Railroad wheel tread abnormality detection system, railroad wheel tread abnormality detection method, and railroad wheel tread abnormality detection program

The railway wheel tread abnormality detection system addresses high costs by converting and analyzing vibration sensor signals to detect wheel flats accurately with fewer sensors, reducing costs and noise interference.

JP2024162774APending Publication Date: 2024-11-21MITSUBISHI ELECTRIC CORP
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
JP2023078659
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-11
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

Existing wheel tread abnormality detection systems require multiple vibration sensors for each wheel, leading to high costs when detecting abnormalities in a large number of wheels.

Method used

A railway wheel tread abnormality detection system that converts vibration sensor signals into frequency bands, uses a frequency analysis unit to separate wheel tread abnormalities from rail joint vibrations, and employs independent component analysis to remove noise, allowing for accurate detection with a reduced number of sensors.

Benefits of technology

The system effectively detects wheel tread abnormalities like wheel flats at a lower cost by reducing the number of required vibration sensors and minimizing false detections due to rail joint noise.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024162774000001_ABST
    Figure 2024162774000001_ABST
Patent Text Reader

Abstract

To obtain a railroad wheel tread abnormality detection system that can detect wheel tread abnormalities at a low cost even when detecting wheel tread abnormalities for many wheels.SOLUTION: A railroad wheel tread abnormality detection system 1A comprises: a frequency analysis section 10A that converts a vibration sensor signal measured by a vibration sensor installed on a rail into a first time signal indicating the signal intensity for each frequency band; a joint vibration removal section 40A that calculates a second time signal obtained by removing a signal of vibration caused by a rail joint from a corresponding signal corresponding to the first time signal; a tread abnormality detection section 80A that determines the presence or absence of wheel tread abnormality from the second time signal; and an output section 90 that outputs a determination result of the tread abnormality detection section 80A. When the signal intensity of a third time signal including the frequency of the vibration caused by the rail joint extracted from the corresponding signal exceeds a specific value, the joint vibration removal section 40A calculates the second time signal by removing the third time signal from the corresponding signal.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present disclosure relates to a railway wheel tread abnormality detection system, a railway wheel tread abnormality detection method, and a railway wheel tread abnormality detection program for detecting abnormalities in a railway wheel tread. [Background technology]

[0002] Wheel flats are wear marks that occur on the wheel tread due to friction between the rail and the wheels when a moving train applies heavy braking such as sudden braking. Wheel flats can cause abnormal noise or vibrations that lead to a worsening ride and damage to the rail, so early detection of wheel flats is essential. One technology for detecting wheel flats uses vibration data obtained from vibration sensors installed on the axles of the train.

[0003] For example, the abnormality diagnosis device in Patent Document 1 identifies whether abnormal vibration is caused by a wheel flat or an axle bearing, based on vibration data obtained from a vibration sensor attached to the bearing housing of each wheel. In addition to wheel flats, there are other abnormalities that occur on the wheel tread, such as thermal cracks, which are widespread in the wheel, and deep scratches, which are called peeling, and these also require early detection. Hereinafter, these abnormalities are collectively referred to as wheel tread abnormalities. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2007-170815 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the technology of Patent Document 1 uses a vibration sensor attached to the bearing housing of each wheel, so a vibration sensor is required for each wheel for which wheel flats need to be detected. Therefore, the technology of Patent Document 1 has a problem that it is costly to detect wheel flats for many wheels.

[0006] The present disclosure has been made in consideration of the above, and aims to provide a railway wheel tread abnormality detection system that can detect wheel tread abnormalities, including wheel flats, at low cost, even when detecting wheel tread abnormalities, including wheel flats, for a large number of wheels. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems and achieve the object, the railway wheel tread abnormality detection system disclosed herein includes a frequency analysis unit that converts a vibration sensor signal indicating information on vibration measured by a vibration sensor installed on a rail into a first time signal indicating the signal strength for each frequency band, and a joint vibration elimination unit that calculates a second time signal by removing a signal of vibration caused by a rail joint, which is a joint of a rail, from a corresponding signal corresponding to the first time signal. The railway wheel tread abnormality detection system disclosed herein also includes a tread abnormality detection unit that determines the presence or absence of a wheel tread abnormality occurring in a wheel of a vehicle running on a rail from the second time signal, and an output unit that outputs the determination result of the tread abnormality detection unit. The joint vibration elimination unit extracts a third time signal including a frequency of vibration caused by a rail joint from the corresponding signal, and calculates a second time signal by removing the third time signal from the corresponding signal when the signal strength of the third time signal exceeds a specific value. Effect of the Invention

[0008] The railway wheel tread abnormality detection system disclosed herein has the advantage of being able to detect wheel tread abnormalities, such as wheel flats, at low cost, even when detecting wheel tread abnormalities, such as wheel flats, for a large number of wheels. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing a configuration of a railway wheel tread abnormality detection system according to a first embodiment. [Diagram 2] FIG. 1 is a diagram for explaining the arrangement positions of a vibration sensor and a wheel detection sensor connected to the railway wheel tread abnormality detection system according to the first embodiment. [Diagram 3] FIG. 1 is a diagram for explaining an example of a vibration sensor signal input to the railway wheel tread abnormality detection system according to the first embodiment; [Figure 4] FIG. 1 is a diagram for explaining an example of a frequency spectrum signal calculated by a normalization unit of the railway wheel tread abnormality detection system according to the first embodiment; [Diagram 5] FIG. 1 is a diagram showing an example of a first independent component signal calculated by an independent component decomposition unit of the railway wheel tread abnormality detection system according to the first embodiment; [Figure 6] FIG. 10 is a diagram showing an example of a second independent component signal calculated by an independent component decomposition unit of the railway wheel tread abnormality detection system according to the first embodiment; [Figure 7] FIG. 11 is a diagram showing an example of a third independent component signal calculated by an independent component decomposition unit of the railway wheel tread abnormality detection system according to the first embodiment; [Figure 8] FIG. 11 is a diagram showing an example of a fourth independent component signal calculated by an independent component decomposition unit of the railway wheel tread abnormality detection system according to the first embodiment; [Figure 9] FIG. 1 is a diagram showing an example of a frequency spectrum signal calculated by a removal width expanding unit of the railway wheel tread abnormality detection system according to the first embodiment; [Figure 10] FIG. 1 is a diagram showing an example of a frequency spectrum signal calculated by a similarity filter unit of the railway wheel tread abnormality detection system according to the first embodiment; [Figure 11] FIG. 1 is a diagram showing an example of a time signal calculated by a feature amount calculation unit of the railway wheel tread abnormality detection system according to the first embodiment; [Figure 12] FIG. 1 is a diagram showing an example of a wheel detection output and a wheel tread abnormality detection determination result displayed by a display unit of the railway wheel tread abnormality detection system according to the first embodiment. [Figure 13]1 is a flowchart showing an operation process of the railway wheel tread abnormality detection system according to the first embodiment. [Figure 14] FIG. 13 is a diagram showing an example of a norm calculated by an independent component decomposition unit of the railway wheel tread abnormality detection system according to the second embodiment. [Figure 15] FIG. 13 is a diagram showing an example of a first frequency set by an independent component removal unit of the railway wheel tread abnormality detection system according to the third embodiment when calculating signal elements of a frequency spectrum signal group. [Figure 16] FIG. 13 is a diagram showing an example of the norm of a first peak calculated by an independent component removal unit of the railway wheel tread abnormality detection system according to the third embodiment; [Figure 17] FIG. 13 is a diagram showing an example of the norm of a second peak calculated by the independent component removal unit of the railway wheel tread abnormality detection system according to the third embodiment; [Figure 18] FIG. 13 is a diagram showing an example of the norm of a third peak calculated by the independent component removal unit of the railway wheel tread abnormality detection system according to the third embodiment; [Figure 19] FIG. 13 is a diagram showing an example of the norm of the reverberation noise of the third peak calculated by the independent component removal unit of the railway wheel tread abnormality detection system according to the third embodiment; [Figure 20] FIG. 13 is a diagram showing a configuration of a railway wheel tread abnormality detection system according to a fourth embodiment. [Figure 21] FIG. 13 is a diagram showing an example of a time signal limited to a first frequency band calculated by a frequency analysis unit of the railway wheel tread abnormality detection system according to the fourth embodiment. [Figure 22] FIG. 13 is a diagram showing an example of a time signal limited to a second frequency band calculated by a frequency analysis unit of the railway wheel tread abnormality detection system according to the fourth embodiment. [Figure 23] FIG. 13 is a diagram for explaining an example of a threshold value set by an independent component decomposition unit of the railway wheel tread abnormality detection system according to the fourth embodiment. [Figure 24] FIG. 13 is a diagram showing an example of an independent component signal extracted from a time signal limited to a first frequency band by an independent component decomposition unit of the railway wheel tread abnormality detection system according to the fourth embodiment; [Diagram 25]FIG. 13 is a diagram showing an example of an independent component signal extracted from a time signal limited to a second frequency band by an independent component decomposition unit of the railway wheel tread abnormality detection system according to the fourth embodiment; [Figure 26] FIG. 13 is a diagram showing an example of a time signal obtained by removing noise components from a time signal limited to a second frequency band by an independent component removal unit of the railway wheel tread abnormality detection system according to the fourth embodiment; [Figure 27] A flowchart showing an operation process of the railway wheel tread abnormality detection system according to the fourth embodiment. [Figure 28] FIG. 1 is a diagram showing an example of the configuration of a processing circuit provided in the railway wheel tread abnormality detection system according to the first to fourth embodiments when the processing circuit is realized by a processor and a memory. [Figure 29] FIG. 1 is a diagram showing an example of a processing circuit in the railway wheel tread abnormality detection system according to the first to fourth embodiments, in the case where the processing circuit is configured with dedicated hardware. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Below, a railway wheel tread abnormality detection system, a railway wheel tread abnormality detection method, and a railway wheel tread abnormality detection program according to embodiments of the present disclosure will be described in detail with reference to the drawings.

[0011] Embodiment 1 1 is a diagram showing a configuration of a railway wheel tread abnormality detection system according to a first embodiment. The railway wheel tread abnormality detection system 1A includes a frequency analysis unit 10A, a normalization unit 20, a data extraction unit 30, a joint vibration elimination unit 40A, a data combination unit 50, a elimination width expansion unit 60, a similarity filter unit 70, a tread abnormality detection unit 80A, an output unit 90, and a display unit 91. Note that the display unit 91 and the railway wheel tread abnormality detection system 1A may be configured separately.

[0012] The joint vibration elimination unit 40A has an independent component decomposition unit 41A and an independent component elimination unit 42A. The tread abnormality detection unit 80A has a feature amount calculation unit 81A and an abnormality type determination unit 82A. The frequency analysis unit 10A is connected to the vibration sensor 3 described later, and receives a signal sent from the vibration sensor 3 (a vibration sensor signal X1 described later). The similarity filter unit 70 is connected to the wheel detection sensor 2 described later, and receives a signal sent from the wheel detection sensor 2 (a wheel detection sensor signal X2 described later).

[0013] 2 is a diagram for explaining the positions of the vibration sensor and the wheel detection sensor connected to the railway wheel tread abnormality detection system according to the embodiment 1. The vibration sensor 3 and the wheel detection sensor 2 are installed near a rail 5 on which a vehicle 4, which is a railway vehicle, runs.

[0014] For example, one vibration sensor 3 is disposed for one rail 5. That is, for two rails 5, one vibration sensor 3 is attached to one rail 5, and one vibration sensor 3 is attached to the other rail 5. The two vibration sensors 3 are disposed, for example, at positions facing each other in a direction perpendicular to the rails 5.

[0015] Furthermore, one wheel detection sensor 2 is disposed for one rail 5. That is, for two rails 5, one wheel detection sensor 2 is disposed near one rail 5, and one wheel detection sensor 2 is disposed near the other rail 5. In order to calculate the speed of the vehicle 4 from the difference in detection times and the difference in placement distances of the two wheel detection sensors 2, one wheel detection sensor 2 and the other wheel detection sensor 2 are disposed at a fixed distance in the longitudinal direction of the rail.

[0016] The vibration sensor 3 is a sensor that measures vibrations that occur when the vehicle 4 is traveling. The vibration sensor 3 measures vibrations of the rail 5 excited by the traveling vehicle 4. The vibration sensor 3 is, for example, an acceleration sensor. The vibration sensor 3 sends vibration data indicating information on the measured vibration to the frequency analysis unit 10A as a vibration sensor signal X1. In this way, the vibration sensor 3 detects vibrations of the rail 5, and outputs an output signal indicating the detection result to the frequency analysis unit 10A as the vibration sensor signal X1.

[0017] The wheel detection sensor 2 is a sensor that detects the wheels of the vehicle 4 traveling on the rail 5. The wheel detection sensor 2 detects the wheels that have passed the position where the wheel detection sensor 2 is disposed. Specifically, the wheel detection sensor 2 has a detection range in a direction perpendicular to the rail 5, and outputs an ON signal indicating that the wheel has been detected when the wheel enters this detection range. In addition, the wheel detection sensor 2 does not output an ON signal when the wheel does not enter the detection range. The wheel detection sensor 2 sends information indicating that the wheel has been detected to the similarity filter unit 70 as a wheel detection sensor signal X2. In this way, the wheel detection sensor 2 detects the wheel, and sends an output signal indicating the detection result to the similarity filter unit 70 as the wheel detection sensor signal X2. The wheel detection sensor 2 is also capable of detecting the vehicle 4 that is traveling.

[0018] Fig. 3 is a diagram for explaining an example of a vibration sensor signal input to the railway wheel tread abnormality detection system according to the first embodiment. The horizontal axis of the graph shown in Fig. 3 is time, and the vertical axis is vibration amplitude. The graph shown in Fig. 3 illustrates a vibration sensor signal Sa1 obtained during a specific period, rather than the entire vibration sensor signal X1 obtained for an entire train. In other words, the graph shown in Fig. 3 illustrates a vibration sensor signal Sa1 (a part of the vibration sensor signal X1) obtained for a part of a train.

[0019] 3 shows a vibration sensor signal Sa1 obtained for a part of a train, but the frequency analysis unit 10A and the normalization unit 20 perform arithmetic processing on the entire vibration sensor signal X1 obtained for the entire train. Here, the frequency analysis unit 10A performs arithmetic processing on the vibration sensor signal Sa1, and the normalization unit 20 performs arithmetic processing on a frequency spectrum signal Sb1 (not shown) that is the result of the calculation by the frequency analysis unit 10A.

[0020] Peaks P1, P2, and P3 of vibration sensor signal Sa1 shown in Fig. 3 are vibration data (vibration data of joint vibration) when vehicle 4 passes over a joint of rail 5, and peaks P4 and P5 are vibration data (vibration data of abnormal wheel tread vibration) when an abnormal surface of the wheel tread comes into contact with rail 5. At this point, railway wheel tread abnormality detection system 1A cannot determine which signal is vibration data of joint vibration and which signal is vibration data of abnormal wheel tread vibration, but by subsequent processing, it extracts only the vibration data of abnormal wheel tread vibration and determines whether or not there is a wheel tread abnormality. Vibration sensor signal X1 including vibration sensor signal Sa1 is detected by vibration sensor 3, and vibration sensor 3 outputs it to frequency analysis unit 10A.

[0021] When the frequency analysis unit 10A receives the vibration sensor signal X1 including the vibration sensor signal Sa1, it performs a short-time Fourier transform on the vibration sensor signal X1 to calculate a frequency spectrum signal including a frequency spectrum signal (two-dimensional spectrum signal) Sb representing the frequency spectrum at each time. The frequency spectrum signal for the entire train including the frequency spectrum signal Sb1 is a time signal indicating the intensity for each frequency band of the vibration sensor signal X1, which is vibration data. The frequency spectrum signal Sb1 is a signal element included in the frequency spectrum signal Sb, and corresponds to the vibration sensor signal Sa1. In the first embodiment, the frequency spectrum signal for the entire train including the frequency spectrum signal Sb1 is a first time signal.

[0022] In the above description, the frequency analysis unit 10A uses a short-time Fourier transform for the frequency analysis. However, the frequency analysis unit 10A may use a wavelet transform for the frequency analysis. The frequency analysis unit 10A outputs the frequency spectrum signal Sb1 to the normalization unit 20.

[0023] When the frequency spectrum signal Sb1 is input, the normalization unit 20 calculates the scale of noise other than joint vibration for the time signal of each frequency of the frequency spectrum signal Sb1. The normalization unit 20 calculates the noise scale of the time signal of each frequency by dividing the smallest m% values ​​of the time signals by the value at the m% point of the distribution to which noise other than vibration caused by the joint of the rail 5 (hereinafter referred to as the rail joint) follows. m is a preset parameter. The normalization unit 20 calculates a frequency spectrum signal Sc in which the noise scale is normalized by dividing the time signal by the calculated scale.

[0024] The normalization performed by the normalization unit 20 makes the signal strength (scale) uniform for each frequency band. Since the noise at each frequency differs for each frequency, the normalization unit 20 averages small noise in the time signal by performing normalization, thereby making the signal strength uniform for each frequency band. In this case, the normalization unit 20 normalizes the noise scale by excluding the noise of the seam vibration, so that the signal strength for each frequency band of the noise other than the seam vibration can be accurately made uniform.

[0025] The noise contained in the frequency spectrum signal Sb1 is a Gaussian noise with an expected value of 0 and a variance of σ^2 contained in the vibration sensor signal X1, which is subjected to a short-time Fourier transform. Therefore, the noise contained in the frequency spectrum signal Sb1 follows a gamma distribution with k=1 / 2 and θ=2σ^2 for the DC component, and follows an exponential distribution with λ=1 / (2σ^2) for frequency bands other than the DC component. The normalization unit 20 outputs the normalized frequency spectrum signal Sc to the data extraction unit 30.

[0026] Fig. 4 is a diagram for explaining an example of a frequency spectrum signal calculated by the normalization unit of the railway wheel tread abnormality detection system according to the first embodiment. The horizontal axis of the graph shown in Fig. 4 is time, and the vertical axis is vibration frequency. Fig. 4 shows a color map in which frequency is expressed by color.

[0027] 4 shows a frequency spectrum signal Sc1 obtained by performing arithmetic processing on the frequency spectrum signal Sb1 by the normalization unit 20. The frequency spectrum signal Sc contains non-periodic noise N1. The non-periodic noise N1 is a noise obtained by performing a short-time Fourier transform on the aforementioned Gaussian noise.

[0028] Peaks P1 to P5 shown in Fig. 4 correspond to peaks P1 to P5 shown in Fig. 3. The frequency spectrum signal Sc includes a signal of vibration caused by the rail joint and a signal of vibration caused by abnormal vibration of the wheel tread.

[0029] The spectra of peaks P1 to P3 are observed over a wide band, and the spectra of peaks P4 and P5 are observed in the low frequency band. That is, in the case of joint vibration, a spectrum is observed over a wide band from low to high frequency bands, and in the case of abnormal wheel tread vibration, a spectrum is observed in the low frequency band.

[0030] When the normalized frequency spectrum signal Sc is input, the data extraction unit 30 calculates a frequency spectrum signal group Scn by extracting the frequency spectrum signal Sc by limiting it to a specific time width. That is, the data extraction unit 30 divides the normalized frequency spectrum signal Sc into specific time widths to calculate frequency spectrum signals Sc1, Sc2, Sc3, . . . , ScN that are signal elements of the frequency spectrum signal group (time signal group) Scn. In the first embodiment, the frequency spectrum signal group Scn calculated by the data extraction unit 30 is a corresponding signal corresponding to the frequency spectrum signal (first time signal) for the entire train including the frequency spectrum signal Sb1.

[0031] The data extraction unit 30 extracts the signal by sliding an extraction window of width T1 by width T2 at a time. That is, the frequency spectrum signal Sc1 is the signal of the frequency spectrum signal Sc from time 0 to time T1, the frequency spectrum signal Sc2 is the signal from time T2 to time (T1+T2), and the frequency spectrum signal Sc3 is the signal from time 2×T2 to time (T1+2×T2).

[0032] The joint vibration elimination unit 40A, which executes a calculation process later than the calculation process executed by the data extraction unit 30, does not execute the calculation process for the entire train of one formation all at once, but executes the calculation process for each specific period. That is, the joint vibration elimination unit 40A does not execute the calculation process for the entire period of the vibration sensor signal X1 corresponding to the entire train of one formation all at once, but executes the calculation process for each period divided by the data extraction unit 30. For this reason, the data extraction unit 30 calculates a frequency spectrum signal group Scn that is extracted by limiting the frequency spectrum signal Sc to a specific time width. The data extraction unit 30 outputs the extracted frequency spectrum signal group Scn to the independent component decomposition unit 41A. Below, a case where the frequency spectrum signal Sc1 corresponds to the frequency spectrum signal Sb1 will be described.

[0033] When the extracted frequency spectrum signal group Scn is input, the independent component decomposition unit 41A calculates an independent component signal group Sdn by decomposing each signal element of the frequency spectrum signal group Scn into independent components by independent component analysis. In the following, a frequency spectrum signal Sc1, which is a signal element of the frequency spectrum signal group Scn, will be described.

[0034] For example, the independent component decomposition unit 41A calculates an independent component signal Sd1 from the frequency spectrum signal Sc1, and calculates an independent component signal Sd2 from the frequency spectrum signal Sc2. Each of the independent component signals Sd1 and Sd2 includes one or more independent component signals. The independent component signal Sd1 includes, for example, independent component signals Sd1a, Sd1b, Sd1c, and Sd1d, which will be described later.

[0035] In the independent component analysis, each signal element of the frequency spectrum signal group Scn can be decomposed into independent component signals equal to the number of frequency bins. However, in practice, in order to speed up processing, the independent component decomposition unit 41A terminates the decomposition when sufficient decomposition has been achieved. For example, when the independent component decomposition unit 41A decomposes the frequency spectrum signal Sc1 into M (M is a natural number) independent component signals, it calculates the AIC (Akaike's Information Criterion) of the difference between the frequency spectrum signal Sc1 and the component obtained by adding up the M independent component signals. The independent component decomposition unit 41A determines that sufficient decomposition has been achieved when the AIC calculated for M is greater than the AIC calculated when the previous independent component signals were decomposed into (M-1) independent component signals.

[0036] The independent component decomposition unit 41A decomposes the independent component signals of the frequency spectrum signal Sc from the first to the Mth in order. For example, for the frequency spectrum signal Sc1, the independent component decomposition unit 41A decomposes the independent component signal Sd1a in FIG. 5 described later as the first independent component signal, and the independent component signal Sd1b in FIG. 6 described later as the second independent component signal. When the independent component decomposition unit 41A decomposes the second independent component signal, it calculates the AIC of the difference between the two independent component signals Sd1a and Sd1b and the frequency spectrum signal Sc1. That is, the independent component decomposition unit 41A calculates a signal obtained by removing the independent component signals Sd1a and Sd1b corresponding to the peaks P1 and P2 from the frequency spectrum signal Sc1 shown in FIG. 4. In this case, the independent component decomposition unit 41A determines that the signal has been sufficiently decomposed when the calculated AIC is greater than the AIC when the previous independent component signal was decomposed into (M-1) independent component signals (here, 1).

[0037] The independent component decomposition unit 41A calculates an independent component signal group Sdn (independent component signals Sd1, Sd2, Sd3, . . ., SdN) from the extracted frequency spectrum signal group Scn (frequency spectrum signals Sc1, Sc2, Sc3, . . ., ScN). That is, the independent component decomposition unit 41A calculates the independent component signal group Sdn from the frequency spectrum signal group Scn by independent component analysis.

[0038] The independent component decomposition unit 41A outputs the extracted frequency spectrum signal group Scn and independent component signal group Sdn to the independent component removal unit 42A.

[0039] Here, the independent component signals obtained when the independent component decomposition unit 41A executes arithmetic processing on each signal element of the normalized frequency spectrum signal group Scn will be described. Here, the independent component signal Sd1 obtained when the independent component decomposition unit 41A executes arithmetic processing on the frequency spectrum signal Sc1 will be described.

[0040] Fig. 5 is a diagram illustrating an example of a first independent component signal calculated by an independent component decomposition unit of the railway wheel tread abnormality detection system according to the first embodiment. Fig. 6 is a diagram illustrating an example of a second independent component signal calculated by an independent component decomposition unit of the railway wheel tread abnormality detection system according to the first embodiment. Fig. 7 is a diagram illustrating an example of a third independent component signal calculated by an independent component decomposition unit of the railway wheel tread abnormality detection system according to the first embodiment. Fig. 8 is a diagram illustrating an example of a fourth independent component signal calculated by an independent component decomposition unit of the railway wheel tread abnormality detection system according to the first embodiment.

[0041] The horizontal axis of each graph in FIG. 5 to FIG. 8 is time, and the vertical axis is frequency. FIG. 5 to FIG. 8 show color maps in which frequency is expressed by color. The independent component signal Sd1 calculated by the independent component decomposition unit 41A from the frequency spectrum signal Sc1 includes independent component signals Sd1a to Sd1d as signal elements. FIG. 5 shows the independent component signal Sd1a which is the first independent component signal, and FIG. 6 shows the independent component signal Sd1b which is the second independent component signal. FIG. 7 shows the independent component signal Sd1c which is the third independent component signal, and FIG. 8 shows the independent component signal Sd1d which is the fourth independent component signal. The independent component signal Sd1d shown in FIG. 8 is the same signal as the frequency spectrum signal Se1 described later. The independent component signals Sd1a to Sd1d include non-periodic noise N1.

[0042] The independent component signals shown in Fig. 5 to Fig. 8 correspond to peaks P1 to P5 of the frequency spectrum signal Sc1 shown in Fig. 4. The independent component signal Sd1a shown in Fig. 5 corresponds to peak P1, the independent component signal Sd1b shown in Fig. 6 corresponds to peak P2, and the independent component signal Sd1c shown in Fig. 7 corresponds to peak P3. That is, Figs. 5 to 7 correspond to peaks P1 to P3 of the joint vibration. Note that the independent component signal shown in Fig. 7 does not include reverberation noise P3E of peak P3, which will be described later. The independent component signal Sd1d shown in Fig. 8 is a component other than the joint vibration. The independent component signal Sd1d shown in Fig. 8 includes peaks P4 and P5, which are abnormal wheel tread vibration, as well as reverberation noise P3E of peak P3 that could not be resolved.

[0043] When the cut-out frequency spectrum signal Sc1 and the independent component signal Sd1 are input, the independent component removal unit 42A removes the corresponding signal element of the independent component signal Sd1 from the frequency spectrum signal Sc1 until the noise component is sufficiently removed for each signal element of the frequency spectrum signal Sc1. In this way, the independent component removal unit 42A calculates a frequency spectrum signal Se1 from which the noise components are removed from the frequency spectrum signal Sc1. In this case, as described above, when Q (Q is a natural number) noise components are removed from the frequency spectrum signal Sc1, the independent component removal unit 42A determines that the noise components are sufficiently removed if the AIC of the first frequency band (high frequency band) that does not include the abnormal wheel tread vibration of the removed signal becomes larger than the AIC when (Q-1) noise components are removed from the frequency spectrum signal Sc1. That is, the independent component removal unit 42A removes the signal elements (noise components) of the independent component signal Sd1 until the AIC of the first frequency band (high frequency band) becomes minimum. The independent component removing section 42A here judges that the noise components have been sufficiently removed when the peaks P1 to P3 of the joint vibration shown in Figs. 5 to 7, which are noise components, have been removed.

[0044] The independent component removal unit 42A removes noise components from the independent component signal Sd1 in the order of the signal with the largest norm in the first frequency band. That is, the independent component removal unit 42A removes noise components from the independent component signal Sd1 in the order of the strongest signal strength in the first frequency band. As a result, when the strength of a time signal in the first frequency band of the independent component signal Sd1 is a magnitude that should be removed based on the AIC, the independent component removal unit 42A removes this time signal from the frequency spectrum signal Sc1 as a time signal of a noise component. In this way, the independent component removal unit 42A removes the signal (noise component) of vibration caused by the rail joint from the frequency spectrum signal Sc, which is a time signal.

[0045] The independent component removal unit 42A here calculates a frequency spectrum signal Se1 by removing the independent component signals Sd1a-Sd1c from the frequency spectrum signal Sc1. The independent component removal unit 42A also removes noise components from the frequency spectrum signals Sc2-ScN, as with the frequency spectrum signal Sc1. In this way, the independent component removal unit 42A calculates a frequency spectrum signal set Sen (frequency spectrum signals Se1, Se2, Se3, . . . , SeN) from which the noise components have been removed from the frequency spectrum signal set Scn. The independent component removal unit 42A outputs the frequency spectrum signal set Sen from which the noise components have been removed to the data combination unit 50.

[0046] In the first embodiment, the frequency spectrum signal group Sen is the second time signal, and the independent component signal group Sdn is the third time signal.

[0047] When the frequency spectrum signal group Sen from which the noise components have been removed is input, the data combination unit 50 calculates a frequency spectrum signal Se by combining frequency spectrum signals Se1, Se2, Se3, ..., SeN which are signal elements of the frequency spectrum signal group Sen. Specifically, the data combination unit 50 calculates a frequency spectrum signal Se from which the noise components have been removed and which has the same time width as the frequency spectrum signal Sc before being cut out. In other words, the data combination unit 50 combines the frequency spectrum signals Se1, Se2, Se3, ..., SeN so that the frequency spectrum signal group Sen from which the noise components have been removed becomes a frequency spectrum signal Se which has the same time width as the frequency spectrum signal Sc before being cut out.

[0048] When combining data, the data combining unit 50 uses the values ​​of each signal element of the frequency spectrum signal group Sen, and combines the signal elements by using the minimum value of the overlapping signal elements for the overlapping time, i.e., the time when the extraction windows overlap. In this way, even if the independent component removal unit 42A fails to remove the seam vibration from a signal, the independent component removal unit 42A can remove the seam vibration from another signal for the same time. The data combining unit 50 outputs the frequency spectrum signal Se from which the noise components have been removed to the removal width expansion unit 60.

[0049] When the frequency spectrum signal Se from which the noise components have been removed is input, the removal width expanding unit 60 calculates a frequency spectrum signal Sf from which the reverberation noise P3E has been removed by also removing the signal from the time when each noise component of the frequency spectrum signal Se has been removed until a specific time later. That is, the removal width expanding unit 60 removes the reverberation noise P3E by removing the signal from the time when the peaks P1 to P3, which are noise components of the frequency spectrum signal Se, have been removed (the signal immediately after removal). The removal width expanding unit 60 outputs the frequency spectrum signal Sf from which the reverberation noise P3E has been removed to the similarity filter unit 70.

[0050] Fig. 9 is a diagram showing an example of a frequency spectrum signal calculated by the removal width expanding unit of the railway wheel tread abnormality detection system according to the first embodiment. The horizontal axis of the graph shown in Fig. 9 is time, and the vertical axis is vibration frequency. Fig. 9 shows a color map in which frequency is expressed by color.

[0051] The graph shown in Fig. 9 represents the frequency spectrum signal Sf from which the reverberation noise P3E has been removed, obtained when calculations are performed by the removal width expanding unit 60. The peaks P4 and P5 shown in Fig. 9 correspond to the peaks P4 and P5 shown in Fig. 8. As shown in Fig. 9, the frequency spectrum signal Sf obtained when calculations are performed by the removal width expanding unit 60 has not only the peaks P1 to P3, which are joint vibrations, but also the reverberation noise P3E of the peak P3 that could not be resolved.

[0052] When the similarity filter unit 70 receives the wheel detection sensor signal X2 from the wheel detection sensor 2, it calculates the speed of the vehicle 4 from the wheel detection sensor signal X2 and calculates the time it takes for the wheel to make one revolution from the speed of the vehicle 4.

[0053] Furthermore, when the frequency spectrum signal Sf from which the reverberation noise P3E has been removed is input, the similarity filter unit 70 applies a filter to the signal at each time of the frequency spectrum signal Sf such that if there is a similar signal between signals having a time difference of one revolution of the front and rear wheels, the filter emphasizes the signal at each time and reduces (removes) the intensity if there is no similar signal. That is, the similarity filter unit 70 emphasizes the signal at each time when there is a similar signal at least at the time before one revolution of the wheel or the time after one revolution of the wheel. In other words, if the signal at a specific time of the frequency spectrum signal Sf is similar to the signal before one revolution of the wheel or the signal after one revolution of the wheel, the similarity filter unit 70 increases the intensity of both signals, and if the signals are not similar, the filter unit 70 reduces the intensity.

[0054] The time difference between the signal before one rotation of the wheel and the signal after one rotation of the wheel is the time difference of one rotation of the wheel. The similarity filter unit 70 judges whether the signals are similar or not based on the difference in signal strength for each frequency, the difference in the period during which the signals appear, and the like. Specifically, the similarity filter unit 70 calculates the cosine similarity of one rotation of the front and rear wheels. That is, for a signal at a certain time, the similarity filter unit 70 calculates the cosine similarity with the signal at a time before one rotation of the wheel and the cosine similarity with the signal at a time after one rotation of the wheel, and multiplies the maximum value of these. That is, for the signal at the Rth (R is a natural number)th rotation of the wheel, the similarity filter unit 70 calculates the cosine similarity with the signal at the (R-1)th rotation and the cosine similarity with the signal at the (R+1)th rotation, and multiplies the signal at the Rth rotation by the maximum value of these.

[0055] Cosine similarity is expressed as a value between 0 and 1. When signals for one revolution of the wheel are similar (when the similarity is equal to or greater than a specific value), the similarity filter unit 70 performs filtering by multiplying these signals by "1", which is the maximum value of cosine similarity. As a result, when there is a pair of a signal before one revolution of the wheel and a signal after one revolution of the wheel, the pair of signals is emphasized and remains. This filtering may also be performed by multiplying by cosine similarity.

[0056] In this way, the similarity filter unit 70 strengthens or weakens the signal strength based on the cosine similarity between a signal at a certain time and a signal at a time one revolution before the wheel and the cosine similarity between a signal at a time one revolution after the wheel, so that it is possible to calculate a frequency spectrum signal Sg from which the non-periodic noise N1 that could not be removed by the processing up to the removal width expansion unit 60 has been removed. That is, the similarity filter unit 70 can calculate a frequency spectrum signal Sg from which the non-periodic noise N1, which is a signal other than the rotation period of the wheel, has been removed. The similarity filter unit 70 outputs the frequency spectrum signal Sg from which the non-periodic noise N1 has been removed to the feature calculation unit 81A.

[0057] The similarity filter unit 70 also calculates a wheel detection output (wheel passing time data) indicating the time when the wheel passed the arrangement position of the wheel detection sensor 2 based on the wheel detection sensor signal X2, and outputs the wheel detection output to the output unit 90.

[0058] Fig. 10 is a diagram showing an example of a frequency spectrum signal calculated by the similarity filter unit of the railway wheel tread abnormality detection system according to the first embodiment. The horizontal axis of the graph shown in Fig. 10 is time, and the vertical axis is vibration frequency. Fig. 10 shows a color map in which frequency is expressed by color.

[0059] The graph shown in Fig. 10 represents the frequency spectrum signal Sg from which the non-periodic noise N1 has been removed, obtained when the similarity filter unit 70 performs the calculation. The peaks P4 and P5 shown in Fig. 10 correspond to the peaks P4 and P5 shown in Fig. 9. As shown in Fig. 10, the frequency spectrum signal Sg from which the similarity filter unit 70 performs the calculation has also had the non-periodic noise N1 removed.

[0060] When the frequency spectrum signal Sg from which the non-periodic noise N1 has been removed is input, the feature amount calculation unit 81A calculates, for each time instant of the frequency spectrum signal Sg, a value obtained by dividing the sum of the absolute values ​​of the signals in a second frequency band (a low frequency band having a frequency lower than the first frequency band) by the sum of the absolute values ​​of the signals in frequency bands other than the second frequency band, thereby obtaining a time signal Sh representing the presence or absence of a wheel tread abnormality at each time instant. The feature amount calculation unit 81A outputs the time signal Sh representing the presence or absence of a wheel tread abnormality at each time instant to the abnormality type determination unit 82A.

[0061] The abnormality type determination unit 82A determines whether or not a wheel tread abnormality has been detected by comparing the time signal Sh with a preset threshold value. The abnormality type determination unit 82A determines that there is a wheel tread abnormality when the time signal Sh is greater than the threshold value. In addition, the abnormality type determination unit 82A determines the size and depth of the tread abnormality from the time when the time signal Sh exceeded the threshold value, the difference between the threshold value, and the total length of time when the time signal Sh exceeded the threshold value within a certain time frame, for the time when it was determined that there was a wheel tread abnormality, and determines the type of abnormality.

[0062] Fig. 11 is a diagram showing an example of a time signal calculated by the feature amount calculation unit of the railway wheel tread abnormality detection system according to the first embodiment. The horizontal axis of the graph shown in Fig. 11 represents time, and the vertical axis represents signal strength. The vertical axis of Fig. 11 is given the phrase "magnitude of signal Sh", which means signal strength.

[0063] The graph shown in Fig. 11 represents a time signal Sh indicating the presence or absence of a wheel tread abnormality obtained when the feature calculation unit 81A performs calculations on the frequency spectrum signal Sg from which the non-periodic noise N1 has been removed. Peaks P4 and P5 shown in Fig. 11 correspond to peaks P4 and P5 shown in Fig. 10.

[0064] The abnormality type determination unit 82A detects peaks P4 and P5, which are wheel tread abnormalities, by comparing the time signal Sh of peaks P4 and P5 with a threshold value. The abnormality type determination unit 82A also determines the depth and magnitude of the tread abnormality from the difference between the threshold value and each of peaks P4 and P5 and the time at which the threshold value is exceeded. The abnormality type determination unit 82A outputs the tread abnormality detection determination result to the output unit 90. The output unit 90 outputs the tread abnormality detection determination result sent from the abnormality type determination unit 82A and the wheel detection output sent from the similarity filter unit 70 to the display unit 91. The display unit 91 displays the tread abnormality detection determination result and the wheel detection output.

[0065] Fig. 12 is a diagram showing an example of a wheel detection output and a tread abnormality detection judgment result displayed by the display unit of the railway wheel tread abnormality detection system according to the first embodiment. The horizontal axis of the graph shown in the upper part of Fig. 12 is time, and the vertical axis is the wheel detection output. The horizontal axis of the graph shown in the lower part of Fig. 12 is time, and the vertical axis is the tread abnormality detection judgment result.

[0066] In the graph shown in the upper part of Fig. 12, a waveform appears when a wheel passes, and in the graph shown in the lower part of Fig. 12, a waveform appears when a tread abnormality is detected. This makes it easy to identify the wheel on which the wheel tread abnormality is occurring.

[0067] Next, an operation process procedure of the railway wheel tread abnormality detection system 1A will be described. Fig. 13 is a flowchart showing the operation process procedure of the railway wheel tread abnormality detection system according to the first embodiment. Fig. 13 shows the detection process procedure of a wheel tread abnormality by the railway wheel tread abnormality detection system 1A.

[0068] The frequency analysis unit 10A receives the vibration sensor signal X1 sent from the vibration sensor 3. The frequency analysis unit 10A calculates a frequency spectrum signal Sb from the vibration sensor signal X1 (step S10). Specifically, the frequency analysis unit 10A performs a short-time Fourier transform on the vibration sensor signal X1 to calculate a frequency spectrum signal Sb representing a frequency spectrum at each time. The frequency analysis unit 10A outputs the frequency spectrum signal Sb to the normalization unit 20.

[0069] The normalization unit 20 calculates a frequency spectrum signal Sc in which the scale of noise has been normalized from the frequency spectrum signal Sb (step S20). Specifically, the normalization unit 20 calculates the scale of noise other than the joint vibration, and divides the frequency spectrum signal Sb by the calculated scale to calculate the frequency spectrum signal Sc in which the scale of noise has been normalized. The normalization unit 20 outputs the normalized frequency spectrum signal Sc to the data extraction unit 30.

[0070] The data extracting unit 30 calculates a set of frequency spectrum signals Scn (n=1, 2, 3, . . . , N) by extracting the frequency spectrum signal Sc for each specific time duration (step S30). The data extracting unit 30 outputs the set of extracted frequency spectrum signals Scn to the independent component decomposition unit 41A.

[0071] The independent component decomposition unit 41A calculates an independent component signal group Sdn by decomposing each signal element of the frequency spectrum signal group Scn into independent components by independent component analysis (step S41). The independent component decomposition unit 41A outputs the extracted frequency spectrum signal group Scn and independent component signal group Sdn to the independent component removal unit 42A.

[0072] The independent component removal unit 42A removes the signal elements of the independent component signal group Sdn from the frequency spectrum signal group Scn until the noise components are sufficiently removed from each signal element of the frequency spectrum signal group Scn. In this way, the independent component removal unit 42A calculates the frequency spectrum signal group Sen from which the noise components of the independent component signal group Sdn have been removed (step S42). The independent component removal unit 42A outputs the frequency spectrum signal group Sen from which the noise components have been removed to the data combination unit 50.

[0073] The data combining unit 50 calculates a frequency spectrum signal Se from which the noise components have been removed, which has the same time width as the frequency spectrum signal Sc before being extracted, from the frequency spectrum signal group Sen from which the noise components have been removed (step S50). The data combining unit 50 outputs the frequency spectrum signal Se from which the noise components have been removed to the removal width expanding unit 60.

[0074] The elimination width expanding unit 60 calculates a frequency spectrum signal Sf from which the reverberation noise P3E has been removed from the frequency spectrum signal Se (step S60). Specifically, the elimination width expanding unit 60 calculates the frequency spectrum signal Sf from which the reverberation noise P3E has been removed by removing signals from the time when each noise component of the frequency spectrum signal Se has been removed until a specific time later. The elimination width expanding unit 60 outputs the frequency spectrum signal Sf from which the reverberation noise P3E has been removed to the similarity filter unit 70.

[0075] The similarity filter unit 70 receives the wheel detection sensor signal X2 sent from the wheel detection sensor 2. The similarity filter unit 70 calculates the speed of the vehicle 4 from the wheel detection sensor signal X2, and calculates the time it takes for the wheel to make one revolution from the speed of the vehicle 4.

[0076] The similarity filter unit 70 calculates a frequency spectrum signal Sg from which the non-periodic noise N1 has been removed, based on the time for one revolution of the wheel and the frequency spectrum signal Sf (step S70). Specifically, the similarity filter unit 70 applies a filter to the frequency spectrum signal Sf so as to emphasize a signal similar to a signal at a time with a time difference of one revolution of the front and rear wheels for each time, and to reduce the strength of the signal when there is no similar signal.

[0077] The similarity filter unit 70 outputs the frequency spectrum signal Sg from which the non-periodic noise N1 has been removed to the feature calculation unit 81A. In addition, the similarity filter unit 70 calculates a wheel detection output indicating the time when the wheel passed the arrangement position of the wheel detection sensor 2 based on the wheel detection sensor signal X2, and outputs the wheel detection output to the output unit 90.

[0078] The feature amount calculation unit 81A calculates a time signal Sh representing the presence or absence of wheel tread abnormality at each time from the frequency spectrum signal Sg, and judges the presence or absence of wheel tread abnormality detection based on the time signal Sh (step S81). Specifically, the feature amount calculation unit 81A obtains a time signal Sh representing the presence or absence of wheel tread abnormality at each time by calculating a value obtained by dividing the sum of the absolute values ​​of the signals in the second frequency band by the sum of the absolute values ​​of the signals in frequency bands other than the second frequency band for each time of the frequency spectrum signal Sg. The feature amount calculation unit 81A also outputs the time signal Sh to the abnormality type judgment unit 82A.

[0079] The abnormality type determination unit 82A compares the time signal Sh with a preset threshold value to determine whether or not a wheel tread abnormality has been detected. The abnormality type determination unit 82A determines that a wheel tread abnormality exists when the time signal Sh is greater than the threshold value. The abnormality type determination unit 82A then determines the size and depth of the tread abnormality from the time when the time signal Sh exceeded the threshold value, the difference between the time signal Sh and the threshold value, the total length of the time when the time signal Sh exceeded the threshold value within a certain time frame, and the like, for the time when the wheel tread abnormality was determined to exist, and determines the type of the abnormality (step S82). The abnormality type determination unit 82A outputs the tread abnormality detection determination result to the output unit 90. The output unit 90 outputs the tread abnormality detection determination result and the wheel detection output to the display unit 91. The display unit 91 displays the tread abnormality detection determination result and the wheel detection output (step S90).

[0080] Thus, in the first embodiment, the railway wheel tread abnormality detection system 1A detects a wheel tread abnormality based on the vibration sensor signal X1 sent from the vibration sensor 3 installed on the rail 5. In this case, the railway wheel tread abnormality detection system 1A can record the abnormal wheel tread vibration only at the time when a wheel on which a wheel tread abnormality has occurred passes near the installation position of the vibration sensor 3. Even in this case, the railway wheel tread abnormality detection system 1A includes the independent component decomposition unit 41A and the independent component removal unit 42A, and therefore can detect vibrations caused by wheel tread abnormalities while preventing erroneous detection due to noise caused by rail joints, etc.

[0081] That is, even if the number of abnormal wheel tread vibrations included in the data of the vibration sensor signal X1 is small, the railway wheel tread abnormality detection system 1A can accurately detect wheel tread abnormalities because the independent component decomposition unit 41A calculates an independent component signal for the normalized frequency spectrum signal Sc and the independent component removal unit 42A removes noise based on the independent component signal. In this way, the railway wheel tread abnormality detection system 1A does not need to suppress erroneous detection based on the agreement between the number of shock waves at a specific time and the wheel rotation speed, and can accurately detect wheel tread abnormalities because the independent component decomposition unit 41A and the independent component removal unit 42A suppress erroneous detection.

[0082] As described above, according to the first embodiment, the railway wheel tread abnormality detection system 1A detects wheel tread abnormalities based on the vibration sensor signals X1 sent from the vibration sensors 3 installed on the rails 5, making it possible to reduce the number of vibration sensors 3 required for detecting wheel tread abnormalities. In other words, if the vibration sensors 3 are installed on the vehicle 4 side, the same number of vibration sensors 3 are required as the number of wheels for which wheel tread abnormalities are to be detected, but the railway wheel tread abnormality detection system 1A of the first embodiment makes it possible to reduce the number of vibration sensors 3 arranged.

[0083] In addition, the railway wheel tread abnormality detection system 1A can accurately detect wheel tread abnormalities because the independent component decomposition unit 41A calculates an independent component signal for the normalized frequency spectrum signal Sc, and the independent component removal unit 42A removes noise based on the independent component signal.

[0084] Therefore, the railway wheel tread abnormality detection system 1A is capable of accurately detecting wheel tread abnormalities at low cost even when detecting wheel tread abnormalities for a large number of wheels.

[0085] Embodiment 2 Next, a second embodiment will be described with reference to FIG. 14. In the second embodiment, another form of the independent component decomposition unit 41A will be described. In the first embodiment, the independent component decomposition unit 41A decomposes the signal using independent component analysis, but in the second embodiment, the independent component decomposition unit 41A determines whether or not the signal norm at each time is a vibration by threshold processing, and decomposes the vibration signal that is generated independently. Note that, among the components included in the railway wheel tread abnormality detection system 1A, the components other than the independent component decomposition unit 41A execute the same processing as in the first embodiment, and therefore the description thereof will be omitted.

[0086] Fig. 14 is a diagram illustrating an example of a norm calculated by an independent component decomposition unit of the railway wheel tread abnormality detection system according to the embodiment 2. The horizontal axis of the graph illustrated in Fig. 14 represents time, and the vertical axis represents the norm.

[0087] 14 shows norms obtained when the signal elements of the normalized frequency spectrum signal group Scn are calculated by the independent component decomposition unit 41A. The independent component decomposition unit 41A calculates the norm at each time by calculating the sum of the absolute values ​​of the signal strengths of each frequency. The independent component decomposition unit 41A decomposes the frequency spectrum signal group Scn into independent component signals by performing threshold processing on each signal element for which the norm has been calculated. For example, the independent component decomposition unit 41A decomposes the frequency spectrum signal Sc1 into the independent component signals Sd1a to Sd1d shown in FIGS. 5 to 8 by extracting signal elements that are greater than a threshold from among the signal elements for which the norm has been calculated.

[0088] Specifically, when the extracted frequency spectrum signal group Scn is input, the independent component decomposition unit 41A of the second embodiment calculates the independent component signal group Sdn by extracting only the time when the norm of all frequencies exceeds a first threshold value Th1 for each signal element (frequency spectrum signals Sc1, Sc2, Sc3, . . . , ScN). The independent component decomposition unit 41A outputs the extracted frequency spectrum signal group Scn and the independent component signal group Sdn to the independent component removal unit 42A.

[0089] In this way, in the second embodiment, the independent component decomposition unit 41A determines whether or not the norm of the frequency spectrum signal group Scn at each time is a vibration by threshold processing, and decomposes the independently occurring vibration signal into independent component signals. This enables the railway wheel tread abnormality detection system 1A to accurately detect wheel tread abnormalities with a small number of vibration sensors 3, as in the first embodiment.

[0090] Embodiment 3 Next, a third embodiment will be described with reference to Figs. 15 to 19. In the third embodiment, another form of the independent component removal unit 42A will be described. In the first embodiment, the independent component removal unit 42A removes components other than the abnormal wheel tread vibration by using the AIC. In the third embodiment, however, the independent component removal unit 42A removes components other than the abnormal wheel tread vibration by using the difference in the distribution of the frequency spectrum between the vibration signal of the wheel tread abnormality and the vibration signal other than this signal. Note that, among the components included in the railway wheel tread abnormality detection system 1A, the components other than the independent component removal unit 42A execute the same processing as in the first embodiment, and therefore the description thereof will be omitted.

[0091] Fig. 15 is a diagram illustrating an example of a first frequency set when the independent component removal unit of the railway wheel tread abnormality detection system according to the third embodiment calculates signal elements of a frequency spectrum signal group. The horizontal axis of the graph illustrated in Fig. 15 represents time, and the vertical axis represents frequency.

[0092] As explained in Figure 4 of embodiment 1, the frequency spectrum of the vibration signal of the wheel tread abnormality is distributed in the low frequency band, whereas the frequency spectrum of vibration signals other than this vibration signal is widely distributed from the low frequency band to the high frequency band.

[0093] The independent component removal unit 42A receives the extracted frequency spectrum signal group Scn and independent component signal group Sdn from the independent component decomposition unit 41A. The independent component removal unit 42A calculates a frequency spectrum signal group Sen in which noise components are removed from the frequency spectrum signal group Scn based on a first frequency band F1 defined by a preset threshold value. The first frequency band F1 is the entire frequency range (frequency region) equal to or higher than a preset threshold value. This threshold value is set in advance by the user to be a value greater than the frequencies in which vibration signals of wheel tread abnormalities are distributed.

[0094] The independent component remover 42A selects a high frequency band that does not include peaks P4 and P5, which are vibration signals of wheel tread abnormality, as a first frequency band F1 based on a preset threshold value. The independent component remover 42A calculates the norm in the first frequency band F1 of the signal elements of the independent component signal group Sdn corresponding to each signal element of the frequency spectrum signal group Scn.

[0095] Here, the norm calculated by the independent component remover 42A based on the frequency spectrum signal group Scn and the independent component signal group Sdn will be described. Here, the case where the independent component remover 42A calculates the norm in the first frequency band F1 of the signal elements of the independent component signal Sd1 corresponding to the frequency spectrum signal Sc1 shown in FIG.

[0096] Fig. 16 is a diagram illustrating an example of the norm of the first peak calculated by the independent component removal unit of the railway wheel tread abnormality detection system according to the third embodiment. Fig. 17 is a diagram illustrating an example of the norm of the second peak calculated by the independent component removal unit of the railway wheel tread abnormality detection system according to the third embodiment. Fig. 18 is a diagram illustrating an example of the norm of the third peak calculated by the independent component removal unit of the railway wheel tread abnormality detection system according to the third embodiment. Fig. 19 is a diagram illustrating an example of the norm of the reverberation noise of the third peak calculated by the independent component removal unit of the railway wheel tread abnormality detection system according to the third embodiment.

[0097] The horizontal axis of each graph in Figures 16 to 19 is time, and the vertical axis is norm. Independent component remover 42A calculates the norms shown in Figures 16 to 19 for independent component signals Sd1a, Sd1b, Sd1c, and Sd1d shown in Figures 5 to 8. In Figures 16 to 18, the first peak is peak P1, the second peak is peak P2, and the third peak is peak P3.

[0098] The norms of the peaks P1 to P3 shown in Fig. 16 to Fig. 18 correspond to the peaks P1 to P3 shown in Fig. 15. The norm shown in Fig. 16 is the norm of the peak P1 in the first frequency band F1, the norm shown in Fig. 17 is the norm of the peak P2 in the first frequency band F1, and the norm shown in Fig. 18 is the norm of the peak P3 in the first frequency band F1. That is, Figs. 16 to 18 correspond to the norms of the peaks P1 to P3 of the joint vibration in the first frequency band F1. Note that the norm in the first frequency band F1 shown in Fig. 18 does not include the norm of the reverberation noise P3E of the peak P3. The norm in the first frequency band F1 shown in Fig. 19 is the norm of the reverberation noise P3E of the peak P3.

[0099] The independent component removal unit 42A extracts only the peaks P1 to P3 by performing threshold processing on the norms shown in Figures 16 to 19. Specifically, the independent component removal unit 42A calculates the frequency spectrum signal Se1 shown in Figure 8 by removing frequency spectrum signals having a norm larger than a threshold Th2, which is a second threshold, from the frequency spectrum signal Sc1. The threshold Th2 is a value smaller than the norm of the peaks P1 to P3 and larger than the norm of the reverberation noise P3E.

[0100] In this manner, the independent component removal unit 42A removes components whose norms in the first frequency band F1 exceed the threshold value Th2 from among the signal elements of the independent component signal group Sdn corresponding to each signal element of the frequency spectrum signal group Scn, thereby obtaining a frequency spectrum signal group Sen from which noise components have been removed. The independent component removal unit 42A outputs the frequency spectrum signal group Sen from which noise components have been removed to the data combination unit 50.

[0101] In this way, in the third embodiment, the independent component removal unit 42A removes signals in the first frequency band F1 whose norm is greater than the threshold value Th2 from the frequency spectrum signal Sc1. As a result, the railway wheel tread abnormality detection system 1A of the third embodiment can obtain the frequency spectrum signal Se1 from which the noise components shown in Fig. 8 have been removed, similar to the railway wheel tread abnormality detection system 1A of the first embodiment. Therefore, the railway wheel tread abnormality detection system 1A can accurately detect wheel tread abnormalities using a small number of vibration sensors 3, similar to the first embodiment.

[0102] Embodiment 4 Next, a fourth embodiment will be described with reference to Fig. 20 to Fig. 27. In the fourth embodiment, the railway wheel tread abnormality detection system calculates a time signal limited to a first frequency band F1 capable of detecting vibrations caused by rail joints, and a time signal limited to a second frequency band F2 capable of detecting both vibrations caused by rail joints and vibrations caused by wheel tread abnormalities. The railway wheel tread abnormality detection system then calculates a time signal from which noise components have been removed for the second frequency band F2 from the time signal limited to the first frequency band F1 and the time signal limited to the second frequency band F2, and compares this time signal with a threshold value to determine whether or not a tread abnormality has been detected.

[0103] Fig. 20 is a diagram showing a configuration of a railway wheel tread abnormality detection system according to embodiment 4. Among the components in Fig. 20, components that achieve the same functions as those in the railway wheel tread abnormality detection system 1A according to embodiment 1 shown in Fig. 1 are given the same reference numerals, and duplicated explanations will be omitted.

[0104] The railway wheel tread abnormality detection system 1B includes a frequency analysis unit 10B, a joint vibration elimination unit 40B, a elimination width expansion unit 60, a similarity filter unit 70, a tread abnormality detection unit 80B, an output unit 90, and a display unit 91. Note that the display unit 91 and the railway wheel tread abnormality detection system 1B may be configured separately.

[0105] The seam vibration elimination section 40B has an independent component decomposition section 41 B and an independent component elimination section 42 B. The frequency analysis section 10B is connected to the vibration sensor 3 and receives the vibration sensor signal X1 sent from the vibration sensor 3.

[0106] The frequency analysis unit 10B calculates a time signal Sbb1 limited to a first frequency band F1 capable of detecting vibrations caused by rail joints, based on the vibration sensor signal X1. The frequency analysis unit 10B also calculates a time signal Sbb2 limited to a second frequency band F2 capable of detecting both vibrations caused by rail joints and vibrations caused by wheel tread abnormalities, based on the vibration sensor signal X1. The first frequency band F1 is a high frequency band including the frequency of vibrations caused by rail joints. The second frequency band F2 is a low frequency band lower than the first frequency band F1, including the frequency of vibrations caused by rail joints and vibrations caused by wheel tread abnormalities. In the fourth embodiment, the time signals Sbb1 and Sbb2 are first time signals.

[0107] The frequency analysis unit 10B calculates a time signal Sbb1 limited to a first frequency band F1 by applying a high-pass filter (HPF) or a band-pass filter (BPF) to the vibration sensor signal X1.

[0108] Moreover, the frequency analysis unit 10B calculates a time signal Sbb2 limited to a second frequency band F2 by applying a low-pass filter (LPF) or a band-pass filter to the vibration sensor signal X1.

[0109] The frequency analysis unit 10B outputs a time signal Sbb1 limited to the first frequency band F1 and a time signal Sbb2 limited to the second frequency band F2 to the independent component decomposition unit 41B.

[0110] Fig. 21 is a diagram illustrating an example of a time signal limited to a first frequency band calculated by a frequency analysis unit of the railway wheel tread abnormality detection system according to the fourth embodiment. Fig. 22 is a diagram illustrating an example of a time signal limited to a second frequency band calculated by a frequency analysis unit of the railway wheel tread abnormality detection system according to the fourth embodiment.

[0111] Fig. 21 shows a time signal Sbb1 calculated by the frequency analysis unit 10B, and Fig. 22 shows a time signal Sbb2 calculated by the frequency analysis unit 10B. The horizontal axis of each graph in Fig. 21 and Fig. 22 represents time, and the vertical axis represents vibration amplitude.

[0112] The time signal Sbb1 shown in FIG. 21 includes components of the first frequency band F1 of peaks P1 to P3, which are joint vibrations, and the time signal Sbb2 shown in FIG. 22 includes components of the second frequency band F2 of peaks P1 to P3 in addition to peaks P4 and P5, which are abnormal wheel tread vibrations.

[0113] In FIG. 21, the component of the first frequency band F1 of peak P1 is indicated by the first frequency component FH1, the component of the first frequency band F1 of peak P2 is indicated by the first frequency component FH2, and the component of the first frequency band F1 of peak P3 is indicated by the first frequency component FH3.

[0114] 22, the component of the second frequency band F2 of peak P1 is indicated by a second frequency component FL1, the component of the second frequency band F2 of peak P2 is indicated by a second frequency component FL2, and the component of the second frequency band F2 of peak P3 is indicated by a second frequency component FL3. Also, in FIG. 22, the component of the second frequency band F2 of peak P4 is indicated by a second frequency component FL4, and the component of the second frequency band F2 of peak P5 is indicated by a second frequency component FL5.

[0115] When a time signal Sbb1 limited to the first frequency band F1 is input, the independent component decomposition unit 41B calculates an independent component signal Sdd1 by extracting only the time when the amplitude (signal strength) exceeds a specific threshold (specific value) from the time signal Sbb1. When a time signal Sbb2 limited to the second frequency band F2 is input, the independent component decomposition unit 41B calculates an independent component signal Sdd2 by extracting only the signal at the same time as the time extracted when calculating the independent component signal Sdd1 from the time signal Sbb2.

[0116] Here, the process executed by the independent component decomposition unit 41B will be described. Fig. 23 is a diagram for explaining an example of a threshold value set by the independent component decomposition unit of the railway wheel tread abnormality detection system according to the fourth embodiment. Fig. 24 is a diagram showing an example of an independent component signal extracted by the independent component decomposition unit of the railway wheel tread abnormality detection system according to the fourth embodiment from a time signal limited to a first frequency band. Fig. 25 is a diagram showing an example of an independent component signal extracted by the independent component decomposition unit of the railway wheel tread abnormality detection system according to the fourth embodiment from a time signal limited to a second frequency band.

[0117] The horizontal axis of each graph in Fig. 23 to Fig. 25 is time, and the vertical axis is vibration amplitude. The graph shown in Fig. 23 corresponds to the graph shown in Fig. 21. Fig. 23 shows a time signal Sbb1 calculated by the frequency analysis unit 10B, and thresholds Th3 and Th4 used by the independent component decomposition unit 41B. The graph shown in Fig. 24 corresponds to the graph shown in Fig. 23, and the graph shown in Fig. 25 corresponds to the graph shown in Fig. 22.

[0118] The threshold value Th3 is a positive value, and the threshold value Th4 is a negative value. The threshold values ​​Th3 and Th4 have the same absolute value but different signs, positive and negative.

[0119] The independent component decomposition unit 41B compares the time signal Sbb1 limited to the first frequency band F1 with thresholds Th3 and Th4, and extracts an independent component signal Sdd1, which is a time signal larger than the threshold Th3 or smaller than the threshold Th4, from the time signal Sbb1. The independent component decomposition unit 41B extracts a time signal of a specific time width from the time signal Sbb1 larger than the threshold Th3 or smaller than the threshold Th4.

[0120] FIG. 24 shows a first frequency component FH1 of peak P1, a first frequency component FH2 of peak P2, and a first frequency component FH3 of peak P3 as the independent component signal Sdd1 extracted by the independent component decomposition section 41B.

[0121] The independent component decomposition unit 41B extracts a time signal having the same time as the first frequency components FH1-FH3 from the time signal Sbb2 limited to the second frequency band F2. In Fig. 25, the second frequency component FL1 of the peak P1, the second frequency component FL2 of the peak P2, and the second frequency component FL3 of the peak P3 are shown as the independent component signal Sdd2 extracted by the independent component decomposition unit 41B. In the fourth embodiment, the independent component signal Sdd1 is the first limited signal, and the independent component signal Sdd2 is the second limited signal.

[0122] The independent component decomposition unit 41B outputs a time signal Sbb1 limited to the first frequency band F1, a time signal Sbb2 limited to the second frequency band F2, and the independent component signals Sdd1 and Sdd2 to the independent component removal unit 42B.

[0123] When the independent component removal unit 42B receives the time signal Sbb1 limited to the first frequency band F1, the time signal Sbb2 limited to the second frequency band F2, and the independent component signals Sdd1 and Sdd2, it removes signal elements of the independent component signal Sdd1 until the noise components are sufficiently removed from the time signal Sbb1. In this way, the independent component removal unit 42B calculates a time signal See1 from which the noise components are removed for the first frequency band F1. The time when the noise components are sufficiently removed is when the AIC of the removed time signal becomes larger when L (L is a natural number) noise components are removed from the time signal Sbb1 than the AIC when (L-1) noise components are removed from the time signal Sbb1.

[0124] Similar to the independent component removal section 42A, the independent component removal section 42B removes noise components from the independent component signal Sdd1 in ascending order of norm in the first frequency band F1.

[0125] The independent component remover 42B removes, from the time signal Sbb2, an independent component signal Sdd2 corresponding to the time of the independent component signal Sdd1 removed from the time signal Sbb1, to calculate a time signal See2 from which a noise component has been removed for the second frequency band F2. In the fourth embodiment, the time signal See2 is the second time signal.

[0126] Although the method in which the independent component removal unit 42B uses AIC as a method for removing noise components has been described here, the independent component removal unit 42B may also use a method for removing all components of the independent component signal Sdd2 from the time signal Sbb2 that correspond to the time at which the independent component signal Sdd1 exceeds a specific threshold value. The independent component removal unit 42B outputs the time signal See2 from which the noise components have been removed for the second frequency band F2 to the removal width expansion unit 60.

[0127] Fig. 26 is a diagram showing an example of a time signal obtained by removing noise components from a time signal limited to the second frequency band by the independent component removal unit of the railway wheel tread abnormality detection system according to the fourth embodiment. The horizontal axis of the graph in Fig. 26 represents time, and the vertical axis represents vibration amplitude. The graph shown in Fig. 26 corresponds to the graphs shown in Figs. 21 to 25.

[0128] 26 shows a time signal See2 from which noise components have been removed, which is obtained when the independent component remover 42B executes arithmetic processing on the time signal Sbb2 and the independent component signals Sdd1 and Sdd2. In the time signal See2, the time signals of peaks P1 to P3, which are joint vibrations, have been removed.

[0129] When the time signal See2 from which the noise components in the second frequency band F2 have been removed is input, the elimination width expanding unit 60 calculates a time signal Sff (not shown) from which the reverberation noise P3E has been removed by also removing a signal from the time signal See2 a specific time after the time at which each noise component has been removed. The elimination width expanding unit 60 outputs the time signal Sff from which the reverberation noise P3E has been removed to the similarity filter unit 70.

[0130] When the similarity filter unit 70 receives the wheel detection sensor signal X2 from the wheel detection sensor 2, it calculates the speed of the vehicle 4 from the wheel detection sensor signal X2 and calculates the time it takes for the wheel to make one revolution from the speed of the vehicle 4.

[0131] Furthermore, when the time signal Sff from which the reverberation noise P3E has been removed is input, the similarity filter unit 70 applies a filter to the time signal Sff such that similar signals are emphasized when there are similar signals between signals having a time difference of one revolution of the front and rear wheels, and the strength is reduced (removed) when there are no similar signals. That is, the similarity filter unit 70 increases the strength of the signals before one revolution of the wheel and after one revolution of the wheel among the time signal Sff if they are similar signals, and reduces the strength if they are not similar signals. The similarity filter unit 70 of the fourth embodiment emphasizes similar signals based on the cosine similarity of one revolution of the front and rear wheels, similar to the similarity filter unit 70 of the first embodiment.

[0132] In this way, the similarity filter unit 70 strengthens or weakens the signal strength based on whether the signal before the wheel makes one rotation and the signal after the wheel makes one rotation are similar signals, so that it is possible to calculate a time signal Sgg (not shown) from which the non-periodic noise N1 that could not be removed by the processing up to the removal width expansion unit 60 has been removed. The similarity filter unit 70 outputs the time signal Sgg from which the non-periodic noise N1 has been removed to the tread abnormality detection unit 80B. In addition, the similarity filter unit 70 calculates a wheel detection output indicating the time when the wheel passed the arrangement position of the wheel detection sensor 2 based on the wheel detection sensor signal X2, and outputs the wheel detection output to the output unit 90.

[0133] When the time signal Sgg from which the non-periodic noise N1 has been removed is input, the tread abnormality detection unit 80B compares the time signal Sgg at each time with a preset threshold value to determine whether or not a tread abnormality has been detected. The tread abnormality detection unit 80B determines that there is a wheel tread abnormality when the time signal Sgg is greater than the threshold value. The tread abnormality detection unit 80B outputs the tread abnormality detection judgment result to the output unit 90. The output unit 90 outputs the tread abnormality detection judgment result sent from the tread abnormality detection unit 80B and the wheel detection output sent from the similarity filter unit 70 to the display unit 91. The display unit 91 displays the tread abnormality detection judgment result and the wheel detection output.

[0134] Next, an operation process procedure of the railway wheel tread abnormality detection system 1B will be described. Fig. 27 is a flowchart showing the operation process procedure of the railway wheel tread abnormality detection system according to the fourth embodiment. Fig. 27 shows the detection process procedure of a wheel tread abnormality by the railway wheel tread abnormality detection system 1B.

[0135] The frequency analysis unit 10B receives the vibration sensor signal X1 sent from the vibration sensor 3. The frequency analysis unit 10B calculates a time signal Sbb1 limited to a first frequency band F1 and a time signal Sbb2 limited to a second frequency band F2 from the vibration sensor signal X1 (step S110). Specifically, the frequency analysis unit 10B calculates the time signal Sbb1 by applying a high-pass filter or a band-pass filter to the vibration sensor signal X1. The frequency analysis unit 10B also calculates the time signal Sbb2 by applying a low-pass filter or a band-pass filter to the vibration sensor signal X1. The frequency analysis unit 10B outputs the time signals Sbb1 and Sbb2 to the independent component decomposition unit 41B.

[0136] The independent component decomposition unit 41B extracts an independent component signal Sdd1 from the time signal Sbb1 limited to the first frequency band F1, and extracts an independent component signal Sdd2 from the time signal Sbb2 limited to the second frequency band F2 (step S141). The independent component decomposition unit 41B outputs the time signal Sbb1 limited to the first frequency band F1, the time signal Sbb2 limited to the second frequency band F2, and the independent component signals Sdd1 and Sdd2 to the independent component removal unit 42B.

[0137] The independent component remover 42B calculates a time signal See2 from which noise components have been removed for the second frequency band F2, based on the time signal Sbb1 limited to the first frequency band F1, the time signal Sbb2 limited to the second frequency band F2, and the independent component signals Sdd1 and Sdd2 (step S142). The independent component remover 42B outputs the time signal See2 to the removal width expander 60.

[0138] The removal width expanding unit 60 calculates a time signal Sff by removing the reverberation noise P3E from the time signal See2 (step S160). The removal width expanding unit 60 outputs the time signal Sff to the similarity filter unit .

[0139] The similarity filter unit 70 calculates a time signal Sgg from which the non-periodic noise N1 has been removed, based on the time for the wheel to rotate once and the time signal Sff (step S170). The similarity filter unit 70 outputs the time signal Sgg from which the non-periodic noise N1 has been removed to the tread abnormality detection unit 80B. The similarity filter unit 70 also calculates a wheel detection output indicating the time when the wheel passed the arrangement position of the wheel detection sensor 2, based on the wheel detection sensor signal X2, and outputs the wheel detection output to the output unit 90.

[0140] The tread abnormality detection unit 80B compares the time signal Sgg at each time with a preset threshold value to determine whether or not a tread abnormality has been detected (step S180). Specifically, the tread abnormality detection unit 80B determines that there is a wheel tread abnormality when the time signal Sgg is greater than the threshold value. The tread abnormality detection unit 80B outputs the tread abnormality detection result to the output unit 90.

[0141] The output unit 90 outputs the tread abnormality detection determination result and the wheel detection output to the display unit 91. The display unit 91 displays the tread abnormality detection determination result and the wheel detection output (step S190).

[0142] Next, the hardware configuration of the railway wheel tread abnormality detection systems 1A and 1B will be described. The railway wheel tread abnormality detection systems 1A and 1B are realized by a processing circuit. This processing circuit may be a processor and memory that executes a program stored in a memory, or may be dedicated hardware. The processing circuit is also called a control circuit.

[0143] 28 is a diagram showing an example of the configuration of a processing circuit when the processing circuit included in the railway wheel tread abnormality detection system according to the first to fourth embodiments is realized by a processor and a memory. Since the railway wheel tread abnormality detection systems 1A and 1B have the same hardware configuration, the hardware configuration of the railway wheel tread abnormality detection system 1A will be described below.

[0144] The processing circuit 150 shown in FIG. 28 is a control circuit and includes a processor 151 and a memory 152. When the processing circuit 150 is configured with the processor 151 and the memory 152, each function of the processing circuit 150 is realized by software, firmware, or a combination of software and firmware. The software or firmware is written as a program and stored in the memory 152. In the processing circuit 150, the processor 151 reads and executes the program stored in the memory 152 to realize each function. That is, the processing circuit 150 includes a memory 152 for storing a railway wheel tread abnormality detection program that results in the processing of the railway wheel tread abnormality detection system 1A being executed. This railway wheel tread abnormality detection program can also be said to be a program for causing the railway wheel tread abnormality detection system 1A to execute each function realized by the processing circuit 150. This railway wheel tread abnormality detection program may be provided by a storage medium in which the program is stored, or may be provided by other means such as a communication medium.

[0145] The railway wheel tread abnormality detection program executed by the railway wheel tread abnormality detection system 1A has a modular configuration including a frequency analysis unit 10A, a normalization unit 20, a data extraction unit 30, a joint vibration elimination unit 40A, a data combination unit 50, a elimination width expansion unit 60, a similarity filter unit 70, a tread abnormality detection unit 80A, and an output unit 90, which are loaded onto the main memory device and generated on the main memory device.

[0146] The railway wheel tread abnormality detection program executed by the railway wheel tread abnormality detection system 1B has a modular configuration including a frequency analysis unit 10B, a joint vibration elimination unit 40B, a elimination width expansion unit 60, a similarity filter unit 70, a tread abnormality detection unit 80B, and an output unit 90, which are loaded onto the main memory device and generated on the main memory device.

[0147] Here, the processor 151 is, for example, a CPU (Central Processing Unit), a processing device, an arithmetic device, a microprocessor, a microcomputer, or a DSP (Digital Signal Processor), etc. Also, the memory 152 is, for example, a non-volatile or volatile semiconductor memory such as a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable ROM), an EEPROM (Electrically EPROM), a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, or a DVD (Digital Versatile Disc), etc.

[0148] Fig. 29 is a diagram showing an example of a processing circuit when the processing circuit included in the railway wheel tread abnormality detection system according to the first to fourth embodiments is configured with dedicated hardware. The processing circuit 153 shown in Fig. 29 corresponds to, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination of these.

[0149] The processing circuits 150, 153 may be partially realized by dedicated hardware and partially realized by software or firmware. In this way, the processing circuits 150, 153 can realize the above-mentioned functions by dedicated hardware, software, firmware, or a combination of these. The railway wheel tread abnormality detection system 1A may be realized by one processing circuit or multiple processing circuits.

[0150] Thus, in the fourth embodiment, the independent component decomposition unit 41B calculates a time signal Sbb1 limited to a first frequency band F1 capable of detecting vibrations caused by rail joints, and a time signal Sbb2 limited to a second frequency band F2 capable of detecting both vibrations caused by rail joints and vibrations caused by wheel tread abnormalities. Then, the independent component removal unit 42B removes the independent component signal Sdd2 corresponding to the time of the independent component signal Sdd1 removed from the time signal Sbb1 from the time signal Sbb2, thereby calculating a time signal See2 from which noise components have been removed for the second frequency band F2. Furthermore, the independent component removal unit 42B compares the time signal See2 with a threshold value to determine whether or not a wheel tread abnormality has been detected. Therefore, the railway wheel tread abnormality detection system 1B can accurately detect wheel tread abnormalities with a small number of vibration sensors 3, as in the first embodiment.

[0151] The configurations shown in the above embodiments are merely examples, and may be combined with other known technologies, or the embodiments may be combined with each other. Also, parts of the configurations may be omitted or modified without departing from the spirit of the invention.

[0152] Various aspects of the present disclosure are summarized below as appendices.

[0153] (Appendix 1) a frequency analysis unit that converts a vibration sensor signal indicating information on vibrations measured by a vibration sensor installed on the rail into a first time signal indicating a signal strength for each frequency band; a joint vibration elimination unit that calculates a second time signal by eliminating a signal of vibration caused by a rail joint, which is a joint of the rail, from a corresponding signal corresponding to the first time signal; a wheel tread abnormality detection unit that determines, from the second time signal, whether or not there is a wheel tread abnormality occurring on a wheel of a vehicle traveling on the rail; An output unit that outputs a determination result of the tread abnormality detection unit; Equipped with The joint vibration elimination unit includes: extracting a third time signal including a frequency of vibration caused by the rail joint from the corresponding signal, and calculating the second time signal by removing the third time signal from the corresponding signal when a signal strength of the third time signal exceeds a specific value. A railway wheel tread abnormality detection system characterized by the above. (Appendix 2) A normalization unit that normalizes a scale of noise other than the vibration caused by the rail joint based on the first time signal, The joint vibration elimination unit includes: calculating a second time signal obtained by removing a signal of vibration caused by the rail joint from the corresponding signal corresponding to the first time signal having the noise scale normalized; 2. A railway wheel tread abnormality detection system according to claim 1. (Appendix 3) The normalization unit is where m is a preset parameter, calculating a scale of the noise by dividing m% of the smallest signal values ​​of the first time signal by the value at the m% point of a distribution to which noise other than the vibration caused by the rail joint follows, and calculating the first time signal with a normalized scale of the noise by dividing the first time signal by the calculated scale of the noise. 3. A railway wheel tread abnormality detection system according to claim 2. (Appendix 4) a removal width expansion unit that removes a signal a specific time after the time when the third time signal is removed from the second time signal, thereby removing reverberation noise caused by vibration due to the rail joint; a similarity filter unit that, when receiving a wheel detection sensor signal indicating that the wheel has been detected from a wheel detection sensor that detects the wheel, removes non-periodic noise, which is a signal other than a rotation period of the wheel, from the second time signal from which the reverberation noise has been removed, based on the wheel detection sensor signal; Further equipped with The tread abnormality detection unit is determining whether or not there is an abnormality in the wheel tread from the second time signal from which the reverberation noise and the non-periodic noise have been removed; 4. A railway wheel tread abnormality detection system according to any one of claims 1 to 3. (Appendix 5) The similarity filter unit includes: a speed of the vehicle is calculated from the wheel detection sensor signal, and a time taken for the wheel to make one revolution is calculated from the speed; a similarity between a signal at each time point of the second time signal from which the reverberation noise has been removed and a signal having a time difference corresponding to one revolution of the wheel is calculated; and the non-periodic noise is removed by emphasizing signals having a similarity equal to or greater than a specific value. 5. A railway wheel tread abnormality detection system according to claim 4. (Appendix 6) A data extracting unit extracts the corresponding signal at specific time intervals to calculate a time signal group including a plurality of signal elements, The seam vibration elimination unit calculates the second time signal for each of the time signal groups. 6. A railway wheel tread abnormality detection system according to any one of claims 1 to 5. (Appendix 7) The joint vibration elimination unit includes: an independent component decomposition unit that decomposes the corresponding signal into independent component signals that are signals of independent vibration components; an independent component remover that calculates the second time signal by removing the independent component signal from the corresponding signal; having 7. A railway wheel tread abnormality detection system according to any one of claims 1 to 6. (Appendix 8) The independent component decomposition unit decomposing said corresponding signals into said independent component signals using independent component analysis; 8. The railway wheel tread abnormality detection system according to claim 7. (Appendix 9) The independent component decomposition unit extracting, as the independent component signal, a signal whose norm of the independent component signal is greater than a first threshold, thereby decomposing the corresponding signal into the independent component signals; 8. The railway wheel tread abnormality detection system according to claim 7. (Appendix 10) The independent component decomposition unit decomposing the independent component signals until an Akaike information criterion for a difference between a sum of M independent component signals and the corresponding signal is minimized, where M is a natural number; 10. The railway wheel tread abnormality detection system according to any one of claims 7 to 9. (Appendix 11) The independent component removal unit removing the independent component signals until the Akaike information criterion of the L independent component signals is minimized, where L is a natural number; 11. The railway wheel tread abnormality detection system according to any one of claims 7 to 10. (Appendix 12) The independent component removal unit removing the independent component signals whose norms are greater than a second threshold; 11. The railway wheel tread abnormality detection system according to any one of claims 7 to 10. (Appendix 13) The tread abnormality detection unit is a feature amount calculation unit that calculates a time signal representing the presence or absence of a wheel tread abnormality from the corresponding signal; an abnormality type determination unit that determines a type of wheel tread abnormality from the corresponding signal; having 2. A railway wheel tread abnormality detection system according to claim 1. (Appendix 14) The feature amount calculation unit A time signal indicating the presence or absence of a wheel tread abnormality is calculated by dividing the sum of absolute values ​​of signals having a fourth frequency or less among the corresponding signals by the sum of absolute values ​​of signals having a fourth frequency or more. 14. The railway wheel tread abnormality detection system according to claim 13. (Appendix 15) The abnormality type determination unit detecting a tread abnormality when the response signal exceeds a third threshold, and determining the size and depth of the tread abnormality from the difference between the response signal and the third threshold, the time during which the response signal exceeds the third threshold, and the sum of the time during which the response signal exceeds the third threshold within a certain time frame; 14. The railway wheel tread abnormality detection system according to claim 13. (Appendix 16) the signal strength being a magnitude of the norm of the third time signal; 16. A railway wheel tread abnormality detection system according to any one of claims 1 to 15. (Appendix 17) a frequency analysis unit that converts a vibration sensor signal indicating information on vibrations measured by a vibration sensor installed on the rail into a first time signal indicating a signal strength for each frequency band; a joint vibration elimination unit that calculates a second time signal by eliminating a signal of vibration caused by a rail joint, which is a joint of the rail, from the first time signal; a wheel tread abnormality detection unit that determines, from the second time signal, whether or not there is a wheel tread abnormality occurring on a wheel of a vehicle traveling on the rail; An output unit that outputs a determination result of the tread abnormality detection unit; Equipped with The frequency analysis unit is calculating, as the first time signal, a first limited signal limited to a first frequency band including the frequency of the vibration caused by the rail joint, and a second limited signal limited to a second frequency band capable of detecting both the frequency of the vibration caused by the rail joint and the frequency of the vibration caused by an abnormality in the wheel tread; The joint vibration elimination unit includes: calculating the second time signal by removing from the second limited signal a signal having a signal intensity that is equal to both a signal corresponding to the first limited signal and a signal corresponding to the second limited signal; A railway wheel tread abnormality detection system characterized by the above. (Appendix 18) The joint vibration elimination unit includes: extracting a first independent component signal, which is a signal at a time when the signal strength exceeds a specific value, from the first limited signal, and extracting a second independent component signal, which is a signal at the same time as the first limited signal, from the second limited signal, and removing the second independent component signal from the second limited signal, thereby calculating the second time signal. 18. The railway wheel tread abnormality detection system according to claim 17, (Appendix 19) a frequency analysis step in which the railway wheel tread abnormality detection system converts a vibration sensor signal, which indicates information on vibration measured by a vibration sensor installed on the rail, into a first time signal, which indicates signal strength for each frequency band; a joint vibration removing step in which the railway wheel tread abnormality detection system calculates a second time signal by removing a signal of vibration caused by a rail joint, which is the joint of the rail, from a corresponding signal corresponding to the first time signal; a tread abnormality detection step in which the railway wheel tread abnormality detection system determines whether or not there is a wheel tread abnormality occurring in a wheel of a vehicle running on the rail from the second time signal; an output step in which the railway wheel tread abnormality detection system outputs a determination result of the presence or absence of the wheel tread abnormality; Including, In the step of removing vibration at the joint, the railway wheel tread abnormality detection system extracts a third time signal including a frequency of vibration caused by the rail joint from the corresponding signal, and calculates the second time signal by removing the third time signal from the corresponding signal when a signal strength of the third time signal exceeds a specific value; A railway wheel tread abnormality detection method comprising: (Appendix 20) a frequency analysis step of converting a vibration sensor signal indicating information on vibration measured by a vibration sensor installed on the rail into a first time signal indicating signal strength for each frequency band; a joint vibration removing step of calculating a second time signal by removing a signal of vibration caused by a rail joint, which is a joint of the rail, from a corresponding signal corresponding to the first time signal; a wheel tread abnormality detection step of determining, from the second time signal, whether or not there is a wheel tread abnormality occurring on a wheel of a vehicle running on the rail; an output step of outputting a result of the determination of the presence or absence of an abnormality in the wheel tread; on the computer, In the step of removing vibration at the joint, extracting a third time signal including a frequency of vibration caused by the rail joint from the corresponding signal, and calculating the second time signal by removing the third time signal from the corresponding signal when a signal strength of the third time signal exceeds a specific value. A railway wheel tread abnormality detection program characterized by the above. [Explanation of symbols]

[0154] 1A, 1B Railway wheel tread abnormality detection system, 2 Wheel detection sensor, 3 Vibration sensor, 4 Vehicle, 5 Rail, 10A, 10B Frequency analysis unit, 20 Normalization unit, 30 Data extraction unit, 40A, 40B Joint vibration removal unit, 41A, 41B Independent component decomposition unit, 42A, 42B Independent component removal unit, 50 Data combination unit, 60 Removal width expansion unit, 70 Similarity filter unit, 80A, 80B Tread abnormality detection unit, 81A Feature calculation unit, 82A Anomaly type determination unit, 90 Output unit, 91 Display unit, 150, 153 Processing circuit, 151 Processor, 152 Memory, F1 First frequency band, F2 Second frequency band, FH1 to FH3 First frequency components, FL1 to FL5 Second frequency components, N1 Non-periodic noise, P1 to P5 Peak, P3E reverberation noise, Sa1, X1 vibration sensor signal, Sb, Sb1, Sc, Sc1~ScN, Se, Se1~SeN, Sf, Sg frequency spectrum signals, Sbb1, Sbb2, See1, See2, Sff, Sgg, Sh time signal, Scn, Sen frequency spectrum signal group, Sd1~SdN, Sd1a~Sd1d, Sdd1, Sdd2 independent component signals, Sdn independent component signal group, Th1~Th4 threshold, X2 wheel detection sensor signal.

Claims

1. a frequency analysis unit that converts a vibration sensor signal indicating information on vibrations measured by a vibration sensor installed on the rail into a first time signal indicating a signal strength for each frequency band; a joint vibration elimination unit that calculates a second time signal by eliminating a signal of vibration caused by a rail joint, which is a joint of the rail, from a corresponding signal corresponding to the first time signal; a wheel tread abnormality detection unit that determines, from the second time signal, whether or not there is a wheel tread abnormality occurring on a wheel of a vehicle traveling on the rail; An output unit that outputs a determination result of the tread abnormality detection unit; Equipped with The joint vibration elimination unit includes: extracting a third time signal including a frequency of vibration caused by the rail joint from the corresponding signal, and calculating the second time signal by removing the third time signal from the corresponding signal when a signal strength of the third time signal exceeds a specific value. A railway wheel tread abnormality detection system characterized by the above.

2. A normalization unit that normalizes a scale of noise other than the vibration caused by the rail joint based on the first time signal, The joint vibration elimination unit includes: calculating a second time signal obtained by removing a signal of vibration caused by the rail joint from the corresponding signal corresponding to the first time signal having the noise scale normalized; 2. The railway wheel tread abnormality detection system according to claim 1 .

3. The normalization unit is where m is a preset parameter, a scale of the noise is calculated by dividing m% of the smallest signal values ​​of the first time signal by the value of the m% point of a distribution to which noise other than the vibration caused by the rail joint follows, and the first time signal is divided by the calculated scale of the noise to calculate the first time signal with the scale of the noise normalized.

3. The railway wheel tread abnormality detection system according to claim 2 .

4. a removal width expansion unit that removes a signal a specific time after the time when the third time signal is removed from the second time signal, thereby removing reverberation noise caused by vibration due to the rail joint; a similarity filter unit that, when receiving a wheel detection sensor signal indicating that the wheel has been detected from a wheel detection sensor that detects the wheel, removes non-periodic noise, which is a signal other than a rotation period of the wheel, from the second time signal from which the reverberation noise has been removed, based on the wheel detection sensor signal; Further equipped with The tread abnormality detection unit is determining whether or not the wheel tread abnormality exists based on the second time signal from which the reverberation noise and the non-periodic noise have been removed; 2. The railway wheel tread abnormality detection system according to claim 1 .

5. The similarity filter unit includes: a speed of the vehicle is calculated from the wheel detection sensor signal, and a time taken for the wheel to make one revolution is calculated from the speed; a similarity between a signal at each time point of the second time signal from which the reverberation noise has been removed and a signal having a time difference corresponding to one revolution of the wheel is calculated; and the non-periodic noise is removed by emphasizing signals for which the similarity is equal to or greater than a specific value.

5. The railway wheel tread abnormality detection system according to claim 4.

6. A data extracting unit extracts the corresponding signal at specific time intervals to calculate a time signal group including a plurality of signal elements, the seam vibration elimination unit calculates the second time signal for each of the time signal groups.

2. The railway wheel tread abnormality detection system according to claim 1 .

7. The joint vibration elimination unit includes: an independent component decomposition unit that decomposes the corresponding signal into independent component signals that are signals of independent vibration components; an independent component remover that calculates the second time signal by removing the independent component signal from the corresponding signal; having 2. The railway wheel tread abnormality detection system according to claim 1 .

8. The independent component decomposition unit decomposing said corresponding signals into said independent component signals using independent component analysis; 8. The railway wheel tread abnormality detection system according to claim 7.

9. The independent component decomposition unit extracting, as the independent component signal, a signal whose norm of the independent component signal is greater than a first threshold, thereby decomposing the corresponding signal into the independent component signals; 8. The railway wheel tread abnormality detection system according to claim 7.

10. The independent component decomposition unit decomposing the independent component signals until an Akaike information criterion of a difference between a sum of M independent component signals and the corresponding signal is minimized, where M is a natural number; 8. The railway wheel tread abnormality detection system according to claim 7.

11. The independent component removal unit includes: removing the independent component signals until the Akaike information criterion of the L independent component signals is minimized, where L is a natural number; 8. The railway wheel tread abnormality detection system according to claim 7.

12. The independent component removal unit removing the independent component signals whose norms are greater than a second threshold; 8. The railway wheel tread abnormality detection system according to claim 7.

13. The tread abnormality detection unit is a feature amount calculation unit that calculates a time signal representing the presence or absence of a wheel tread abnormality from the corresponding signal; an abnormality type determination unit that determines a type of wheel tread abnormality from the corresponding signal; having 2. The railway wheel tread abnormality detection system according to claim 1 .

14. The feature amount calculation unit is a sum of absolute values ​​of signals having a fourth frequency or less among the corresponding signals is divided by a sum of absolute values ​​of signals having a fourth frequency or more to calculate a time signal indicating the presence or absence of an abnormality in the wheel tread; The railway wheel tread abnormality detection system according to claim 13.

15. The abnormality type determination unit a step abnormality is detected when the corresponding signal exceeds a third threshold, and the size and depth of the step abnormality are determined based on a difference between the corresponding signal and the third threshold, a time during which the corresponding signal exceeds the third threshold, and a total sum of a time during which the corresponding signal exceeds the third threshold within a certain time frame; The railway wheel tread abnormality detection system according to claim 13.

16. the signal strength being a magnitude of the norm of the third time signal; 16. A railway wheel tread abnormality detection system according to any one of claims 1 to 15.

17. a frequency analysis unit that converts a vibration sensor signal indicating information on vibrations measured by a vibration sensor installed on the rail into a first time signal indicating a signal strength for each frequency band; a joint vibration elimination unit that calculates a second time signal by eliminating a signal of vibration caused by a rail joint, which is a joint of the rail, from the first time signal; a wheel tread abnormality detection unit that determines, from the second time signal, whether or not there is a wheel tread abnormality occurring on a wheel of a vehicle traveling on the rail; An output unit that outputs a determination result of the tread abnormality detection unit; Equipped with The frequency analysis unit is calculating, as the first time signal, a first limited signal limited to a first frequency band including a frequency of the vibration caused by the rail joint, and a second limited signal limited to a second frequency band capable of detecting both the frequency of the vibration caused by the rail joint and the frequency of the vibration caused by an abnormality in the wheel tread; The joint vibration elimination unit includes: calculating the second time signal by removing from the second limited signal a signal having a signal strength that is the same as both a signal corresponding to the first limited signal and a signal corresponding to the second limited signal; A railway wheel tread abnormality detection system characterized by the above.

18. The joint vibration elimination unit includes: extracting a first independent component signal, which is a signal at a time when the signal strength exceeds a specific value, from the first limited signal, and extracting a second independent component signal, which is a signal at the same time as the time, from the second limited signal, and removing the second independent component signal from the second limited signal, thereby calculating the second time signal.

18. The railway wheel tread abnormality detection system according to claim 17.

19. a frequency analysis step in which the railway wheel tread abnormality detection system converts a vibration sensor signal indicating information of vibration measured by a vibration sensor installed on the rail into a first time signal indicating signal strength for each frequency band; a joint vibration removing step in which the railway wheel tread abnormality detection system calculates a second time signal by removing a signal of vibration caused by a rail joint, which is a joint of the rail, from a corresponding signal corresponding to the first time signal; a tread abnormality detection step in which the railway wheel tread abnormality detection system determines, from the second time signal, whether or not there is a wheel tread abnormality occurring in a wheel of a vehicle running on the rail; an output step in which the railway wheel tread abnormality detection system outputs a determination result of the presence or absence of the wheel tread abnormality; Including, In the step of removing seam vibration, the railway wheel tread abnormality detection system extracts a third time signal including a frequency of vibration caused by the rail joint from the corresponding signal, and calculates the second time signal by removing the third time signal from the corresponding signal when a signal strength of the third time signal exceeds a specific value. A railway wheel tread abnormality detection method comprising:

20. a frequency analysis step of converting a vibration sensor signal indicating information on vibrations measured by a vibration sensor installed on the rail into a first time signal indicating signal strength for each frequency band; a joint vibration removing step of calculating a second time signal by removing a signal of vibration caused by a rail joint, which is a joint of the rail, from a corresponding signal corresponding to the first time signal; a wheel tread abnormality detection step of determining, from the second time signal, whether or not there is a wheel tread abnormality occurring on a wheel of a vehicle running on the rail; an output step of outputting a result of the determination of the presence or absence of an abnormality in the wheel tread; Run the following on your computer: In the step of removing seam vibration, extracting a third time signal including a frequency of vibration caused by the rail joint from the corresponding signal, and calculating the second time signal by removing the third time signal from the corresponding signal when a signal strength of the third time signal exceeds a specific value. A railway wheel tread abnormality detection program characterized by the above.

Citation Information

Patent Citations

  • Abnormality diagnostic system

    JP2007170815A