WO2022234637A1 - 異常検出装置、異常検出方法及び記憶媒体 - Google Patents
異常検出装置、異常検出方法及び記憶媒体 Download PDFInfo
- Publication number
- WO2022234637A1 WO2022234637A1 PCT/JP2021/017460 JP2021017460W WO2022234637A1 WO 2022234637 A1 WO2022234637 A1 WO 2022234637A1 JP 2021017460 W JP2021017460 W JP 2021017460W WO 2022234637 A1 WO2022234637 A1 WO 2022234637A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- abnormality
- data
- information
- target
- analysis range
- Prior art date
Links
- 230000005856 abnormality Effects 0.000 title claims abstract description 226
- 238000001514 detection method Methods 0.000 title claims abstract description 114
- 238000004458 analytical method Methods 0.000 claims abstract description 192
- 238000013480 data collection Methods 0.000 claims abstract description 152
- 238000004364 calculation method Methods 0.000 claims description 66
- 238000000034 method Methods 0.000 claims description 55
- 230000008569 process Effects 0.000 claims description 26
- 230000007717 exclusion Effects 0.000 claims description 23
- 230000007613 environmental effect Effects 0.000 claims description 22
- 238000005259 measurement Methods 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 6
- 230000004048 modification Effects 0.000 description 77
- 238000012986 modification Methods 0.000 description 77
- 230000002159 abnormal effect Effects 0.000 description 39
- 238000013500 data storage Methods 0.000 description 38
- 238000010586 diagram Methods 0.000 description 18
- 230000006870 function Effects 0.000 description 16
- 238000009825 accumulation Methods 0.000 description 12
- 230000000694 effects Effects 0.000 description 6
- 230000009471 action Effects 0.000 description 5
- 230000006866 deterioration Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000002547 anomalous effect Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 239000000853 adhesive Substances 0.000 description 1
- 230000001070 adhesive effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4445—Classification of defects
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61K—AUXILIARY EQUIPMENT SPECIALLY ADAPTED FOR RAILWAYS, NOT OTHERWISE PROVIDED FOR
- B61K9/00—Railway vehicle profile gauges; Detecting or indicating overheating of components; Apparatus on locomotives or cars to indicate bad track sections; General design of track recording vehicles
- B61K9/08—Measuring installations for surveying permanent way
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L23/00—Control, warning or like safety means along the route or between vehicles or trains
- B61L23/04—Control, warning or like safety means along the route or between vehicles or trains for monitoring the mechanical state of the route
- B61L23/042—Track changes detection
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
- B61L27/50—Trackside diagnosis or maintenance, e.g. software upgrades
- B61L27/53—Trackside diagnosis or maintenance, e.g. software upgrades for trackside elements or systems, e.g. trackside supervision of trackside control system conditions
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/14—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object using acoustic emission techniques
Definitions
- the present disclosure relates to technology for detecting anomalies.
- Patent Document 1 and Cited Document 4 based on the relationship between the axle box acceleration applied to the axle box of the vehicle, the vertical deviation of the rail at the traveling point of the vehicle, and the stress applied to the joint plate of the adhesive insulation rail, measured A method is disclosed for estimating the stress applied to the fish plate from the self axle box acceleration and the elevation deviation.
- Patent Document 2 discloses a device that uses a gauge to measure the size of the gap formed at the joint of rails.
- Patent Document 3 discloses a method of Fourier transforming an acoustic signal acquired by a vehicle running on a track and detecting the activation state based on the peak value at predetermined time intervals.
- Patent Document 5 discloses a device for determining abnormality of an axle bearing of an object using vibration data of the object when the distance between the reference point of the object traveling along the track and the track is within a predetermined range. disclosed.
- Patent Document 6 discloses an anomaly detection device that calculates signal pattern features related to an acoustic signal to be anomaly detected and calculates an anomaly score for performing anomaly detection based on the signal pattern features.
- a signal pattern feature of an acoustic signal to be detected as an anomaly is based on an acoustic signal having a first duration and a long-term feature quantity calculated from an acoustic signal having a second duration longer than the first duration. It is calculated based on the learned signal pattern model.
- Anomalies such as loose bolts on rail joints may appear as sounds when trains pass. This is an experience known to drivers and the like. In order to train a model that accurately detects anomalies using sound, it is necessary to collect the sounds of trains passing through rail joints where anomalies such as loose bolts have occurred.
- Patent Documents 1 to 6 describe techniques for detecting anomalies. The techniques of Patent Literatures 1 to 6 cannot efficiently collect acoustic data obtained from an abnormal target.
- One of the purposes of the present disclosure is to provide a data collection device or the like that can efficiently collect acoustic data obtained from a subject with an abnormality.
- a data collection device includes target detection means for detecting a target data point, which is a data point at which the target is observed, in acoustic data obtained by observing the target, and based on the target data point, determining means for determining an analysis range in the acoustic data; 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 is detected.
- a data collection method detects a target data point, which is a data point at which the target is observed, in acoustic data obtained by observing the target, and based on the target data point, detects the acoustic An analysis range in the data is determined, an abnormality is detected in the analysis range, and information of the analysis range in which the abnormality is detected is output.
- a program includes a target detection process for detecting a target data point, which is a data point at which the target is observed, in acoustic data obtained by observing the target, and based on the target data point, causes a computer to execute determination processing for determining an analysis range in the acoustic data, abnormality detection processing for detecting an abnormality in the analysis range, and output processing for outputting information on the analysis range in which the abnormality is detected .
- One aspect of the present disclosure is also implemented by a storage medium that stores the above program.
- the present disclosure has the effect of streamlining the collection of acoustic data obtained from a subject with an abnormality.
- FIG. 1 is a block diagram showing an example configuration of a data collection device according to the first embodiment of the present disclosure.
- FIG. 2 is a flowchart representing an example of the operation of the data collection device 100 according to the first embodiment of the present disclosure.
- FIG. 3 is a block diagram showing an example configuration of the data collection device 101 according to the second embodiment of the present disclosure.
- FIG. 4 is a flowchart representing an example of the operation of the data collection device 101 according to the second embodiment of the present disclosure.
- FIG. 5 is a block diagram showing an example configuration of a data collection device 101A according to the first modification of the second embodiment.
- FIG. 6 is a block diagram showing an example configuration of a data collection device 101B according to a second modification of the second embodiment.
- FIG. 1 is a block diagram showing an example configuration of a data collection device according to the first embodiment of the present disclosure.
- FIG. 2 is a flowchart representing an example of the operation of the data collection device 100 according to the first embodiment of the present disclosure.
- FIG. 7 is a block diagram showing an example configuration of a data collection device 101C according to the third modification of the second embodiment.
- FIG. 8 is a block diagram showing an example configuration of a data collection device 101D according to the fifth modification of the second embodiment of the present disclosure.
- FIG. 9 is a flow chart showing an example of the operation of the data collection device 101D according to the fifth modified example of the second embodiment of the present disclosure for assigning target reliability.
- FIG. 10 is a block diagram showing an example configuration of a data collection device 101E according to the seventh modification of the second embodiment of the present disclosure.
- FIG. 11 is a flow chart showing an example of the operation of the data collection device 101E according to the seventh embodiment of the present disclosure.
- FIG. 12 is a block diagram showing an example configuration of a data collection device 101F according to the eighth modification of the second embodiment of the present disclosure.
- FIG. 13 is a diagram showing an example of a hardware configuration of computer 1000 that can implement each of the data collection devices according to the embodiments of the present disclosure.
- FIG. 1 is a block diagram showing an example configuration of a data collection device according to the first embodiment of the present disclosure.
- the data collection device 100 includes a target detection section 120 , a determination section 130 , an abnormality detection section 140 and an output section 170 .
- the target detection unit 120 detects target data points, which are data points at which the target is observed, in acoustic data obtained by observing the target.
- a determination unit 130 determines an analysis range in the acoustic data based on the target data points.
- the determination unit 130 detects an abnormality in the analysis range.
- the output unit 170 outputs information on the analysis range in which the abnormality is detected.
- the data obtained by observation is vibration data, but the data obtained by observation may be vibration data instead of acoustic data.
- Acoustic data is, for example, time-series data representing changes in acoustics obtained by converting data observed by sensors attached to vehicles traveling on railroad tracks into data in the frequency domain.
- the sensors are, for example, acoustic sensors, such as microphones, or sensors, such as vibration sensors, capable of observing the sounds or vibrations emitted by the vehicle as it passes over rail joints.
- the sensor will be described as being an acoustic sensor.
- the location where the sensor is mounted may be, for example, a lower portion of the vehicle, such as near the truck or rails of the vehicle.
- the location where the sensor is mounted may be the portion of the vehicle that rests on a truck.
- the location where the sensor is mounted may be on the surface of the bogie or vehicle.
- the location where the sensor is mounted may be inside the bogie or vehicle.
- Data at individual time points included in the acoustic data are hereinafter referred to as element data.
- the method of conversion may be any of a variety of existing methods.
- the object is, for example, a rail joint.
- Data points of interest are, for example, data observed when the wheel closest to the sensor passes a rail joint.
- the target detection unit 120 detects, for example, a point in the acoustic data at which the sound pressure has a maximum value equal to or greater than a threshold as a target data point.
- Acoustic data may be associated with the time of observation. For example, the time interval of each element data of acoustic data and the start time of observation of acoustic data are given. Each element data of the acoustic data may be associated with an observation time. Furthermore, the running 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, as target data points, points in the acoustic data at which the sound pressure has a maximum value greater than or equal to a threshold. In this case, the target detection unit 120 further calculates the time at which the next target data point is obtained based on the time at which the detected target data point was observed, the running speed of the vehicle, and the length of the rail.
- 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 at which the sound pressure has a maximum value equal to or greater than the threshold from data observed during a predetermined time period including the calculated time.
- the location of observation obtained using, for example, GPS (Global Positioning System) may be associated with the time of observation.
- the object detection unit 120 may use the relationship between the observation location and the observation time to estimate the time when the rail joint was passed during the period when the observation data was obtained.
- the target detection unit 120 may detect the data observed at the estimated time as the target data point.
- the target detection unit 120 may detect, as target data points, points at which the sound pressure has a maximum value equal to or greater than a threshold from data observed during a predetermined time span including the estimated time.
- the determining unit 130 selects a predetermined time (second predetermined time) after the time when the target data point is observed from a time before the time when the target data point is observed (referred to as a first predetermined time).
- the data obtained during the time period may be determined 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 period and the second predetermined time period 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 period and the second predetermined time period may be set so as to become shorter as the traveling speed of the vehicle increases.
- the range of observation data from the time a first predetermined time before the time the target data point was observed to the time a second predetermined time after the time the target data point was observed is defined as the influence Described as a 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.
- the influence range is the part of the acoustic data observed between the influence start time and the influence end time.
- the determining unit 130 may determine the range of influence to be the range of analysis.
- the determination unit 130 may determine, as the analysis range, a range of the influence range that includes the target data point and excludes a range with a length shorter than the length of the influence range (denoted as an exclusion range).
- the start time of the exclusion range is referred to as exclusion start time.
- the end time of the exclusion range is referred to as exclusion end time.
- the exclusion start time is determined to be later than the influence start time.
- the exclusion end time is determined to be earlier than the influence end time.
- the time from the exclusion start time to the time when the target data point is observed is referred to as a third predetermined time.
- the time from the time when the target data point is observed to the exclusion end time is referred to as a fourth predetermined time.
- the third predetermined time and the fourth predetermined time may be fixed.
- the third predetermined time period and the fourth predetermined time period 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 set so as to become shorter as the traveling speed of the vehicle increases.
- the determination unit 130 determines the range obtained by removing the exclusion range from the influence range as the analysis range. In other words, the determination unit 130 determines the range of acoustic data observed between the influence start time and the exclusion start time, and the range of acoustic data observed between the exclusion end time and the influence end time as follows: Determine the scope of analysis.
- the anomaly detection unit 140 detects an anomaly in the analysis range. Specifically, the anomaly detection unit 140 detects an anomaly pattern that occurs when an anomaly exists in a rail joint, for example, in the analysis range.
- An anomalous pattern may be, for example, an intensity peak present between 10 and 20 Hz.
- the abnormal pattern may be an intensity peak present between 10 and 20 Hz and attributed to the hair for more than a predetermined period of time.
- the abnormal pattern may be, for example, a pattern obtained by learning in advance.
- the abnormality detection unit 140 determines that an abnormality has been detected in the rail joint.
- the abnormality detection unit 140 may extract features of the detected abnormal pattern.
- a feature of the abnormal pattern may be, for example, the duration of intensity peaks present between 10 and 20 Hz in the analysis range.
- Anomaly patterns are characterized, for example, by the duration of an intensity peak between 10 and 20 Hz in the analysis range prior to the time the data point of interest was observed, and the time the data point of interest was observed. It may be the duration of the intensity peak later than 10-20 Hz.
- the features of the abnormal pattern are not limited to these examples.
- the anomaly detection unit 140 may detect an anomaly in a rail joint by, for example, a detector that detects an anomaly in a rail joint obtained by learning in advance.
- the output unit 170 outputs information on the analysis range in which the abnormality was detected.
- the information on the analysis range in which the abnormality was detected is, for example, acoustic data in the analysis range.
- the information of the analysis range in which the abnormality was detected is, for example, the acoustic data in the analysis range and the characteristics of the detected abnormality.
- the output unit 170 may output information on the analysis range in which an abnormality was detected to the display of the data collection device 100.
- the output unit 170 may store information on the analysis range in which an abnormality was detected in the storage device.
- This storage device may be an external storage device, server, or the like connected to the data collection device 100 .
- This storage device may be a storage device installed inside the data collection device 100 .
- This storage device may be a storage medium that can be read and written by the data collection device 100 .
- FIG. 2 is a flowchart representing an example of the operation of the data collection device 100 according to the first embodiment of the present disclosure.
- the target detection unit 120 first detects target data points in the acoustic data (step S101).
- the object detector 120 may detect one or more object data points present in the acoustic data.
- the object detector 120 may detect all object data points present in the acoustic data.
- the determining unit 130 determines the analysis range based on the target data points in the acoustic data (step S102).
- the determination unit 130 may determine the analysis range for each target data point detected in step S101.
- the anomaly detection unit 140 detects an anomaly in the determined analysis range (step S103).
- the anomaly detection unit 140 may detect an anomaly in each of the analysis ranges determined in step S102.
- the data collection device 100 terminates the operation shown in FIG.
- the output unit 170 of the data collection device 100 may output information indicating that no abnormality was detected in the acoustic data before ending the operation shown in FIG.
- the output unit 170 outputs information on the analysis range in which the abnormality was detected.
- the output unit 170 may output information on the analysis range in which an abnormality was detected for each analysis range in which an abnormality was detected.
- the present disclosure has the effect of streamlining the collection of acoustic data obtained from a subject with an abnormality. This is because 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.
- FIG. 3 is a block diagram showing an example configuration of the data collection device 101 according to the second embodiment of the present disclosure.
- the data collection device 101 includes a data reception unit 110, a target detection unit 120, a determination unit 130, an anomaly 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 environment information reception unit 210 .
- the data collection device 101 may further include an attribute reception unit 220.
- the data reception unit 110 receives acoustic data representing sounds observed by a sensor (for example, a microphone) attached to, for example, a truck of a vehicle.
- the data reception unit 110 may receive acoustic data directly from the sensor.
- the data reception unit 110 may receive acoustic data accumulated in a server or the like from the server or the like.
- the acoustic data received by the data receiving unit 110 may be data in the frequency domain.
- the acoustic data received by the data receiving 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.
- the data reception unit 110 sends the acoustic data to the object detection unit 120.
- the object detection unit 120 receives acoustic data from the data reception unit 110 . Similar to the object detection unit 120 of the first embodiment, the object detection unit 120 detects object data points, which are data points at which objects are observed, in the acoustic data. The object detection unit 120 sends information representing the detected object data points to the determination unit 130 .
- the information representing the target data point is information specifying the target data point in the acoustic data.
- the information representing the data point of interest may be the time at which the data of the data point of interest was observed.
- the information representing the target data point may be a number indicating the order of the data of the target data point in the acoustic data, which is time-series information.
- the information representing the target data point may be identification information such as a number assigned to the data of the target data point in the acoustic data, which is time-series information.
- specifying data observed at a certain time in acoustic data is referred to as specifying information.
- the determiner 130 receives information representing target data points from the target detector 120 .
- the determining unit 130 determines the analysis range in the acoustic data based on the target data points, like the determining unit 130 of the first embodiment.
- the determination unit 130 sends information representing the determined analysis range to the abnormality detection unit 140 .
- the information representing the analysis range may be the influence start time and the influence end time.
- the information representing the scope of analysis includes information such as numbers or identifiers that identify the data observed at the time the impact started (i.e. identification information), and numbers or identifiers that identify the data observed at the time the impact ends. information (that is, specific information);
- 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 that indicates the scope of analysis consists of the specific information of the data observed at the start time of the influence, the specific information of the data observed at the start time of exclusion, the specific information of the data observed at the end time of exclusion, and the specific information of the data observed at the end time of the impact. and specific information of the observed data.
- the anomaly detection unit 140 receives information representing the determined analysis range from the determination unit 130 .
- the anomaly detection unit 140 detects an anomaly in the analysis range in the same manner as the anomaly detection unit 140 of the first embodiment.
- the anomaly detection unit 140 sends information about the detected anomaly and information about the analysis range in which the anomaly was detected to the classification unit 150 .
- the anomaly detection unit 140 may detect multiple types of anomalies in the analysis range.
- the anomaly detection unit 140 may detect an anomaly pattern in the analysis range, and determine that an anomaly has been detected when the anomaly pattern is detected.
- An anomaly pattern may be represented by a combination of one or more frequency bands, including, for example, peaks.
- An abnormal pattern may be represented, for example, by a combination of one or more frequency bands containing peaks and the peak intensity ratio in each frequency band. Abnormal patterns may differ from the above examples.
- the anomaly detection unit 140 may identify an anomaly pattern that best matches the acoustic data in the analysis range among the plurality of anomaly patterns.
- the anomaly detection unit 140 may calculate a score representing the degree of matching between the acoustic data in the analysis range and each of the plurality of anomaly patterns. A score may be appropriately defined to represent the degree of match.
- the type of abnormality may be, for example, bolt breakage at a rail joint, bolt loosening at a rail joint, or the like.
- the plurality of abnormality patterns include an abnormality pattern when bolt loosening occurs at the rail joint and an abnormality pattern when bolt breakage occurs at the rail joint.
- the anomaly detection unit 140 may detect an anomaly using a plurality of anomaly patterns that differ depending on weather, temperature, vehicle type, vehicle weight, and the like. In this case, when at least one of the plurality of abnormal patterns is detected in the analysis range, the abnormality detection unit 140 may determine that a type of abnormality corresponding to the detected abnormality pattern has been detected.
- These multiple abnormal patterns are, for example, abnormal patterns obtained in advance by learning.
- the anomaly detection unit 140 may detect an anomaly using the detector described above.
- the abnormality detection unit 140 may detect an abnormality using a plurality of detectors that differ depending on the weather, temperature, type of vehicle, weight of the vehicle, and the like. In this case, if any detector detects an abnormality, the abnormality detection unit 140 may determine that a type of abnormality corresponding to the detector that detected the abnormality has been detected in the analysis range.
- These multiple detectors are, for example, detectors obtained in advance by learning.
- the anomaly detection unit 140 collects anomaly information (for example, information including information specifying the type of the detected anomaly and characteristics of the detected anomaly) and information specifying acoustic data in the analysis range in which the anomaly was detected. , may be sent to the classification unit 150 .
- anomaly information for example, information including information specifying the type of the detected anomaly and characteristics of the detected anomaly
- the classification unit 150 may be sent to the classification unit 150 .
- the analysis range in which an abnormality is detected is also referred to as the analysis range in which an abnormality is detected.
- the classification unit 150 receives, from the anomaly detection unit 140, information on the detected anomaly and information on the analysis range in which the anomaly was detected.
- the anomaly information includes, for example, information representing the detected anomaly (for example, data included in the analysis range of the observation data) and characteristics of the detected anomaly (for example, information specifying the type of the detected anomaly). may contain.
- the classification unit 150 classifies the analysis range in which an abnormality is 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 anomaly types. The classification may be the type of anomaly. The types of abnormalities are not limited to the above examples. The classification unit 150 may classify data in the analysis range in which anomalies are detected into categories associated with the types of detected anomalies. The classification unit 150 may classify the analysis range in which the abnormal pattern is detected into a classification associated with the abnormal pattern that best matches the analysis range. Classification may be determined based on other information. Classification based on other information will be described later as a modification.
- the classification unit 150 stores, in the data storage unit 160, information on the analysis range in which the abnormality was detected and information on the classification into which the analysis range was classified.
- the classification unit 150 may assign the degree of urgency corresponding to the classification to the information of the analysis range in which an abnormality was detected. For example, the classification unit 150 assigns the information on the analysis range in which an abnormality is detected, classified as bolt breakage, to the information in the analysis range in which an abnormality is detected, which is classified as bolt looseness, rather than the urgency given to the information in the analysis range where an abnormality is detected. Assign an urgency level to indicate that the urgency is high.
- FIG. 4 is a flowchart representing an example of the operation of the data collection device 101 according to the second embodiment of the present disclosure.
- the data reception unit 110 receives observation data (step S101).
- the target detection unit 120 detects target data points in the observation data (step S102).
- the determination unit 130 determines the analysis range based on the target data points (step S103).
- the anomaly detection unit 140 detects an anomaly in the analysis range (step S104). If no abnormality is detected (NO in step S105), data collection device 101 terminates the operation shown in FIG.
- the classification unit 150 classifies the data in the analysis range in which the abnormality is detected (step S206).
- the classification unit 150 may store in the data accumulation unit 160 the abnormal data, which is information about the analysis range in which the abnormality was detected, and the classification of the abnormal data.
- the classification unit 150 may send to the output unit 170 the abnormal data, which is information on the analysis range in which the abnormality was detected, and the classification of the abnormal data. Then, the output unit 170 outputs the abnormal data, which is the information of the analysis range in which the abnormality is detected, and the classification of the abnormal data (step S207).
- FIG. 5 is a block diagram showing an example configuration of a data collection device 101A according to the first modification of the second embodiment. Differences of the data collection device 101A of this modified example from the data collection device 101 of the second embodiment will be described below. Except for differences described below, the data collection device 101A of this modified example has the same functions as the data collection device 101 of the second embodiment, and operates in the same manner.
- a data collection device 101A of this modified example includes an environment information reception unit 210 in addition to all the components of the data collection device 101 of the second embodiment.
- the environment information reception unit 210 receives environment information from another device such as a server that stores information at the time of observation.
- the environmental information includes, for example, the date and time of observation, the temperature at the observation location, and the weather.
- Environmental information is not limited to these examples. Environmental information may not include some or all of them.
- the environment information reception unit 210 sends the received environment information to the classification unit 150 .
- the classification unit 150 of this embodiment receives environment information from the environment information reception unit 210 .
- the classification unit 150 classifies the analysis range in which an abnormality is detected into one of the classifications based on the environment information.
- Classification based on environmental information is, for example, classification determined based on at least one of month, season, temperature, and weather at the time of observation.
- FIG. 6 is a block diagram showing an example configuration of a data collection device 101B according to a second modification of the second embodiment. Differences of the data collection device 101B of this modified example from the data collection device 101 of the second embodiment will be described below. Except for differences described below, the data collection device 101B of this modified example 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 modified example includes an attribute reception unit 220 in addition to all the components of the data collection device 101 of the second embodiment.
- 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 vehicle type, vehicle weight, track information (for example, the degree of deterioration of the rail, the time elapsed since the rail was laid, etc.).
- the degree of deterioration of the rail may be classified according to the frequency with which the vehicle passes the rail.
- the degree of deterioration of the rail may be the degree of deterioration determined visually.
- Attribute information is not limited to these examples. Attribute information does not have to include some or all of them.
- the attribute reception unit 220 sends the received environment information to the classification unit 150.
- the classification unit 150 of this embodiment receives attribute information from the attribute reception unit 220 .
- the classification unit 150 classifies an analysis range in which an abnormality is detected into one of classifications based on attribute information.
- Classification based on attribute information is, for example, classification determined based on at least one of vehicle type, weight category including vehicle weight, and track state category including track information at the time of observation.
- the weight category is a predetermined vehicle weight range.
- the division of the track state is, for example, a predetermined range of time that has elapsed since the rail was laid.
- the classification of the track state may be the degree of deterioration of the rail.
- FIG. 7 is a block diagram showing an example configuration of a data collection device 101C according to the third modification of the second embodiment. Differences of the data collection device 101C of this modified example from the data collection device 101 of the second embodiment will be described below. Except for differences described below, the data collection device 101C of this modified example has the same functions as the data collection device 101 of the second embodiment, and operates in the same manner.
- the data collection device 101B of this modified example includes an environment 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 environment information reception unit 210 of this modification is the same as the environment 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.
- the classification unit 150 of this embodiment receives environment information from the environment information reception unit 210 .
- the classification unit 150 of this embodiment also receives attribute information from the attribute reception unit 220 .
- the classification unit 150 classifies an analysis range in which an abnormality is detected into one of classifications based on at least one of environment information and attribute information.
- a fourth variant of the second embodiment is the same as the second embodiment except for the differences described below.
- the data collection device 101 does not have to include the classification unit 150.
- the classification unit 150 sends information on the analysis range in which the abnormality was detected and information on the classification into which the analysis range is classified to the output unit 170 .
- the output unit 170 receives from the classification unit 150 the information of the analysis range in which the abnormality was detected and the information of the classification into which the analysis range was classified.
- the data collection device 101 of this modification is the same as the data collection device 101 of the second embodiment in other respects.
- FIG. 8 is a block diagram showing an example configuration of a data collection device 101D according to the fifth modification of the second embodiment of the present disclosure.
- a data collection device 101D of this modified example includes a target reliability calculation unit 230 in addition to all the components of the data collection device 101 of the second embodiment.
- the data collection device 101D of this modification has the same functions as the data collection device 101 of the second embodiment except for the differences described below, and the data collection device 101 of the second embodiment operates. works the same as Note that the data collection device 101D of this modified example does not have to include the classification unit 150 . Also, this modification can be applied to the first to third modifications.
- an identifier (hereinafter referred to as a joint identifier) is assigned to each joint of the rail.
- a joint identifier is assigned to each joint of the rail.
- the data reception unit 110 receives, in addition to the acoustic data, data that associates the target data point with the joint of the rail.
- the data that associates the target data point with the rail joint is, for example, data specifying the time at which 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 the joint identifier and the time when the vehicle passed the joint indicated by the joint identifier.
- the data specifying the time at which the vehicle passed through the seam during observation may be data containing a plurality of combinations of the position of the vehicle and the time at which the vehicle was at that position during observation.
- the data receiving unit 110 assumes that the vehicle traveled at a constant speed between two adjacent positions on the track based on a plurality of combinations of vehicle positions and times when the vehicle was at that position. You may calculate the time when it passed the position of the joint of a rail under.
- the abnormality detection unit 140 further generates, for each rail joint (that is, for each detected target data point), a combination of information identifying the rail joint and information representing whether or not an abnormality has been detected. . Specifically, the anomaly detection unit 140 detects an anomaly for each analysis range detected in the acoustic data, and also identifies the rail joint where the data of the target data point based on the analysis range was obtained. . The anomaly detection unit 140 detects, for example, a rail joint where 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, and the data of the target data point based on the analysis range was obtained. Identify as a rail seam. The anomaly detector 140 may use other methods to identify the rail joint where the data for the target data point on which the analysis range is based is obtained.
- the abnormality detection unit 140 detects, for each target data point, information specifying the joint of the rail and information indicating whether or not an abnormality has been detected. is stored in the data storage unit 160 .
- the information on the analysis range in which anomalies are detected is also referred to as anomaly data.
- the data accumulation unit 160 stores information on the analysis range in which an abnormality was detected (that is, abnormality data), information specifying rail joints for each target data point, and information indicating whether or not an abnormality was detected in the analysis range. (hereinafter also referred to as the result of detection of anomalies in the analysis range). In this description, the result of detection of anomalies in the analysis range is also simply referred to as the result of detection of anomalies. As described above, in this modification, multiple sets of acoustic data obtained by multiple observations of the same track are input to the data collection device 101D.
- the data storage unit 160 stores information on the analysis range in which an abnormality was detected, obtained from multiple sets of acoustic data, and information indicating whether or not an abnormality was detected for each rail joint. .
- the data storage unit 160 stores information indicating whether or not an abnormality is detected in the analysis range of the joint of the same rail for each of the plurality of sets of acoustic data.
- the data accumulation unit 160 stores information on the analysis range in which the abnormality was detected.
- the target reliability calculation unit 230 reads information for identifying rail joints and information indicating whether an abnormality has been detected in the analysis range for each target data point, stored in the data storage unit 160 .
- the target reliability calculation unit 230 analyzes each joint where an abnormality has been detected at least once in the analysis range based on a combination of information specifying the rail joint and information indicating whether or not an abnormality has been detected in the analysis range. Calculate the rate at which anomalies are detected in the range. Then, the target reliability calculation unit 230 calculates the target reliability based on the rate at which an abnormality is detected for each joint.
- the target reliability is, for example, a value representing how reliable the data in the analysis range where the abnormality was detected is as the data observed at the joint where the abnormality occurred. In this example, it is assumed that the higher the possibility that an abnormality has occurred at a joint, the higher the probability that an abnormality will be detected in the analysis range data at that joint.
- the target reliability calculation unit 230 may use the rate of detection of anomalies as the target reliability.
- the target reliability calculation unit 230 may calculate the target reliability according to a formula representing the relationship between the rate of abnormality detection and the target reliability.
- the target reliability calculation unit 230 adds to the abnormal data stored in the data storage unit 160 the target reliability calculated for the seam where the abnormal data is observed.
- the target reliability calculation unit 230 stores the target reliability for each joint in the data storage unit 160, and adds the abnormal data stored in the data storage unit 160 to the joint where the abnormal data is observed. Associate the calculated target confidence.
- the target reliability calculation unit 230 may send the target reliability for each joint to the 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 .
- the output unit 170 may read the abnormal data to which the target reliability is assigned from the data storage unit 160 and output the read abnormal data.
- FIG. 9 is a flow chart showing an example of the operation of the data collection device 101D according to the fifth modified example of the second embodiment of the present disclosure for assigning target reliability.
- the results of detection of anomalies in the analysis range based on target data points detected from multiple sets of acoustic data are stored in the data storage unit 160 .
- the target reliability calculation unit 230 reads the results of detection of anomalies in the analysis range (step S301).
- the result of detection of anomalies in the analysis range is a combination of information identifying rail joints and information indicating whether anomalies have been detected in the analysis range for each target data point.
- the target reliability calculation unit 230 extracts the detection result of abnormality in the analysis range for each seam from the read result of detection of abnormality in the analysis range (step S302).
- the object reliability calculation unit 230 calculates, for example, the number of times the object data point is detected and the number of times the object data point is detected and the abnormality in the analysis range based on the object data point as a result of detecting an abnormality in the analysis range for each seam. is detected.
- the target reliability calculation unit 230 then calculates the ratio of anomalies detected in the analysis range (that is, 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 gives the target reliability to the abnormal data stored in the data storage unit 160 (step S305). Specifically, the target reliability calculation unit 230 adds to the abnormality data stored in the data storage unit 160 the target reliability of the seam from which the data of the analysis range in which the abnormality was detected, which is the abnormality data, is obtained. to give
- the data collection device 101D ends the operation shown in FIG.
- 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 those of the data collection device 101D according to the fifth modification of the second embodiment, except for the differences described below. operates in the same manner as the data collection device 101D according to the fifth modification of . Also, this modification can be applied to the first to third modifications.
- an identifier (hereinafter referred to as a joint identifier) is assigned to each joint of the rails, as in the fifth modified example.
- a joint identifier is assigned to each joint of the rails, as in the fifth modified example.
- multiple sets of acoustic data obtained by multiple observations of the same track are input to the data collection device 101D.
- the data receiving unit 110 further receives information (hereinafter referred to as actual measurement information of abnormality) indicating whether or not there is an abnormality visually confirmed, for example, for each joint of the rail.
- the data reception unit 110 sends out the measured abnormality information to the classification unit 150 via the object detection unit 120, the determination unit 130, and the abnormality detection unit 140, for example.
- the classification unit 150 receives the measured abnormality information and stores the received measured abnormality information in the data storage unit 160 .
- the data reception unit 110 may directly store the received abnormal measurement information in the data accumulation unit 160 .
- the data reception unit 110 may send the received abnormal measurement information to the object reliability calculation unit 230 .
- a line connecting the data reception unit 110 and the data storage unit 160 and a line connecting the data reception unit 110 and the object reliability calculation unit 230 are omitted for the sake of simplification of the drawing. .
- the target reliability calculation unit 230 reads the abnormality actual measurement information from the data storage unit 160 .
- the target reliability calculation unit 230 may receive the actual measurement data of the abnormality from the data reception unit 110 .
- the target reliability calculation unit 230 calculates the target reliability of a seam in which an abnormality exists in the abnormality actual measurement information in the same way as the target reliability calculation unit 230 of the fifth modification of the second embodiment calculates the target reliability. Calculate in the same way.
- the target reliability calculation unit 230 sets the target reliability of seams where there is no abnormality to zero in the abnormality actual measurement information.
- FIG. 10 is a block diagram showing an example configuration of a data collection device 101E according to the seventh modification of the second embodiment of the present disclosure.
- the data collection device 101E includes, in addition to all the components of the data collection device 101 according to the second embodiment, an environment information reception unit 210, an attribute reception unit 220, a classification reliability calculation 240. Note that the data collection device 101E does not have to include one of the environment information reception unit 210 and the attribute reception unit 220 . Also, this modification can be applied to the fifth and sixth modifications.
- the data reception unit 110 of this modification has the same functions as the data reception unit 110 of the fifth modification, and performs the same operations as the data reception unit 110 of the fifth modification.
- the data receiving unit 110 receives, in addition to the acoustic data, data that associates the target data points with the joints of the rails.
- the data that associates the target data point with the rail joint is, for example, data specifying the time at which 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 the joint identifier and the time when the vehicle passed the joint indicated by the joint identifier.
- the data specifying the time at which the vehicle passed through the seam during observation may be data containing a plurality of combinations of the position of the vehicle and the time at which the vehicle was at that position during observation.
- the data receiving unit 110 assumes that the vehicle traveled at a constant speed between two adjacent positions on the track based on a plurality of combinations of vehicle positions and times when the vehicle was at that position. You may calculate the time when it passed the position of the joint of a rail under.
- the data receiving unit 110 further includes information indicating whether or not an abnormality exists, for example, visually confirmed for each rail joint (i.e., actual measurement of abnormality). information).
- the data reception unit 110 sends out the measured abnormality information to the classification unit 150 via the object detection unit 120, the determination unit 130, and the abnormality detection unit 140, for example.
- the classification unit 150 receives the measured abnormality information and stores the received measured abnormality information in the data storage unit 160 .
- the data reception unit 110 may directly store the received abnormal measurement information in the data accumulation unit 160 .
- the data reception unit 110 may send the received abnormal measurement information to the classification reliability calculation unit 240 .
- a line connecting the data reception unit 110 and the data storage unit 160 and a line connecting the data reception unit 110 and the classification reliability calculation unit 240 are omitted for the sake of simplification. .
- the abnormality detection section 140 of this modification has the same function as the abnormality detection section 140 of the fifth modification, and performs the same operation as the abnormality detection section 140 of the fifth modification.
- the data storage unit 160 of this modification is the same as the data storage unit 160 of the fifth modification.
- the data accumulation unit 160 stores information on the analysis range in which an abnormality was detected (that is, abnormality data), information specifying rail joints for each target data point, and information indicating whether or not an abnormality was detected in the analysis range.
- a combination of and . As described above, a combination of information indicating whether or not an abnormality has been detected in the analysis range is also expressed as an abnormality detection result in the analysis range and an abnormality detection result.
- multiple sets of acoustic data obtained by multiple observations of the same track are input to the data collection device 101D.
- the data storage unit 160 stores information on the analysis range in which an abnormality was detected, obtained from multiple sets of acoustic data, and information indicating whether or not an abnormality was detected for each rail joint. .
- the data storage unit 160 stores information indicating whether or not an abnormality is detected in the analysis range of the joint of the same rail for each of the plurality of sets of acoustic data.
- the data accumulation unit 160 stores information on the analysis range in which the abnormality was detected.
- the environment information reception unit 210 of this modification is the same as the environment information reception unit 210 of the first modification.
- the environment information reception unit 210 of this modification has the same function as the environment information reception unit 210 of the first modification, and performs the same operation as the environment information reception unit 210 of the first modification. conduct.
- the attribute reception unit 220 of this modification is the same as the attribute reception unit 220 of the second modification.
- the attribute reception unit 220 of this modification has the same function as the attribute reception unit 220 of the second modification, and performs the same operation as the attribute reception unit 220 of the first modification.
- the classification unit 150 has the same function as the classification unit 150 of the first modification, and the same operation as the classification unit 150 of the first modification. Configured to perform an action.
- the classification unit 150 has the same functions as the classification unit 150 of the second modification, and operates in the same manner as the classification unit 150 of the second modification. configured to do
- the classification of this modified example is based on at least one of environmental information and attribute information. Note that if the data collection device 101F does not include the environment information receiving unit 210, the classification in this modification may be based on attribute information. If the data collection device 101F does not include the attribute reception unit 220, the classification of this modification may be based on environmental information.
- the classification unit 150 classifies each detected target data point into one of the classifications.
- the classification unit 150 stores, for each target data point, information representing the classification into which the target data point is classified (hereinafter referred to as a classification result) in the data accumulation unit 160 .
- the data storage unit 160 of this modification functions similarly to the data storage unit 160 of the fifth modification.
- the data accumulation unit 160 of this modification further stores the classification results.
- the classification reliability calculation unit 240 reads the abnormality actual measurement information stored in the data accumulation unit 160 .
- the classification reliability calculation unit 240 may receive the abnormality actual measurement information from the data reception unit 110 .
- the classification reliability calculation unit 240 reads out information specifying rail joints and information indicating whether an abnormality has been detected in the analysis range for each target data point, stored in the data storage unit 160 .
- the classification reliability calculation unit 240 further reads the classification results from the data storage unit 160 .
- the classification reliability calculation unit 240 identifies an abnormality in the analysis range for each joint where an abnormality exists in the abnormality measurement information, based on a combination of information specifying the joint of the rail and information indicating whether an abnormality has been detected in the analysis range. is detected. Then, the classification reliability calculation unit 240 calculates the classification reliability based on the rate at which an abnormality is detected for each classification in which joints in which an abnormality exists in the abnormality measurement information is classified.
- the classification reliability is, for example, a value that indicates the degree of probability that an abnormality will be detected in a situation corresponding to the classification when an abnormality occurs in a seam.
- the classification reliability calculation unit 240 may set a higher classification reliability as the probability of an abnormality being detected from an analysis range observed at a joint where an abnormality has occurred is higher.
- the classification reliability calculation unit 240 may use the rate of detection of an abnormality for each classification as the classification reliability.
- the classification reliability calculation unit 240 may calculate the classification reliability according to a formula representing the relationship between the rate of abnormality detection and the classification reliability.
- the classification reliability calculation unit 240 calculates the classification reliability calculated for the abnormal data stored in the data storage unit 160 for classification based on at least one of the environmental information and attributes when the abnormal data was observed. to give 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 stores the abnormal data stored in the data storage unit 160 in the object calculated for the classification based on at least one of the environmental information and the attributes when the abnormal data was observed. Associate confidence.
- the classification reliability calculation unit 240 may send the classification reliability for each classification to the output unit 170 .
- the output unit 170 may receive the target reliability for each classification from the classification reliability calculation unit 240 .
- the output unit 170 may output the target reliability for each classification received from the classification reliability calculation unit 240 .
- the output unit 170 may read the abnormal data to which the classification reliability is assigned from the data storage unit 160 and output the read abnormal data.
- FIG. 11 is a flowchart representing an example of the operation of the data collection device 101E according to the seventh embodiment of the present disclosure.
- Classification information is stored in the data storage unit 160 at the start of the operation shown in FIG.
- the results of detection of anomalies in the analysis range based on target data points detected from multiple sets of acoustic data are stored in the data storage unit 160 .
- actual measurement information of abnormality is stored in the data storage unit 160 .
- the classification reliability calculation unit 240 reads the abnormality detection result, the classification information, and the abnormality actual measurement information from the data storage unit 160 (step S401). At the time when the operation of step S401 is finished, no classification has been selected.
- the classification reliability calculation unit 240 selects one classification from the unselected classifications (step S403).
- the classification reliability calculation unit 240 extracts the detection result of abnormality in the analysis range of the object (that is, the joint of the rail) in which abnormal data classified into the selected classification is detected (step S404).
- the classification reliability calculation unit 240 calculates the rate of detection of anomalies in the analysis range of objects (that is, joints of rails) in which anomalous data classified into the selected classification is detected (step S405).
- the classification reliability calculation unit 240 calculates classification reliability based on the calculated ratio for each classification (step S406).
- the operation of the data collection device 101E returns to step S402 after step S406.
- the output unit 170 outputs the classification reliability of each classification (step S407).
- the output unit 170 may output the abnormal data to which the classification reliability is assigned.
- FIG. 12 is a block diagram showing an example configuration of a data collection device 101F according to the eighth modification of the second embodiment of the present disclosure.
- the data collection device 101F of this modified example includes all of the components of the data collection device 101F according to the seventh modified example, as well as a target reliability calculation unit 230 .
- the data collection device 101F of this modification has the same functions as 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 operation as the data collection device 101D of the fifth or sixth modification in addition to the operation of the data collection device 101E of the seventh modification.
- Each of the data collection devices according to embodiments of the present disclosure can be implemented by a computer including a processor executing a program loaded in memory.
- Each of the data collection devices according to embodiments of the present disclosure can also be implemented by dedicated hardware.
- Each of the data collection devices according to the embodiments of the present disclosure can also be implemented by a combination of the computer described above and dedicated hardware.
- FIG. 13 is a diagram showing an example of the hardware configuration of computer 1000 that can implement each of the data collection devices according to the embodiments of the present disclosure.
- computer 1000 includes processor 1001 , memory 1002 , storage device 1003 , and I/O (Input/Output) interface 1004 .
- Computer 1000 can also access storage medium 1005 .
- the memory 1002 and the storage device 1003 are storage devices such as RAM (Random Access Memory) and hard disks, for example.
- the storage medium 1005 is, for example, a storage device such as a RAM or hard disk, a ROM (Read Only Memory), or a portable storage medium.
- Storage device 1003 may be storage medium 1005 .
- the processor 1001 can read and write data and programs from the memory 1002 and the storage device 1003 .
- Processor 1001 may access other devices, such as servers, for example, via I/O interface 1004 .
- Processor 1001 can access storage medium 1005 .
- the storage medium 1005 stores a program that causes the computer 1000 to operate as a data collection device according to the embodiment of the present disclosure.
- the processor 1001 loads into the memory 1002 a program stored in the storage medium 1005 that causes the computer 1000 to operate as a data collection device according to the embodiment of the present disclosure.
- the computer 1000 operates as a data collection device according to the embodiment of the present disclosure by the processor 1001 executing the program loaded in the memory 1002 .
- the data reception unit 110, the object detection unit 120, the determination unit 130, the anomaly detection unit 140, the classification unit 150, and the output unit 170 can be implemented by, for example, the processor 1001 that executes a program loaded in the memory 1002.
- the environment information reception unit 210, the attribute reception unit 220, the object reliability calculation unit 230, and the classification reliability calculation unit 240 can be implemented by, for example, the processor 1001 executing a program loaded in the memory 1002.
- the data storage unit 160 can be realized by a memory 1002 included in the computer 1000 and a storage device 1003 such as a hard disk device.
- a part or all of the data reception unit 110, the object detection unit 120, the determination unit 130, the abnormality detection unit 140, the classification unit 150, the data accumulation unit 160, and the output unit 170 are realized by a dedicated circuit that realizes the function of each unit.
- can also Part or all of the environment information reception unit 210, the attribute reception unit 220, the object reliability calculation unit 230, and the classification reliability calculation unit 240 can be realized by a dedicated circuit that realizes the function of each unit.
- An object detection means for detecting an object data point, which is a data point at which the object is observed, in acoustic data obtained by observing the object; determining means for determining a range of analysis in the acoustic data based on the data points of interest; Abnormality detection means for detecting an abnormality in the analysis range; output means for outputting information on the analysis range in which the abnormality is detected;
- a data collection device comprising:
- Appendix 2 The data collection device according to appendix 1, wherein the determining means excludes an exclusion range that is shorter than the analysis range and includes the target data point from the analysis range.
- appendix 4 The data collection device according to appendix 3, further comprising: classifying means for classifying the information of the analysis range based on the type of the detected abnormality.
- Appendix 5 further comprising environmental information receiving means for receiving environmental information of the observation of the target;
- the data collection device according to appendix 4, wherein the classification means classifies the information of the analysis range based on the environment information.
- Appendix 6 further comprising an attribute receiving means for receiving an attribute of the target; 6.
- the data collection device according to appendix 4 or 5, wherein the classification unit classifies the information of the analysis range based on the attribute.
- Supplementary notes 4 to 6 further comprising a classification reliability calculation means for calculating a classification reliability for each classification into which the information in the analysis range is classified based on the rate at which an abnormality is detected in the object in which the abnormality is detected.
- a data collection device according to any one of claims 1 to 3.
- Supplementary notes 1 to 1 further comprising: target reliability calculation means for calculating a target reliability of the information of the abnormality of the target based on the rate at which the abnormality is detected in a plurality of measurements of the target in which the abnormality is detected.
- target reliability calculation means for calculating a target reliability of the information of the abnormality of the target based on the rate at which the abnormality is detected in a plurality of measurements of the target in which the abnormality is detected.
- Appendix 10 10. The data collection device according to any one of Appendices 1 to 9, wherein the target is a joint of rails.
- Appendix 14 14. The data collection method according to appendix 13, wherein the information in the analysis range is classified based on the type of the detected anomaly.
- Appendix 15 Receiving environmental information of observations of the target; 15. The data collection method according to appendix 14, wherein the information in the analysis range is classified based on the environment information.
- Appendix 16 receiving attributes of said object; 16.
- Appendix 17 The data according to any one of appendices 14 to 16, wherein a classification reliability is calculated for each classification into which the information in the analysis range is classified, based on the rate at which an abnormality is detected in the object in which the abnormality is detected. Collection method.
- Appendix 18 18. The method according to any one of appendices 11 to 17, wherein a target reliability of the information of the abnormality of the target is calculated based on the ratio of detection of the abnormality in a plurality of measurements of the target in which the abnormality is detected. data collection methods.
- a storage medium that stores a program that causes a computer to execute
- Appendix 25 Said program causing the computer to further execute environmental information reception processing for receiving environmental information of the observation of the target; 25.
- Appendix 26 Said program causing the computer to further execute an attribute acceptance process for accepting the attributes of the target; 26.
- Appendix 28 Said program causing the computer to further execute a target reliability calculation process for calculating the target reliability of the information of the abnormality of the target based on the ratio of the detection of the abnormality in a plurality of measurements of the target in which the abnormality is detected.
- Appendix 29 29.
- Appendix 30 30.
- 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 determination unit 140 abnormality detection unit 150 classification unit 160 data accumulation unit 170 output unit 210 environmental 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
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Signal Processing (AREA)
- Acoustics & Sound (AREA)
- Biomedical Technology (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
Description
まず、本開示の第1の実施形態について説明する。
図1は、本開示の第1の実施形態に係るデータ収集装置の構成の例を表すブロック図である。
図1に示す例では、データ収集装置100は、対象検出部120と、決定部130と、異常検出部140と、出力部170と、を備える。対象検出部120は、対象の観測によって得られた音響データにおいて、前記対象が観測されたデータ点である対象データ点を検出する。決定部130は、前記対象データ点に基づいて、前記音響データにおける分析範囲を決定する。決定部130は、前記分析範囲において、異常を検出する。出力部170は、前記異常が検出された前記分析範囲の情報を出力する。以下では、観測によって得られるデータは振動データであるとして説明するが、観測によって得られるデータは、音響データではなく、振動のデータであってもよい。
音響データは、例えば、線路を走行する車両等に取り付けられたセンサによって観測されたデータを、周波数領域のデータに変換することによって得られる、音響の推移を表す時系列データである。センサは、例えば、マイクロフォン等の音響センサ、又は、振動センサなどの、車両がレールの継ぎ目を通過する時に発する音響又は振動を観測できるセンサである。以下では、センサは音響センサであるとして説明する。センサが取り付けられる位置は、例えば、車両の台車又はレール付近等の車両の下方の部分であってもよい。センサが取り付けられる位置は、台車に載せられている車両の部分であってもよい。センサが取り付けられる位置は、台車又は車両の表面であってもよい。センサが取り付けられる位置は、台車又は車両の内部であってもよい。音響データが含む個々の時点のデータを、以下では、要素データと表記する。変換の方法は、既存の様々な方法のいずれかであってよい。対象は、例えば、レールの継ぎ目である。対象データ点は、例えば、センサからの距離が最も短い車輪がレールの継ぎ目を通過した時点で観測されたデータである。対象検出部120は、例えば、音響データにおける、音圧が閾値以上の大きさの極大値を取る点を、対象データ点として検出する。
決定部130は、例えば、対象データ点が観測された時刻から所定時間(第1所定時間と表記)前の時刻から、対象データ点が観測された時刻から所定時間(第2所定時間)後の時刻までの期間に得られたデータを、分析範囲に決定してもよい。第1所定時間と第2所定時間は、同じであってもよい。第1所定時間及び第2所定時間は、固定されていてもよい。第1所定時間及び第2所定時間は、対象データ点が観測された時刻における車両の走行の速度に基づいて定められていてもよい。具体的には、第1所定時間及び第2所定時間は、車両の走行の速度が大きいほど短くなるように定められていてもよい。以下の説明では、対象データ点が観測された時刻から第1所定時間前の時刻から、対象データ点が観測された時刻から第2所定時間後の時刻までの間の観測データの範囲を、影響範囲と表記する。影響範囲の開始時刻を、影響開始時刻と表記する。影響範囲の終了時刻を、影響終了時刻と表記する。言い換えると、影響範囲は、影響開始時刻から影響終了時刻までの間に観測された音響データの一部分である。決定部130は、影響範囲を、分析範囲に決定してもよい。
異常検出部140は、分析範囲において、異常を検出する。具体的には、異常検出部140は、例えば、分析範囲において、レールの継ぎ目に異常が存在する場合に生じる異常パターンを検出する。異常パターンは、例えば、10~20Hzの間に存在する、強さのピークであってもよい。異常パターンは、10~20Hzの間に存在し、所定時間以上の間毛帰属する、強さのピークであってもよい。異常パターンは、例えば、あらかじめ学習によって得られているパターンであってもよい。
出力部170は、異常が検出された分析範囲の情報を出力する。異常が検出された分析範囲の情報は、例えば、分析範囲における音響データである。異常が検出された分析範囲の情報は、例えば、分析範囲における音響データと、検出された異常の特徴とである。
次に、本開示の第1の実施形態のデータ収集装置100の動作について、図面を使用して詳細に説明する。
本開示には、異常が生じている対象から得られた音響データの収集を効率化できるという効果がある。その理由は、対象検出部120が対象データ点を検出し、決定部130が対象データ点に基づく分析範囲を決定し、異常検出部140が決定された分析範囲において異常を検出するからである。
次に、本開示の第2の実施形態について、図面を使用して詳細に説明する。
図3は、本開示の第2の実施形態に係るデータ収集装置101の構成の例を表すブロック図である。
データ受付部110は、例えば車両の台車に取り付けられたセンサ(例えばマイクロフォン)によって観測された音響を表す音響データを受け付ける。データ受付部110は、センサから直接音響データを受け付けてもよい。データ受付部110は、サーバ等に蓄積された音響データを、そのサーバなどから受け付けてもよい。
対象検出部120は、データ受付部110から音響データを受け取る。対象検出部120は、第1の実施形態の対象検出部120と同様に、音響データにおいて、対象が観測されたデータ点である対象データ点を検出する。対象検出部120は、検出した対象データ点を表す情報を、決定部130に送出する。
決定部130は、対象検出部120から、対象データ点を表す情報を受け取る。決定部130は、第1の実施形態の決定部130と同様に、対象データ点に基づいて、音響データにおける分析範囲を決定する。決定部130は、決定した分析範囲を表す情報を、異常検出部140に送出する。
異常検出部140は、決定部130から、決定した分析範囲を表す情報を受け取る。異常検出部140は、第1の実施形態の異常検出部140と同様に、分析範囲において、異常を検出する。異常検出部140は、検出した異常の情報と、異常が検出された分析範囲の情報とを、分類部150に送出する。
分類部150は、異常検出部140から、検出した異常の情報と、異常が検出された分析範囲の情報とを受け取る。異常の情報は、例えば、検出した異常を表す情報(例えば、観測データのうち分析範囲に含まれるデータ)と、検出した異常の特徴(例えば、検出された異常の種類を特定する情報)とを含んでいてよい。
次に、本開示の第2の実施形態のデータ収集装置101の動作について、図面を使用して詳細に説明する。
本実施形態には、第1の実施形態の効果と同じ効果がある。その理由は、第1の実施形態の効果が生じる理由と同じである。
図5は、第2の実施形態の第1の変形例に係るデータ収集装置101Aの構成の例を表すブロック図である。以下では、本変形例のデータ収集装置101Aの、第2の実施形態のデータ収集装置101に対する相違点について説明する。以下で説明する相違点を除いて、本変形例のデータ収集装置101Aは、第2の実施形態のデータ収集装置101と同じ機能を備え、同様に動作する。図5に示す例では、本変形例のデータ収集装置101Aは、第2の実施形態のデータ収集装置101のすべての構成要素に加えて、環境情報受付部210を含む。
環境情報受付部210は、観測時の情報を記憶する例えばサーバなどの他の装置から、環境情報を受け付ける。環境情報は、例えば、観測時の、日時、観測の場所における気温、天候などである。環境情報は、これらの例に限られない。環境情報は、これらの一部または全部を含んでいなくてもよい。
本実施形態の分類部150は、環境情報受付部210から環境情報を受け取る。分類部150は、異常が検出された分析範囲を、環境情報に基づく分類のいずれかに分類する。環境情報に基づく分類は、例えば、観測時の、月、季節、気温、天候の少なくともいずれかに基づいて定められる分類である。
図6は、第2の実施形態の第2の変形例に係るデータ収集装置101Bの構成の例を表すブロック図である。以下では、本変形例のデータ収集装置101Bの、第2の実施形態のデータ収集装置101に対する相違点について説明する。以下で説明する相違点を除いて、本変形例のデータ収集装置101Bは、第2の実施形態のデータ収集装置101と同じ機能を備え、同様に動作する。図6に示す例では、本変形例のデータ収集装置101Bは、第2の実施形態のデータ収集装置101のすべての構成要素に加えて、属性受付部220を含む。
属性受付部220は、観測時の情報を記憶する例えばサーバなどの他の装置から、属性情報を受け付ける。属性情報は、車両の種別、車両の重量、軌道情報(例えば、レールの劣化の程度、レールが敷設されてから経過した時間等)などである。レールの劣化の程度は、車両がレールを通過する頻度に応じた、区分であってもよい。レールの劣化の程度は、目視によって判定された劣化の程度であってもよい。属性情報は、これらの例に限られない。属性情報は、これらの一部または全部を含んでいなくてもよい。
本実施形態の分類部150は、属性受付部220から属性情報を受け取る。分類部150は、異常が検出された分析範囲を、属性情報に基づく分類のいずれかに分類する。属性情報に基づく分類は、例えば、観測時の、車両の種別、車両の重量が含まれる重量の区分、軌道情報が含まれる軌道状態の区分の少なくともいずれかに基づいて定められる分類である。重量の区分は、あらかじめ定められた、車両の重量の範囲である。軌道状態の区分は、例えば、あらかじめ定められた、レールが敷設されてから経過した時間の範囲である。軌道状態の区分は、レールの劣化の程度であってもよい。
図7は、第2の実施形態の第3の変形例に係るデータ収集装置101Cの構成の例を表すブロック図である。以下では、本変形例のデータ収集装置101Cの、第2の実施形態のデータ収集装置101に対する相違点について説明する。以下で説明する相違点を除いて、本変形例のデータ収集装置101Cは、第2の実施形態のデータ収集装置101と同じ機能を備え、同様に動作する。図7に示す例では、本変形例のデータ収集装置101Bは、第2の実施形態のデータ収集装置101のすべての構成要素に加えて、環境情報受付部210と、属性受付部220とを含む。本変形例の環境情報受付部210は、第2の実施形態の第1の変形例の環境情報受付部210と同じである。本変形例の属性受付部220は、第2の実施形態の第2の変形例の属性受付部220と同じである。
本実施形態の分類部150は、環境情報受付部210から環境情報を受け取る。本実施形態の分類部150は、さらに、属性受付部220から属性情報を受け取る。分類部150は、異常が検出された分析範囲を、環境情報及び属性情報の少なくともいずれかに基づく分類のいずれかに分類する。
第2の実施形態の第4の変形例は、以下で説明する相違点を除いて、第2の実施形態と同じである。
<構成>
図8は、本開示の第2の実施形態の第5の変形例に係るデータ収集装置101Dの構成の例を表すブロック図である。図8に示す例では、本変形例のデータ収集装置101Dは、第2の実施形態のデータ収集装置101の構成要素の全てに加えて、対象信頼度算出部230を含む。本変形例のデータ収集装置101Dは、以下で説明する相違点を除いて、第2の実施形態のデータ収集装置101の機能と同じ機能を備え、第2の実施形態のデータ収集装置101が動作するのと同様に動作する。なお、本変形例のデータ収集装置101Dは、分類部150を含んでいなくてもよい。また、本変形例を、第1から第3の変形例に適用することもできる。
データ受付部110は、音響データに加えて、対象データ点とレールの継ぎ目とを関連付けるデータを受け付ける。対象データ点とレールの継ぎ目とを関連付けるデータは、例えば、観測の際に車両が継ぎ目を通過した時刻を特定するデータである。観測の際に車両が継ぎ目を通過した時刻を特定するデータは、例えば、継ぎ目識別子とその継ぎ目識別子が示す継ぎ目を車両が通過した時刻との組み合わせであってもよい。観測の際に車両が継ぎ目を通過した時刻を特定するデータは、観測の際の、車両の位置と、車両がその位置に存在した時刻と、の組み合わせを複数含むデータであってもよい。この場合、例えばデータ受付部110が、車両の位置と車両がその位置に存在した時刻と、の複数の組み合わせから、車両が線路において隣接する2つの位置の間を一定の速度で走行したという仮定の下で、レールの継ぎ目の位置を通過した時刻を算出してもよい。
異常検出部140は、さらに、レールの継ぎ目ごとに(すなわち、検出された対象データ点ごとに)、レールの継ぎ目を特定する情報と異常が検出されたか否かを表す情報との組み合わせを生成する。具体的には、異常検出部140は、音響データにおいて検出された分析範囲ごとに、異常を検出するのに加えて、分析範囲が基づく対象データ点のデータが得られたレールの継ぎ目を特定する。異常検出部140は、例えば、分析範囲が基づく対象データ点のデータが観測された時刻に最も近い時刻に車両が通過した、レールの継ぎ目を、分析範囲が基づく対象データ点のデータが得られたレールの継ぎ目として特定する。異常検出部140は、他の方法によって、分析範囲が基づく対象データ点のデータが得られたレールの継ぎ目として特定してもよい。
データ蓄積部160は、異常が検出された分析範囲の情報(すなわち、異常データ)と、対象データ点ごとの、レールの継ぎ目を特定する情報及び分析範囲において異常が検出されたか否かを表す情報の組み合わせ(以下、分析範囲における異常の検出の結果とも表記)と、を記憶する。本説明では、分析範囲における異常の検出の結果は、単に、異常の検出の結果とも表記される。上述のように、本変形例では、同一の線路に対する複数回の観測によって得られた、複数セットの音響データが、データ収集装置101Dに入力される。その結果、データ蓄積部160は、複数セットの音響データから得られた、異常が検出された分析範囲の情報と、レールの継ぎ目ごとの、異常が検出されたか否かを表す情報とを記憶する。そして、データ蓄積部160には、複数セットの音響データの各々について、同一のレールの継ぎ目の分析範囲において異常が検出されたか否かを表す情報が格納されている。そして、データ蓄積部160には、分析範囲において異常が検出された場合、異常が検出された分析範囲の情報が格納されている。
対象信頼度算出部230は、データ蓄積部160に格納されている、対象データ点ごとの、レールの継ぎ目を特定する情報と分析範囲において異常が検出されたか否かを表す情報とを読み出す。
出力部170は、対象信頼度算出部230から、継ぎ目ごとの対象信頼度を受け取ってもよい。出力部170は、対象信頼度算出部230からから受け取った、継ぎ目ごとの対象信頼度を出力してもよい。
図9は、本開示の第2の実施形態の第5の変形例に係るデータ収集装置101Dの、対象信頼度を付与する動作の例を表すフローチャートである。図9に示す動作の開始時において、複数セットの音響データから検出された対象データ点に基づく分析範囲における、異常の検出の結果が、データ蓄積部160に格納されている。
本開示の第2の実施形態の第6の変形例に係るデータ収集装置101Dの構成は、本開示の第2の実施形態の第5の変形例に係るデータ収集装置101Dの構成と同じである。本変形例のデータ収集装置101Dは、以下で説明する相違点を除いて、第2の実施形態の第5の変形例に係るデータ収集装置101Dの機能と同じ機能を備え、第2の実施形態の第5の変形例に係るデータ収集装置101Dが動作するのと同様に動作する。また、本変形例を、第1から第3の変形例に適用することもできる。
データ受付部110は、さらに、レールの継ぎ目ごとに、例えば目視によって確認された、異常が存在するか否かを表す情報(以下、異常実測情報と表記)を受け取る。データ受付部110は、例えば、対象検出部120、決定部130、異常検出部140を介して、異常実測情報を分類部150に送出する。分類部150は、異常実測情報を受け取り、受け取った異常実測情報をデータ蓄積部160に格納する。データ受付部110は、受け付けた異常実測情報を、直接、データ蓄積部160に格納してもよい。データ受付部110は、受け付けた異常実測情報を、対象信頼度算出部230に送出してもよい。なお、図8では、図の簡単化のために、データ受付部110とデータ蓄積部160とをつなぐ線、及び、データ受付部110と対象信頼度算出部230とをつなぐ線は省略されている。
対象信頼度算出部230は、異常実測情報をデータ蓄積部160から読み出す。対象信頼度算出部230は、異常実測データを、データ受付部110から受け取ってもよい。
図10は、本開示の第2の実施形態の第7の変形例に係るデータ収集装置101Eの構成の例を表すブロック図である。図10に示す例では、データ収集装置101Eは、第2の実施形態に係るデータ収集装置101の全ての構成要素に加えて、環境情報受付部210と、属性受付部220と、分類信頼度算出部240とを含む。なお、データ収集装置101Eは、環境情報受付部210、及び、属性受付部220の一方を含んでいなくてもよい。また、本変形例を、第5、及び、第6の変形例に適用することもできる。
本変形例のデータ受付部110は、第5の変形例のデータ受付部110と同じ機能を備え、第5の変形例のデータ受付部110の動作と同じ動作を行う。すなわち、データ受付部110は、音響データに加えて、対象データ点とレールの継ぎ目とを関連付けるデータを受け付ける。対象データ点とレールの継ぎ目とを関連付けるデータは、例えば、観測の際に車両が継ぎ目を通過した時刻を特定するデータである。観測の際に車両が継ぎ目を通過した時刻を特定するデータは、例えば、継ぎ目識別子とその継ぎ目識別子が示す継ぎ目を車両が通過した時刻との組み合わせであってもよい。観測の際に車両が継ぎ目を通過した時刻を特定するデータは、観測の際の、車両の位置と、車両がその位置に存在した時刻と、の組み合わせを複数含むデータであってもよい。この場合、例えばデータ受付部110が、車両の位置と車両がその位置に存在した時刻と、の複数の組み合わせから、車両が線路において隣接する2つの位置の間を一定の速度で走行したという仮定の下で、レールの継ぎ目の位置を通過した時刻を算出してもよい。
本変形例の異常検出部140は、第5の変形例の異常検出部140と同じ機能を備え、第5の変形例の異常検出部140の動作と同じ動作を行う。
本変形例のデータ蓄積部160は、第5の変形例のデータ蓄積部160と同じである。データ蓄積部160は、異常が検出された分析範囲の情報(すなわち、異常データ)と、対象データ点ごとの、レールの継ぎ目を特定する情報及び分析範囲において異常が検出されたか否かを表す情報の組み合わせと、を記憶する。上述のように、分析範囲において異常が検出されたか否かを表す情報の組み合わせは、分析範囲における異常の検出の結果、及び、異常の検出の結果とも表記される。また、本変形例では、同一の線路に対する複数回の観測によって得られた、複数セットの音響データが、データ収集装置101Dに入力される。その結果、データ蓄積部160は、複数セットの音響データから得られた、異常が検出された分析範囲の情報と、レールの継ぎ目ごとの、異常が検出されたか否かを表す情報とを記憶する。そして、データ蓄積部160には、複数セットの音響データの各々について、同一のレールの継ぎ目の分析範囲において異常が検出されたか否かを表す情報が格納されている。そして、データ蓄積部160には、分析範囲において異常が検出された場合、異常が検出された分析範囲の情報が格納されている。
本変形例の環境情報受付部210は、第1の変形例の環境情報受付部210と同じである。言い換えると、本変形例の環境情報受付部210は、第1の変形例の環境情報受付部210の機能と同じ機能を備え、第1の変形例の環境情報受付部210の動作と同じ動作を行う。
本変形例の属性受付部220は、第2の変形例の属性受付部220と同じである。言い換えると、本変形例の属性受付部220は、第2の変形例の属性受付部220の機能と同じ機能を備え、第1の変形例の属性受付部220の動作と同じ動作を行う。
データ収集装置101Fが、環境情報受付部210を含む場合、分類部150は、第1の変形例の分類部150の機能と同じ機能を備え、第1の変形例の分類部150の動作と同じ動作を行うように構成される。データ収集装置101Fが、属性受付部220を含む場合、分類部150は、第2の変形例の分類部150の機能と同じ機能を備え、第2の変形例の分類部150の動作と同じ動作を行うように構成される。
本変形例のデータ蓄積部160は、第5の変形例のデータ蓄積部160と同様に機能する。本変形例のデータ蓄積部160は、さらに、分類結果を記憶する。
分類信頼度算出部240は、データ蓄積部160に格納されている、異常実測情報を読み出す。分類信頼度算出部240は、データ受付部110から異常実測情報を受け取ってもよい。
出力部170は、分類信頼度算出部240から、分類ごとの対象信頼度を受け取ってもよい。出力部170は、分類信頼度算出部240からから受け取った、分類ごとの対象信頼度を出力してもよい。
次に、本開示の第7の実施形態に係るデータ収集装置101Eの動作について、図面を使用して詳細に説明する。
図12は、本開示の第2の実施形態の第8の変形例に係るデータ収集装置101Fの構成の例を表すブロック図である。図12に示す例では、本変形例のデータ収集装置101Fは、第7の変形例に係るデータ収集装置101Fの構成要素の全てに加えて、対象信頼度算出部230を含む。本変形例のデータ収集装置101Fは、第7の変形例のデータ収集装置101Eの機能に加えて、第5又は第6の変形例のデータ収集装置101Dの機能と同じ機能を備える。本変形例のデータ収集装置101Fは、第7の変形例のデータ収集装置101Eの動作に加えて、第5又は第6の変形例のデータ収集装置101Dの動作と同じ動作を行う。
本開示の実施形態に係るデータ収集装置の各々は、メモリにロードされたプログラムを実行するプロセッサを含むコンピュータによって実現できる。本開示の実施形態に係るデータ収集装置の各々は、専用のハードウェアによって実現することもできる。本開示の実施形態に係るデータ収集装置の各々は、上述のコンピュータと専用のハードウェアとの組み合わせによっても実現できる。
対象の観測によって得られた音響データにおいて、前記対象が観測されたデータ点である対象データ点を検出する対象検出手段と、
前記対象データ点に基づいて、前記音響データにおける分析範囲を決定する決定手段と、
前記分析範囲において、異常を検出する異常検出手段と、
前記異常が検出された前記分析範囲の情報を出力する出力手段と、
を備えるデータ収集装置。
前記決定手段は、前記分析範囲よりも短く、前記対象データ点を含む除外範囲を、前記分析範囲から除外する
付記1に記載のデータ収集装置。
前記出力手段は、前記異常が検出された場合、前記分析範囲の情報を、異常データベースに格納する
付記1又は2に記載のデータ収集装置。
検出された前記異常の種類に基づいて前記分析範囲の情報を分類する分類手段
をさらに備える付記3に記載のデータ収集装置。
前記対象の観測の環境情報を受け付ける環境情報受付手段
をさらに備え、
前記分類手段は、前記環境情報に基づいて前記分析範囲の情報を分類する
付記4に記載のデータ収集装置。
前記対象の属性を受け付ける属性受付手段
をさらに備え、
前記分類手段は、前記属性に基づいて前記分析範囲の情報を分類する
付記4又は5に記載のデータ収集装置。
前記異常が検出された前記対象において異常が検出された割合に基づいて、前記分析範囲の情報が分類される分類ごとに分類信頼度を算出する分類信頼度算出手段
をさらに備える付記4乃至6のいずれか1項に記載のデータ収集装置。
前記異常が検出された前記対象における複数の測定において、前記異常が検出された割合に基づいて、前記対象の前記異常の情報の対象信頼度を算出する対象信頼度算出手段
をさらに備える付記1乃至7のいずれか1項に記載のデータ収集装置。
前記異常検出手段は、検出された前記異常の種類に基づいて、前記対象に生じた異常の緊急度を判定する
付記1乃至8のいずれか1項に記載のデータ収集装置。
前記対象は、レールの継ぎ目である
付記1乃至9のいずれか1項に記載のデータ収集装置。
対象の観測によって得られた音響データにおいて、前記対象が観測されたデータ点である対象データ点を検出し、
前記対象データ点に基づいて、前記音響データにおける分析範囲を決定し、
前記分析範囲において、異常を検出し、
前記異常が検出された前記分析範囲の情報を出力する、
データ収集方法。
前記分析範囲よりも短く、前記対象データ点を含む除外範囲を、前記分析範囲から除外する
付記11に記載のデータ収集方法。
前記異常が検出された場合、前記分析範囲の情報を、異常データベースに格納する
付記11又は12に記載のデータ収集方法。
検出された前記異常の種類に基づいて前記分析範囲の情報を分類する
付記13に記載のデータ収集方法。
前記対象の観測の環境情報を受け付け、
前記環境情報に基づいて前記分析範囲の情報を分類する
付記14に記載のデータ収集方法。
前記対象の属性を受け付け、
前記属性に基づいて前記分析範囲の情報を分類する
付記14又は15に記載のデータ収集方法。
前記異常が検出された前記対象において異常が検出された割合に基づいて、前記分析範囲の情報が分類される分類ごとに分類信頼度を算出する
付記14乃至16のいずれか1項に記載のデータ収集方法。
前記異常が検出された前記対象における複数の測定において、前記異常が検出された割合に基づいて、前記対象の前記異常の情報の対象信頼度を算出する
付記11乃至17のいずれか1項に記載のデータ収集方法。
検出された前記異常の種類に基づいて、前記対象に生じた異常の緊急度を判定する
付記11乃至18のいずれか1項に記載のデータ収集方法。
前記対象は、レールの継ぎ目である
付記11乃至19のいずれか1項に記載のデータ収集方法。
対象の観測によって得られた音響データにおいて、前記対象が観測されたデータ点である対象データ点を検出する対象検出処理と、
前記対象データ点に基づいて、前記音響データにおける分析範囲を決定する決定処理と、
前記分析範囲において、異常を検出する異常検出処理と、
前記異常が検出された前記分析範囲の情報を出力する出力処理と、
をコンピュータに実行させるプログラムを記憶する記憶媒体。
前記決定処理は、前記分析範囲よりも短く、前記対象データ点を含む除外範囲を、前記分析範囲から除外する
付記21に記載の記憶媒体。
前記出力処理は、前記異常が検出された場合、前記分析範囲の情報を、異常データベースに格納する
付記21又は22に記載の記憶媒体。
前記プログラムは、
検出された前記異常の種類に基づいて前記分析範囲の情報を分類する分類処理
をさらにコンピュータに実行させる付記23に記載の記憶媒体。
前記プログラムは、
前記対象の観測の環境情報を受け付ける環境情報受付処理
をさらにコンピュータに実行させ、
前記分類処理は、前記環境情報に基づいて前記分析範囲の情報を分類する
付記24に記載の記憶媒体。
前記プログラムは、
前記対象の属性を受け付ける属性受付処理
をさらにコンピュータに実行させ、
前記分類処理は、前記属性に基づいて前記分析範囲の情報を分類する
付記24又は25に記載の記憶媒体。
前記プログラムは、
前記異常が検出された前記対象において異常が検出された割合に基づいて、前記分析範囲の情報が分類される分類ごとに分類信頼度を算出する分類信頼度算出処理
をさらにコンピュータに実行させる付記24乃至26のいずれか1項に記載の記憶媒体。
前記プログラムは、
前記異常が検出された前記対象における複数の測定において、前記異常が検出された割合に基づいて、前記対象の前記異常の情報の対象信頼度を算出する対象信頼度算出処理
をさらにコンピュータに実行させる付記21乃至27のいずれか1項に記載の記憶媒体。
前記異常検出処理は、検出された前記異常の種類に基づいて、前記対象に生じた異常の緊急度を判定する
付記21乃至28のいずれか1項に記載の記憶媒体。
前記対象は、レールの継ぎ目である
付記21乃至29のいずれか1項に記載の記憶媒体。
101 データ収集装置
101A データ収集装置
101B データ収集装置
101C データ収集装置
101D データ収集装置
101E データ収集装置
101F データ収集装置
110 データ受付部
120 対象検出部
130 決定部
140 異常検出部
150 分類部
160 データ蓄積部
170 出力部
210 環境情報受付部
220 属性受付部
230 対象信頼度算出部
240 分類信頼度算出部
1000 コンピュータ
1001 プロセッサ
1002 メモリ
1003 記憶装置
1004 I/Oインタフェース
1005 記憶媒体
Claims (30)
- 対象の観測によって得られた音響データにおいて、前記対象が観測されたデータ点である対象データ点を検出する対象検出手段と、
前記対象データ点に基づいて、前記音響データにおける分析範囲を決定する決定手段と、
前記分析範囲において、異常を検出する異常検出手段と、
前記異常が検出された前記分析範囲の情報を出力する出力手段と、
を備えるデータ収集装置。 - 前記決定手段は、前記分析範囲よりも短く、前記対象データ点を含む除外範囲を、前記分析範囲から除外する
請求項1に記載のデータ収集装置。 - 前記出力手段は、前記異常が検出された場合、前記分析範囲の情報を、異常データベースに格納する
請求項1又は2に記載のデータ収集装置。 - 検出された前記異常の種類に基づいて前記分析範囲の情報を分類する分類手段
をさらに備える請求項3に記載のデータ収集装置。 - 前記対象の観測の環境情報を受け付ける環境情報受付手段
をさらに備え、
前記分類手段は、前記環境情報に基づいて前記分析範囲の情報を分類する
請求項4に記載のデータ収集装置。 - 前記対象の属性を受け付ける属性受付手段
をさらに備え、
前記分類手段は、前記属性に基づいて前記分析範囲の情報を分類する
請求項4又は5に記載のデータ収集装置。 - 前記異常が検出された前記対象において異常が検出された割合に基づいて、前記分析範囲の情報が分類される分類ごとに分類信頼度を算出する分類信頼度算出手段
をさらに備える請求項4乃至6のいずれか1項に記載のデータ収集装置。 - 前記異常が検出された前記対象における複数の測定において、前記異常が検出された割合に基づいて、前記対象の前記異常の情報の対象信頼度を算出する対象信頼度算出手段
をさらに備える請求項1乃至7のいずれか1項に記載のデータ収集装置。 - 前記異常検出手段は、検出された前記異常の種類に基づいて、前記対象に生じた異常の緊急度を判定する
請求項1乃至8のいずれか1項に記載のデータ収集装置。 - 前記対象は、レールの継ぎ目である
請求項1乃至9のいずれか1項に記載のデータ収集装置。 - 対象の観測によって得られた音響データにおいて、前記対象が観測されたデータ点である対象データ点を検出し、
前記対象データ点に基づいて、前記音響データにおける分析範囲を決定し、
前記分析範囲において、異常を検出し、
前記異常が検出された前記分析範囲の情報を出力する、
データ収集方法。 - 前記分析範囲よりも短く、前記対象データ点を含む除外範囲を、前記分析範囲から除外する
請求項11に記載のデータ収集方法。 - 前記異常が検出された場合、前記分析範囲の情報を、異常データベースに格納する
請求項11又は12に記載のデータ収集方法。 - 検出された前記異常の種類に基づいて前記分析範囲の情報を分類する
請求項13に記載のデータ収集方法。 - 前記対象の観測の環境情報を受け付け、
前記環境情報に基づいて前記分析範囲の情報を分類する
請求項14に記載のデータ収集方法。 - 前記対象の属性を受け付け、
前記属性に基づいて前記分析範囲の情報を分類する
請求項14又は15に記載のデータ収集方法。 - 前記異常が検出された前記対象において異常が検出された割合に基づいて、前記分析範囲の情報が分類される分類ごとに分類信頼度を算出する
請求項14乃至16のいずれか1項に記載のデータ収集方法。 - 前記異常が検出された前記対象における複数の測定において、前記異常が検出された割合に基づいて、前記対象の前記異常の情報の対象信頼度を算出する
請求項11乃至17のいずれか1項に記載のデータ収集方法。 - 検出された前記異常の種類に基づいて、前記対象に生じた異常の緊急度を判定する
請求項11乃至18のいずれか1項に記載のデータ収集方法。 - 前記対象は、レールの継ぎ目である
請求項11乃至19のいずれか1項に記載のデータ収集方法。 - 対象の観測によって得られた音響データにおいて、前記対象が観測されたデータ点である対象データ点を検出する対象検出処理と、
前記対象データ点に基づいて、前記音響データにおける分析範囲を決定する決定処理と、
前記分析範囲において、異常を検出する異常検出処理と、
前記異常が検出された前記分析範囲の情報を出力する出力処理と、
をコンピュータに実行させるプログラムを記憶する記憶媒体。 - 前記決定処理は、前記分析範囲よりも短く、前記対象データ点を含む除外範囲を、前記分析範囲から除外する
請求項21に記載の記憶媒体。 - 前記出力処理は、前記異常が検出された場合、前記分析範囲の情報を、異常データベースに格納する
請求項21又は22に記載の記憶媒体。 - 前記プログラムは、
検出された前記異常の種類に基づいて前記分析範囲の情報を分類する分類処理
をさらにコンピュータに実行させる請求項23に記載の記憶媒体。 - 前記プログラムは、
前記対象の観測の環境情報を受け付ける環境情報受付処理
をさらにコンピュータに実行させ、
前記分類処理は、前記環境情報に基づいて前記分析範囲の情報を分類する
請求項24に記載の記憶媒体。 - 前記プログラムは、
前記対象の属性を受け付ける属性受付処理
をさらにコンピュータに実行させ、
前記分類処理は、前記属性に基づいて前記分析範囲の情報を分類する
請求項24又は25に記載の記憶媒体。 - 前記プログラムは、
前記異常が検出された前記対象において異常が検出された割合に基づいて、前記分析範囲の情報が分類される分類ごとに分類信頼度を算出する分類信頼度算出処理
をさらにコンピュータに実行させる請求項24乃至26のいずれか1項に記載の記憶媒体。 - 前記プログラムは、
前記異常が検出された前記対象における複数の測定において、前記異常が検出された割合に基づいて、前記対象の前記異常の情報の対象信頼度を算出する対象信頼度算出処理
をさらにコンピュータに実行させる請求項21乃至27のいずれか1項に記載の記憶媒体。 - 前記異常検出処理は、検出された前記異常の種類に基づいて、前記対象に生じた異常の緊急度を判定する
請求項21乃至28のいずれか1項に記載の記憶媒体。 - 前記対象は、レールの継ぎ目である
請求項21乃至29のいずれか1項に記載の記憶媒体。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US18/288,070 US20240199095A1 (en) | 2021-05-07 | 2021-05-07 | Abnormality detection device, abnormality detection method, and storage medium |
JP2023518570A JPWO2022234637A5 (ja) | 2021-05-07 | データ収集装置、データ収集方法及びプログラム | |
PCT/JP2021/017460 WO2022234637A1 (ja) | 2021-05-07 | 2021-05-07 | 異常検出装置、異常検出方法及び記憶媒体 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2021/017460 WO2022234637A1 (ja) | 2021-05-07 | 2021-05-07 | 異常検出装置、異常検出方法及び記憶媒体 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022234637A1 true WO2022234637A1 (ja) | 2022-11-10 |
Family
ID=83932678
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/017460 WO2022234637A1 (ja) | 2021-05-07 | 2021-05-07 | 異常検出装置、異常検出方法及び記憶媒体 |
Country Status (2)
Country | Link |
---|---|
US (1) | US20240199095A1 (ja) |
WO (1) | WO2022234637A1 (ja) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002340869A (ja) * | 2001-05-11 | 2002-11-27 | Nippon Steel Corp | 打音検査物の非破壊検査方法、非破壊検査装置及び品質管理方法 |
JP2007145270A (ja) * | 2005-11-30 | 2007-06-14 | Univ Nihon | 軌道状態解析方法及び軌道状態解析装置並びに軌道状態解析プログラム |
JP2009025015A (ja) * | 2007-07-17 | 2009-02-05 | Omron Corp | 知識作成支援装置及びプログラム |
WO2018101430A1 (ja) * | 2016-11-30 | 2018-06-07 | パイオニア株式会社 | サーバ装置、解析方法、及びプログラム |
JP2020172861A (ja) * | 2019-04-08 | 2020-10-22 | 富士通株式会社 | 異常判別方法、異常判別装置および異常判別プログラム |
-
2021
- 2021-05-07 US US18/288,070 patent/US20240199095A1/en active Pending
- 2021-05-07 WO PCT/JP2021/017460 patent/WO2022234637A1/ja active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002340869A (ja) * | 2001-05-11 | 2002-11-27 | Nippon Steel Corp | 打音検査物の非破壊検査方法、非破壊検査装置及び品質管理方法 |
JP2007145270A (ja) * | 2005-11-30 | 2007-06-14 | Univ Nihon | 軌道状態解析方法及び軌道状態解析装置並びに軌道状態解析プログラム |
JP2009025015A (ja) * | 2007-07-17 | 2009-02-05 | Omron Corp | 知識作成支援装置及びプログラム |
WO2018101430A1 (ja) * | 2016-11-30 | 2018-06-07 | パイオニア株式会社 | サーバ装置、解析方法、及びプログラム |
JP2020172861A (ja) * | 2019-04-08 | 2020-10-22 | 富士通株式会社 | 異常判別方法、異常判別装置および異常判別プログラム |
Also Published As
Publication number | Publication date |
---|---|
JPWO2022234637A1 (ja) | 2022-11-10 |
US20240199095A1 (en) | 2024-06-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10203306B2 (en) | Resonant signal analysis-based inspection | |
US10040465B2 (en) | Abnormal vehicle dynamics detection | |
Alemi et al. | Condition monitoring approaches for the detection of railway wheel defects | |
US8326582B2 (en) | Acoustic-based rotating component analysis | |
US9255913B2 (en) | System and method for acoustically identifying damaged sections of a route | |
US9310340B2 (en) | Resonant signal analysis-based inspection of rail components | |
EP3219574B1 (en) | Method and system for determining a vertical profile of a rail surface | |
JP7287873B2 (ja) | 異常検知システム、異常検知装置、異常検知方法及びプログラム | |
Ramos-Romero et al. | Identification and mapping of asphalt surface deterioration by tyre-pavement interaction noise measurement | |
WO2022234637A1 (ja) | 異常検出装置、異常検出方法及び記憶媒体 | |
WO2019081772A1 (en) | CONTROL OF RAILWAY TRACK | |
Alten et al. | Detecting and classifying rail corrugation based on axle bearing vibration | |
Yang et al. | Missing rail fastener detection based on laser Doppler vibrometer measurements | |
Jensen et al. | Monitoring rail condition based on sound and vibration sensors installed on an operational train | |
JP7425430B2 (ja) | レールの普通継目の時間位置を特定するための方法及びプログラム、並びに情報処理システム | |
KR102264039B1 (ko) | 차량 탑재형 열차 지진 경보 시스템 및 방법 | |
Sun et al. | Looseness detection of rail fasteners using MEMS sensor and power spectrum entropy | |
Davis et al. | Addressing future rail network performance challenges through effective structural health monitoring | |
El Guerouani et al. | Instrumentation and automatic evaluation of event indicators alongside railway lines: a first attempt to comply with article 90 of the French mobility legislation on transport | |
KR20240146984A (ko) | 음향 데이터를 이용한 철도 차량 안전 진단 방법 및 시스템 | |
JP2023517593A (ja) | イベント検出装置、方法及びプログラム | |
Talebi Rostami et al. | Investigation of Early Detection of Wheel Flat Defect Based on Machine Learning Techniques | |
Bolshakova et al. | Rail Defects Detection Algorithm Based on Continuous Wavelet Transform and Frequency Domain Analysis |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21939830 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18288070 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2023518570 Country of ref document: JP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21939830 Country of ref document: EP Kind code of ref document: A1 |