etc. of the train.
[0042]
　For example, as shown in FIG. 7, the traveling direction of the train can be detected based on the direction of the line of the detection information. In the example of FIG. 7, the traveling direction is different between the train in the area A and the train in the area B.
　Further, as shown in FIG. 8, the number of trains running can be detected based on the number of lines of detection information in the area surrounded by a circle.
　Further, as shown in FIG. 9, the traveling speed of the train can be detected based on the inclination of the line of the detection information in the area surrounded by the circle.
　Further, as shown in FIG. 10, the running interval of the train can be detected based on the interval between the lines of the plurality of detection information represented diagonally.
　Further, as shown in FIG. 11, the acceleration / deceleration of the train can be detected based on the inclination of the line of the detection information in the area surrounded by the circle.
　As described above, the patterns shown in FIGS. 7 to 11 are dynamic patterns according to the running state of the train on the track 10.
[0043]
　Therefore, when detecting the running state of the train on the track 10, the detection unit 332 first detects a pattern according to the running state of the train on the track 10, as shown in FIGS. 7 to 11. Subsequently, the detection unit 332 detects the running state of the train on the track 10 by the method described with reference to FIGS. 7 to 11. Further, the detection unit 332 may detect the traveling state of a plurality of trains on the track 10 by the method described with reference to FIGS. 7 to 11.
[0044]
(B2) Method B2
　Next, a method B2 for detecting the running state of the train on the track 10 will be described.
　In the method B2, the detection unit 332 holds a corresponding table in which a pattern corresponding to the running state of the train on the track 10 and the running state of the train on the track 10 are associated with each other. Therefore, when detecting the running state of the train on the track 10, the detection unit 332 first detects a pattern according to the running state of the train on the track 10. Subsequently, the detection unit 332 uses the above-mentioned correspondence table to specify the running state of the train on the track 10 corresponding to the pattern corresponding to the running state of the train on the track 10 acquired above.
[0045]
(B3) Method B3
　Next, a method B3 for detecting a running state of a train on the track 10 will be described.
　In the method B3, the detection unit 332 machine-learns (for example, deep learning) a pattern according to the running state of the train on the track 10, and uses the learning result of the machine learning (initial learning model) on the track 10. Detects the running state of the train.
[0046]
　First, the machine learning method in the method B3 will be described with reference to FIG.
　As shown in FIG. 12, the detection unit 332 inputs the teacher data indicating the running state of the train on the track 10 and the pattern corresponding to the running state of the train on the track 10 (steps S11 and S12).
[0047]
　Subsequently, the detection unit 332 matches and classifies the two (step S13), and performs supervised learning (step S14). As a result, an initial learning model is obtained (step S15). This initial learning model is a model in which the running state of the train is output when a pattern corresponding to the running state of the train on the track 10 is input.
[0048]
　Subsequently, a method of detecting the running state of the train on the track 10 in the method B3 will be described.
　When detecting the running state of the train on the track 10, the detection unit 332 first detects a pattern according to the running state of the train on the track 10. Subsequently, the detection unit 332 inputs the pattern to the initial learning model. As a result, the detection unit 332 obtains the running state of the train as the output result of the initial learning model.
[0049]
　Subsequently, a method of detecting an abnormal state of the train on the track 10 by the detection unit 332 will be described below.
(C1) Method C1
　First, a method C1 for detecting an abnormal state of a train on a track 10 will be described with reference to FIGS. 13 and 14. 13 and 14 show vibration data (horizontal axis is time, vertical axis is vibration intensity) of the track 10 when a train passes through a specific position of the track 10. Further, FIG. 13 shows vibration data of the track 10 when a normal train passes, and FIG. 14 shows vibration data of the track 10 when a train having an abnormality such as deterioration over time passes. Is shown. Note that FIGS. 13 and 14 show vibration data when the train is a 5-car train and two wheels are arranged in each vehicle along the traveling direction of the train.
[0050]
　On track 10, the vibration pattern usually occurs for each wheel (axle) of the train car. The pattern of vibration generated from this wheel is a dynamic pattern in which a normal train and a train in which an abnormality occurs are different.
　As shown in FIG. 13, since the train is a 5-car train, five vibration patterns are generated for each vehicle (of the five vibration patterns in FIG. 13, the leftmost is the vibration pattern of the first car. , The rightmost is the vibration pattern of the 5th car). In addition, two vibrations are generated for each wheel in each vehicle.
　Here, when FIG. 13 and FIG. 14 are compared, the peak patterns of vibration of the second vehicle are different from each other, and the peak of vibration is larger in FIG. Therefore, the peak pattern of vibration of the second vehicle shown in FIG. 14 is detected as an abnormal pattern.
[0051]
　Therefore, when detecting the abnormal state of the train on the track 10, the detection unit 332 first detects the vibration data (for example, FIGS. 13 and 14) of the track 10 when the train passes. Subsequently, the detection unit 332 detects the abnormal state of the train on the track 10 based on the peak pattern of the vibration in the vibration data of the track 10.
[0052]
(C2) Method C2
　Subsequently, a method C2 for detecting an abnormal state of a train on the track 10 will be described with reference to FIGS. 15 and 16. FIG. 15 shows vibration data of the track 10 when the train passes through a specific position of the track 10 (horizontal axis is time, vertical axis is vibration intensity), and FIG. 16 shows train information of the train passing through the track 10. Shown.
[0053]
　Vibration may vary depending on the model and weight of the train car. That is, there are cases where the vibration pattern generated from the wheels of the vehicle becomes a dynamic pattern that differs depending on the vehicle type and weight of the vehicle.
　Therefore, the detection unit 332 holds the train information (FIG. 16) of the train in advance for each train, and also holds the vibration data (FIG. 15) when the train passes by the train at a specific position on the track 10 in advance. Keep it. The train information includes information on the vehicle type and weight of each train vehicle. Further, the weight should be a weight that takes into account not only the weight of the vehicle itself but also the number of passengers.
[0054]
　Therefore, when detecting the abnormal state of the train on the track 10, the detection unit 332 first detects the vibration data (for example, FIG. 15) of the track 10 when the train passes. Subsequently, the detection unit 332 compares the detected vibration data with the expected pre-held vibration data for the train, and based on whether or not there is a vehicle deviating from the pre-held vibration data. , Detects an abnormal state of the train on the track 10. As will be described later, the detection unit 332 may machine-learn the vibration data expected for the train and detect the abnormal state of the train on the track 10 by using the learning result (initial learning model) of the machine learning. good.
[0055]
(C3) Method C3
　Next, a method C3 for detecting an abnormal state of a train on the track 10 will be described.
　In the method C3, the detection unit 332 holds a correspondence table in which the pattern corresponding to the state of the train on the track 10 and the state of the train on the track 10 are associated with each other. Therefore, when detecting an abnormal state of a train on the track 10, the detection unit 332 first detects a pattern according to the state of the train on the track 10. Subsequently, the detection unit 332 uses the above-mentioned correspondence table to identify the abnormal state of the train on the track 10 corresponding to the pattern corresponding to the state of the train on the track 10 acquired above.
[0056]
(C4) Method C4
　Next, a method C4 for detecting an abnormal state of a train on the track 10 will be described.
　In the method C4, the detection unit 332 machine-learns (for example, deep learning) a pattern according to the state of the train on the track 10, and uses the learning result of the machine learning (initial learning model) to train the train on the track 10. Detects abnormal conditions.
[0057]
　The detection unit 332 machine-learns a pattern according to the state of the train on the track 10, and obtains an initial learning model in advance as a learning result of the machine learning.
　When detecting an abnormal state of a train on the track 10, the detection unit 332 first detects a pattern according to the state of the train on the track 10. Subsequently, the detection unit 332 inputs the pattern to the initial learning model. As a result, the detection unit 332 obtains the state of the train on the track 10 as the output result of the initial learning model, and thus determines whether or not the train is in an abnormal state.
[0058]
　In the above methods A3, B3, and C4, a pattern according to the state of the track 10, a pattern according to the running state of the train, and a pattern according to the state of the train are machine-learned, and the learning result of the machine learning is used. , The abnormal state of the track 10, the running state of the train, and the abnormal state of the train are detected.
　It may be difficult for human analysis to extract features for detecting an abnormal state of the track 10, a running state of a train, or an abnormal state of a train from the data. In the methods A3, B3, and C4, by constructing a learning model from a large number of patterns, even if it is difficult for human analysis, the abnormal state of the track 10, the running state of the train, and the abnormal state of the train are high. It can be detected with high accuracy.
[0059]
　Further, in the machine learning in the above-mentioned methods A3, B3, and C4, in the initial state, a learning model may be generated based on two or more teacher data. Further, the newly detected pattern may be newly learned in this learning model. At that time, detailed conditions for detecting the abnormal state of the track 10, the running state of the train, and the abnormal state of the train may be adjusted from the new learning model.
[0060]
　Subsequently, with reference to FIG. 17, an application that can be realized based on the abnormal state of the track 10 detected by the detection unit 332 and the abnormal state of the train on the track 10 will be described.
　Based on the abnormal state of the line 10 detected by the detection unit 332, for example, the following applications (a) to (g) can be realized. Each application will be described below.
[0061]
　(A) Landslide, rockfall detection, intrusion detection of animals and humans
　Issues and effects:
　Appropriate notification to drivers and dangerous areas by remotely detecting landslides, rockfalls and intrusion of animals and humans in real time. It becomes possible to deal with the problem quickly.
　Further, when the invasion of an animal or a human is detected, it is possible to detect the route followed by the animal or the human.
　Outline of operation:
　Vibration generated by landslides, rockfalls, invasion of animals, humans, etc. is monitored via an optical fiber cable 20 laid under the track 10, and an abnormality is determined based on the vibration pattern.
　Further, the optical fiber cable 20 may be laid on a fence or a mountain slope.
[0062]
(B) Fire occurrence
　issues and effects in and along railway tracks :
　By remotely monitoring the situation of fire occurrence in real time, it is possible to prevent rapid digestion activity and progress to dangerous areas.
　Outline of operation:
　The surface temperature of the line 10 is monitored via an optical fiber cable 20 laid along the line 10, and a fire is detected when the temperature is equal to or higher than a specific temperature.
[0063]
(C) Earthquake detection
　issues and effects:
　By monitoring the vibration status over a wide area, it is possible to grasp the location of the earthquake and the propagation of the earthquake. It is possible to make breaking news of earthquakes and quickly grasp the situation.
　Outline of operation:
　The vibration of the optical fiber cable 20 embedded in the line 10 is monitored, and the earthquake is determined by the vibration pattern.
[0064]
(D) Abnormality
　problems and effects of the
　track 10 and the train : By remotely detecting an abnormality such as damage to the track 10 and the train, it is possible to reduce the man-hours for manual inspection.
　Outline of operation:
　Vibration when a train passes through the track 10 is monitored via an optical fiber cable 20, and an abnormality such as damage to the track 10 or the train is determined based on the vibration pattern.
[0065]
(E) 　Abnormal noise detection
　task and effect:
By remotely detecting abnormalities in the track 10, trains, surrounding structures, and the environment around the track, it is possible to reduce the man-hours for manual inspection.
　Outline of operation:
　Sounds inside and outside the line 10 are monitored via an optical fiber cable 20, and a specific pattern is determined to be abnormal sound.
[0066]
(F)
　Problems and effects of generating strong winds (including typhoons and tornadoes) :
　By remotely detecting the wind speed of the entire track along the track 10, it is possible to avoid the progress of the train to the dangerous area.
　Outline of operation: The
　wind speed is monitored from the vibration of the optical fiber cable 20 laid along the overhead wire on the line 10, and the wind speed exceeding the threshold value is determined as a strong wind.
[0067]
(G) Flood damage
　issues and effects:
　By remotely detecting the flood damage situation along the track 10, it is possible to avoid the progress of the train to the dangerous area.
　Outline of operation: The
　position where the temperature change is remarkably changed is specified from the temperature condition of the entire line along the line 10, and it is determined that flood damage has occurred at the specified position.
[0068]
　Subsequently, with reference to FIG. 18, the hardware configuration of the computer 40 that realizes the line monitoring device 33 will be described below.
　As shown in FIG. 18, the computer 40 includes a processor 401, a memory 402, a storage 403, an input / output interface (input / output I / F) 404, a communication interface (communication I / F) 405, and the like. The processor 401, the memory 402, the storage 403, the input / output interface 404, and the communication interface 405 are connected by a data transmission line for transmitting and receiving data to and from each other.
[0069]
　The processor 401 is, for example, an arithmetic processing unit such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). The memory 402 is, for example, a memory such as a RAM (Random Access Memory) or a ROM (Read Only Memory). The storage 403 is a storage device such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), or a memory card. Further, the storage 403 may be a memory such as a RAM or a ROM.
[0070]
　The storage 403 stores a program that realizes the functions of the fiber sensing unit 331 and the detection unit 332 included in the line monitoring device 33. The processor 401 realizes the functions of the fiber sensing unit 331 and the detection unit 332 by executing each of these programs. Here, when executing each of the above programs, the processor 401 may read these programs onto the memory 402 and then execute the programs, or may execute the programs without reading them onto the memory 402. The memory 402 and the storage 403 also play a role of storing information and data held by the fiber sensing unit 331 and the detection unit 332.
[0071]
　In addition, the above-mentioned programs are stored using various types of non-transitory computer readable medium and can be supplied to a computer (including a computer 40). Non-transient computer-readable media include various types of tangible storage media. Examples of non-temporary computer-readable media include magnetic recording media (eg, flexible discs, magnetic tapes, hard disk drives), photomagnetic recording media (eg, photomagnetic discs), CD-ROMs (Compact Disc-Read Only Memory). , CD-R (CD-Recordable), CD-R / W (CD-ReWritable), semiconductor memory (for example, mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (Random Access Memory) )including. The program may also be supplied to the computer by various types of transient computer readable medium. Examples of temporary computer-readable media include electrical, optical, and electromagnetic waves. The temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire and an optical fiber, or a wireless communication path.
[0072]
　The input / output interface 404 is connected to a display device 4041, an input device 4042, and the like. The display device 4041 is a device that displays a screen corresponding to drawing data processed by the processor 401, such as an LCD (Liquid Crystal Display) or a CRT (Cathode Ray Tube) display. The input device 4042 is a device that receives an operator's operation input, and is, for example, a keyboard, a mouse, a touch sensor, and the like. The display device 4041 and the input device 4042 may be integrated and realized as a touch panel. The computer 40 may also include a distributed acoustic sensor, a distributed vibration sensor, a sensor (not shown) including a distributed temperature sensor, and the like, and the sensor may be connected to the input / output interface 404.
[0073]
　The communication interface 405 transmits / receives data to / from an external device. For example, the communication interface 405 communicates with an external device via a wired communication path or a wireless communication path.
[0074]

　Hereinafter, the operation of the track monitoring system according to the present embodiment will be described. Here, the operation flow of the line monitoring system according to the present embodiment will be described with reference to FIG.
[0075]
　As shown in FIG. 19, first, the fiber sensing unit 331 injects pulsed light into at least one communication optical fiber included in the optical fiber cable 20 (step S21).
　Subsequently, the fiber sensing unit 331 receives the backscattered light from the same communication optical fiber as the communication optical fiber incident with the pulsed light (step S22).
[0076]
　Subsequently, the fiber sensing unit 331 identifies the position of the line 10 that generated the backscattered light received in step S22 (step S23). At this time, the fiber sensing unit 331 may specify the position where the backscattered light is generated by using the method based on the time difference described above. Further, the fiber sensing unit 331 detects the vibration state, the temperature state, the sound state, and the like at the specified position of the line 10.
[0077]
　Subsequently, the detection unit 332 detects a pattern according to the running state of the train on the track 10 based on the backscattered light received in step S22. More specifically, the pattern is detected based on the processing result of the backscattered light by the fiber sensing unit 331. Then, the detection unit 332 detects the running state of the train on the track 10 based on the detected pattern (step S24). At this time, the detection unit 332 may detect the running state of the train on the track 10 by using any of the methods B1 to B3 described above.
[0078]
　Subsequently, the detection unit 332 detects a pattern according to the state of the position of the line 10 identified in step S23 based on the backscattered light received in step S22. More specifically, the pattern is detected based on the processing result of the backscattered light by the fiber sensing unit 331. Then, the detection unit 332 detects an abnormal state of the position of the line 10 identified in step S23 based on the detected pattern (step S25). At this time, the detection unit 332 may detect the abnormal state by using any of the methods A1 to A3 described above.
[0079]
　After that, the detection unit 332 detects a pattern according to the state of the train passing through the position of the track 10 specified in step S23, based on the backscattered light received in step S22. More specifically, the pattern is detected based on the processing result of the backscattered light by the fiber sensing unit 331. Then, the detection unit 332 detects an abnormal state of the train that has passed the position of the track 10 specified in step S23 based on the detected pattern (step S26). At this time, the detection unit 332 may detect the abnormal state by using any of the methods C1 to C4 described above.
[0080]
　In FIG. 19, the processes of steps S23 to S26 may be performed each time the backscattered light is received in step S22. Alternatively, in step S22, after receiving a plurality of backscattered light, the processes of steps S23 to S26 may be performed for each backscattered light. Alternatively, in steps S22 and S23, after receiving a plurality of backscattered lights and specifying the generation positions of each, the processes of steps S24 and S26 may be performed.
[0081]

　As described above, according to the present embodiment, the backscattered light (optical signal) is received from at least one communication optical fiber included in the optical fiber cable 20, and the received backscattered light (optical signal) is received. A pattern corresponding to the state of the line 10 is detected based on the light, and an abnormal state of the line 10 is detected based on the detected pattern. As described above, according to the present embodiment, for example, the abnormal state of the line 10 can be determined by dynamically pattern-analyzing the change of the vibration generated in the line 10 (for example, the transition of the change in the strength of the vibration). To detect. Therefore, the abnormal state of the line 10 can be detected with high accuracy.
[0082]
　Further, according to the present embodiment, a pattern corresponding to the running state of the train on the track 10 is detected based on the received backscattered light, and the running state of the train on the track 10 is based on the detected pattern. Is detected. As described above, according to the present embodiment, similarly to the detection of the abnormal state of the track 10, for example, by dynamically pattern-analyzing the change of the vibration generated on the track 10, the running state of the train on the track 10 Is detected. Therefore, the running state of the train on the track 10 can be detected with high accuracy.
[0083]
　Further, according to the present embodiment, a pattern corresponding to the state of the train on the track 10 is detected based on the received backscattered light, and an abnormal state of the train on the track 10 is determined based on the detected pattern. To detect. As described above, according to the present embodiment, similarly to the detection of the abnormal state of the track 10, for example, by dynamically pattern-analyzing the change of the vibration generated on the track 10, the abnormal state of the train on the track 10 is analyzed. Is detected. Therefore, the abnormal state of the train on the track 10 can be detected with high accuracy.
[0084]
　Further, according to the present embodiment, in order to detect an abnormal state of the track 10 and a running state of the train, an existing optical fiber for communication may be used. Therefore, since a dedicated structure for detecting the abnormal state of the track 10 and the running state of the train is not required, the track monitoring system can be constructed at low cost.
[0085]
　Further, according to the present embodiment, since the abnormal state of a plurality of lines 10 can be detected simultaneously and remotely by using the existing optical fiber for communication, the state of the line 10 can be easily grasped and the state of the line 10 can be grasped. The cost for grasping the state of the track 10 can also be reduced.
[0086]
　Further, according to the present embodiment, an optical fiber sensing technique using an optical fiber as a sensor is used. Therefore, advantages such as being unaffected by electromagnetic noise, eliminating the need for power supply to the sensor, being excellent in environmental resistance, and facilitating maintenance can be obtained.
[0087]
The
　detection unit 332 shall hold the abnormal state of the line 10 detected above for each position of the line 10, and periodically (for example, every year) at that position. By detecting the abnormal state of, the state change of the abnormal state at that position over time may be detected.
[0088]
　Further, the detection unit 332 may detect a sign of abnormality or breakage of the position of the line 10 based on a change of state of the position of the line 10 with time.
[0089]
　Further, the analyst may actually disassemble the portion of the position of the line 10 detected as abnormal by the detection unit 332 to determine the actual abnormality level. At this time, if there is a difference between the abnormality level detected by the detection unit 332 and the abnormality level determined by the analyst, the difference may be fed back to the detection unit 332. In this case, since the detection unit 332 subsequently detects the abnormal state of the line 10 so as to approach the actual abnormality level, the detection accuracy can be improved.
[0090]
　Further, the detection unit 332 may predict a collision between trains based on the position of each train, the traveling speed, the degree of acceleration / deceleration, etc., as the traveling state of the trains on the track 10.
[0091]
　Further, when the detection unit 332 machine-learns the pattern according to the state of the line 10 by the above-mentioned method A3, it is considered that the state of the line 10 differs depending on the region. For example, the conditions may differ between warm and cold regions. When the pattern according to the running state of the train on the track 10 is machine-learned by the above-mentioned method B3, it is considered that the running state of the train differs depending on the region. Therefore, the detection unit 332 may perform machine learning for each region by using the teacher data corresponding to the region.
[0092]
　Further, in the above-described embodiment, it is assumed that the existing optical fiber cable 20 is used, but as shown in FIG. 20, the optical fiber cable 20 is newly installed, and the data collecting unit 34 is attached to the newly installed optical fiber cable 20. May be connected. The data collection unit 34 also collects data of the pattern of the line 10 (for example, sound, temperature, vibration, etc.) and transmits the collected data to the detection unit 332. At this time, the data may be transmitted from the data collection unit 34 to the detection unit 332 via the optical fiber cable 20 or via a separately provided radio. The detection unit 332 detects an abnormal state of the track 10 and a running state of the train based on the data collected by the data collecting unit 34 and the fiber sensing unit 331. Therefore, the detection accuracy can be improved.
[0093]
　Further, as shown in FIG. 21, a train operation system 50 that manages the operation of trains on the track 10 may be provided based on the detection result by the track monitoring device 33. The train operation system 50 is an example of a transmission unit. The train operation system 50 provides the train driver with a train control signal that controls the running of the train based on the abnormal state of the track 10 or the train, or the running state of the train on the track 10, to the train driver, the highway radio, and the track. It may be transmitted via the information board on the 10th, the Internet, an application, or the like. For example, the train operation system 50 is for trains that instructs the driver of the corresponding train to stop the train in an emergency when an abnormal state of the track 10 or the train is detected or a collision between trains is predicted. It is conceivable to transmit a control signal. Further, the train operation system 50 presents to the system administrator, etc., an abnormal state of the track 10 or the train, a change in the state of the abnormal state of the track 10 or the train over time, a sign of the abnormality or damage of the track 10 or the train, and the like. You may. Further, the train operation system 50 may calculate the repair time of the track 10 and the repair time of the train based on the detection result by the track monitoring device 33, and present the repair time of the track 10 to the system administrator or the like. good. Further, although the train operation system 50 is provided outside the communication carrier station building 30, a part of the functions (for example, the function of the transmission unit, etc.) may be provided inside the communication carrier station building 30. Further, when the train operation system 50 is provided outside the communication carrier station building 30, the line 10 connected to each of the plurality of communication carrier station buildings 30 by the optical fiber cable 20 is centralized in one train operation system 50. You may monitor it.
[0094]
　Further, the fiber sensing unit 331 and the detection unit 332 of the line monitoring device 33 may be provided separately from each other. For example, only the fiber sensing unit 331 may be provided inside the communication carrier station building 30, and the line monitoring device 33 including the detection unit 332 may be provided outside the communication carrier station building 30.
[0095]
　Further, in the above-described embodiment, only one fiber sensing unit 331 is provided and occupies the optical fiber cable 20, but the present invention is not limited to this. Here, the arrangement of the fiber sensing unit 331 in the line monitoring system according to another embodiment will be described with reference to FIGS. 22 to 25. Note that in FIGS. 22 to 25, the detection unit 332 is not shown.
[0096]
　In the example of FIG. 22, the fiber sensing unit 331 shares the optical fiber cable 20 with the existing communication equipment 31. Further, in order to share the optical fiber cable 20 between the fiber sensing unit 331 and the existing communication equipment 31, a filter 32 for signal separation is provided.
[0097]
　In the example of FIG. 23, one fiber sensing unit 331 is provided for each of the plurality of communication carrier station buildings 30 (in FIG. 23, the two communication carrier stations 30A and 30Z). Specifically, fiber sensing units 331A and 331Z are provided inside the communication carrier station buildings 30A and 30Z, respectively. In the example of FIG. 23, the line 10A is connected to the communication carrier station building 30A by the optical fiber cable 20, and the line 10B is connected to the communication carrier station building 30Z by the optical fiber cable 20, and the lines 10A and 10B are connected. Is connected by an optical fiber cable 20. The communication equipments 31A and 31Z correspond to the communication equipment 31, and the filters 32A and 32Z correspond to the filter 32.
　In the example of FIG. 23, the fiber sensing units 331A and 331Z both monitor the lines 10A and 10B.
[0098]
　In the example of FIG. 24, the data collection unit 34 is provided in the vicinity of the line 10A as compared with FIG. 23. Here, only one data collection unit 34 is provided for the lines 10A and 10B, but the data collection unit 34 is one for a predetermined number of lines 10 or a predetermined line length of the line 10. One is provided for each, and one or more may be provided.
[0099]
　In the example of FIG. 24, each data collection unit 34 collects data of the corresponding line 10 pattern (for example, sound, temperature, vibration, etc.), and the detection unit 332 collects the data collected by each data collection unit 34. Summarize. At this time, data may be transmitted from each data collection unit 34 to the detection unit 332 via the optical fiber cable 20 or via a separately provided radio. The detection unit 332 detects an abnormal state or a running state of the train based on the data of the track 10 for which the data collection unit 34 has collected data.
[0100]
　Therefore, the monitor section of one fiber sensing unit 331 is shortened, and the number of lines 10 to be monitored and the line length are reduced. Since the monitor section of the fiber sensing unit 331 is short, the transmission distance of the pulsed light and the backscattered light is shortened, so that the fiber loss is reduced. As a result, the S / N ratio (signal-to-noise ratio) of the received backscattered light can be improved, and the monitor accuracy can be improved. Further, the monitoring cycle can be improved by reducing the number of lines 10 to be monitored and the line length of the fiber sensing unit 331.
[0101]
　In the example of FIG. 25, a plurality of fiber sensing units 331 (in FIG. 25, two fiber sensing units 331A and 331Z) are provided in one communication carrier station building 30AZ. In the example of FIG. 25, the line 10A is connected to the fiber sensing unit 331A by the optical fiber cable 20, the line 10B is connected to the fiber sensing unit 331Z by the optical fiber cable 20, and the lines 10A and 10B are optical. It is connected by a fiber cable 20. The communication equipments 31A and 31Z correspond to the communication equipment 31, and the filters 32A and 32Z correspond to the filter 32.
[0102]
　In the example of FIG. 25, the fiber sensing units 331A and 331Z both monitor the lines 10A and 10B. However, the fiber sensing unit 331A injects pulsed light in the clockwise direction to monitor these lines 10, and the fiber sensing unit 331Z injects pulsed light in the counterclockwise direction to transmit these lines 10. Monitor.
[0103]
　When a plurality of fiber sensing units 331 are provided as shown in FIGS. 23 to 25, one line monitoring device 33 including the detection unit 332 may be provided for the plurality of fiber sensing units 331. Then, the state of the line 10 connected to each of the plurality of fiber sensing units 331 by the optical fiber cable 20 may be intensively detected by one line monitoring device 33. In this case, the line monitoring device 33 may be provided inside any one of the communication carrier station building 30, or may be provided outside the communication carrier station building 30.
[0104]
　Further, the optical fiber cable 20 laid on the line 10 may be disconnected. Therefore, with reference to FIGS. 26 to 28, the operation of the fiber sensing unit 331 when the optical fiber cable 20 is disconnected in the line monitoring system according to another embodiment will be described. Note that in FIGS. 26 to 28, the detection unit 332 is not shown.
[0105]
　The example of FIG. 26 is an example in which the optical fiber cable 20 of the line 10 is disconnected in the configuration of FIG. 22. The fiber sensing unit 331 continues to inject pulsed light into the optical fiber cable 20 even if the optical fiber cable 20 is disconnected. As a result, the communication carrier station building 30 can continuously monitor the section up to the disconnected position.
[0106]
　The example of FIG. 27 is an example in which the optical fiber cable 20 of the line 10A is broken in the configuration of FIG. 23. The fiber sensing units 331A and 331Z continue to inject pulsed light into the optical fiber cable 20 even if the optical fiber cable 20 is disconnected. At this time, the line 10 is always connected to two or more communication carrier station buildings 30 (two communication carrier station buildings 30A and 30Z in FIG. 27). Therefore, by monitoring the communication carrier stations 30A and 30Z from both directions, it is possible to construct a redundant configuration in which the entire section can be continuously monitored in the event of a single failure.
[0107]
　The example of FIG. 28 is an example in which the optical fiber cable 20 of the line 10A is broken in the configuration of FIG. 25. The fiber sensing units 331A and 331Z continue to inject pulsed light into the optical fiber cable 20 even if the optical fiber cable 20 is disconnected. At this time, in the example of FIG. 28, a ring configuration in which the optical fiber cables 20 are connected in a ring shape is constructed. Therefore, by monitoring the ring from one communication carrier station building 30AZ in both directions, it is possible to construct a redundant configuration capable of continuously monitoring the entire section in the event of a single failure.
[0108]
　Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various changes that can be understood by those skilled in the art can be made to the structure and details of the present disclosure within the scope of the present disclosure.
[0109]
　In addition, some or all of the above embodiments may be described as in the following appendix, but are not limited to the following.
　　　(Appendix 1)
　A cable including a communication optical fiber laid on a line,
　a receiving unit that receives an optical signal from at least one communication optical fiber included in the cable, and the
　line based on the optical signal. A
　line monitoring system including a detection unit that detects a pattern according to the state of the line and detects an abnormal state of the line based on the detected pattern according to the state of the line.
　　　(Appendix 2) The
　receiving unit
　identifies the position of the line on which the optical signal is generated based on the optical signal, and the
　detecting unit is
　based on a pattern according to the detected state of the line. ,
　The track monitoring system according to Appendix 1, which detects an abnormal state of the identified track position .
　　　(Appendix 3) The
　detection unit detects
　a pattern according to the running state of the train on the track based on the optical signal, and based on the detected pattern according to the running state of the train on the track, said.
　The track monitoring system according to Appendix 1 or 2 , which detects the running state of a train on a track.
　　　(Appendix 4) The
　detection unit is
　On the basis of the optical signal, the detected pattern according to the state of the train in line, on the basis of the pattern corresponding to the state of the train in the detected said line, for detecting the train of the abnormal condition in the line,
　Appendix The track monitoring system according to 3.
　　　(Appendix 5)
　Train control for controlling train travel to the train driver based on the detected abnormal state of the track, the running state of the train on the track, and the abnormal state of the train on the track.
　The line monitoring system according to Appendix 4, further comprising a transmitter for transmitting a signal .
　　　(Appendix 6)
　When
　an abnormal state of the track or train is detected, or when a collision between trains is predicted as a running state of the train on the track , the transmitter informs the driver of the corresponding train.
　The track monitoring system according to Appendix 5, which transmits the control signal for the train instructing the emergency stop of the train .
　　　(Appendix 7) From
　at least one communication optical fiber included in the cable laid on the line, a receiving unit that receives an
　optical signal and a pattern according to the state of the line are detected based on the optical signal. A
　line monitoring device including a detection unit that detects an abnormal state of the line based on a pattern corresponding to the detected state of the line.
　　　(Appendix 8) The
　receiving unit is
　The position of the line on which the optical signal is generated is specified based on the optical signal, and the
　detection unit determines the position of the specified
　line based on a pattern according to the detected state of the line. The
　track monitoring device according to Appendix 7, which detects an abnormal state of the above.
　　　(Appendix 9) The
　detection unit detects
　a pattern according to the running state of the train on the track based on the optical signal, and based on the detected pattern according to the running state of the train on the track, said.
　The track monitoring device according to Appendix 7 or 8 , which detects the running state of a train on a track.
　　　(Appendix 10) The
　detection unit detects
　a pattern according to the state of the train on the line based on the optical signal, and based on the detected pattern according to the state of the train on the line , the detection unit on the line.
　The track monitoring device according to Appendix 9, which detects an abnormal state of a train .
　　　(Appendix 11)
　A line monitoring method using a line monitoring device, in which
　an optical signal is received from at least one communication optical fiber included in a cable laid on the
　line, and the state of the line is based on the optical signal. A
　line monitoring method for detecting an abnormal state of the line based on the detected pattern according to the state of the line.
　　　(Appendix 12) The
　computer 　detects an optical signal
　from at least one communication optical fiber included in a cable laid on the
line, and a pattern according to the state of the line based on the optical signal.
　A non-temporary computer-readable medium containing a procedure for detecting an abnormal state of the line and a program for executing the detected abnormal state of the line based on a pattern corresponding to the detected state of the line .
[0110]
　This application claims priority on the basis of Japanese application Japanese Patent Application No. 2018-226683 filed on December 3, 2018, and incorporates all of its disclosures herein.
Code description
[0111]
　10, 10A, 10B Line
　20 Optical fiber cable
　30, 30A, 30Z, 30AZ Communication carrier station building
　31, 31A, 31Z Communication equipment
　32, 32A, 32Z Filter
　33 Line monitoring device
　331, 331A, 331Z Fiber sensing unit
　332 Detection unit
　34 Data collection unit
　40 Computer
　401 Processor
　402 Memory
　403 Storage
　404 Input / output interface
　4041 Display device
　4042 Input device
　405 Communication interface
　50 Train operation system
The scope of the claims
[Claim 1]
　A cable including a communication optical fiber laid on a line,
　a receiving unit that receives an optical signal from at least one communication optical fiber included in the cable, and a receiver
　based on the optical signal, depending on the state of the line. A
　line monitoring system including a detection unit that detects a pattern and detects an abnormal state of the line based on a pattern corresponding to the detected state of the line.
[Claim 2]
　The receiving unit
　identifies the position of the line on which the optical signal is generated based on the optical signal, and the
　detecting unit identifies the position of the line according to the detected
　state of the line.
　The line monitoring system according to claim 1, wherein an abnormal state of the position of the line is detected .
[Claim 3]
　The detection unit detects
　a pattern according to the running state of the train on the track based on the optical signal, and based on the detected pattern according to the running state of the train on the track , the detection unit of the train on the track.
　The track monitoring system according to claim 1 or 2 , which detects a traveling state .
[Claim 4]
　The detection unit detects
　a pattern according to the state of the train on the track based on the optical signal, and based on the detected pattern according to the state of the train on the track, the abnormal state of the train on the track. detecting a
　line monitoring system according to claim 3.
[Claim 5]
　A train control signal for controlling train running is transmitted to the train driver based on the detected abnormal state of the track, the running state of the train on the track, and the abnormal state of the train on the track.
　The line monitoring system according to claim 4, further comprising a transmitter .
[Claim 6]
　When
　an abnormal state of the track or train is detected, or when a collision between trains is predicted as a running state of the train on the track , the transmitting unit informs the driver of the corresponding train of the train.
　The track monitoring system according to claim 5 , which transmits the train control signal instructing an emergency stop .
[Claim 7]
　A receiving unit that receives an optical signal from at least one communication optical fiber included in a cable laid on the
　line, and a pattern corresponding to the state of the line is detected based on the optical signal, and the detected pattern is described. A line
　monitoring device including a detection unit that detects an abnormal state of the line based on a pattern according to the state of the line.
[Claim 8]
　The receiving unit
　identifies the position of the line on which the optical signal is generated based on the optical signal, and the
　detecting unit identifies the position of the line according to the detected
　state of the line.
　The line monitoring device according to claim 7, wherein an abnormal state of the position of the line is detected .
[Claim 9]
　The detection unit detects
　a pattern according to the running state of the train on the track based on the optical signal, and based on the detected pattern according to the running state of the train on the track , the detection unit of the train on the track.
　The track monitoring device according to claim 7 or 8 , which detects a traveling state .
[Claim 10]
　The detection unit detects
　a pattern according to the state of the train on the track based on the optical signal, and based on the detected pattern according to the state of the train on the track, the abnormal state of the train on the track. detecting a
　line monitoring device according to claim 9.
[Claim 11]
　A line monitoring method using a line monitoring device,
　in which an optical signal is received from at least one communication optical fiber included in a cable laid on the
　line, and a pattern according to the state of the line is obtained based on the optical signal. A
　line monitoring method for detecting an abnormal state of the line based on a pattern corresponding to the detected state of the line.
[Claim 12]
　The computer 　detects and detects a pattern according to the state of the line based on
　the procedure of receiving an optical signal from at least one communication optical fiber included in the cable laid on the line and the
optical signal. A
　non-temporary computer-readable medium containing a procedure for detecting an abnormal state of the line and a program for executing the procedure based on a pattern according to the state of the line .