CN110082107B - Micro vibration motor defect diagnosis device and defect identification method based on audio analysis - Google Patents
Micro vibration motor defect diagnosis device and defect identification method based on audio analysis Download PDFInfo
- Publication number
- CN110082107B CN110082107B CN201910277843.9A CN201910277843A CN110082107B CN 110082107 B CN110082107 B CN 110082107B CN 201910277843 A CN201910277843 A CN 201910277843A CN 110082107 B CN110082107 B CN 110082107B
- Authority
- CN
- China
- Prior art keywords
- vibration motor
- micro vibration
- audio
- micro
- 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.)
- Active
Links
Images
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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Engineering & Computer Science (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Discrete Mathematics (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a defect diagnosis device and a defect identification method of a miniature vibration motor based on audio analysis, wherein the diagnosis device mainly comprises an object stage, a pressing mechanism, an audio acquisition mechanism and a computer; the method comprises the steps of firstly fixing a micro vibration motor in a clamping groove of an objective table by using a damping pressing mechanism to form a fixing mode with rigid lower end and flexible upper end, then collecting audio signals by a sound sensor of an audio collecting mechanism, processing the audio signals by a computer, converting the collected audio signals into human ear Mel frequency spectrum, and identifying the defects of the micro vibration motor by the distribution of importance coefficients of each frequency band, thereby realizing the nondestructive, real-time and high-precision detection of the defects of the micro vibration motor. The invention can realize the defect detection of the micro vibration motor with the eccentric block, fills the blank of the detection technology of the micro vibration motor with the eccentric block and has great application prospect in the technical field of nondestructive detection.
Description
Technical Field
The invention belongs to the technical field of machine defect detection, relates to a miniature vibration motor defect detection technology based on audio analysis, and particularly relates to a diagnosis device and a recognition method for realizing motor defect recognition by simulating miniature tactile feedback by human ears based on a neighborhood analysis method.
Background
With the rapid development of interactive electronic devices, people will increasingly pay more attention to the problem of whether the devices can stably transmit effective signals in operation. The micro vibration motor is used as a basis for transmitting vibration signals of the interactive electronic equipment, and the stability of the state of the micro vibration motor is directly related to the experience and even safety of a user. The production environment at home and abroad has long started to carry out various nondestructive tests on the miniature vibration motor so as to ensure the touch, hearing comfort and safety of users when the electronic equipment is used. Meanwhile, the production quantity and the demand of the electronic equipment are huge (only in China, about 35 hundred million interactive electronic equipment with feedback effect are put on the market every year), so that the quality of the electronic equipment is detected and the detection efficiency is high.
At present, the nondestructive detection technology of the miniature vibration motor mainly comprises operation voltage detection, vibration detection, infrared detection and the like. Japanese keyence corporation invented a device for detecting motor damage from vibration signals generated during motor operation, which has a high false rate due to the complexity of the vibration signals and can only identify relatively simple types of faults. Vibration type micro motor detection device is further developed by Kunzshan Meyer measurement and control equipment company, but the identification efficiency of the device is still not high, the operation loss condition of the vibration motor with the eccentric block cannot be detected, and the requirement on detection speed cannot be met. TSC company has developed the port current detection system of miniature motor, discerns the transient fault signal of motor current in the miniature vibrating motor operation, and when the sampling frequency reached 50KHz, detection system can realize 10/s's detection speed, but such detection speed still is very low to with vibration detection, can't detect whether miniature vibrating motor with eccentric block normally worked and differentiate the travelling comfort that the user used.
The other mature motor nondestructive detection technology is audio detection, the existing audio detection technology is used for detecting the miniature vibration motor without the eccentric block, and is mainly used for detecting transient faults in audio signals. Therefore, this detection method cannot satisfy the generation environment of a large amount of tactile feedback at present. And because the signal data required by transient analysis are extracted from a period of time, the real-time performance is generally difficult to meet, and the detection speed of the detection method for the micro vibration motor is low.
In summary, the conventional micro vibration motor nondestructive testing technology cannot achieve high testing speed or achieve simultaneous testing of various performances. With the development of haptic feedback devices, it is urgently needed to develop a technology capable of implementing non-destructive testing of various aspects of performance (such as shaft deformation, vibration failure caused by bearing wear, etc.) of a micro-vibration motor in synchronization with production speed, so as to ensure the detection speed of production and the safety and comfort of users.
Disclosure of Invention
Aiming at the problems that the detection speed is low and the comprehensive detection of all aspects of performances of the miniature vibration motor cannot be realized simultaneously in the existing miniature vibration motor nondestructive detection technology, the invention aims to provide a miniature vibration motor defect diagnosis device and a defect identification method based on audio analysis, which can simultaneously realize the high-speed nondestructive detection of the defects of the miniature vibration motor, such as overlarge sound, too sharp sound, accompanying noise, too small sound and obvious sound gradual change, caused by the faults of shaft deformation, bearing abrasion, shell deformation, too little lubricating oil, sundries and the like on a rotor.
Audio detection researches show that the sensitivity intensity of human ears to sound is unevenly distributed, and when the control tremor frequency caused by a vibration system is changed between 3000 Hz and 4000Hz, the human ears have strong bur noise. When the micro vibration motor product has defects, the frequency band energy generated by the micro vibration motor product is greatly different from that of a normal micro vibration motor product, and the frequency band energy distribution of the normal micro vibration motor product is specified according to the provisions of GB _ T2298-2010 and Japanese Kawasaki heavy work regulation 1345. Therefore, according to the distribution condition of different sound frequency bands in the human ear Mel frequency spectrum, the collected audio signals are converted into the Mel frequency spectrum, the judgment weight is increased in the human ear sensitive band (especially in the 3000-4000 Hz part), and finally, the defect detection of the vibration motor is realized by utilizing different sensitivity distribution information on the human ear analog frequency band.
Based on the above invention thought, the miniature vibration motor defect diagnosis device based on audio analysis provided by the invention comprises an objective table for mounting the miniature vibration motor to be tested, a pressing mechanism for pressing and fixing the miniature vibration motor on the objective table, an audio acquisition mechanism positioned on one side of the miniature vibration motor and a computer; the object stage body is provided with a notch, a clamping groove matched with the shape of the micro vibration motor is arranged on one groove wall of the notch, a limiting structure for preventing the micro vibration motor from axially moving is arranged on the clamping groove, and an electrode corresponding to a power connection port of the micro vibration motor is arranged on the other groove wall of the notch; the pressing mechanism is a damping pressing mechanism and comprises a first support, a damping pestle component arranged on the first support and a pressing component for pressing a pestle rod in the damping pestle component; the audio acquisition mechanism comprises a second bracket and a sound sensor arranged in the second bracket through flexible constraint, and the sound acquisition end of the sound sensor is aligned with the micro vibration motor; and the computer is connected with the sound sensor and is used for processing the received sound signal to obtain a Mel frequency spectrum inverse coefficient MFCC and identifying the defects of the micro vibration motor according to the obtained Mel frequency spectrum inverse coefficient MFCC.
Based on the law of conservation of energy, when the vibration system generates large-area resonance, the energy of the system is dissipated quickly, and the vibration signal tends to be discretized and mixed. The more the rigid system structure is, the weaker the discretization of the transmitted vibration signal is, and the fewer the resonance peaks are generated. Based on the analysis, the invention adopts a fixing mode of rigidity at the lower end and flexibility at the upper end for fixing the micro vibration motor to be tested.
The lower end rigid fixation is realized by an objective table used for installing a micro vibration motor to be tested. The objective table selects a single rigid structure, the objective table is further fixed on the rigid base, the objective table and the rigid base form a vibration system, and the single rigid structure can absorb vibration signals of the vibration system and does not produce large resonance. The rigid structure is made of high-hardness materials such as steel, silicon steel sheets or ferrite materials. When the rigid structure base is further processed by shockproof treatment, the isolated rigid single system has better signal restraint, so that the vibration signal generated by the collision of the rotation of the micro vibration motor and the objective table can be used for secondary indirect measurement. The micro vibration motor to be tested is fixed in the clamping groove on the side wall of the notch of the object stage body. For the micro vibration motor with the eccentric block, in order to prevent the micro vibration motor from moving axially, a corresponding limiting structure is designed on the clamping groove. In order to fix the micro vibration motor in the clamping groove of the objective table, a magnet for attracting the micro vibration motor can be arranged at the bottom of the notch or the clamping groove.
The upper end flexible fixation is realized through a damping pressing mechanism. After the micro vibration motor to be tested is installed in the objective table, the micro vibration motor is pressed by the damping pestle component of the damping pressing mechanism under the action of the pressing component. On one hand, when the micro vibrating motor rotates, the damping pestle component can prevent the micro vibrating motor from flying out; on the other hand, the damping pestle subassembly can freely stretch out and draw back in certain extent along with micro motor rotates to realize the stable centre gripping to micro vibrating motor under the condition of not destroying micro vibrating motor structure. Damping pestle subassembly includes pestle pole, damping spring and briquetting, but pestle pole axial motion ground installs on first support, and the briquetting is installed at pestle pole lower extreme, and the damping spring cover is put on pestle pole, and the lower extreme acts on the briquetting, and the upper end acts on the pestle pole as the limit structure of spring holder, and the pestle pole is exerted pressure to the briquetting through damping spring. According to the invention, the pestle rod is of a combined structure and comprises a pestle rod body and a bolt serving as an extension body of the pestle rod, and the bolt is connected with the pestle rod through a thread pair; the briquetting is the briquetting that is equipped with the cavity, and the opening direction perpendicular to pestle pole of cavity, but the briquetting passes through cavity wall mounting hole and installs on the bolt with axial float, and damping spring cover is put outside the bolt. And the pressing block pressing side is provided with a pressing terminal which is matched with the structure of the upper end face of the micro vibration motor and is made of plastic, rubber and the like. And rubber is arranged at the contact part of the compression terminal and the miniature vibration motor conducting strip and is used as a flexible material buffer layer. The pressure assembly for applying pressure to the damper pestle assembly may be a drive mechanism such as a pneumatic drive or a motor drive, or may be manually applied via a handle hinged to the pestle shaft.
The micro vibration motor to be tested is driven by the eccentric block to do eccentric vibration, so that the micro vibration motor collides with the clamping groove of the objective table, the objective table and the rigid base generate forced vibration and simultaneously drive surrounding air to vibrate, energy generated by vibration is distributed in a vibration system formed by the objective table and the rigid base, and the vibration system and the micro vibration motor jointly send out an audio signal which is enough to be received by a sound sensor of the audio acquisition mechanism. In order to reduce the influence of the collision of the micro vibration motor and the clamping groove of the object stage on the working state of the sound sensor, the sound sensor is required to be in a flexible shockproof link with the second bracket so as to ensure that the sound sensor receives audio signals without interference. Therefore, the second support is a cage support and mainly comprises a flexible support and a squirrel-cage support connected with the flexible support, the flexible support is fixed on the workbench, and the squirrel-cage support is used for mounting the sound sensor. The sound sensor is arranged in the cage type support through a fixing structure which is formed by overlapping strip-shaped rubber and fixed on hooping frames at two ends of the cage type support. In addition, the audio acquisition structure still designs the annular cover that prevents sound diffuse reflection, and the annular cover is through being fixed in the bracing piece suspension on the second support at the acoustic sensor front end. In order to improve the audio acquisition effect, the sound acquisition end of the sound sensor is positioned on a sound intensity enveloping surface which is formed by taking the center position of the groove bottom of the clamping groove as the center.
The invention further provides a method for identifying the defects of the micro vibration motor by using the diagnosis device, the micro vibration motor to be tested is pressed and fixed on the object stage by the damping pressing mechanism and is driven by the eccentric block to perform eccentric vibration so as to generate rigid collision with the object stage clamping groove, and audio signals sent by the vibration system and the micro vibration motor are collected by the audio collection mechanism and are transmitted to the computer. The computer converts the received audio signal into a frequency band region sensitive to human ears to obtain a human ear simulation frequency band, and realizes the defect detection of the vibration motor according to the sensitivity distribution information on the human ear simulation frequency band. In order to improve the defect detection precision of the miniature vibration motor, the invention further adopts a neighborhood analysis method to enable the frequency spectrum characteristics of the sensitive region to have higher weight, marks the characteristic energy frequency bands under various defects obtained by an orthogonal test, refers to the auditory Mel frequency spectrum energy characteristics of human ears, and takes the marked characteristic energy frequency bands as the characteristic discrimination standard.
The method for identifying the defects of the miniature vibration motor specifically comprises the following steps:
(1) placing the micro vibration motor to be tested on an objective table, and compacting the micro vibration motor by using a damping compaction mechanism;
(2) starting the micro vibration motor to rotate;
(3) a sound sensor of the audio acquisition mechanism acquires audio signals, and the acquired audio signals are transmitted to a computer through a data acquisition unit;
(4) and processing the received audio signal to obtain a Mel cepstrum, and identifying the defects of the micro vibration motor according to the obtained Mel cepstrum.
The step (4) comprises the following sub-steps:
(41) pre-emphasis and discrete Fast Fourier Transform (FFT) are carried out on the collected audio signals to obtain frequency spectrum information corresponding to the audio signals;
(42) processing the frequency spectrum information obtained in the step (41) by adopting a triangular band-pass filter bank to obtain a Mel frequency spectrum;
(43) acquiring a Mel cepstrum based on the Mel spectrum;
(44) and calculating by adopting an attribute reduction algorithm based on forward greedy to obtain an importance coefficient corresponding to each spectral band of the Mel cepstrum, extracting the spectral bands corresponding to part of the importance coefficients, comparing the extracted partial spectral bands with the spectral band whole at the corresponding positions of the Mel cepstrum under various types of defects, and determining whether the micro vibration motor has defects and defect types.
According to the defect diagnosis device and the defect identification method of the miniature vibration motor based on the audio analysis, provided by the invention, the acquired audio signals are converted into the human ear Mel frequency spectrum, a plurality of key cepstrum bands are determined through sensitivity distribution information (namely importance coefficients of different frequency bands) on different frequency bands, and then the selected cepstrum bands are compared with the whole spectrum band at the position corresponding to the Mel cepstrum under various types of defects, so that the defect detection of the miniature vibration motor is realized. From the installation of the sample to be detected to the completion of defect identification, the detection time is not more than 2s, the detection time is greatly shortened, and the detection efficiency is improved. The invention can also adjust the obtained feature weight proportion of each frequency band by adjusting the test envelope distance of the sound sensor, the running speed of the miniature vibration motor and the defect type of the motor; and then the audio energy collected by each characteristic frequency band is changed, so that the working condition of the miniature vibration motor can be accurately judged by a program.
Compared with the prior art, the micro vibration motor defect diagnosis device and the defect identification method based on audio analysis have the following beneficial effects:
1. the invention firstly fixes the micro vibration motor in the clamping groove of the objective table by using the damping pressing mechanism to form a fixing mode with rigid lower end and flexible upper end, then collects audio signals by a sound sensor of the audio collection mechanism, then processes the audio signals by a computer to convert the collected audio signals into human ear Mel frequency spectrum, confirms a plurality of key spectral bands by the importance coefficient distribution of each spectral band, and identifies the defects of the micro vibration motor according to the plurality of key spectral bands, thereby realizing the nondestructive, real-time and high-precision detection of the defects of the micro vibration motor.
2. The miniature vibration motor, the objective table clamping groove and the damping pestle are driven by the eccentric block to perform eccentric vibration, so that the miniature vibration motor collides with the objective table clamping groove, the collision energy is distributed in the whole vibration system, and the vibration system and the motor jointly send sound frequency spectrum distribution information which is enough to be recorded by an audio sensor, therefore, the defect detection of the miniature vibration motor with the eccentric block can be realized, the blank of the detection technology of the miniature vibration motor with the eccentric block is filled, and the miniature vibration motor with the eccentric block has a great application prospect in the technical field of nondestructive detection.
3. The lower end of the object stage is rigidly fixed, the upper end of the damping pressing mechanism is fixed, energy dissipation caused by device resonance can be greatly reduced, and the energy dissipation of vibration signals is far less than the energy of audio signals absorbed by the sound sensor, so that effective data are provided for audio signal analysis, and the detection precision of the defect detection of the miniature vibration motor is improved.
4. The invention analyzes the collected audio signal based on the frequency band area sensitive to human ears, thereby improving the comfort level of the human body using virtual touch feedback and being beneficial to the standardization of the vibration sounding quality control of the micro vibration motor.
5. The invention can realize the defect detection of all aspects of the micro-vibration motor (including overlarge sound, too sharp sound, sound accompanied by noise, too small sound, obvious sound gradient and the like), and is extremely suitable for the high-speed nondestructive detection of the micro-vibration motor and the working environment customized by standards.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other embodiments and drawings can be obtained according to the embodiments shown in the drawings without creative efforts.
Fig. 1 is a schematic diagram of a defect diagnosis device for a miniature vibration motor based on audio analysis.
Fig. 2 is an enlarged view of a portion a in fig. 1.
Fig. 3 is a schematic structural diagram of the pressing mechanism.
Fig. 4 is a schematic diagram of part of components of an audio acquisition mechanism.
Fig. 5 is a schematic diagram of a sound intensity envelope.
Fig. 6 is a diagram of audio signals before and after pre-emphasis processing, where (a) is a captured original audio signal and (b) is a pre-emphasis processed audio signal.
Fig. 7 is a fast fourier transform spectrogram.
FIG. 8 is a transformation of a linear spectrum to a Mel spectrum, where the triangular area is equal to the passband of a triangular band pass filter, and thus the length of the Mel spectrum.
Figure 9 is a plot of Mel spectrum.
FIG. 10 is the Mel inverted spectrum.
Fig. 11 is a vibration map collected during the operation of the micro vibration motor.
Fig. 12 is a graph of the Mel cepstrum importance coefficient spectrum for each frequency band corresponding to the qualified micro vibration motor.
The device comprises an object stage, an object stage body, a notch, a limiting sheet, electrodes, a micro vibration motor and a flexible material buffer layer, wherein the object stage comprises 1, 11, the object stage body, 12, the notch, 13, the limiting sheet, 14, the electrodes, 15 and the flexible material buffer layer;
2-hold down mechanism, 21-first bracket, 22-damping pestle component, 221-pestle rod, 222-bolt, 223-damping spring, 224-briquetting, 225-hold down terminal, 23-handle;
3-audio acquisition mechanism, 31-second bracket, 311-squirrel cage bracket, 312-support rod, 32-sound sensor, 33-annular cover.
Detailed Description
The technical solutions of the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings, and it is to be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The apparatus for diagnosing defect of micro vibration motor based on audio analysis provided by this embodiment, as shown in fig. 1, includes a stage 1 for mounting a micro vibration motor 15 to be tested, a pressing mechanism 2 for pressing and fixing the micro vibration motor on the stage, an audio collecting mechanism 3 located at one side of the micro vibration motor, and a computer 4. Objective table 1 and hold-down mechanism 2 set up on being located the marble rigid base on the workstation, and audio acquisition mechanism 3 and computer set up on the workstation, further set up the rubber pad between marble rigid base and the workstation to carry out shockproof processing to marble rigid base.
As shown in fig. 2, the objective table in this embodiment is an integrated structure, the objective table body 11 is fixed on the marble rigid base, the objective table body 11 is designed with a notch 12, a slot matched with the micro vibration motor in shape is designed on a slot wall of the notch, the slot is designed with a limiting piece 13 for preventing the micro vibration motor from moving axially, the limiting piece is fixed on an inner side wall of the slot, a limiting opening matched with the micro vibration motor eccentric block in shape is designed on the limiting piece, an electrode 14 corresponding to the micro vibration motor power connection port is designed on another slot wall of the notch, and a magnet for fixing the micro vibration motor is arranged at the bottom of the slot.
As shown in fig. 1 and 3, the pressing mechanism 2 is a damping pressing mechanism, and includes a first bracket 21, a damping pestle assembly 22 mounted on the first bracket, and a pressing assembly for pressing a pestle rod in the damping pestle assembly, and the pressing assembly in this embodiment is a handle 23. The damping pestle component comprises a pestle rod 221, a damping spring 223 and a pressing block 224, wherein the pressing block is arranged at the lower end of the pestle rod, the pestle rod is of a combined structure pestle rod and comprises a pestle rod body and a bolt 222 serving as an extension body of the pestle rod, the bolt is connected with the pestle rod body through a nut, the pressing block is a pressing block with a cavity, the opening direction of the cavity is perpendicular to the pestle rod, the bolt penetrates through a wall mounting hole of the cavity of the pressing block and is fixed through the nut, so that the pressing block can be axially movably arranged on the bolt, the damping spring 223 is sleeved on the bolt 222, the upper end of the damping spring acts on the nut serving as a spring seat. When the mounting hole of the cavity wall of the pressing block is too large, a gasket can be arranged at the upper end of the pressing block. The pressing block pressing side is provided with a pressing terminal 225 which is matched with the upper end face structure of the micro vibration motor and is made of plastic. The rubber is arranged at the contact part of the compression terminal and the micro vibration motor conducting strip and is used as a flexible material buffer layer 16. The first bracket 21 is fixed on the marble rigid base, the upper end of the first bracket 21 is provided with a clamping seat, the handle is connected to the clamping seat through a rotating shaft penetrating through the handle, and one end of the handle is hinged with the pestle rod body 221, so that the pestle rod can be axially movably arranged on the first bracket. During testing, when the handle is pressed, the pestle rod moves downwards, and after the pestle rod is contacted with the lower end of the pressing block cavity, the pressing block is continuously driven to move towards the direction close to the objective table until the pressing terminal presses the micro vibration motor to be tested; after the test is finished, the handle is loosened, the damping spring resets under the elastic action, and meanwhile, the pressing block is driven to move upwards, so that the pressing terminal moves along the direction away from the objective table.
As shown in fig. 1 and 4, the audio capturing mechanism includes a second holder 31, a sound sensor 32 mounted in the second holder by flexible restraint, and an annular cover 33 that prevents diffuse reflection of sound. The second support is a cage support, which is mainly composed of a flexible support and a squirrel-cage support 311 connected with the flexible support, the flexible support is fixed on the workbench, and the squirrel-cage support is used for installing the sound sensor 32. The sensitivity of the sound sensor is 50mV/Pa, and the frequency band induction precision is 1 multiplied by 10-12The effective working interval of the converted sound sensor is 40 dB-120 dB. The cage type bracket is installed in the cage type bracket through a fixing structure which is fixed on hooping frames at two ends of the cage type bracket and is formed by lapping strip-shaped rubber. The annular cover 33 is suspended at the front end of the acoustic sensor by a support rod fixed to the second bracket. In order to improve the audio acquisition effect, the sound acquisition end of the sound sensor is aligned with the micro vibration motor, and the sound acquisition end of the sound sensor is positioned on a sound intensity envelope surface which is formed by taking the center position of the groove bottom of the clamping groove as the center. In this embodiment, as shown in fig. 5, the slot provided in the slot of the stage is used as a reference body, the center position of the slot bottom is used as a center, and the radius of the sound intensity signal envelope surface is 10cm, so that the sound intensity sound sensor is disposed at a measuring point position (i.e., point O in fig. 5) which is 10cm away from one side of the slot of the stage.
The computer is connected with the sound sensor, the sound sensor transmits the received audio signal to the computer, and the computer is used for processing the received sound signal to obtain a Mel cepstrum and identifying the defects of the micro vibration motor according to the obtained Mel cepstrum.
Since the resonance peaks of the stage and the rigid base are fixed by the analysis of ansys software, the stage and the rigid base can be fabricated by selecting a material having a resonance peak far from the main frequency band generated by the operation of the micro vibration motor according to the energy conservation theorem. Object stage in this embodimentPrepared from No. 45 steel, and the resonance peak of the object stage and the marble rigid base is shown as F in figure 11x 210 times the fundamental frequency, F in FIG. 11x 1For the main frequency band of operation of micro-vibration motors, Fx 3The resonance peak is excited, and the rest is the intrinsic resonance peak of the system. As can be seen from the figure, the excitation formants are far away from the main frequency band generated by the operation of the micro vibration motor, so as to avoid the interference of the excitation formants on the defect detection of the micro vibration motor.
This embodiment is through adopting the lower extreme rigid fixation to miniature vibrating motor, the fixed mode of upper end flexible fixation, make miniature vibrating motor and objective table draw-in groove collision, make objective table and rigid base produce forced vibration, and drive the ambient air vibration, the vibration signal of giving birth is absorbed and not produce great resonance by objective table and the single rigid structure of rigid base, and guarantee that the energy of vibration signal dissipation is far less than the audio signal energy that sound sensor absorbed, ensure the audio signal data validity who is used for miniature vibrating motor defect analysis.
Example 2 micro vibration motor Defect identification based on Audio analysis
1. Quadrature test
Selecting a plurality of micro vibration motor standard workpieces (including normal workpieces without defects) with various types of defects, and then carrying out orthogonal test on the selected micro vibration motors according to the following steps to obtain Mel cepstrum significance coefficients corresponding to various types of defects:
(1) the micro vibration motor 15 is placed on the stage 1, and is pressed by the damping pressing mechanism 2.
The miniature vibration motor 15 is placed in the clamping groove of the objective table, meanwhile, the handle 23 applies pressure to the damping pestle component 22 installed on the first support 21, the pestle rod 221 applies pressure to the pressing block 224 through the damping spring 223, the pressing terminal 225 of the pressing block presses the miniature vibration motor, the conducting strip of the miniature vibration motor faces upwards, and the miniature vibration motor is conveniently matched with the flexible material buffer layer 16.
(2) And starting the micro vibration motor to rotate.
Through the electrode that sets up on the objective table notch lateral wall to miniature vibrating motor circular telegram, miniature vibrating motor rotates under eccentric block drives to bump with the objective table draw-in groove, objective table and marble rigid base produce forced vibration and constitute vibration system, and drive the ambient air vibration, the energy that the vibration produced is absorbed by objective table and marble rigid base.
(3) The sound sensor of the audio acquisition mechanism acquires audio signals, and the acquired audio signals are transmitted to the computer through the data acquisition unit.
The sound sensor operates the micro vibration motor and generates audio signals of the vibration system, and transmits the audio signals to the computer.
(4) The computer processes the received audio signal to obtain Mel cepstrum, and the method comprises the following steps:
(41) and pre-emphasizing the acquired audio signal, and performing discrete Fast Fourier Transform (FFT) to obtain frequency spectrum information corresponding to the audio signal.
Along with the continuous collection of the signals, the sound sensor collects stable motor running characteristic signals. The miniature vibration motor is human-computer interaction, and a large amount of signals are concentrated in the high-frequency part, and in order to aggravate the high-frequency part of audio signal, get rid of because the influence of the resonance of vibration system arouses great low-frequency energy, increase the high frequency resolution of discernment, this embodiment is at first carried out pre-emphasis, discrete fast Fourier transform FFT to the audio signal of gathering to obtain the spectral information that corresponds with the audio signal.
Firstly, the collected original audio signal is processed by a first-order FIR high-pass digital filter (see the following formula (1)) to obtain a pre-emphasized audio signal.
y(t)＝x(t)-ax(t-1) (1)
Wherein x (t) represents a speech sample value at the time t, x (t-1) represents a speech sample value at the time t-1, y (t) represents an audio signal at the time t after pre-emphasis processing, a is a pre-emphasis coefficient, and 0.9< a < 1.0. In this embodiment, a is taken as the authorization scheme, and a is 0.94.
The original audio signal is shown in fig. 6(a), and the audio signal weighted by the fast a is shown in fig. 6 (b).
The pre-emphasized audio signal is then processed using a discrete fast fourier transform FFT (see equation (2) below), where the FFT uses a hamming window, taking the window duration as 15 ms.
Y(ω)＝FFT[y(t)] (2)
Where Y (t) is the pre-emphasized audio signal, FFT [. cndot. ] is the fast Fourier transform, and Y (ω) is the spectral information that is fast Fourier transformed into the frequency domain. The spectral information of the pre-emphasized audio signal after fast fourier transform is shown in fig. 7.
(42) And (4) processing the spectrum information obtained in the step (41) by adopting a triangular band-pass filter bank to obtain a Mel spectrum (namely a Mel spectrum).
The spectrum above is processed by a Mel filter bank to obtain a Mel spectrum; (line-shaped natural frequency spectrum linear frequency is converted into Mel frequency spectrum melFrequency which embodies human auditory characteristics through Mel frequency spectrum)
melFrequency＝2595*log(1+linearFrequency/700) (3)
Wherein, linerfequency represents the frequency spectrum after FFT, and the transformation relationship between linerfequency and melFrequency is shown in FIG. 8.
Fig. 9 shows Mel spectrum obtained by processing the spectrum information Y (ω) obtained by the fast fourier transform in step (41) with a triangular band-pass filter bank.
(43) Based on the Mel-frequency spectrum, Mel-frequency cepstrum is obtained.
Performing logarithm operation on the signal on the Mel frequency spectrum obtained in the step (42),
namely log X ω ═ log (melfrequency) (4);
and splitting the signal on the Mel frequency spectrum into an envelope signal (namely a low-frequency part) and a detail quantity signal (namely a high-frequency part):
log X[ω]＝log H[ω]+log E[ω] (5)
wherein, X [ omega ] is the whole frequency spectrum signal, H [ omega ] is the frequency spectrum envelope signal, E [ omega ] is the detail quantity signal in the frequency spectrum.
And performing inverse Fourier transform (IDFT) on the signal subjected to the logarithmic operation to obtain a Mel cepstrum.
x′[t]＝h′[t]+e′[t] (6)
Wherein, X ', t, H ', t, E't are inverse Fourier transformed IDFT result corresponding to X, H, E.
By taking the cepstrum, the component bands are separated, and the separated Mel cepstrum bands are shown in fig. 10.
Selecting a plurality of miniature vibration motors with various defects (including loud sound, sharp sound, noise accompanied with sound, small sound and obvious sound gradual change) and qualified miniature vibration motors as standard parts, and repeating the steps (1) to (4) on the selected standard parts to obtain Mel cepstrums corresponding to the miniature vibration motors with various defects and the qualified miniature vibration motors.
(5) And acquiring Mel cepstrum band importance coefficients under different types of defects.
According to the Mel cepstrum corresponding to the miniature vibration motors with various defects and qualified miniature vibration motors obtained in the step (4), the importance coefficient of each spectral band of the Mel cepstrum is established,
and obtaining the importance coefficient of each spectral band of the Mel cepstrum by adopting an attribute reduction algorithm. So-called shorthand, i.e. the process of removing unnecessary and redundant attributes from the Mel-frequency cepstrum without affecting the capability of the decision-making system.
The method for calculating the importance coefficient of each spectral band of Mel cepstrum is described below by taking a qualified micro vibration motor workpiece as an example.
Given a neighborhood decision system NDS ═ U, a, D >:
(1) u is a domain and is formed by all data in the Mel cepstrum of the workpiece of the miniature vibration motor, and U is { x ═ x1,x2,…,xi,…xN}，xiTo represent the ith band data in Mel-frequency cepstrum, i represents the number of each band in Mel-frequency cepstrum, i is 1,2, …, and N is the total number of Mel-frequency cepstrum bands. For xiE.g. U, define xiIs δ (x)i)，δ(xi)＝{x|x∈U,△(x,xi) Delta is not more than 0, delta (x)i) Is xiIs a distance function.
(2) A is an attribute set and is composed of median frequency, skewness, average value, kurtosis and the like of the Mel cepstrum.
(3) D is a decision attribute set which is composed of the ratio of the energy of each spectral band of the Mel cepstrum to the total energy value of the corresponding Mel cepstrum, and divides the domain of discourse U into N equivalence classes (X)1，X2，…，Xi，…，XN) (ii) a Setting B as a condition attribute set,
the following approximation of decision attribute D with respect to B is defined as:
wherein the content of the first and second substances,
BNd is a decision-making domain commonly referred to as a neighborhood decision-making system, also denoted POSB(D) In that respect The value of the positive field may reflect the degree to which the classification problem is separable in a given attribute space, with a larger positive field indicating less overlap of classes.
Due to the fact that
The importance coefficient C of the attribute a relative to B is calculated according to the following formula,
C(a,B,D)＝γB∪a(D)-γB(D) (8)；
in the formula, gammaB(D) To determine the dependency of the attribute D on the conditional attribute B, γB∪a(D) Is the dependency of decision attribute D on conditional attribute B @. Below by γB(D) For example, γ is illustratedB(D) Method of calculating of gammaB∪a(D) The calculation method is similar. Gamma rayB(D) Calculated according to the following formula:
from the above analysis, it can be seen that the importance of the attribute a to the decision attribute D is the degree of reducing the dependency of the decision attribute D on the condition attribute B after the attribute a is deleted from the condition attribute set brute.
The embodiment obtains the condition attribute set B according to the following steps:
(S1) initializing the set, and setting the empty set
(S2) for any alE.g. A-B, calculating C (a)l，B，D)＝γB∪a(D)-γB(D) Definition of
(S3) selecting akSo that it satisfies C (a)k，B，D)＝max(C(al，B，D))；
(S4) if C (a)kB, D) > 0, then B ^ ak→ B, otherwise state akIndependent of the attribute in B, the importance coefficient is 0, let B → B. And (5) repeating the steps (S2) - (S4) after the judgment is finished until the importance coefficients of the residual attributes are all 0, and outputting the importance coefficient corresponding to the attribute element in the condition attribute set B, namely the importance coefficient C of the important spectral band in each spectral band of the Mel cepstrum corresponding to the workpieceiAnd the importance coefficients of the other spectral bands are set to zero. The step of Mel-frequency cepstral bands of acceptable workpieces marked by the importance coefficients in the frequency domain is shown in fig. 12.
According to the method, the importance coefficient corresponding to each spectral band of the Mel cepstrum of all the standard workpieces can be obtained, and the corresponding spectral band is marked by using the importance coefficient.
Summarizing Mel cepstrums marked by importance coefficients corresponding to all the miniature vibration motor standard workpieces with the same type of defects or qualified workpieces, averaging the spectral band energy of the same position of each Mel cepstrum of all the standard workpieces, and taking the average value as the corresponding spectral band energy setting value of the miniature vibration motor with the type of defects or the qualified miniature vibration motor.
Mel cepstrum bands marked by importance coefficients of all types of defective micro vibration motors and qualified micro vibration motors and energy setting values of the bands are constructed into a micro vibration motor standard library.
2. Defect detection for miniature vibration motor
In this embodiment, the diagnosis device provided in embodiment 1 is used to identify the defect of the micro vibration motor, and specifically includes the following steps:
(1) placing the micro vibration motor to be tested on an objective table, and compacting the micro vibration motor by using a damping compaction mechanism;
(2) starting the micro vibration motor to rotate;
(3) a sound sensor of the audio acquisition mechanism acquires audio signals, and the acquired audio signals are transmitted to a computer through a data acquisition unit;
(4) and processing the received audio signal to obtain a Mel cepstrum, and identifying the defects of the micro vibration motor according to the obtained Mel cepstrum.
Steps (1) - (3) are the same as steps (1) - (3) in the orthogonal assay and are not repeated here.
For step (4), the following steps are included:
(41) pre-emphasis and discrete Fast Fourier Transform (FFT) are carried out on the collected audio signals to obtain frequency spectrum information corresponding to the vibration signals;
(42) processing the frequency spectrum information obtained in the step (41) by adopting a triangular band-pass filter bank to obtain a Mel frequency spectrum;
(43) acquiring a Mel cepstrum based on the Mel spectrum;
(44) and calculating by adopting an attribute reduction algorithm based on forward greedy to obtain an importance coefficient corresponding to each spectral band of the Mel cepstrum, extracting the spectral bands corresponding to part of the importance coefficients, comparing the extracted partial spectral bands with the spectral band whole at the corresponding positions of the Mel cepstrum under various types of defects, and determining whether the micro vibration motor has defects and defect types.
Steps (41) - (43) are the same as steps (41) - (43) in the orthogonal experiment, and are not repeated here.
And (44) obtaining the importance coefficient corresponding to each spectral band of the Mel cepstrum of the workpiece to be measured according to the method.
According to the obtained importance coefficients corresponding to the various spectral bands of the Mel cepstrum of the workpiece to be detected, extracting a plurality of (five extracted in the embodiment) spectral bands corresponding to the importance coefficients from the obtained importance coefficients according to the sequence from large to small, and comparing the extracted spectral bands with the Mel cepstrum spectral bands marked by the importance coefficients under various types of defects in the standard library of the miniature vibration motor to determine whether the miniature vibration motor has defects and defect types. In this embodiment, the positions of the five extracted spectral bands can be determined according to the importance coefficient of the workpiece to be measured, then the energies of the five extracted spectral bands are respectively compared with the energy setting values of the spectral bands corresponding to various types of defects in the micro vibration motor standard library, and the defect type corresponding to the energy setting value with the energy deviation of the five spectral bands within 15% is taken as the defect type of the workpiece to be measured.
In addition, as can be seen from the foregoing analysis, the importance coefficient distributions of the micro vibration motors with different defect types are different, and therefore, according to the position distributions (i.e., importance coefficient distributions) of five spectral bands extracted from the Mel cepstrum of the workpiece to be detected, the defect type identical to the spectral band position distribution thereof can be directly found from the micro vibration motor standard library, however, in order to improve the defect identification accuracy, the energy of the extracted five spectral bands still needs to be compared with the energy setting value of the corresponding spectral band of the found micro defect type, and only when the energy deviation of the five spectral bands is within 15%, the defect type is taken as the defect type of the workpiece to be detected.
The invention simulates human ear frequency spectrum, carries out autocorrelation operation on the collected information to reduce mutation signals, screens main characteristic energy bands by a neighborhood analysis method, and finally obtains specific information in the running process of the micro vibration motor to identify the defects of the micro vibration motor.
When the micro vibration motor works, the micro vibration motor collides with the clamping groove of the objective table to generate forced vibration and drive surrounding air to vibrate at the same time, and the objective table and the rigid base are analyzed by ansys software, so that the formants are fixed, and whether the formants of each order are removed from the acquired audio signals can be determined according to specific scenes. According to the energy conservation theorem, the resonance peak of the vibration system formed by the objective table and the rigid base can be designed to be far away from the frequency band of the micro motor vibration, and the audio frequency transmits larger energy.
The invention firstly carries out orthogonal test when the miniature vibration motor with various defects works to obtain the importance coefficient of each frequency band of Mel cepstrum under various defects. And then optimizing the characteristic frequency band according to a neighborhood importance method on the basis of an orthogonal test, and marking the characteristic frequency band and the corresponding orthogonal test defect audio frequency to be finally used for judging the defect of the miniature vibration motor.
By adopting the method, the workpiece installation and test can be completed within 2s, so that the micro-vibration motor can be quickly and accurately identified under various working conditions, and the use comfort is improved.
It will be appreciated by those of ordinary skill in the art that the examples provided herein are intended to assist the reader in understanding the principles of the invention and are to be construed as being without limitation to such specifically recited examples and embodiments. Those skilled in the art can make various other specific changes and combinations based on the teachings of the present invention without departing from the spirit of the invention, and these changes and combinations are within the scope of the invention.
Claims (8)
1. A micro vibration motor defect diagnosis device based on audio analysis is characterized by comprising an object stage (1) for mounting a micro vibration motor to be tested, a pressing mechanism (2) for pressing and fixing the micro vibration motor on the object stage, an audio acquisition mechanism (3) positioned on one side of the micro vibration motor and a computer (4);
a notch (12) is designed on the objective table body (11), a clamping groove matched with the shape of the micro vibration motor is designed on one groove wall of the notch, a limiting structure for preventing the micro vibration motor from moving axially is designed on the clamping groove, and an electrode (14) corresponding to a power connection port of the micro vibration motor is designed on the other groove wall of the notch;
the pressing mechanism is a damping pressing mechanism and comprises a first support (21), a damping pestle component (22) arranged on the first support and a pressing component for pressing a pestle rod in the damping pestle component; the damping pestle component comprises a pestle rod (221), a damping spring (223) and a pressing block (224), the pestle rod is axially movably mounted on the first support, the pressing block is mounted at the lower end of the pestle rod, the damping spring is sleeved on the pestle rod, the lower end of the damping spring acts on the pressing block, the upper end of the damping spring acts on the pestle rod to serve as a limiting structure of a spring seat, and the pestle rod applies pressure to the pressing block through the damping spring; the pestle rod is of a combined structure and comprises a pestle rod body and a bolt (222) serving as an extension body of the pestle rod, and the bolt is connected with the pestle rod through a thread pair; the pressing block is provided with a cavity, the opening direction of the cavity is perpendicular to the pestle rod, the pressing block can be axially movably arranged on the bolt through the mounting hole on the wall of the cavity, and the damping spring is sleeved outside the bolt;
the audio acquisition mechanism (3) comprises a second bracket (31) and a sound sensor (32) which is arranged in the second bracket through flexible constraint, wherein the sound acquisition end of the sound sensor is aligned with the micro vibration motor;
the computer is connected with the sound sensor (32) and used for processing the received sound signal to obtain a Mel frequency spectrum inverse coefficient MFCC and identifying the defects of the micro vibration motor according to the obtained Mel frequency spectrum inverse coefficient MFCC.
2. The apparatus for diagnosing defect of micro vibration motor based on audio analysis as claimed in claim 1, wherein the pressing block pressing side is provided with a pressing terminal (225) made of plastic or rubber adapted to the structure of the upper end surface of the micro vibration motor.
3. The apparatus for diagnosing defects of a miniature vibration motor based on audio analysis as claimed in claim 1, wherein the position-limiting structure on the slot is constituted by a position-limiting plate (13) fixed on the stage body.
4. The apparatus for diagnosing defects of a miniature vibration motor based on audio analysis of claim 1, wherein said second frame is a cage frame, and said sound sensor is installed in said cage frame by means of a fixing structure formed by overlapping of rubber strips fixed to the brackets at both ends of said cage frame.
5. The apparatus for diagnosing defects of a miniature vibration motor based on audio analysis as claimed in any one of claims 1 to 4, wherein the sound collecting end of the sound sensor is located on the sound intensity envelope surface formed by centering on the center position of the bottom of the slot.
6. The apparatus for diagnosing defect of miniature vibration motor based on audio analysis as claimed in any one of claims 1 to 4, wherein the audio capturing mechanism is further designed with an annular cover (33) for preventing sound from diffuse reflection, and the annular cover is suspended at the front end of the sound sensor by a supporting rod (312) fixed on the second bracket.
7. A method for identifying a defect of a micro vibration motor using the diagnosis device of any one of claims 1 to 6, comprising the steps of:
(1) placing the micro vibration motor to be tested on an objective table, and compacting the micro vibration motor by using a damping compaction mechanism;
(2) starting the micro vibration motor to rotate;
(3) a sound sensor of the audio acquisition mechanism acquires audio signals and transmits the acquired audio signals to a computer through a data acquisition unit;
(4) and processing the received audio signal to obtain a Mel cepstrum, and identifying the defects of the micro vibration motor according to the obtained Mel cepstrum.
8. The method for identifying defects in a miniature vibration motor as set forth in claim 7, wherein the step (4) comprises the sub-steps of:
(41) pre-emphasis and discrete Fast Fourier Transform (FFT) are carried out on the collected audio signals to obtain frequency spectrum information corresponding to the audio signals;
(42) processing the frequency spectrum information obtained in the step (41) by adopting a triangular band-pass filter bank to obtain a Mel frequency spectrum;
(43) acquiring a Mel cepstrum based on the Mel spectrum;
(44) and calculating by adopting an attribute reduction algorithm based on forward greedy to obtain an importance coefficient corresponding to each spectral band of the Mel cepstrum, extracting the spectral bands corresponding to part of the importance coefficients, comparing the extracted partial spectral bands with the spectral band whole at the corresponding positions of the Mel cepstrum under various types of defects, and determining whether the micro vibration motor has defects and defect types.
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 CN110082107A (en) | 2019-08-02 |
| CN110082107B true 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) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN110602488B (en) * | 2019-09-18 | 2021-07-02 | 普联技术有限公司 | Day and night type camera device switching abnormity detection method and device and camera device |
| 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 |
| 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 |
| CN112212968B (en) * | 2020-09-15 | 2023-03-17 | 深圳传世生物医疗有限公司 | Vibration detection method and device for mixing cup grabbing hand |
| CN112945376B (en) * | 2021-03-24 | 2023-05-16 | 东风汽车集团股份有限公司 | Noise detection method, system and medium for adjusting motor of vehicle exterior rearview mirror |
| 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 (5)
| 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 |
| 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 |
| CN109443758A (en) * | 2018-12-29 | 2019-03-08 | 哈尔滨理工大学 | A kind of compound diagnostic device of rotating machinery |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
| CN108490349B (en) * | 2018-01-23 | 2020-08-18 | 浙江大学山东工业技术研究院 | Motor abnormal sound detection method based on Mel frequency cepstrum coefficient |
| 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 |
| CN109406842B (en) * | 2018-11-30 | 2024-01-02 | 东风电动车辆股份有限公司 | Motor test bench |
-
2019
- 2019-04-08 CN CN201910277843.9A patent/CN110082107B/en active Active
Patent Citations (5)
| 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 |
| 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 |
| CN109443758A (en) * | 2018-12-29 | 2019-03-08 | 哈尔滨理工大学 | A kind of compound diagnostic device of rotating machinery |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110082107A (en) | 2019-08-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110082107B (en) | Micro vibration motor defect diagnosis device and defect identification method based on audio analysis | |
| CN110472587B (en) | Micro vibration motor defect identification method and device based on CNN and sound time-frequency characteristic diagram | |
| CN105841797B (en) | A kind of Car window electric machine extraordinary noise detection method and device based on MFCC and SVM | |
| CN110954826B (en) | Step screw motor defect diagnosis device and defect identification method based on audio analysis | |
| US9909953B2 (en) | Method and apparatus for non-destructive detection of tire anomalies | |
| EP0655623B1 (en) | Relative resonant frequency shifts to detect cracks | |
| CN112201260B (en) | Transformer running state online detection method based on voiceprint recognition | |
| CN100350130C (en) | Method and apparatus for research and evaluation of foundation type | |
| CN108663115A (en) | A kind of car inside idle noise objective quantification evaluation method | |
| CN106568501B (en) | Near-field detection method for sound quality objective parameters of low-noise product | |
| CN108896878A (en) | A kind of detection method for local discharge based on ultrasound | |
| CN104266749A (en) | Device and method for offline detecting NVH (Noise Vibration and Harshness) of vehicle generator | |
| TW201204960A (en) | Diagnosis method of ball screw preload loss via Hilbert-Huang Transform and apparatus therefor | |
| CN106525981A (en) | Acoustic nondestructive detection experimental device for ripeness of thick-peel melons and fruits | |
| Dubey et al. | Pitch-Adaptive Front-end Feature for Hypernasality Detection. | |
| CN114242085A (en) | Fault diagnosis method and device for rotating equipment | |
| CN112420074A (en) | Method for diagnosing abnormal sound of motor of automobile rearview mirror | |
| CN111486547A (en) | Air conditioner diagnosis method, diagnosis device, air conditioner and computer readable storage medium | |
| CN106596145A (en) | Motorcycle shock absorber testing and control system | |
| CN110836721A (en) | Static frequency testing device and method for blades of blisk of aircraft engine | |
| CN207751640U (en) | A kind of sound signal collecting processing module with spectrum analysis function | |
| CN110530495A (en) | A kind of cutting polarization monitoring method based on vibration analysis | |
| CN115955645A (en) | System for testing performance of loudspeaker on line | |
| CN112461552A (en) | Detection method and system of electronic power-assisted brake system and readable storage medium | |
| CN219876129U (en) | TWS earphone in-ear detection function testing device |
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 |