CN109917287A - Decelerating motor product examine method based on empirical mode decomposition and octave spectrum analysis - Google Patents
Decelerating motor product examine method based on empirical mode decomposition and octave spectrum analysis Download PDFInfo
- Publication number
- CN109917287A CN109917287A CN201910214209.0A CN201910214209A CN109917287A CN 109917287 A CN109917287 A CN 109917287A CN 201910214209 A CN201910214209 A CN 201910214209A CN 109917287 A CN109917287 A CN 109917287A
- Authority
- CN
- China
- Prior art keywords
- motor
- spectrum analysis
- decelerating motor
- vibration signal
- ocsvm
- 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
Landscapes
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The decelerating motor product examine method based on empirical mode decomposition and octave spectrum analysis that the invention discloses a kind of switchs to digital voltage signal and is passed in PC machine comprising steps of 1) extracting decelerating motor vibration signal to be measured by hardware device；2) PC machine obtains the vibration signal of motor, is converted into sextuple data characteristics by EMD analysis and CPB spectrum analysis；3) the sextuple data characteristics is inputted, by the OCSVM disaggregated model for selecting corresponding motor model training to finish, identification obtains the classification information of final motor superiority and inferiority.By the present invention in that judging whether the quality of the source motor of the signal is qualified with the EMD and CPB vibration signal characteristics obtained and with one-class support vector machine, solves the problems such as huge labour cost brought by the widely used artificial detection method in the field at present and detection tired out, while guaranteeing accurate rate, the efficiency to decelerating motor quality identification is improved.
Description
Technical field
The present invention relates to the fields of technology for mechanical fault diagnosis and analysis of vibration signal, and in particular to one kind is based on Empirical Mode
State is decomposed and the decelerating motor product examine method of octave spectrum analysis, obtains improved motor oscillating signal by using EMD and CPB
Feature and OCSVM model solve the problems, such as decelerating motor Quality Detection.
Background technique
With the mankind science and technology it is increasingly developed, automation will become 21 century production development one of theme.And conduct
The motor that mechanical energy can be converted electrical energy into always is the indispensable core component of each field automated system.Wherein,
In low speed, the occasion of big torque, toothed gearing electric motor is always most economical, practical preferred option.
Gear reduction box is exactly installed on the output shaft of motor by so-called toothed gearing electric motor, passes through subtracting for gear
Speed by output revolving speed by being reduced to low speed at a high speed, while improving output torque.Due to the characteristic, such micromotor product is extensive
For automatic production line, in the precision instruments such as Medical Devices and intelligent industrial, reading intelligent agriculture, smart home, intelligence machine
In the output of the relevant devices intelligent power such as people.Under the market competitive pressure of such fierceness of such product, how extensive
The quality for guaranteeing product while production, will can become toothed gearing electric motor enterprise create the weight of considerable economic well-being of workers and staff
Want one of problem.
It, will also be to making an uproar other than to several rigid index revolving speeds, torque, temperature rise etc. at present to decelerating motor Quality Detection
Sound and gear quality are identified.And at home in miniature gears decelerating motor factory, part detection is generally by artificial
Mode identified, is that the noise that perceives the vibration of empty load of motor by both hands and listen to empty load of motor with ear is comprehensive to carry out
Close the superiority and inferiority for determining product.This backward ineffective technique not only greatly increases the labour cost in production, but also due to this heavy
Renaturation labour can make worker error in judgement tired out occur, march toward market so as to cause substandard products, prestige and subsequent economy to enterprise
Bring the loss that can not be retrieved.
The present invention is directed to the problems such as decelerating motor Quality Detection efficiency and precision, and analysis of vibration signal method is incorporated it
In.By combining EMD and CPB analysis method to obtain the vibration signal characteristics of motor, then pass through the vibration signal characteristics of acquisition
Data train OCSVM model (one-class support vector machine model), realize decelerating motor Quality Detection task.Guaranteeing essence
While true rate, the efficiency to decelerating motor quality identification is improved.
Summary of the invention
The present invention is that the motor oscillating signal characteristic that will be improved is applied in decelerating motor Quality Detection, and use is improved
The OCSVM model of feature training can significantly improve the precision and efficiency of motor product examine, reduce enterprise human cost and
The problems such as precision efficiency.
The present invention adopts the following technical scheme that realization:
A kind of decelerating motor product examine method based on empirical mode decomposition and octave spectrum analysis, comprising steps of
1) decelerating motor vibration signal to be measured is extracted by hardware device, switchs to digital voltage signal and is passed in PC machine；
2) PC machine obtains the vibration signal of motor, is converted into sextuple data characteristics by EMD analysis and CPB spectrum analysis；
3) the sextuple data characteristics is inputted, by the OCSVM disaggregated model for selecting corresponding motor model training to finish, is known
The classification information of final motor superiority and inferiority is not obtained.
Further, in step 1), the extraction decelerating motor vibration signal to be measured is specifically included: being obtained by hardware device
Obtain the time domain vibration signal of continuously five groups of one second decelerating motors to be measured.
Further, in step 2), the EMD analysis is specifically included: obtaining IMF points in the one second time of vibration signal
Amount, and using its first three rank IMF energy as the preceding three-dimensional of the sextuple data characteristics.
Further, in step 2), the CPB spectrum analysis is specifically included: being advised according to actual measurement motor and third-octave
Then, 26 spectrum regions that time domain vibration signal is marked off by FFT, by PCA dimension reduction method by the energy feature in 26 regions
It is down to three-dimensional, the rear three-dimensional as the sextuple data characteristics.
Further, the frequency range in 26 spectrums region is 20Hz~3150Hz.
Further, in step 3), the OCSVM model is based on following quadratic programming problem:
s.t.ΦT(xi)·ω≥ρ-ξi, ξi≥0
Wherein ω and ρ is the higher-dimension parameter of hyperplane in OCSVM model；N is the quantity of trained sample；V ∈ (0,1) is used to
Control supporting vector proportion in training sample；ξiIt is non-zero slack variable, for compensating objective function；ΦT() is special
Mapping function is levied, it can be by i-th of trained sample xiIt is transformed into hyperplane space.
Further, in step 3), the training process of the OCSVM disaggregated model includes:
According to the artificial judgment method of vestibule, corresponding several platforms of model motor best in quality are collected；
By the hardware device, several groups 5s motor oscillating signal is acquired to every sample motor；
Each motor oscillating signal is divided into training set, test set, verifying collection according to 6:2:2 ratio, and 5s motor is shaken
Dynamic signal is divided into 5 parts of 1s motor oscillating signals in order；
PC machine obtains the vibration signal of motor, is converted into sextuple data characteristics by EMD analysis and CPB spectrum analysis；
The OCSVM disaggregated model that the sextuple data characteristics input is established is trained the OCSVM after being trained points
Class model.
Further, described to identify that the classification information for obtaining final motor superiority and inferiority specifically includes: by five in step 3)
Second motor signal divide and passes through the decision function of the OCSVM model to be judged respectively, is sentenced if the excellent result of appearance is more
Break as excellent motor, is otherwise determined as bad motor.
Compared with prior art, the motor oscillating signal characteristic improved is applied to decelerating motor Quality Detection by the present invention
In, it is intended to it solves the huge labour cost brought by the widely used artificial detection method in the field at present and detection tired out etc. and asks
Topic can significantly improve the precision and efficiency of motor product examine using the OCSVM model of improved feature training, reduce enterprise
The problems such as human cost and precision efficiency.
Detailed description of the invention
Fig. 1 is the decelerating motor product examine system structure diagram based on empirical mode decomposition and octave spectrum analysis.
Fig. 2 is the vibration signal IMF component extraction flow chart analyzed based on EMD.
Fig. 3 is the identification process of the toothed gearing electric motor product examine system based on empirical mode decomposition and octave spectrum analysis
Figure.
Specific embodiment
The present invention is described further in the following with reference to the drawings and specific embodiments.
Attached drawing 1 is the decelerating motor product examine system structure diagram based on empirical mode decomposition and octave spectrum analysis, is led to
MOTECH digital control type linear direct current regulated power supply LPS-305 is crossed to power to minisize dc toothed gearing electric motor pressure stabilizing to be detected, and
It is contacted with CT1050LC acceleration transducer surface rigidity by metal steel disc.It is suitable by CT5201 single-channel constant current at this time
Orchestration is powered to acceleration transducer, and transmits amplification voltage signal to MCC1608G usb multifunctional data acquisition card DAQ's
Simulation input port, analog signal can be converted to digital signal and is passed in PC machine by data collector, to carry out model instruction
Experienced and product examine judgement.
As shown in figure 3, a kind of decelerating motor product examine method based on empirical mode decomposition and octave spectrum analysis, including step
It is rapid:
1) decelerating motor vibration signal to be measured is extracted by hardware device, switchs to digital voltage signal and is passed in PC machine；
2) PC machine obtains the vibration signal of motor, is converted into sextuple data characteristics by EMD analysis and CPB spectrum analysis；
3) the sextuple data characteristics is inputted, by the OCSVM disaggregated model for selecting corresponding motor model training to finish, is known
The classification information of final motor superiority and inferiority is not obtained.
Specifically, the extraction decelerating motor vibration signal to be measured specifically includes: being obtained by hardware device in step 1)
Obtain the time domain vibration signal of continuously five groups of one second decelerating motors to be measured.
Specifically, the EMD analysis specifically includes: obtaining the IMF in the one second time of vibration signal in step 2)
(Intrinsic Mode Function, natural mode of vibration component) component and using its first three rank IMF energy as the sextuple data
The preceding three-dimensional of feature.Motor oscillating signal belongs to non-stationary signal, can decompose sample motor oscillating signal by EMD method,
To obtain the array natural mode of vibration component of the signal, specific formula is as follows:
Wherein, imfi(t) it is i-th of IMF that signal x (t) is decomposed by EMD；rn(t) divide to decomposite IMF every time
Signal residual components after amount, extraction process is as shown in Fig. 2, specifically include step:
1. initializing r0(t)=x (t), i=1.
2. extracting signal x (t) i-th of IMF component, riIt (t) is residual components, hjIt (t) is decomposition modal components, mj(t) it is
The sequence of upper and lower envelope mean value composition, wherein j represents residual components ri(t) cycle-index in the cycle.Specific steps
It is: by residual components ri(t) function renamed as decomposes modal components hj(t), and to component hj(t) Min-max is calculated, it is right
Each extreme value uses cubic spline interpolation (using three respectively) respectively, obtains envelope up and down and mean value is taken to obtain sequence mj
(t), and before meeting stop condition, sequence m is deleted by not stoppingj(t) it is iterated the final decomposition mode h of acquisitionJ(t), this
When obtain i-th of IMF component imf of signal x (t)i(t)=hj(t).Wherein stop condition is by standard deviation SdIt determines:
Wherein, SdStandard deviation and S between two continuous processing resultsdRange takes 0.1 to 0.3, when obtaining SdDo not exist
In setting range, then circulation is exited, obtains signal x (t) i-th of IMF component.
3. calculating current residual component ri(t)=ri-1(t)-imfi(t), if residual components ri(t) still contain 2 or more
Extreme value, then obtain the IMF component of i+1, return to step 2., otherwise terminate, obtain the final a series of of vibration signal
IMF component.
4. calculating the energy IMF of all IMF components of vibration signali(t):
IMFi(t)=imfi 2(t)。
5. first three rank IMF component is taken to form three-dimensional feature A=[IMF1IMF2IMF3]。
Specifically, the CPB spectrum analysis specifically includes in step 2): being advised according to actual measurement motor and third-octave
Then, 26 spectrum regions that time domain vibration signal is marked off by FFT (Fast Fourier Transformation), pass through PCA
The energy feature in 26 regions is down to three-dimensional by dimension reduction method, as the rear three-dimensional of the sextuple data characteristics, specifically includes step
It is rapid:
Step 1: the vibration signal for treating measured motor carries out Fast Fourier Transform (FFT) (Fast Fourier
Transformation, FFT), obtain the power spectrum of vibration signal.
Step 2: using octave analysis, analyzes used here as third-octave, i.e., in the frequency range pair of third-octave
Power spectrum chart is divided, and forms 26 frequency bands in 20Hz to 3150Hz, and calculate each centre frequency f0Neighbouring third-octave
ENERGY Ex(f0):
Wherein X (k) is the vibration signal of discrete form, and N is sequence length, and T is sample frequency fsInverse, fl, nlIt is divided into
Centre frequency f0The lower frequency limit and starting point of neighbouring third-octave, fh, nhIt is divided into centre frequency f0Nearby third-octave is upper
Frequency limit rate and end point.
Step 3: the third-octave energy datum matrix of motor to be measured sampling is carried out
Then PCA dimensionality reduction, the i.e. covariance matrix of calculating matrix carry out singular value decomposition to matrix and are dropped from big to small
Sequence characteristics value spectrum, then linear transformation obtains the characteristic of dimensionality reduction, and characteristic dimension takes three.
Specifically, the OCSVM model is based on following quadratic programming problem in step 3):
s.t.ΦT(xi)·ω≥ρ-ξi,ξi≥0
Wherein ω and ρ is the higher-dimension parameter of hyperplane in OCSVM model；N is the quantity of trained sample；V ∈ (0,1) is used to
Control supporting vector proportion in training sample；ξiIt is non-zero slack variable, for compensating objective function；ΦT() is special
Mapping function is levied, it can be by i-th of trained sample xiIt is transformed into hyperplane space.
Specifically, in step 3), the training process of the OCSVM disaggregated model includes:
According to the artificial judgment method of vestibule, corresponding model 100 platforms of motor best in quality are collected；
By the hardware device, 20 groups of 5s motor oscillating signals are acquired to every sample motor；
Each motor oscillating signal is divided into training set, test set, verifying collection according to 6:2:2 ratio, and 5s motor is shaken
Dynamic signal is divided into 5 parts of 1s motor oscillating signals in order；
PC machine obtains the vibration signal of motor, is converted into sextuple data characteristics by EMD analysis and CPB spectrum analysis, i.e., will
The feature that EMD analysis and CPB spectrum analysis obtain, which combines, makes each sample data obtain only one 6 DOF characteristic.
The OCSVM disaggregated model that the sextuple data characteristics input is established is exercised supervision learning training, after being trained
OCSVM disaggregated model, with supporting vector be unfolded decision function may be expressed as:
Wherein k (xi, x) and it is gaussian kernel function, xiFor supporting vector, ρ is that decision function exports threshold value, can be by any edge
Vector x is calculated, wherein coefficient aiIt is acquired by SMO algorithm.
It, can be to unknown toothed gearing electric motor after obtaining the OCSVM model that the training of particular gear decelerating motor is completed
It is identified, it is therefore, described to identify that the classification information for obtaining final motor superiority and inferiority specifically includes: by five seconds in step 3)
Motor signal is divided and passes through the decision function of the OCSVM model to be judged respectively, if occurring judging if excellent result is more
For excellent motor, otherwise it is determined as bad motor.It is specific to be led as shown in figure 3, working as motor oscillating signal by hardware device described in Fig. 1
Enter to PC machine, 5 seconds vibration signals are then become to by EMD analysis and CPB spectrum analysis the sextuple degree of continuous 5 groups of 1s
According to feature and the OCSVM disaggregated model by selecting corresponding motor model training to finish, judged by the decision function of OCSVM each
Group recognition result then judges motor product if it is determined that motor is that excellent quantity num is greater than 2.5 with majority rule
Matter be it is excellent, if it is determined that motor be excellent quantity num less than 2.5, then judge that motor quality is bad.
The present invention can accurately extract decelerating motor vibration signal, in conjunction with the depth model based on convolutional network of foundation
Library judges decelerating motor superiority and inferiority situation, and then reduces the workload manually judged and improve electric machines test precision, to improve electricity
Machine production efficiency.
The above, only the invention patent preferred embodiment, but the scope of protection of the patent of the present invention is not limited to
In this, anyone skilled in the art is in the range disclosed in the invention patent, according to the present invention patent
Technical solution and its patent of invention design are subject to equivalent substitution or change, belong to the scope of protection of the patent of the present invention.
Claims (8)
1. a kind of decelerating motor product examine method based on empirical mode decomposition and octave spectrum analysis, which is characterized in that including step
It is rapid:
1) decelerating motor vibration signal to be measured is extracted by hardware device, switchs to digital voltage signal and is passed in PC machine；
2) PC machine obtains the vibration signal of motor, is converted into sextuple data characteristics by EMD analysis and CPB spectrum analysis；
3) the sextuple data characteristics is inputted, by the OCSVM disaggregated model for selecting corresponding motor model training to finish, is identified
To the classification information of final motor superiority and inferiority.
2. the decelerating motor product examine method according to claim 1 based on empirical mode decomposition and octave spectrum analysis,
Feature is: in step 1), the extraction decelerating motor vibration signal to be measured is specifically included: obtaining continuous five by hardware device
The time domain vibration signal of one second decelerating motor to be measured of group.
3. the decelerating motor product examine method according to claim 2 based on empirical mode decomposition and octave spectrum analysis,
Feature is: in step 2), the EMD analysis is specifically included: obtaining the IMF component in the one second time of vibration signal, and with it
Preceding three-dimensional of first three rank IMF energy as the sextuple data characteristics.
4. the decelerating motor product examine method according to claim 1 based on empirical mode decomposition and octave spectrum analysis,
Feature is: in step 2), the CPB spectrum analysis is specifically included: according to actual measurement motor and third-octave rule, being passed through
FFT marks off 26 spectrum regions of time domain vibration signal, and the energy feature in 26 regions is down to three by PCA dimension reduction method
Dimension, the rear three-dimensional as the sextuple data characteristics.
5. the decelerating motor product examine method according to claim 4 based on empirical mode decomposition and octave spectrum analysis,
Feature is: the frequency range in 26 spectrums region is 20Hz~3150Hz.
6. the decelerating motor product examine method according to claim 1 based on empirical mode decomposition and octave spectrum analysis,
Feature is: in step 3), the OCSVM model is based on following quadratic programming problem:
s.t.ΦT(xi)·ω≥ρ-ξi, ξi≥0
Wherein ω and ρ is the higher-dimension parameter of hyperplane in OCSVM model；N is the quantity of trained sample；V ∈ (0,1) is used to control
Supporting vector proportion in training sample；ξiIt is non-zero slack variable, for compensating objective function；ΦT() is that feature is reflected
Function is penetrated, it can be by i-th of trained sample xiIt is transformed into hyperplane space.
7. the decelerating motor product examine method according to claim 1 based on empirical mode decomposition and octave spectrum analysis,
Feature is: in step 3), the training process of the OCSVM disaggregated model includes:
According to the artificial judgment method of vestibule, corresponding several platforms of model motor best in quality are collected；
By the hardware device, several groups 5s motor oscillating signal is acquired to every sample motor；
Each motor oscillating signal is divided into training set, test set, verifying collection according to 6: 2: 2 ratios, and 5s motor oscillating is believed
Number it is divided into 5 parts of 1s motor oscillating signals in order；
PC machine obtains the vibration signal of motor, is converted into sextuple data characteristics by EMD analysis and CPB spectrum analysis；
The OCSVM disaggregated model that the sextuple data characteristics input is established is trained the classification mould of the OCSVM after being trained
Type.
8. the decelerating motor product examine method according to claim 1 based on empirical mode decomposition and octave spectrum analysis,
Feature is: described to identify that the classification information for obtaining final motor superiority and inferiority specifically includes in step 3): by believing five seconds motors
Number divide and judged respectively by the decision function of the OCSVM model, is judged as excellent electricity if the excellent result of appearance is more
Otherwise machine is determined as bad motor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910214209.0A CN109917287B (en) | 2019-03-20 | 2019-03-20 | Speed reduction motor quality inspection method based on empirical mode decomposition and octave spectrum analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910214209.0A CN109917287B (en) | 2019-03-20 | 2019-03-20 | Speed reduction motor quality inspection method based on empirical mode decomposition and octave spectrum analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109917287A true CN109917287A (en) | 2019-06-21 |
| CN109917287B CN109917287B (en) | 2021-06-08 |
Family
ID=66965907
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910214209.0A Active CN109917287B (en) | 2019-03-20 | 2019-03-20 | Speed reduction motor quality inspection method based on empirical mode decomposition and octave spectrum analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109917287B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100978913B1 (en) * | 2009-12-30 | 2010-08-31 | 전자부품연구원 | A query by humming system using plural matching algorithm based on svm |
| CN103235260A (en) * | 2013-04-15 | 2013-08-07 | 哈尔滨工业大学 | Submersible motor rotor broken bar fault recognition method based on HHT (Hilbert-Huang transform) |
| CN103558547A (en) * | 2013-11-01 | 2014-02-05 | 东南大学 | Intelligent fault diagnosis method for permanent magnet synchronous machine |
| CN103809115A (en) * | 2014-02-27 | 2014-05-21 | 北京航空航天大学 | Online monitoring and fault diagnosis system based on vibration signal detection for circuit breaker |
| CN106682303A (en) * | 2016-12-26 | 2017-05-17 | 江南大学 | Method for diagnosing faults of three-level inverters on basis of empirical mode decomposition and decision-making tree RVM (relevant vector machines) |
| CN108507787A (en) * | 2018-06-28 | 2018-09-07 | 山东大学 | Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion and method |
| CN108520134A (en) * | 2018-03-30 | 2018-09-11 | 天津大学 | A kind of Engine Noise weight analysis method |
| CN108535648A (en) * | 2018-03-29 | 2018-09-14 | 上海交通大学 | Method of Motor Fault Diagnosis and system |
| CN108593308A (en) * | 2018-04-24 | 2018-09-28 | 桂林电子科技大学 | A kind of multi-source being turned to vibration path based on truck is shaken a little equivalent faulty section localization method with damaged structure region |
| CN108761332A (en) * | 2018-05-08 | 2018-11-06 | 郑州轻工业学院 | A kind of set empirical mode decomposition current diagnostic method of motor broken bar fault |
-
2019
- 2019-03-20 CN CN201910214209.0A patent/CN109917287B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100978913B1 (en) * | 2009-12-30 | 2010-08-31 | 전자부품연구원 | A query by humming system using plural matching algorithm based on svm |
| CN103235260A (en) * | 2013-04-15 | 2013-08-07 | 哈尔滨工业大学 | Submersible motor rotor broken bar fault recognition method based on HHT (Hilbert-Huang transform) |
| CN103558547A (en) * | 2013-11-01 | 2014-02-05 | 东南大学 | Intelligent fault diagnosis method for permanent magnet synchronous machine |
| CN103809115A (en) * | 2014-02-27 | 2014-05-21 | 北京航空航天大学 | Online monitoring and fault diagnosis system based on vibration signal detection for circuit breaker |
| CN106682303A (en) * | 2016-12-26 | 2017-05-17 | 江南大学 | Method for diagnosing faults of three-level inverters on basis of empirical mode decomposition and decision-making tree RVM (relevant vector machines) |
| CN108535648A (en) * | 2018-03-29 | 2018-09-14 | 上海交通大学 | Method of Motor Fault Diagnosis and system |
| CN108520134A (en) * | 2018-03-30 | 2018-09-11 | 天津大学 | A kind of Engine Noise weight analysis method |
| CN108593308A (en) * | 2018-04-24 | 2018-09-28 | 桂林电子科技大学 | A kind of multi-source being turned to vibration path based on truck is shaken a little equivalent faulty section localization method with damaged structure region |
| CN108761332A (en) * | 2018-05-08 | 2018-11-06 | 郑州轻工业学院 | A kind of set empirical mode decomposition current diagnostic method of motor broken bar fault |
| CN108507787A (en) * | 2018-06-28 | 2018-09-07 | 山东大学 | Wind power gear speed increase box fault diagnostic test platform based on multi-feature fusion and method |
Non-Patent Citations (3)
| Title |
|---|
| 吴定海: "基于支持向量的单类分类方法综述", 《计算机工程》 * |
| 罗炳聪: "小型电机生产过程在线品质检测方法研究", 《测控技术》 * |
| 黄建: "基于经验模态分解的高压断路器机械故障诊断方法", 《中国电机工程学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109917287B (en) | 2021-06-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102284888B (en) | Online monitoring method for turning stability of digital control machine tool | |
| Xiao et al. | Fault diagnosis of asynchronous motors based on LSTM neural network | |
| CN109297713B (en) | Steam turbine fault diagnosis method based on stable and non-stable vibration signal characteristic selection | |
| CN104794492B (en) | Machine tool processing running status ONLINE RECOGNITION method based on power features model | |
| CN111879508B (en) | Method and device for estimating instantaneous rotating speed of rotating machine based on time-frequency transformation and storage medium | |
| CN109861250B (en) | Power oscillation type discrimination method based on multi-dimensional characteristics of power system | |
| CN111508517A (en) | Intelligent micro-motor product control method based on noise characteristics | |
| CN111898443A (en) | Flow monitoring method for wire feeding mechanism of FDM type 3D printer | |
| CN114595858A (en) | Short-term wind speed prediction method and system based on rolling time series and support vector machine | |
| CN115392133A (en) | Wind power plant optimal clustering equivalence method adopting Gaussian mixture model | |
| CN115954017A (en) | HHT-based engine small sample sound abnormal fault identification method and system | |
| Zamudio-Ramirez et al. | Detection of uniform gearbox wear in induction motors based on the analysis of stray flux signals through statistical time-domain features and dimensionality reduction techniques | |
| CN109917287A (en) | Decelerating motor product examine method based on empirical mode decomposition and octave spectrum analysis | |
| CN109782167A (en) | Toothed gearing electric motor product examine device and method based on convolutional network depth model | |
| Zheng et al. | Fault diagnosis of variable speed bearing based on EMDOS-DCCNN model | |
| CN111539381A (en) | Construction method of wind turbine bearing fault classification diagnosis model | |
| CN110838725A (en) | Parameter setting method and device for wind power plant closed-loop PI controller | |
| CN115795341A (en) | Two-dimensional piston pump health state assessment method based on variable rotating speed | |
| CN109975702B (en) | Direct-current gear reduction motor quality inspection method based on circulation network classification model | |
| CN107065524B (en) | Servo system frequency domain identification system and identification method | |
| CN116090216A (en) | Power generation power prediction method and system based on typical correlation analysis | |
| Gu et al. | Research on bearing cross-domain fault diagnosis based on invariant subspace learning with tensor alignment | |
| CN114723252A (en) | Wind power plant sample board machine selection method | |
| CN114358160A (en) | Data anomaly detection method in power system | |
| CN114755010A (en) | Rotary machine vibration fault diagnosis method and system |
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 |