CN104807640A - Method of detecting life state of spatial rolling bearing based on vibration-sensitive time-frequency characteristics - Google Patents

Method of detecting life state of spatial rolling bearing based on vibration-sensitive time-frequency characteristics Download PDF

Info

Publication number
CN104807640A
CN104807640A CN201510232111.XA CN201510232111A CN104807640A CN 104807640 A CN104807640 A CN 104807640A CN 201510232111 A CN201510232111 A CN 201510232111A CN 104807640 A CN104807640 A CN 104807640A
Authority
CN
China
Prior art keywords
life state
service life
class
time
rolling bearing
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
Application number
CN201510232111.XA
Other languages
Chinese (zh)
Inventor
陈仁祥
陈思杨
杨黎霞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing Jiaotong University
Original Assignee
Chongqing Jiaotong University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing Jiaotong University filed Critical Chongqing Jiaotong University
Priority to CN201510232111.XA priority Critical patent/CN104807640A/en
Publication of CN104807640A publication Critical patent/CN104807640A/en
Pending legal-status Critical Current

Links

Abstract

The invention relates to a method of detecting life state of a spatial rolling bearing based on vibration-sensitive time-frequency characteristics and belongs to the technical field of reliability estimation and life prediction for rolling bearings. The method includes: establishing a life state characteristic set of the spatial rolling bearing via vibration frequency-domain characteristic parameters to represent the life state; removing non-sensitive characteristics in the life state characteristic set by means of life sensitivity index computation, and establishing a life state sensitive characteristic subset to enhance representation of the life state; subjecting the life state sensitive characteristic subset to dimensionality reduction and redundancy removal by a linear local tangent space alignment algorithm so as to obtain a low-dimensional life state characteristic set with good class characteristics; using a nearest neighbor classifier to recognize different life states of the spatial rolling bearing. The method allows the life state of the spatial rolling bearing to be accurately recognized and is better in application effect.

Description

Based on the Space Rolling Bearing service life state detection method of vibration sensing time-frequency characteristics
Technical field
The invention belongs to rolling bearing reliability assessment and forecasting technique in life span field, relate to a kind of Space Rolling Bearing service life state detection method based on vibration sensing time-frequency characteristics.
Background technology
The life-span of Space Rolling Bearing refers to the number of total coils or total hourage that normally run at certain working environment and condition (as rotating speed, load) lower bearing.And in engineering practice, due to rotating speed, the factor such as load and working environment thereof of space bearing, cannot test the bearing operation number of turns and add up, thus need to seek new characteristic quantity and bearing life is characterized and assesses.At present, for Space Rolling Bearing, experimental test means conventional both at home and abroad have Tribological Characteristic Analysis, friction torque test and temperature test, but the reflection of these characteristic quantities is bearing friction performance or duty, effectively cannot reflect the degenerative process of bearing life state, namely can not effectively characterize bearing life state.A new point of penetration comprises the abundant vibration signal of running state information to characterize Space Rolling Bearing service life state.
Along with the running of bearing, there are wearing and tearing in various degree in bearing element (as inside and outside raceway, retainer and rolling body) surface, namely the degree of wear represents service life state residing for bearing life.When after the wearing and tearing that bearing occurs in various degree, there is faint change in bear vibration situation, this faint change of vibration signal has directly reflected Space Rolling Bearing service life state degenerative process thereupon.The faint change of vibration signal is embodied in the energy of Time Domain Amplitude, probability distribution, frequency content, different frequency composition, and the difference of the main energy spectrum peak position of frequency spectrum etc.In order to portray these changes of vibration signal and be convenient to the Classification and Identification that different service life state is carried out in application model recognition methods comprehensively, the time and frequency domain characteristics of comprehensive utilization vibration signal is set up and is reflected that the time and frequency domain characteristics collection of bearing life state reflects.But the bearing life status flag collection set up like this will certainly be introduced non-sensitive characteristic sum and cause feature set dimension too high, weaken characteristics to Space Rolling Bearing service life state of service life state feature set, have a strong impact on the accuracy of service life state identification.
Summary of the invention
In view of this, the object of the present invention is to provide a kind of Space Rolling Bearing service life state detection method based on vibration sensing time-frequency characteristics, for vibration time and frequency domain characteristics to the susceptibility of Space Rolling Bearing service life state and the too high problem being unfavorable for Classification and Identification of service life state feature set dimension, propose solution, the method can identify Space Rolling Bearing service life state accurately.
For achieving the above object, the invention provides following technical scheme:
Based on the Space Rolling Bearing service life state detection method of vibration sensing time-frequency characteristics, the method comprises the following steps:
S1: the time domain of synthesis oscillation signal and frequency domain information, chooses D time and frequency domain characteristics parametric configuration higher-dimension time and frequency domain characteristics collection as the vibrational spectra feature of bearing life state, is Space Rolling Bearing service life state feature set;
S2: the mark utilizing scatter matrix in scatter matrix and class between scatter matrix compute classes, then calculates susceptibility index J i(i=1,2 ..., D), wherein D represents the number of time and frequency domain characteristics parameter; Build responsive time and frequency domain characteristics subset X={ x i∈ R d ', i=1,2 ..., N}, wherein, x ifor the service life state sample be made up of sensitive features, D ' represents the number of sensitive features, and N is service life state sample number;
S3: responsive for higher-dimension service life state time-frequency characteristics subset input linear local tangent space alignment (LLTSA) is trained, obtains the low-dimensional world coordinates Y={y of mapping matrix A and service life state sample i∈ R d, i=1,2 ..., N}, wherein d is the number of fusion feature, and N is service life state sample number; Low-dimensional service life state sample set and class label thereof then constitute the training sample set { y of nearest neighbor classifier (KNNC) i, l i;
S4: carry out Fusion Features to test sample book by mapping matrix A, inputs the service life state classification that KNNC obtains test sample book by result.
Further, the number D of described time and frequency domain characteristics parameter is 30; Wherein, 16 is time domain charactreristic parameter, for the distribution situation of the size and amplitude that describe Time Domain Amplitude and energy, and P 1~ P 7reflection Time Domain Amplitude and energy size, P 8~ P 16reflecting time sequence distribution situation; 14 is frequency domain character parameter, for describing the change of main band position and the degree of scatter of spectral power distribution in frequency spectrum, P 17the size of reflection frequency domain vibrational energy, P 18~ P 21the change of reflection main band position, P 22~ P 30the dispersion of reflection frequency spectrum or intensity.
Further, described S2 specifically comprises the following steps:
S21: establish sample set to be made up of C class, it is N that every class comprises number of training i, scatter matrix between scatter matrix and class in compute classes:
Scatter matrix S in described class wfor:
S W = Σ j = 1 C Σ i = 1 N i ( x i j - u i ) ( x i j - u i ) T
In formula, represent i-th data feature values of jth class, u irepresent the i-th category feature value average;
Scatter matrix S between described class bfor:
S B = Σ j = 1 C N i ( u i - u 0 ) ( u i - u 0 ) T
In formula, u 0for the overall mean vector of population sample;
S22: ask matrix S respectively wwith S bmark, be designated as tr{S wand tr{S b; Wherein, tr{S wbe the averaged measure of the feature variance of all classes, tr{S bestimate for the one of mean distance between the average of each class and overall average;
S23: according to class spacing structure service life state feature sensitivity index J:
J = tr { S B } tr ( S W )
Work as S blarger or S wmore hour, feature sensitivity index is larger; Feature sensitivity index J value larger expression character pair classification capacity is stronger, otherwise presentation class ability is weak;
S24: the susceptibility index J calculating each characteristic quantity in service life state feature set respectively i(i=1,2 ..., D); Ask for the mean value u of susceptibility index again j, select J i>=u jcharacteristic quantity build service life state sensitive features subset X={ x i∈ R d ', i=1,2 ..., N}, wherein D ' represents the number of sensitive features, x ifor the service life state sample be made up of sensitive features, N is service life state sample number.
Beneficial effect of the present invention is: a kind of Space Rolling Bearing service life state detection method based on vibration sensing time-frequency characteristics provided by the invention, vibration time and frequency domain characteristics parameter is utilized to set up Space Rolling Bearing service life state feature set, realize the sign to service life state, life sensitive index calculating method is proposed according to scatter matrix, get rid of non-sensibility feature in service life state feature set, construct service life state sensitive features subset, what strengthen service life state is characteristics; Secondly, utilize LLTSA algorithm to carry out Dimensionality Reduction to service life state sensitive features subset, remove redundant information, obtain the low-dimensional service life state feature set that sort feature is good, be convenient to pattern-recognition; Finally, the life-span identification that KNNC realizes different service life state spaces bearing is applied.The method can identify Space Rolling Bearing service life state accurately, has good effect.
Accompanying drawing explanation
In order to make the object, technical solutions and advantages of the present invention clearly, below in conjunction with accompanying drawing, the present invention is described in further detail, wherein:
Fig. 1 is the process flow diagram of the method for the invention;
Fig. 2 is original signal figure;
Fig. 3 is two kinds of feature set yojan results.
Embodiment
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are described in detail.
A kind of Space Rolling Bearing service life state detection method based on vibration sensing time-frequency characteristics provided by the invention, as shown in Figure 1, the method comprises the following steps:
S1: the time domain of synthesis oscillation signal and frequency domain information, from different characteristic, not same area, Space Rolling Bearing service life state carried out accurately, comprehensively characterize and portray, choose D time and frequency domain characteristics parametric configuration higher-dimension time and frequency domain characteristics collection as the vibrational spectra feature of bearing life state, be Space Rolling Bearing service life state feature set;
The number D of described time and frequency domain characteristics parameter is 30, as shown in table 1; Wherein, 16 is time domain charactreristic parameter, for the distribution situation of the size and amplitude that describe Time Domain Amplitude and energy, and P 1~ P 7reflection Time Domain Amplitude and energy size, P 8~ P 16reflecting time sequence distribution situation; 14 is frequency domain character parameter, for describing the change of main band position and the degree of scatter of spectral power distribution in frequency spectrum, P 17the size of reflection frequency domain vibrational energy, P 18~ P 21the change of reflection main band position, P 22~ P 30the dispersion of reflection frequency spectrum or intensity.
Table 1 service life state feature set
Note: in formula, x (n) is time-domain signal sequence, n=1,2 ..., N, N are sample points.S (k) is the frequency spectrum of signal x (n), k=1,2 ..., K, K are spectral line number, f kit is the frequency values of kth bar spectral line.A is the vibration acceleration root-mean-square value in 50 ~ 10000Hz frequency range, and unit is m/s 2; U is the mean value of x (n); a 0for reference acceleration, its value is 9.81 × 10 -3m/s 2.
S2: the mark utilizing scatter matrix in scatter matrix and class between scatter matrix compute classes, then calculates susceptibility index J i, i=1,2 ..., D, wherein D represents the number of time and frequency domain characteristics parameter; Choose the good eigenwert of susceptibility index and build responsive time and frequency domain characteristics subset X={ x i∈ R d ', i=1,2 ..., N}, wherein, x ifor the service life state sample be made up of sensitive features, D 'represent the number of sensitive features, N is service life state sample number; Specifically comprise the following steps:
S21: establish sample set to be made up of C class, it is N that every class comprises number of training i, scatter matrix between scatter matrix and class in compute classes:
Scatter matrix S in described class wfor:
S W = Σ j = 1 C Σ i = 1 N i ( x i j - u i ) ( x i j - u i ) T
In formula, represent i-th data feature values of jth class, u irepresent the i-th category feature value average;
Scatter matrix S between described class bfor:
S B = Σ j = 1 C N i ( u i - u 0 ) ( u i - u 0 ) T
In formula, u 0for the overall mean vector of population sample;
S22: ask matrix S respectively wwith S bmark, be designated as tr{S wand tr{S b; Wherein, tr{S wbe the averaged measure of the feature variance of all classes, tr{S bestimate for the one of mean distance between the average of each class and overall average;
S23: according to class spacing structure service life state feature sensitivity index J:
J = tr { S B } tr ( S W )
Work as S blarger (namely between class, spread values is larger) or S wtime less (namely in class, spread values is less), feature sensitivity index is larger.Feature sensitivity index J value larger expression character pair classification capacity is stronger, otherwise presentation class ability is weak.
S24: the susceptibility index J calculating each characteristic quantity in service life state feature set respectively i(i=1,2 ..., D), then ask for the mean value u of susceptibility index j, select J i>=u jcharacteristic quantity construct service life state sensitive features subset X={ x i∈ R d ', i=1,2 ..., N}, wherein D ' represents the number of sensitive features, x ifor the service life state sample be made up of sensitive features, N is service life state sample number.
S3: by higher-dimension service life state responsive time-frequency characteristics subset input linear local tangent space alignment (Linear local tangentspace alignment, LLTSA) train, obtain the low-dimensional world coordinates Y={y of mapping matrix A and service life state sample i∈ R d, i=1,2 ..., N}, wherein d is the number of fusion feature, and N is service life state sample number; Low-dimensional service life state sample set and class label thereof then constitute the training sample set { y of nearest neighbor classifier (K-nearest neighbors classifier, KNNC) i, l i;
S4: carry out Fusion Features to test sample book by mapping matrix A, inputs the service life state classification that KNNC obtains test sample book by result.
Embodiment:
The first step: the vibration signal receiving the many groups Space Rolling Bearing under three service life states to be analyzed, service life state is as table 2.In bearing operational process, other conditions are identical, and the larger then bearing wear of load is more serious, and namely the degree of wear of three service life states is T1<T2<T3.
Table 2 bearing life state
The space flight rolling bearing of three kinds of service life states rotating speed be 1000rpm, axial load gathers vibration signal under being the operating mode of 2kg, sample frequency is 25600Hz, and sampling length is 102400 points, obtains 6 vibration signals (front 2048 points) as shown in Figure 2.
Second step: to 6 vibration signals, be one group with 2048 respectively and each vibration signal is divided into 50 groups, namely 100 groups of vibration signals are just had under each state, randomly draw wherein 10 groups as training sample, in remaining data, randomly draw 20 groups as test sample book, ask for the service life state feature set (shown in table 1) of each training sample and test sample book.
3rd step: the susceptibility index of 30 features calculated is as shown in table 3, susceptibility index mean value is u j=18.949, select susceptibility index to be more than or equal to mean value u j12 eigenwerts (table 3 boldface) be configured to susceptibility time-frequency characteristics subset.
The susceptibility index of table 3 time-frequency characteristics collection
4th step: former feature set (shown in table 1) and sensitive features subset input LLSTA are carried out dimension is 3, Fig. 3 for the ease of observation yojan target dimension is yojan result.In Fig. 3 (a), owing to containing the more feature to bearing life susceptibility difference in former feature set, dimensionality reduction poor effect, T2 and T3 two kinds of service life states effectively do not separate.And in Fig. 3 (b), after characteristic quantity filtering low for life sensitive, through LLTSA dimensionality reduction, three kinds of service life states are efficiently separated, obtain better Clustering Effect simultaneously.
5th step: as shown in table 4 by carrying out discrimination in the low-dimensional service life state feature set input KNNC after former feature set (shown in table 1) and sensitive features subset dimensionality reduction.As can be seen from this table, the average recognition rate of former feature set is 74.3%, and sensitive features subset reaches 95.7%, and the service life state discrimination of the latter improves 28.9%.Engineer applied result demonstrates the present invention accurately can identify three kinds of service life states.
Table 4 accuracy of identification contrasts
The present embodiment characterizes and recognition methods based on the Space Rolling Bearing service life state of vibration sensing time-frequency characteristics, by to vibration time-frequency characteristics to the sensitivity analysis of Space Rolling Bearing service life state, have devised life sensitive index algorithm, life sensitive character subset is constructed according to susceptibility index, recycling LLTSA carries out yojan to life sensitive character subset and obtains low-dimensional service life state feature set, finally applies the identification that KNNC realizes service life state.The present invention can accurately identify Space Rolling Bearing service life state, has absolutely proved feasibility of the present invention and validity.
What finally illustrate is, above preferred embodiment is only in order to illustrate technical scheme of the present invention and unrestricted, although by above preferred embodiment to invention has been detailed description, but those skilled in the art are to be understood that, various change can be made to it in the form and details, and not depart from claims of the present invention limited range.

Claims (3)

1., based on the Space Rolling Bearing service life state detection method of vibration sensing time-frequency characteristics, it is characterized in that: the method comprises the following steps:
S1: the time domain of synthesis oscillation signal and frequency domain information, chooses D time and frequency domain characteristics parametric configuration higher-dimension time and frequency domain characteristics collection as the vibrational spectra feature of bearing life state, is Space Rolling Bearing service life state feature set;
S2: the mark utilizing scatter matrix in scatter matrix and class between scatter matrix compute classes, then calculates susceptibility index J i, i=1,2 ..., D, wherein, D represents the number of time and frequency domain characteristics parameter; Build responsive time and frequency domain characteristics subset X={ x i∈ R d ', i=1,2 ..., N}, wherein, x ifor the service life state sample be made up of sensitive features, D ' represents the number of sensitive features, and N is service life state sample number;
S3: higher-dimension service life state responsive time-frequency characteristics subset input linear local tangent space alignment is trained, obtains the low-dimensional world coordinates Y={y of mapping matrix A and service life state sample i∈ R d, i=1,2 ..., N}, wherein d is the number of fusion feature, and N is service life state sample number; Training sample set { the y of low-dimensional service life state sample set and class label composition nearest neighbor classifier (KNNC) thereof i, l i;
S4: carry out Fusion Features to test sample book by mapping matrix A, inputs the service life state classification that KNNC obtains test sample book by result.
2. the Space Rolling Bearing service life state detection method based on vibration sensing time-frequency characteristics according to claim 1, is characterized in that: the number D of described time and frequency domain characteristics parameter is 30; Wherein, 16 is time domain charactreristic parameter, for the distribution situation of the size and amplitude that describe Time Domain Amplitude and energy, and P 1~ P 7reflection Time Domain Amplitude and energy size, P 8~ P 16reflecting time sequence distribution situation; 14 is frequency domain character parameter, for describing the change of main band position and the degree of scatter of spectral power distribution in frequency spectrum, P 17the size of reflection frequency domain vibrational energy, P 18~ P 21the change of reflection main band position, P 22~ P 30the dispersion of reflection frequency spectrum or intensity.
3. the Space Rolling Bearing service life state detection method based on vibration sensing time-frequency characteristics according to claim 1, is characterized in that: described S2 specifically comprises the following steps:
S21: establish sample set to be made up of C class, it is N that every class comprises number of training i, scatter matrix between scatter matrix and class in compute classes:
Scatter matrix S in described class wfor:
S W = &Sigma; j = 1 C &Sigma; i = 1 N i ( x i j - u i ) ( x i j - u i ) T
In formula, represent i-th data feature values of jth class, u irepresent the i-th category feature value average;
Scatter matrix S between described class bfor:
S B = &Sigma; j = 1 C N i ( u i - u 0 ) ( u i - u 0 ) T
In formula, u 0for the overall mean vector of population sample;
S22: ask matrix S respectively wwith S bmark, be designated as tr{S wand tr{S b; Wherein, tr{S wbe the averaged measure of the feature variance of all classes, tr{S bestimate for the one of mean distance between the average of each class and overall average;
S23: according to class spacing structure service life state feature sensitivity index J:
J = tr { S B } tr ( S W )
Work as S blarger or S wmore hour, feature sensitivity index is larger; Feature sensitivity index J value larger expression character pair classification capacity is stronger, otherwise presentation class ability is weak;
S24: the susceptibility index J calculating each characteristic quantity in service life state feature set respectively i, i=1,2 ..., D, then the mean value u asking for susceptibility index j, select J i>=u jcharacteristic quantity construct service life state sensitive features subset X={ x i∈ R d ', i=1,2 ..., N}, wherein D ' represents the number of sensitive features, x ifor the service life state sample be made up of sensitive features, N is service life state sample number.
CN201510232111.XA 2015-05-08 2015-05-08 Method of detecting life state of spatial rolling bearing based on vibration-sensitive time-frequency characteristics Pending CN104807640A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510232111.XA CN104807640A (en) 2015-05-08 2015-05-08 Method of detecting life state of spatial rolling bearing based on vibration-sensitive time-frequency characteristics

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510232111.XA CN104807640A (en) 2015-05-08 2015-05-08 Method of detecting life state of spatial rolling bearing based on vibration-sensitive time-frequency characteristics

Publications (1)

Publication Number Publication Date
CN104807640A true CN104807640A (en) 2015-07-29

Family

ID=53692663

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510232111.XA Pending CN104807640A (en) 2015-05-08 2015-05-08 Method of detecting life state of spatial rolling bearing based on vibration-sensitive time-frequency characteristics

Country Status (1)

Country Link
CN (1) CN104807640A (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105956574A (en) * 2016-05-17 2016-09-21 重庆交通大学 Rolling bearing service life state same-scale characterization and recognition method under different rotating speeds
CN106597149A (en) * 2016-11-22 2017-04-26 电子科技大学 Oscillator residual life estimation method based on acceleration sensitivity
CN106644474A (en) * 2015-10-28 2017-05-10 财团法人工业技术研究院 Hydrostatic bearing monitoring system and method thereof
CN106769051A (en) * 2017-03-10 2017-05-31 哈尔滨理工大学 A kind of rolling bearing remaining life Forecasting Methodology based on MCEA KPCA and combination S VR
CN107631882A (en) * 2017-08-21 2018-01-26 北京锦鸿希电信息技术股份有限公司 The acquisition methods and device of vehicle axle box residual life
CN109027017A (en) * 2018-08-15 2018-12-18 重庆交通大学 A kind of Space Rolling Bearing state of wear appraisal procedure
CN111274149A (en) * 2020-02-06 2020-06-12 中国建设银行股份有限公司 Test data processing method and device
CN111597722A (en) * 2020-05-20 2020-08-28 北京航空航天大学 Method for predicting equipment precision retention time by using running state information
CN112561306A (en) * 2020-12-11 2021-03-26 领伟创新智能系统(浙江)有限公司 Rolling bearing health state evaluation method based on Hankel matrix
CN112710474A (en) * 2020-12-31 2021-04-27 中国人民解放军92942部队 Diesel engine state evaluation method based on real-time vibration data

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005095919A1 (en) * 2004-03-31 2005-10-13 The Chugoku Electric Power Co., Inc. Method and device for assessing remaining life of rolling bearing
CN102778357A (en) * 2012-08-15 2012-11-14 重庆大学 Mechanical failure feature extracting method based on optimal parameter ensemble empirical mode decomposition (EEMD)
CN103822793A (en) * 2014-01-20 2014-05-28 北京邮电大学 Complicated equipment acoustic fault recognition and location 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

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005095919A1 (en) * 2004-03-31 2005-10-13 The Chugoku Electric Power Co., Inc. Method and device for assessing remaining life of rolling bearing
CN102778357A (en) * 2012-08-15 2012-11-14 重庆大学 Mechanical failure feature extracting method based on optimal parameter ensemble empirical mode decomposition (EEMD)
CN103822793A (en) * 2014-01-20 2014-05-28 北京邮电大学 Complicated equipment acoustic fault recognition and location 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

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
李锋等: "基于线性局部切空间排列维数化简的故障诊断", 《振动与冲击》 *
栗茂林等: "利用非线性流形学习的轴承早期故障特征提取方法", 《西安交通大学学报》 *

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106644474A (en) * 2015-10-28 2017-05-10 财团法人工业技术研究院 Hydrostatic bearing monitoring system and method thereof
CN105956574A (en) * 2016-05-17 2016-09-21 重庆交通大学 Rolling bearing service life state same-scale characterization and recognition method under different rotating speeds
CN106597149A (en) * 2016-11-22 2017-04-26 电子科技大学 Oscillator residual life estimation method based on acceleration sensitivity
CN106769051B (en) * 2017-03-10 2019-07-23 哈尔滨理工大学 A kind of rolling bearing remaining life prediction technique based on MCEA-KPCA and combination S VR
CN106769051A (en) * 2017-03-10 2017-05-31 哈尔滨理工大学 A kind of rolling bearing remaining life Forecasting Methodology based on MCEA KPCA and combination S VR
CN107631882A (en) * 2017-08-21 2018-01-26 北京锦鸿希电信息技术股份有限公司 The acquisition methods and device of vehicle axle box residual life
CN109027017A (en) * 2018-08-15 2018-12-18 重庆交通大学 A kind of Space Rolling Bearing state of wear appraisal procedure
CN109027017B (en) * 2018-08-15 2019-12-10 重庆交通大学 method for evaluating wear state of space rolling bearing
CN111274149A (en) * 2020-02-06 2020-06-12 中国建设银行股份有限公司 Test data processing method and device
CN111597722A (en) * 2020-05-20 2020-08-28 北京航空航天大学 Method for predicting equipment precision retention time by using running state information
CN111597722B (en) * 2020-05-20 2023-11-10 北京航空航天大学 Method for predicting equipment precision holding time by using running state information
CN112561306A (en) * 2020-12-11 2021-03-26 领伟创新智能系统(浙江)有限公司 Rolling bearing health state evaluation method based on Hankel matrix
CN112561306B (en) * 2020-12-11 2023-12-08 领伟创新智能系统(浙江)有限公司 Rolling bearing health state evaluation method based on Hankel matrix
CN112710474A (en) * 2020-12-31 2021-04-27 中国人民解放军92942部队 Diesel engine state evaluation method based on real-time vibration data

Similar Documents

Publication Publication Date Title
CN104807640A (en) Method of detecting life state of spatial rolling bearing based on vibration-sensitive time-frequency characteristics
CN103996287B (en) A kind of vehicle compulsory based on decision-tree model changes decision-making technique
CN102778355B (en) Rolling bearing state identification method based on empirical mode decomposition (EMD) and principal component analysis (PCA)
CN102829974B (en) LMD (local mean decomposition) and PCA (principal component analysis) based rolling bearing state identification method
CN109754110B (en) Early warning method and system for traction converter faults
CN106314438A (en) Method and system for detecting abnormal track in driver driving track
CN104849050A (en) Rolling bearing fault diagnosis method based on composite multi-scale permutation entropies
CN105139070A (en) Fatigue driving evaluation method based on artificial nerve network and evidence theory
CN102156873B (en) Chaos-based method for detecting and classifying early single-point faults of mechanical component
CN103115668B (en) The fault signature extracting method of milling train oscillation mark vibration signal and recognition methods
CN109612729A (en) A kind of malfunction recognition methods of port Machine Trolley Wheel Bearings
CN110411766A (en) The snakelike unstability detection method of train bogie, device, system and storage medium
CN101916241A (en) Method for identifying time-varying structure modal frequency based on time frequency distribution map
CN106913351A (en) A kind of recognition methods of Mental Workload level
CN104688252A (en) Method for detecting fatigue status of driver through steering wheel rotation angle information
CN109255094A (en) Commercial truck quality estimation method based on SVR_Adaboost innovatory algorithm
CN105956574A (en) Rolling bearing service life state same-scale characterization and recognition method under different rotating speeds
CN102663252A (en) Combined type pavement usability performance evaluation method for underground road
Wang et al. Identification of driver braking intention based on long short-term memory (LSTM) network
CN105632187A (en) Low-power consumption side parking detection method based on geomagnetic sensor network
CN114997218A (en) Recognition and detection method for polygonal abrasion of wheels of railway vehicle
Yu et al. Lubrication state recognition based on energy characteristics of friction vibration with EEMD and SVM
CN109649399A (en) A kind of driver distraction&#39;s method of discrimination based on lateral running speed
Brisimi et al. Sensing and classifying roadway obstacles: The street bump anomaly detection and decision support system
Ge et al. A review of research on driving distraction based on bibliometrics and co-occurrence: focus on driving distraction recognition methods

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
EXSB Decision made by sipo to initiate 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: 20150729