CN108898050A - A kind of flexible material process equipment roll shaft performance index calculation method - Google Patents
A kind of flexible material process equipment roll shaft performance index calculation method Download PDFInfo
- Publication number
- CN108898050A CN108898050A CN201810476133.4A CN201810476133A CN108898050A CN 108898050 A CN108898050 A CN 108898050A CN 201810476133 A CN201810476133 A CN 201810476133A CN 108898050 A CN108898050 A CN 108898050A
- Authority
- CN
- China
- Prior art keywords
- roll shaft
- data
- matrix
- frequency domain
- flexible material
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Signal Processing (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
A kind of flexible material process equipment roll shaft performance index calculation method, includes the following steps：Step 1：The vibration data of roll shaft is acquired by three axis acceleration sensors；Step 2：Vibration data carries out data feature extraction after sliding average noise reduction, and the data characteristics includes the time domain charactreristic parameter of vibration data, frequency domain character parameter and time and frequency domain characteristics parameter；Step 3：The data characteristics is input to Principal Component Analysis Weighted Fusion module, is used for roll shaft performance degradation index to obtaining after data Feature Dimension Reduction.Flexible material process equipment roll shaft vibration data feature mainly includes temporal signatures, frequency domain character and time and frequency domain characteristics.By temporal signatures, frequency domain character, time and frequency domain characteristics be used for roll shaft performance degradation index calculate, can comprehensive and accurate assessment roll shaft performance degradation the case where.
Description
Technical field
The present invention relates to technical fields of mechanical processing, and in particular to a kind of flexible material process equipment roll shaft performance indicator meter
Calculation method.
Background technique
Under the demand that extensive mass is efficiently manufactured, process equipment behavior pattern determines the matter of product manufacturing
Amount and efficiency.The performance of usual process equipment will receive the control of a parameters multiple or even up to a hundred, and actually specifically influence
Machining equipment only has a small number of key parameters, therefore when analyzing huge data, in order to avoid dimension disaster,
On the basis of not losing data information, main characteristic parameters how are screened as research hotspot.
The performance of flexible material process equipment roll shaft directly determines flexible material roll-to-roll (Roll to Roll) processing
Quality and production efficiency, and since the roll-to-roll process of flexible material easily deforms, the roll shaft of roll-to-roll process equipment
The minor change of performance can all cause material process quality issue.And current flexible material process equipment roll shaft performance indicator needs
Many principal components are used to characterize the performance characteristic of roll shaft, it is difficult to analyzing for huge data, dimension disaster is caused,
And also it is easily lost data information.
Summary of the invention
It can comprehensive and accurate assessment roller it is an object of the invention to aiming at the deficiencies in the prior art, provide one kind
The flexible material process equipment roll shaft performance index calculation method of the case where axis performance degradation.
For this purpose, the present invention uses following technical scheme：A kind of flexible material process equipment roll shaft performance indicator meter
Calculation method, includes the following steps：
Step 1：The vibration data of roll shaft is acquired by three axis acceleration sensors；
Step 2：Vibration data carries out data feature extraction after sliding average noise reduction, and the data characteristics includes vibration number
According to time domain charactreristic parameter, frequency domain character parameter and time and frequency domain characteristics parameter；
Step 3：The data characteristics is input to Principal Component Analysis Weighted Fusion module, to obtaining after data Feature Dimension Reduction
It must be used for roll shaft performance degradation index.
Preferably, the time domain charactreristic parameter includes absolute average, root mean square and kurtosis.
Preferably, the frequency domain character parameter includes centre frequency, root mean square frequency and standard deviation.
Preferably, the time and frequency domain characteristics parameter includes the energy value E (C of 4 intrinsic mode functions components1)、E(C2)、E
(C3) and E (C4)。
Preferably, the step 2 includes：
Step 2.1：It is smoothed by the vibration data of sliding average method roll shaft, i.e., continuously takes M sampling
Value regards a queue as, and the length of queue is fixed as M, samples a new data every time and is put into tail of the queue, and rejects original head of the queue
Data, calculate the arithmetic average of M data in queue, and calculation formula is as follows：
Yn=(Xn+Xn-1+Xn-2+…+Xn-M-1)/M
Step 2.2：Time domain charactreristic parameter extraction is carried out to smoothed out data, calculating process is as follows：
Absolute average：
Root mean square：
Kurtosis：
In formula：Indicate sample mean, N indicates the data amount check that each sample includes, xiIndicate i-th of numerical value, XRMS
Indicate that sample root mean square, β indicate sample kurtosis characteristic ginseng value；
Step 2.3：Frequency domain character parameter extraction is carried out to smoothed out data, calculating process is as follows：
Power spectrum：
Centre frequency：
Root mean square frequency：
Standard variance：
In formula：F indicates the frequency of vibration signal, and s (f) is the power spectrum of vibration signal, centre frequency (FC), root mean square
Frequency (RMSF) is all description power spectrum main band change in location, and standard variance (RVF) is used to describe the dispersion of spectrum energy
Degree；
Step 3.3：Using empirical mode decomposition method (EMD)：
Vibration signal x(t)It is broken down into n intrinsic mode functions component and a remainder rn, intrinsic mode functions component C1,...,
CnIt is the ingredient of different frequency sections from high to low, rnIt is that a constant or an average tendency, decomposition result are represented by：
Wherein intrinsic mode functions component Ci(t) it is intrinsic mode function, contains original signal in the part of different time scales
Characteristic information, finally using the energy value of its decomposition result intrinsic mode functions component as time and frequency domain characteristics parameter；
I-th of component Ci(t) energy can be expressed as：
In formula：N is intrinsic mode functions component Ci(t) data length；
Take the energy of first four component as time and frequency domain characteristics parameter, i.e. E (C herein1)、E(C2)、E(C3) and E (C4)；
Empirical mode decomposition method has orthogonality, and specific manifestation is as follows：
E [x (t)]=E [c1(t)]+E[c2(t)]+...+E[cn(t)]+E[rn(t)]；
Step 3.4：The feature information extraction of roll shaft vibration data is completed, and extracts it by time domain, frequency domain, time and frequency domain characteristics
The data matrix of characteristic information composition afterwards is expressed as：
WhereinSample number is n, and the characteristic parameter of extraction is p dimension.In conclusion p=10 herein.In matrix
x21Indicate corresponding 1st characteristic ginseng value --- the absolute average of the 2nd sample data.
Preferably, the step 3 includes：
Step 3.1：Initial parameter matrix is standardized, normalization operation, obtains normalization characteristic matrix；
Step 3.2：It is screened by contribution, obtains eigenvectors matrix；
Step 3.3：It is weighted fusion, obtains performance indicator matrix, and then calculates performance degradation index.
Preferably, the step 3.1 is：
Assuming that initial data XiX is used after standardizationi *It indicates, then
Wherein E (Xi) it is feature vector, XiMean value, D (Xi) it is feature vector, XiVariance：
Then normalization characteristic matrix is：
Preferably, the step 3.2 is：
Solve normalization characteristic matrix X*Covariance matrix, be defined as follows：
Then matrix X*Covariance matrix be：
Finally, by the characteristic value and feature vector (orthogonal basis) that solve covariance matrix, so that the energy quantity set of sample set
In be distributed on these specific directions；
Covariance matrix C is p rank square matrix, if it exists constant λ and non-vanishing vector u, so that Cu=λ u (u ≠ 0), then claim λiFor
One characteristic value of Matrix C, uiAs λiCorresponding feature vector.Screening rule is as follows：
K value before being filtered out in the characteristic value acquired, corresponding feature vector composition characteristic vector matrix U：
In formula：uiIndicate ith feature value λiCorresponding feature vector, wherein ui=[u1i,u2i,...,upi]T。
Preferably, the step 3.3 is：
The linear combination obtained by principal component transform can be expressed as X1*, X2..., X *p* linear combination calculates public
Formula is as follows：
In formula：F1,F2,...,FkBetween be independent of each other two-by-two, F1It is maximum for variance in linear combination, i.e. first principal component,
The descending sequence of characteristic value, successively obtains Second principal component, F2..., kth principal component Fk, finally by this k performance degradation
Index variation tendency judges the health status of flexible material process equipment roll shaft, when cataclysm occurs for performance indicator curve (suddenly
Rise or fall), indicate that roll-to-roll process equipment is in abnormal operational conditions at this time.
Beneficial effects of the present invention：This patent innovatively constructs the roll-to-roll process roll shaft vibration multidimensional of flexible material
Principal component analysis (PCA) extracting method of characteristic, roll shaft performance characteristic is characterized with a small number of principal components, both available to have
Information is imitated, and data can be simplified, is the optimal selection for establishing flexible material process equipment roll shaft performance indicator.
A kind of flexible material process equipment roll shaft performance index calculation method, flexible material process equipment roll shaft vibration data
Feature mainly includes temporal signatures, frequency domain character and time and frequency domain characteristics.Temporal signatures, frequency domain character, time and frequency domain characteristics are used for
Roll shaft performance degradation index calculate, can comprehensive and accurate assessment roll shaft performance degradation the case where.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples.
Fig. 1 is the flexible material process equipment roll shaft performance index calculation method block diagram of one embodiment of the invention.
Specific embodiment
To further illustrate the technical scheme of the present invention below with reference to the accompanying drawings and specific embodiments.
Firstly, acquiring the vibration data of roll shaft by three axis acceleration sensors, vibration data is laggard through sliding average noise reduction
Row data feature extraction, including：The time domain charactreristic parameter of vibration data, frequency domain character parameter, time and frequency domain characteristics parameter, specially
Absolute average, root mean square, kurtosis, centre frequency, root mean square frequency, standard deviation and 4 intrinsic mode functions components energy
It is worth (E (C1), E (C2), E (C3), E (C4)).
Finally, the characteristic extracted is input to Principal Component Analysis (PCA) Weighted Fusion module, to characteristic
The formula calculated for roll shaft performance degradation index is obtained after dimensionality reduction.
A kind of flexible material process equipment roll shaft performance index calculation method is realized using following steps.
It is smoothed by the vibration velocity data of sliding average method roll shaft, i.e., continuously takes M sampled value to see
At a queue, the length of queue is fixed as M, samples a new data every time and is put into tail of the queue, and rejects the data of original head of the queue,
Calculate the arithmetic average of M data in queue.Calculation formula is as follows：
Yn=(Xn+Xn-1+Xn-2+…+Xn-M-1)/M
Wherein：N is the data amount check that sample includes, and Xn indicates n-th of sample data, and Yn indicates the continuous N currently chosen
The average value of a data, M are the width of sliding window, and the bigger smooth effect of M is better, and response speed relative drop, M value range exists
Between 10~50.
Feature extraction is carried out to smoothed out data, progress time domain charactreristic parameter extraction first, main includes absolutely average
It is worth (feature 1), three root mean square (feature 2), kurtosis (feature 3) characteristic parameters.
Absolute average：
Root mean square：
Kurtosis：
In formula：Indicate sample mean, N indicates the data amount check that each sample includes, xiIndicate i-th of numerical value, XRMS
Indicate that sample root mean square, β indicate sample kurtosis characteristic ginseng value；
Frequency domain character parameter extraction mainly includes centre frequency (feature 4), root mean square frequency (feature 5) and standard variance
(feature 6) three characteristic parameters.
Power spectrum：
Centre frequency：
Root mean square frequency：
Standard variance：
In formula：F indicates the frequency of vibration signal, and s (f) is the power spectrum of vibration signal, centre frequency (FC), root mean square
Frequency (RMSF) is all description power spectrum main band change in location, and standard variance (RVF) is used to describe the dispersion of spectrum energy
Degree；
Due to the vibration signal of roll-to-roll process equipment roll shaft have the characteristics that it is non-linear, non-stationary, herein using warp
Test mode decomposition (EMD)：
Vibration signal x(t)It is broken down into n intrinsic mode functions component and a remainder rn, intrinsic mode functions component C1,...,
CnIt is the ingredient of different frequency sections from high to low, rnIt is that a constant or an average tendency, decomposition result are represented by：
Wherein intrinsic mode functions component is intrinsic mode function, and the local feature for containing original signal in different time scales is believed
Breath, finally using the energy value of its decomposition result intrinsic mode functions component as time and frequency domain characteristics parameter；
The energy of i-th of component can be expressed as：
In formula：N is intrinsic mode functions component Ci(t) data length；
Take the energy value of first four component as time and frequency domain characteristics parameter, i.e. E (C herein1) (feature 7), E (C2) (feature
8)、E(C3) (feature 9) and E (C4) (feature 10).
Empirical mode decomposition method has orthogonality, and specific manifestation is as follows：
E [x (t)]=E [c1(t)]+E[c2(t)]+...+E[cn(t)]+E[rn(t)]
At this point, the feature information extraction of roll shaft vibration data is completed, after extracting by time domain, frequency domain, time and frequency domain characteristics
Characteristic information composition data matrix be expressed as：
WhereinSample number is n, and the characteristic parameter of extraction is p dimension.In conclusion p=10 herein.In matrix
x21Indicate corresponding 1st characteristic ginseng value --- the absolute average of the 2nd sample data.
Firstly, it is necessary to be standardized to initial parameter matrix, normalization operation.
Assuming that initial data XiX is used after standardizationi *It indicates, then
Wherein E (Xi) it is feature vector, XiMean value, D (Xi) it is feature vector, XiVariance：
Then normalization characteristic matrix is：
Second step solves eigenmatrix X*Covariance matrix, be defined as follows：
Then matrix X*Covariance matrix be：
As it can be seen that covariance matrix is a symmetrical matrix, and diagonal line is the variance of each dimension.Covariance matrix C
The calculation of correlation between all observational variables is contained, while reflecting the noise of data and the degree of redundancy.On diagonal line
Variance is bigger, shows that signal is stronger, and the importance of variable is higher, and the smaller expression of variance may be secondary variable or believe for noise
Number.
Finally, by the characteristic value and feature vector (orthogonal basis) that solve covariance matrix, so that the energy quantity set of sample set
In be distributed on these specific directions.
Covariance matrix C is p rank square matrix, if it exists constant λ and non-vanishing vector u, so that Cu=λ u (u ≠ 0), then claim λiFor
One characteristic value of Matrix C, uiAs λiCorresponding feature vector.Screening rule is as follows：
K value before being filtered out in the characteristic value acquired, corresponding feature vector composition characteristic vector matrix U：
In formula：uiIndicate ith feature value λiCorresponding feature vector, wherein ui=[u1i,u2i,...,upi]T。
The linear combination obtained by principal component transform can be expressed as X1*, X2..., X *p* linear combination calculates public
Formula is as follows：
In formula：F1,F2,...,FkBetween be independent of each other two-by-two, F1It is maximum for variance in linear combination, i.e. first principal component,
The descending sequence of characteristic value, successively obtains Second principal component, F2..., kth principal component Fk, finally by this k performance degradation
Index variation tendency judges the health status of flexible material process equipment roll shaft, when cataclysm occurs for performance indicator curve (suddenly
Rise or fall), indicate that roll-to-roll process equipment is in abnormal operational conditions at this time.
The above is only a preferred embodiment of the present invention, for those of ordinary skill in the art, according to the present invention
Thought, there will be changes in the specific implementation manner and application range, and the content of the present specification should not be construed as to the present invention
Limitation.
Claims (9)
1. a kind of flexible material process equipment roll shaft performance index calculation method, it is characterised in that：Include the following steps：
Step 1：The vibration data of roll shaft is acquired by three axis acceleration sensors；
Step 2：Vibration data carries out data feature extraction after sliding average noise reduction, and the data characteristics includes vibration data
Time domain charactreristic parameter, frequency domain character parameter and time and frequency domain characteristics parameter；
Step 3：The data characteristics is input to Principal Component Analysis Weighted Fusion module, to being used after data Feature Dimension Reduction
In roll shaft performance degradation index.
2. flexible material process equipment roll shaft performance index calculation method according to claim 1, it is characterised in that：It is described
Time domain charactreristic parameter includes absolute average, root mean square and kurtosis.
3. flexible material process equipment roll shaft performance index calculation method according to claim 1, it is characterised in that：It is described
Frequency domain character parameter includes centre frequency, root mean square frequency and standard deviation.
4. flexible material process equipment roll shaft performance index calculation method according to claim 1, it is characterised in that：It is described
Time and frequency domain characteristics parameter includes the energy value E (C of 4 intrinsic mode functions components1)、E(C2)、E(C3) and E (C4)。
5. flexible material process equipment roll shaft performance index calculation method according to claim 1, it is characterised in that：It is described
Step 2 includes：
Step 2.1：It is smoothed by the vibration data of sliding average method roll shaft, i.e., continuously takes M sampled value to see
At a queue, the length of queue is fixed as M, samples a new data every time and is put into tail of the queue, and rejects the data of original head of the queue,
The arithmetic average of M data in queue is calculated, calculation formula is as follows：
Yn=(Xn+Xn-1+Xn-2+…+Xn-M-1)/M
Step 2.2：Time domain charactreristic parameter extraction is carried out to smoothed out data, calculating process is as follows：
Absolute average：
Root mean square：
Kurtosis：
In formula：Indicate sample mean, N indicates the data amount check that each sample includes, xiIndicate i-th of numerical value, XRMSIt indicates
Sample root mean square, β indicate sample kurtosis characteristic ginseng value；
Step 2.3：Frequency domain character parameter extraction is carried out to smoothed out data, calculating process is as follows：
Power spectrum：
Centre frequency：
Root mean square frequency：
Standard variance：
In formula：F indicates the frequency of vibration signal, and s (f) is the power spectrum of vibration signal, centre frequency (FC), root mean square frequency
It (RMSF) is all description power spectrum main band change in location, and standard variance (RVF) is used to describe the degree of scatter of spectrum energy；
Step 3.3：Using empirical mode decomposition method (EMD)：
Vibration signal x(t)It is broken down into n intrinsic mode functions component and a remainder rn, intrinsic mode functions component C1,...,CnIt is
The ingredient of different frequency sections from high to low, rnIt is that a constant or an average tendency, decomposition result are represented by：
Wherein intrinsic mode functions component CiIt (t) is intrinsic mode function, the local feature for containing original signal in different time scales is believed
Breath, finally using the energy value of its decomposition result intrinsic mode functions component as time and frequency domain characteristics parameter；
I-th of component Ci(t) energy can be expressed as：
In formula：N is intrinsic mode functions component Ci(t) data length；
Take the energy of first four component as time and frequency domain characteristics parameter, i.e. E (C herein1)、E(C2)、E(C3) and E (C4)；
Empirical mode decomposition method has orthogonality, and specific manifestation is as follows：
E [x (t)]=E [c1(t)]+E[c2(t)]+...+E[cn(t)]+E[rn(t)]；
Step 3.4：The feature information extraction of roll shaft vibration data is completed, after extracting by time domain, frequency domain, time and frequency domain characteristics
The data matrix of characteristic information composition is expressed as：
WhereinSample number is n, and the characteristic parameter of extraction is p dimension, in conclusion p=10 herein, x in matrix21I.e.
Indicate corresponding 1st characteristic ginseng value --- the absolute average of the 2nd sample data.
6. flexible material process equipment roll shaft performance index calculation method according to claim 5, it is characterised in that：It is described
Step 3 includes：
Step 3.1：Initial parameter matrix is standardized, normalization operation, obtains normalization characteristic matrix；
Step 3.2：It is screened by contribution, obtains eigenvectors matrix；
Step 3.3：It is weighted fusion, obtains performance indicator matrix, and then calculates performance degradation index.
7. flexible material process equipment roll shaft performance index calculation method according to claim 6, it is characterised in that：It is described
Step 3.1 is：
Assuming that initial data XiX is used after standardizationi *It indicates, then
Wherein E (Xi) it is feature vector, XiMean value, D (Xi) it is feature vector, XiVariance：
Then normalization characteristic matrix is：
8. flexible material process equipment roll shaft performance index calculation method according to claim 7, it is characterised in that：It is described
Step 3.2 is：
Solve normalization characteristic matrix X*Covariance matrix, be defined as follows：
Then matrix X*Covariance matrix be：
Finally, being divided by the characteristic value and feature vector (orthogonal basis) that solve covariance matrix so that the energy of sample set is concentrated
Cloth is on these specific directions；
Covariance matrix C is p rank square matrix, if it exists constant λ and non-vanishing vector u, so that Cu=λ u (u ≠ 0), then claim λiFor Matrix C
A characteristic value, uiAs λiCorresponding feature vector, screening rule are as follows：
K value before being filtered out in the characteristic value acquired, corresponding feature vector composition characteristic vector matrix U：
In formula：uiIndicate ith feature value λiCorresponding feature vector, wherein ui=[u1i,u2i,...,upi]T。
9. flexible material process equipment roll shaft performance index calculation method according to claim 8, it is characterised in that：It is described
Step 3.3 is：
The linear combination obtained by principal component transform can be expressed as X1*, X2..., X *p* linear combination, calculation formula is such as
Under：
In formula：F1,F2,...,FkBetween be independent of each other two-by-two, F1For variance maximum, i.e. first principal component, feature in linear combination
It is worth descending sequence, successively obtains Second principal component, F2..., kth principal component Fk, finally by this k performance degradation index
Variation tendency judges the health status of flexible material process equipment roll shaft.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810476133.4A CN108898050A (en) | 2018-05-17 | 2018-05-17 | A kind of flexible material process equipment roll shaft performance index calculation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810476133.4A CN108898050A (en) | 2018-05-17 | 2018-05-17 | A kind of flexible material process equipment roll shaft performance index calculation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108898050A true CN108898050A (en) | 2018-11-27 |
Family
ID=64342833
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810476133.4A Pending CN108898050A (en) | 2018-05-17 | 2018-05-17 | A kind of flexible material process equipment roll shaft performance index calculation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108898050A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109946075A (en) * | 2018-12-25 | 2019-06-28 | 东北大学 | A kind of bearing condition monitoring and method for diagnosing faults |
| CN110344824A (en) * | 2019-06-25 | 2019-10-18 | 中国矿业大学(北京) | A kind of sound wave curve generation method returned based on random forest |
| CN110837130A (en) * | 2019-11-22 | 2020-02-25 | 中国电子科技集团公司第四十一研究所 | Target automatic detection algorithm based on millimeter wave/terahertz wave radiation |
| CN113049749A (en) * | 2021-03-12 | 2021-06-29 | 中国农业大学 | Electronic nose detection system |
| CN113566953A (en) * | 2021-09-23 | 2021-10-29 | 中国空气动力研究与发展中心设备设计与测试技术研究所 | Online monitoring method for flexible-wall spray pipe |
| CN113933056A (en) * | 2021-11-05 | 2022-01-14 | 上海电气风电集团股份有限公司 | Bearing fault diagnosis method and device for wind generating set |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102829974A (en) * | 2012-08-07 | 2012-12-19 | 北京交通大学 | LMD (local mean decomposition) and PCA (principal component analysis) based rolling bearing state identification method |
| CN103954450A (en) * | 2014-05-19 | 2014-07-30 | 重庆交通大学 | Bearing life degradation performance evaluation index construction method based on main component analysis |
| CN106404396A (en) * | 2016-08-30 | 2017-02-15 | 四川中烟工业有限责任公司 | Rolling bearing fault diagnosis method |
| CN106909756A (en) * | 2017-03-29 | 2017-06-30 | 电子科技大学 | A kind of rolling bearing method for predicting residual useful life |
| CN106980761A (en) * | 2017-03-29 | 2017-07-25 | 电子科技大学 | A kind of rolling bearing running status degradation trend Forecasting Methodology |
-
2018
- 2018-05-17 CN CN201810476133.4A patent/CN108898050A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102829974A (en) * | 2012-08-07 | 2012-12-19 | 北京交通大学 | LMD (local mean decomposition) and PCA (principal component analysis) based rolling bearing state identification method |
| CN103954450A (en) * | 2014-05-19 | 2014-07-30 | 重庆交通大学 | Bearing life degradation performance evaluation index construction method based on main component analysis |
| CN106404396A (en) * | 2016-08-30 | 2017-02-15 | 四川中烟工业有限责任公司 | Rolling bearing fault diagnosis method |
| CN106909756A (en) * | 2017-03-29 | 2017-06-30 | 电子科技大学 | A kind of rolling bearing method for predicting residual useful life |
| CN106980761A (en) * | 2017-03-29 | 2017-07-25 | 电子科技大学 | A kind of rolling bearing running status degradation trend Forecasting Methodology |
Non-Patent Citations (6)
| Title |
|---|
| 刘胜等: "智能预报技术及其在船舶工程中应用", 《智能预报技术及其在船舶工程中应用》 * |
| 徐金梧: "冶金生产过程质量监控理论与方法", 《冶金生产过程质量监控理论与方法》 * |
| 戚宗锋等: "《电子信息***仿真可信度评估理论方法》", 31 May 2013 * |
| 朱可恒: "滚动轴承振动信号特征提取及诊断方法研究", 《中国博士学位论文全文数据库工程科技Ⅱ辑》 * |
| 梅宏斌: "滚动轴承振动监测与诊断 理论·方法·***", 《滚动轴承振动监测与诊断 理论·方法·***》 * |
| 王玉静: "滚动轴承振动信号特征提取与状态评估方法研究", 《中国博士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109946075A (en) * | 2018-12-25 | 2019-06-28 | 东北大学 | A kind of bearing condition monitoring and method for diagnosing faults |
| CN110344824A (en) * | 2019-06-25 | 2019-10-18 | 中国矿业大学(北京) | A kind of sound wave curve generation method returned based on random forest |
| CN110837130A (en) * | 2019-11-22 | 2020-02-25 | 中国电子科技集团公司第四十一研究所 | Target automatic detection algorithm based on millimeter wave/terahertz wave radiation |
| CN113049749A (en) * | 2021-03-12 | 2021-06-29 | 中国农业大学 | Electronic nose detection system |
| CN113566953A (en) * | 2021-09-23 | 2021-10-29 | 中国空气动力研究与发展中心设备设计与测试技术研究所 | Online monitoring method for flexible-wall spray pipe |
| CN113566953B (en) * | 2021-09-23 | 2021-11-30 | 中国空气动力研究与发展中心设备设计与测试技术研究所 | Online monitoring method for flexible-wall spray pipe |
| CN113933056A (en) * | 2021-11-05 | 2022-01-14 | 上海电气风电集团股份有限公司 | Bearing fault diagnosis method and device for wind generating set |
| CN113933056B (en) * | 2021-11-05 | 2024-02-23 | 上海电气风电集团股份有限公司 | Bearing fault diagnosis method and device for wind generating set |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108898050A (en) | A kind of flexible material process equipment roll shaft performance index calculation method | |
| Das et al. | Openness and growth in emerging Asian economies: Evidence from GMM estimations of a dynamic panel | |
| AlThobiani et al. | An application to transient current signal based induction motor fault diagnosis of Fourier–Bessel expansion and simplified fuzzy ARTMAP | |
| Xue et al. | Feature extraction using hierarchical dispersion entropy for rolling bearing fault diagnosis | |
| CN104655423A (en) | Rolling bearing fault diagnosis method based on time-frequency domain multidimensional vibration feature fusion | |
| US20120130678A1 (en) | Wind turbine monitoring device, method, and program | |
| CA2965340A1 (en) | An enhanced system and method for conducting pca analysis on data signals | |
| JP2009288100A (en) | Soundness diagnosis method and program, and soundness diagnosis apparatus of windmill | |
| Wang et al. | Fault detection and identification using a Kullback-Leibler divergence based multi-block principal component analysis and Bayesian inference | |
| CN112668105A (en) | Helicopter transmission shaft abnormity judgment method based on SAE and Mahalanobis distance | |
| CN116684878B (en) | 5G information transmission data safety monitoring system | |
| CN112182912A (en) | Manufacturing equipment main shaft bearing health assessment method based on probability description and spectrum analysis | |
| CN110738259B (en) | Fault detection method based on Deep DPCA-SVM | |
| CN115081331A (en) | Wind turbine generator running state abnormity detection method based on state parameter reconstruction error | |
| CN114429238A (en) | Wind turbine generator fault early warning method based on space-time feature extraction | |
| Wang et al. | Multiple event identification and characterization by retrospective analysis of structured data streams | |
| CN113408578A (en) | Harmonic reducer fault diagnosis method and system based on generative countermeasure network | |
| CN109000924B (en) | Method for monitoring state of ball screw pair based on K mean value | |
| Liu et al. | Bearing failure diagnosis at time-varying speed based on adaptive clustered fractional Gabor transform | |
| CN111507374A (en) | Power grid mass data anomaly detection method based on random matrix theory | |
| CN108647604A (en) | Object state identification method based on the extraction of frequency domain histogram feature | |
| CN104808643B (en) | A kind of control loop non-linear detection method based on improved double-spectrum analysis | |
| CN109684970B (en) | Window length determination method for moving principal component analysis of structural dynamic response | |
| Wang et al. | Conductor galloping detection on imbalanced dataset: Svm with smart sampling | |
| Choi et al. | Comparison of various statistical methods for detecting disease outbreaks |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181127 |