GB2520628A - Abnormal noise detection system - Google Patents
Abnormal noise detection system Download PDFInfo
- Publication number
- GB2520628A GB2520628A GB1419256.1A GB201419256A GB2520628A GB 2520628 A GB2520628 A GB 2520628A GB 201419256 A GB201419256 A GB 201419256A GB 2520628 A GB2520628 A GB 2520628A
- Authority
- GB
- United Kingdom
- Prior art keywords
- zero point
- density distribution
- point density
- abnormal
- input signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 45
- 238000001514 detection method Methods 0.000 title claims abstract description 24
- 238000009826 distribution Methods 0.000 claims abstract description 71
- 238000004364 calculation method Methods 0.000 claims abstract description 51
- 238000003745 diagnosis Methods 0.000 claims abstract description 48
- 230000005856 abnormality Effects 0.000 claims abstract description 43
- 238000000034 method Methods 0.000 description 15
- 238000012545 processing Methods 0.000 description 11
- 238000005259 measurement Methods 0.000 description 6
- 230000005236 sound signal Effects 0.000 description 6
- 239000000284 extract Substances 0.000 description 4
- 230000008520 organization Effects 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 238000007796 conventional method Methods 0.000 description 3
- 230000000052 comparative effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H3/00—Measuring characteristics of vibrations by using a detector in a fluid
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M7/00—Vibration-testing of structures; Shock-testing of structures
Abstract
The purpose of the present invention is to detect, among abnormal noises emitted from a device, abnormal noises in which changes in amplitude intensity (sound pressure) do not occur or are negligible, and abnormal noises in which a phase change occurs. This abnormal noise detection system, which diagnoses abnormalities in a device being diagnosed using sound data extracted from the device as an input signal, comprises: a zero point magnitude calculation unit that calculates zero point magnitudes of the sound data for one cycle of the input signal; a zero point density distribution calculation unit that calculates a zero point density distribution from the zero point magnitudes; and a normal/abnormal diagnosis unit that determines whether the device being diagnosed is normal or abnormal by comparing the zero point density distribution of the input signal with the zero point density distribution of normal sound data.
Description
DESCRIPTION
Title of the Invention
ABNORMAL SOUND DETECTION SYSTEM
Technical Field
[0001] The present invention relates to an abnormal sound detection system.
Background Art
[0002]
In the background art of this technical field,
diagnosis of a device has grown in importance in maintaining the utilization rate of the device. Upon diagnosis of the device, it may be difficult to attach sensors to a diagnosis target portion of the device. In such cases, acoustic diagnosis is deemed worth resorting to because it requires no contact with the diagnosis target portion. For this reason, acoustic diagnosis has been adopted for years.
[0003) Patent Literature 1 describes an "acoustic diagnosis support apparatus for supporting diagnosis of a sound source that produces noise in a predetermined cycle when an abnormality has occurred" and discloses that "the apparatus is capable of easily recognizing the abnormality." It is also disclosed that for the purpose, "a sound collector records measurement data obtained by sampling the sounds produced from a rotating device at a predetermined frequency over a predetermined time longer than the rotation period. The diagnosis support appaatus acquires the measurement data from the sound collector. The diagnosis support apparatus extracts one cycle portion of a reference data series from the beginning of first measurement data, extracts one cycle portion of a comparative data series while staggering the extracting position in n-th measurement data, calculates the degree of correlation between the reference data series and the comparative data series, shifts second measurement data by the amount of shift obtained from the extracting position having the highest degree of correlation, and supplements the first measurement data with the shifted data." [0004] Also, Patent Literature 2 describes "a method of diagnosing an abnormality based on a sound signal produced from a diagnosis target, the abnormality being generated in the diagnosis target, the method including, when the diagnosis target is in a normal state, using the relation between a sound pressure and a frequency or a frequency band obtained by analyzing the sound signal f or frequency, as the basis for obtaining a relative sound pressure difference between the sound pressure of the frequency or frequency band in quetion on the one hand, and the sound pressure corresponding to at least one other frequency or frequency band than the frequency or frequency band in question." [0005] Further, Patent Literature 3 discloses that "the invention relates to a signal detection method of searching for and detecting a predetermined signal or a signal partially similar to the predetermined signal from among a series of stored signals,.and more particularly to the detection of a sound signal. In the past, there has been the signal search method for detecting that portion of stored signals that is similar to a target signal. However, because it used bnly localized pruning, the method had the disadvantage of taking a long time to make the search through a large quantity of stored signals. The proposed method offers the advantage of rapid, effective, and partial signal detection while maintaining the search precision, by narrowing a search space efficiently through global and local groupings based on anLl distance." [0006] As outlined, the attempts have been made in the past to implement the method for detecting abnormal sound * produced from the device as well as to make the search for feature quantities and similar information.
Prior Art Literature
Patent Literature [0007] Patent Literature 1: JP-20l2-93094-A Patent Literature 2: JP-2005-257460-A Patent Literature 2: W02006/009035
Summary of the Invention. .
Problem to be Solved by the Invention [0008] However, the conventional techniques presuppose that changes in abnormal sound appear in amplitude intensity (spund pressure).. Thus if the abnormal sound produces no abnormality in amplitude intensity (sound pressure) and emerges only as a phase change, as in the case of a clogged air intake constituting an abnormality involving a small amplitude change, that abnormality cannot be detected.
[0009] * 4 * The invention of Patent Literature 1 is an apparatus which, when an abnormality occurs, acquires multiple cyclic sound data, synchronizes them, and superimposes them one on top of the other to grasp the abnormality of a sound source generating the sound cyclically. The apparatus is thus incapable of grasping the abnormality of the sound source that does not generate abnormal sound cyclically, as in the case of abnormal sound producing a phase change. For this reason, the apparatus cannot detect early abnormalities and abnormalities such as a clogged air intake constituting an abnormality involving a small amplitude change.
[00101 The invention of Patent Literature 2 is a method by which, on the basis of the relation between the frequency or frequency band obtained by analyzing the sound sIgnal for frequency on the one hand and the sound pressure on the other hand, an upper threshold valueand a lower threshold value of the difference in level for abnormality determination are established. At the time of making diagnosis, the method involves using the frequency component or it sound pressure. For this reason, the method fails to detect abnormalities of which the abnormal sound is not reflected in the frequency band and sound pressure value (size).
[0011] The invention of Patent Literature 3 is a method by which feature quantities are turned into a histogram to make a rapid search using the Li distance. The feature quantities are the colors of images. The Li distance is defined as the distance of which the difference is based on the first power.
[0012]
In the prior art literature, as outlined above,
there are no disclosed techniques for detecting an abnormal sound that produces no change in the frequency band and amplitude intensity (sound pressure) while entailing a phase change.
[0013] An object of the present invention is to detect, from among abnormal sounds produced by a device, an abnormal sound that produces little or no change in amplitude intensity (sound pressure) while entailing a phase change.
Means for Solving the Problem [0014] In the above circumstances, the present invention focuses on zero points as the feature quantities for use in abnormality diagnosis. The zero points are zero crossings of waveforms in the time domain, each of the points having zero energy in the frequency domain. A density distribution of zero point sizes corresponds to phase changes. The interval between zero crossings in the time ddmain appears as a zero-point size on. a complex number plane. On the complex number plane, it is possible to count the number of zero points by size.
That is, where there is no phase change, the distribution of zero points is uniquely determined; where there are phase changes, changes occur in the density distribution of zero points.
[00151 In view of the above, the zero point density distribution is used to detect, from among abnormal sounds not causing changes in amplitude intensity (sound pressure), an abnormal sound which involves phase changes -and which it has been impossible to detect with conventional techniques.
[00161.
The present invention provides, for example, an abnormal Sound detection system that diagnoses an abnormality of a diagnosis target device using sound data collected from the device as an input signal. The abnormal sound detection system includes: a zero point size calculation unit that calculates the sizes of zero points of one-cycle-portion sound data in the input signal; a zero point density distribution calculation unit that calculates a zero point density distribution from the sizes of the zero points; and a normality/abnormality diagnosis unit that compares the zero point density distribution of the input signal with the zero point density distribution of normal sound data to determine whether the diagnosis target device is 1 or abnormal.
Effect of the Invention [0017] According to the present invention, it is possible.
to detect an abnormal sound that has little change in amplitude intensity while entailing a phase change.
[0018] The objects, structures, and effects other than those outlined above will become apparent upon a reading
of the following description of an embodiment
Brief Description of the Drawings
[00191 Fig. 1 is a typical configuration diagram of an abnormal sound detection system.
Fig. 2 shows a typical hardware configuration.
Fig. 3 is a typical system flowchart.
Fig. 4 shows typical processing performed by a one-cycle calculation unit.
Fig. S shows a typical organization of zero point density distribution data.
Fig. 6 shows a typical zero point density distribution.
Fig. 7 shows a typical zero point density distribution display.
Fig. 8 shows an example in which a motor sound is diagnosed.
Mode for Carrying out the Invention
[0020] An embodiment of the present inv!ntion is explained below with reference to the accompanying drawings. Throughout the drawings, identical or similar components are designated by the same reference symbols, and their explanations will not be repeated hereunder where redundant.
[0021J Fig. 1 is a typical configuration diagram of an abnormal sound detection system. Fig. 2 shows a typical hardware configuration. As shown in Fig. 1, the abnormal sound detection, system 1 includes a one-cycle calculation unit 101, a zero *point calculation unit 102, a zero point size calculation unit 103, a zero point density distribution calculation unit 104, a stored signal comparison unit 1O5,a normality/abnormality diagnosis unit 106, and a zero point density database 107. The abnormal sound detection system 1 shown in Fig. 1 corresponds to a data processing unit H02 indicated in Fig. 2, the processing being implemented with a computer or a microcomputer, for example. A display device 108 which is shown in Fig. 1 and which displays density distributions and other results corresponds to an output result display unit H03 indicated in Fig. 2.
[0022] The abnormal sound detection system 1 has an input signal Ii input tq the one-cycle calculation unit 101.
The one-cycle calculation unit 101 extracts one cycle portion of the input signal Ii and outputs what is extracted to the zero point calculation unit 102 as a one-cycle-portion input signal. The input signal Il is sound data collected from a diagnosis target device. The input signal Il may conceivably be input in one of two ways: the sound signal may be input directly to the data processing unit 1102 from a microphone 1101 shown in Fig. 2; and the sound signal may be input to the data processing unit H02 from the microphone HOl by way of a data logger or the like.
[0023] The zero point calculation unit 102 calculates zero points from the one-cycle-portion input signal calculated by the one-cycle calculation unit 101, and outputs the calculated zero points to the zero point size calculation unit 103. The method of calculating zero points involves resorting to n-th degree polynomial approximation and solving an n-th degree approximate equation. The known techniques for polynomial approximation are numerical calculations such as power series expansion and Lagrange interpolation (see "Methods of Numerical Calculations" (Japanese publication) by Hideyo Nagashima).
[0024] The zero point size calculation unit 103 calculates zero point sizes from the zero points calculated by the zero point calculation unit 102. The zero point is defined by a complexnumber. Thus the size of a given zero point is calculated by use of the absolute value of a complex number. The zero point sizes calculated by the zero point size calculation unit 103 are input to the zero point density distribution calculation unit 104.
[0025] The zero point density distribution calculation unit 104 calculates a zero point density distribution from the input data on the zero point sizes.
Specifically, out of all zero points, the proportion of the number of zero points having a specific zero point size is calculated. As many zero points are calculated as the number of degrees adopted for approximation. For example, if approximation is performed by a sixth degree function, up to six zero points are calculated. If there exist six cycle portions of waveforms that are approximated by a sixth degree function, there are a total of 36 zero points. *The zero point density distribution of the input signal Il calculated by the zero point density distribution calculation unit 104 is output tp the stored signal comparison unit 105.
[0026] Given a stored signal ±2, the abnormal sound detection signal 1 also performs similar calculations with the one-cycle calculation unit 101, zero point calculation unit 102, zero point size calculation unit 103, and zero point density distribution calculation unit 104. Here, the stored signal 12 is the normal sound collected when the target device is in its normal state.
The zero point density distribution of the stored signal 12 calculated by the stored signal 12 is recorded to the zero point density database 107.
[00271 From a database of the zero point density distribution of the stored signal 12 provided in the zero point density database 107, the stored signal comparison unit 105 retrieves the zero point density distribution of the stored signal 12 for comparison with the zero point * density distribution of the input signal Ii calculated by the input signal Il. The stored signal comparison unit outputs the zero point density distribution of the input signal Ii and the zero point density distribution of the stored signal 12 to the normality/abnormality diagnosis unit 106.
[00281 The zero point density database 107 stores th zexo point density distribution of the stored signal 12 as normal data.
[00291 The normality/abnormality diagnosis unit 106 compares the zero point density distribution of the input signal Ii with the zero point density distributiOn of the stored signal 12 to diagnose normality or abnormality, and outputs the result of the diagnosis. The comparison of the zero point density distribution of the input signal Il with the zero point density distribution of the stored signal 12 may be accomplished by calculating the coefficient of correlation between the zero point density 13 * distribution of the input signal Ii and the zero point density distribution of the stored signal 12, for example.
[0030] Where the coefficient of correlation is used for comparison, the correlation coefficient of 1.0 indicates a strong correlation and signifies that the stored signal 12 is substantially the same as the input signal Il. The correlation coefficient of 0.0 indicates the absence of correlation and signifies that the stored signal 12 is different fromthe input signal Ii. The use of the correlatith coefficient is a known technique for statistically evaluating the degree of similarity between random variables. Incidentally, a threshold value for distinguishing normality from abnormality using the coefficient of correlation needs to be determined depending on the device targeted for diagnosis, the device for performing detection, the degree of seriousness of the failure, and the lilce-For example, if the normality/abnormality determination threshold value is set to 0.8, normality may be determined when the correlation coefficient is equal to or larger than the normality/abnormality determination threshold value and abnormality may be determined when the correlation coefficient is smaller than the normality/abnormality determination threshold value. The result of the determination is output to the display device 108.
EOO3lJ The display device 108 displays the result of the determination of normality or abnormality made by the normality/abnormality diagnosis unit 105. The abnormal sound detection system 1 also has a display control unit, not shown, that controls the indications on. the display device 108. The display device 108 may also display other information at the same time for example, as will be explained later with reference to Fig. 7.
[0032] Fig. 3 is a typical system flowchart. ma one-cycle calculation step P01, the one-cycle calculation unit 101 is fed with either the input signal Ii or stored signal 12, the number of revolutions 110 of the diagnosis target device, and the name ISO of the diagnosis target device. The numberof revolutions 110 and the device name ISO may be input online, from a keyboard, or in any other suitable manner. The one-cycle calculation unit 101 calculates one cycle portion of the input signal (or one cycle portion of the stored signal) and dutputs the calculated signal.
[0033] On the basis of the one-cycle-portion input signal (or one-cycle-portion stored signal) calculated in the one-cycle calculation step P01, the zero point calculation unit 102 calculates zero points in a zero point calculation step P02 and outputs the calculated zero points. In a zero point size calculation step F03, the zero point size calculation unit 103 calculates the sizes of the zero points.
[0034] * In a zero point density distribution calculation step F04, the zero point density distribution calculation unit 104 calculates a zero point density distribution.
An interval 160 for the density distribution is also input to the zero point density distribution calculation unit 104. The interval 160 maybe input online, directly from a keyboard, or in any other suitable manner. The interval 160 is a spacing for.calculating the number of * zero points by size when the density distribution is calculated. For example, if the interval 160 is 10, that means the sizes of zero points are calculated at intervals of the size of 10.
[0035] * In a stored signal comparison step P05, the stored signal comparison unit 105 is fed with the zero point density distribution of the input signal Ii calculated in * the zero point density distribution calculatipn step F04, the number of revolutions 110 of the diagnosis target device corresponding to the input signal Il, and the diagnosis target device name 150 corresponding to the input signal Ii. Retrieved from the zero point density database 107 are the number of revolutions 110 of the diagnosis target device corresponding to the input signal Ii and the zero point density distribution of the stored signal 12 corresponding to the diagnosis target device name 150 that in turn corresponds to the input signal Il.
In a normality/abnormality diagnosis step FOG, the normality/abnormality diagnosis unit 106 carries out normality/abnormality determination.
[0036] Fig. 4 shows typical processing performed by the one-cycle calculation unit. The one-cycle calculation unit 101 calculates one cycle of the input signal Ii from the number of revolutions 110 of the input signal Ii, a sound pickup time 120, and a sampling frequency 130; extracts one cycle portion of the input signal Il, and outputs a one-cycle-portion input signal 140. For example, if the number of revolutions is 60 (Hz), the sound pickup time is 20 (seconds), and thesampling frequency is 50,000 (Hz), then "60" (Hz) is input as the number of revolutions 110, "20" (seconds) as the sound pickup time 120, and "50,000" (Hz) as the sampling frequency 130. The data may be input online, from a keyboard; or in any other suitable manner. Whereas Fig. 4 shows the example of processing with the input signal Il, the same processing also applies to the stored signal 12.
[00371 Fig. S shows a typical organization of zero point density distribution data. A data organization KOl of the zero point density database 107 shown in Fig. S is made up of the device name ISO, the number of revolutions no, a zero point density distribution 170, and the interval 160. The number of revolutions 110 may be either the revolutions per minute (rpm) or the revolutions per second (Hz). If the number of revolutions is the revolutions per minute (rpm), this number needs to be converted to the revolutions per second (Hz) . For example, given the input of 600 rpm, the number needs to be converted to 10 Hz. The example of Fig. 5 shows that the device name is device X, that thenumber of revolutions is 10 (Hz), and that the zero point density distribution has zero point densities of 10%, 20%, 40%, 20%, and 10% spaced at intervals of the zero point size of 10.
[0038] Fig. 6 shows a typical zero point density distribution. Regarding a zero point density distribution MOl shown in Fig. 6, the horizontal axis represents zero point sizes and the vertical axis denotes zero point densities (.1) -A zero point density (U means the ratio of the number of zero points having specific sizes to the total number of zero. points. In Fig. 6, for example,. it is assumed that the total number of zero points is 600 and that there are 60 zero points with their sizes ranging from 0 to less than 10, 120 zero points with their sizes ranging from 10 to less than 20, 240 zero points with their sizes ranging from 20 to less than 30, 120 zero points with their sizes ranging from 30 to less than 40, and 60 zero points with.their sizes ranging from 40 to less than 50. On that assumption, it is shown that the density of the zero points is 10 (1) when their sizes range from 0 to less than 10, 20 (U when their sizes range from 10 to less than 20,40 (%j when their sizes range from 20 to less than 30, 20 (U when their sizes range from 30 to less than 40, and 10 (U when their sizes range from 40 to less than 50.
[0039] . Fig. 7 shows a typical zero point density distribution display. A zero point density distiibution display IDOl in Fig. 7 is a typical screen displayed on the display device 108. A zero point density distribution Ml of the input signal Ii is indicated by 19.
dotted lines, and a zero point density distribution M2 of the stored signal 12 corresponding to the input signal Ii is indicated by solid lines. In Fig. 7, the horizontal axis represents zero point sizes, and the vertical axis denotes zero point densities (%) -Also in the example of Fig. 7, the typical indices calculated by the normality/abnormality diagnosis unit 106 are shown. For example, if normal and abnormal sounds are to be determined by use of the coefficient of correlation, if the calculated correlation coefficient is 0.7, and if the normality/abnormality determination threshold value is 0.8, the display of Fig.. 7 indicate that "CORRELATION COEFFICIENT OF 0.7" as a numerical evaluation index, "CORRELATION COEFFICIENT OF 0.8" as the normality/abnormality determination threshold value, and "ABNORMAL" as the result of determination. Incidentally, these indications are controlled by the display control unit, not shown, of the abnormal sound detection system 1 [00401 Fig. S shows an example in which a motor sound is diagnbsed. In the example of Fig. 8, the diagnosis target device is a motor JOl. A power source J02 is connected to the motor JOl to drive it. . [0041] A microphone HOl is setup near the motor JUl.
The sound (Sound data) picked up by the microphone 1101 is input to a data logger cr03. The picked-up Sound input to the data logger J03 is input to the dat processing unit H02 as the input signal Ii for diagnosis processing. The output result display unit H03 displays the result of the diagnosis.
[0042] As the stored signal 12, the normal sound is to be picked up beforehand. The data processing unit H02 calculates the zero point density distribution of the stored signal 12. what is calculated here is stored into the zero point density database 107 as the zero point density distribution data.
[0043] The stored signal 12 may be picked up a number of times at intervals of 60 seconds, for example, or may be collected in cumulative fashion while the device is allowed to operate continuously. Likewise, the input signal Ii may be input a number of times, or may be input consecutively for diagnosis hile the device is operated continuously.
[0044] In the manner described above, upon diagnosis of abnormality, it is possible to detect, from among abnormal sounds not causing changes. in amplitude intensity (sound pressure), an abnormal sound which involves phase changes and which it has been impossible to detect with conventional techniques.
[00451 While a preferred embodiment of this invention has been described using specific terms, such description is fpr illustrative purposes only, and it is to be understood that changes and variations may be made without departing from the spirit or scope of the present invention.
Description of Reference Symbols
1 Abnormal sound detection system 101 One-cycle calculation unit 102 Zero point calculation unit 103 Zero point size calculation unit 104 Zero point density distribution calculation unit Stored signal comparison unit 106 Normality/abnormality diagnosis unit 107 Zero point density database 108 Display device HOl Microphone H02 Data processingunit H03 Output result display unit FOl One-cycle calculation step F02 Zero point calculation step F03 Zero point size calculation.step F04 Zero point density distribution calculation step FOS Stored signal comparison step F06 Normality/abnormality diagnosis step Ii Input signal 12 stored signal Number at revolutions Sound pickup time Sampling frequency One-cycle-portion input signal ISO Device name Interval Zero point density distribution KOl Organization of zero point density distribution data MOl Zero point density distribution Ml Zero point density distribution of input signal* * M2 Zero point density distribution of stored signal IDOl Zero point density distribution display JUl Motor J02 Power source * J03 Data logger *
Claims (4)
- CLAIMS1. An abnormal sound detection system that diagnoses an abnormality of a diagnosis target device using sound data collected from the device as an input signal, the abnormal sound detection system comprising: a zero point size calculation unit that calculates sizes of zero points of one-cycle-portion sound data in the input signal; a zero point density distribution calculation unit that calculates a zero point density distribution from the sizes of the zero points; and a normality/abnormality diagnosis unit that compares the zero point density distribution of the input signal with a zero point density distribution of normal sound data to determine whether the diagnosis target device is normal or abnormal.
- 2. The abnormal sound detection system according to claim 1, wherein the normality/abnormality diagnosis unit calculates a coefficient of correlation between the zero point density distribution of the input signal and the zero point density distribution of the normal sound data, and compares the correlation coefficient with a normality/abnormality determination threshold value to determine whether the diagnosis target device is normal or abnormal.
- 3. The abnormal sound detection system according to claim 1 or 2, further comprising a display control unit, the display control unit allowing display of a result of the determination indicating whether the diagnosis target device is normal or abnormal.
- 4. The abnormal sound detection system according to claim 3, wherein the display control unit allows display of the zero point density distribution of the input signal and the zero point density distribution of the normal sound data.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/JP2012/068755 WO2014016914A1 (en) | 2012-07-25 | 2012-07-25 | Abnormal noise detection system |
Publications (3)
| Publication Number | Publication Date |
|---|---|
| GB201419256D0 GB201419256D0 (en) | 2014-12-10 |
| GB2520628A true GB2520628A (en) | 2015-05-27 |
| GB2520628B GB2520628B (en) | 2020-03-11 |
Family
ID=49996750
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| GB1419256.1A Expired - Fee Related GB2520628B (en) | 2012-07-25 | 2012-07-25 | Abnormal sound detection system |
Country Status (4)
| Country | Link |
|---|---|
| JP (1) | JP5948418B2 (en) |
| CN (1) | CN104380063B (en) |
| GB (1) | GB2520628B (en) |
| WO (1) | WO2014016914A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2576309A (en) * | 2018-08-10 | 2020-02-19 | Green Running Ltd | Systems and methods for condition monitoring |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104907132B (en) * | 2015-06-01 | 2017-10-03 | 遵义市立新机械有限责任公司 | A kind of hammer mill audio monitoring system |
| CN106023499B (en) * | 2016-04-28 | 2018-05-22 | 北京北邮国安技术股份有限公司 | A kind of dual recognition methods of optical fiber security signal and system |
| CN106531193B (en) * | 2016-10-31 | 2019-09-17 | 济南中维世纪科技有限公司 | A kind of abnormal sound detection method that ambient noise is adaptive and system |
| JP2019164107A (en) * | 2018-03-20 | 2019-09-26 | 本田技研工業株式会社 | Abnormal sound determination device and determination method |
| CN109556818A (en) * | 2018-12-03 | 2019-04-02 | 济南大学 | A kind of method and system of the measurement material collisional damping coefficient based on sound calibration |
| CN112233692A (en) * | 2020-09-28 | 2021-01-15 | 东莞市东纳通信有限公司 | Abnormal sound detection method and device, electronic equipment and storage medium |
| CN115035913B (en) * | 2022-08-11 | 2022-11-11 | 合肥中科类脑智能技术有限公司 | Sound abnormity detection method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10504107A (en) * | 1994-08-15 | 1998-04-14 | モニタリング テクノロジー コーポレイション | Digital signal processing of encoder signals for detecting resonance of rotating machinery |
| JP2012510585A (en) * | 2008-11-28 | 2012-05-10 | スネクマ | Aircraft engine abnormality detection |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4247195B2 (en) * | 2005-03-23 | 2009-04-02 | 株式会社東芝 | Acoustic signal processing apparatus, acoustic signal processing method, acoustic signal processing program, and recording medium recording the acoustic signal processing program |
| JP2010030356A (en) * | 2008-07-25 | 2010-02-12 | Fujitsu Ltd | Door opening detection device, microphone device, door opening detection program, and door opening detection method |
| CN100595548C (en) * | 2008-09-05 | 2010-03-24 | 华南理工大学 | Automotive engine fault diagnosis system and method based on sparse expression |
| JP5452158B2 (en) * | 2009-10-07 | 2014-03-26 | 株式会社日立製作所 | Acoustic monitoring system and sound collection system |
-
2012
- 2012-07-25 CN CN201280074211.9A patent/CN104380063B/en active Active
- 2012-07-25 JP JP2014526650A patent/JP5948418B2/en not_active Expired - Fee Related
- 2012-07-25 GB GB1419256.1A patent/GB2520628B/en not_active Expired - Fee Related
- 2012-07-25 WO PCT/JP2012/068755 patent/WO2014016914A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10504107A (en) * | 1994-08-15 | 1998-04-14 | モニタリング テクノロジー コーポレイション | Digital signal processing of encoder signals for detecting resonance of rotating machinery |
| JP2012510585A (en) * | 2008-11-28 | 2012-05-10 | スネクマ | Aircraft engine abnormality detection |
Non-Patent Citations (2)
| Title |
|---|
| KESAAKI MINEMURA ET AL.: 'Spectral Signal Representation of Vowels Using Power Series Expansion and Its Zeros' THE TRANSACTIONS OF THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS A vol. J93-A, no. 12, 01 December 2010, pages 833 - 834 * |
| TAKASHI MANABE ET AL.: 'Reverberation phase and zeros in a 1-D and 2-D sound fields' IEICE TECHNICAL REPORT. EA, ENGINEERING ACOUSTICS vol. 95, no. 433, 15 December 1995, pages 23 - 28 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2576309A (en) * | 2018-08-10 | 2020-02-19 | Green Running Ltd | Systems and methods for condition monitoring |
Also Published As
| Publication number | Publication date |
|---|---|
| JPWO2014016914A1 (en) | 2016-07-07 |
| GB201419256D0 (en) | 2014-12-10 |
| GB2520628B (en) | 2020-03-11 |
| CN104380063A (en) | 2015-02-25 |
| CN104380063B (en) | 2017-04-12 |
| WO2014016914A1 (en) | 2014-01-30 |
| JP5948418B2 (en) | 2016-07-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| GB2520628A (en) | Abnormal noise detection system | |
| US8171796B2 (en) | Acoustic emission detector and controller | |
| CN110370649B (en) | Online monitoring device and system of 3D printing equipment | |
| CN102317770B (en) | Method and device for classification of sound-generating processes | |
| US20030209077A1 (en) | Automated fault diagnosis device and method | |
| JP5197853B2 (en) | Monitoring device | |
| KR20070018740A (en) | Method and apparatus for signal signature analysis for event detection in rotating machinery | |
| CN111859732B (en) | Ship lock gate and automatic monitoring system and monitoring method for damage degree of supporting operation member thereof | |
| CN111248928A (en) | Pressure identification method and device | |
| CN105741850A (en) | Method and device for diagnosing mechanical equipment based on audio signal | |
| JP2012018066A (en) | Device for inspecting abnormality | |
| JP2010181203A (en) | Device and method for detecting crack | |
| CN112507784A (en) | Validity detection method for ballistocardiogram time sequence signal | |
| CN106770151A (en) | A kind of method and device of quick detection raman spectral signal | |
| JP2016031307A (en) | Signal processing method and signal processing device | |
| JP2008097361A (en) | Anomaly monitoring device | |
| WO2018189866A1 (en) | Data processing system and data processing method for apparatus for manufacturing plurality of types of items in mixed manner | |
| CN111319787B (en) | Helicopter moving part vibration monitoring data validity evaluation method | |
| JP2004125641A (en) | Abnormal sound detecting apparatus | |
| Song et al. | AStrion data validation of non-stationary wind turbine signals | |
| Ignjatovska et al. | Time-domain Analysis of Vibration Signals of Rotating Machinery with defects under varying load conditions | |
| US20190029562A1 (en) | Biological sound analyzing apparatus, biological sound analyzing method, computer program, and recording medium | |
| US11439320B2 (en) | Biological-sound analysis device, biological-sound analysis method, program, and storage medium | |
| US20190011296A1 (en) | Method of monitoring a vector-based position sensor | |
| Nishijima et al. | Improvement of Vascular Stenosis Detection by Screening Uncertain Data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 789A | Request for publication of translation (sect. 89(a)/1977) |
Ref document number: 2014016914 Country of ref document: WO |
|
| PCNP | Patent ceased through non-payment of renewal fee |
Effective date: 20230725 |