Information processing device, information processing program, and information processing method

Abstract

To provide an information processing device capable of accurately detecting arrival timing of P waves even in the case of an earthquake having slow rising of amplitude in an earthquake motion, even if a miscellaneous vibration of a vehicle or the like is observed immediately before an earthquake motion, and even if coda waves because of an earthquake immediately before a foreshock or the like are observed.SOLUTION: An information processing device 20 includes an amplitude calculation section 21, a frequency analysis section 22, and an abnormality detection section 23. The amplitude calculation section 21 calculates amplitude (x) that changes following lapse of time from observation digital data Dg of an earth motion observed by a sensor 10. The frequency analysis section 22 calculates running spectra PS, PL as frequency characteristics in real time from the amplitude (x) by using an auto-regressive model. The abnormality detection section 23 detects abnormal P waves from the observation digital data Dg on the basis of the running spectra PS, PL.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present disclosure relates to an anomaly detection device that detects the occurrence of an anomaly that differs from normal times in a time series of observation data observed by a sensor. [Background technology]

[0002] Seismometers, which can immediately estimate damage immediately after an earthquake occurs and prevent damage before it occurs, need to detect the seismic motion caused by an earthquake in real time. In particular, when estimating the location of the epicenter to estimate damage, it is necessary to detect the exact arrival timing of the P-waves from the seismic motion.

[0003] In response to this, the technology disclosed in Non-Patent Document 1 discloses a method called the STA / LTA method, which detects a sudden rise in amplitude, as a method for detecting the arrival timing of P waves, which are the earliest waves of seismic motion that reach a seismometer. [Prior art documents] [Non-patent literature]

[0004] [Non-Patent Document 1] Naoyasu Iwata, Shunroku Yamamoto, Shunta Noda, Masahiro Korenaga. Algorithms for Estimating Earthquake Parameters and Identifying Noise for Early Earthquake Warning. Journal of the Japan Society of Civil Engineers, Proceedings of the JSCE A1 (Structural and Earthquake Engineering). 2016, Vol. 72, No. 1, pp. 133-147. Summary of the Invention [Problem to be solved by the invention]

[0005] However, in subduction-zone earthquakes such as the 2011 Tohoku Pacific Coast Earthquake, the rise in seismic amplitude is slow, which can result in the detection of P waves being delayed or even impossible. In addition, when miscellaneous vibrations from vehicles or the like are observed immediately before a seismic event, the background vibration level (LTA) rises, making it impossible to detect subsequent P waves. In addition, when coda waves from a preceding earthquake such as a foreshock are observed, the background vibration level (LTA) rises, making it impossible to detect subsequent P waves.

[0006] The present disclosure aims to provide an information processing device that can accurately detect the arrival timing of P waves, even in the case of an earthquake with a gradual rise in the amplitude of seismic motion, when miscellaneous vibrations of vehicles, etc. are observed immediately before seismic motion, or when coda waves from an earthquake immediately before a foreshock, etc. are observed. [Means for solving the problem]

[0007] The information processing device according to the present disclosure includes: an amplitude calculation unit that calculates an amplitude that changes over time from observation data of an event observed by a sensor; a frequency analysis unit that calculates a frequency characteristic from the amplitude in real time using an autoregressive model; Equipped with. Effect of the Invention

[0008] The information processing device according to the present disclosure includes a frequency analysis unit, and therefore, even in the case of an earthquake in which the rise in the amplitude of seismic motion is slow when all frequency components are included, or in the case where miscellaneous vibrations of a vehicle or the like are observed immediately before the seismic motion, the information processing device according to the present disclosure can accurately detect the arrival timing of the P wave by detecting frequency components specific to the seismic motion. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a system configuration diagram of an abnormality detection device 30 according to the first embodiment. [Diagram 2] FIG. 1 is a functional block diagram of an information processing device 20 according to a first embodiment. [Diagram 3] FIG. 10 is a flowchart showing an abnormality detection process of the information processing device 20 according to the first embodiment. [Figure 4] FIG. 10 is a flowchart showing the abnormality end determination process of the information processing device 20 according to the first embodiment. [Diagram 5]FIG. 1 is a diagram of the first embodiment, showing the seismic motion of the 2011 Tohoku Pacific Ocean Earthquake. [Figure 6] FIG. 1 is a diagram of the first embodiment, showing the seismic motion of the 2009 Suruga Bay offshore earthquake. [Figure 7] FIG. 1 is a diagram of the hardware configuration of an information processing device 20 according to the first embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] In the description of the embodiments and the drawings, the same elements and corresponding elements are given the same reference numerals. Descriptions of elements given the same reference numerals are omitted or simplified as appropriate. In the following embodiments, "unit" may be read as "circuit", "process", "step", "processing" or "circuitry" as appropriate.

[0011] The symbols used in the first embodiment are summarized below. In the descriptions other than those of the formulas 1 to 37, the lowercase letter l of L will be abbreviated as l to distinguish it from the number 1. * It is written as follows.

[0012] <Index and data sent and received> (1)l * :l * is a counter that counts up with each sampling. (2) m:m is the index of the AR model. (3) f: f is frequency (Hz). (4) Dg(l * ):Dg(l * ) is the observational digital data. (5) x (l * ):x(l * ) is the amplitude data in physical units. (6)PS(l * ,f):PS(l * ,f) is the running spectrum based on the AR model (short-term average). (7) PL(l * ,f):PL(l *,f) is the running spectrum based on the AR model (long-term average). (8)SLa(l * ):SLa(l * ) is the index value for anomaly detection. (9)l * t:l * t is the timing of abnormality detection. (10)SLb(l * ):SLb(l * ) is an index value for determining abnormal termination. (11)l * e:l * e is the timing of abnormal termination.

[0013] <Internal variable> (1) μS(l * ):μS(l * ) is the average based on the AR model (short-term average). (2)CS m (l * ):CSm(l * ) is the covariance function based on the AR model (short-term averaging) (m = 0, , M). (3)φS m (l * ):φS m (l * ) is the AR coefficient of the AR model (short-term average) (m = 1, , M). (4) xS(l * ):xS(l * ) is an estimate of the amplitude data using an AR model (short-term averaging). (5)σS 2 (l * ):σS 2 (l * ) is the variance of the estimation error of the amplitude data using the AR model (short-term averaging). (6) μL (l * ):μL(l * ) is the average based on the AR model (long-term average). (7)CL m (l * ):CL m (l *) is the covariance function due to the AR model (long-term average) (m = 0, , M). (8)φL m (l * ):φL m (l * ) is the AR coefficient of the AR model (long-term average) (m = 1, , M). (9) xL(l * ):xL(l * ) is an estimate of the amplitude data using an AR model (long-term average). (10) σL 2 (l * ):σL 2 (l * ) is the variance of the estimation error of the amplitude data using the AR model (long-term average).

[0014] <parameters> (1) fs: fs is the sampling frequency (Hz) of the observed digital data. (2) Cf: Cf is the physical value conversion coefficient. (3) M: M is the order of the AR model. (4) rS: rS is the forgetting factor of the AR model (short-term averaging). It is a coefficient that determines the window size for smoothing the running spectrum. The larger rS is, the smaller the window size becomes, resulting in a short-term average. (5) rL: rL is the forgetting factor of the AR model (long-term average). It is a coefficient that determines the window size for smoothing the running spectrum. The smaller rL is, the larger the window size is, resulting in a long-term average. (6) fsl * 1:fsl * 1 is the lower limit of the frequency (Hz) for calculating the index value for abnormality detection and the index value for abnormality termination determination. (7) fsl * 2:fsl * 2 is the upper limit of the frequency (Hz) for calculating the index value for abnormality detection and the index value for abnormality termination determination. (8) ETL: ETL is a threshold for detecting anomalies. (9) EEL: EEL is a threshold value for determining the termination of an abnormality.

[0015] Embodiment 1 Anomaly detection device 30 according to the first embodiment will be described with reference to Figs. 1 to 7. In the following first embodiment, a seismometer is assumed as the anomaly detection device 30. The sensor described below is assumed to be a sensor that detects seismic motion, and the anomaly detection unit 23 is assumed to be a P-wave detection unit that detects P-waves (Primary waves) as anomalies. However, the anomaly detection device 30 is not limited to a seismometer. The anomaly detection device 30 may also be an observation device that observes natural phenomena, such as a rain gauge or an anemometer. In a rain gauge, the observed data is rainfall, and in an anemometer, the observed data is wind speed.

[0016] In the following embodiment 1, detection of abnormality will be described as detection of P waves.

[0017] ***Configuration Description*** 1 is a system configuration diagram of an abnormality detection device 30. The abnormality detection device 30 includes a sensor 10 and an information processing device 20. The abnormality detection device 30 is capable of communicating with an external device 40 via a network 50.

[0018] 2 is a block diagram of the information processing device 20. The information processing device 20 includes, as functional elements, an amplitude calculation unit 21, a frequency analysis unit 22, an abnormality detection unit 23, and an abnormality end determination unit 24. (1) The amplitude calculation unit 21 calculates the amplitude of the counter l from the observation data of the event observed by the sensor 10. * The amplitude x(l * ) is calculated. The observation data is the observation digital data Dg(l * ) Counter l * corresponds to time, and the interval is the reciprocal of the sampling frequency fs (fs) -1 The event in the first embodiment is an earthquake. (2) The frequency analysis unit 22 calculates the amplitude x(l * ) to calculate frequency characteristics in real time. In addition, the frequency analysis unit 22 calculates the amplitude x(l *) using a first time window, a first frequency characteristic (PS(l * , f)) in real time and a second frequency characteristic (PL(l * ,f)) is analyzed in real time. The frequency analysis unit 22 uses an autoregressive model to calculate the amplitude x(l * ) the running spectrum is calculated in real time, and the running spectrum is an example of frequency response. (3) The anomaly detection unit 23 detects anomalies in the observation data based on the running spectrum. (4) The abnormality end determination unit 24 determines the end of the abnormality when an abnormality is detected. The abnormality end determination unit determines the end of the abnormality by comparing the running spectrum immediately before the occurrence of the abnormality with the current running spectrum.

[0019] ***Explanation of Operation*** 3 and 4, the operation of the information processing device 20 will be described. The operation of the information processing device 20 corresponds to an information processing method. The operation of the information processing method corresponds to processing by an information processing program 231, which will be described later. The information processing device 20 can be in a normal state or an abnormal state. The state of the information processing device 20 is the "normal state" when the power is turned on. When the information processing device 20 determines that the formula 15 described below is satisfied, the state of the information processing device 20 is the "abnormal state". When the information processing device 20 determines that the formula 17 described below is satisfied, the state of the information processing device 20 is the "normal state". Fig. 3 is a flowchart for explaining the operation of the abnormality detection process by the information processing device 20. The abnormality detection corresponds to the P wave detection. Fig. 3 is executed when the information processing device 20 is in the "normal state". Fig. 4 is a flowchart for explaining the operation of the abnormality end determination process by the information processing device 20. The abnormality end corresponds to the end of earthquake motion including P waves. Fig. 4 is executed when the information processing device 20 is in an "abnormal state".

[0020] In the following description, the abnormality detection will be described as P wave detection. In FIG. 3, the operation of the information processing device 20 is shown as process P201 to process P204. The information processing device 20 detects the P wave by detecting the reciprocal (fs) of the sampling frequency fs. -1 Ground motion is acquired as observed digital data from the sensor 10 at time intervals of fs. Ground motion is the vibration of the earth, and among ground motions, the vibration of the earth caused by an earthquake is called "earthquake motion." Ground motions other than earthquake motion include miscellaneous vibrations caused by vehicles, background vibrations (continuous microtremors), noise, etc. In the following, the reciprocal (fs) -1 is called a sampling interval. In a normal state, the information processing device 20 performs an abnormality detection process for each sampling.

[0021] <Process P201: Calculate the amplitude of observed data> (1) The amplitude calculation unit 21 receives the observed digital data Dg(l * ) is obtained. * ) is the ground motion. (2) The amplitude calculation unit 21 calculates the acquired observation digital data Dg(l * ) based on the amplitude data x(l * ) to calculate

number

[0022] <Process P202: Calculate the running spectrum> The frequency analysis unit 22 calculates a first running spectrum corresponding to a first time using a first time window. The first time window is a window for calculating a short-time average running spectrum. The first running spectrum is a short-time average running spectrum. The frequency analysis unit 22 also calculates a second running spectrum corresponding to the second time window using a second time window that is longer than the first time window. The second time window is a window for calculating a long-time average running spectrum. The second running spectrum is a long-time average running spectrum. The first running spectrum and the second running spectrum are used for anomaly detection by the anomaly detection unit 23. This will be specifically described below.

[0023] The frequency analysis unit 22 first calculates the amplitude data x(l * ) time series is smoothed by time averaging. Next, the time-averaged running spectrum of the amplitude data is calculated by expressing it as an autoregressive model. In this case, two types of running spectra are calculated using two methods, short-term averaging and long-term averaging, which have different smoothing window sizes. Hereinafter, the autoregressive model will be referred to as the AR model. (1) The frequency analysis unit 22 calculates the average μS(l * ) to calculate

number

number

number

number

number

number

number

number

number

number

number

number

[0024] <Process P203: Calculate index value for anomaly detection> The anomaly detection unit 23 detects an anomaly from the observed digital data by comparing the first running spectrum with the second running spectrum. The anomaly detection unit 23, which is a P-wave detection unit, calculates the index value SLa(l * ) is calculated. Here, abnormality detection is P wave detection. The index value SLa(l * ) is the running spectrum PS(l * ,f) and the running spectrum PL(l * ,f) means the frequency average of the ratio of PS(l * ,f) / PL(l * ,f) corresponds to performing the STA / LTA method for each frequency component.

number

[0025] <Process P204: Anomaly detected> The abnormality detection unit 23 calculates the abnormality detection index value SLa(l * ) satisfies Equation 15.

number

[0026] Highly accurate abnormality detection is possible according to the flowchart in Fig. 3. In particular, highly accurate abnormality detection is possible by the processing of formula 14 in the abnormality detection unit 23.

[0027] The operation of the abnormality end determination process in the abnormality detection device 30 will be described with reference to Fig. 4. The process in Fig. 4 is executed when the information processing device 20 is in an "abnormal state".

[0028] <Process P201-1, P202-1> The information processing device 20 acquires ground motion, which is observed digital data, from the sensor 10 at a sampling interval that is the reciprocal of the sampling frequency fs. When the information processing device 20 is in an abnormal state, the information processing device 20 counts up the counter l * The contents of process P201-1 and process P202-1 are the same as those of process P201 and process P202, respectively.

[0029] <Process P205: Calculate the index value for determining abnormal termination> The abnormality end determination unit 24 calculates the index value SLb(l * ) is calculated. The index value SLb(l * ) is the current time (l* ) The running spectrum of the short-term average in the AR model and the timing of anomaly detection (l * The index value SLb(l * ) is an index value for each frequency component indicating whether the running spectrum has returned to the state before the abnormality was detected.

number

[0030] <Process P206: Determining abnormal termination> The abnormality end determination unit 24 determines the index value SLb(l * ) satisfies Equation 17.

number

[0031] The frequency analysis unit 22 can be summarized as follows. The information processing device 20 of the first embodiment includes the frequency analysis unit 22. The frequency analysis unit 22 calculates a running spectrum using an autoregressive model. Compared with FFT, the method of calculating a running spectrum using an autoregressive model has the following advantages (1) to (7). (1) High time resolution because no taper is required. (2) The AR model allows for natural smoothing of the spectrum. (3) Since the AR coefficients are calculated sequentially, the calculation time does not depend on the window size, and high-speed calculation is possible. (4) Because the AR coefficients are discrete values, it is possible to reduce the dimensions of the data, which is suitable for machine learning applications. (5) By converting the digital observation data into multi-channel data, it is also possible to measure the cross-correlation between channels. (6) The window width can be easily adjusted by simply changing the forgetting factor. (7) By calculating the Akaike Information Criterion (AIC) described later, the fit of the AR model to the amplitude data can be evaluated, making it possible to set the optimal AR order.

[0032] FIG. 5 shows P-wave detection (anomaly detection) by the information processing device 20 in response to seismic motion from the 2011 Tohoku Pacific Ocean Earthquake. Fig. 6 shows P-wave detection (anomaly detection) by the information processing device 20 for seismic motion from the 2009 Suruga Bay earthquake. The horizontal axis in Fig. 5 and Fig. 6 represents time, and the vertical axis represents the amplitude value of the amplitude data and the index value of anomaly detection (index value of P-wave detection).

[0033] ***Advantages of the First Embodiment*** Compared with the STA / LTA method disclosed in Non-Patent Document 1, which detects a sudden rise in amplitude, the information processing device 20 of the first embodiment detects a sudden rise in amplitude for each frequency component. Therefore, even in the case of an earthquake with a gradual rise in the amplitude of seismic motion, when miscellaneous vibrations of a vehicle or the like are observed immediately before the seismic motion, or when coda waves from an earthquake immediately before a foreshock or the like overlap, the P-wave arrival timing can be accurately detected. In addition, the parameter fsl in Eq. * 1 and fsl * By adjusting 2, it is possible to focus only on the desired frequency band. Therefore, it is possible to detect earthquake motion while avoiding known frequency bands such as those caused by train vibrations. In addition, frequency characteristics such as the running spectrum can be obtained when an anomaly is detected (detection of P waves), which can be used to distinguish whether the detected anomaly is due to an earthquake or noise.

[0034] In the above, the frequency analysis unit 22 calculates the running spectrum in real time and calculates the index value SLa(l * ) is assumed to be used to detect anomalies. However, the index value SLa(l * ) is the running spectrum PS(l * ,f) and the running spectrum PL(l * , f) may be defined in various other ways. For example, the following embodiment is possible. (1) In the case of short-time average, the frequency analysis unit 22 solves the M-th order polynomial (characteristic equation) for the complex number z shown in Equation 18, and identifies the solutions whose imaginary part is 0 or positive as the characteristic roots zS of the AR model (short-time average). q (l * ) (q is a sequential number, q = 1, , Q).

number

number

number

number

number

number

number

number

number

number

number

number

number

number

number

number

[0035] Running spectrum PS(l * ,f) and the running spectrum PL(l * As the distance index in (f), other embodiments may be possible that use a chi-squared kernel, a positive definite chi-squared kernel, a histogram intersection kernel, a Hellinger kernel, a correlation function, or the like.

[0036] In addition, the PS(l * ,f) and PL(l * By using all or part of (f) in machine learning such as deep learning to learn the characteristics of anomalies, it is possible to implement an embodiment that performs highly accurate anomaly detection.

[0037] In addition, zS calculated using Equations 18 to 20 and 23 to 25 q (l * ), fS q (l * ), P.S. q (l * ), zL q (l * ), fL q (l * ) and P.L.q (l * ) is equivalent to the dimensionality reduction of the running spectrum across all frequencies f, so that all or part of these can be used in machine learning such as deep learning to effectively learn the characteristics of anomalies, enabling an embodiment to perform highly accurate anomaly detection.

[0038] In the first embodiment, the amplitude data x(l * ) is assumed to be one of the three spatial components, but it is also possible to use multiple spatial components simultaneously, or to use a function value calculated from multiple spatial components. For example, it is possible to use particle motion (particle trajectory) calculated from the displacement data of the three spatial components.

[0039] In the first embodiment, the abnormality detection unit 23 calculates the abnormality detection index value SLa(l * ) is the running spectrum PS(l * ,f) and the running spectrum PL(l * , f), however, it is also possible to use an embodiment that simply uses the dominant frequency itself as in Equation 34, an embodiment that simply uses the loss function itself based on an AR model (short-time average) as in Equation 35, or an embodiment that simply uses the Akaike Information Criterion itself based on an AR model (short-time average) as in Equation 36.

number

number

number

[0040] Also, a modification in which (1) in the explanation of equation 15 in the first embodiment is changed to the following (1) is possible. (1) Anomaly detection index value SLa(l * ) satisfies Expression 15, the abnormality detection unit 23 (P wave detection unit) determines that an abnormality has been detected. That is, the abnormality detection unit 23 determines that a P wave has been detected (YES in process P204). In this case, the state of the information processing device 20 transitions to an "abnormal state." An event in which an abnormality is detected by the abnormality detection unit 23 (P wave detection unit) is called an "abnormality detection." Next, the counter l * Going back in time, find the maximum l that satisfies Equation 37. * The timing when 1 is added to the abnormality detection timing l * The abnormality detection unit 23 detects the abnormality at timing l * t is output to the external device 40.

number

[0041] In addition, in the first embodiment, the order of the AR model (short-term average) and the AR model (long-term average) is set to a common value M, but an embodiment in which the orders of the two models are different from each other is also possible.

[0042] Furthermore, in the first embodiment, an autoregressive model is used to calculate the running spectrum in the frequency analysis section 22, but an embodiment in which the running spectrum is calculated using other methods such as FFT (Fast Fourier Transform) is also possible.

[0043] Furthermore, in the first embodiment, a device for observing natural phenomena, such as a seismometer, is assumed as the abnormality detection device. However, a self-diagnosis device for a machine, or a structural health monitoring device for monitoring damage caused by an earthquake to a structure such as a bridge, may also be assumed as the abnormality detection device. In the case of a self-diagnosis device, the observation data may be self-diagnosis data obtained from a sensor attached to the machine, and in the case of a structural health monitoring device, the observation data may be microtremor measurement data attached to the structure.

[0044] (Hardware Supplement) 7 shows a hardware configuration of the information processing device 20. The hardware configuration of the information processing device 20 is shown. The information processing device 20 is a computer. The information processing device 20 includes a processor 210. The information processing device 20 includes, as hardware, the processor 210, a main storage device 220, an auxiliary storage device 230, and a communication interface 240. The processor 210 is connected to other hardware via a signal line 250 and controls the other hardware.

[0045] The information processing device 20 includes an amplitude calculation unit 21, a frequency analysis unit 22, an abnormality detection unit 23, and an abnormality end determination unit 24. These functions are realized by an information processing program 231.

[0046] The processor 210 is a device that executes an information processing program 231. The processor 210 executes the information processing program 231 to realize the functions of an amplitude calculation unit 21, a frequency analysis unit 22, an abnormality detection unit 23, and an abnormality end determination unit 24. The processor 210 is an integrated circuit (IC) that performs arithmetic processing.

[0047] A specific example of the main memory device 220 is a static random access memory (SRAM). The main memory 220 stores the results of calculations performed by the processor 210.

[0048] The auxiliary storage device 230 is a storage device that stores data in a non-volatile manner. A specific example of the auxiliary storage device 230 is a hard disk drive (HDD). The auxiliary storage device 230 may be a portable recording medium. The auxiliary storage device 230 stores an information processing program 231.

[0049] The communication interface 240 is a communication port that enables the processor 210 to communicate with other devices. The communication interface 240 is connected to a network 50.

[0050] The processor 210 loads the information processing program 231 from the auxiliary storage device 230 into the main storage device 220. The processor 210 reads the loaded information processing program 231 from the main storage device 220 and executes it.

[0051] The information processing program 231 is a program that causes a computer to execute each process, procedure, or step of the amplitude calculation unit 21, the frequency analysis unit 22, the abnormality detection unit 23, and the abnormality termination determination unit 24, where the "part" is replaced with a "process," "procedure," or "step."

[0052] Moreover, a method performed by the information processing device 20, which is a computer, executing the information processing program 231 is an information processing method. The information processing program 231 may be provided by being stored in a computer-readable recording medium, or may be provided as a program product.

[0053] Various aspects of the present disclosure are summarized below as appendices. (Appendix 1) an amplitude calculation unit that calculates an amplitude that changes over time from observation data of an event observed by a sensor; a frequency analysis unit that calculates a frequency characteristic from the amplitude in real time using an autoregressive model; An information processing device comprising: (Appendix 2) an amplitude calculation unit that calculates an amplitude that changes over time from observation data of an event observed by a sensor; A first frequency characteristic corresponding to the first time window is analyzed in real time from the amplitude using a first time window; a frequency analysis unit that analyzes in real time a second frequency characteristic corresponding to a second time window, the second time window being longer than the first time window, from the amplitude; An information processing device comprising: (Appendix 3) The frequency analysis unit is 3. The information processing device according to claim 2, wherein the first frequency characteristic and the second frequency characteristic are analyzed in real time by using an autoregressive model. (Appendix 4) The information processing device further includes: 4. The information processing device according to claim 2, further comprising an anomaly detection unit configured to detect an anomaly from the observation data by using the first frequency characteristic and the second frequency characteristic. (Appendix 5) The abnormality detection unit 5. The information processing device according to claim 4, further comprising: a processor for detecting an anomaly in the observation data by comparing the first frequency characteristic with the second frequency characteristic. (Appendix 6) The information processing device further includes: 6. The information processing device according to claim 4 or 5, further comprising an abnormality end determination unit that determines an end of the abnormality when the abnormality is detected. (Appendix 7) The abnormality termination determination unit is 7. The information processing device according to claim 6, wherein the end of the abnormality is determined by comparing the second frequency characteristic immediately before the occurrence of the abnormality with the current first frequency characteristic. (Appendix 8) On the computer, an amplitude calculation process for calculating an amplitude that changes over time from the observation data of the event observed by the sensor; A frequency analysis process for calculating a frequency characteristic from the amplitude in real time using an autoregressive model; The information processing program to be executed. (Appendix 9) On the computer, an amplitude calculation process for calculating an amplitude that changes over time from the observation data of the event observed by the sensor; a frequency analysis process for analyzing, in real time, a first frequency characteristic corresponding to the first time window from the amplitude using a first time window, and analyzing, in real time, a second frequency characteristic corresponding to the second time window from the amplitude using a second time window that is longer than the first time window; An information processing program that executes the above. (Appendix 10) The frequency analysis process includes: 10. The information processing program according to claim 9, further comprising: analyzing the first frequency characteristic and the second frequency characteristic in real time using an autoregressive model. (Appendix 11) The information processing program further comprises: The information processing program according to claim 9 or 10, further comprising an anomaly detection process for detecting an anomaly from the observation data by using the first frequency characteristic and the second frequency characteristic. (Appendix 12) The abnormality detection process includes: 12. The information processing program according to claim 11, further comprising: detecting an anomaly from the observation data by comparing the first frequency characteristic with the second frequency characteristic. (Appendix 13) The information processing program further comprises: 13. The information processing program according to claim 11, further comprising an abnormality end determination process for determining an end of the abnormality when the abnormality is detected. (Appendix 14) The abnormality termination determination process includes: The information processing program according to claim 13, further comprising: determining whether the abnormality has ended by comparing the second frequency characteristic immediately before the occurrence of the abnormality with the current first frequency characteristic. (Appendix 15) The computer Calculate the amplitude that changes over time from the observation data of the event observed by the sensor, Using an autoregressive model, frequency characteristics are calculated in real time from the amplitude. Information processing methods. (Appendix 16) The computer Calculate the amplitude that changes over time from the observation data of the event observed by the sensor, an information processing method for analyzing, in real time, a first frequency characteristic corresponding to a first time window from the amplitude using a first time window, and analyzing, in real time, a second frequency characteristic corresponding to the second time window from the amplitude using a second time window that is longer than the first time window. [Explanation of symbols]

[0054] 10 sensor, 20 information processing device, 21 amplitude calculation unit, 22 frequency analysis unit, 23 anomaly detection unit, 24 anomaly termination determination unit, 30 anomaly detection device, 40 external device, 50 network, 210 processor, 220 main memory device, 230 auxiliary memory device, 231 information processing program, 240 communication interface, 250 signal line.

Claims

1. an amplitude calculation unit that calculates an amplitude that changes over time from observation data of an event observed by a sensor; a frequency analysis unit that analyzes, in real time, a first frequency characteristic corresponding to the first time window from the amplitude using a first time window, and analyzes, in real time, a second frequency characteristic corresponding to the second time window from the amplitude using a second time window that is longer than the first time window; Equipped with The frequency analysis unit is An information processing apparatus that analyzes the first frequency characteristic and the second frequency characteristic in real time by using an autoregressive model, The information processing device further includes: an anomaly detection unit that detects an anomaly from the observation data by using the first frequency characteristic and the second frequency characteristic.

2. The abnormality detection unit The information processing apparatus according to claim 1 , wherein the first frequency characteristic is compared with the second frequency characteristic to detect an anomaly from the observation data.

3. The information processing device further includes: The information processing apparatus according to claim 1 , further comprising an abnormality end determination unit that determines an end of the abnormality when the abnormality is detected.

4. The abnormality termination determination unit is The information processing apparatus according to claim 3 , wherein the termination of the abnormality is determined by comparing the second frequency characteristic immediately before the occurrence of the abnormality with the current first frequency characteristic.

5. On the computer, an amplitude calculation process for calculating an amplitude that changes over time from the observation data of the event observed by the sensor; a frequency analysis process for analyzing, in real time, a first frequency characteristic corresponding to the first time window from the amplitude using a first time window, and analyzing, in real time, a second frequency characteristic corresponding to the second time window from the amplitude using a second time window that is longer than the first time window; An information processing program for executing In the frequency analysis process, Analyzing the first frequency characteristic and the second frequency characteristic in real time using an autoregressive model; The information processing program further comprises: An information processing program comprising an anomaly detection process for detecting an anomaly from the observation data by using the first frequency characteristic and the second frequency characteristic.

6. The abnormality detection process includes: The information processing program according to claim 5 , further comprising: detecting an anomaly from the observation data by comparing the first frequency characteristic with the second frequency characteristic.

7. The information processing program further comprises:

7. The information processing program according to claim 5, further comprising an abnormality end determination process for determining an end of the abnormality when the abnormality is detected.

8. The abnormality termination determination process includes:

8. The information processing program according to claim 7, wherein the termination of the abnormality is determined by comparing the second frequency characteristic immediately before the occurrence of the abnormality with the current first frequency characteristic.

9. The computer Calculate the amplitude that changes over time from the observation data of the event observed by the sensor, an information processing method for analyzing, in real time, a first frequency characteristic corresponding to the first time window from the amplitude using a first time window, and analyzing, in real time, a second frequency characteristic corresponding to the second time window from the amplitude using a second time window that is longer than the first time window, The computer includes: Analyzing the first frequency characteristic and the second frequency characteristic in real time using an autoregressive model; The computer includes: An information processing method for detecting an anomaly from the observation data by using the first frequency characteristic and the second frequency characteristic.

10. The computer includes: The information processing method according to claim 9 , further comprising the step of: detecting an anomaly from the observation data by comparing the first frequency characteristic with the second frequency characteristic.

11. The computer includes: The information processing method according to claim 9 or 10, further comprising the step of determining whether the abnormality has ended when the abnormality is detected.

12. The computer includes: The information processing method according to claim 11 , further comprising the step of: determining whether the abnormality has ended by comparing the second frequency characteristic immediately before the occurrence of the abnormality with the current first frequency characteristic.

13. an amplitude calculation unit that calculates an amplitude that changes over time from observation data of an event observed by a sensor; a frequency analysis unit that analyzes, in real time, a first frequency characteristic corresponding to the first time window from the amplitude using a first time window, and analyzes, in real time, a second frequency characteristic corresponding to the second time window from the amplitude using a second time window that is longer than the first time window; Equipped with The frequency analysis unit is An information processing apparatus that analyzes the first frequency characteristic and the second frequency characteristic in real time by using an autoregressive model, The information processing device further includes: An information processing apparatus comprising: an abnormality detection unit that compares the first frequency characteristic with the second frequency characteristic.

14. On the computer, an amplitude calculation process for calculating an amplitude that changes over time from the observation data of the event observed by the sensor; a frequency analysis process for analyzing, in real time, a first frequency characteristic corresponding to the first time window from the amplitude using a first time window, and analyzing, in real time, a second frequency characteristic corresponding to the second time window from the amplitude using a second time window that is longer than the first time window; An information processing program for executing In the frequency analysis process, Analyzing the first frequency characteristic and the second frequency characteristic in real time using an autoregressive model; The information processing program further comprises: An information processing program comprising an abnormality detection process for comparing the first frequency characteristic with the second frequency characteristic.

15. The computer Calculate the amplitude that changes over time from the observation data of the event observed by the sensor, an information processing method for analyzing, in real time, a first frequency characteristic corresponding to the first time window from the amplitude using a first time window, and analyzing, in real time, a second frequency characteristic corresponding to the second time window from the amplitude using a second time window that is longer than the first time window, The computer includes: Analyzing the first frequency characteristic and the second frequency characteristic in real time using an autoregressive model; The computer includes: An information processing method for comparing the first frequency characteristic with the second frequency characteristic.

Images