CN109917287B - Speed reduction motor quality inspection method based on empirical mode decomposition and octave spectrum analysis - Google Patents
Speed reduction motor quality inspection method based on empirical mode decomposition and octave spectrum analysis Download PDFInfo
- Publication number
- CN109917287B CN109917287B CN201910214209.0A CN201910214209A CN109917287B CN 109917287 B CN109917287 B CN 109917287B CN 201910214209 A CN201910214209 A CN 201910214209A CN 109917287 B CN109917287 B CN 109917287B
- Authority
- CN
- China
- Prior art keywords
- motor
- vibration
- spectrum analysis
- ocsvm
- dimensional data
- 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
Landscapes
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a method for quality inspection of a speed reduction motor based on empirical mode decomposition and octave spectrum analysis, which comprises the following steps: 1) extracting a vibration signal of the speed reducing motor to be detected through hardware equipment, converting the vibration signal into a digital voltage signal and transmitting the digital voltage signal into a PC (personal computer); 2) the method comprises the following steps that a PC machine obtains vibration signals of a motor, and the vibration signals are converted into six-dimensional data characteristics through EMD analysis and CPB spectrum analysis; 3) and inputting the six-dimensional data characteristics, and identifying and obtaining the final classification information of the motor by selecting the OCSVM classification model after the training of the corresponding motor model. The method judges whether the quality of the source motor of the signal is qualified or not by using the vibration signal characteristics obtained by the EMD and the CPB and using a support vector machine, solves the problems of huge labor cost, fatigue detection and the like caused by a manual detection method widely used in the field at present, and improves the efficiency of identifying the quality of the speed reducing motor while ensuring the accuracy.
Description
Technical Field
The invention relates to the field of mechanical fault diagnosis technology and vibration signal analysis, in particular to a speed reduction motor quality inspection method based on empirical mode decomposition and octave spectrum analysis.
Background
With the increasing development of human science and technology, automation will become one of the main melodies for the production development of the 21 st century. As a motor capable of converting electric energy into mechanical energy, it has been an indispensable core component of automation systems in various fields. Among them, in the occasion of low-speed, big torque, gear reduction motor is the most economical, practical preferred scheme always.
The gear reduction motor is a motor in which a gear reduction box is attached to an output shaft of a motor, and an output rotational speed is reduced from a high speed to a low speed by reduction of a gear, and an output torque is increased. Due to the characteristics, the micro motor product is widely applied to precision instruments such as an automatic production line and medical equipment and intelligent power output of related equipment such as intelligent industry, intelligent agriculture, intelligent home and intelligent robot. Under the intense market competition pressure of the products, how to ensure the quality of the products during large-scale production becomes one of the important problems of whether gear reduction motor enterprises can create considerable economic benefits.
At present, the quality of the speed reducing motor is detected, and besides the rotating speed, the torque, the temperature rise and the like of a plurality of hard indexes, the noise and the gear quality are also required to be identified. In the domestic miniature gear reduction motor factory, the detection is generally identified manually, namely, the quality of the product is comprehensively judged by sensing the idle-load vibration of the motor by hands and listening to the idle-load noise of the motor by ears. The method has the advantages that the labor cost in production is greatly increased, and due to the repetitive labor, workers have fatigue judgment errors, so that inferior-quality products are led to enter the market, and irretrievable losses are brought to the reputation of enterprises and the subsequent economy.
Aiming at the problems of the quality detection efficiency, the precision and the like of the speed reducing motor, the invention integrates the vibration signal analysis method into the method. The vibration signal characteristics of the motor are obtained by combining an EMD analysis method and a CPB analysis method, and then an OCSVM model (one type of support vector machine model) is trained through the obtained vibration signal characteristic data, so that the quality detection task of the speed reduction motor is realized. The efficiency of identifying the quality of the speed reducing motor is improved while the accuracy rate is ensured.
Disclosure of Invention
The improved motor vibration signal characteristics are applied to the quality detection of the speed reducing motor, and the OCSVM model trained by the improved characteristics can obviously improve the precision and efficiency of the motor quality detection, and reduce the problems of labor cost, precision efficiency and the like of enterprises.
The invention is realized by adopting the following technical scheme:
a quality inspection method of a speed reduction motor based on empirical mode decomposition and octave spectrum analysis comprises the following steps:
1) extracting a vibration signal of the speed reducing motor to be detected through hardware equipment, converting the vibration signal into a digital voltage signal and transmitting the digital voltage signal into a PC (personal computer);
2) the method comprises the following steps that a PC machine obtains vibration signals of a motor, and the vibration signals are converted into six-dimensional data characteristics through EMD analysis and CPB spectrum analysis;
3) and inputting the six-dimensional data characteristics, and identifying and obtaining the final classification information of the motor by selecting the OCSVM classification model after the training of the corresponding motor model.
Further, in step 1), extracting the vibration signal of the speed reduction motor to be detected specifically includes: and acquiring five groups of continuous time domain vibration signals of the speed reducing motor to be detected for one second through hardware equipment.
Further, in step 2), the EMD analysis specifically includes: obtaining IMF component of the vibration signal within one second, and taking the IMF energy of the first three orders as the first three dimensions of the six-dimensional data characteristic.
Further, in step 2), the CPB spectrum analysis specifically includes: according to an actual measurement motor and an 1/3 octave rule, 26 spectrum regions of a time domain vibration signal are divided through FFT, and the energy characteristics of the 26 regions are reduced to three dimensions through a PCA dimension reduction method to serve as the rear three dimensions of the six-dimensional data characteristics.
Further, the frequency range of the 26 spectral regions is 20Hz to 3150 Hz.
Further, in step 3), the OCSVM model is based on the following quadratic programming problem:
s.t.ΦT(xi)·ω≥ρ-ξi，ξi≥0
wherein ω and ρ are the high dimensional parameters of the hyperplane in the OCSVM model; n is the number of training samples; v is belonged to (0,1) and is used for controlling the proportion of the support vector in the training sample; xiiA non-zero relaxation variable for compensating the objective function; phiT() Is a feature mapFunction of ray, the ith training sample xiTo a hyperplane space.
Further, in step 3), the training process of the OCSVM classification model includes:
collecting a plurality of motors with corresponding models and excellent quality according to a manual judgment method of a factory technician;
collecting a plurality of groups of 5s motor vibration signals for each sample motor through the hardware equipment;
dividing each motor vibration signal into a training set, a testing set and a verification set according to a ratio of 6:2:2, and sequentially dividing 5s motor vibration signals into 5 parts of 1s motor vibration signals;
the method comprises the following steps that a PC machine obtains vibration signals of a motor, and the vibration signals are converted into six-dimensional data characteristics through EMD analysis and CPB spectrum analysis;
and inputting the six-dimensional data characteristics into the established OCSVM classification model for training to obtain the trained OCSVM classification model.
Further, in step 3), the identifying and obtaining the final classification information of the quality of the motor specifically includes: and dividing the five-second motor signal and respectively judging through a decision function of the OCSVM model, if the excellent result is more, judging the motor to be an excellent motor, and if not, judging the motor to be an inferior motor.
Compared with the prior art, the improved motor vibration signal characteristics are applied to the quality detection of the speed reducing motor, the problems of huge labor cost, fatigue detection and the like caused by the manual detection method widely used in the field are solved, the accuracy and efficiency of motor quality detection can be remarkably improved by using the improved characteristic-trained OCSVM model, and the problems of labor cost, accuracy efficiency and the like of enterprises are reduced.
Drawings
Fig. 1 is a schematic structural diagram of a quality inspection system of a speed reduction motor based on empirical mode decomposition and octave spectrum analysis.
Fig. 2 is a flow chart of vibration signal IMF component extraction based on EMD analysis.
Fig. 3 is a flow chart of identification of a gear reduction motor quality inspection system based on empirical mode decomposition and octave spectrum analysis.
Detailed Description
The invention is further described with reference to the following figures and specific embodiments.
FIG. 1 is a schematic structural diagram of a speed reduction motor quality inspection system based on empirical mode decomposition and octave spectrum analysis, wherein a micro direct current gear speed reduction motor to be detected is subjected to voltage stabilization power supply through an MOTECH numerical control linear direct current stabilized power supply LPS-305, and is in rigid contact with the surface of a CT1050LC acceleration sensor through a metal steel sheet. At the moment, the acceleration sensor is powered by the CT5201 single-channel constant-current adapter, an amplified voltage signal is transmitted to the analog input port of the MCC1608G usb multifunctional data acquisition card DAQ, and the data acquisition unit converts the analog signal into a digital signal and transmits the digital signal into a PC (personal computer), so that model training and quality inspection judgment are performed.
As shown in fig. 3, a method for quality inspection of a reduction motor based on empirical mode decomposition and octave spectrum analysis includes the steps of:
1) extracting a vibration signal of the speed reducing motor to be detected through hardware equipment, converting the vibration signal into a digital voltage signal and transmitting the digital voltage signal into a PC (personal computer);
2) the method comprises the following steps that a PC machine obtains vibration signals of a motor, and the vibration signals are converted into six-dimensional data characteristics through EMD analysis and CPB spectrum analysis;
3) and inputting the six-dimensional data characteristics, and identifying and obtaining the final classification information of the motor by selecting the OCSVM classification model after the training of the corresponding motor model.
Specifically, in step 1), extracting the vibration signal of the speed reduction motor to be detected specifically includes: and acquiring five groups of continuous time domain vibration signals of the speed reducing motor to be detected for one second through hardware equipment.
Specifically, in step 2), the EMD analysis specifically includes: obtaining an IMF (Intrinsic Mode Function) component of the vibration signal within one second, and taking the IMF energy of the first three orders as the first three dimensions of the six-dimensional data characteristic. The motor vibration signal belongs to a non-stationary signal, and the sample motor vibration signal can be decomposed by an EMD method, so that an array inherent modal component of the signal is obtained, and the specific formula is as follows:
wherein, imfi(t) is the signal x (t) the ith IMF obtained by EMD decomposition; r isn(t) is the residual signal component after each decomposition of the IMF component, and the extraction process is shown in fig. 2, and specifically includes the steps of:
r is initialized0(t)＝x(t),i＝1。
② extracting signal x (t) ith IMF component, ri(t) is the residual component, hj(t) is the decomposition modal component, mj(t) is a sequence of upper and lower envelope means, where j represents the residual component ri(t) the number of cycles in the cycle. The method comprises the following specific steps of dividing the residual component ri(t) function renaming decomposition mode component hj(t) and for the component hj(t) calculating maximum and minimum values, respectively using a cubic spline interpolation method (three are used respectively) for each extreme value to obtain upper and lower envelope lines, and taking an average value to obtain a sequence mj(t) and until the stop condition is satisfied, deleting the sequence m by not stoppingj(t) a final decomposition mode h obtained by iterationJ(t) where a signal x (t) is obtained, the ith IMF component IMFi(t)＝hj(t) of (d). Wherein the stopping condition is defined by the standard deviation SdDetermining:
wherein S isdIs the standard deviation and S between two successive processing resultsdIn the range of 0.1 to 0.3, when S is obtaineddIf not, the loop is exited to obtain the ith IMF component of the signal x (t).
Calculating the current residual component ri(t)＝ri-1(t)-imfi(t) if the residual component riAnd (t) if more than 2 extreme values still exist, acquiring the IMF component of the (i + 1) th, returning to the step II, and if not, ending to acquire a final series of IMF components of the vibration signal.
Fourthly, calculatingEnergy IMF of all IMF components of the vibration signali(t)：
IMFi(t)＝imfi 2(t)。
Taking the first three-order IMF components to form a three-dimensional characteristic A ═ IMF1IMF2IMF3]。
Specifically, in step 2), the CPB spectrum analysis specifically includes: according to an actual measurement motor and an 1/3 octave rule, dividing 26 spectrum regions of a time-domain vibration signal through FFT (fast Fourier transform), and reducing the energy characteristics of the 26 regions to three dimensions by a PCA dimension reduction method to be used as the rear three dimensions of the six-dimensional data characteristics, specifically comprising the steps of:
the method comprises the following steps: fast Fourier Transform (FFT) is performed on a vibration signal of a motor to be measured, and a power spectrum of the vibration signal is obtained.
Step two: using an octave analysis, here 1/3 octave analysis, i.e. dividing the power spectrum over the frequency range 1/3 octaves, forming 26 frequency bins at 20Hz to 3150Hz, and calculating the respective center frequencies f0Near 1/3 octave energy Ex(f0)：
Where X (k) is a discrete form of the vibration signal, N is the sequence length, and T is the sampling frequency fsReciprocal of (a), fl，nlDivided into a central frequency f0Lower limit frequency and starting point of near 1/3 octaves, fh，nhDivided into a central frequency f0Upper frequency and end point of the near 1/3 octaves.
Step three: 1/3 octave energy data matrix for sampling motor to be tested
And (3) PCA dimension reduction, namely calculating a covariance matrix of the matrix, then performing singular value decomposition on the matrix to obtain a descending order characteristic value spectrum from large to small, and then performing linear transformation to obtain dimension-reduced characteristic data, wherein the characteristic dimension is three.
Specifically, in step 3), the OCSVM model is based on the following quadratic programming problem:
s.t.ΦT(xi)·ω≥ρ-ξi,ξi≥0
wherein ω and ρ are the high dimensional parameters of the hyperplane in the OCSVM model; n is the number of training samples; v is belonged to (0,1) and is used for controlling the proportion of the support vector in the training sample; xiiA non-zero relaxation variable for compensating the objective function; phiT() Is a feature mapping function, and can map the ith training sample xiTo a hyperplane space.
Specifically, in step 3), the training process of the OCSVM classification model includes:
collecting 100 motors with corresponding models and excellent quality according to a manual judgment method of a factory technician;
collecting 20 groups of 5s motor vibration signals for each sample motor through the hardware equipment;
dividing each motor vibration signal into a training set, a testing set and a verification set according to a ratio of 6:2:2, and sequentially dividing 5s motor vibration signals into 5 parts of 1s motor vibration signals;
the PC machine obtains vibration signals of the motor, and the vibration signals are converted into six-dimensional data characteristics through EMD analysis and CPB spectrum analysis, namely the characteristics obtained through EMD analysis and CPB spectrum analysis are combined to enable each sample data to obtain only one six-dimensional characteristic data.
And carrying out supervised learning training on the OCSVM classification model established by inputting the six-dimensional data characteristics to obtain the trained OCSVM classification model, wherein a decision function expanded by a support vector can be expressed as:
wherein k (x)iX) is a Gaussian kernel function, xiFor support vectors, p is a blockThe policy function output threshold can be calculated from any edge vector x, wherein the coefficient aiAnd obtaining the result through an SMO algorithm.
After obtaining the OCSVM model of the trained specific gear reducer motor, the unknown gear reducer motor can be identified, and therefore, in step 3), the identification of the classification information of the final motor quality obtained by the identification specifically includes: and dividing the five-second motor signal and respectively judging through a decision function of the OCSVM model, if the excellent result is more, judging the motor to be an excellent motor, and if not, judging the motor to be an inferior motor. Specifically, as shown in fig. 3, that is, when a motor vibration signal is introduced into the PC through the hardware device shown in fig. 1, the vibration signal of 5 seconds is changed into a six-dimensional data characteristic of 5 continuous groups of 1s through the EMD analysis and the CPB spectrum analysis, an OCSVM classification model trained according to the motor model is selected, and a decision function of the OCSVM is used to determine the recognition result of each group, if the number num of the motors determined to be superior is greater than 2.5, the quality of the motors is determined to be superior by using a minority-compliant majority principle, and if the number num of the motors determined to be superior is less than 2.5, the quality of the motors is determined to be inferior.
The method can accurately extract the vibration signal of the speed reducing motor, and judges the quality of the speed reducing motor by combining the established depth model base based on the convolutional network, thereby reducing the workload of manual identification and improving the detection precision of the motor, and further improving the production efficiency of the motor.
The above description is only a preferred embodiment of the present invention, but the protection scope of the present invention is not limited thereto, and any person skilled in the art can substitute or change the technical solution of the present invention and the inventive concept within the scope of the present invention disclosed by the present invention, and all those persons skilled in the art should fall within the protection scope of the present invention.
Claims (4)
1. A quality inspection method of a speed reduction motor based on empirical mode decomposition and octave spectrum analysis is characterized by comprising the following steps:
1) extracting a vibration signal of the speed reducing motor to be detected through hardware equipment, converting the vibration signal into a digital voltage signal and transmitting the digital voltage signal into a PC (personal computer); the step of extracting the vibration signal of the speed reducing motor to be detected specifically comprises the following steps: acquiring five groups of continuous time domain vibration signals of the speed reducing motor to be detected for one second through hardware equipment;
2) the PC machine acquires vibration digital signals of the motor to be measured and subtracted, and the vibration digital signals are converted into six-dimensional data characteristics through EMD analysis and CPB spectrum analysis; the EMD analysis specifically includes: obtaining IMF components of the vibration signals within one second, and taking the IMF energy of the first three orders as the first three dimensions of the six-dimensional data characteristics; the CPB spectrum analysis specifically includes: dividing 26 spectrum regions of a time domain vibration signal through FFT (fast Fourier transform) according to an actual measurement motor and an 1/3 octave rule, and reducing the energy characteristics of the 26 regions to three dimensions by a PCA (principal component analysis) dimension reduction method to be used as the back three dimensions of the six-dimensional data characteristics;
3) inputting the six-dimensional data characteristics, and identifying and obtaining final classification information of the motor by selecting an OCSVM classification model after training corresponding to the motor model; the OCSVM model is based on the following quadratic programming problem:
s.t.ΦT(xi)·ω≥ρ-ξi,ξi≥0
wherein ω and ρ are the high dimensional parameters of the hyperplane in the OCSVM model; n is the number of training samples; the v belongs to (0,1) and is used for controlling the proportion of the support vector in the training sample; xiiA non-zero relaxation variable for compensating the objective function; phiT() Is a feature mapping function, and can map the ith training sample xiTo a hyperplane space.
2. The quality inspection method for the speed reduction motor based on empirical mode decomposition and octave spectrum analysis according to claim 1, characterized in that: the frequency range of the 26 spectrum regions is 20Hz to 3150 Hz.
3. The quality inspection method for the speed reduction motor based on empirical mode decomposition and octave spectrum analysis according to claim 1, characterized in that: in step 3), the training process of the OCSVM classification model includes:
collecting a plurality of motors with corresponding models and excellent quality according to a manual judgment method of a factory technician;
collecting a plurality of groups of 5s motor vibration signals for each sample motor through the hardware equipment;
dividing each motor vibration signal into a training set, a testing set and a verification set according to a ratio of 6:2:2, and sequentially dividing 5s motor vibration signals into 5 parts of 1s motor vibration signals;
the method comprises the following steps that a PC machine obtains vibration signals of a motor, and the vibration signals are converted into six-dimensional data characteristics through EMD analysis and CPB spectrum analysis;
and inputting the six-dimensional data characteristics into the established OCSVM classification model for training to obtain the trained OCSVM classification model.
4. The quality inspection method for the speed reduction motor based on empirical mode decomposition and octave spectrum analysis according to claim 1, characterized in that: in step 3), the step of identifying and obtaining the final classification information of the quality of the motor specifically includes: and dividing the vibration signals of the five-second motor and respectively judging through a decision function of the OCSVM model, if the excellent results are more, judging the motor to be an excellent motor, and if the excellent results are not more, judging the motor to be an inferior 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 CN109917287A (en) | 2019-06-21 |
| CN109917287B true 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 |
|---|
| 基于支持向量的单类分类方法综述;吴定海;《计算机工程》;20110331;第37卷(第5期);第187-189页 * |
| 基于经验模态分解的高压断路器机械故障诊断方法;黄建;《中国电机工程学报》;20110425;第31卷(第12期);第108-113页 * |
| 小型电机生产过程在线品质检测方法研究;罗炳聪;《测控技术》;20151231;第34卷(第12期);第34-37页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109917287A (en) | 2019-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | A new intelligent bearing fault diagnosis method using SDP representation and SE-CNN | |
| JP3993825B2 (en) | Inference signal generator for instrumented equipment and processes | |
| CN112418013A (en) | Complex working condition bearing fault diagnosis method based on meta-learning under small sample | |
| CN109253882A (en) | A kind of rotor crack fault diagnostic method based on variation mode decomposition and gray level co-occurrence matrixes | |
| Li et al. | A nonintrusive load identification model based on time-frequency features fusion | |
| CN109623489B (en) | Improved machine tool health state evaluation method and numerical control machine tool | |
| Medina et al. | Deep learning-based gear pitting severity assessment using acoustic emission, vibration and currents signals | |
| CN114429152A (en) | Rolling bearing fault diagnosis method based on dynamic index antagonism self-adaption | |
| CN111898443A (en) | Flow monitoring method for wire feeding mechanism of FDM type 3D printer | |
| CN116950917A (en) | Large centrifugal compressor blade crack online diagnosis method based on blade tip timing | |
| CN114755010A (en) | Rotary machine vibration fault diagnosis method and system | |
| CN109917287B (en) | Speed reduction motor quality inspection method based on empirical mode decomposition and octave spectrum analysis | |
| CN109782167B (en) | Gear reduction motor quality inspection device and method based on convolutional network depth model | |
| CN114297264A (en) | Method and system for detecting abnormal segments of time sequence signal | |
| CN106599391B (en) | Association vector machine soft measurement modeling method based on dynamic weighting of triangle angle values | |
| CN115795341A (en) | Two-dimensional piston pump health state assessment method based on variable rotating speed | |
| CN110261108B (en) | CNN color characteristic diagram-based bearing fault identification method during rated operation | |
| CN107356431A (en) | Rolling bearing performance degradation assessment method based on ADMM Yu sparse ensemble learning | |
| CN116522237A (en) | Rolling bearing fault diagnosis method based on parallel convolution neural network | |
| CN107065524B (en) | Servo system frequency domain identification system and identification method | |
| CN107341503B (en) | Identification method for multi-source energy efficiency state in cutting process | |
| Mao et al. | Bearing fault diagnosis based on multi-task learning | |
| CN112948755A (en) | Telemetering sine parameter interpretation method | |
| Feng et al. | A time-series driven mechanical system state description method and its application in condition monitoring | |
| CN112257773A (en) | Mechanical equipment fault diagnosis method based on multiple measurement vectors of wireless sensor network |
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 |