CN106153363B - A kind of mechanical equipment fault automatic identifying method based on acoustic image monitoring - Google Patents
A kind of mechanical equipment fault automatic identifying method based on acoustic image monitoring Download PDFInfo
- Publication number
- CN106153363B CN106153363B CN201510159052.8A CN201510159052A CN106153363B CN 106153363 B CN106153363 B CN 106153363B CN 201510159052 A CN201510159052 A CN 201510159052A CN 106153363 B CN106153363 B CN 106153363B
- Authority
- CN
- China
- Prior art keywords
- line spectrum
- mechanical equipment
- fault
- acoustic image
- library
- 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.)
- Active
Links
Landscapes
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The present invention provides a kind of mechanical equipment fault automatic identifying method based on acoustic image monitoring, this method establishes line spectrum identification library and failure acoustic image identification library respectively under conditions of mechanical equipment continuous normal table work;The online spectrum discrimination library of actual measurement line spectrum of the noise signal of the mechanical equipment acquired in real time to sonoscope is identified, if identified successfully, export line spectrum fault index, otherwise judge this line spectrum for abnormal line spectrum, it calculates the ultrasonogram of abnormal line spectrum and is identified in failure acoustic image identification library, if identified successfully, export acoustic image resultant fault index and equipment fault prediction scheme, otherwise, abnormal line spectrum, the ultrasonogram of abnormal line spectrum and its corresponding mechanical equipment fault prediction scheme are added in failure acoustic image identification library by the corresponding equipment fault prediction scheme of the abnormal line spectrum of diagnosis.After method using the present invention, acoustic imaging fault detection system can use under conditions of any complex sound field, and can uninterruptedly realize automatic alarm and failure prompting function.
Description
Technical field
The invention belongs to Microphone array measurement technical fields, are monitored based on acoustic image specifically, the present invention relates to one kind
Mechanical equipment fault automatic identifying method.
Background technology
Sound phase instrument also known as acoustical camera are to utilize the special of a certain range of sound-filed simulation of Microphone array measurement
Equipment can be used for measuring the state of the position and acoustic radiating of the sound that object is sent out, cloud atlas mode is used in combination to show intuitively
Image, i.e. acoustic imaging measure.
Acoustic imaging (acoustic imaging) is to be based on Microphone array measurement technology, by measuring in certain space
Sound wave reaches the signal phase difference of each microphone, and the position of sound source is determined according to phased array principle, measures the amplitude of sound source, and
Distribution of the sound source in space is shown in a manner of image, that is, space sound-filed simulation cloud atlas-ultrasonogram is obtained, wherein with image
The power of color and brightness representative voice.By the real video image clapped of the camera shooting being equipped on ultrasonogram and array with transparent side
Formula is superimposed together, and is formed the noise source situation that can intuitively analyze measured object sound field in real time.It is this to utilize acoustics, electronics
With the technologies such as information processing, by sound mapping at the technology of the visible image of human eye can help people intuitively recognize sound field,
Sound wave, sound source easily understand position and reason that mechanical equipment generates noise, react its sound field state being presently in.
When microphone array acoustic imaging measuring system is applied to mechanical equipment fault monitoring, manual intervention decision is being combined
Under the conditions of, failure noise source is found in the case of capable of being existed simultaneously from multiple noise sources, and identify acoustic fault type, this is
The advantage of acoustic imaging measuring system.But acoustic current imaging measurement system can't fully achieve the various acoustics events of automatic identification
Barrier, main cause is that the acoustic fault origin cause of formation of different mechanical equipments is multifarious, and automatic identification failure is a technical barrier.Mesh
Before, acoustic imaging fault detection system does not have the function of automatic identification failure, needs artificial long-term on duty, and then affects sound
It is imaged the popularization and application of fault detection system.
Invention content
The mesh of the present invention is to overcome the deficiencies of the prior art and provide a kind of equipment fault monitored based on acoustic image to be known automatically
Other method can realize the function of acoustic imaging fault detection system means for automatic monitoring tool equipment fault.
For achieving the above object, the present invention provides a kind of mechanical equipment fault automatic identifications based on acoustic image monitoring
Method, this method establish line spectrum identification library and failure acoustic image are known respectively under conditions of mechanical equipment continuous normal table work
Other library;The online spectrum discrimination library of actual measurement line spectrum of the noise signal of the mechanical equipment acquired in real time to sonoscope is identified, if
It identifies successfully, exports line spectrum fault index, otherwise judge that this line spectrum for abnormal line spectrum, calculates the ultrasonogram of abnormal line spectrum and in event
Barrier acoustic image identification library is identified, if identified successfully, exports acoustic image resultant fault index and otherwise equipment fault prediction scheme is examined
The corresponding equipment fault prediction scheme of exception of breaking line spectrum, abnormal line spectrum, the ultrasonogram of abnormal line spectrum and its corresponding equipment fault is pre-
Case is added in failure acoustic image identification library.
The method further includes:
Step 1) sonoscope monitors mechanical equipment, the noise signal of real-time collection machinery equipment;By the noise signal
Frequency spectrum carries out spectrum smoothing, obtains actual measurement line spectrum;
The actual measurement line spectrum is identified step 2) in mechanical equipment line spectrum identifies library, calculate the actual measurement line spectrum and
Mechanical equipment line spectrum identifies the minimum value of the not Duplication of each line spectrum in library, as line spectrum fault index;When line spectrum failure refers to
When number is less than 1, line spectrum successful match exports line spectrum fault index;Otherwise, judge that this line spectrum for abnormal line spectrum, is transferred to step 3);
Mechanical equipment line spectrum identification library includes the corresponding line spectrum of mechanical equipment noise spectrum;
The occurrence number N of step 3) the statistics abnormal line spectrum;Judge whether N is more than threshold value N0, if a determination be made that
Certainly, it enters step 4);Otherwise, it is transferred to step 6);
The threshold value N0It is preferably obtained by experience and statistical law;
Step 4) calculates the ultrasonogram of abnormal line spectrum, is identified in mechanical equipment steady state fault acoustic image library, if identification
Success;Export acoustic image resultant fault index and equipment fault prediction scheme;Otherwise, it is transferred to step 5);
The mechanical equipment steady state fault acoustic image library includes the corresponding ultrasonogram of mechanical equipment steady state fault;The acoustic image is comprehensive
Close the between class distance that fault index is the ultrasonogram and the ultrasonogram identified of the abnormal line spectrum;
The corresponding mechanical equipment fault prediction scheme of the abnormal line spectrum of step 5) diagnosis, by abnormal line spectrum, the ultrasonogram of abnormal line spectrum
And its corresponding mechanical equipment fault prediction scheme is added in the mechanical equipment steady state fault acoustic image library;
Step 6) calculates the acoustic image of abnormal line spectrum, and abnormal line spectrum sound is identified in the mechanical equipment transient fault acoustic image library
Picture exports acoustic image resultant fault index and equipment fault prediction scheme if identified successfully;Otherwise, it is transferred to step 7);
The mechanical equipment transient fault acoustic image library includes the corresponding ultrasonogram of mechanical equipment transient fault;
The corresponding mechanical equipment fault prediction scheme of the abnormal line spectrum of step 7) diagnosis, by abnormal line spectrum, the ultrasonogram of abnormal line spectrum
And its corresponding mechanical equipment fault prediction scheme is added in the mechanical equipment transient fault acoustic image library.
In above-mentioned technical proposal, before the step 1), in mechanical equipment under normal table operating condition, machine is established
Tool equipment line spectrum identifies library, mechanical equipment steady state fault acoustic image library and mechanical equipment transient fault acoustic image library;It specifically includes:
Establish mechanical equipment line spectrum identification library:Mechanical equipment measures the frequency of mechanical noise of equipment when normal table works
Spectrum, obtains accurate frequency spectrum, and identify each line spectrum using spectrum smoothing technology;It is label with Frequency point, by its line spectrum list
It is sequentially stored into mechanical equipment line spectrum identification library;
Establish mechanical equipment steady state fault acoustic image library:Mechanical equipment normal table work when, sound phase instrument from low to high,
Signal-to-noise ratio is selected to be more than the line spectrum of 5dB, for every line spectrum, by acoustic image dynamic range adjustment to 3dB, using acoustic image smoothing technique
Stable state ultrasonogram is obtained, and the intensity to acoustic image, area, frequency carry out 5 smoothing processings, is label with line spectrum, by steady-state sound
As figure and corresponding fault countermeasure are sequentially stored into the mechanical equipment steady state fault acoustic image library;
Establish mechanical equipment transient fault acoustic image library:Ultrasonogram is calculated to abnormal line spectrum of the amplitude beyond 3dB, is with line spectrum
Label, the mechanical equipment transient fault acoustic image library is sequentially stored by its ultrasonogram and corresponding fault countermeasure.
In above-mentioned technical proposal, the threshold value N0Value be 10.
The advantage of the invention is that:After equipment fault automatic identifying method using the present invention, acoustic imaging fault detect
System can use under conditions of any complex sound field, and can uninterruptedly realize that automatic alarm and failure remind work(
Energy.
Description of the drawings
Fig. 1 is the flow chart of the mechanical equipment fault automatic identifying method based on acoustic image monitoring of the present invention.
Specific implementation mode
Following further describes the present invention with reference to the drawings.
As shown in Figure 1, a kind of mechanical equipment fault automatic identifying method based on acoustic image monitoring, the method includes:
Step 1) sonoscope monitors mechanical equipment, the noise signal of real-time collection machinery equipment;By the noise signal
Frequency spectrum carries out spectrum smoothing, obtains actual measurement line spectrum;
Before the step 1), in mechanical equipment under normal table operating condition, the identification of mechanical equipment line spectrum is established
Library, mechanical equipment steady state fault acoustic image library and mechanical equipment transient fault acoustic image library;It specifically includes:
Establish mechanical equipment line spectrum identification library:Mechanical equipment measures the frequency of mechanical noise of equipment when normal table works
Spectrum, obtains accurate frequency spectrum, and identify each line spectrum using spectrum smoothing technology;It is label with Frequency point, by its line spectrum list
It is sequentially stored into mechanical equipment line spectrum identification library;
Establish mechanical equipment steady state fault acoustic image library:Mechanical equipment normal table work when, sound phase instrument from low to high,
Signal-to-noise ratio is selected to be more than the line spectrum of 5dB, for every line spectrum, by acoustic image dynamic range adjustment to 3dB, using acoustic image smoothing technique
Stable state ultrasonogram is obtained, and the intensity to acoustic image, area, frequency carry out 5 smoothing processings, is label with line spectrum, by steady-state sound
As figure and corresponding fault countermeasure are sequentially stored into the mechanical equipment steady state fault acoustic image library;
Establish mechanical equipment transient fault acoustic image library:Ultrasonogram is calculated to abnormal line spectrum of the amplitude beyond 3dB, is with line spectrum
Label, the mechanical equipment transient fault acoustic image library is sequentially stored by its ultrasonogram and corresponding fault countermeasure.
The actual measurement line spectrum is identified step 2) in mechanical equipment line spectrum identifies library, calculate the actual measurement line spectrum and
Mechanical equipment line spectrum identifies the minimum value of the not Duplication of each line spectrum in library, as line spectrum fault index;When line spectrum failure refers to
When number is less than 1, line spectrum successful match exports line spectrum fault index;Otherwise, judge that this line spectrum for abnormal line spectrum, is transferred to step 3);
The occurrence number N of step 3) the statistics abnormal line spectrum;Judge whether N is more than threshold value N0, if a determination be made that
Certainly, it enters step 4);Otherwise, it is transferred to step 6);
The threshold value N0It is preferably obtained by experience and statistical law;Preferably, N0=10;
Step 4) calculates the ultrasonogram of abnormal line spectrum, is identified in mechanical equipment steady state fault acoustic image library, if identification
Success;Export acoustic image resultant fault index and equipment fault prediction scheme;Otherwise, it is transferred to step 5);
The acoustic image resultant fault index is the between class distance of the ultrasonogram of abnormal line spectrum and the ultrasonogram identified;
The corresponding mechanical equipment fault prediction scheme of the abnormal line spectrum of step 5) diagnosis, by abnormal line spectrum, the ultrasonogram of abnormal line spectrum
And its corresponding mechanical equipment fault prediction scheme is added in the mechanical equipment steady state fault acoustic image library;
Step 6) calculates the acoustic image of abnormal line spectrum, and abnormal line spectrum sound is identified in the mechanical equipment transient fault acoustic image library
Picture exports acoustic image resultant fault index and equipment fault prediction scheme if identified successfully;Otherwise, it is transferred to step 7);
The corresponding mechanical equipment fault prediction scheme of the abnormal line spectrum of step 7) diagnosis, by abnormal line spectrum, the ultrasonogram of abnormal line spectrum
And its corresponding mechanical equipment fault prediction scheme is added in the mechanical equipment transient fault acoustic image library.
It is emphasized that particular embodiments described above is to the purpose of the present invention, technical solution and advantageous effect
It is described in detail.It should be understood that the above is only specific embodiments of the present invention, it is not limited to
The present invention.With within principle, any modification, equivalent replacement and improvement for being made etc. should all include all spirit in the present invention
Within protection scope of the present invention.
Claims (3)
1. a kind of mechanical equipment fault automatic identifying method based on acoustic image monitoring, which is characterized in that this method includes:In machinery
Under conditions of the continuous normal table work of equipment, mechanical equipment line spectrum identification library and the identification of mechanical equipment fault acoustic image are established respectively
Library;The online spectrum discrimination library of actual measurement line spectrum of the noise signal of the mechanical equipment acquired in real time to sonoscope is identified, if known
Not Cheng Gong, export line spectrum fault index, otherwise judge that this line spectrum is abnormal line spectrum, calculate the ultrasonogram of exception line spectrum and in failure
Acoustic image identification library is identified, if identified successfully, exports acoustic image resultant fault index and equipment fault prediction scheme, otherwise, diagnosis
The corresponding equipment fault prediction scheme of abnormal line spectrum, by abnormal line spectrum, the ultrasonogram of abnormal line spectrum and its corresponding mechanical equipment fault
Prediction scheme is added in failure acoustic image identification library;
The method further includes:
Step 1) sonoscope monitors mechanical equipment, the noise signal of real-time collection machinery equipment;By the frequency spectrum of the noise signal
Spectrum smoothing is carried out, actual measurement line spectrum is obtained;
The actual measurement line spectrum is identified step 2) in mechanical equipment line spectrum identifies library, calculates the actual measurement line spectrum and machinery
Equipment line spectrum identifies the minimum value of the not Duplication of each line spectrum in library, as line spectrum fault index;When line spectrum fault index is small
When 1, line spectrum successful match exports line spectrum fault index;Otherwise, judge that this line spectrum for abnormal line spectrum, is transferred to step 3);
Mechanical equipment line spectrum identification library includes the corresponding line spectrum of mechanical equipment noise spectrum;
The occurrence number N of step 3) the statistics abnormal line spectrum;Judge whether N is more than threshold value N0, if a determination be made that certainly
, it enters step 4);Otherwise, it is transferred to step 6);
The threshold value N0It is obtained by experience and statistical law;
Step 4) calculates the ultrasonogram of abnormal line spectrum, is identified in mechanical equipment steady state fault acoustic image library, if identified successfully;
Export acoustic image resultant fault index and equipment fault prediction scheme;Otherwise, it is transferred to step 5);
The mechanical equipment steady state fault acoustic image library includes the corresponding ultrasonogram of mechanical equipment steady state fault;The acoustic image synthesis event
Barrier index is the between class distance of the ultrasonogram and the ultrasonogram identified of the abnormal line spectrum;
The corresponding mechanical equipment fault prediction scheme of the abnormal line spectrum of step 5) diagnosis, by abnormal line spectrum, abnormal line spectrum ultrasonogram and its
Corresponding mechanical equipment fault prediction scheme is added in the mechanical equipment steady state fault acoustic image library;
Step 6) calculates the acoustic image of abnormal line spectrum, and abnormal line spectrum acoustic image is identified in mechanical equipment transient fault acoustic image library, if
It identifies successfully, exports acoustic image resultant fault index and equipment fault prediction scheme;Otherwise, it is transferred to step 7);
The mechanical equipment transient fault acoustic image library includes the corresponding ultrasonogram of mechanical equipment transient fault;
The corresponding mechanical equipment fault prediction scheme of the abnormal line spectrum of step 7) diagnosis, by abnormal line spectrum, abnormal line spectrum ultrasonogram and its
Corresponding mechanical equipment fault prediction scheme is added in the mechanical equipment transient fault acoustic image library.
2. the mechanical equipment fault automatic identifying method according to claim 1 based on acoustic image monitoring, which is characterized in that
Before the step 1), in mechanical equipment under normal table operating condition, mechanical equipment line spectrum identification library, mechanical equipment are established
Steady state fault acoustic image library and mechanical equipment transient fault acoustic image library;It specifically includes:
Establish mechanical equipment line spectrum identification library:Mechanical equipment measures the frequency spectrum of mechanical noise of equipment, adopts when normal table works
Accurate frequency spectrum is obtained with spectrum smoothing technology, and identifies each line spectrum;It is label with Frequency point, its line spectrum list is deposited successively
Enter mechanical equipment line spectrum identification library;
Establish mechanical equipment steady state fault acoustic image library:When mechanical equipment normal table works, sound phase instrument from low to high, selects
Signal-to-noise ratio is more than the line spectrum of 5dB, obtains acoustic image dynamic range adjustment to 3dB using acoustic image smoothing technique for every line spectrum
Stable state ultrasonogram, and the intensity to acoustic image, area, frequency carry out 5 smoothing processings, are label with line spectrum, by stable state ultrasonogram
It is sequentially stored into the mechanical equipment steady state fault acoustic image library with corresponding fault countermeasure;
Establish mechanical equipment transient fault acoustic image library:Ultrasonogram is calculated to abnormal line spectrum of the amplitude beyond 3dB, is mark with line spectrum
Note, the mechanical equipment transient fault acoustic image library is sequentially stored by its ultrasonogram and corresponding fault countermeasure.
3. the mechanical equipment fault automatic identifying method according to claim 1 based on acoustic image monitoring, which is characterized in that institute
State threshold value N0Value be 10.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510159052.8A CN106153363B (en) | 2015-04-07 | 2015-04-07 | A kind of mechanical equipment fault automatic identifying method based on acoustic image monitoring |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510159052.8A CN106153363B (en) | 2015-04-07 | 2015-04-07 | A kind of mechanical equipment fault automatic identifying method based on acoustic image monitoring |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106153363A CN106153363A (en) | 2016-11-23 |
CN106153363B true CN106153363B (en) | 2018-09-14 |
Family
ID=57338691
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510159052.8A Active CN106153363B (en) | 2015-04-07 | 2015-04-07 | A kind of mechanical equipment fault automatic identifying method based on acoustic image monitoring |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106153363B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109212628B (en) * | 2018-10-22 | 2020-02-18 | 中国科学院声学研究所 | Detection system for detecting unconventional target of automobile chassis |
CN109991003B (en) * | 2019-03-21 | 2021-06-11 | 北京宇航系统工程研究所 | Engine state monitoring and diagnosing system based on acoustic monitoring and implementation method |
CN110006672A (en) * | 2019-04-09 | 2019-07-12 | 唐山百川智能机器股份有限公司 | Rail vehicle fault monitoring method based on acoustic imaging technology |
CN110470379A (en) * | 2019-08-23 | 2019-11-19 | 武汉理工大学 | A kind of substation's movable-type intelligent noise continuous collecting system |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101865789B (en) * | 2010-06-30 | 2012-03-21 | 上海交通大学 | Fault detecting device of near field acoustic holography sound image mode identification and detecting method thereof |
CN101936818B (en) * | 2010-08-27 | 2012-09-05 | 上海交通大学 | Diagnostic system of non-contact type rotary mechanical failure |
US8777856B2 (en) * | 2012-06-26 | 2014-07-15 | General Electric Company | Diagnostic system and method for obtaining an ultrasound image frame |
CN103220701B (en) * | 2013-03-21 | 2016-01-06 | 深圳市信锐网科技术有限公司 | A kind of AP fault detection method and device |
CN103278801A (en) * | 2013-05-22 | 2013-09-04 | 河南省电力公司周口供电公司 | Noise imaging detection device and detection calculation method for transformer substation |
-
2015
- 2015-04-07 CN CN201510159052.8A patent/CN106153363B/en active Active
Non-Patent Citations (1)
Title |
---|
基于SVDD的多设备故障源识别定位方法研究;崔立林 等;《噪声与振动控制》;20101031(第5期);第137-140、148页 * |
Also Published As
Publication number | Publication date |
---|---|
CN106153363A (en) | 2016-11-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106153363B (en) | A kind of mechanical equipment fault automatic identifying method based on acoustic image monitoring | |
CN109300471B (en) | Intelligent video monitoring method, device and system for field area integrating sound collection and identification | |
CN107026953B (en) | Diagnostic device and diagnostic system | |
KR101204499B1 (en) | Ultrasonic apparatus having an image for diagnosis of electrical facilities | |
KR102058841B1 (en) | Systems and methods to detect generator collector flashover | |
CN104316847A (en) | On-line monitoring and positioning system for partial discharge of transformer station | |
CN102426328A (en) | Capacitive equipment insulation state real-time on-line monitoring method | |
CN102710341A (en) | Ingenious examination room radio cheating counter measure equipment | |
CN111753712A (en) | Method, system and equipment for monitoring safety of power production personnel | |
WO2018232846A1 (en) | Large-scale peripheral security monitoring method and system | |
CN109850711A (en) | A kind of elevator door condition detection method and system based on 3D measuring technique | |
CN111223261A (en) | Composite intelligent production security system and security method thereof | |
CN109116196A (en) | A kind of power cable fault discharging sound intelligent identification Method | |
CN104375068A (en) | Visual ultrasonic quick inspection device used for power transmission and distribution line patrolling | |
CN102288882A (en) | Partial discharge monitoring system and method for multichannel electrical equipment | |
JP2017181138A (en) | Photovoltaic power generation facility abnormality diagnostic method, abnormality diagnostic device, and abnormality diagnostic program | |
KR102105275B1 (en) | Inverter Protection Monitoring System for Photovoltaic Power Generation | |
CN208872806U (en) | A kind of HVDC transmission line voltage class identification device | |
US20130322690A1 (en) | Situation recognition apparatus and method using object energy information | |
KR102009993B1 (en) | Intelligent fire prevention diagnosis system and method | |
CN105867353A (en) | Oscillation monitoring method and system | |
CN117032055A (en) | Industrial equipment intelligent control system | |
CN109019349A (en) | fault detection method, detector, computer storage medium and crane | |
EP2779340B1 (en) | Home run arc detection at the photovoltaic string level using multiple current sensors | |
CN204188753U (en) | A kind of dry reactor office is placed on line monitoring system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |