WO2019026297A1

WO2019026297A1 - Abnormality detection device, abnormality detection system, and abnormality detection method

Info

Publication number: WO2019026297A1
Application number: PCT/JP2017/028493
Authority: WO
Inventors: 悟士隅田; 暁史高橋
Original assignee: 株式会社日立製作所
Priority date: 2017-08-04
Filing date: 2017-08-04
Publication date: 2019-02-07
Also published as: JP6743304B2; EP3663160A4; EP3663160A1; JPWO2019026297A1

Abstract

[Problem] To provide an abnormality detection device capable of detecting an abnormality on a track. [Solution] The present invention comprises: an acquisition section that acquires a threshold excess time indicating the time at which a characteristic value of a physical quantity of each drive system disposed in a rail vehicle exceeds a threshold and a drive system position indicating the position of the drive system with respect to the rail vehicle at the threshold excess time; a determination section that determines whether or not there is a correlation between the plurality of threshold excess times and the drive system positions at the threshold excess times acquired for the plurality of drive systems disposed in the rail vehicle by the acquisition section; and an output section that performs output on the basis of the determination result of the determination section. If it is determined by the determining section that there is a correlation, the output section outputs a track abnormality signal indicating that there is an abnormality on the track.

Description

ABNORMALITY DETECTING APPARATUS, ABNORMALITY DETECTING SYSTEM, AND ABNORMALITY DETECTING METHOD

The present invention relates to an abnormality detection apparatus, an abnormality detection system, and an abnormality detection method, and is suitably applied to, for example, a track traveling vehicle traveling on a track.

Since a track traveling vehicle travels on a track with little friction, it requires less energy for transportation and has become one of the social infrastructures. On the other hand, if an abnormality occurs in the drive system or the track, it affects other track traveling vehicles traveling on the same track, so it is required to detect the abnormality without leaking it. However, since the abnormality detection work using a dedicated device is costly, a technology capable of detecting an abnormality in parallel with the commercial operation of a track traveling vehicle has been developed.

For example, there is disclosed a technique of observing the currents of two motors driving the left and right wheels respectively and judging that there is an abnormality in the drive system when the difference between the current values exceeds a threshold (see Patent Document 1). . Furthermore, in the technology described in Patent Document 1, the difference between the current value due to the speed difference between the inner ring and the outer ring at the time of curve is allowed by changing the current threshold at the time of straight line and at the time of curve based on the track position. , To prevent abnormal false detection at the time of curve.

JP, 2015-42106, A

However, in the technology described in Patent Document 1, the target of abnormality detection is only the drive system of the track traveling vehicle, and it is not possible to detect the track abnormality. When the track is worn or broken, the current waveform of the motor is different from that in the normal state, but the technology described in Patent Document 1 erroneously detects this as an abnormality in the drive system. For this reason, the inspection cost for the drive system that should be normal is wasted. In addition, when an abnormality in the drive system is erroneously detected and an abnormality in the track is missed, there is a risk that the track traveling vehicle may derail.

The present invention has been made in consideration of the above points, and an object of the present invention is to propose an abnormality detection apparatus, an abnormality detection system, and an abnormality detection method capable of detecting an abnormality in a track.

In order to solve such problems, the present invention is an abnormality detection device for detecting an abnormality relating to a track traveling vehicle traveling on a track, wherein the feature amount of the physical quantity of the drive system provided in the track traveling vehicle exceeds a threshold. An acquisition unit for acquiring a drive system position indicating the position of the drive system with respect to the track traveling vehicle at the threshold exceed time indicating the detected time, and the plurality of drive systems provided in the track traveling vehicle A determination unit that determines whether there is a correlation between a plurality of threshold excess times acquired by the acquisition unit and the drive system position at the threshold excess time; an output unit that outputs based on the determination result by the determination unit The output unit is configured to output a trajectory abnormality signal indicating that there is an abnormality in the trajectory when it is determined by the determination unit that there is a correlation.

Further, in the present invention, a track traveling vehicle traveling on a track, and at a threshold overrun time indicating a time when a feature quantity of a physical quantity of a drive system provided on the track traveling vehicle exceeds a threshold, and the threshold overrun time An acquisition unit for acquiring a drive system position indicating a position of the drive system with respect to the track traveling vehicle, and a plurality of threshold exceeded times and the threshold values acquired by the acquisition unit for a plurality of drive systems provided in the track traveling vehicle A determination unit that determines whether or not there is a correlation in the drive system position at the excess time, and an output unit that performs an output based on the determination result by the determination unit, the output unit being correlated by the determination unit When it is determined that there is a sex, an orbit abnormal signal indicating that there is an abnormality in the orbit is output.

Further, in the present invention, the abnormality detection method is performed by an abnormality detection apparatus for detecting an abnormality related to a track traveling vehicle traveling on a track, wherein the feature amount of the drive system physical quantity provided in the track traveling vehicle is a threshold. A first step of acquiring a drive system position indicating a position of the drive system with respect to the track traveling vehicle at a threshold over time showing the exceeded time and the threshold run time; and a plurality of drives provided on the track traveling vehicle A second step of determining whether or not there is a correlation between the plurality of threshold exceeded times obtained in the first step and the drive system position at the threshold exceeded time for the system, and the determination in the second step And a third step of outputting a signal based on the result, wherein, in the third step, the trajectory is abnormal when it is determined that there is a correlation in the second step. And it outputs a track error signal indicating that.

Further, in the present invention, it is an abnormality detection device for detecting an abnormality relating to a track traveling vehicle traveling on a track, wherein a feature amount of a physical quantity of a drive system provided on the track traveling vehicle and the feature amount are measured. An acquiring unit that acquires a track position indicating a position on the track, and a plurality of physical quantities acquired by the acquiring unit and a track position at which the physical quantity is acquired for a plurality of drive systems provided in the track traveling vehicle It is determined whether or not the distance between the track positions where the physical quantity exceeds the threshold among the plurality of track positions is constant, and the physical quantity of the track position exceeding the threshold is over time. A determination unit that determines whether or not there is an increase, and an output unit that performs an output based on the determination result by the determination unit, the output unit being determined by the determination unit to be dependent, and Not equal is determined, if it is determined to be increased, and outputs a track error signal indicating that there is abnormality in the track.

According to the present invention, it is possible to realize an abnormality detection device capable of detecting an abnormality in a track, an abnormality detection system, and an abnormality detection method.

It is a figure showing an example of composition of an unusual detection system in a 1st embodiment. It is a figure showing an example of the composition of the track traveling vehicle in a 1st embodiment. It is a figure which shows the current waveform of the motor in 1st Embodiment. It is a figure which shows the flowchart which concerns on the process which the abnormality detection apparatus in 1st Embodiment performs. It is a figure which shows the relationship of the threshold value excess time and driving system position in 1st Embodiment. FIG. 5 is a schematic view of a track abnormality and a drive system abnormality in the first embodiment. It is a figure which shows the flowchart which concerns on the process which the abnormality detection apparatus in 2nd Embodiment performs. It is a schematic diagram of the seam in a 2nd embodiment, and orbital abnormalities. It is a figure which shows the relationship of the correlation in the joint in 2nd Embodiment, and the relationship of the correlation in orbital abnormality. It is a figure which shows the flowchart which concerns on the process which the abnormality detection apparatus in 3rd Embodiment performs. It is a schematic diagram of the wheel abnormality in 3rd Embodiment, a gear abnormality, and a motor abnormality. In the third embodiment, the relationship between the threshold excess time and the drive system position in the wheel abnormality, the relationship between the threshold excess time and the drive system position in the gear abnormality, and the relationship between the threshold excess time and the drive system position in the motor abnormality are described. FIG. It is a figure which shows the flowchart which concerns on the process which the abnormality detection apparatus in 4th Embodiment performs. It is a figure which shows the relationship of the feature-value and track position in drive-system abnormality in 4th Embodiment, and the relationship between the feature-value in track | orbit abnormality, a joint, and a pointer, and a track position. It is a schematic diagram of the track abnormality in a 4th embodiment, a joint, and a pointer. It is a figure which shows the relationship of the feature-value and track position in track | orbit abnormality in 4th Embodiment, and the relationship between the feature-value in a pointer, and a track position. It is a figure which shows the relationship of the feature-value in case there exists an abnormal trajectory, a pointer, and a joint in a 4th embodiment, and an orbital position.

An embodiment of the present invention will now be described in detail with reference to the drawings.

(1) First Embodiment FIG. 1 is a diagram showing an example of a configuration of an abnormality detection system 100 according to a first embodiment. The abnormality detection system 100 is configured to include a plurality of track traveling vehicles such as the track traveling vehicle 1 and a host system 20 capable of communicating with the plurality of track traveling vehicles. In addition, since each structure of a plurality of track traveling vehicles is basically the same, in the present embodiment, the track traveling vehicle 1 will be described as an example. In the abnormality detection system 100, an abnormality (an abnormality of the track traveling vehicle 1, an abnormality of the track 2, etc.) related to the track traveling vehicle 1 traveling on the track 2 is detected.

The track traveling vehicle 1 is composed of the vehicles 1a to 1n, includes wheels 3a to 3k, and travels on the track 2 at a vehicle speed v, for example. In the present embodiment, it will be described distance to each wheel axis of the case relative to the distal end of the track traveling vehicle 1 (relative position) as the drive system position y _{a ~} y _k.

The host system 20 generates a command (a d-axis current command, a q-axis current command, a stop command, a degeneracy command, etc.) for controlling the traveling of the track traveling vehicle 1 and transmits it to the track traveling vehicle 1 Example) to receive and record data transmitted from the track traveling vehicle 1. The functions of the host system 20 (command unit, identification unit described later, etc.) may be realized by the CPU reading and executing a program in the memory, or may be realized by hardware such as a dedicated circuit, It may be realized by other methods.

An appropriate configuration can be adopted for the host system 20. For example, as a configuration of the upper system 20, a computer may be provided for each track traveling vehicle, and a computer that manages all these computers may be provided, or another configuration may be used. Also, for example, some components of the upper system 20 may be provided in the track traveling vehicle 1 or may be provided separately from the upper system 20 and the track traveling vehicle 1.

FIG. 2A is a diagram showing an example of a configuration of one track traveling vehicle 1 (vehicle 1a). The configuration of the vehicles 1b to 1n other than the vehicle 1a of the track traveling vehicle 1 is the same, and thus the illustration and the description thereof will be omitted.

The vehicle 1a includes wheels 3a to 3d, motors 4a to 4d, inverters 5a to 5d, gears 6a to 6d, and an abnormality detection device 8. For example, the torque of the motor 4a which is a drive source is controlled by the inverter 5a, and is transmitted to the wheel 3a via the gear 6a. The inverter 5a is composed of a main circuit 5a1 and a control circuit 5a2.

In the present embodiment, the case is illustrated where all the wheels 3a to 3d are provided with the motors 4a to 4d and the inverters 5a to 5d, but in the case where at least two front and rear wheels are provided with a motor and an inverter. Can realize anomaly detection of the trajectory 2. In the following, the wheel 3a, the motor 4a and the gear 6a are defined as the drive system 7a, the wheel 3b, the motor 4b and the gear 6b are defined as the drive system 7b, and an abnormality for the track 2 and the

drive systems

7a and 7b The detection is mainly described. The same applies to abnormality detection of the drive systems 7c to 7k (not shown).

The abnormality detection device 8 is an FPGA (Field-Programmable Gate Array), a personal computer or the like. The functions (acquisition unit, determination unit, output unit, adjustment unit, etc.) of the abnormality detection device 8 shown in FIG. 2B may be realized by, for example, an integrated circuit whose configuration can be set by a designer, or the CPU It may be realized by reading and executing a program of the memory, or may be realized by hardware such as a dedicated circuit, or may be realized by another method.

For example, the abnormality detection device 8 is communicably connected to the

inverters

5a and 5b, and acquires physical quantities such as current flowing to the

motors

4a and 4b or the

inverters

5a and 5b via the

inverters

5a and 5b (an example of an acquisition unit) Based on the acquired physical quantities, abnormalities in the track 2 and the

drive systems

7a and 7b are detected (judged) (an example of a determination unit).

Further, for example, the abnormality detection device 8 is communicably connected to the host system 20, and transmits and receives various information (for example, transmits a trajectory abnormality signal described later, a drive system abnormality signal, etc., d axis current command, q An axis current command, a stop command, a degeneracy command and the like are received (an example of an output unit).

The main components related to the abnormality detection are as described above. Next, the problem of abnormality detection will be described.

FIG. 3A shows a current waveform of U-phase current _iu-4a of motor 4a when abnormality occurs in track 2 or drive system 7a, and FIG. 3B shows track 2 or drive FIG. 18 is a diagram showing a current waveform of U-phase current _iu-4 b of motor 4 b when an abnormality occurs in system 7 b.

Setting the threshold value ± _{i uX} is the track 2 and the

driving system

7a, 7b indicates the extent to which U-phase current _i _u-4a, is _{i u-4b} fit when it is normal, for example, based on the rated current of the motor 4a it can. The abnormality of the track 2 includes wear, breakage and the like. The abnormality of the drive system 7a includes the deformation of the wheel 3a, the seizure of the bearing of the wheel 3a, the deformation of the rotation shaft of the motor 4a, and the loss of the teeth of the gear 6a.

An abnormality in the track 2 or the drive system 7a eventually becomes a disturbance torque to the motor 4a, but appears as a current waveform since the torque of the motor 4a and the current of the motor 4a are in a proportional relationship. For example, an abnormality of the track 2 or drive system 7a is generated at time _{t 1,} U-phase current _{i u-4a} may exceed the threshold _{i uX.} The same applies to the U-phase current _iu-4b of the motor 4b.

The problem here is that when an abnormality is detected by observation of the U-phase current _iu-4a , the cause can not be limited to either the orbit 2 or the drive system 7a. For this reason, the maintenance worker needs to inspect both the track 2 and the drive system 7a, which increases the working time. In order to reduce the working time, it is necessary to be able to detect an abnormality by observing the U-phase currents _iu-4a and _iu-4b , and to be able to identify the cause of the abnormality.

The contents described above are not limited to the U-phase current, and the same applies to the V-phase current and the W-phase current.

The problems with anomaly detection are as described above. Next, an operation principle (an example of an abnormality detection method) of the abnormality detection device 8 which performs the abnormality detection will be described.

FIG. 4 is a diagram showing a flowchart related to the processing performed by the abnormality detection device 8. A flow chart 8a shown in FIG. 4A is a flow chart for current observation, and a flow chart 8b shown in FIG. 4B is a flow chart for detecting an abnormality, and the processes are repeated independently of one another. However, the processing content shown in the

flowcharts

8a and 8b is an aspect of an implementation example of the abnormality detection device 8 and immediately before the trajectory abnormality / drive system abnormality determination flow of FIG. 4, that is, the threshold described later in the flow (A0) stage. If there is data on excess time and drive system position, the flow before that is optional.

As shown in the flowchart 8a, the abnormality detection device 8 observes the U-phase current (step S10). Subsequently, the abnormality detection device 8 determines whether the feature amount of the U-phase current exceeds a threshold (step S12). If the abnormality detection device 8 determines that it exceeds, it records the time (hereinafter referred to as threshold exceeded time) and the drive system number exceeding the threshold (step S14), and determines that it does not exceed. finish. The drive system number is information which can uniquely identify the drive systems 7a to 7k, and the drive system position is linked to the drive system number.

Here, the feature value refers to the maximum value of the physical quantity (for example, U-phase current), the effective value of the physical quantity, the band pass filter value of the physical quantity, the specific frequency component by Fourier analysis of the physical quantity (for example, FFT (Fast Fourier Transform etc.) These are data processing results of statistical methods for physical quantities, etc., and the accuracy of anomaly detection can be enhanced compared to the case of directly using observed values of physical quantities.

Similarly, the following observation targets may be added to improve the accuracy of the abnormality detection. Alternatively, the observation of the U-phase current may be stopped instead.
Electrical data: three-phase alternating current of motors 4a-4k, three-phase alternating voltage of motors 4a-4d, d-axis current of motors 4a-4d, q-axis current of motors 4a-4d, d-axis voltage of motors 4a-4d, Q axis voltage of motors 4a to 4d Machine data: rotational speed of drive systems 7a to 7d, torque of drive systems 7a to 7d, vibration of drive systems 7a to 7d, noise of drive systems 7a to 7d Control software variable: d axis current Command deviation, q-axis current command deviation

The d-axis current command deviation described above is, for example, one of the control software variables of the control circuit 5a2, and the d-axis current command (a command value transmitted from the upper system 20) of the control software variable and the d of the motor 4a. It is a deviation from the axial current (measured value). The same applies to the q-axis current command deviation. The control software variables indicating the deviation between the control command and the control target amount such as d-axis current command deviation and q-axis current command deviation are zero in the normal state, and increase when transitioning to the abnormal state. It is suitable as an observation target for

Further, as shown in the flowchart 8b, the abnormality detection device 8 determines whether the data of the threshold excess time and the drive system number are sufficient (whether or not there is a predetermined number) (step S20). If the abnormality detection device 8 determines that there is a predetermined number of data, the process proceeds to step S22. If it is determined that the predetermined number of data does not exist, the process ends. The predetermined number is a number necessary to determine whether or not there is a correlation between the plurality of threshold excess times and the drive system position. For example, when the vehicle speed v of the track traveling vehicle 1 is known, it can be determined based on whether the threshold overrun time and the driveline position match the vehicle speed v, so at least two points of data (threshold overtime If there are two sets of drive system positions, the correlation can be determined.

In step S22, the abnormality detection device 8 reads data of the threshold excess time and drive system number. Subsequently, the abnormality detection device 8 examines the correlation between the threshold excess time and the drive system position (step S24), and when it is determined that there is a correlation, a trajectory abnormality indicating that the trajectory 2 is abnormal (trajectory abnormality) When a signal is output (step S26) and it is determined that there is no correlation, a drive system abnormality signal indicating that there is an abnormality (drive system abnormality) in drive systems 7a to 7d is output (step S28), and the process is ended. Do.

In addition, an output may be transmitting a signal to the host system 20, may transmit a signal to another orbital traveling vehicle different from the orbital traveling vehicle 1, or an orbital traveling vehicle The determination result may be shown on a display, a warning light, etc. (not shown) provided in 1 or any other output or combination thereof.

FIG. 5 shows an example of the relationship between the threshold excess times t _a to t _k and the drive system positions y _a to y _k . FIG. 5A is a diagram showing an example of the relationship between threshold excess times t _a to t _k and drive system positions y _a to y _k in track abnormality, and FIG. 5B is a threshold on drive system abnormality. it is a diagram showing an example of the relationship between the excess time _{_t} a ~ _t _k and the drive system position _{_y} a ~ _y _k. Hereinafter, a log related to the threshold excess will be referred to as a threshold excess log as appropriate.

For example, since the track abnormal 9a wheels 3a ~ 3k shown in FIG. 6 (A) is passed by the vehicle speed v, the point shown in FIG. _{_{5 (A) (t a,}} y a) ~ (t k, y k) is , Aligned on the straight line of inclination v.

On the other hand, for example, in the case where there are drive system abnormalities 9b1 to 9b4 shown in FIG. 6B, regularity such as being aligned on the straight line of the slope v is not seen, and exceeding of the threshold occurs at random time.

That is, the difference between the case where there is the track abnormality 9a and the case where there is the drive system abnormality 9b1 to 9b4 appears as the presence or absence of the correlation between the threshold excess time and the drive system position. Therefore, in the flowchart 8b, the abnormality detection device 8 outputs a track abnormality signal when there is a correlation between the plurality of threshold excess times and the drive system position, and outputs a drive system abnormality signal when there is no correlation. Do.

Here, FIG. 5 (A) point _{_{_{(t a, y a) ~}}} (t k, y k) lining up in the gradient v straight line of only if the vehicle speed v is constant. If a change in the vehicle speed v is not negligible, the abnormality detection apparatus 8, for example, a point on the integral curve of the vehicle acceleration _{p (t a, y a)} ~ (t k, y k) outputs a track error signal when the overlap If they do not overlap, they output a drive system abnormality signal.

The difference between the track abnormality 9a and the drive system abnormalities 9b1 to 9b4 appears as the presence or absence of the correlation between the threshold crossing time and the drive system position, as shown in FIG. 6B only for some wheels (for example, the wheels 3a). The same is true when an abnormality occurs in the In addition, when the track abnormality 9a and the drive system errors 9b1 to 9b4 are occurring at the same time, the data on the track abnormality 9a is first extracted according to the correlation, and the presence or absence of the drive system errors 9b1 to 9b4 is determined from the remaining data. Is also possible.

The operation principle of the abnormality detection device 8 is as described above. According to this configuration, since the track abnormality and the drive system abnormality can be determined, the maintenance work time can be shortened. Hereinafter, means for enhancing the effectiveness of the abnormality detection device 8 will be described.

For example, in order to reduce the amount of recording data of the threshold excess time and the drive system position, the following may be performed.
(I) A data center (data server or the like) is constructed in the host system 20, and the data center aggregates record data of a plurality of track traveling vehicles. By applying data compression technology after data aggregation, for example, by finding and compressing data related to anomaly detection common to several track vehicles, it is possible to apply data compression technology for each track vehicle. The amount of data can be reduced as a whole. In the data center, in addition to the recording data, the output logs of the trajectory abnormality signal and the drive system abnormality signal may be aggregated. The data center may be built in a building or may be built on a specific track traveling vehicle.
(Ii) The abnormality detection device 8 operates at a specific time zone or place. For example, the abnormality detection device 8 may be operated only by the first power generation vehicle or the last train, or the abnormality detection device 8 may be operated only at a place where the wear of the track 2 such as climbing or curve tends to progress.
(Iii) The abnormality detection device 8 may be mounted only on a specific track traveling vehicle.
(Iv) The abnormality detection device 8 may change the operation cycle of the flowchart 8a, and may shorten the operation cycle only in a predetermined period after the feature amount exceeds the threshold.

Also, for example, in order to enhance the accuracy of abnormality detection, after the data collection in (i) above, the host system 20 may output a track abnormality signal using recording data of a plurality of track traveling vehicles. For example, the host system 20 can estimate (specify) the occurrence point (abnormal point) of the track abnormality with high accuracy by collating the position of the track abnormality obtained from the recorded data of each track traveling vehicle with each other. (An example of a specific part).

Further, for example, in order to prevent abnormal erroneous detection, the abnormality detection device 8 may measure environmental data regarding environmental conditions such as air temperature and humidity, and adjust the threshold based on the measurement result (an example of the adjustment unit) . For example, at low temperatures, the track 2 shrinks and gaps such as joints of the track 2 and pointers increase, so when the track traveling vehicle 1 passes them, there is a possibility that the threshold will be exceeded. In that case, the abnormality detection device 8 erroneously detects the seam or the pointer that should be normal as the trajectory abnormality 9a. Therefore, false detection can be prevented by adjusting the threshold according to the temperature. When the motors 4a to 4k are magnet motors, the torque constant changes with temperature, and the current value also changes during normal operation with the same torque. Therefore, also in this case, it is desirable that the abnormality detection device 8 adjust the threshold with respect to the temperature.

Further, for example, in order to realize safer vehicle operation, when the abnormality detection device 8 detects the track abnormality 9a, a track traveling vehicle in the vicinity (for example, the rear), the upper system 20 (for example, a railway operation management system And the like) may transmit an abnormality detection signal. The railway operation management system may or may not be included in the upper system 20. Further, it is desirable that the host system 20 stop or degenerate the corresponding drive system when the drive system abnormality 9b1 to 9b4 is detected. Even when the drive system is stopped, if a normal drive system remains in the track traveling vehicle, the host system 20 travels the track traveling command to move to a nearby station or maintenance site by the normal drive system. It may be transmitted to the vehicle.

As described above, according to the present embodiment, it is possible to reduce the amount of recording data, improve the accuracy of abnormality detection, prevent abnormal error detection, and perform safer vehicle operation.

(2) Second Embodiment FIG. 7 is a diagram showing a flowchart according to processing performed by the abnormality detection device 8 in the second embodiment. However, illustration and explanation of points equivalent to the first embodiment will be omitted as appropriate. In the present embodiment, the abnormality detection device 8 can distinguish between a track abnormality and a joint by replacing the processing after (A1) and (A2) shown in FIG. 4 with the processing of the flowchart shown in FIG. Become. The operation principle is described below.

FIG. 8 (A) is a schematic view showing the seam 10, and FIG. 8 (B) is a schematic view showing the orbit abnormality 9a. Although the seam 10 is not an abnormality of the trajectory 2, it is preferable to adopt a configuration for discriminating between the seam 10 and the trajectory abnormality 9 a because the threshold 10 may be generated even by the seam 10.

The difference between the seam 10 and the orbit anomaly 9a is the position interval between them. The position interval of the seam 10 is constant, but the position interval of the orbit anomaly 9a is random. Therefore, as shown in FIG. 9 (A), in the case where there is a seam 10, after the correlation alpha ₁ over-threshold time _t a1 _{~ t k1} and the drive system position _{_y} a ~ _y _k was observed, correlation α ₂ to α ₄ are observed at a constant threshold excess period ΔT. On the other hand, when there is the orbit abnormality 9a, as shown in FIG. 9 (B), after the correlation β ₁ is observed, the correlation β ₂ and β ₃ are random threshold excess periods ΔT ₁ and ΔT ₂ . It is observed.

Therefore, as shown in the flowchart of FIG. 7 (orbit abnormality / seam determination flow), the abnormality detection device 8 determines the presence or absence of the periodicity of the correlation between the threshold excess time and the drive system position (step S30). For example, when the interval between the seams 10 is known, the abnormality detection device 8 determines the presence or absence of periodicity based on at least two or more correlations, and when the interval between the seams 10 is unknown, at least three or more. The presence or absence of periodicity is determined based on the correlation of If the abnormality detection device 8 determines that there is periodicity, it outputs a seam detection signal indicating the seam 10 of the trajectory 2 (step S32), and if it determines that there is no periodicity, it outputs a trajectory abnormality signal (step S32) S34), the process ends. In step S28, the abnormality detection device 8 outputs a drive system abnormality signal as in the first embodiment.

The operation principle of the abnormality detection device 8 in the present embodiment is as described above. According to this configuration, in addition to the effects of the first embodiment, it is possible to prevent erroneous detection of the track abnormality due to the seam and reduce the maintenance cost.

(3) Third Embodiment FIG. 10 is a diagram showing a flowchart according to processing performed by the abnormality detection device 8 in the third embodiment. However, illustration and explanation of points equivalent to the first embodiment will be omitted as appropriate. In the present embodiment, the abnormality detection device 8 identifies an abnormal part in the drive systems 7a to 7d by replacing the processing after (A1) and (A2) shown in FIG. 4 with the processing of the flowchart shown in FIG. become able to. The operation principle is described below.

Here, the abnormalities of the drive systems 7a to 7k are classified into the abnormalities of the wheels 3a to 3k, the gears 6a to 6k, and the motors 4a to 4k. However, there may be cases where multiple abnormalities occur simultaneously. In the following, a case where a wheel abnormality 9b1 (the same meaning as the same symbol in FIG. 6) occurs in the drive system 7a, a gear abnormality 9c occurs in the drive system 7b, and a motor abnormality 9d occurs in the drive system 7d is taken as an example. Explain. 11 (A) shows a wheel abnormality 9b1, FIG. 11 (B) shows a gear abnormality 9c, and FIG. 11 (C) shows a motor abnormality 9d. The gear abnormality 9c 'on the wheel side can be considered as the gear abnormality in FIG. 11B, but the result when this occurs is the same as the wheel abnormality 9b1 in FIG. 11A, so the description will be omitted. .

FIG. 12 is a diagram showing a threshold excess log related to the wheel abnormality 9b1, the gear abnormality 9c, and the motor abnormality 9d. If the vehicle speed v is constant, the influence of the cause of the abnormality has on the motor 4a ~ 4d become periodically, the threshold in the period T _{1 ~} T ₃ different for each abnormal part (the abnormal cause) as shown in FIG. 12 Excess is observed.

The threshold excess periods T ₁ to T ₃ are derived as follows.

(Threshold excess period T ₁ )
Threshold exceeded period T ₁ shown in FIG. 12, since equal to the rotation period of the wheel 3a, the wheel radius is r, is expressed as follows.
T ₁ = 2πr / v (Equation 1)

(Threshold excess period T ₂ )
Threshold exceeded period T ₂ shown in FIG. 12, since equal to the rotation period of the motor side of the gear 6b, the gear ratio is eta, is expressed as follows.
T ₂ = 2πr / ηv (Equation 2)

(Threshold excess period T ₃ )
Threshold exceeded period T ₃ shown in FIG. 12, since equal electrical rotation period of the motor 4d, when the number of pole pairs of the motor 4d and P _m, is expressed as follows.
T ₃ = 2πr / ηP _m v (Equation 3)

As shown in (Equation 1) to (Equation 3), the threshold excess periods T ₁ to T ₃ differ depending on the cause of abnormality. Therefore, as shown in the flowchart of FIG. 10 (drive system abnormality determination flow), a wheel abnormality signal indicating that the abnormality is identified according to the threshold excess period T ₁ to T ₃ and indicating that the wheels 3 a to 3 d are abnormal; A gear abnormality signal indicating that there is an abnormality in the gears 6a to 6d and a motor abnormality signal indicating that there is an abnormality in the motors 4a to 4d are output.

More specifically, when the abnormality detection device 8 outputs a drive system abnormality signal (step S28), the abnormality detection device 8 determines whether the threshold excess period becomes the wheel circumference / vehicle speed (step S40). In the case where it is determined that the process is not performed at step S42, the process proceeds to step S44. In step S42, the abnormality detection device 8 outputs a wheel / axle side gear abnormality signal (wheel abnormality signal), and the process proceeds to step S44.

In step S44, the abnormality detection device 8 determines whether or not the threshold excess period is equal to the wheel circumference / vehicle speed / gear ratio. If it is determined that it is, the process proceeds to step S46. The process moves to step S48. In step S46, the abnormality detection device 8 outputs a motor gear abnormality signal (gear abnormality signal), and the process proceeds to step S48.

In step S48, the abnormality detection device 8 determines whether the threshold excess period is equal to wheel circumference / vehicle speed / gear ratio / pole logarithm. If it is determined that it is, it is determined that the process is not transferred to step S50. If it does, the process ends. In step S50, the abnormality detection device 8 outputs a motor abnormality signal, and the process ends.

In step S26, the abnormality detection device 8 outputs a track abnormality signal as in the first embodiment.

In the flowchart shown in FIG. 10, since the presence or absence of each abnormality is all determined in order, the present invention is also applicable to the case where there is a plurality of abnormalities in a certain drive system. In addition, when there is a plurality of one type of abnormality, for example, when there is a threshold excess log with a sufficient length even when the wheel 3a is deformed in two or more places, the number of deformed portions is specified by data processing technology such as machine learning. It is also possible.

The operation principle of the abnormality detection device 8 in the present embodiment is as described above. According to this configuration, in addition to the effects of the first embodiment, since the abnormal part of the drive system can be identified, it is possible to reduce the stock of the maintenance parts by arranging only the necessary maintenance parts.

(4) Fourth Embodiment FIG. 13 is a diagram showing a flowchart according to processing performed by the abnormality detection device 8 in the fourth embodiment. A flow chart 8c shown in FIG. 13A is a flow chart for current observation, and a flow chart 8d shown in FIG. 13B is a flow chart for detecting an abnormality, and the process is repeated independently of each other. In the present embodiment, the abnormality detection device 8 determines each of the trajectory abnormality, the drive system abnormality, the seam, and the pointer by executing the processes shown in the

flowcharts

8c and 8d. The operation principle is described below.

In step S60, the abnormality detection device 8 observes the current as in the first embodiment. Subsequently, the abnormality detection device 8 records the feature amount of the current and the track position (step S62), and ends the process. The feature of the present embodiment is to record the feature amount and the orbit position of the current, which is hereinafter referred to as a feature amount log. The orbital position represents the position on the trajectory 2 (absolute position). The orbital position can be measured, for example, by GPS (Global Positioning System). The track position can also be estimated, for example, from the integral value of the vehicle speed v. Moreover, it is also possible for the abnormality detection apparatus 8 to acquire a track position by another method. Although the origin of the track position is arbitrary, for example, the stop position target of the first train station can be set as the origin.

In step S70, the abnormality detection device 8 determines whether the number of data of the feature amount and the track position is sufficient for the determination of the track abnormality, the drive system abnormality, the seam, and the pointer. If the abnormality detection device 8 determines that the process is sufficient, the process proceeds to step S72, and if it is determined that the process is not sufficient, the process ends.

In step S72, the abnormality detection device 8 reads data of the feature amount and the trajectory position. Subsequently, the abnormality detection device 8 determines whether the feature amounts of all the read data are in the vicinity of "0" (step S74), and it is determined that the feature amounts of all the data are in the vicinity of "0" If YES in step S76, the processing ends, and if it is determined that any feature amount of all the data is not near “0”, the processing is shifted to step S76.

In step S76, the abnormality detection device 8 determines the dependence of the feature amount on the track position, and if it is determined that there is a dependence, the process proceeds to step S78. If it is determined that there is no dependence, the drive system abnormality A signal is output (step S88), and the process ends. As shown in FIG. 14A, when there is an abnormality in the drive systems 7a to 7k, the normalized feature amount s exceeds the threshold value “1” regardless of the trajectory position x. On the other hand, if there is an orbit abnormality, a seam, or a pointer, the feature quantity s is a phenomenon dependent on the orbit position x, and the feature value s is limited to the threshold value “1” only for specific orbit positions x _j and x _k. Over.

In the processing of step S78 to step S86, the abnormality detection device 8 determines the trajectory abnormality 9a shown in FIG. 15 (A), the seam 10 shown in FIG. 15 (B), and the pointer 11 shown in FIG. 15 (C). The trajectory abnormality 9a shown in FIG. 15A and the seam 10 shown in FIG. 15B are the same as those shown in FIGS. 8A and 8B, and the positional distance between the seams 10 is constant. Because of this, it can be determined by the processing of the flowchart shown in FIG. 7 (see the second embodiment). That is, also in step S78, the abnormality detection device 8 similarly determines whether the interval between the track positions at which the feature amount exceeds the threshold (hereinafter, the threshold excess position) is constant, and determines that it is constant. In the case, the seam detection signal is output (step S80), and the process ends. On the other hand, if it is determined that the pointer 11 shown in FIG. 15 (C) is not constant, the position interval is not constant as in the case of the trajectory abnormality 9a. 11 and the orbit abnormality 9a can not be distinguished.

Therefore, as shown in FIG. 16, based on the temporal change of the feature amount s of the pointer 11 and the trajectory abnormality 9a, they are determined. As shown in FIG. 16 (A), if the trajectory abnormality 9a proceeds in orbital position _{x j,} the feature value s in the orbital position _{x j,} increases with the lapse of time t (t0 → t1 → t2 → t3) . On the other hand, as shown in FIG. 16B, when the pointer 11 is at the trajectory position x _k , the pointer 11 is present from the time of installation of the trajectory 2, so the feature amount s at the trajectory position x _k is , Does not depend on time t.

Therefore, in step S82, the abnormality detection device 8 determines whether the feature amount increases with the passage of time, and when it is determined that the feature amount increases, outputs the track abnormality signal (step S84). If it is determined that the number does not increase, a pointer detection signal indicating the pointer 11 of the trajectory 2 is output (step S86), and the process is ended. By this processing, the abnormality detection device 8 determines the pointer 11 and the trajectory abnormality 9a. Note that the abnormality detection device 8 may read data recorded in the past in order to see the elapsed time, or may acquire past data from the host system 20.

Further, FIG. 17 shows a threshold value excess log in the case where the trajectory abnormality 9a, the seam 10 and the pointer 11 shown in FIG. 15 (D) are present. The operation of the abnormality detection device 8 at this time is as follows.

(Seam determination)
Since there are seams 10 at the track positions x ₁ , x ₂ , x ₃ , and x ₄ shown in FIG. 17, since the interval Δx of the over-threshold position is constant, the seam detection signal is output.

(Orbit error judgment)
The x _j shown in FIG. 17, there are track abnormal 9a, the spacing of the over-threshold position is not constant, and since the feature value is increasing with time, the track error signal is output.

(Pointer judgment)
A pointer detection signal is output because there is a pointer 11 at x _k shown in FIG. 17 and the interval of the position exceeding the threshold is not constant and the feature amount does not increase with time.

By sequentially performing the above-described seam determination, trajectory abnormality determination, and pointer determination, the abnormality detection device 8 detects an abnormality signal or detection signal that matches the trajectory abnormality 9a, the seam 10, and the pointer 11, even when they are mixed. Can be output.

Further, the abnormality detection device 8 can also specify the occurrence position of the track abnormality 9a by comparing the track position with the recording (refer to the track position).

Also, it is conceivable that the seam 10 and the pointer 11 also wear out due to the change with time and become an abnormal state. In this case, in FIG. 17, the abnormality of the seam 10 and the pointer 11 can also be detected by means of changing the threshold for each abnormal state, changing the definition of the observation amount and the feature amount for each abnormal state, or the like.

The operation principle of the abnormality detection device 8 in the present embodiment is as described above. According to such a configuration, since each of the track abnormality, the drive system abnormality, the seam and the pointer can be determined, the maintenance work time can be shortened. Moreover, according to such a configuration, it is possible to reduce the stock of maintenance parts as in the third embodiment.

(5) Other Embodiments Although the above embodiment has described the case where the present invention is applied to the abnormality detection system 100, the present invention is not limited to this and other various abnormality detections. It can be widely applied to devices, abnormality detection systems, and the like.

In the above-mentioned embodiment, although the case where abnormality detection device 8 detects abnormality was described, the present invention is not limited to this, and other devices may detect abnormality. For example, the host system 20 may execute the process shown in the flowchart 8b of FIG. 4, the process shown in the flowchart of FIG. 7, the process shown in the flowchart of FIG. 10, and the process shown in the flowchart 8d of FIG.

The configurations shown in the above-described embodiments can be combined or changed as appropriate without departing from the scope of the present invention.

DESCRIPTION OF SYMBOLS 1 ... Trajectory vehicle 1a-1n ...... Vehicle 2 ... Trajectory 3a-3k ...... Wheel 4a-4k ...... Motor 5a-5k ...... inverter 5a1 ...... Main circuit 5a2 ...... Control Circuits 6a to 6k: gear 7a to 7k: drive system 8: abnormality detection device 9a to 9k: wheel abnormality 10: seam 11, 11: pointer 20: upper system 100: 100 ... Anomaly detection system

Claims

An abnormality detection device for detecting an abnormality related to a track traveling vehicle traveling on a track,
Obtain a drive system position indicating the position of the drive system with respect to the track traveling vehicle at a threshold over time when the feature amount of the drive system physical quantity provided in the track traveling vehicle exceeds a threshold and the threshold over time. Acquisition department,
A determination unit that determines whether or not there is a correlation between the plurality of threshold excess times acquired by the acquisition unit and the drive location at the threshold excess time with respect to the plurality of drive trains provided in the track traveling vehicle;
An output unit that outputs based on the determination result by the determination unit;
Equipped with
The said output part outputs the track | orbit abnormality signal which shows that the said track | orbit has abnormality, when it determines with there being correlation by the said determination part, The abnormality detection apparatus characterized by the above-mentioned.
In the abnormality detection device according to claim 1,
The abnormality detection device, wherein the output unit outputs a drive system abnormality signal indicating that there is an abnormality in the plurality of drive systems when the determination unit determines that there is no correlation.
In the abnormality detection device according to claim 2,
The output unit includes a physical quantity of a drive system provided in the track traveling vehicle, a drive system position at a threshold excess time acquired by the acquisition unit and a threshold excess time, a track abnormality signal output from the output unit, An abnormality detection apparatus, which transmits at least one of drive system abnormality signals output from an output unit to a data center.
In the abnormality detection device according to claim 1,
The characteristic quantities of the physical quantity of the drive system provided in the track traveling vehicle are the maximum value of the physical quantity, the effective value of the physical quantity, the band pass filter value of the physical quantity, the specific frequency component by Fourier analysis of the physical quantity, and the physical quantity An abnormality detection apparatus characterized by being any one of data processing results by the statistical method of
In the abnormality detection device according to claim 1,
The physical quantity of the drive system provided in the track traveling vehicle is
Three-phase AC current of the motor which is a drive source of the drive system, three-phase AC voltage of the motor, d-axis current of the motor, q-axis current of the motor, d-axis voltage of the motor, q-axis voltage of the motor ,
Rotational speed of the drive system, torque of the drive system, vibration of the drive system, noise of the drive system,
An abnormality detection apparatus characterized by being any one of control software variables of an inverter connected to the motor.
In the abnormality detection device according to claim 1,
The abnormality detection device further comprising: an adjustment unit configured to adjust the threshold based on environmental data on an environmental condition of a drive system provided in the track vehicle.
In the abnormality detection device according to claim 1,
The abnormality detection device, wherein the output unit transmits the track abnormality signal to another track traveling vehicle or a railway operation management system.
In the abnormality detection device according to claim 1,
The determination unit determines the presence or absence of the periodicity of the correlation,
The output unit outputs a seam detection signal indicating a seam of the trajectory when the determination unit determines that the correlation periodicity is present, and the determination unit determines that the correlation periodicity is not present. And an abnormality detection device for outputting the trajectory abnormality signal.
In the abnormality detection device according to claim 2,
The determination unit determines whether or not there is an abnormality in a wheel included in a drive system provided in the track traveling vehicle, or an abnormality in a gear included in the drive system based on a cycle that exceeds the threshold. Determine whether the motor included in the drive system is abnormal or not
When the determination unit determines that the wheel is abnormal, the output unit outputs a wheel abnormality signal indicating that the wheel has an abnormality, and the determination unit determines that the gear is abnormal. In this case, a gear abnormality signal indicating that there is an abnormality in the gear is output, and a motor abnormality signal indicating that the motor has an abnormality is output when the determination unit determines that the motor has an abnormality. An abnormality detection device characterized by
In the abnormality detection device according to claim 9,
The determination unit determines whether an abnormality of the wheel on the basis of the period T 1 of the said period and the following (Equation 1), based on the period T 2 of the said period and the following (Equation 2) wherein it is determined whether the abnormality of the gear, the period and the following (equation 3) abnormality detection apparatus characterized by determining whether an abnormality of the motor based on the cycle T 3 of.
T 1 = 2πr / v (Equation 1)
T 2 = 2πr / ηv (Equation 2)
T 3 = 2πr / ηP m v (Equation 3)
An abnormality detection system comprising the abnormality detection device according to claim 3 corresponding to each of a plurality of track traveling vehicles,
An abnormality detection system comprising: a specification unit that specifies an abnormality part of the track based on the track abnormality signal transmitted from each of the abnormality detection devices.
An abnormality detection system comprising the abnormality detection device according to claim 3, wherein
The vehicle control system further includes a command unit that instructs the track traveling vehicle based on the information transmitted from the abnormality detection device.
The command unit instructs the track vehicle to stop or degenerate the drive system related to the drive system abnormality signal based on the drive system abnormality signal transmitted from the abnormality detection device. An anomaly detection system characterized by
An orbiting vehicle traveling on an orbit,
Obtain a drive system position indicating the position of the drive system with respect to the track traveling vehicle at a threshold over time when the feature amount of the drive system physical quantity provided in the track traveling vehicle exceeds a threshold and the threshold over time. Acquisition department,
A determination unit that determines whether or not there is a correlation between the plurality of threshold excess times acquired by the acquisition unit and the drive location at the threshold excess time with respect to the plurality of drive trains provided in the track traveling vehicle;
An output unit that outputs based on the determination result by the determination unit;
Equipped with
The track traveling vehicle, wherein the output unit outputs a track abnormality signal indicating that the track has an abnormality when it is determined by the determination unit that there is a correlation.
An anomaly detection method executed by an anomaly detection apparatus for detecting an anomaly related to a track traveling vehicle traveling on a track,
Obtain a drive system position indicating the position of the drive system with respect to the track traveling vehicle at a threshold over time when the feature amount of the drive system physical quantity provided in the track traveling vehicle exceeds a threshold and the threshold over time. The first step to
A second determination is made as to whether or not there is a correlation between the plurality of threshold excess times obtained in the first step with respect to the plurality of drive lines provided in the track vehicle and the drive position at the threshold excess time. Step and
A third step of outputting a signal based on the determination result in the second step;
Equipped with
In the third step, when it is determined that there is a correlation in the second step, a trajectory abnormal signal indicating that the trajectory is abnormal is outputted.
An abnormality detection device for detecting an abnormality related to a track traveling vehicle traveling on a track,
An acquisition unit for acquiring a feature amount of a physical quantity of a drive system provided on the track traveling vehicle and a track position indicating a position on the track where the feature amount is measured;
It is determined whether or not the plurality of physical quantities acquired by the acquisition unit and the track position at which the physical quantity is acquired is dependent on the plurality of drive systems provided in the track traveling vehicle, and the plurality of track positions And a determination unit that determines whether or not the distance between track positions at which the physical amount exceeds the threshold is constant, and whether the physical amount at the track position above the threshold increases with time.
An output unit that outputs based on the determination result by the determination unit;
Equipped with
The output unit may output a trajectory abnormality signal indicating that the trajectory has an abnormality, when it is determined by the determination unit that there is dependency, is determined not to be constant, and is determined to be increasing. An abnormality detection device characterized by
In the abnormality detection device according to claim 15,
The abnormality detection device, wherein the output unit outputs a drive system abnormality signal indicating that there is an abnormality in the plurality of drive systems when it is determined by the determination unit that there is no dependency.
In the abnormality detection device according to claim 15,
The abnormality detection device, wherein the output unit is configured to output a seam detection signal indicating a seam of the trajectory when it is determined by the determination unit that there is dependency and that the output unit is determined to be constant.
In the abnormality detection device according to claim 15,
The output unit is configured to output a pointer detection signal indicating a pointer provided on the track when it is determined by the determination unit that there is dependency, is determined not to be constant, and is determined not to increase. An abnormality detection device characterized by