Data collection device, data collection method, and program

Abstract

Provided is a data collection device, etc., that can increase the efficiency of collection of acoustic data obtained from a subject in which an abnormality has occurred. The data collection device 100 according to one aspect of the present disclosure comprises: a subject detection unit 120 that detects a subject data point, which is a data point in which a subject is observed, in acoustic data obtained by observation of the subject; a determination unit 130 that, on the basis of the subject data point, determines an analysis range in the acoustic data; an abnormality detection unit 140 that detects an abnormality within the analysis range; and an output unit 170 that outputs information pertaining to the analysis range within which the abnormality was detected.

Description

Technical Field

[0001] The present disclosure relates to a technique for detecting abnormalities.

Background Art

[0002] Regular inspections of railway facilities are obligatory by the Ministry of Land, Infrastructure, Transport and Tourism, and railway companies are conducting patrols according to the types of railways and facilities they own. In addition, the development of technologies for monitoring abnormalities during operation using advanced technologies is underway. Among these, loosening of bolts at rail joints and loosening of hook bolts on bridges may not be detected until the loosened bolts break, and there is a demand for an abnormality identification system that supplements patrols and regular inspections.

[0003] Examples of techniques for estimating the state of rail joints are disclosed in the following documents.

[0004] Patent Document 1 and Cited Document 4 disclose a method for estimating the stress applied to a joint plate from the measured axle box acceleration and unevenness based on the relationship between the axle box acceleration applied to the axle box of a vehicle, the unevenness of the rail at the running location of the vehicle, and the stress applied to the joint plate of an adhesive insulated rail.

[0005] Patent Document 2 discloses an apparatus for measuring the size of the clearance formed at a rail joint using a gauge.

[0006] Patent Document 3 discloses a method for detecting the starting state by performing a Fourier transform on an acoustic signal acquired in a vehicle running on a track and based on the peak value at each predetermined time.

[0007] Patent Document 5 discloses an apparatus for determining an abnormality in a vehicle axle bearing of an object using vibration data of the object when the distance between a reference point of the object running along a track and the track is within a predetermined range.

[0008] Patent Document 6 discloses an abnormality detection device that calculates signal pattern features regarding an acoustic signal to be subjected to abnormality detection and calculates an abnormality score for performing abnormality detection based on the signal pattern features. The signal pattern features regarding the acoustic signal to be subjected to abnormality detection are calculated based on a signal pattern model learned based on an acoustic signal having a first time width and a long-time feature amount calculated from an acoustic signal having a second time width longer than the first time width.

Prior Art Documents

Patent Documents

[0009]

Patent Document 1

Patent Document 2

Patent Document 3

Patent Document 4

Patent Document 5

Patent Document 6

Summary of the Invention

Problems to be Solved by the Invention

[0010] Abnormalities such as loosening of bolts at rail joints may appear as sounds when a train passes. This is a phenomenon known from experience by train drivers and the like. In order to learn a model for accurately detecting abnormalities using sound, it is necessary to collect the sound when a train passes over a rail joint where an abnormality such as bolt loosening has occurred.

[0011] Patent Documents 1 to 6 describe techniques for detecting abnormalities. With the techniques of Patent Documents 1 to 6, it is not possible to improve the efficiency of collecting acoustic data obtained from an object in which an abnormality has occurred.

[0012] One of the objects of the present disclosure is to provide a data collection device or the like that can improve the efficiency of collecting acoustic data obtained from a target in which an abnormality has occurred.

Means for Solving the Problems

[0013] A data collection device according to an aspect of the present disclosure includes: target detection means for detecting a target data point that is a data point at which the target was observed in acoustic data obtained by observing the target; determination means for determining an analysis range in the acoustic data based on the target data point; abnormality detection means for detecting an abnormality in the analysis range; and output means for outputting information on the analysis range in which the abnormality was detected.

[0014] A data collection method according to an aspect of the present disclosure includes: detecting a target data point that is a data point at which the target was observed in acoustic data obtained by observing the target; determining an analysis range in the acoustic data based on the target data point; detecting an abnormality in the analysis range; and outputting information on the analysis range in which the abnormality was detected.

[0015] A program according to an aspect of the present disclosure causes a computer to execute: a target detection process for detecting a target data point that is a data point at which the target was observed in acoustic data obtained by observing the target; a determination process for determining an analysis range in the acoustic data based on the target data point; an abnormality detection process for detecting an abnormality in the analysis range; and an output process for outputting information on the analysis range in which the abnormality was detected. An aspect of the present disclosure is also realized by a storage medium storing the above-described program.

Advantages of the Invention

[0016] The present disclosure has an effect of being able to improve the efficiency of collecting acoustic data obtained from a target in which an abnormality has occurred.

Brief Description of the Drawings

[0017]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Mode for Carrying Out the Invention

[0018] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings.

[0019] <First Embodiment> First, a first embodiment of the present disclosure will be described.

[0020] <Configuration> FIG. 1 is a block diagram showing an example of the configuration of a data collection device according to a first embodiment of the present disclosure.

[0021] <Data Collection Device 100> In the example shown in FIG. 1, the data collection device 100 includes a target detection unit 120, a determination unit 130, an abnormality detection unit 140, and an output unit 170. The target detection unit 120 detects target data points, which are data points where the target is observed, in the acoustic data obtained by observing the target. The determination unit 130 determines an analysis range in the acoustic data based on the target data points. The determination unit 130 detects an abnormality within the analysis range. The output unit 170 outputs information on the analysis range in which the abnormality is detected. Hereinafter, the data obtained by observation will be described as vibration data, but the data obtained by observation may be vibration data instead of acoustic data.

[0022] <Target Detection Unit 120> The acoustic data is time-series data representing the transition of sound, obtained by converting data observed by a sensor attached to, for example, a vehicle traveling on a track into data in the frequency domain. The sensor is, for example, an acoustic sensor such as a microphone, or a sensor such as a vibration sensor that can observe the sound or vibration generated when the vehicle passes over a rail joint. Hereinafter, the sensor will be described as an acoustic sensor. The position where the sensor is attached may be, for example, a lower part of the vehicle such as a bogie of the vehicle or near the rail. The position where the sensor is attached may be a part of the vehicle mounted on the bogie. The position where the sensor is attached may be the surface of the bogie or the vehicle. The position where the sensor is attached may be inside the bogie or the vehicle. The data at each individual time point included in the acoustic data will be hereinafter referred to as element data. The conversion method may be any of various existing methods. The object is, for example, a rail joint. The target data point is, for example, data observed when the wheel with the shortest distance from the sensor passes over the rail joint. The target detection unit 120 detects, for example, a point having a maximum value of sound pressure greater than or equal to a threshold value in the acoustic data as the target data point.

[0023] The acoustic data may be associated with the observation time. For example, the time interval between individual element data of the acoustic data and the start time of the observation of the acoustic data are given. Each of the element data of the acoustic data may be associated with the observation time. Further, the traveling speed of the vehicle at the time of observation and the length of the rail may be obtained. The target detection unit 120 may detect, for example, a point having a maximum value of sound pressure greater than or equal to a threshold value in the acoustic data as the target data point. In this case, the target detection unit 120 may further calculate the time when the next target data point is obtained based on the time when the detected target data point was observed, the traveling speed of the vehicle, and the length of the rail. Then, the target detection unit 120 may detect the data observed at the calculated time as the target data point. The target detection unit 120 may detect, as the target data point, a point having a maximum value of sound pressure greater than or equal to a threshold value from the data observed during a predetermined time width including the calculated time.

[0024] Furthermore, for example, the location of the observation obtained using GPS (Global Positioning System) or the like may be associated with the time of the observation. The target detection unit 120 may estimate the time when the rail joint was passed during the period when the observation data was obtained, using the relationship between the location of the observation and the time of the observation. The target detection unit 120 may detect the data observed at the estimated time as a target data point. The target detection unit 120 may also detect, as a target data point, a point that takes a maximum value of sound pressure greater than or equal to a threshold value from the data observed during a predetermined time width including the estimated time.

[0025] <Determination unit 130> The determination unit 130 may determine, for example, the data obtained during the period from a time a predetermined time (referred to as a first predetermined time) before the time when the target data point was observed to a time a predetermined time (second predetermined time) after the time when the target data point was observed, as the analysis range. The first predetermined time and the second predetermined time may be the same. The first predetermined time and the second predetermined time may be fixed. The first predetermined time and the second predetermined time may be determined based on the traveling speed of the vehicle at the time when the target data point was observed. Specifically, the first predetermined time and the second predetermined time may be determined such that they become shorter as the traveling speed of the vehicle is higher. In the following description, the range of the observation data from a time a first predetermined time before the time when the target data point was observed to a time a second predetermined time after the time when the target data point was observed is referred to as the influence range. The start time of the influence range is referred to as the influence start time. The end time of the influence range is referred to as the influence end time. In other words, the influence range is a part of the acoustic data observed between the influence start time and the influence end time. The determination unit 130 may determine the influence range as the analysis range.

[0026] The determination unit 130 may determine, as the analysis range, a range within the influence range that includes the target data point and excludes a range (referred to as the exclusion range) having a length shorter than the length of the influence range. In the following description, the start time of the exclusion range is referred to as the exclusion start time. The end time of the exclusion range is referred to as the exclusion end time. The exclusion start time is determined to be a time later than the influence start time. The exclusion end time is determined to be a time earlier than the influence end time. The time from the exclusion start time to the time when the target data point was observed is referred to as the third predetermined time. The time from the time when the target data point was observed to the exclusion end time is referred to as the fourth predetermined time. The third predetermined time and the fourth predetermined time may be fixed. The third predetermined time and the fourth predetermined time may be determined based on the traveling speed of the vehicle at the time when the target data point was observed. Specifically, the third predetermined time and the fourth predetermined time may be determined such that they become shorter as the traveling speed of the vehicle is higher. In other words, the determination unit 130 determines, as the analysis range, a range obtained by excluding the exclusion range from the influence range. More specifically, the determination unit 130 determines, as the analysis range, the range of the acoustic data observed between the influence start time and the exclusion start time, and the range of the acoustic data observed between the exclusion end time and the influence end time.

[0027] <Abnormality detection unit 140> The abnormality detection unit 140 detects an abnormality within the analysis range. Specifically, for example, the abnormality detection unit 140 detects an abnormal pattern that occurs when there is an abnormality at the rail joint within the analysis range. The abnormal pattern may be, for example, a peak in intensity that exists between 10 and 20 Hz. The abnormal pattern may be a peak in intensity that exists between 10 and 20 Hz and belongs to a predetermined time period or longer. The abnormal pattern may be, for example, a pattern obtained in advance by learning.

[0028] When the abnormality detection unit 140 detects an abnormal pattern within the analysis range, it determines that an abnormality has been detected at the rail joint. When an abnormal pattern is detected within the analysis range, the abnormality detection unit 140 may extract the characteristics of the detected abnormal pattern. The characteristics of the abnormal pattern may be, for example, the duration of the peak intensity that exists between 10 and 20 Hz within the analysis range. The characteristics of the abnormal pattern may be, for example, the duration of the peak intensity between 10 and 20 Hz before the time when the target data point was observed and the duration of the peak intensity between 10 and 20 Hz after the time when the target data point was observed within the analysis range. The characteristics of the abnormal pattern are not limited to these examples.

[0029] The abnormality detection unit 140 may detect an abnormality at the rail joint, for example, by means of a detector that has been obtained in advance through learning and that detects an abnormality at the rail joint.

[0030] <Output unit 170> The output unit 170 outputs information on the analysis range in which an abnormality has been detected. The information on the analysis range in which an abnormality has been detected is, for example, acoustic data within the analysis range. The information on the analysis range in which an abnormality has been detected is, for example, the acoustic data within the analysis range and the characteristics of the detected abnormality.

[0031] The output unit 170 may output the information on the analysis range in which an abnormality has been detected to the display of the data collection device 100. The output unit 170 may store the information on the analysis range in which an abnormality has been detected in a storage device. This storage device may be an external storage device, a server, etc. that is connected to the data collection device 100. This storage device may be a storage device that is installed inside the data collection device 100. This storage device may be a storage medium that the data collection device 100 can read and write to.

[0032] <Operation> Next, the operation of the data collection device 100 according to the first embodiment of the present disclosure will be described in detail with reference to the drawings.

[0033] FIG. 2 is a flowchart showing an example of the operation of the data collection device 100 according to the first embodiment of the present disclosure.

[0034] In the example shown in FIG. 2, first, the target detection unit 120 detects target data points in the acoustic data (step S101). The target detection unit 120 may detect one or more target data points existing in the acoustic data. The target detection unit 120 may detect all the target data points existing in the acoustic data.

[0035] Next, the determination unit 130 determines an analysis range based on the target data points in the acoustic data (step S102). The determination unit 130 may determine an analysis range for each of the target data points detected in step S101.

[0036] Next, the abnormality detection unit 140 detects an abnormality in the determined analysis range (step S103). The abnormality detection unit 140 may detect an abnormality in each of the analysis ranges determined in step S102.

[0037] If no abnormality is detected (NO in step S104), the data collection device 100 ends the operation shown in FIG. 2. In this case, before the data collection device 100 ends the operation shown in FIG. 2, the output unit 170 may output information indicating that no abnormality is detected in the acoustic data.

[0038] If an abnormality is detected (YES in step S104), the output unit 170 outputs information on the analysis range in which the abnormality is detected. The output unit 170 may output information on the analysis range in which the abnormality is detected for each of the analysis ranges in which the abnormality is detected.

[0039] <Effect> The present disclosure has an effect of being able to improve the efficiency of collecting acoustic data obtained from a target in which an abnormality has occurred. The reason is that the target detection unit 120 detects target data points, the determination unit 130 determines an analysis range based on the target data points, and the abnormality detection unit 140 detects an abnormality in the determined analysis range.

[0040] <Second Embodiment> Next, the second embodiment of the present disclosure will be described in detail with reference to the drawings.

[0041] <Configuration> FIG. 3 is a block diagram showing an example of the configuration of the data collection device 101 according to the second embodiment of the present disclosure.

[0042] In the example shown in FIG. 3, the data collection device 101 includes a data reception unit 110, an object detection unit 120, a determination unit 130, an abnormality detection unit 140, a classification unit 150, and an output unit 170. The data collection device 101 may further include a data storage unit 160. The data collection device 101 may further include an environmental information reception unit 210. The data collection device 101 may further include an attribute reception unit 220.

[0043] <Data Reception Unit 110> The data reception unit 110 receives acoustic data representing the sound observed by a sensor (e.g., a microphone) attached to the bogie of a vehicle, for example. The data reception unit 110 may receive the acoustic data directly from the sensor. The data reception unit 110 may receive the acoustic data stored in a server or the like from that server or the like.

[0044] The acoustic data received by the data reception unit 110 may be data in the frequency domain. The acoustic data received by the data reception unit 110 may be data in the time domain. In that case, the data reception unit 110 converts the received acoustic data into data in the time domain.

[0045] The data reception unit 110 sends the acoustic data to the object detection unit 120.

[0046] <Object Detection Unit 120> The target detection unit 120 receives acoustic data from the data reception unit 110. Similar to the target detection unit 120 in the first embodiment, the target detection unit 120 detects target data points that are data points where the target is observed in the acoustic data. The target detection unit 120 sends information representing the detected target data points to the determination unit 130.

[0047] The information representing the target data points is information that identifies the target data points in the acoustic data. The information representing the target data points may be the time when the data of the target data points was observed. The information representing the target data points may be a number indicating the order of the data of the target data points in the acoustic data, which is time-series information. The information representing the target data points may be identification information such as a number assigned to the data of the target data points in the acoustic data, which is time-series information. In the following description, information that identifies the data observed at a certain time in the acoustic data is referred to as specific information.

[0048] <Determination unit 130> The determination unit 130 receives information representing the target data points from the target detection unit 120. Similar to the determination unit 130 in the first embodiment, the determination unit 130 determines the analysis range in the acoustic data based on the target data points. The determination unit 130 sends information representing the determined analysis range to the anomaly detection unit 140.

[0049] When the analysis range is the above-described influence range, the information representing the analysis range may be the influence start time and the influence end time. In this case, the information representing the analysis range may be information such as a number or identifier (i.e., specific information) that identifies the data observed at the influence start time and information such as a number or identifier (i.e., specific information) that identifies the data observed at the influence end time.

[0050] When the analysis range is the range obtained by excluding the exclusion range from the influence range, the information representing the analysis range may be the influence start time, the exclusion start time, the exclusion end time, and the influence end time. The information representing the analysis range may be the specific information of the data observed at the influence start time, the specific information of the data observed at the exclusion start time, the specific information of the data observed at the exclusion end time, and the specific information of the data observed at the influence end time.

[0051] <Abnormality detection unit 140> The abnormality detection unit 140 receives the information representing the determined analysis range from the determination unit 130. Similar to the abnormality detection unit 140 in the first embodiment, the abnormality detection unit 140 detects an abnormality in the analysis range. The abnormality detection unit 140 sends the detected abnormality information and the information of the analysis range in which the abnormality is detected to the classification unit 150.

[0052] The abnormality detection unit 140 may detect a plurality of types of abnormalities in the analysis range. The abnormality detection unit 140 detects an abnormal pattern in the analysis range, and when an abnormal pattern is detected, it may determine that an abnormality has been detected. The abnormal pattern may be represented by, for example, a combination of one or more frequency bands including peaks. The abnormal pattern may be represented by, for example, a combination of one or more frequency bands including peaks and the ratio of the peak strengths in each frequency band. The abnormal pattern may be different from the above examples. The abnormality detection unit 140 may identify the abnormal pattern that best matches the acoustic data in the analysis range among the plurality of abnormal patterns. The abnormality detection unit 140 may calculate a score representing the degree of match between the acoustic data in the analysis range and each of the plurality of abnormal patterns. The score may be appropriately defined to represent the degree of match.

[0053] The types of anomalies may be, for example, bolt breakage at the rail joint, bolt loosening at the rail joint, etc. In this case, the plurality of anomaly patterns include an anomaly pattern when bolt loosening occurs at the rail joint and an anomaly pattern when bolt breakage occurs at the rail joint. The anomaly detection unit 140 may detect anomalies using a plurality of anomaly patterns that vary depending on weather, temperature, vehicle type, vehicle weight, etc. In this case, when at least any one of the plurality of anomaly patterns is detected within the analysis range, the anomaly detection unit 140 may determine that an anomaly of the type corresponding to the detected anomaly pattern has been detected. These plurality of anomaly patterns are, for example, anomaly patterns obtained in advance by learning.

[0054] The anomaly detection unit 140 may detect anomalies using the above-described detectors. The anomaly detection unit 140 may detect anomalies using a plurality of detectors that vary depending on weather, temperature, vehicle type, vehicle weight, etc. In this case, when an anomaly is detected by any one of the detectors, the anomaly detection unit 140 may determine that an anomaly of the type corresponding to the detector that detected the anomaly has been detected within the analysis range. These plurality of detectors are, for example, detectors obtained in advance by learning.

[0055] The anomaly detection unit 140 may send to the classification unit 150 information on the anomaly (for example, information including information specifying the type of the detected anomaly and characteristics of the detected anomaly) and information specifying the acoustic data of the analysis range where the anomaly was detected. In the description of the present disclosure, the analysis range where the anomaly was detected is also referred to as the analysis range where the anomaly was detected.

[0056] <Classification unit 150> The classification unit 150 receives from the anomaly detection unit 140 information on the detected anomaly and information on the analysis range where the anomaly was detected. The information on the anomaly may include, for example, information representing the detected anomaly (for example, data included in the analysis range among the observation data) and characteristics of the detected anomaly (for example, information specifying the type of the detected anomaly).

[0057] The classification unit 150 classifies the analysis range in which an abnormality has been detected into at least one of a plurality of classifications, for example. Each classification may be associated with at least one or more of a plurality of types of abnormalities. The classification may be a type of abnormality. The types of abnormalities are not limited to the above examples. The classification unit 150 may classify the data of the analysis range in which an abnormality has been detected into classifications associated with the types of abnormalities detected. The classification unit 150 may classify the analysis range in which an abnormal pattern has been detected into classifications associated with the abnormal pattern that most matches the analysis range. The classification may be determined based on other information. The classification based on other information will be described as a modification example later.

[0058] The classification unit 150 stores the information on the analysis range in which an abnormality has been detected and the information on the classification into which the analysis range has been classified in the data storage unit 160.

[0059] The classification unit 150 may assign an urgency level corresponding to the classification to the information on the analysis range in which an abnormality has been detected. For example, the classification unit 150 assigns an urgency level indicating a higher urgency to the information on the analysis range in which an abnormality has been detected and classified as bolt breakage than the urgency level assigned to the information on the analysis range in which an abnormality has been detected and classified as bolt loosening.

[0060] <Operation> Next, the operation of the data collection device 101 according to the second embodiment of the present disclosure will be described in detail with reference to the drawings.

[0061] FIG. 4 is a flowchart showing an example of the operation of the data collection device 101 according to the second embodiment of the present disclosure.

[0062] In the example shown in FIG. 4, the data reception unit 110 receives observation data (step S101). Next, the target detection unit 120 detects target data points in the observation data (step S102). Next, the determination unit 130 determines an analysis range based on the target data points (step S103). The abnormality detection unit 140 detects an abnormality within the analysis range (step S104). If no abnormality is detected (NO in step S105), the data collection device 101 ends the operation shown in FIG. 4.

[0063] If an abnormality is detected (YES in step S105), the classification unit 150 classifies the data within the analysis range where the abnormality was detected (step S206). After step S206, the classification unit 150 may store the abnormal data, which is the information of the analysis range where the abnormality was detected, and the classification of the abnormal data in the data storage unit 160. After step S206, the classification unit 150 may send the abnormal data, which is the information of the analysis range where the abnormality was detected, and the classification of the abnormal data to the output unit 170. Then, the output unit 170 outputs the abnormal data, which is the information of the analysis range where the abnormality was detected, and the classification of the abnormal data (step S207).

[0064] <Effect> This embodiment has the same effects as those of the first embodiment. The reason is the same as the reason for the effects of the first embodiment.

[0065] <First Variation of the Second Embodiment> FIG. 5 is a block diagram showing an example of the configuration of a data collection device 101A according to the first variation of the second embodiment. Hereinafter, the differences between the data collection device 101A of this variation and the data collection device 101 of the second embodiment will be described. Except for the differences described below, the data collection device 101A of this variation has the same functions as the data collection device 101 of the second embodiment and operates in the same manner. In the example shown in FIG. 5, the data collection device 101A of this variation includes an environmental information reception unit 210 in addition to all the components of the data collection device 101 of the second embodiment.

[0066] <Environmental information reception unit 210> The environmental information reception unit 210 receives environmental information from another device such as a server that stores information at the time of observation. The environmental information is, for example, the date and time at the time of observation, the temperature at the observation location, the weather, and the like. The environmental information is not limited to these examples. The environmental information may not include some or all of these.

[0067] The environmental information reception unit 210 sends the received environmental information to the classification unit 150.

[0068] <Classification unit 150> The classification unit 150 of the present embodiment receives environmental information from the environmental information reception unit 210. The classification unit 150 classifies the analysis range in which an abnormality is detected into any one of the classifications based on the environmental information. The classification based on the environmental information is a classification determined based on, for example, at least any one of the month, season, temperature, and weather at the time of observation.

[0069] <Second modification of the second embodiment> FIG. 6 is a block diagram showing an example of the configuration of the data collection device 101B according to the second modification of the second embodiment. Hereinafter, the differences between the data collection device 101B of this modification and the data collection device 101 of the second embodiment will be described. Except for the differences described below, the data collection device 101B of this modification has the same functions as the data collection device 101 of the second embodiment and operates in the same manner. In the example shown in FIG. 6, the data collection device 101B of this modification includes an attribute reception unit 220 in addition to all the components of the data collection device 101 of the second embodiment.

[0070] <Attribute reception unit 220> The attribute reception unit 220 receives attribute information from another device such as a server that stores information at the time of observation. The attribute information includes, for example, the type of vehicle, the weight of the vehicle, track information (e.g., the degree of rail deterioration, the time elapsed since the rail was laid, etc.). The degree of rail deterioration may be a classification according to the frequency with which the vehicle passes over the rail. The degree of rail deterioration may be the degree of deterioration determined visually. The attribute information is not limited to these examples. The attribute information may not include some or all of these.

[0071] The attribute reception unit 220 sends the received environmental information to the classification unit 150.

[0072] <Classification unit 150> The classification unit 150 of the present embodiment receives attribute information from the attribute reception unit 220. The classification unit 150 classifies the analysis range in which an abnormality is detected into any one of the classifications based on the attribute information. The classification based on the attribute information is a classification determined based on at least any one of, for example, the type of vehicle, the weight classification including the weight of the vehicle, and the track state classification including the track information at the time of observation. The weight classification is a predefined range of the weight of the vehicle. The track state classification is, for example, a predefined range of the time elapsed since the rail was laid. The track state classification may be the degree of rail deterioration.

[0073] <Third modification of the second embodiment> FIG. 7 is a block diagram showing an example of the configuration of a data collection device 101C according to a third modification of the second embodiment. Hereinafter, differences between the data collection device 101C of this modification and the data collection device 101 of the second embodiment will be described. Except for the differences described below, the data collection device 101C of this modification has the same functions as the data collection device 101 of the second embodiment and operates in the same manner. In the example shown in FIG. 7, the data collection device 101B of this modification includes an environmental information reception unit 210 and an attribute reception unit 220 in addition to all the components of the data collection device 101 of the second embodiment. The environmental information reception unit 210 of this modification is the same as the environmental information reception unit 210 of the first modification of the second embodiment. The attribute reception unit 220 of this modification is the same as the attribute reception unit 220 of the second modification of the second embodiment.

[0074] <Classification unit 150> The classification unit 150 of this embodiment receives environmental information from the environmental information reception unit 210. The classification unit 150 of this embodiment further receives attribute information from the attribute reception unit 220. The classification unit 150 classifies the analysis range in which an abnormality is detected into any one of classifications based on at least one of the environmental information and the attribute information.

[0075] <Fourth modification of the second embodiment> The fourth modification of the second embodiment is the same as the second embodiment except for the differences described below.

[0076] The data collection device 101 may not include the classification unit 150. In that case, the classification unit 150 sends information on the analysis range in which an abnormality is detected and information on the classification into which the analysis range is classified to the output unit 170. The output unit 170 receives information on the analysis range in which an abnormality is detected and information on the classification into which the analysis range is classified from the classification unit 150. The data collection device 101 of this modification is the same as the data collection device 101 of the second embodiment in other respects.

[0077] It is also possible to apply this modification to each of the first to third modifications of the second embodiment.

[0078] <Fifth Variation of the Second Embodiment> <Configuration> FIG. 8 is a block diagram showing an example of the configuration of the data collection device 101D according to the fifth variation of the second embodiment of the present disclosure. In the example shown in FIG. 8, the data collection device 101D of this variation includes a target reliability calculation unit 230 in addition to all of the components of the data collection device 101 of the second embodiment. The data collection device 101D of this variation has the same functions as the data collection device 101 of the second embodiment, except for the differences described below, and operates in the same manner as the data collection device 101 of the second embodiment. Note that the data collection device 101D of this variation may not include the classification unit 150. Further, this variation can also be applied to the first to third variations.

[0079] In this variation, an identifier (hereinafter referred to as a joint identifier) is assigned to each of the rail joints. Also, in this variation, a plurality of sets of acoustic data obtained by a plurality of observations of the same track are input to the data collection device 101D.

[0080] <Data Reception Unit 110> The data reception unit 110 receives data that associates a target data point with a rail joint, in addition to the acoustic data. The data that associates a target data point with a rail joint is, for example, data that specifies the time when a vehicle passed through a joint during observation. The data that specifies the time when a vehicle passed through a joint during observation may be, for example, a combination of a joint identifier and the time when the vehicle passed through the joint indicated by the joint identifier. The data that specifies the time when a vehicle passed through a joint during observation may be data that includes a plurality of combinations of the position of the vehicle and the time when the vehicle was present at that position during observation. In this case, for example, the data reception unit 110 may calculate the time when the vehicle passed through the position of the rail joint under the assumption that the vehicle traveled at a constant speed between two adjacent positions on the track from a plurality of combinations of the position of the vehicle and the time when the vehicle was present at that position.

[0081] <Abnormality Detection Unit 140> The abnormality detection unit 140 further generates a combination of information identifying the rail joint and information indicating whether an abnormality has been detected for each rail joint (i.e., for each detected target data point). Specifically, in addition to detecting an abnormality for each analysis range detected in the acoustic data, the abnormality detection unit 140 identifies the rail joint from which the data of the target data point based on the analysis range was obtained. For example, the abnormality detection unit 140 identifies, as the rail joint from which the data of the target data point based on the analysis range was obtained, the rail joint at which the vehicle passed at the time closest to the time when the data of the target data point based on the analysis range was observed. The abnormality detection unit 140 may identify, by other methods, the rail joint from which the data of the target data point based on the analysis range was obtained.

[0082] In addition to the information on the analysis range in which an abnormality has been detected, the abnormality detection unit 140 stores, for each target data point, the information identifying the rail joint and the information indicating whether an abnormality has been detected in the data storage unit 160. As described above, the information on the analysis range in which an abnormality has been detected is also referred to as abnormality data.

[0083] <Data Storage Unit 160> The data storage unit 160 stores the information of the analysis range in which an abnormality is detected (i.e., abnormal data), and a combination of information for identifying the rail joints for each target data point and information indicating whether an abnormality has been detected in the analysis range (hereinafter, also referred to as the result of detecting an abnormality in the analysis range). In this description, the result of detecting an abnormality in the analysis range is simply also referred to as the result of detecting an abnormality. As described above, in this modification example, a plurality of sets of acoustic data obtained by observing the same line multiple times are input to the data collection device 101D. As a result, the data storage unit 160 stores the information of the analysis range in which an abnormality is detected obtained from the plurality of sets of acoustic data, and information indicating whether an abnormality has been detected for each rail joint. And in the data storage unit 160, information indicating whether an abnormality has been detected in the analysis range of the same rail joint is stored for each of the plurality of sets of acoustic data. And when an abnormality is detected in the analysis range, the data storage unit 160 stores the information of the analysis range in which the abnormality is detected.

[0084] <Target reliability calculation unit 230> The target reliability calculation unit 230 reads out the information for identifying the rail joints for each target data point and the information indicating whether an abnormality has been detected in the analysis range, which are stored in the data storage unit 160.

[0085] The target reliability calculation unit 230 calculates the ratio of anomalies detected in the analysis range for each joint where at least one anomaly has been detected in the analysis range, based on the combination of information identifying the joint of the rail and information indicating whether an anomaly has been detected in the analysis range. Then, the target reliability calculation unit 230 calculates the target reliability for each joint based on the ratio of anomalies detected. The target reliability is, for example, a value representing how reliable the data in the analysis range where an anomaly has been detected is as the data observed at the joint where the anomaly occurred. In this example, it is considered that the higher the likelihood of an anomaly occurring at a joint, the higher the probability of detecting an anomaly in the data of the analysis range at that joint. The target reliability calculation unit 230 may use the ratio of anomalies detected as the target reliability. The target reliability calculation unit 230 may calculate the target reliability according to an expression representing the relationship between the ratio of anomalies detected and the target reliability.

[0086] The target reliability calculation unit 230 assigns the target reliability calculated for the joint at which the abnormal data is observed to the abnormal data stored in the data storage unit 160. In other words, the target reliability calculation unit 230 stores the target reliability for each joint in the data storage unit 160 and associates the target reliability calculated for the joint at which the abnormal data is observed with the abnormal data stored in the data storage unit 160.

[0087] The target reliability calculation unit 230 may send the target reliability for each joint to the output unit 170.

[0088] <Output unit 170> The output unit 170 may receive the target reliability for each joint from the target reliability calculation unit 230. The output unit 170 may output the target reliability for each joint received from the target reliability calculation unit 230.

[0089] The output unit 170 may read out the abnormal data with the target reliability assigned thereto from the data storage unit 160 and output the read-out abnormal data.

[0090] <Operation> Figure 9 is a flowchart showing an example of an operation of assigning target reliability to the data collection device 101D according to the fifth modification of the second embodiment of the present disclosure. At the start of the operation shown in Figure 9, the result of anomaly detection in the analysis range based on the target data points detected from a plurality of sets of acoustic data is stored in the data storage unit 160.

[0091] In the example shown in Figure 9, first, the target reliability calculation unit 230 reads out the result of anomaly detection in the analysis range (step S301). As described above, the result of anomaly detection in the analysis range is a combination of information for specifying the rail joints for each target data point and information indicating whether an anomaly has been detected in the analysis range. The target reliability calculation unit 230 extracts the result of anomaly detection in the analysis range for each joint from the read result of anomaly detection in the analysis range (step S302). In step S302, the target reliability calculation unit 230 extracts, as the result of anomaly detection in the analysis range for each joint, for example, the number of times the target data point is detected and the number of times an anomaly is detected in the analysis range based on the target data point for each joint.

[0092] Next, the target reliability calculation unit 230 calculates the ratio of anomalies detected in the analysis range (i.e., the ratio of anomalies detected) for each joint (step S303). The target reliability calculation unit 230 calculates the target reliability based on the calculated ratio for each rail joint (step S304). The target reliability calculation unit 230 assigns the target reliability to the anomaly data stored in the data storage unit 160 (step S305). Specifically, the target reliability calculation unit 230 assigns the target reliability of the joint from which the data of the analysis range in which the anomaly is detected, which is the anomaly data, is obtained to the anomaly data stored in the data storage unit 160.

[0093] Then, the data collection device 101D ends the operation shown in Figure 9.

[0094] <Sixth Modification of the Second Embodiment> The configuration of the data collection device 101D according to the sixth modification of the second embodiment of the present disclosure is the same as the configuration of the data collection device 101D according to the fifth modification of the second embodiment of the present disclosure. The data collection device 101D of this modification has the same functions as the data collection device 101D according to the fifth modification of the second embodiment, except for the differences described below, and operates in the same manner as the data collection device 101D according to the fifth modification of the second embodiment. Also, this modification can be applied to the first to third modifications.

[0095] In this modification, as in the fifth modification, an identifier (hereinafter referred to as a joint identifier) is assigned to each joint of the rail. Also, in this modification, a plurality of sets of acoustic data obtained by multiple observations of the same line are input to the data collection device 101D.

[0096] <Data reception unit 110> The data reception unit 110 further receives information indicating whether there is an abnormality (hereinafter referred to as abnormal measurement information) confirmed, for example, visually, for each joint of the rail. The data reception unit 110 sends the abnormal measurement information to the classification unit 150 via, for example, the target detection unit 120, the determination unit 130, and the abnormality detection unit 140. The classification unit 150 receives the abnormal measurement information and stores the received abnormal measurement information in the data storage unit 160. The data reception unit 110 may directly store the received abnormal measurement information in the data storage unit 160. The data reception unit 110 may send the received abnormal measurement information to the target reliability calculation unit 230. Note that in FIG. 8, for simplicity of the figure, the line connecting the data reception unit 110 and the data storage unit 160, and the line connecting the data reception unit 110 and the target reliability calculation unit 230 are omitted.

[0097] <Target reliability calculation unit 230> The target reliability calculation unit 230 reads the abnormal measurement information from the data storage unit 160. The target reliability calculation unit 230 may receive the abnormal measurement data from the data reception unit 110.

[0098] The target reliability calculation unit 230 calculates the target reliability of the joint where an abnormality exists in the abnormal measurement information in the same manner as the target reliability calculation unit 230 in the fifth modification of the second embodiment calculates the target reliability. The target reliability calculation unit 230 sets the target reliability of the joint where no abnormality exists in the abnormal measurement information to zero.

[0099] <Seventh Modification of the Second Embodiment> FIG. 10 is a block diagram showing an example of the configuration of the data collection device 101E according to the seventh modification of the second embodiment of the present disclosure. In the example shown in FIG. 10, the data collection device 101E includes an environment information reception unit 210, an attribute reception unit 220, and a classification reliability calculation unit 240 in addition to all the components of the data collection device 101 according to the second embodiment. Note that the data collection device 101E may not include either the environment information reception unit 210 or the attribute reception unit 220. Further, this modification can also be applied to the fifth and sixth modifications.

[0100] <Data Reception Unit 110> The data reception unit 110 of this modification has the same function as the data reception unit 110 of the fifth modification and performs the same operation as the operation of the data reception unit 110 of the fifth modification. That is, in addition to acoustic data, the data reception unit 110 receives data associating the target data point with the joint of the rail. The data associating the target data point with the joint of the rail is, for example, data specifying the time when the vehicle passed the joint during observation. The data specifying the time when the vehicle passed the joint during observation may be, for example, a combination of a joint identifier and the time when the vehicle passed the joint indicated by the joint identifier. The data specifying the time when the vehicle passed the joint during observation may be data including a plurality of combinations of the position of the vehicle and the time when the vehicle existed at that position during observation. In this case, for example, the data reception unit 110 may calculate the time when the vehicle passed the position of the joint of the rail under the assumption that the vehicle traveled at a constant speed between two adjacent positions on the track from a plurality of combinations of the position of the vehicle and the time when the vehicle existed at that position.

[0101] Similar to the data reception unit 110 of the sixth modification example, the data reception unit 110 further receives information indicating whether there is an abnormality (i.e., abnormal measurement information), which is, for example, confirmed visually, for each joint of the rail. The data reception unit 110 sends the abnormal measurement information to the classification unit 150 via, for example, the target detection unit 120, the determination unit 130, and the abnormality detection unit 140. The classification unit 150 receives the abnormal measurement information and stores the received abnormal measurement information in the data storage unit 160. The data reception unit 110 may directly store the received abnormal measurement information in the data storage unit 160. The data reception unit 110 may send the received abnormal measurement information to the classification confidence calculation unit 240. In FIG. 10, for the sake of simplicity of the figure, the line connecting the data reception unit 110 and the data storage unit 160, and the line connecting the data reception unit 110 and the classification confidence calculation unit 240 are omitted.

[0102] <Abnormality detection unit 140> The abnormality detection unit 140 of this modification example has the same function as the abnormality detection unit 140 of the fifth modification example and performs the same operation as the operation of the abnormality detection unit 140 of the fifth modification example.

[0103] <Data storage unit 160> The data storage unit 160 of this modification example is the same as the data storage unit 160 of the fifth modification example. The data storage unit 160 stores the information of the analysis range in which an abnormality is detected (i.e., abnormal data), and a combination of information for identifying the rail joints for each target data point and information indicating whether an abnormality has been detected in the analysis range. As described above, the combination of information indicating whether an abnormality has been detected in the analysis range is also expressed as the result of detecting an abnormality in the analysis range and the result of detecting an abnormality. Also, in this modification example, a plurality of sets of acoustic data obtained by observing the same line multiple times are input to the data collection device 101D. As a result, the data storage unit 160 stores the information of the analysis range in which an abnormality is detected obtained from the plurality of sets of acoustic data, and the information indicating whether an abnormality has been detected for each rail joint. And in the data storage unit 160, information indicating whether an abnormality has been detected in the analysis range of the same rail joint is stored for each of the plurality of sets of acoustic data. And when an abnormality is detected in the analysis range, the information of the analysis range in which the abnormality is detected is stored in the data storage unit 160.

[0104] <Environmental information reception unit 210> The environmental information reception unit 210 of this modification example is the same as the environmental information reception unit 210 of the first modification example. In other words, the environmental information reception unit 210 of this modification example has the same function as the environmental information reception unit 210 of the first modification example and performs the same operation as the environmental information reception unit 210 of the first modification example.

[0105] <Attribute reception unit 220> The attribute reception unit 220 of this modification example is the same as the attribute reception unit 220 of the second modification example. In other words, the attribute reception unit 220 of this modification example has the same function as the attribute reception unit 220 of the second modification example and performs the same operation as the attribute reception unit 220 of the first modification example.

[0106] <Classification unit 150> When the data collection device 101F includes the environmental information reception unit 210, the classification unit 150 has the same functions as the classification unit 150 in the first modification example and is configured to perform the same operations as the classification unit 150 in the first modification example. When the data collection device 101F includes the attribute reception unit 220, the classification unit 150 has the same functions as the classification unit 150 in the second modification example and is configured to perform the same operations as the classification unit 150 in the second modification example.

[0107] The classification in this modification example is a classification based on at least one of environmental information and attribute information. Note that when the data collection device 101F does not include the environmental information reception unit 210, the classification in this modification example may be a classification based on attribute information. When the data collection device 101F does not include the attribute reception unit 220, the classification in this modification example may be a classification based on environmental information.

[0108] In this modification example, the classification unit 150 classifies each of the detected target data points into one of the classifications. The classification unit 150 stores, in the data storage unit 160, information (hereinafter referred to as classification result) representing the classification into which the target data point is classified for each target data point.

[0109] <Data storage unit 160> The data storage unit 160 in this modification example functions in the same manner as the data storage unit 160 in the fifth modification example. The data storage unit 160 in this modification example further stores the classification results.

[0110] <Classification reliability calculation unit 240> The classification reliability calculation unit 240 reads out the abnormal measurement information stored in the data storage unit 160. The classification reliability calculation unit 240 may receive the abnormal measurement information from the data reception unit 110.

[0111] The classification reliability calculation unit 240 reads out, from the data storage unit 160, information for identifying the rail joints and information indicating whether an abnormality has been detected in the analysis range for each target data point. The classification reliability calculation unit 240 further reads out the classification results from the data storage unit 160.

[0112] The classification reliability calculation unit 240 calculates, for each joint where an abnormality exists in the abnormal measurement information, the ratio of abnormalities detected in the analysis range, from the combination of information identifying the joint of the rail and information indicating whether or not an abnormality has been detected in the analysis range. Then, the classification reliability calculation unit 240 calculates the classification reliability based on the ratio of detected abnormalities for each classification to which the joints with abnormalities detected in the abnormal measurement information belong. The classification reliability is, for example, a value representing the degree of likelihood of detecting an abnormality in a situation corresponding to the classification when an abnormality has occurred in the joint. The classification reliability calculation unit 240 may set a higher classification reliability, for example, the higher the likelihood of detecting an abnormality from the analysis range observed at the joint where the abnormality has occurred. The classification reliability calculation unit 240 may use the ratio of detected abnormalities for each classification as the classification reliability. The classification reliability calculation unit 240 may calculate the classification reliability according to an expression representing the relationship between the ratio of detected abnormalities and the classification reliability.

[0113] The classification reliability calculation unit 240 assigns the classification reliability calculated for the classification based on at least either the environmental information and attributes at the time when the abnormal data was observed to the abnormal data stored in the data storage unit 160. In other words, the classification reliability calculation unit 240 stores the classification reliability for each classification in the data storage unit 160. Then, the classification reliability calculation unit 240 associates the object reliability calculated for the classification based on at least either the environmental information and attributes at the time when the abnormal data was observed with the abnormal data stored in the data storage unit 160.

[0114] The classification reliability calculation unit 240 may send the classification reliability for each classification to the output unit 170.

[0115] <Output unit 170> The output unit 170 may receive the object reliability for each classification from the classification reliability calculation unit 240. The output unit 170 may output the object reliability for each classification received from the classification reliability calculation unit 240.

[0116] The output unit 170 may read out the abnormal data with classification reliability from the data storage unit 160 and output the read abnormal data.

[0117] <Operation> Next, the operation of the data collection device 101E according to the seventh embodiment of the present disclosure will be described in detail with reference to the drawings.

[0118] FIG. 11 is a flowchart showing an example of the operation of the data collection device 101E according to the seventh embodiment of the present disclosure. At the start of the operation shown in FIG. 11, classification information is stored in the data storage unit 160. Also, the result of abnormality detection in the analysis range based on the target data points detected from a plurality of sets of acoustic data is stored in the data storage unit 160. Further, abnormal measurement information is stored in the data storage unit 160.

[0119] In the example shown in FIG. 11, the classification reliability calculation unit 240 reads out the result of abnormality detection, classification information, and abnormal measurement information from the data storage unit 160 (step S401). At the time when the operation of step S401 ends, no classification has been selected.

[0120] If there is an unselected classification (YES in step S402), the classification reliability calculation unit 240 selects one classification from the unselected classifications (step S403). The classification reliability calculation unit 240 extracts the result of abnormality detection in the analysis range of the target (i.e., the rail joint) where the abnormal data classified into the selected classification is detected (step S404). The classification reliability calculation unit 240 calculates the ratio of the detection of abnormalities in the analysis range of the target (i.e., the rail joint) where the abnormal data classified into the selected classification is detected (step S405). The classification reliability calculation unit 240 calculates the classification reliability for each classification based on the calculated ratio (step S406). The operation of the data collection device 101E returns to step S402 after step S406.

[0121] When there is no unselected classification (NO in step S402), the output unit 170 outputs the classification confidence of each classification (step S407). In step S407, the output unit 170 may output abnormal data to which the classification confidence is assigned.

[0122] <Eighth Modification of the Second Embodiment> FIG. 12 is a block diagram showing an example of the configuration of a data collection device 101F according to the eighth modification of the second embodiment of the present disclosure. In the example shown in FIG. 12, the data collection device 101F of this modification includes a target confidence calculation unit 230 in addition to all of the components of the data collection device 101F according to the seventh modification. The data collection device 101F of this modification has the same functions as those of the data collection device 101D of the fifth or sixth modification in addition to the functions of the data collection device 101E of the seventh modification. The data collection device 101F of this modification performs the same operations as those of the data collection device 101D of the fifth or sixth modification in addition to the operations of the data collection device 101E of the seventh modification.

[0123] <Other Embodiments> Each of the data collection devices according to the embodiments of the present disclosure can be realized by a computer including a processor that executes a program loaded into a memory. Each of the data collection devices according to the embodiments of the present disclosure can also be realized by dedicated hardware. Each of the data collection devices according to the embodiments of the present disclosure can also be realized by a combination of the above-described computer and dedicated hardware.

[0124] FIG. 13 is a diagram showing an example of the hardware configuration of a computer 1000 that can implement each of the data collection devices according to the embodiments of the present disclosure. In the example shown in FIG. 13, the computer 1000 includes a processor 1001, a memory 1002, a storage device 1003, and an I / O (Input / Output) interface 1004. Further, the computer 1000 can access a storage medium 1005. The memory 1002 and the storage device 1003 are storage devices such as, for example, a RAM (Random Access Memory) and a hard disk. The storage medium 1005 is a storage device such as, for example, a RAM, a hard disk, a ROM (Read Only Memory), or a removable storage medium. The storage device 1003 may be the storage medium 1005. The processor 1001 can read and write data and programs to and from the memory 1002 and the storage device 1003. The processor 1001 can access, for example, another device such as a server via the I / O interface 1004. The processor 1001 can access the storage medium 1005. A program for operating the computer 1000 as a data collection device according to the embodiments of the present disclosure is stored in the storage medium 1005.

[0125] The processor 1001 loads into the memory 1002 a program for operating the computer 1000 as a data collection device according to the embodiments of the present disclosure, which is stored in the storage medium 1005. Then, by executing the program loaded into the memory 1002, the computer 1000 operates as a data collection device according to the embodiments of the present disclosure.

[0126] The data reception unit 110, target detection unit 120, determination unit 130, anomaly detection unit 140, classification unit 150, and output unit 170 can be realized, for example, by a processor 1001 that executes a program loaded in a memory 1002. The environment information reception unit 210, attribute reception unit 220, target reliability calculation unit 230, and classification reliability calculation unit 240 can be realized, for example, by a processor 1001 that executes a program loaded in a memory 1002. The data storage unit 160 can be realized by a storage device 1003 such as a memory 1002 or a hard disk device included in the computer 1000. Part or all of the data reception unit 110, target detection unit 120, determination unit 130, anomaly detection unit 140, classification unit 150, data storage unit 160, and output unit 170 can also be realized by a dedicated circuit that realizes the functions of each unit. Part or all of the environment information reception unit 210, attribute reception unit 220, target reliability calculation unit 230, and classification reliability calculation unit 240 can also be realized by a dedicated circuit that realizes the functions of each unit.

[0127] Also, part or all of the above-described embodiments can be described as follows in the appended claims, but are not limited thereto.

[0128] (Appended Note 1) In acoustic data obtained by observing a target, target detection means for detecting a target data point that is a data point at which the target is observed; Determination means for determining an analysis range in the acoustic data based on the target data point; Anomaly detection means for detecting an anomaly in the analysis range; Output means for outputting information on the analysis range in which the anomaly is detected; A data collection device comprising:

[0129] (Appended Note 2) The determination means excludes an exclusion range that is shorter than the analysis range and includes the target data point from the analysis range. The data collection device according to Appended Note 1.

[0130] (Appended Note 3) When the abnormality is detected, the output means stores the information of the analysis range in an abnormality database. The data collection device according to Appendix 1 or 2.

[0131] (Appendix 4) Classification means for classifying the information of the analysis range based on the type of the detected abnormality The data collection device according to Appendix 3, further comprising the same.

[0132] (Appendix 5) Environment information receiving means for receiving environment information of the observation of the target further comprising The classification means classifies the information of the analysis range based on the environment information. The data collection device according to Appendix 4.

[0133] (Appendix 6) Attribute receiving means for receiving the attribute of the target further comprising The classification means classifies the information of the analysis range based on the attribute. The data collection device according to Appendix 4 or 5.

[0134] (Appendix 7) Classification reliability calculation means for calculating classification reliability for each classification in which the information of the analysis range is classified based on the ratio at which an abnormality is detected in the target in which the abnormality is detected. The data collection device according to any one of Appendices 4 to 6, further comprising the same.

[0135] (Appendix 8) Target reliability calculation means for calculating the target reliability of the abnormality information of the target based on the ratio at which the abnormality is detected in a plurality of measurements in the target in which the abnormality is detected. The data collection device according to any one of Appendices 1 to 7, further comprising the same.

[0136] (Appendix 9) The abnormality detection means determines the urgency of the abnormality that has occurred in the target based on the type of the detected abnormality. The data collection device according to any one of Appendices 1 to 8.

[0137] (Appendix 10) The target is a joint of a rail. The data collection device according to any one of Appendices 1 to 9.

[0138] (Appendix 11) In the acoustic data obtained by observing the target, a target data point that is the data point at which the target is observed is detected. Based on the target data point, an analysis range in the acoustic data is determined. An abnormality is detected within the analysis range. Information on the analysis range in which the abnormality is detected is output. Data collection method.

[0139] (Appendix 12) An exclusion range that is shorter than the analysis range and includes the target data point is excluded from the analysis range. The data collection method according to Appendix 11.

[0140] (Appendix 13) When the abnormality is detected, the information on the analysis range is stored in an abnormality database. The data collection method according to Appendix 11 or 12.

[0141] (Appendix 14) Classify the information on the analysis range based on the type of the detected abnormality. The data collection method according to Appendix 13.

[0142] (Appendix 15) Receive environmental information on the observation of the target. Classify the information on the analysis range based on the environmental information. The data collection method according to Appendix 14.

[0143] (Appendix 16) Receive the attributes of the target, Classify the information within the analysis range based on the attributes The data collection method described in Appendix 14 or 15.

[0144] (Appendix 17) Calculate the classification reliability for each classification into which the information within the analysis range is classified, based on the ratio at which an abnormality is detected in the target in which the abnormality has been detected. The data collection method described in any one of Appendices 14 to 16.

[0145] (Appendix 18) In a plurality of measurements on the target in which the abnormality has been detected, calculate the target reliability of the abnormality information of the target based on the ratio at which the abnormality has been detected. The data collection method described in any one of Appendices 11 to 17.

[0146] (Appendix 19) Determine the urgency of the abnormality that has occurred in the target, based on the type of the detected abnormality. The data collection method described in any one of Appendices 11 to 18.

[0147] (Appendix 20) The target is a rail joint The data collection method described in any one of Appendices 11 to 19.

[0148] (Appendix 21) In the acoustic data obtained by observing the target, a target detection process for detecting a target data point that is the data point at which the target has been observed, A determination process for determining an analysis range in the acoustic data based on the target data point, An abnormality detection process for detecting an abnormality within the analysis range, An output process for outputting information on the analysis range in which the abnormality has been detected, A storage medium storing a program for causing a computer to execute the above.

[0149] (Appendix 22) The determination process excludes an exclusion range that is shorter than the analysis range and includes the target data point from the analysis range. The storage medium according to Appendix 21.

[0150] (Appendix 23) When the abnormality is detected, the output process stores the information of the analysis range in an abnormal database. The storage medium according to Appendix 21 or 22.

[0151] (Appendix 24) The program A classification process for classifying the information of the analysis range based on the type of the detected abnormality The storage medium according to Appendix 23, which further causes a computer to execute the process.

[0152] (Appendix 25) The program An environmental information reception process for receiving environmental information of the observation of the target further causes a computer to execute, The classification process classifies the information of the analysis range based on the environmental information. The storage medium according to Appendix 24.

[0153] (Appendix 26) The program An attribute reception process for receiving an attribute of the target further causes a computer to execute, The classification process classifies the information of the analysis range based on the attribute. The storage medium according to Appendix 24 or 25.

[0154] (Appendix 27) The program A classification confidence level calculation process for calculating a classification confidence level for each classification in which the information of the analysis range is classified based on the ratio at which an abnormality is detected in the target in which the abnormality is detected The storage medium according to any one of Appendices 24 to 26, which further causes a computer to execute.

[0155] (Appendix 28) The program is In a plurality of measurements on the target in which the abnormality is detected, a target reliability calculation process for calculating the target reliability of the abnormality information of the target based on the ratio at which the abnormality is detected The storage medium according to any one of Appendices 21 to 27, which further causes a computer to execute.

[0156] (Appendix 29) The abnormality detection process determines the urgency of the abnormality that has occurred in the target based on the type of the detected abnormality The storage medium according to any one of Appendices 21 to 28.

[0157] (Appendix 30) The target is a joint of a rail The storage medium according to any one of Appendices 21 to 29.

[0158] The present invention has been described above with reference to the embodiments, but the present invention is not limited to the above embodiments. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

Explanation of Signs

[0159] 100 Data collection device 101 Data collection device 101A Data collection device 101B Data collection device 101C Data collection device 101D Data collection device 101E Data collection device 101F Data collection device 110 Data reception unit 120 Target detection unit 130 Decision unit 140 Abnormality detection unit 150 Classification unit 160 Data storage unit 170 Output unit 210 Environment information reception unit 220 Attribute reception unit 230 Target reliability calculation unit 240 Classification reliability calculation unit 1000 Computer 1001 Processor 1002 Memory 1003 Storage device 1004 I / O interface 1005 Storage medium

Claims

1. In acoustic data obtained by observing a target that is a rail joint, a target detection means for detecting a target data point that is a data point at which the target is observed; Determination means for determining an analysis range in the acoustic data based on the target data point; Anomaly detection means for detecting an anomaly in the analysis range and identifying the joint of the rail from which the data of the target data point on which the analysis range is based is obtained; Classification means for classifying the information of the analysis range based on the type of the detected anomaly; Classification confidence calculation means for calculating a classification confidence for each classification into which the information of the analysis range is classified based on the ratio at which the anomaly is detected in the analysis range where the anomaly is detected; Target confidence calculation means for calculating a target confidence representing the ratio at which the anomaly is detected for the joint where it is confirmed by visual inspection that an anomaly exists, and setting the target confidence for the joint where it is confirmed by visual inspection that no anomaly exists to zero; Output means for outputting the information of the analysis range, which is the information of the analysis range where the anomaly is detected and to which the target confidence of the joint from which the acoustic data of the analysis range is obtained is assigned, the target confidence for each joint, and the classification confidence for each classification; A data collection device comprising the above.

2. The determination means excludes an exclusion range that is shorter than the analysis range and includes the target data point from the analysis range. The data collection device according to Claim 1.

3. When the anomaly is detected, the output means stores the information of the analysis range in an anomaly database. The data collection device according to Claim 1 or 2.

4. Environment information reception means for receiving environment information of the observation of the target further comprising: The classification means classifies the information of the analysis range based on the environment information. The data collection device according to any one of claims 1 to 3.

5. Attribute receiving means for receiving the attributes of the object further comprising The classification means classifies the information of the analysis range based on the attribute The data collection device according to any one of claims 1 to 4.

6. In the acoustic data obtained by observing an object that is a joint of a rail, a target data point that is a data point where the object is observed is detected, Based on the target data point, a analysis range in the acoustic data is determined, In the analysis range, an abnormality is detected, and the joint of the rail from which the data of the target data point on which the analysis range is based is obtained is specified, Classify the information of the analysis range based on the type of the detected abnormality, Calculate a classification confidence for each classification into which the information of the analysis range is classified based on the ratio at which the abnormality is detected in the analysis range where the abnormality is detected, Calculate a target confidence representing the ratio at which the abnormality is detected for the joint where it is confirmed by visual inspection that an abnormality exists, and set the target confidence for the joint where it is confirmed by visual inspection that no abnormality exists to zero, Output the information of the analysis range in which the abnormality is detected, the information of the analysis range to which the target confidence of the joint from which the acoustic data of the analysis range is obtained is assigned, the target confidence for each joint, and the classification confidence for each classification. Data collection method.

7. In the acoustic data obtained by observing an object that is a joint of a rail, a target detection process for detecting a target data point that is a data point where the object is observed, A determination process for determining an analysis range in the acoustic data based on the target data point, In the analysis range, an abnormality detection process for detecting an abnormality and specifying the joint of the rail from which the data of the target data point based on the analysis range is obtained, a classification process for classifying the information of the analysis range based on the type of the detected abnormality, a classification confidence calculation process for calculating a classification confidence for each classification in which the information of the analysis range is classified based on the ratio at which the abnormality is detected in the analysis range where the abnormality is detected, a target confidence calculation process for calculating a target confidence representing the ratio at which the abnormality is detected for the joint where it is confirmed by visual inspection that an abnormality exists, and setting the target confidence for the joint where it is confirmed by visual inspection that no abnormality exists to zero, an output process for outputting the information of the analysis range in which the abnormality is detected, the information of the analysis range to which the target confidence of the joint from which the acoustic data of the analysis range is obtained is assigned, the target confidence for each joint, and the classification confidence for each classification, A program for causing a computer to execute the above.

Images