CN110082107A - Vibrating motor defect diagonsis device and defect identification method based on audio analysis - Google Patents
Vibrating motor defect diagonsis device and defect identification method based on audio analysis Download PDFInfo
- Publication number
- CN110082107A CN110082107A CN201910277843.9A CN201910277843A CN110082107A CN 110082107 A CN110082107 A CN 110082107A CN 201910277843 A CN201910277843 A CN 201910277843A CN 110082107 A CN110082107 A CN 110082107A
- Authority
- CN
- China
- Prior art keywords
- vibrating motor
- defect
- spectrum
- audio
- pestle
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M15/00—Testing of engines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
- G06F17/141—Discrete Fourier transforms
- G06F17/142—Fast Fourier transforms, e.g. using a Cooley-Tukey type algorithm
Abstract
The invention discloses a kind of vibrating motor defect diagonsis device and defect identification method based on audio analysis, the diagnostic device are mainly made of objective table, hold-down mechanism, audio collection mechanism and computer；Vibrating motor is fixed in objective table card slot first with damping hold-down mechanism, form lower end rigidity, upper end fixed form flexible, then audio signal is acquired by the sound transducer of audio collection mechanism, it is handled again by computer, the audio signal of acquisition is transformed into human ear Meier frequency spectrum, and be distributed by the different degree coefficient of each frequency band, it recognizes defect existing for vibrating motor, realizes and lossless, real-time, the high-precision of vibrating motor defect are detected.The present invention can be realized the defects detection to the vibrating motor with eccentric block, has filled up the blank with eccentric block vibrating motor detection technique, has had great application prospect in technical field of nondestructive testing.
Description
Technical field
The invention belongs to machine defect detecting technique fields, are related to a kind of vibrating motor defect based on audio analysis
Detection technique more particularly to a kind of human ear based on neighbor analysis method simulate miniature touch feedback to realize motor defect recognition
Diagnostic device and recognition methods.
Background technique
With the fast development of interactive electronic apparatus, whether equipment, which can steadily transmit useful signal in operation, is asked
Topic will increasingly attract people's attention.Basis of the vibrating motor as interactive electronic apparatus transmitting vibration signal,
The stability of its state is directly related to the experience or even safety of user.Production environment both domestic and external is begun to very early to miniature vibration
Dynamic motor carries out various non-destructive testings, to guarantee sense of touch, sense of hearing comfort and the safety of class of electronic devices user in use
Property.Simultaneously as the production quantity and demand of the class of electronic devices all very huge (only China, the tool to put goods on the market every year
Have the interactive electronic equipment just about 3,500,000,000 of feedback effects), therefore while being detected to the class of electronic devices quality, also
Need detection efficiency with higher.
Currently, vibrating motor non-destructive testing technology mainly has working voltage detection, vibration detection and infrared detection etc..
A kind of device according to the vibration signal generated in motor operation course detection motor damage has been invented by Japanese Keyemce company, by
In the mixing property of vibration signal, the device False Rate is very high, can only identify better simply failure mode.The auspicious measuring and controlling equipment advanced in years in Kunshan
Company further develops oscillating mode micro motor detection device, but the recognition efficiency of the device is not still high, and it can not be examined
The vibrating motor running losses situation of measuring tape eccentric block, while being also unable to satisfy detection rate request.TSC company develops miniature
The port current detection system of motor identifies the transient fault signal of current of electric in vibrating motor operational process, when adopting
When sample frequency reaches 50KHz, detection system can realize the detection speed of 10/s, but such detection speed is still very low, and
As vibration detection, the vibrating motor with eccentric block cannot be detected and whether work normally and differentiate that user uses relaxes
Adaptive.
Another more mature motor non-destructive testing technology be audio detection, current audio detection technology by with
The vibrating motor of eccentric block is free of in detection, mainly for detection of the transient fault in audio signal, due to band eccentric block
Vibrating motor inherently contain a large amount of transient signals, therefore be not suitable for the vibrating motor defects detection containing eccentric block.
Therefore this detection mode is also unable to satisfy the build environment for largely cutting touch feedback instantly.And due to transient analysis desired signal
Data are extracted out of a period of time, are generally difficult to meet real-time, detection speed of the detection method to vibrating motor
It spends lower.
In conclusion existing vibrating motor non-destructive testing technology or high detection speed cannot be reached, or
It is detection while can not achieve various aspects performance.With the development of haptic feedback devices, it would be highly desirable to research and develop a kind of energy
Realize it is synchronous with speed of production, vibrating motor various aspects performance (such as is vibrated caused by shaft distortion, bearing wear
Failure etc.) technology that carries out non-destructive testing, realize the safety and comfort for ensuring that the detection speed of production capacity and user use.
Summary of the invention
For detection speed is slow present in current vibrating motor non-destructive testing technology, not can be implemented simultaneously to miniature
The problem of vibrating motor various aspects of performance complete detection, the object of the invention are intended to provide a kind of micro-vibration based on audio analysis
Motor defect diagonsis device and defect identification method can be achieved at the same time to vibrating motor due to shaft distortion, bearing wear, outer
Shell deformation, lubricating oil is very few, has that sound caused by the failures such as sundries is excessive, sound is too sharp, sound is with noise, sound on rotor
Sound is too small, the apparent defect of sound gradual change carries out high-speed lossless detection.
Audio detection is the study found that human ear is uneven distribution to the sensitive intensity of sound, caused by vibrational system
Control trembles frequency when converting between 3000~4000Hz, and human ear has very strong burr noise sense.And work as miniature vibration
In dynamic motor product when existing defects, the frequency band energy generated can be very different compared with normal part, normal micro-vibration
The frequency band energy distribution of motor is provided according to GB_T 2298-2010 and 1345 treaty of Kawasaki, Japan heavy industry regulations.Therefore, originally
The audio signal of acquisition, in human ear Meier spectrum distribution situation, is converted to Meier frequency spectrum according to alternative sounds frequency band by invention, and
It is increased in human ear sensitive strip (part especially 3000~4000Hz) and differentiates weight, it is final using different in human ear analog frequency band
Sensitivity distribution information, realize to vibrating motor defects detection.
Based on foregoing invention thinking, the vibrating motor defect diagonsis device provided by the invention based on audio analysis,
Including for installing vibrating motor to be tested objective table, for being fixed vibrating motor on objective table
Hold-down mechanism, audio collection mechanism and computer positioned at vibrating motor side；Objective table body design has a notch, slot
Design has the card slot to match with vibrating motor external form on one cell wall of mouth, and card slot design prevents vibrating motor axial
Mobile position limiting structure, design, which has, on another cell wall of notch connects the corresponding electrode of power port with vibrating motor；The compression
Mechanism is damping and amortization hold-down mechanism, including first support, the damping pestle component being mounted in first support and to damping pestle component
In pestle bar pressure pressure assembly；The audio collection mechanism includes second support, is installed on second by flexible constraint
The sound harvesting end of sound transducer in frame, sound transducer is directed at vibrating motor；The computer and sound sensor
Device connection, obtains the Mel frequency spectrum MFCC of falling coefficient for being handled received voice signal, and according to obtained Mel frequency spectrum
The MFCC of falling coefficient recognizes defect existing for vibrating motor.
Based on law of conservation of energy, when vibrational system occurrence of large-area resonates, system capacity dissipates fastly, and vibration signal becomes
In discretization and mixing.And study and find that rigid system structure is more single, the vibration signal discretization of transmitting is weaker, meanwhile,
Also fewer formant can be generated.Based on above-mentioned analysis, the present invention uses lower end for the fixation of vibrating motor to be tested
Rigidity, upper end fixed form flexible.
Lower end, which rigidly fixes, to be realized by the objective table for installing vibrating motor to be tested.Objective table is selected
Single rigid structure, objective table are further secured on rigid base, and objective table and rigid base constitute vibrational system, single rigid
Property structure can absorb the vibration signal of vibrational system and not generate larger resonance.Rigid structure uses high hardness material as far as possible,
Such as steel, silicon steel sheet or Ferrite Material.After rigid structure pedestal further makees shockproof processing, isolated rigidity is single
System has preferable signal to restrain property, therefore the vibration signal that vibrating motor rotation is generated with objective table collision can be used for two
Secondary indirect measurement.Vibrating motor to be tested is fixed in the card slot of objective table ontology pocket side wall.For having bias
Block vibrating motor, vibrating motor moves axially in order to prevent, and design has corresponding position limiting structure on card slot, the present invention
The position limiting structure of middle use is made of the limit film being fixed on objective table ontology, and design has and vibrating motor in limit film
The limit opening that eccentric block external form matches.It, can be in slot in order to which vibrating motor to be fixed in objective table card slot
The magnet of mouth or card slot bottom setting one for vibrating motor to be sucked.
Flexibility fixation in upper end is realized by damping hold-down mechanism.It installs in vibrating motor to be tested into objective table
Later, the damping pestle component for damping hold-down mechanism compresses vibrating motor under pressure assembly effect.On the one hand miniature
When vibrating motor rotates, damping pestle component can prevent it from flying out；On the other hand, damping pestle component can turn with micro motor
Dynamic free extension in a certain range, to realize in the case where not destroying vibrating motor structure to vibrating motor
Stable holding.The damping pestle component includes pestle bar, damping spring and briquetting, and pestle bar is axially moveably mounted on first
On frame, briquetting is mounted on pestle bar lower end, and damping spring is nested on pestle bar, and lower end acts on briquetting, and upper end acts on pestle bar
As the position limiting structure of spring base, pestle bar presses to briquetting by damping spring.In the present invention, the pestle bar is composite structure pestle
Bar is made of pestle bar body and the bolt as pestle bar extension body, and bolt is coupled by screw thread pair with pestle bar；The briquetting is to set
There is the briquetting of cavity, perpendicular to pestle bar, briquetting can be installed to axial float the opening direction of cavity by cavity wall upper installing hole
On bolt, damping spring is nested with outside bolt.Briquetting compression side is provided with suitable with vibrating motor upper end surface structure
The material matched is the compression terminal of plastics, rubber etc..The position that terminal is contacted with vibrating motor conductive sheet is compressed to be provided with
Rubber, as flexible material buffer layer.Pressure assembly for pressing to damping pestle component can be such as pneumatic actuation or electricity
The driving mechanisms such as machine driving, can also pass through the handle hinged with pestle bar, manual pressure.
Vibrating motor to be tested makees eccentric vibrating under the drive of eccentric block, touches it with objective table card slot
It hits, objective table and rigid base generate forced vibration, while surrounding air being driven to vibrate, and vibrate the Energy distribution of generation by carrying
In the vibrational system that object platform and rigid base are constituted, vibrational system and vibrating motor issue jointly and are enough to pass through audio collection
The received audio signal of the sound transducer of mechanism.In order to reduce vibrating motor and the collision of objective table card slot to sound sensor
The influence of device working condition, sound transducer should keep flexibility is shockproof to link with second support, to guarantee that sound transducer connects
It is interference-free to receive audio signal.For this purpose, the second support is cage bracket, mainly by flexible support and the mouse cage being attached thereto
Formula bracket is constituted, and flexible support is fixed on the worktable, and squirrel-cage bracket is for installing sound transducer.Sound transducer passes through
It is fixed on the spider of squirrel-cage bracket both ends and is mounted in cage bracket by the fixed structure that strip-shaped rubber is overlapped to form.In addition, institute
Stating audio collection structure and being also devised with prevents the irreflexive circular cowling of sound, and circular cowling is by being fixed on second support upper support bar
It is suspended at sound transducer front end.In order to improve audio collection effect, the sound harvesting end of the sound transducer is located at card
On the loudness of a sound enveloping surface formed centered on slot slot bottom center.
Invention further provides a kind of sides identified using above-mentioned diagnostic device to vibrating motor defect
Method, vibrating motor to be tested are fixed in after objective table by damping hold-down mechanism, are made under eccentric block drive inclined
Heart vibration, so that rigid collision occur with objective table card slot, the audio signal that vibrational system and vibrating motor issue is by sound
The acquisition of frequency collecting mechanism, and it is transferred to computer.Computer is scaled to the sensitive band region of human ear to received audio signal,
Human ear analog frequency band is obtained, and according to the sensitivity distribution information in human ear analog frequency band, realizes and the defect of vibrating motor is examined
It surveys.In order to improve vibrating motor defects detection precision, the present invention further uses neighbor analysis method, makes the frequency of sensitizing range
Spectrum signature possesses higher weight, and the characteristic energy frequency band under the various defects obtained through orthogonal test is marked, and joins
Human auditory system Meier spectrum energy feature is examined, using labeled characteristic energy frequency band as feature decision standard.
Above-mentioned vibrating motor defect identification method specifically includes the following steps:
(1) vibrating motor to be tested is placed on objective table, using damping and amortization hold-down mechanism by micro-vibration horse
Up to compression；
(2) starting vibrating motor rotation；
(3) sound transducer of audio collection mechanism acquires audio signal, through acquiring the audio signal of acquisition through data
Device is transmitted to computer；
(4) audio signal received is handled to obtain Mel cepstrum, and miniature according to obtained Mel cepstrum identification
Defect existing for vibrating motor.
Above-mentioned steps (4) include it is following step by step:
(41) audio signal of acquisition is obtained corresponding with audio signal through preemphasis, discrete Fast Fourier Transform iterative inversion FFT
Spectrum information；
(42) spectrum information that step (41) obtains is handled using triangle bandpass filter group, obtains Mel frequency spectrum；
(43) it is based on Mel frequency spectrum, obtains Mel cepstrum；
(44) different degree corresponding with each bands of a spectrum of Mel cepstrum is calculated using based on the preceding old attribute reduction algorithms to greed
Coefficient, and extract the corresponding bands of a spectrum of part of different degree coefficient, by the partial spectrum band of extraction and under various types defect
The bands of a spectrum of Mel cepstrum corresponding position are integrally compared, and determine vibrating motor with the presence or absence of defect and defect kind.
The vibrating motor defect diagonsis device and defect identification method based on audio analysis provided through the invention,
The audio signal of acquisition is converted to human ear Meier frequency spectrum, passes through sensitivity distribution information (the i.e. different frequency bands on different frequency bands
Different degree coefficient), determine crucial multiple cepstrum bands of a spectrum, multiple cepstrum bands of a spectrum of selection recycled to lack with various types
The bands of a spectrum for the Mel cepstrum corresponding position sagged integrally are compared, and realize the defects detection to vibrating motor.From installation to
Test sample is completed to defect recognition, and detection time is no more than 2s, greatly shortening detection time, improves detection efficiency.This hair
It is bright also to pass through test envelope distance, the running speed of vibrating motor and the motor defect kind of adjusting sound transducer
Class, come each frequency band feature weight proportion adjusted；And then change the collected audio power of each feature band, it is convenient for journey
Sequence accurately differentiates the working condition of vibrating motor.
Compared with prior art, it vibrating motor defect diagonsis device provided by the invention based on audio analysis and lacks
Sunken recognition methods has the advantages that
1, the invention firstly uses damping hold-down mechanisms is fixed on vibrating motor in objective table card slot, forms lower end
Then rigidity, upper end fixed form flexible acquire audio signal by the sound transducer of audio collection mechanism, then by computer
It is handled, the audio signal of acquisition is transformed into human ear Meier frequency spectrum, confirmed by the different degree coefficient distribution of each bands of a spectrum more
A key bands of a spectrum, and the defect according to existing for multiple crucial bands of a spectrum identification vibrating motors, realize and lack to vibrating motor
Sunken lossless, real-time, high-precision detects.
2, vibrating motor of the present invention, objective table card slot and damping pestle make eccentric vibrating under the drive of eccentric block, make
Vibrating motor collides with objective table card slot, and distribution of bumping energy is in entire vibrational system, vibrational system and horse
Up to common sending it is enough the sound spectrum distributed intelligence recorded by audio sensor, therefore can be realized to eccentric block
The defects detection of vibrating motor has filled up the blank with eccentric block vibrating motor detection technique, in non-destructive testing skill
Art field has great application prospect.
3, the present invention constitutes lower end by objective table and rigidly fixes, and damping hold-down mechanism constitutes upper end and fixes, and can greatly subtract
The small energy dissipation generated by device resonance, enables vibration signal dissipation energy to be much smaller than the audio signal that sound transducer absorbs
Amount, to provide valid data for audio signal analysis, improves the detection accuracy to vibrating motor defects detection.
4, the present invention is by being then based on audio signal analysis of the band region to acquisition of human ear sensitivity, therefore can be improved
The comfort level that human body uses virtual haptic to feed back, and the standardization of vibrating motor vibration sounding quality control can be conducive to.
5, the present invention can be achieved to vibrating motor various aspects defects detection (including sound is excessive, sound is too sharp,
Sound is with noise, sound is too small and sound gradual change is obvious etc.), be extremely applicable to the high-speed lossless detection of vibrating motor with
The working environment of standard customization.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, be described below in attached drawing be only this
Some embodiments of invention for those of ordinary skills without creative efforts, can be with
Illustrated embodiment obtains other embodiments and its attached drawing according to these attached drawings.
Fig. 1 is the vibrating motor defect diagonsis schematic device based on audio analysis.
Fig. 2 is the enlarged drawing of part A in Fig. 1.
Fig. 3 is hold-down mechanism structural schematic diagram.
Fig. 4 is audio collection mechanism section block diagram.
Fig. 5 is loudness of a sound enveloping surface schematic diagram.
Fig. 6 is the audio signal figure of preemphasis before and after the processing, wherein (a) is the original audio signal of acquisition, figure (b) is pre-
Aggravate treated audio signal.
Fig. 7 is Fast Fourier Transform (FFT) spectrogram.
Fig. 8 is the transformation relation of linear spectral and Mel frequency spectrum, and wherein triangle area is equal to the logical of triangle bandpass filter
Frequency range, and then it is equal to the length of Mel frequency spectrum.
Fig. 9 is Mel spectrogram.
Figure 10 is Mel cepstrum figure.
Figure 11 is the vibration map acquired in vibrating motor operation process.
Figure 12 is the corresponding each frequency band different degree coefficient spectrogram of Mel cepstrum of qualified vibrating motor.
Wherein, 1- objective table, 11- objective table ontology, 12- notch, 13- limit film, 14- electrode, 15- micro-vibration horse
It reaches, 16- flexible material buffer layer；
2- hold-down mechanism, 21- first support, 22- damping pestle component, 221- pestle bar, 222- bolt, 223- damping spring,
224- briquetting, 225- compress terminal, 23- handle；
3- audio collection mechanism, 31- second support, 311- squirrel-cage bracket, 312- support rod, 32- sound transducer,
33- circular cowling.
Specific embodiment
Clear, complete description is carried out below with reference to technical solution of the attached drawing to various embodiments of the present invention, it is clear that is retouched
Stating embodiment is only a part of the embodiments of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, originally
Field those of ordinary skill obtained all other embodiment without making creative work, belongs to this hair
Bright protected range.
Vibrating motor defect diagonsis device of the embodiment 1 based on audio analysis
Vibrating motor defect diagonsis device provided in this embodiment based on audio analysis, as shown in Figure 1, including using
In the objective table 1 of installation vibrating motor 15 to be tested, for being fixed vibrating motor in the pressure on objective table
Tight mechanism 2, audio collection mechanism 3 and computer 4 positioned at vibrating motor side.Objective table 1 and hold-down mechanism 2 are set to
On marble rigid base on workbench, on workbench, marble is rigid for audio collection mechanism 3 and computer installation
Rubber pad is further set between pedestal and workbench, to carry out shockproof processing to marble rigid base.
As shown in Fig. 2, the objective table in the present embodiment is an integral structure, objective table ontology 11 is fixed on marble rigidity
On pedestal, design has a notch 12 on objective table ontology 11, and designing on one cell wall of notch has and vibrating motor external form phase
The card slot matched, card slot design have the limit film 13 for preventing vibrating motor from moving axially, and limit film is fixed on card slot inner sidewall,
And design has the limit opening to match with vibrating motor eccentric block external form in limit film, designing on another cell wall of notch has
The corresponding electrode 14 of power port is connect with vibrating motor, card slot bottom is provided with the magnet for fixing vibrating motor.
As shown in Figures 1 and 3, hold-down mechanism 2 is damping and amortization hold-down mechanism, including first support 21, is mounted on first
Pestle component 22 and the pressure assembly to the pestle bar pressure in damping pestle component are damped on frame, the pressure assembly in the present embodiment is
Handle 23.Damping pestle component includes pestle bar 221, damping spring 223 and briquetting 224, and briquetting is mounted on pestle bar lower end, and pestle bar is group
Structure pestle bar is closed, is made of pestle bar body and the bolt 222 as pestle bar extension body, bolt is joined by nut and pestle bar body
It connects, briquetting is the briquetting equipped with cavity, and for the opening direction of cavity perpendicular to pestle bar, bolt passes through briquetting cavity wall upper installing hole simultaneously
It is fixed by nuts, so that briquetting be made can be mounted on bolt to axial float, damping spring 223 is placed on bolt 222, thereon
End acts on the nut as spring base, and lower end acts on briquetting, and pestle bar presses to briquetting by damping spring.When briquetting cavity
When wall mounting hole is excessive, gasket can be set in briquetting upper end.Briquetting compresses side and is provided with and vibrating motor upper end surface structure
The material of adaptation is the compression terminal 225 of plastics.It compresses the position that terminal is contacted with vibrating motor conductive sheet and is provided with rubber
Glue, as flexible material buffer layer 16.Above-mentioned first support 21 is fixed in marble rigid base, and 21 upper end of first support is set
It is equipped with deck, handle is connected on deck by the shaft by passing through handle, and handle one end and pestle bar body 221 are hinged, thus
It is mounted on pestle bar axially moveably in first support.When test, to handle press when, pestle bar moves down, when pestle bar with
Under briquetting cavity after end in contact, it is mobile to the direction of close objective table to continue drive briquetting, until it is to be tested to compress terminal compression
Vibrating motor；After test, release handle, damping spring resets under elastic reaction, while driving briquetting to moving up
It is dynamic, move the direction for compressing the separate objective table in terminal edge.
As shown in Fig. 1 and Fig. 4, audio collection mechanism includes second support 31, by flexible constraint is installed on second support
Interior sound transducer 32 and prevent the irreflexive circular cowling 33 of sound.Second support is cage bracket, mainly by flexible support
It is constituted with the squirrel-cage bracket 311 being attached thereto, flexible support is fixed on the worktable, and squirrel-cage bracket is for installing sound biography
Sensor 32.The sensitivity of sound transducer is 50mV/Pa, and frequency band induction precision is 1 × 10-12, through having for conversion sound transducer
Effect operation interval is 40dB~120dB.By being fixed on the fixation being overlapped to form on the spider of squirrel-cage bracket both ends by strip-shaped rubber
Structure is mounted in cage bracket.Circular cowling 33 is suspended at sound transducer front end by being fixed on second support upper support bar.
In order to improve audio collection effect, the sound harvesting end of sound transducer is directed at vibrating motor, and the sound of sound transducer
Sound harvesting end is located on the loudness of a sound enveloping surface formed centered on card slot slot bottom center.In the present embodiment, as shown in figure 5,
Using the card slot being arranged on objective table notch as benchmark body, centered on card slot slot bottom center, the half of loudness of a sound signal envelope face
Diameter is 10cm, and therefore, loudness of a sound sound transducer is arranged in (the i.e. O in Fig. 5 of the point position apart from objective table notch side 10cm
Point).
Computer is connect with sound transducer, and sound transducer is by received audio signal transmission to computer, computer
For being handled received voice signal to obtain Mel cepstrum, and deposited according to obtained Mel cepstrum identification vibrating motor
Defect.
It is analyzed by ansys software, it is fixed according to the conservation of energy since the formant of objective table and rigid base is fixed
Reason can choose the material production objective table and rigid base of the main band that formant is generated far from vibrating motor operating.
Objective table in the present embodiment is prepared by No. 45 steel, in the formant such as Figure 11 of objective table and marble rigid base
Fx 2, it is 10 times of fundamental frequency, F in Figure 11x 1For the primary bands of vibrating motor operating, Fx 3To motivate formant, remaining is
System natural resonance peak.It can be seen from the figure that the main band that excitation formant is generated far from vibrating motor operating, thus
Avoid its interference to vibrating motor defects detection.
The present embodiment is made by using the fixed form that lower end rigidly fixes, upper end flexibility is fixed to vibrating motor
Vibrating motor and objective table card slot collide, and so that objective table and rigid base is generated forced vibration, and surrounding air is driven to shake
Dynamic, raw vibration signal is absorbed by objective table and the single rigid structure of rigid base and is not generated larger resonance, and guarantees to vibrate
The energy of signal dissipation is much smaller than the audio signal energies that sound transducer absorbs, it is ensured that is used for vibrating motor defect analysis
Audio signal data validity.
Vibrating motor defect recognition of the embodiment 2 based on audio analysis
1, orthogonal test
Several vibrating motor standard workpieces with various types of defects are chosen (including not have defective normal
Workpiece), orthogonal test then is carried out to the vibrating motor of selection according to the following steps, it is corresponding to obtain various types defect
Mel cepstrum band different degree coefficient:
(1) vibrating motor 15 is placed on objective table 1, using damping and amortization hold-down mechanism 2 by vibrating motor
It compresses.
Vibrating motor 15 is placed in objective table card slot, while by handle 23 to being installed in first support 21
Damping pestle component 22 press, pestle bar 221 presses to briquetting 224 by damping spring 223, and the compression terminal 225 of briquetting compresses
The conductive sheet of vibrating motor, vibrating motor faces upward, convenient to agree with flexible material buffer layer 16.
(2) starting vibrating motor rotation.
It is powered by the electrode being arranged in objective table pocket side wall to vibrating motor, vibrating motor is in eccentric block
Lower rotation is driven, and is collided with objective table card slot, objective table and marble rigid base generate forced vibration and constitute vibration
System, and surrounding air is driven to vibrate, the energy for vibrating generation is absorbed by objective table and marble rigid base.
(3) sound transducer of audio collection mechanism acquires audio signal, through acquiring the audio signal of acquisition through data
Device is transmitted to computer.
The audio signal that sound transducer operates vibrating motor and vibrational system generates, and by audio signal transmission
To computer.
(4) computer is handled to obtain Mel cepstrum to the audio signal received, including it is following step by step:
(41) audio signal of acquisition is obtained corresponding with audio signal through preemphasis, discrete Fast Fourier Transform iterative inversion FFT
Spectrum information.
With the continuous acquisition of signal, sound transducer collects stable motor operating characteristics signal.Micro-vibration horse
It is human-computer interaction up to itself, a large amount of signals concentrate on high frequency section, in order to which the high frequency section to audio signal aggravates, go
The influence of biggish low frequency energy caused by except being resonated due to vibrational system, increases the high frequency resolution of identification, and the present embodiment is first
Preemphasis, discrete Fast Fourier Transform iterative inversion FFT first are carried out to the audio signal of acquisition, to obtain frequency spectrum corresponding with audio signal
Information.
The original audio signal of acquisition is carried out by single order FIR high-pass digital filter (see following formula (1)) first
Processing, obtains the audio signal of preemphasis.
Y (t)=x (t)-ax (t-1) (1)
In formula, x (t) represents the speech sample value of t moment, and x (t-1) represents the speech sample value at t-1 moment, and y (t) is represented
Preemphasis treated t moment audio signal, a is pre emphasis factor, 0.9 < a < 1.0.A weighted is taken to transport mode, a in the present embodiment
=0.94.
Shown in original audio signal such as Fig. 6 (a), by shown in audio signal such as Fig. 6 (b) after quick A weighted.
Then (see following formula (2)) are handled using discrete Fast Fourier Transform iterative inversion FFT to the audio signal after preemphasis,
Here FFT uses Hamming window, a length of 15ms when taking window.
Y (ω)=FFT [y (t)] (2)
Wherein y (t) is the audio signal after preemphasis, and FFT [] is Fast Fourier Transform (FFT), and Y (ω) is through quick Fu
In leaf transformation to frequency domain spectrum information.Spectrum information of the audio signal after Fast Fourier Transform (FFT) such as Fig. 7 after preemphasis
It is shown.
(42) spectrum information that step (41) obtains is handled using triangle bandpass filter group, obtains Mel frequency spectrum
(i.e. Meier frequency spectrum).
Frequency spectrum above is obtained into Mel frequency spectrum by Mel filter group；(by Mel frequency spectrum, by linear natural frequency spectrum
LinearFrequency is converted to the Mel frequency spectrum melFrequency for embodying human auditory system)
MelFrequency=2595*log (1+linearFrequency/700) (3)
Wherein linearFrequency indicates the frequency spectrum after FFT, the change of linearFrequency and melFrequency
It is as shown in Figure 8 to change relationship.
The spectrum information Y (ω) that step (41) Fast Fourier Transform (FFT) obtains is used at triangle bandpass filter group
It is as shown in Figure 9 to manage obtained Mel frequency spectrum.
(43) it is based on Mel frequency spectrum, obtains Mel cepstrum.
The signal on Mel frequency spectrum obtained to step (42) does logarithm operation,
That is log X [ω]=log (melFrequency) (4)；
And split the signal on Mel frequency spectrum, it is split as envelope signal (i.e. low frequency part) and amount of detail signal (i.e.
High frequency section):
Log X [ω]=log H [ω]+log E [ω] (5)
Wherein, X [ω] is frequency spectrum overall signal, and H [ω] is spectrum envelope signal, and E [ω] is amount of detail signal in frequency spectrum.
Inverse Fourier transform IDFT is done to the signal after logarithm operation, obtains Mel cepstrum.
X ' [t]=h ' [t]+e ' [t] (6)
Wherein, x ' [t], h ' [t], e ' [t] respectively correspond X [ω], H [ω], E [ω] and carry out inverse Fourier transform IDFT knot
Fruit.
It by taking scramble, is split each at split-band, the Mel cepstrum band split out is as shown in Figure 10.
Choose it is several have various types defect (including sound is excessive, sound is too sharp, sound with noise, sound too
Small and sound gradual change is obvious) vibrating motor and qualified vibrating motor as standard component, to the standard component weight of selection
Multiple step (1)-(4) obtain various types defect vibrating motor Mel cepstrum corresponding with qualified vibrating motor.
(5) the Mel cepstrum band different degree coefficient under different type defect is obtained.
The various types defect vibrating motor Mel corresponding with qualified vibrating motor obtained according to step (4)
Cepstrum, the different degree coefficient of each bands of a spectrum of Mel cepstrum is established,
Each bands of a spectrum different degree coefficient of Mel cepstrum is obtained using old attribute reduction algorithms.It is so-called brief, i.e., do not influencing decision system
Under the premise of system ability, by the process of attribute deletion unnecessary in Mel cepstrum and redundancy.
Below by taking a qualified vibrating motor workpiece as an example, to illustrate the meter of each bands of a spectrum different degree coefficient of Mel cepstrum
Calculation method.
Given neighborhood decision system a NDS=<U, A, D>:
(1) U is domain, is made of all data in the vibrating motor workpiece Mel cepstrum, U={ x1,x2,…,
xi,…xN, xiTo indicate i-th of bands of a spectrum data in Mel cepstrum, i represents each bands of a spectrum serial number of Mel cepstrum, i=1,2 ..., N, N
For Mel cepstrum bands of a spectrum total quantity.For xi∈ U defines xiNeighborhood be δ (xi), δ (xi)={ x | x ∈ U, △ (x, xi)≤δ },
Wherein δ >=0, δ (xi) become xiNeighborhood particle, △ be a distance function.
(2) A is property set, is made of the median frequency of Mel cepstrum, degree of skewness, average value, kurtosis etc..
(3) D is decision kind set, by the ratio between the total energy value of each bands of a spectrum energy of Mel cepstrum and corresponding Mel cepstrum structure
At domain U is divided into N number of equivalence class (X1, X2..., Xi..., XN)；B is set as conditional attribute collection,Decision category
Lower aprons of the property D about B is defined as:
Wherein,
NB D is commonly referred to as the positive domain of decision of neighborhood decision system, is also denoted as POSB(D).The numerical value in positive domain can reflect classification
Separable degree of the problem in given attribute space, positive domain is bigger, shows that all kinds of overlapping regions is fewer.
Due toAttribute a is calculated relative to the different degree coefficient C of B according to following formula,
C (a, B, D)=γB∪a(D)-γB(D) (8)；
In formula, γBIt (D) is dependency degree of the decision attribute D to conditional attribute B, γB∪aIt (D) is decision attribute D to condition category
The dependency degree of property B ∪ a.Below with γB(D) for, illustrate γB(D) calculation method, γB∪a(D) calculation method is similar.γB
(D) it is calculated according to following formula:
As can be seen from the above analysis, attribute a is to delete from conditional attribute collection B ∪ a for the different degree of decision attribute D
After attribute a, degree that decision attribute D reduces conditional attribute B dependency degree.
The present embodiment obtains conditional attribute collection B according to the following steps:
(S1) initialization set, empties collection
(S2) to any al∈ A-B calculates C (al, B, D) and=γB∪a(D)-γB(D), it defines
(S3) a is selectedk, it is made to meet C (ak, B, D) and=max (C (al, B, D))；
(S4) if C (ak, B, D) and > 0, then by B ∪ ak→ B, otherwise illustrates akWith attribute independent in B, different degree coefficient is 0,
By B → B.After judgement, step (S2)-(S4) is repeated, until the different degree coefficient of remaining attribute is 0, output condition category
The different degree that the corresponding different degree coefficient of property element in property collection B, the as workpiece correspond to important bands of a spectrum in each bands of a spectrum of Mel cepstrum
Coefficient Ci, the different degree coefficient zero setting of remaining bands of a spectrum.Pass through the Mel cepstrum bands of a spectrum for the qualified workpiece that different degree coefficient marks
It is as shown in figure 12 in the substep of frequency domain.
The corresponding different degree coefficient of each bands of a spectrum of Mel cepstrum of available all standard workpieces according to the method described above, and benefit
Corresponding bands of a spectrum are marked with different degree coefficient.
By the corresponding different degree coefficient label of all vibrating motor standard workpieces of same type defect or qualification
Mel cepstrum is summarized, and the bands of a spectrum energy of each Mel cepstrum same position of all standard workpieces is averaged, with the average value
Corresponding bands of a spectrum energy setting valve as the type defect vibrating motor or qualified vibrating motor.
The Mel cepstrum spectrum of the different degree coefficient label of all types defect vibrating motor and qualified vibrating motor
The energy setting valve of band and each bands of a spectrum is built into vibrating motor java standard library.
2, defects detection is carried out to vibrating motor
The present embodiment identifies vibrating motor defect using the diagnostic device that embodiment 1 provides, and specifically includes
Following steps:
(1) vibrating motor to be tested is placed on objective table, using damping and amortization hold-down mechanism by micro-vibration horse
Up to compression；
(2) starting vibrating motor rotation；
(3) sound transducer of audio collection mechanism acquires audio signal, through acquiring the audio signal of acquisition through data
Device is transmitted to computer；
(4) audio signal received is handled to obtain Mel cepstrum, and miniature according to obtained Mel cepstrum identification
Defect existing for vibrating motor.
Step (1)-(3) are identical as step (1)-(3) in orthogonal test, and which is not described herein again.
For step (4), comprising the following steps:
(41) audio signal of acquisition is obtained corresponding with vibration signal through preemphasis, discrete Fast Fourier Transform iterative inversion FFT
Spectrum information；
(42) spectrum information that step (41) obtains is handled using triangle bandpass filter group, obtains Mel frequency spectrum；
(43) it is based on Mel frequency spectrum, obtains Mel cepstrum；
(44) different degree corresponding with each bands of a spectrum of Mel cepstrum is calculated using based on the preceding old attribute reduction algorithms to greed
Coefficient, and extract the corresponding bands of a spectrum of part of different degree coefficient, by the partial spectrum band of extraction and under various types defect
The bands of a spectrum of Mel cepstrum corresponding position are integrally compared, and determine vibrating motor with the presence or absence of defect and defect kind.
Step (41)-(43) are identical as step (41)-(43) in orthogonal test, and which is not described herein again.
For step (44), method obtains the corresponding different degree of each bands of a spectrum of workpiece for measurement Mel cepstrum as described above
Coefficient.
According to the obtained corresponding different degree coefficient of each bands of a spectrum of workpiece for measurement Mel cepstrum, according to sequence from big to small, from
It is middle to extract multiple (the present embodiment extraction is five) corresponding bands of a spectrum of different degree coefficient, by multiple bands of a spectrum of extraction and miniature vibration
The Mel cepstrum bands of a spectrum of different degree coefficient label in dynamic motor java standard library under various types defect are integrally compared, and are determined micro-
Type vibrating motor whether there is defect and defect kind.It, can be true according to the different degree coefficient of workpiece for measurement in the present embodiment
Surely the position of five bands of a spectrum extracted, then by the energy of five bands of a spectrum of extraction respectively with it is each in vibrating motor java standard library
The energy setting valve that seed type defect corresponds to bands of a spectrum is compared, and takes this energy of five bands of a spectrum energy deviations within 15%
Defect type of the corresponding defect type of setting valve as the workpiece for measurement.
In addition, according to the analysis of front as can be seen that the vibrating motor for different defect types, different degree system
Number distribution is different, therefore, according to the position distributions of five bands of a spectrum extracted from workpiece for measurement Mel cepstrum (namely different degree
Coefficient distribution), band position therewith can be directly found from vibrating motor java standard library and is distributed identical defect type, so
And in order to improve defect recognition accuracy, it is still necessary to which the energy of five bands of a spectrum of extraction and the corresponding defect type found is miniature
The energy setting valves of corresponding bands of a spectrum be compared, only when meeting simultaneously with this five bands of a spectrum energy deviations within 15%
When, which is just used as the defect type of workpiece for measurement.
The present invention simulates human ear frequency spectrum, and the information being collected into, which is done auto-correlation computation, reduces jump signal, then passes through neighborhood
Analytic approach screens main feature energy band, the specific information in vibrating motor operation process is finally obtained, to micro-vibration
Motor defect is identified.
Vibrating motor of the present invention collides when working with objective table card slot, generates forced vibration, while driving week
Enclose air vibration, by the analysis of ansys software, formant is fixed for objective table and rigid base, therefore can according to concrete scene,
Decide whether that each rank formant will be rejected in its audio signal from acquisition.According to principle of conservation of energy, it can design and allow loading
The frequency band that the formant for the vibrational system that platform and rigid base are constituted is vibrated far from micro motor, audio transmission large energy.
The present invention carries out orthogonal test in the vibrating motor work with various types defect first, obtains various
Each frequency band different degree coefficient of Mel cepstrum under type flaw.Then on the basis of orthogonal test, optimized according to neighborhood Importance Degree Method
Feature band, and by itself and corresponding orthogonal experiment defect audio indicia, finally it is used as vibrating motor defect estimation.
It using this method workpiece Installation And Test, can be completed in 2s, therefore can fast and accurately realize each operating condition
Under micro- characteristic vibration motor identification, and improve comfort.
Those of ordinary skill in the art will understand that embodiment here be to help reader understand it is of the invention
Principle, it should be understood that protection scope of the present invention is not limited to such specific embodiments and embodiments.This field it is common
Technical staff disclosed the technical disclosures can make the various various other tools for not departing from essence of the invention according to the present invention
Body variations and combinations, these variations and combinations are still within the scope of the present invention.
Claims (10)
1. a kind of vibrating motor defect diagonsis device based on audio analysis, it is characterised in that including to be tested for installing
The objective table (1) of vibrating motor, for being fixed vibrating motor in the hold-down mechanism (2) on objective table, position
Audio collection mechanism (3) and computer (4) in vibrating motor side；Objective table ontology (11) design has a notch
(12), design has the card slot to match with vibrating motor external form on one cell wall of notch, and card slot design prevents micro-vibration
The position limiting structure of motor axial movement, design, which has, on another cell wall of notch connects the corresponding electrode of power port with vibrating motor
(14)；The hold-down mechanism is damping and amortization hold-down mechanism, including first support (21), the damping pestle group being mounted in first support
Part (22) and the pressure assembly to press to the pestle bar in damping pestle component；The audio collection mechanism (3) includes second support
(31), the sound transducer (32) in second support, the sound harvesting end alignment of sound transducer are installed on by flexible constraint
Vibrating motor；The computer is connect with sound transducer (32), for being handled to obtain to received voice signal
The Mel frequency spectrum MFCC of falling coefficient, and the defect according to existing for the obtained Mel frequency spectrum MFCC of falling coefficient identification vibrating motor.
2. the vibrating motor defect diagonsis device based on audio analysis according to claim 1, it is characterised in that described
Damping pestle component includes that pestle bar (221), damping spring (223) and briquetting (224), pestle bar are axially moveably mounted on first
On frame, briquetting is mounted on pestle bar lower end, and damping spring is nested on pestle bar, and lower end acts on briquetting, and upper end acts on pestle bar
As the position limiting structure of spring base, pestle bar presses to briquetting by damping spring.
3. the vibrating motor defect diagonsis device based on audio analysis according to claim 2, it is characterised in that described
Pestle bar is composite structure pestle bar, is made of pestle bar body and the bolt (222) as pestle bar extension body, bolt by screw thread pair and
The connection of pestle bar；The briquetting is the briquetting equipped with cavity, and the opening direction of cavity is perpendicular to pestle bar, and briquetting on cavity wall by pacifying
Dress hole can be mounted on bolt to axial float, and damping spring is nested with outside bolt.
4. the vibrating motor defect diagonsis device based on audio analysis according to claim 3, it is characterised in that described
Briquetting compresses side and is provided with the compression terminal that the material being adapted to vibrating motor upper end surface structure is plastics or rubber
(225)。
5. the vibrating motor defect diagonsis device based on audio analysis according to claim 1, it is characterised in that card slot
On position limiting structure be made of the limit film (13) being fixed on objective table ontology.
6. the vibrating motor defect diagonsis device based on audio analysis according to claim 1, other are characterized in that institute
Stating second support is cage bracket, and sound transducer is overlapped to form by being fixed on the spider of squirrel-cage bracket both ends by strip-shaped rubber
Fixed structure be mounted in cage bracket.
7. according to claim 1 to 6 any vibrating motor defect diagonsis devices based on audio analysis, other features
It is that the sound harvesting end of the sound transducer is located on the loudness of a sound enveloping surface formed centered on card slot slot bottom center.
8. according to claim 1 to the vibrating motor defect diagonsis device described in 6 any claims based on audio analysis,
Other, which are characterized in that the audio collection structure is also devised with, prevents the irreflexive circular cowling of sound (33), and circular cowling passes through fixation
Sound transducer front end is suspended in second support upper support bar (312).
9. a kind of carry out knowledge method for distinguishing to vibrating motor defect using any diagnostic device of claim 1 to 8,
Be characterized in that the following steps are included:
(1) vibrating motor to be tested is placed on objective table, using damping and amortization hold-down mechanism by vibrating motor pressure
Tightly；
(2) starting vibrating motor rotation；
(3) sound transducer of audio collection mechanism acquires audio signal, through passing the audio signal of acquisition through data collector
Transport to computer；
(4) audio signal received is handled to obtain Mel cepstrum, and micro-vibration is recognized according to obtained Mel cepstrum
Defect existing for motor.
10. vibrating motor defect identification method according to claim 9, it is characterised in that step (4) includes following point
Step:
(41) frequency corresponding with audio signal is obtained through preemphasis, discrete Fast Fourier Transform iterative inversion FFT to the audio signal of acquisition
Spectrum information；
(42) spectrum information that step (41) obtains is handled using triangle bandpass filter group, obtains Meier frequency spectrum；
(43) it is based on Mel frequency spectrum, obtains Mel cepstrum；
(44) different degree corresponding with each bands of a spectrum of Mel cepstrum system is calculated using based on the preceding old attribute reduction algorithms to greed
Number, and extracts the corresponding bands of a spectrum of part of different degree coefficient, by the partial spectrum band of extraction and with the Mel under various types defect
The bands of a spectrum of cepstrum corresponding position are integrally compared, and determine vibrating motor with the presence or absence of defect and defect kind.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910277843.9A CN110082107B (en) | 2019-04-08 | 2019-04-08 | Micro vibration motor defect diagnosis device and defect identification method based on audio analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910277843.9A CN110082107B (en) | 2019-04-08 | 2019-04-08 | Micro vibration motor defect diagnosis device and defect identification method based on audio analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110082107A true CN110082107A (en) | 2019-08-02 |
| CN110082107B CN110082107B (en) | 2021-03-02 |
Family
ID=67414495
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910277843.9A Active CN110082107B (en) | 2019-04-08 | 2019-04-08 | Micro vibration motor defect diagnosis device and defect identification method based on audio analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110082107B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110472587A (en) * | 2019-08-19 | 2019-11-19 | 四川大学 | Vibrating motor defect identification method and device based on CNN and sound time-frequency characteristics figure |
| CN110602488A (en) * | 2019-09-18 | 2019-12-20 | 普联技术有限公司 | Day and night type camera device switching abnormity detection method and device and camera device |
| CN110954826A (en) * | 2019-12-17 | 2020-04-03 | 四川安和精密电子电器股份有限公司 | Step screw motor defect diagnosis device and defect identification method based on audio analysis |
| CN111783616A (en) * | 2020-06-28 | 2020-10-16 | 北京瓦特曼科技有限公司 | Data-driven self-learning-based nondestructive testing method |
| CN111798865A (en) * | 2020-07-07 | 2020-10-20 | 北京字节跳动网络技术有限公司 | Terminal motor detection method and device, terminal and storage medium |
| CN112212968A (en) * | 2020-09-15 | 2021-01-12 | 深圳传世生物医疗有限公司 | Vibration detection method and device for mixing cup grabbing hand |
| CN112945376A (en) * | 2021-03-24 | 2021-06-11 | 东风汽车集团股份有限公司 | Noise detection method, system and medium for adjusting motor of vehicle outside rear-view mirror lens |
| CN113588782A (en) * | 2021-07-01 | 2021-11-02 | 广州珠江天然气发电有限公司 | Nondestructive inspection method, device and equipment based on audio analysis |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101701938A (en) * | 2009-11-23 | 2010-05-05 | 中国计量学院 | Audio detection method of defect type of workpiece adopting vibrating-mode frequency combination |
| EP2538034A2 (en) * | 2011-06-23 | 2012-12-26 | United Technologies Corporation | MFCC and CELP to detect turbine engine faults |
| CN105203928A (en) * | 2015-08-07 | 2015-12-30 | 北重阿尔斯通（北京）电气装备有限公司 | Device and method for detecting insulation integrity of motor stator coil bar |
| CN105244038A (en) * | 2015-09-30 | 2016-01-13 | 金陵科技学院 | Ore dressing equipment fault abnormity audio analyzing and identifying method based on HMM |
| CN105841797A (en) * | 2016-03-15 | 2016-08-10 | 中南大学 | Window motor abnormal noise detection method and apparatus based on MFCC and SVM |
| CN106950499A (en) * | 2017-04-26 | 2017-07-14 | 贵州标准电机有限公司 | A kind of polytypic micro motor performance automatic checkout equipment |
| CN108490349A (en) * | 2018-01-23 | 2018-09-04 | 浙江大学山东工业技术研究院 | Motor abnormal sound detection method based on Mel frequency cepstral coefficients |
| CN208109885U (en) * | 2018-04-23 | 2018-11-16 | 南安市起胤机械科技有限公司 | A kind of integrated circuit testing multi-station positioning device |
| CN109406842A (en) * | 2018-11-30 | 2019-03-01 | 东风电动车辆股份有限公司 | Electromechanical testing platform |
| CN109443758A (en) * | 2018-12-29 | 2019-03-08 | 哈尔滨理工大学 | A kind of compound diagnostic device of rotating machinery |
-
2019
- 2019-04-08 CN CN201910277843.9A patent/CN110082107B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101701938A (en) * | 2009-11-23 | 2010-05-05 | 中国计量学院 | Audio detection method of defect type of workpiece adopting vibrating-mode frequency combination |
| EP2538034A2 (en) * | 2011-06-23 | 2012-12-26 | United Technologies Corporation | MFCC and CELP to detect turbine engine faults |
| CN105203928A (en) * | 2015-08-07 | 2015-12-30 | 北重阿尔斯通（北京）电气装备有限公司 | Device and method for detecting insulation integrity of motor stator coil bar |
| CN105244038A (en) * | 2015-09-30 | 2016-01-13 | 金陵科技学院 | Ore dressing equipment fault abnormity audio analyzing and identifying method based on HMM |
| CN105841797A (en) * | 2016-03-15 | 2016-08-10 | 中南大学 | Window motor abnormal noise detection method and apparatus based on MFCC and SVM |
| CN106950499A (en) * | 2017-04-26 | 2017-07-14 | 贵州标准电机有限公司 | A kind of polytypic micro motor performance automatic checkout equipment |
| CN108490349A (en) * | 2018-01-23 | 2018-09-04 | 浙江大学山东工业技术研究院 | Motor abnormal sound detection method based on Mel frequency cepstral coefficients |
| CN208109885U (en) * | 2018-04-23 | 2018-11-16 | 南安市起胤机械科技有限公司 | A kind of integrated circuit testing multi-station positioning device |
| CN109406842A (en) * | 2018-11-30 | 2019-03-01 | 东风电动车辆股份有限公司 | Electromechanical testing platform |
| CN109443758A (en) * | 2018-12-29 | 2019-03-08 | 哈尔滨理工大学 | A kind of compound diagnostic device of rotating machinery |
Non-Patent Citations (1)
| Title |
|---|
| 蒋聪等: "基于特征的机械设备故障预测系统", 《测量与检测技术》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110472587A (en) * | 2019-08-19 | 2019-11-19 | 四川大学 | Vibrating motor defect identification method and device based on CNN and sound time-frequency characteristics figure |
| CN110472587B (en) * | 2019-08-19 | 2022-02-08 | 四川大学 | Micro vibration motor defect identification method and device based on CNN and sound time-frequency characteristic diagram |
| CN110602488A (en) * | 2019-09-18 | 2019-12-20 | 普联技术有限公司 | Day and night type camera device switching abnormity detection method and device and camera device |
| CN110954826A (en) * | 2019-12-17 | 2020-04-03 | 四川安和精密电子电器股份有限公司 | Step screw motor defect diagnosis device and defect identification method based on audio analysis |
| CN110954826B (en) * | 2019-12-17 | 2022-01-07 | 四川安和精密电子电器股份有限公司 | Step screw motor defect diagnosis device and defect identification method based on audio analysis |
| CN111783616A (en) * | 2020-06-28 | 2020-10-16 | 北京瓦特曼科技有限公司 | Data-driven self-learning-based nondestructive testing method |
| CN111783616B (en) * | 2020-06-28 | 2024-03-26 | 北京瓦特曼科技有限公司 | Nondestructive testing method based on data-driven self-learning |
| CN111798865A (en) * | 2020-07-07 | 2020-10-20 | 北京字节跳动网络技术有限公司 | Terminal motor detection method and device, terminal and storage medium |
| CN112212968A (en) * | 2020-09-15 | 2021-01-12 | 深圳传世生物医疗有限公司 | Vibration detection method and device for mixing cup grabbing hand |
| CN112945376A (en) * | 2021-03-24 | 2021-06-11 | 东风汽车集团股份有限公司 | Noise detection method, system and medium for adjusting motor of vehicle outside rear-view mirror lens |
| CN113588782A (en) * | 2021-07-01 | 2021-11-02 | 广州珠江天然气发电有限公司 | Nondestructive inspection method, device and equipment based on audio analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110082107B (en) | 2021-03-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110082107A (en) | Vibrating motor defect diagonsis device and defect identification method based on audio analysis | |
| CN110472587A (en) | Vibrating motor defect identification method and device based on CNN and sound time-frequency characteristics figure | |
| CN110954826B (en) | Step screw motor defect diagnosis device and defect identification method based on audio analysis | |
| EP3839942A1 (en) | Quality inspection method, apparatus, device and computer storage medium for insurance recording | |
| CN101451977B (en) | Non- reference Lamb wave damnification monitoring method based on double-element piezoelectric sensor array and time window function | |
| CN202485793U (en) | Handset motor vibration testing device | |
| CN105841797A (en) | Window motor abnormal noise detection method and apparatus based on MFCC and SVM | |
| CN103149029B (en) | Cepstrum identification aeromotor is utilized to turn quiet method of touching position of rubbing | |
| CN109256146A (en) | Audio-frequency detection, device and storage medium | |
| CN105244038A (en) | Ore dressing equipment fault abnormity audio analyzing and identifying method based on HMM | |
| Zeng et al. | Classifying watermelon ripeness by analysing acoustic signals using mobile devices | |
| Wang et al. | Experimental investigation of the fault diagnosis of typical faults in reciprocating compressor valves | |
| WO2018057202A1 (en) | Audio signal emulation method and apparatus | |
| CN110161406A (en) | A kind of vibrating motor current mode failure diagnostic apparatus and diagnostic method | |
| CN206248204U (en) | Transportable transformer vibration characteristic signals detection means | |
| Verma et al. | Android app for intelligent CBM | |
| CN106596145A (en) | Motorcycle shock absorber testing and control system | |
| US8255178B2 (en) | Method for detecting statuses of components of semiconductor equipment and associated apparatus | |
| KR102275571B1 (en) | Method for providing smart device based fault diagnosis service using sound and vibration | |
| CN108009514A (en) | Level of material for ball mill Forecasting Methodology | |
| CN114739667A (en) | Multi-mode information fusion bearing lubrication state monitoring device and method | |
| US20220130411A1 (en) | Defect-detecting device and defect-detecting method for an audio device | |
| CN109342323B (en) | Device and method for eliminating interference of external vibration on photoacoustic cell | |
| Yi-Cheng et al. | Prognostic diagnosis of the health status of an air-turbine dental handpiece rotor by using sound and vibration signals | |
| Cavé et al. | A computer-driven system for assessing speech quality and intelligibility |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: No. 261, East Section of Feiyun Avenue, Mianyang City, Sichuan Province, 621000 Applicant after: Sichuan Anhe Precision Electronics and Electrical Appliances Co., Ltd. Applicant after: Sichuan University Address before: No. 261, East Section of Feiyun Avenue, Mianyang City, Sichuan Province, 621000 Applicant before: SICHUAN ANHE PRECISION ELECTRONIC ELECTRICAL APPLIANCES CO., LTD. Applicant before: Sichuan University |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |