CN107963239A - A kind of booster failure detection device and detection method based on audio - Google Patents
A kind of booster failure detection device and detection method based on audio Download PDFInfo
- Publication number
- CN107963239A CN107963239A CN201711139977.1A CN201711139977A CN107963239A CN 107963239 A CN107963239 A CN 107963239A CN 201711139977 A CN201711139977 A CN 201711139977A CN 107963239 A CN107963239 A CN 107963239A
- Authority
- CN
- China
- Prior art keywords
- audio
- signal
- rocket
- voice
- sound
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64G—COSMONAUTICS; VEHICLES OR EQUIPMENT THEREFOR
- B64G1/00—Cosmonautic vehicles
- B64G1/22—Parts of, or equipment specially adapted for fitting in or to, cosmonautic vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
- G01M99/005—Testing of complete machines, e.g. washing-machines or mobile phones
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The present invention relates to a kind of booster failure detection device and detection method based on audio, and the voice signal of sound transducer array received rocket product to be measured, signal acquisition process is carried out to voice signal；After carrying out wavelet transformation, Fourier transformation, characteristics extraction is carried out；Characteristic value during by characteristic value with being worked normally in voice bank is contrasted, if any feature value judges that there are failure for product to be measured on rocket beyond threshold value is limited；Sound property under characteristic value typical fault corresponding with voice bank is matched, if in the range of the sound property envelope in a certain typical fault, failure judgement type is the typical fault.The present invention carries out fault detect by voice signal, realizes the non-contact testing to rocket, reduces the test circuit inside rocket, avoids test circuit failure is brought on arrow the problem of, while alleviate the weight of rocket.
Description
Technical field
The present invention relates to a kind of booster failure detection device and detection method based on audio, belongs to fault detect neck
Domain.
Background technology
It is to ensure the basic means that rocket succeeds in sending up to carry out diagnosis to the system health status of carrier rocket by test,
In conventional measuring technology, in order to which diagnostic system health status generally requires to increase the measuring point of signal acquisition in systems, no matter
It is sensitive pressure or collection electric current, test access pair is a kind of " caecum design " in itself with system, that is, is inoperative after going up to the sky
State.Meanwhile this contact designs the failure of itself and system is also necessarily influenced generation.
One of feature when sound works as system, has certain identification, can reflect equipment to a certain extent
Working status.Since sound necessarily includes the equipment various multidate informations changed over time in the process of running, exist in addition
Under conditions of digital signal technique and fault signature extractive technique are more mature, the collection to rocket voice signal is with handling
Become a reality, while sound collection process is more convenient, quick, collecting device is simple and reliable, it is easy to accomplish, these conditions are all
Fault diagnosis is carried out using sound test to rocket to lay a good foundation.
As equipment is continuously increased on the development of rocketry and arrow, the failure of system is rapidly and accurately gathered and caught
Information, it has also become Rocket test and the important foundation of successful launch.A kind of energy release when sound works as equipment, sends
Audio signal necessarily implies that the work state information of system in itself.How the audio signal sent using product is tested,
The working status for determining product is this area technical problem urgently to be resolved hurrily.
The content of the invention
It is an object of the invention to overcome the deficiencies of the prior art and provide a kind of booster failure detection based on audio
Device and detection method, during Rocket test, by slave device voice signal extract feature and carry out data analysis can
To judge that equipment whether there is failure.
The object of the invention is achieved by following technical solution：
A kind of booster failure detection device based on audio, including sound transducer array, signal acquisition mould are provided
Block and signal processing module；
The voice signal of product to be measured on the sound transducer array received rocket, signal is carried out through signal acquisition module
Signal processing module is sent to after acquisition process；Signal processing module extracts the characteristic value of voice signal, carries out fault distinguishing.
Preferably, the characteristic value includes frequency, amplitude or phase.
Preferably, the method for signal processing module progress fault distinguishing is：During by being worked normally in characteristic value and voice bank
Characteristic value contrasted, if any feature value beyond limit threshold value, judge that there are failure for product to be measured on rocket.
Preferably, signal processing module is sentenced rocket product to be measured and is deposited after a failure, and characteristic value is corresponding with voice bank
Sound property under typical fault is matched, if in the range of the sound property envelope in a certain typical fault, is judged
Fault type is the typical fault.
Preferably, if without corresponding typical fault, after carrying out accident analysis positioning, by the knocking noise characteristic
And envelope scope adds voice bank.
Preferably, sound transducer array be circumferentially distributed in sensor stand it is interior, in, outer shroud, between adjacent ring
Sensor radial angle is inconsistent.
Preferably, sound transducer array is evenly distributed on the spiral support arm of sensor stand.
Preferably, signal processing module receives voice signal, carries out wavelet transformation and Fourier transformation, then carry out characteristic value
Extraction.
A kind of booster failure detection method based on audio is provided at the same time, is included the following steps：
(1) voice signal of sound transducer array received rocket product to be measured, carries out at signal acquisition voice signal
Reason；
(2) after carrying out wavelet transformation, Fourier transformation to the voice signal after acquisition process, characteristics extraction is carried out；
(3) characteristic value during by characteristic value with being worked normally in voice bank is contrasted, if any feature value is beyond limit
Determine threshold value, then judge that there are failure for product to be measured on rocket.
Preferably, product to be measured is deposited after a failure on rocket, by under characteristic value typical fault corresponding with voice bank
Sound property is matched, if in the range of the sound property envelope in a certain typical fault, failure judgement type is should
Typical fault.
Preferably, the voice bank includes the sound property and envelope model when all products to be measured work normally in rocket
Enclose, and sound property and envelope scope under product typical fault to be measured.
Preferably, if without corresponding typical fault, after carrying out accident analysis positioning, by the knocking noise characteristic
And envelope scope adds voice bank.
The present invention has the following advantages that compared with prior art：
(1) present invention carries out fault detect by voice signal, realizes the non-contact testing to rocket, reduces rocket
Internal test circuit, avoids test circuit failure is brought on arrow the problem of, while alleviates the weight of rocket.
(2) real-time of present invention progress fault detect is good, and improves the efficiency of fault location, due to voice signal not
Limited by measuring point quantity on arrow, improve test coverage.
(3) fault detection method of the invention, reduces test preparation, and it is multiple can to reduce test to a certain extent
Miscellaneous degree.
(4) present invention establishes more perfect sound characteristic storehouse, can effectively ensure the comprehensive of product testing.
Brief description of the drawings
Fig. 1 is test working-flow figure；
Fig. 2 is sound transducer distribution map of the present invention；
Fig. 3 is oscillogram before and after signal denoising of the present invention；
Fig. 4 is that the present invention is Short Time Fourier Transform waveform；
Fig. 5 is inventive engine solenoid valve sound characteristic curve；
Fig. 6 is servo control mechanism sound characteristic curve of the present invention.
Embodiment
Booster failure detecting system of the invention based on sound is used to gather the sound during Rocket test
Signal simultaneously handles signal, is recognized, and is compared by the resolution to audio database, confirms the working status of equipment on arrow,
Improve Rocket test spreadability.
Carrier rocket equipment under operating status, produces substantial amounts of voice signal.Detecting system is sensed by multiple sound
Device collects these voice signals.Voice signal is transferred to host computer and is handled after conditioning conversion and signal acquisition；On
Position machine extracts time and frequency domain characteristics during system work by corresponding signal processing algorithm, judge system work schedule and
Whether break down, display abort situation if there is failure, then by dependent failure location algorithm.Its idiographic flow
As shown in Figure 1.
First, the type selecting and layout of sound transducer
The multichannel collecting of voice signal seeks to the reservation original signal as much as possible under certain picking rate
Energy and information, i.e. choice accuracy are good, the small sound transducer of distortion and to a certain extent, eliminate outside noise to letter
Number collection influence.It is required that uniformity is preferable between sensor.
The 130F22 sound transducers that the sensor that the present invention selects in one embodiment produces for PCB companies of the U.S..
After confirming type selecting, it should also be taken into account that the influence that the distributing position of sound transducer obtains voice signal.Sound
The installation site of sensor directly affects it and exports the primary signal-to-noise ratio of signal, is an important factor for influencing system failure detection
One of.Due to the uncertainty being distributed by detection device internal fault, the sound source of acoustic emission wave is caused to be distributed, propagation medium is formed
Also there is stronger randomness with diffusion path length.But according to the acoustic emission wave mechanism of transmission, propagation path is shorter, acoustic emission wave
Energy attenuation with regard to smaller, it follows that appropriate sound transducer array distribution position can be effectively kept signal energy,
So as to more preferable stick signal feature.
The distribution of sound transducer will cover all voice signals as far as possible, so needing multiple sensor synergisms to adopt
Collection.Distribution for sensor is that single-sensor to be considered has the distance between equipment problem first, secondly to consider more
Range distribution problem between a sensor.For the former, it should ensure that sensor can cover voice signal as wide as possible, have
It is required that the decay that voice signal is as few as possible.
The sound transducer of the present invention is arranged on around the rocket body of rocket, referring to Fig. 2, the uniform cloth of sound transducer a1 to a6
The inner ring in sensor stand is put, sound transducer b1 to b6 is evenly arranged in the middle ring of sensor stand, sound transducer c1
It is evenly arranged in the outer shroud of sensor stand to c6, the sensor between each ring is distributed by certain geometry rule so that sensor
Array can it is sensitive go out sound directive property.
In one embodiment, sound transducer a1 to a6 radial angles corresponding with sound transducer c1 to c6 are consistent (no
Unanimously also can), respectively at sound transducer b1 to b6 into 30 degree of angles.
In another embodiment, sensor stand, including spiral support arm equally distributed vertically, each support arm
Place multiple sensors, the sensor on different support arms presses the circle distribution of certain radius.
Sensor stand is placed in the sound range of receiving of rocket product to be measured, is received the product and is sent during operation
Voice signal.
2nd, signal condition and collection
After signal is collected by sound transducer, itself has larger ambient noise and ambient noise,
And the output voltage amplitude of sound transducer may have follow-up signal capture card to match well, the pretreatment of signal
Purpose is sought to before signal transmission to host computer to carrying out certain processing, the base for making it be gathered in previous link to signal
On plinth, the influence of noise is further filtered out, to complete to provide collection signal rapid translating to branch for the gatherer process of digital signal
Hold, and then meet the further computing of host computer, the requirement of analysis and extraction.
Slave computer receives the voice signal that multiple sound transducers are sent, and voltage range is nursed one's health to the collection of analog input card
In the range of, the high speed acquisition of multi-channel sound data is completed, and be sent to host computer.
3rd, signal processing algorithm
Host computer carries out signal processing after receiving voice signal.The target data collected from sonic transducer, by signal
The noise in signal is greatly reduced after pretreatment, improves signal-to-noise ratio.But the signal data amount obtained at this time is still very big,
It is infeasible directly to carry out Classification and Identification to these data.For Classification and Identification is effectively performed, data must just be become
Change, obtain the target signature that can reflect classification essence.
1) wavelet transformation
Because Rocket test working environment is complicated, detecting system is when collected sound signal, it is difficult to ensure that not
Noise signal is mixed into, if these noise removes cannot can largely be influenced signal characteristic abstraction letter by these signals
The quality of breath, so as to influence breakdown judge result.Therefore, it is that have very much must that denoising is carried out to the voice signal that collects
Want.
The analysis on quick time-domain and frequency-domain is carried out to it for the signal collected, is the work of next step
State-detection provides analysis foundation with fault location detection.Just because of this, the means by wavelet transformation will be just needed first
Carry out the denoising to signal.
Noise-eliminating method can be attributed to three classes:De-noising is carried out using wavelet filtering characteristic, using wavelet modulus maxima
Method carry out de-noising, de-noising carried out by the method for threshold process.
2) Short Time Fourier Analysis
Short Time Fourier Transform is widely used in Non-stationary Signal Analysis, it is on the basis of Fourier transformation
On, non-stationary signal is regarded as and is made of a series of short-term stationarity signals, short-time characteristic is realized by adding window, and join by translating
Number covers whole time domain.I.e. using the product of window function and non-stationary signal to be analyzed, realize the windowing near window with putting down
Move, then carry out Fourier transformation.
The temporal signatures and frequency domain character that signal shows at the same time can be made using Short Time Fourier Transform, are conducive into one
Step processing draws effective time-frequency synthesis identification feature., can be according to system after carrying out denoising for detection signal
Timing command signals carry out framing to obtained signal, carry out Short Time Fourier Analysis to it respectively, can be in time domain, frequency
Different features, including frequency, amplitude, phase etc. are extracted on domain respectively.
3) fault location
Under sound property and envelope scope, and product typical fault when being worked normally by gathering all test products
Sound property and envelope scope, establish voice bank.
The characteristic value of actual measurement is contrasted with the characteristic value in voice bank during corresponding normal work, if any feature
Value then judges that there are failure for test product beyond threshold value is limited.
If it is determined that product is there are failure, then by the sound under the characteristic value of actual measurement typical fault corresponding with voice bank
Characteristic is matched, if for a certain typical fault sound property include in the range of, failure judgement type is the typical case
Failure.
If without corresponding typical fault, show new fault type occurred, will after carrying out accident analysis positioning
The knocking noise characteristic and envelope scope add voice bank.
The detection method of several typical products：
1st, engine electromagnetic valve
As shown in figure 5, by the processing to electromagnetic valve work sound, its frequecy characteristic value is obtained, passes through frequency spectrum
Transformation period can obtain the time of origin (correct times of corresponding electromagnetism valve events) of frequency spectrum, special with frequency in voice bank
Property spectral line contrasted, judge whether spectral line time of origin corresponds to, if not in threshold range, show the solenoid valve exist therefore
Barrier.
Further be compared with typical fault frequency characteristic, judgement be fifth wheel clamping stagnation, supply current deficiency or
Supply gas pressure deficiency.
2nd, servo control mechanism
As shown in fig. 6, by the processing to servo operational sound, its frequecy characteristic value is obtained, with frequency in voice bank
Characteristic spectral line is contrasted, and judges whether spectral line is correct, shows the servo control mechanism if incorrect there are failure；Also judge at the same time
Spectral line switching time whether the theoretical work time of corresponding product, if inconsistent with theoretical value, show that the servo control mechanism is deposited
In failure.
Further it is compared if there is failure with typical fault frequency characteristic, judges the position broken down.
By gathering the sound that equipment is sent in carrier rocket test process, equipment health status is carried out in real time or afterwards
Fault diagnosis and analysis, are provided simultaneously with certain fault location function.It can gather and record the voice signal in test process；
Voice signal can be positioned by sound transducer array different measuring points position；Establish test audio database；Can
The sound collected is recognized and compared with typical sound.
Comparison of wave shape is as shown in Figure 3 before and after de-noising.Before wherein left hand view is de-noising, right part of flg is after de-noising, it can be seen that
Corresponding noise signal amplitude substantially reduces, and characteristic signal becomes readily apparent from.
For the time and frequency domain characteristics extraction between coherent signal, such as the normal feature between signal under malfunction of equipment
Difference, as shown in Figure 4.The sound property (amplitude, frequency, phase) and normal operating conditions of malfunction as seen from Figure 4
Sound property there are larger difference, by setting respective threshold, you can judge to whether there is failure.
The above, is only the optimal embodiment of the present invention, but protection scope of the present invention is not limited thereto,
Any one skilled in the art the invention discloses technical scope in, the change or replacement that can readily occur in,
It should be covered by the protection scope of the present invention.
The content not being described in detail in description of the invention belongs to the known technology of professional and technical personnel in the field.
Claims (12)
1. a kind of booster failure detection device based on audio, it is characterised in that including sound transducer array, signal is adopted
Collect module and signal processing module；
The voice signal of product to be measured on the sound transducer array received rocket, signal acquisition is carried out through signal acquisition module
Signal processing module is sent to after processing；Signal processing module extracts the characteristic value of voice signal, carries out fault distinguishing.
2. the booster failure detection device based on audio as claimed in claim 1, it is characterised in that the characteristic value bag
Include frequency, amplitude or phase.
3. the booster failure detection device based on audio as claimed in claim 2, it is characterised in that signal processing module
Carry out fault distinguishing method be：Characteristic value during by characteristic value with being worked normally in voice bank is contrasted, if any spy
Value indicative then judges that there are failure for product to be measured on rocket beyond threshold value is limited.
4. the booster failure detection device based on audio as claimed in claim 3, it is characterised in that signal processing module
Sentence rocket product to be measured to deposit after a failure, by the sound property progress under characteristic value typical fault corresponding with voice bank
Match somebody with somebody, if in the range of the sound property envelope in a certain typical fault, failure judgement type is the typical fault.
5. the booster failure detection device based on audio as claimed in claim 3, it is characterised in that if do not corresponded to
Typical fault, then after carrying out accident analysis positioning, the knocking noise characteristic and envelope scope are added into voice bank.
6. the booster failure detection device based on audio as claimed in claim 3, it is characterised in that sound transducer battle array
Row be circumferentially distributed in sensor stand it is interior, in, outer shroud, the sensor radial angle between adjacent ring is inconsistent.
7. the booster failure detection device based on audio as claimed in claim 3, it is characterised in that sound transducer battle array
Row are evenly distributed on the spiral support arm of sensor stand.
8. the booster failure detection device based on audio as claimed in claim 1 or 2, it is characterised in that signal processing
Module receives voice signal, carries out wavelet transformation and Fourier transformation, then carry out characteristics extraction.
9. a kind of booster failure detection method based on audio, it is characterised in that include the following steps：
(1) voice signal of sound transducer array received rocket product to be measured, signal acquisition process is carried out to voice signal；
(2) after carrying out wavelet transformation, Fourier transformation to the voice signal after acquisition process, characteristics extraction is carried out；
(3) characteristic value during by characteristic value with being worked normally in voice bank is contrasted, if any feature value is beyond restriction threshold
Value, then judge that there are failure for product to be measured on rocket.
10. the booster failure detection method based on audio as claimed in claim 9, it is characterised in that：Production to be measured on rocket
Product are deposited after a failure, the sound property under characteristic value typical fault corresponding with voice bank are matched, if being in certain
In the range of the sound property envelope of one typical fault, then failure judgement type is the typical fault.
11. the booster failure detection method based on audio as claimed in claim 10, it is characterised in that：The voice bank bag
Include sound property when all products to be measured work normally in rocket and the sound under envelope scope, and product typical fault to be measured
Characteristic and envelope scope.
12. the booster failure detection method based on audio as claimed in claim 10, it is characterised in that：If do not correspond to
Typical fault, then after carrying out accident analysis positioning, the knocking noise characteristic and envelope scope are added into voice bank.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711139977.1A CN107963239B (en) | 2017-11-16 | 2017-11-16 | Carrier rocket fault detection device and method based on audio |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711139977.1A CN107963239B (en) | 2017-11-16 | 2017-11-16 | Carrier rocket fault detection device and method based on audio |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107963239A true CN107963239A (en) | 2018-04-27 |
| CN107963239B CN107963239B (en) | 2020-10-23 |
Family
ID=62001069
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711139977.1A Active CN107963239B (en) | 2017-11-16 | 2017-11-16 | Carrier rocket fault detection device and method based on audio |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107963239B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109019349A (en) * | 2018-06-19 | 2018-12-18 | 上海振华重工(集团)股份有限公司 | fault detection method, detector, computer storage medium and crane |
| CN109582692A (en) * | 2018-11-15 | 2019-04-05 | 北京宇航系统工程研究所 | A kind of carrier rocket test data interpretation method and system based on formalized description |
| CN109991003A (en) * | 2019-03-21 | 2019-07-09 | 北京宇航系统工程研究所 | Engine state monitor and diagnostic system and implementation method based on acoustic monitoring |
| CN110490134A (en) * | 2019-08-20 | 2019-11-22 | 四川九洲电器集团有限责任公司 | Signal recognition method, equipment and storage medium |
| CN110864801A (en) * | 2019-10-30 | 2020-03-06 | 国网福建省电力有限公司检修分公司 | Transformer noise and vibration on-line monitoring and fault analysis system |
| CN111684213A (en) * | 2018-10-22 | 2020-09-18 | 深圳配天智能技术研究院有限公司 | Robot fault diagnosis method, system and storage device |
| CN111810317A (en) * | 2020-08-11 | 2020-10-23 | 安徽九州云箭航天技术有限公司 | Rocket engine frame |
| CN112363020A (en) * | 2020-11-11 | 2021-02-12 | 国网江苏省电力有限公司盐城供电分公司 | Power transmission and distribution line sound abnormity detection method based on different weather |
| CN113033690A (en) * | 2021-04-07 | 2021-06-25 | 东北大学 | Carrier roller fault detection method for double-projection neighborhood embedding based on sound |
| CN113670625A (en) * | 2021-08-23 | 2021-11-19 | 一汽解放大连柴油机有限公司 | Engine test bench |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003214944A (en) * | 2002-01-29 | 2003-07-30 | Daihatsu Motor Co Ltd | Failure inspection device depending on abnormal noise |
| CN202048980U (en) * | 2011-05-03 | 2011-11-23 | 北京中矿信电科技股份有限公司 | Audio-based mechanical failure detection device |
| CN102788671A (en) * | 2012-07-26 | 2012-11-21 | 北京卫星环境工程研究所 | Structure failure mode diagnosing method on basis of sound spectrum of spacecraft vibration test |
| CN102829991A (en) * | 2012-09-21 | 2012-12-19 | 三一重机有限公司 | Fault detection system, fault detection method and module |
| CN105371895A (en) * | 2015-11-25 | 2016-03-02 | 中山市厚源电子科技有限公司 | Sound alarm system used for space shuttle based on internet of things |
| CN105527104A (en) * | 2016-02-14 | 2016-04-27 | 成都柏森松传感技术有限公司 | Bearing running-in abnormal sound detection system |
| CN106934421A (en) * | 2017-03-16 | 2017-07-07 | 山东大学 | Converting station electric power transformer fault detecting system and detection method based on 2DPCA and SVM |
-
2017
- 2017-11-16 CN CN201711139977.1A patent/CN107963239B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003214944A (en) * | 2002-01-29 | 2003-07-30 | Daihatsu Motor Co Ltd | Failure inspection device depending on abnormal noise |
| CN202048980U (en) * | 2011-05-03 | 2011-11-23 | 北京中矿信电科技股份有限公司 | Audio-based mechanical failure detection device |
| CN102788671A (en) * | 2012-07-26 | 2012-11-21 | 北京卫星环境工程研究所 | Structure failure mode diagnosing method on basis of sound spectrum of spacecraft vibration test |
| CN102829991A (en) * | 2012-09-21 | 2012-12-19 | 三一重机有限公司 | Fault detection system, fault detection method and module |
| CN105371895A (en) * | 2015-11-25 | 2016-03-02 | 中山市厚源电子科技有限公司 | Sound alarm system used for space shuttle based on internet of things |
| CN105527104A (en) * | 2016-02-14 | 2016-04-27 | 成都柏森松传感技术有限公司 | Bearing running-in abnormal sound detection system |
| CN106934421A (en) * | 2017-03-16 | 2017-07-07 | 山东大学 | Converting station electric power transformer fault detecting system and detection method based on 2DPCA and SVM |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109019349A (en) * | 2018-06-19 | 2018-12-18 | 上海振华重工(集团)股份有限公司 | fault detection method, detector, computer storage medium and crane |
| CN111684213A (en) * | 2018-10-22 | 2020-09-18 | 深圳配天智能技术研究院有限公司 | Robot fault diagnosis method, system and storage device |
| CN109582692A (en) * | 2018-11-15 | 2019-04-05 | 北京宇航系统工程研究所 | A kind of carrier rocket test data interpretation method and system based on formalized description |
| CN109991003B (en) * | 2019-03-21 | 2021-06-11 | 北京宇航系统工程研究所 | Engine state monitoring and diagnosing system based on acoustic monitoring and implementation method |
| CN109991003A (en) * | 2019-03-21 | 2019-07-09 | 北京宇航系统工程研究所 | Engine state monitor and diagnostic system and implementation method based on acoustic monitoring |
| CN110490134A (en) * | 2019-08-20 | 2019-11-22 | 四川九洲电器集团有限责任公司 | Signal recognition method, equipment and storage medium |
| CN110864801A (en) * | 2019-10-30 | 2020-03-06 | 国网福建省电力有限公司检修分公司 | Transformer noise and vibration on-line monitoring and fault analysis system |
| CN111810317A (en) * | 2020-08-11 | 2020-10-23 | 安徽九州云箭航天技术有限公司 | Rocket engine frame |
| CN112363020A (en) * | 2020-11-11 | 2021-02-12 | 国网江苏省电力有限公司盐城供电分公司 | Power transmission and distribution line sound abnormity detection method based on different weather |
| CN113033690A (en) * | 2021-04-07 | 2021-06-25 | 东北大学 | Carrier roller fault detection method for double-projection neighborhood embedding based on sound |
| WO2022213512A1 (en) * | 2021-04-07 | 2022-10-13 | 东北大学 | Sound-based dual-projection neighborhood preserving embedded carrying idler fault detection method |
| CN113033690B (en) * | 2021-04-07 | 2024-04-02 | 东北大学 | Carrier roller fault detection method for double projection neighborhood keeping embedding based on sound |
| CN113670625A (en) * | 2021-08-23 | 2021-11-19 | 一汽解放大连柴油机有限公司 | Engine test bench |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107963239B (en) | 2020-10-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107963239A (en) | A kind of booster failure detection device and detection method based on audio | |
| CN107013449B (en) | The method and system of voice signal identification compressor fault based on deep learning | |
| CN101865789B (en) | Fault detecting device of near field acoustic holography sound image mode identification and detecting method thereof | |
| CN106447040B (en) | Mechanical equipment health state evaluation method based on Heterogeneous Multi-Sensor Data fusion | |
| Zhang et al. | Towards heart sound classification without segmentation using convolutional neural network | |
| CN110850244B (en) | Local discharge defect time domain map diagnosis method, system and medium based on deep learning | |
| CN109870282B (en) | Blade vibration feature identification method and system based on compressed sensing | |
| CN102435922A (en) | Acoustic-electric combined detection system and positioning method for GIS (Gas Insulated Switchgear) local discharge | |
| CN108008287A (en) | Track circuit failure monitoring platform and its monitoring method based on frequency-shift signaling | |
| Sheng et al. | Applications in bearing fault diagnosis of an improved Kurtogram algorithm based on flexible frequency slice wavelet transform filter bank | |
| CN106096242A (en) | A kind of based on improving the Pressure Fluctuation in Draft Tube integrated evaluating method that EMD decomposes | |
| CN103267652B (en) | Intelligent online diagnosis method for early failures of equipment | |
| CN107355686B (en) | A kind of detection method of drain line blockage failure | |
| CN112858845A (en) | Partial discharge diagnosis method for gas insulated switchgear | |
| CN106404148A (en) | Portable micro vibration testing device and method | |
| CN106323664A (en) | Vibration testing and diagnosing method and device of air conditioning unit and air conditioning unit | |
| CN113283310A (en) | System and method for detecting health state of power equipment based on voiceprint features | |
| CN111898644A (en) | Intelligent identification method for health state of aerospace liquid engine under fault-free sample | |
| CN103821749B (en) | On-line diagnosis method of stall and surge of axial fan | |
| CN109916612A (en) | GIS mechanical breakdown electrification detection system based on acoustics imaging | |
| Emamian et al. | Robust clustering of acoustic emission signals using neural networks and signal subspace projections | |
| CN211478951U (en) | Fault diagnosis device and fault diagnosis system | |
| CN102508120A (en) | Method for realizing weak fault diagnosis and location of airplane wire by utilizing local mean decomposition | |
| CN105928666A (en) | Leakage acoustic characteristic extraction method based on Hilbert-Huang transform and blind source separation | |
| CN112975574B (en) | Surface quality on-line detection system for aluminum alloy thin-wall part in milling process |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |