JP7103141B2 - Anomaly detection system and anomaly detection method for railcar bogies - Google Patents

Description

The present invention relates to an abnormality detection system and an abnormality detection method for a bogie for a railway vehicle.

A railroad vehicle bogie abnormality detection system that detects an abnormality in a railroad vehicle bogie by frequency-analyzing the sound measured by a microphone is disclosed. For example, in Patent Document 1, a clustering process is performed in which data decomposed into time-series frequency components are classified and categorized, and normal data and abnormal data are classified into different categories. It is described that the normality and abnormality of the data are judged, and in the case of an abnormality, what kind of abnormality has occurred is judged.

JP-A-2007-256153

However, in the above-mentioned conventional technique, the load of abnormality determination processing is large due to frequency analysis and clustering processing, and an expensive arithmetic processor is required. In addition, since a microphone is used, the abnormality detection range is narrow, and there is a possibility that the abnormality to be detected cannot be detected.

The present invention has been made in view of the above problems, and provides an abnormality detection system for a railroad vehicle bogie and an abnormality detection method capable of detecting an abnormality in a railroad car bogie with an inexpensive configuration. It is an object.

In order to achieve the above object, the abnormality detection system for a railroad vehicle trolley according to one aspect of the present invention is provided on the railroad vehicle by means of a detection device for detecting vibration generated from the railroad vehicle trolley and the detection device. A diagnostic device for detecting an abnormality of the railroad vehicle carriage based on the frequency with which the absolute value or the square value of the electric signal indicating the detected detected value becomes equal to or higher than the threshold value is provided.

As a result, it is possible to detect an abnormality in a railroad bogie with an inexpensive configuration.

As a desirable embodiment of the abnormality detection system for a railroad vehicle, the diagnostic device samples the detected value, and the absolute value or the square value of the sampled data becomes a predetermined value or more in a predetermined data aggregation period. It is preferable to determine an abnormality when the number exceeds a predetermined number.

As a result, it is possible to reduce the abnormality detection processing of the bogie for railway vehicles. In addition, it is possible to detect the vibration caused by the continuous abnormality of the railroad car bogie, and the vibration caused by the temporary impact applied to the railroad car bogie is erroneously detected as the abnormality of the railroad car bogie. Can be suppressed.

Further, as a desirable embodiment of the abnormality detection system for the bogie for a railroad vehicle, the diagnostic device may be provided on the railroad vehicle.

Further, as a desirable embodiment of the abnormality detection system for the bogie for railway vehicles, the diagnostic device may be provided on the ground equipment.

The method for detecting an abnormality in a railroad vehicle trolley according to one aspect of the present invention is based on the frequency with which the absolute value or the square value of an electric signal indicating the detection value of vibration generated from the railroad vehicle trolley becomes equal to or higher than a threshold value. Detects abnormalities in the trolley.

As a result, it is possible to detect an abnormality in a railroad bogie with an inexpensive configuration.

Further, as a desirable embodiment of the abnormality detection method for a railroad vehicle trolley, the sampling is performed in a step of sampling the detected value, a step of calculating the absolute value or the square value of the sampled data, and a predetermined data aggregation period. It is preferable to have a step of counting the number of samples whose absolute value or square value of the data is equal to or more than a predetermined value, and a step of determining an abnormality when the number of samples is equal to or greater than a predetermined number.

As a result, it is possible to reduce the abnormality detection processing of the bogie for railway vehicles. In addition, it is possible to detect the vibration caused by the continuous abnormality of the railroad car bogie, and the vibration caused by the temporary impact applied to the railroad car bogie is erroneously detected as the abnormality of the railroad car bogie. Can be suppressed.

FIG. 1 is a schematic view showing a configuration example of an abnormality detection system for a railroad bogie according to the first embodiment. FIG. 2 is a block diagram showing a configuration example of the diagnostic device of the first embodiment. FIG. 3 is a diagram for explaining the threshold value determination in the abnormality detection process according to the first embodiment. FIG. 4 is an enlarged view within the broken line shown in FIG. FIG. 5 is a flowchart showing an example of an abnormality detection process of a railroad car bogie according to the first embodiment. FIG. 6 is a schematic view showing a configuration example of an abnormality detection system for a railroad bogie according to the second embodiment. FIG. 7 is a block diagram showing a configuration example of the diagnostic device of the second embodiment.

Hereinafter, embodiments for carrying out the invention (hereinafter referred to as embodiments) will be described in detail with reference to the drawings. The present invention is not limited to the following embodiments. In addition, the components in the following embodiments include those that can be easily assumed by those skilled in the art, those that are substantially the same, that is, those in a so-called equal range. Further, the components disclosed in the following embodiments can be appropriately combined.

(Embodiment 1)
FIG. 1 is a schematic view showing a configuration example of an abnormality detection system for a railroad bogie according to the first embodiment. FIG. 2 is a block diagram showing a configuration example of the diagnostic device of the first embodiment. As shown in FIG. 1, the abnormality detection system (hereinafter, also simply referred to as “abnormality detection system”) 10 for a railroad vehicle bogie according to the first embodiment includes a diagnostic device 1 and a vibration sensor 2.

The vibration sensor (detection device) 2 is provided in a railroad vehicle (hereinafter, also simply referred to as “vehicle”) 100. The vibration sensor 2 is, for example, an acceleration sensor, a speed sensor, a displacement sensor, or the like, and detects vibration generated from a railroad vehicle trolley (hereinafter, also simply referred to as “trolley”) 3 provided in the vehicle 100. The bogie 3 is provided with wheels 4 via bearings and axles (not shown).

The vibration sensor 2 is preferably provided near the axle of the carriage 3, but is not limited to this. Further, FIG. 1 shows an example in which two trolleys 3 are provided on the vehicle 100 and two vibration sensors 2 are provided corresponding to these two trolleys 3, but the number of vibration sensors 2 is based on this. Not limited to this, for example, four vibration sensors 2 may be provided corresponding to the four wheels 4, or one vibration sensor 2 may be provided in the vehicle 100. The present disclosure is not limited by the arrangement or number of vibration sensors 2.

As shown in FIG. 1, in the abnormality detection system 10 for a railroad vehicle bogie according to the present embodiment, the diagnostic device 1 is provided in the vehicle 100, and the detection value of the vibration sensor 2 is input. The diagnostic device 1 detects an abnormality in the carriage 3 based on the detection value detected by the vibration sensor 2. FIG. 1 shows an example in which one diagnostic device 1 is provided for the vehicle 100. However, in a configuration in which a plurality of vehicles 100 are connected, the diagnostic device 1 is provided for one vehicle 100 and is provided for the plurality of vehicles 100. The mode may be such that the detected value of the vibration sensor 2 is input.

As shown in FIG. 2, the diagnostic apparatus 1 includes an AD conversion unit 11, a data conversion unit 12, an abnormality determination unit 13, and a storage unit 14. FIG. 2 shows a configuration corresponding to one vibration sensor 2.

The AD conversion unit 11 samples the detected value detected by the vibration sensor 2 at a predetermined sampling cycle, and outputs the sampled data to the data conversion unit 12.

The data conversion unit 12 calculates the absolute value of the sampling data output from the AD conversion unit 11. Alternatively, the data conversion unit 12 calculates the squared value of the sampling data output from the AD conversion unit 11. As a result, the output value of the data conversion unit 12 becomes a positive value.

The abnormality determination unit 13 detects an abnormality in the carriage 3 based on the frequency with which the absolute value or the square value of the sampling data output from the data conversion unit 12 becomes equal to or higher than a predetermined threshold value, and is the result of the abnormality determination process described later. Output the abnormality judgment result.

FIG. 3 is a diagram for explaining the threshold value determination in the abnormality detection process according to the first embodiment. FIG. 4 is an enlarged view within the broken line shown in FIG. In FIGS. 3 and 4, the vibration sensor 2 is an acceleration sensor, and an example in which acceleration is input as a detection value of the vibration sensor 2 is shown. In FIGS. 3 and 4, the horizontal axis indicates time and the vertical axis represents time. The axis shows the acceleration. Further, in FIGS. 3 and 4, the solid line indicates the acceleration output from the vibration sensor 2, and the number of points is sampled by the AD conversion unit 11 every sampling period t (for example, 1 [ms]), and the data is obtained. Among the acceleration data values G converted to positive values by the conversion unit 12, the number of samples C of the acceleration data values that are equal to or higher than the acceleration data threshold Gth is shown.

In the present embodiment, the storage unit 14 has a predetermined acceleration data threshold Gth and a predetermined data aggregation period T (for example, 1 [s]) shown in FIG. 3, which is longer than the sampling cycle t shown in FIG. Of the acceleration data values G (here, for example, 1000 points) converted to positive values by the data conversion unit 12, the sample number threshold Cth, which is the reference value of the sample number C of the acceleration data values that are equal to or greater than the acceleration data threshold Gth. Is remembered. The abnormality determination unit 13 determines that an abnormality has occurred in the trolley 3 when the number of samples of the acceleration data value that is equal to or greater than the acceleration data threshold Gth becomes equal to or greater than the sample number threshold Cth in the data aggregation period T.

As a result, it is possible to reduce the abnormality detection processing of the trolley 3, specifically, the absolute value calculation processing or the square value calculation processing in the data conversion unit 12, and the comparison calculation processing in the abnormality determination unit 13, which is an inexpensive configuration. The abnormality of the trolley 3 can be detected with. Further, in the data aggregation period T, since the sample number threshold Cth is provided for the sample number C of the acceleration data value that is equal to or greater than the acceleration data threshold Gth, vibration caused by a continuous abnormality of the trolley 3 is detected. This makes it possible to suppress erroneous detection of vibration caused by a temporary impact applied to the trolley 3 as an abnormality of the trolley 3.

Hereinafter, a specific example of the abnormality detection process of the railroad vehicle bogie according to the first embodiment will be described with reference to FIG. FIG. 5 is a flowchart showing an example of an abnormality detection process of a railroad car bogie according to the first embodiment.

First, the abnormality determination unit 13 sets a timer for the data aggregation period T (step S101), and resets (C = 0) the number of samples C of the acceleration data values that are equal to or greater than the acceleration data threshold Gth (step S102).

Subsequently, the abnormality determination unit 13 determines whether or not the acceleration data value G is equal to or greater than the acceleration data threshold Gth (G ≧ Gth) (step S103), and if the acceleration data value G is equal to or greater than the acceleration data threshold Gth. (Step S103; Yes), the number of samples C of the acceleration data value that is equal to or greater than the acceleration data threshold Gth is incremented (C = C + 1) (step S104). If the acceleration data value G is less than the acceleration data threshold Gth (G <Gth), the process of step S103 is repeated.

Subsequently, the abnormality determination unit 13 determines whether or not the data aggregation period T has elapsed (step S105), and if the data aggregation period T has not elapsed (step S105; No), steps S103 to S105. Repeat the process.

If the data aggregation period T has elapsed (step S105; Yes), the abnormality determination unit 13 determines that the number of samples C of the acceleration data value that is equal to or greater than the acceleration data threshold Gth is equal to or greater than the sample number threshold Cth (C ≧ Cth). If it is determined whether or not there is (step S106) and the number of samples C of the acceleration data value that is equal to or greater than the acceleration data threshold Gth is less than the sample number threshold Cth (C <Cth) (step S106; No), step S101. The process of step S106 is repeated.

If the number of samples C of the acceleration data value that is equal to or greater than the acceleration data threshold value Gth is equal to or greater than the sample number threshold value Cth (step S106; Yes), the abnormality determination unit 13 determines that the carriage 3 has an abnormality (step S106; Yes). Step S107), the abnormality determination result is output (step S108), and the process returns to step S101.

By repeatedly performing the above abnormality determination process, it is possible to detect the vibration caused by the continuous abnormality of the carriage 3.

As described above, the abnormality detection system 10 for the railroad vehicle trolley according to the first embodiment is provided in the railroad vehicle (vehicle 100) and detects the vibration generated from the railroad vehicle trolley (car 3). Abnormality detection of a railroad vehicle trolley (trolley 3) is performed based on the frequency with which the absolute value or the square value of the electric signal indicating the detected value detected by the vibration sensor 2) and the detection device (vibration sensor 2) becomes equal to or higher than the threshold value. A diagnostic device 1 for performing is provided.

As a result, it is possible to detect an abnormality in the bogie for railway vehicles (bogie 3) with an inexpensive configuration.

Further, in the above configuration, the diagnostic device 1 samples the detection value (acceleration) detected by the vibration sensor detection device (vibration sensor 2), and in a predetermined data aggregation period T, the absolute value or the square value of the sampled data. When the number of samples C in which (acceleration data value G) is equal to or greater than a predetermined value (acceleration data threshold Gth) becomes equal to or greater than a predetermined number (sample number threshold Cth), an abnormality is determined.

As a result, it is possible to reduce the abnormality detection processing of the bogie for railroad vehicles (bogie 3). Further, in the data aggregation period T, the sample number threshold Cth is provided for the sample number C of the acceleration data value that is equal to or greater than the acceleration data threshold Gth. It is possible to detect the vibration caused by it, and suppress the false detection of the vibration caused by the temporary impact applied to the railroad vehicle bogie (trolley 3) as an abnormality of the railroad vehicle bogie (trolley 3). Can be done.

Further, the method for detecting an abnormality of a railroad car bogie according to the first embodiment is based on the frequency at which the absolute value or the square value of the electric signal indicating the detected value of the vibration generated from the railroad car bogie (carriage 3) becomes equal to or higher than the threshold value. , Detects abnormalities in railroad car bogies (bogie 3).

Specifically, a step of sampling a detected value (acceleration) of vibration generated from a railroad vehicle trolley (trolley 3), a step of calculating an absolute value or a square value (acceleration data value G) of the sampled data, and a step of calculating the squared value (acceleration data value G). In the predetermined data aggregation period T, the step of counting the number of samples C in which the absolute value or the square value (acceleration data value G) of the sampled data is equal to or greater than the predetermined value (acceleration data threshold Gth) and the number of samples C are predetermined. It has a step of determining an abnormality when the number (sample number threshold Cth) or more is reached.

As a result, it is possible to reduce the abnormality detection processing of the bogie for railroad vehicles (bogie 3), and it is possible to detect the abnormality of the bogie for railroad vehicles (bogie 3) with an inexpensive configuration. Further, in the data aggregation period T, the sample number threshold Cth is provided for the sample number C of the acceleration data value that is equal to or greater than the acceleration data threshold Gth. It is possible to detect the vibration caused by it, and suppress the false detection of the vibration caused by the temporary impact applied to the railroad vehicle bogie (trolley 3) as an abnormality of the railroad vehicle bogie (trolley 3). Can be done.

As described above, according to the present embodiment, it is possible to obtain an abnormality detection system for a railroad vehicle bogie and an abnormality detection method capable of detecting an abnormality of the railroad car bogie with an inexpensive configuration.

(Embodiment 2)
FIG. 6 is a schematic view showing a configuration example of an abnormality detection system for a railroad bogie according to the second embodiment. FIG. 7 is a block diagram showing a configuration example of the diagnostic device of the second embodiment. The same components as those described in the first embodiment are designated by the same reference numerals, and duplicate description will be omitted.

As shown in FIG. 5, in the abnormality detection system 10a of the railroad vehicle bogie according to the present embodiment, the diagnostic device 1a is provided in the ground equipment 200. The detection value of the vibration sensor 2 is transmitted from the transmission device 5 provided in the vehicle 100.

As shown in FIG. 7, the diagnostic device 1a includes a receiving unit 15. The receiving unit 15 receives the detection value of the vibration sensor 2 transmitted from the transmitting device 5 and outputs it to the AD conversion unit 11.

The transmission means from the transmission device 5 to the reception unit 15 of the diagnostic device 1a may be wireless communication such as mobile communication, or wired communication connected to a communication line. The present disclosure is not limited by the transmission means from the transmission device 5 to the reception unit 15 of the diagnostic device 1a.

In the configuration of the second embodiment described above, the abnormality detection process and the threshold value determination in the abnormality detection process are the same as those of the first embodiment, and thus duplicate description will be omitted.

In the configuration of the second embodiment, the same effect as that of the first embodiment can be obtained. Specifically, the absolute value calculation process or the square value calculation process in the data conversion unit 12 and the comparison calculation process in the abnormality determination unit 13 can be reduced, and the abnormality of the trolley 3 can be detected with an inexpensive configuration. can. Further, in the data aggregation period T, since the sample number threshold Cth is provided for the sample number C of the acceleration data value that is equal to or greater than the acceleration data threshold Gth, vibration caused by a continuous abnormality of the trolley 3 is detected. This makes it possible to suppress erroneous detection of vibration caused by a temporary impact applied to the trolley 3 as an abnormality of the trolley 3.

The acceleration data threshold Gth may be generated by the abnormality determination unit 13 and stored in the storage unit 14. For example, the abnormality determination unit 13 calculates the root mean square (RMS) and the mean value of the absolute value or the square value (acceleration data value G in the embodiment) of the sampling data output from the data conversion unit 12, and the storage unit 14 It may be a mode to be stored in.

For example, when the root mean square (RMS) or the mean value is used as a threshold value, data for a time sufficiently longer than the data aggregation period T is always generated. As a result, when an abnormality occurs, it is considered that the acceleration data value G rises quickly and deviates from the root mean square (RMS) or the mean value, and it is detected.

Further, the vibration detection direction of the vibration sensor 2 is preferably a vertical direction with respect to the vehicle 100 in order to suppress the influence of the movement of the vehicle 100, but it is a movement direction (front-back direction) or a left-right direction of the vehicle 100. You may. The present disclosure is not limited by the vibration detection direction of the vibration sensor 2.

1,1a Diagnostic device 2 Vibration sensor (detection device)
3 bogies (bogies for railroad cars)
4 Wheels 5 Transmitters 10, 10a Anomaly detection system (Abnormality detection system for railcar bogies)
11 AD conversion unit 12 Data conversion unit 13 Abnormality determination unit 14 Storage unit 15 Reception unit 100 Vehicle (railroad vehicle)
200 Ground equipment

Claims (7)

A vibration sensor installed in a railroad vehicle that detects vibration generated from a bogie for a railroad vehicle,
Based on the detection value detected by the vibration sensor , a diagnostic device that detects anomalies in the railroad bogie and
With
The diagnostic device is
An AD conversion unit that samples the output of the vibration sensor at a predetermined sampling cycle and outputs it as sampling data.
A data conversion unit that calculates the absolute value or square value of the sampling data output from the AD conversion unit, and
Based on the frequency with which the absolute value or squared value of the sampling data output from the data conversion unit becomes equal to or higher than a predetermined threshold value, the abnormality determination unit that detects the abnormality of the railroad bogie and outputs the abnormality determination result, and the abnormality determination unit.
With
The abnormality determination unit
In a data aggregation period longer than the sampling cycle, the number of samples in which the absolute value or square value of the sampled data is equal to or greater than a predetermined value is counted, and when the number of samples is equal to or greater than a predetermined number, the product is used for the railway vehicle. Judge that an abnormality has occurred in the trolley,
Anomaly detection system for railcar bogies. The vibration sensor is an acceleration sensor.
The diagnostic device is
A sample of the acceleration data threshold, which is the threshold of the acceleration data value converted into a positive value by the data conversion unit, and the acceleration data value obtained during the data aggregation period, which is equal to or greater than the acceleration data threshold. It is provided with a storage unit in which a sample number threshold, which is a reference value of a number, is stored.
The abnormality determination unit
A request for determining that an abnormality has occurred in the railcar trolley when the number of samples of the acceleration data value that exceeds the acceleration data threshold becomes equal to or greater than the sample number threshold during the data aggregation period. Item 1. The abnormality detection system for a railroad vehicle trolley according to Item 1. The diagnostic device is an abnormality detection system for a railroad vehicle bogie according to claim 1 or 2, which is provided in the railroad vehicle. The diagnostic device is an abnormality detection system for a railroad vehicle bogie according to claim 1 or 2, which is provided in ground equipment. A railroad vehicle trolley that detects abnormalities of the railroad vehicle trolley based on the frequency with which the absolute value or squared value of the detected value detected by the vibration sensor that detects the vibration generated from the railroad vehicle trolley becomes equal to or higher than a predetermined threshold value. Abnormality detection method
A step of sampling the output of the vibration sensor at a predetermined sampling cycle and outputting it as sampling data .
The step of calculating the absolute value or the square value of the sampling data ,
A step of counting the number of samples in which the absolute value or the square value of the sampling data is equal to or greater than a predetermined value in a data aggregation period longer than the sampling cycle .
A step of determining that an abnormality has occurred in the railroad car bogie when the number of samples exceeds a predetermined number, and
Anomaly detection method for bogies for railroad vehicles. The vibration sensor is an acceleration sensor.
When the number of samples of the acceleration data value that exceeds the predetermined acceleration data threshold becomes equal to or greater than the predetermined number of samples threshold in the data aggregation period, it is determined that an abnormality has occurred in the railroad vehicle carriage.
The method for detecting an abnormality in a railroad bogie according to claim 5. The sample number threshold is a reference value for the number of samples of acceleration data values that are equal to or greater than the acceleration data threshold among the acceleration data values acquired during the data aggregation period.
The method for detecting an abnormality in a railroad bogie according to claim 6.

Images