Professional Documents
Culture Documents
fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2018.2834540, IEEE
Access
Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000.
Digital Object Identifier 10.1109/ACCESS.2017.Doi Number
ABSTRACT Motor bearing is subjected to the joint effects of much more loads, transmissions and shocks
that cause bearing fault and machinery breakdown. Vibration signal analysis method is the most popular
technique that is used to monitor and diagnose the fault of motor bearing. However, the application of
vibration signal analysis method for motor bearing is very limited in engineering practice. In this paper, on
the basis of comparing fault feature extraction by using empirical wavelet transform(EWT) and Hilbert
transform with the theoretical calculation, a new motor bearing fault diagnosis method based on integrating
EWT, fuzzy entropy and support vector machine(SVM), called EWTFSFD is proposed. In the proposed
method, a novel signal processing method called EWT is used to decompose vibration signal into multiple
components in order to extract a series of amplitude modulated-frequency modulated(AM-FM) components
with supporting Fourier spectrum under an orthogonal basis. Then fuzzy entropy is utilized to measure the
complexity of vibration signal, reflect complexity changes of intrinsic oscillation, and compute the fuzzy
entropy values of AM-FM components, which are regarded as the inputs of SVM model to train and
construct a SVM classifier for fulfilling fault pattern recognition. Finally, the effectiveness of the proposed
method is validated by using the simulated signal and real motor bearing vibration signals. The experiment
results show that the EWT outperforms empirical mode decomposition for decomposing the signal into
multiple components, and the proposed EWTFSFD method can accurately and effectively achieve the fault
diagnosis of motor bearing.
INDEX TERMS Motor bearing, Fault diagnosis, Empirical wavelet transform, Fuzzy entropy, Support
vector machine, Fourier spectrum segmentation, AM-FM components
I.INTRODUCTION the loss of production and income, and even occur human
With the constantly increasing automation level in rotating casualties. It was reported that bearing faults accommodate
machinery, fault diagnosis is paying more and more attention motor failures of 45~55%[2,3]. Therefore, the fault diagnosis
in order to increase the reliability and decrease the possible of motor bearing plays a key role in the reliable operation of
loss due to the unforeseen damage and fault. Bearing is one motors. It must be monitored and diagnosed to guarantee the
of the most important components in various rotating safe operation and further prevent the breakdowns of rotating
machinery[1]. The motor bearing is subjected to the joint machines. In general, when the motor bearing has broken
effects of much more loads, transmissions and shocks, which down, the components of outer race, inner race and rolling
cause bearing fault and machinery breakdown, and lead to element induce impulses, which can be detected in the
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2018.2834540, IEEE
Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
acquired vibration signal. When one defective bearing rotates genetic and ant colony adaptive collaborative optimization
at a constant speed, the generated impulses are periodic or algorithm. Deng et al. [24] proposed an improved adaptive
quasi-periodic. Because the mechanical vibration signals PSO algorithm for solving complex problem. Gu et al. [25]
consist of plentiful information with the dynamical features, proposed a structural minimax probability machine for
the vibration-based signal processing method is one of the constructing a margin classifier. Rong et al. [26] proposed a
principal tools for diagnosing the malfunctions of motor novel K+-isomorphism method. Zhao et al. [27] proposed a
bearing. Therefore, it is great importance to deeply study the new feature extraction method based on EEMD and multi-
fault diagnosis method and maintain the safety and stability scale fuzzy entropy. Chen et al. [28] proposed an improved
operation of motors[4-7]. quaternion principal component analysis method for
In recent years, a variety of fault diagnosis methods have processing nonlinear quaternion signals. Wang et al. [29]
been effectively exploited to detect motor bearing faults at proposed a back propagation neural network model. Deng
an early stage in order to keep machinery performing state, et al. [30] proposed a novel intelligent diagnosis method
avoid abnormal progression and reduce productivity loss. using optimal LS-SVM with improved PSO algorithm.
For fault diagnosis, the signal analysis is one of the most Xiong et al. [31] proposed a novel reversible data hiding
important steps, because it can effectively analyze the scheme using integer wavelet transform, histogram shifting
dynamic information. There exist various kinds of the and orthogonal decomposition. Zhang et al. [32] proposed
vibration signal analysis methods, such as spectral analysis, an efficient algorithm to achieve k-barrier coverage. Qu et
correlation analysis, time series analysis, autoregressive al. [33] proposed a multilevel pattern mining architecture to
moving average(ARMA), fast Fourier transform(FFT), support automatic network management. These proposed
wavelet transform(WT), empirical mode decomposition methods have better realized the signal analysis, feature
(EMD), independent component analysis(ICA), blind signal extraction, fault diagnosis, and some research results are
separation(BSS), ensemble empirical mode decomposition obtained in recent years. But these proposed methods also
(EEMD), neural network, fault tree analysis, support vector have their own limitations in the actual engineering
machine(SVM), gray theory and so on. Ming et al.[8] applications. Some methods cannot effectively analyze the
proposed a novel fault diagnosis method based on the fault signal, and extract the fault feature, which result in the
orthogonal projection theory. van Wyk et al.[9] proposed a lower fault diagnosis accuracy, the poor generalization
powerful tool for bearing time series feature extraction and ability of fault diagnosis model, and the higher calculation
classification methods for real-time applications. Mohsen et complexity, and so on.
al.[10] proposed a fault diagnosis method of analog circuits Wavelet transform(WT) is an effective tool to analyze
based on dictionary approach. Liu et al.[11] proposed a the non-stationary signal [34]. A wavelet has good local
signal processing method-amplitude recovery method. time-frequency properties. It can provide time domain and
Rubini and Meneghetti[12] proposed the limits of the frequency domain information by inner production between
mentioned methodologies by showing their application to the analyzed signal and a predetermined wavelet basis. So
bearings affected by different pitting failures. Gao et al.[13] this method has already shown its tremendous ability in
proposed an empirical mode decomposition method for mechanical equipment fault diagnosis due to multi-
decomposing complicated signal. Widodo et al.[14] applied resolution analysis ability [35]. Dyadic wavelet
independent component analysis for feature extraction and transform(DWT) is proposed to extract the fault feature. It
data reduction from original features. Guo et al.[15] can save some computation time because it is a fast method.
proposed a robust feature extraction scheme for the fault This method has widely applied in mechanical fault
diagnosis of rolling element. Dong et al.[16] proposed a diagnosis [36,37]. But the DWT only can decompose the
repeated blind source separation method based on low frequency sub-band. Wavelet packet transform(WPT)
morphological filtering and singular value decomposition to is based on improving its frequency resolution through a
separate the mixed sources. Xue et al.[17] proposed an parallel decomposition of the high-frequency and low-
adaptively fast EEMD method. Cheng et al.[18] proposed a frequency bands. However, the WPT would not allow a
new gear fault diagnosis method in strong noise based on data-driven frequency partition due to the dyadic partition
multi-sensor information fusion. Jayaswal et al.[19] scheme. Although these wavelet methods have gained a lot
proposed a new approach based on wavelet transform, of interesting results in engineering applications, they still
artificial neural network and fuzzy rules for detecting and are limited in the subdivision scheme. They are very
localizing defects in rolling element. Widodo et al.[20] difficult to be altered, and they can lead to severe damages
proposed two multi-class classification techniques for fault on exacting transient vibration features in transition areas of
diagnosis through RVM and support vector machine. Hu et packets. Meanwhile, the EMD method is proposed to
al. [21] proposed a central-tapped node linked modular fault overcome the prescribed dyadic subdivision scheme and
tolerance topology for SRM. Liu et al. [22] proposed a achieve adaptive representation [38]. The EMD is a
speculative approach for spatial-temporal efficiency with completely different method, which is used to identify the
multi-objective optimization. Deng et al. [23] proposed a principal modes with representing the signal. It decomposes
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2018.2834540, IEEE
Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
the multi-modulated vibration signal into a few intrinsic A. EMPIRICAL WAVELET TRANSFORM
mode functions(IMFs). Each IMF is considered as a 1) EMPIRICAL MODE DECOMPOSITION
component. Because the EMD method can effectively The EMD method is a non-linear multi-resolution self-
extract stationary and non-stationary components from a adaptive decomposition technique [45], which provides a
signal, it has been paid attentions to signal processing and different approach to signal processing since it is not
actual engineering applications. However, there is lack of defined as integral transform. It can adaptively decompose
mathematical theory for EMD method, a lot of improved a complicated signal into a set of intrinsic mode
issues and combining other methods are proposed in recent functions(IMFs) without preliminary knowledge from the
years[39]. Empirical wavelet transform(EWT) based on high frequency to low frequency by means of a process,
combining the advantages of wavelet transform and EMD called sifting. The sifting process decomposes the original
method was proposed by Gilles [40]. It is used to extract a signal( S (t ) ) into a number of IMFs according to the
series of amplitude modulated-frequency modulated(AM- following expression:
FM) signals from the given signal. The EWT method is n
used in fault diagnosis for weak fault and compound fault S (t ) ci (t ) rn (t ) (1)
identification. The AM-FM components can be transformed i 1
into a compact supporting Fourier spectrum, and the where rn (t ) represents the residual of the signal S (t ) ,
different approach is developed to construct adaptive ci (t ) indicates the i th IMF. The IMF components, such as
wavelets capable of identifying AM-FM components for
vibration signal. The different modes are identified to c1 , c2 , c3 , ... , cn represent the frequency bands from the
segment Fourier spectrum and apply some filtering for each low frequency to high frequency.
detected supporting. Therefore, the EWT method can An IMF is the function that satisfies two following
effectively analyze a signal and extract the internal features. conditions:
For the nonlinear dynamic features of bearing fault a) The number of extrema and the number of zero-
signals, some nonlinear analysis methods are also used in crossings must be either equal or differ at most by one in one
fault diagnosis, such as approximate entropy, sample data set.
entropy and fuzzy entropy and so on [41-43]. These b) The mean value of the moving envelope defined by
methods have made some successful applications in the local maxima and the envelope defined by local minima are
field of fault diagnosis. But the approximate entropy exits zero at any point.
the shortcomings of dependency on record length and lower 2) WAVELET TRANSFORM
estimation value. The sample entropy is based on the Wavelet theory has emerged as a signal processing tool in
Heaviside step function, it is discontinuous and mutational many fields, and has some distinct merits. It was firstly
at the boundary. The fuzzy entropy is defined by using the proposed by Morlet in 1984 [46]. Wavelets are
concept of membership function. It uses least mean square mathematical functions that divide data into different
and membership function method to process the similarity frequency components. It is different from short time
measures of sequence, so it is an effective tool to measure Fourier transform(STFT) in that each component is studied
the data fuzziness. The SVM is a powerful machine with a resolution to its scale.
learning method based on statistical learning theory and For the sake of simplicity, one-dimensional wavelets are
structural risk minimization principle [44]. It has been considered to illustrate the related concepts. Wavelet
successfully applied to fault diagnosis in order to improve transform(WT) is a method for obtaining harmonic
the accuracy of fault detection and diagnosis. components. It employs a mother wavelet instead of
In this study, in order to make full use of the advantages of orthogonal sine and cosine functions in order to extract
EWT, fuzzy entropy and SVM, a new fault diagnosis method frequency components. A dyadic frequency filter is used to
is proposed for motor bearing. Firstly, the EWT method is obtain the high frequency and low frequency components.
used to adaptively decompose vibration signal into a number The low frequency components are decomposed into higher
of AM-FM components. Next, the values of fuzzy entropy of frequency components. It is possible to obtain signal levels at
AM-FM components are calculated in order to generate frequency bands instead of exact components. The advantage
feature vectors, which are fed into the SVM model to train of WT method is simple calculation and it can be completed
and construct a SVM classifier for fulfilling fault pattern in less time. Generally, the WT method can be described as
recognition. Finally, the effectiveness of the proposed follow:
method is validated by using the simulated signal and real
motor bearing vibration signals. The fault diagnosis results F (a, b) f ( x) (*a , b ) ( x)dx (2)
are compared with the other fault diagnosis methods in the where the * is the complex conjugate symbol, and the
literatures. is a function, which can arbitrarily be chosen that it
II. METHODS AND TECHNIQUES
obeys certain rules.
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2018.2834540, IEEE
Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
3) EMPIRICAL WAVELET TRANSFORM Parameter can ensure that there is no overlap between
The EWT method was proposed by Gilles to obtain two consecutive transition areas. So the parameter must
adaptive wavelet capable for identifying and extracting meet the following equation:
AM-FM components of a signal. The main idea is to extract n
the signal modes by constructing an appropriate wavelet min n ( n1 ) (7)
n1 n
filter bank. In the EWT method, the Fourier frequency
spectrum is normalized and separated into the number of The EWT method is defined by the similar way with
intervals, then the compactly supported orthonormal wavelet transform. The detailed coefficients W f (n, t ) are
wavelet basis is explicitly constructed in each interval. given by the inner products with empirical wavelets:
Hence, the segmentation operation on the Fourier spectrum W f (n, t ) f , n f ( ) n ( t )d (8)
is the important step to make the wavelet adaptive to the And the approximation coefficients W f (0, t ) is given by
signal. Firstly, the local maxima in the Fourier spectrum of the inner products with scaling function:
the analyzed signal is detected. Then the spectrum based on
the detected maxima is segmented. Lastly, a corresponding W f (0, t ) f , 1 f ( )1 ( t )d (9)
wavelet filter bank is constructed. Then the reconstruction signal and empirical mode are
Assuming that a signal consists of N components and given as follows:
each component is well separated in Fourier spectrum. Its N
Fourier spectrum is divided into N segments, and each f (t ) W f (0, t ) * 1 (t ) W f (n, t ) * n (t ) (10)
n 1
segment is corresponding to one mode. n is the boundary
limits between each segments, 0 =0 and N = . f 0 (t ) W f (0, t ) * 1 (t ) (11)
Partitioning of Fourier axis is shown Figure 1. For each n ,
f k (t ) W f (k , t ) * k (t ) (12)
the transition phase( Tn ) with the 2 n width is defined as the
center. n is set as n n ( 0 1 ) in order to B. FUZZY ENTROPY
simplify the equation. Entropy is a general concept, and it is used to measure the
uncertainty of one system or a piece of information. Fuzzy
degree is a quantitative index to describe the degree of
fuzzy set. Fuzzy entropy is a method based on the concept
of approximate entropy and sample entropy to measure the
complexity of time series [47]. The fuzzy entropy is
described as follows:
(1) Give a sample time series with N {u (i ) : 1 i N } .
FIGURE 1. Partitioning of Fourier axis For given m , n and r , a vector set
The empirical scaling function and wavelets are defined as { X im , i 1,2, ... , N m 1} is formed. Each vector contains
follows:
m sequential elements from u (i ) .
1 if | |(1 )n (3)
ˆn ( ) cos[ (
1
(| | (1 )n ))] if (1 )n | | (1 )n X im {u (i ), u (i 1),, u (i m 1)} u 0 (i ) (13)
2 2n
0 otherwise where u0 (i ) is the average of X im .
1 if (1 )n | |(1 )n1 1 m1
cos[ ( 1 (| | (1 )n1))] (4)
u 0 (i ) u (i j ) (14)
if (1 )n1 | |(1 )n1 m j 0
2 2n1
ˆn() (2) For certain vector X im , the distance d ijm between X im
sin[ ( )(| | (1 ) )] if (1 )n | | (1 )n
2 2n n
and X mj ( j 1,2,3,, N m, i j ) is defined as the
0 otherwise
maximum absolute difference of corresponding scalar
The function (x) is an arbitrary C k [0,1] function, components.
0 if x 0 and (x) (1 x) 1 x [0,1] (5) dijm d[Xim, X mj] max (u(i k) u0 (i))(u( j k) u0 ( j)) (15)
(x) k(0,m1)
1 if x 0
(3) Give n and r , the similarity degree Dijm of X mj to
Many polynomial functions meet these properties. The
following polynomial was firstly suggested by Daubechies X im is calculated by using a fuzzy function (d ijm , n, r ) ,
and used by Gilles. In 2 ( d ijm / r ) n
Dijm (n, r ) (d ijm , n, r ) e (16)
( x) x 4 (35 84 x 70 x 2 20 x 3 ) (6)
(4) Define the function . m
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2018.2834540, IEEE
Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
1 N m 1 N m
x(t ) x1 (t ) x2 (t ) x3 (t ) x4 ( x) x5 ( x)
m (n, r ) ( Dijm )
N m i 1 N m! j 1, j i
(17)
x1 (t ) 36cos(30t)
(5) Similarly, { X im1 }is formed and the function m 1 is x2 (t ) 10 sin(150t )
(21)
obtained. x3 (t ) 60sin(340t )
1 N m 1 N m x4 (t ) 25 cos(520t )
m1 (n, r ) ( Dijm1 )
N m i 1 N m! j 1, j i
(18)
x5 (t ) 130 sin(600t )
(6) Fuzzy entropy of sequence {u (i ) : 1 i N } for the The time domain waveforms of five components and the
negative natural logarithm of the deviation is defined as simulated signal are displayed in Figure 2. The sampling
follow. frequency is 1024Hz and data length is 512.
50
x1
0
N -50
10
0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 0.45 0.5
x2
0
-10
0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 0.45 0.5
x3
FuzzyEn (m, n, r ) ln m ( n, r ) ln m1 (n, r ) (20) -100
50
0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 0.45 0.5
x4
-50
0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 0.45 0.5
x5
0
0
x
between itself and those points in lying nearest to it. The For the comparison, the EWT and EMD methods are
hyperplane should be used as the basis for classifying employed to decompose the simulated signal. The
unknown data. Therefore, the SVM was widely applied in segmentation of the frequency spectrum and extracted
pattern recognition, nonlinear system identification, modes are obtained by EWT method in Figure .3. and
modeling, predication and control and so on [48-51]. Figure 4. The extracted modes are obtained by EMD
method in Figure 5.
The SVM is mainly used to solve the binary
classification problem. The basic theory was originally
derived from data classification. It is to find one division
plane with meeting the given requirement in order to keep
the point of the training set far away the plane. The SVM
originated from the optimal classification surface from the
linearly separable circumstance. It is used to solve the
linear constrained quadratic programming problem by
mapping the input space into the high dimensional inner
product space to obtain the global optimal solution and
guarantee the convergence speed and avoid the local FIGURE 3. Segmentation of frequency spectrum by EWT method
minimum value. 50
A M -F M 1
-50
0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 0.45 0.5
follow.
200
A M -F M 5
-200
0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 0.45 0.5
Time(s)
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2018.2834540, IEEE
Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
200
Therefore, the EWT method is more robust to the noise, and
IMF1
0
-200
100
IMF2
0
-100
0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 0.45 0.5 EMD method. The EWT method has better performance in
dealing with multi-component signal, and can effectively
20
IMF3
0
-20
0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 0.45 0.5
0
-50
0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 0.45 0.5
1
IV. A NOVEL FAULT DIAGNOSIS METHOD BASED ON
IMF5
0
-1
0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 0.45 0.5
2
EWT, FUZZY ENTROPY AND SVM
The experiment vibration data comes from Bearing Data
IMF6
0
-2
0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 0.45 0.5
2
Center of Case Western Reserve University [52]. The 6205-
IMF7
0
-2
200
0
inches inches inches inches inches
-100
-200
According to the theoretical calculation values of fault
feature frequency, the faults of outer race, inner race and
-300
0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 0.45 0.5
Time(s)
200
100
Chandra et al. [54] gave the calculation method of fault
Amplitude
-100
-200
-300
0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 0.45 0.5
calculated results are shown in TABLE II.
Time(s)
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2018.2834540, IEEE
Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2018.2834540, IEEE
Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2018.2834540, IEEE
Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
2 140
Amplitude(m /s 2 )
Amplitude(m/s 2 )
0.5 80
0.1
Amplitude(m/s 2)
Amplitude(m/s 2)
most reasonable initial values. These selected values of the
25
0
20
-0.2
15
1.5, respectively. FIGURE 15. Time-domain signal and its corresponding frequency
spectrum of fault vibration signal of rolling element
2) SPLIT FOURIER SPECTRUM AND SELECT
C. THE REALIZATION STEPS OF EWTFSFD
FREQUENCY BAND
1) ORIGINAL VIBRATION SIGNAL AND FREQUENCY The EWT method provides the adaptability with respect to
SPECTRUM the analyzed signal. At same time, in the EWT method,
The experimental vibration signals are firstly analyzed to how to effectively segment Fourier spectrum is very
validate the effectiveness of the EWTFSFD method for important study work. The goal of segmentation is to
bearing fault diagnosis. Data set consists of 160 data separate different portions of the spectrum, which
samples of normal condition, outer race fault, inner race correspond to the different centered modes with specific
fault and rolling element fault under no-load. Each frequency of compact support. So it is a key technical
condition includes 40 data samples. 20 data samples are difficulty to segment Fourier spectrum in engineering
used as training data, and 20 data samples are used as applications. Assuming that a signal consists of N mono-
testing data. The first data in each data set is used to components and each component is well separated in
analyze in detail. The time-domain signals and Fourier spectrum. The Fourier spectrum is divided
corresponding frequency spectrums are shown in Figure into N segments, each corresponding to one mode.
12.~Figure 15. 0.3 70 i (i 1,2,3,..., N ) is denoted to be the boundary between
0.2 60 each segments, the started boundary is 0 and the end
0.1 50
boundary is n . This implies that a total of N 1 extra
boundaries are required to find. In order to find N 1
Amplitude(m/s 2)
Amplitude(m/s 2)
0 40
-0.1 30
boundaries, the N will be determined. Gilles[31] proposed
-0.2 20
a threshold method to determine the value of N . {M i }kM1
is the magnitude of the detected local maximum points in
the frequency domain. Then these values are sorted
-0.3 10
90
( (0,1) ) is relative amplitude ratio. For certain , the
1
80
number of maximum points greater than threshold value is
0.5
70
defined N , and the maximum points of the former N is
used to solve the boundary.
60
Amplitude(m/s 2)
Amplitude(m/s 2 )
0 50
10
-1.5
0 0.02 0.04 0.06 0.08 0.1 0.12 0.14 0.16
0
0 1000 2000 3000 4000
Frequency(Hz)
5000 6000 7000 more, and the frequencies of some local maximum values
are very close. If all local maximum points are selected to
Time(s)
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2018.2834540, IEEE
Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
45
Magnitude
b) Propose a compromise method between the 20
a) The magnitude threshold is set as 30%. That is to As can be seen from Figure 16., it could be found that the
remove the local maximum points of amplitude below low frequency components occupy larger proportion. The
magnitude threshold(30%). whole spectrum is divided into three regions and three
b) The frequency threshold is set as 8 Hz. That is to different frequency bands are obtained in total. As can be
combine two adjacent maxima with interval width less than seen from Figure17., it could be found that the intermediate
8 Hz. frequency components occupy larger proportion. The whole
When the selection of the local maximum points is spectrum is divided into four regions and three different
completed, the boundary is the center of two adjacent local frequency bands are obtained in total. As can be seen from
maximum points. Fourier spectrum and selected frequency Figure 18., it could be found that the low and intermediate
band are shown in Figure 16.~Figure 19. The dotted line is frequency components occupy larger proportion. The whole
the obtained boundary in these figures. spectrum is divided into thirteen regions and thirteen
70 different frequency bands are obtained in total. As can be
60
seen from Figure 19., it could be found that the low and
intermediate frequency components occupy larger
50
proportion. The whole spectrum is divided into ten regions
40
and ten different frequency bands are obtained.
Magnitude
90
0.3
0.2
AM-FM1
80
0.1
0
70
-0.1
0 0.02 0.04 0.06 0.08 0.1 0.12 0.14 0.16
-3
60 x 10
5
Magnitude
AM-FM2
50
0
40 -5
0 0.02 0.04 0.06 0.08 0.1 0.12 0.14 0.16
30 0.15
0.1
AM-FM3
20
0.05
0
10
-0.05
0 0.02 0.04 0.06 0.08 0.1 0.12 0.14 0.16
Time(s)
0
0 1000 2000 3000
Frequency (Hz)
4000 5000 6000 7000
FIGURE 20. Extracted modes for normal signal
0.5
FIGURE 17. Fourier spectrum and selected frequency band of fault
AM-FM1
0
vibration signal of outer race
-0.5
120 0 0.02 0.04 0.06 0.08 0.1 0.12 0.14 0.16
0.1
100
AM-FM2
80 -0.1
0 0.02 0.04 0.06 0.08 0.1 0.12 0.14 0.16
Magnitude
0.05
60
AM-FM3
40 -0.05
0 0.02 0.04 0.06 0.08 0.1 0.12 0.14 0.16
0.1
20
AM-FM4
0 -0.1
0 1000 2000 3000 4000 5000 6000 7000 0 0.02 0.04 0.06 0.08 0.1 0.12 0.14 0.16
Frequency (Hz) Time(s)
FIGURE 18. Fourier spectrum and selected frequency band of fault FIGURE 21. Extracted modes for fault vibration signal of outer race
vibration signal of inner race
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2018.2834540, IEEE
Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
FIGURE 23. Extracted modes for fault vibration signal of rolling element
TABLE IV
Fuzzy entropy values for fault vibration signal of outer race
NO. AM-FM1 AM-FM2 AM-FM3 AM-FM4 AM-FM5 AM-FM6 AM-FM7 AM-FM8
1 18.2683 3.367 4.1124 5.43 0 0 0 0
2 27.3231 0.6371 3.3588 3.8643 2.1886 9.3481 0 0
... ... ... ... ... ... ... ... ...
19 46.4064 0.8942 4.3507 1.8425 3.9928 0.6988 7.1575 0
... ... ... ... ... ... ... ... ...
39 38.632 0.754 4.2778 4.7607 0.7095 5.2605 0 0
40 17.2208 3.4741 5.0154 0 0 0 0 0
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2018.2834540, IEEE
Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
TABLE V
Fuzzy entropy values for fault vibration signal of inner race
NO AM- AM- AM- AM- AM- AM- AM- AM- AM- AM- AM- AM- AM- AM-
. FM1 FM2 FM3 FM4 FM5 FM6 FM7 FM8 FM9 FM10 FM11 FM12 FM13 FM14
1 2.5039 0.1843 0.1568 0.1299 0.4462 1.4816 0.6898 1.5806 1.7288 3.5671 8.3556 8.8272 20.9354 0
2 2.5641 0.2157 0.1707 0.1263 0.4283 0.3574 0.7371 0.8766 1.9536 2.9969 6.8966 8.6242 19.694 0
... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
19 1.7208 0.2188 0.1672 0.0917 0.1442 0.2595 0.7993 0.5418 0.825 1.657 2.8614 6.9673 7.7769 20.2835
... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
39 2.0915 0.2132 0.3247 2.3553 0.7527 3.9039 1.7234 3.3647 9.8304 8.9222 20.1835 0 0 0
40 2.7898 0.2221 0.2856 1.4043 0.8141 1.0309 1.6839 3.6083 8.2804 9.5573 0 0 0 0
TABLE VI
Fuzzy entropy values for fault vibration signal of rolling element
NO. AM-FM1 AM-FM2 AM-FM3 AM-FM4 AM-FM5 AM-FM6 AM-FM7 AM-FM8 AM-FM9 AM-FM10 AM-FM11 AM-FM12 AM-FM13
1 0.5594 0.069 0.0511 0.1302 0.724 0.6123 0.7549 0.9736 0.8992 1.1813 1.168 1.4437 0
... ... ... ... ... ... ... ... ... ... ... ... ... ...
8 0.2142 0.0269 0.0691 0.1257 0.5177 0.7578 0.9242 0.9089 1.864 0.9947 0.916 1.2841 2.0743
... ... ... ... ... ... ... ... ... ... ... ... ... ...
19 9.3939 1.7529 1.8966 1.5913 2.0483 0 0 0 0 0 0 0 0
... ... ... ... ... ... ... ... ... ... ... ... ... ...
39 8.8117 0.8651 0.4381 0.8285 1.2855 1.6908 1.7177 1.5223 1.3898 0 0 0 0
40 9.276 1.9436 1.1639 1.7804 2.2951 1.4294 0 0 0 0 0 0 0
5) TRAIN SVM MODEL obtained expectation classification result of SVM. The RBF
For actual fault diagnosis of motor bearing, it is a small is selected as the kernel function of SVM.
sample and high dimension problem. In order to illustrate 6) TEST AND OUTPUT THE RESULTS
the effectiveness of the EWTFSFD method, the SVM with In the classification experiment, the feature vectors T of
small sample and short training time is selected as a testing samples are gradually input into the trained SVM1.
classifier in here. The obtained values of fuzzy entropy are If the output of SVM1 is zero, then the normal bearing is
selected as feature vectors. That's to say, T=[AM-FM1,AM- determined and the testing experiment ends. Otherwise the
FM2, AM-FM3, ...,AM-FMn-1,AM-FMn]. Then the feature testing samples are input into the trained SVM2. If the
vectors T are input into SVM model to train the SVM output of SVM2 is zero, then the fault bearing of outer race
model and obtain a SVM classifier. According to the above is determined and the testing experiment ends. Otherwise,
method, 160 feature vectors are obtained. For each the testing samples are input into the trained SVM3. If the
vibration signal(40 samples), 20 samples are randomly output of SVM3 is zero, then the fault bearing of inner race
selected as training samples and the rest 20 samples are is determined, otherwise the fault bearing of rolling element
selected as testing samples. Because there are four different is determined. The detailed diagnosis processes do not list
vibration signals, it is necessary to establish three two- one by one. The results of testing samples are show in
classifiers. The established multi-fault classifier is TABLE VII.
described in Figure 24. TABLE VII
Diagnosis results of testing samples
Test Correct Wrong Correctness
f ( x) 0 ? f ( x) 0 ? f ( x) 0 ? States
samples number number rate (%)
Normal signal 20 20 0 100
Fault vibration signal of
20 18 2 90
outer race
Fault vibration signal of
20 20 0 100
FIGURE 24. Multi-fault classifier inner race
Fault vibration signal of
In Figure 24., SVM1 is a classifier to determine the 20 19 1 95
rolling element
normal bearing or fault bearing. SVM2 is a classifier to
determine the fault bearing of outer race or other fault D. EXPERIMENT RESULTS
bearing. SVM3 is a classifier to determine the fault bearing In order to verify the effectiveness of proposed EWTFSFD
of inner race or rolling element. f ( x) 0 represents the method for motor bearing, the fault diagnosis method based
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2018.2834540, IEEE
Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
As can be seen from TABLE VI and TABLE IX, for VI. CONCLUSION AND FUTURE RESEARCH
normal vibration signal, it can be seen that the proposed In the past decades, various methods and techniques have
EWTFSFD method and EMDFSFD method have the same been proposed to diagnose the faults of motor bearing.
testing accuracy of 100%. The testing accuracy of proposed These methods and techniques have their own shortcomings
EWTFSFD method is 100% for fault vibration signal of in fault diagnosis. A novel fault diagnosis method based on
inner race. For all fault vibration signals of motor bearing, integrating EWT, fuzzy entropy and SVM is proposed to
it can be seen that the testing accuracy of proposed identify fault of motor bearing. The EWT method breaks
EWTFSFD method is higher than the EMDFSFD method through the limits of pre-defined dyadic scheme of
in the experiments. At same time, it is difficult to determine traditional DWT and allows to segment Fourier spectrum. It
the faults between inner race and rolling element, and is used to decompose vibration signal into several empirical
between inner race and outer race for motor bearing. But modes with physical meanings and extract a series of AM-
for the proposed EWTFSFD method, it can obtain FM components with supporting Fourier spectrum under an
outstanding diagnosis results. Thus, we believe that the orthogonal basis. Then fuzzy entropy is used to extract the
performance and overall diagnostic capability of the values of fuzzy entropy of AM-FM components in order to
proposed EWTFSFD method outperforms the EMDFSFD construct a feature vectors, which are used to train SVM
method. model for obtaining SVM classifier. The effectiveness of
the EWT method is firstly validated by using simulated
E. ANALYSIS OF SELECTED METHOD FOR signal. The proposed fault diagnosis method had been
MAGNITUDE THRESHOLD applied to identify the motor bearing fault(normal signal,
The section mainly analyzes the effects of selected method outer race fault signal, inner race fault signal, and rolling
for magnitude threshold. The magnitude thresholds are 30% element fault signal). Some attractive features of the EWT
and 40%, respectively, which are selected to study and method and proposed fault diagnosis method are
analyze the fault diagnosis results in detail in the summarized as follows:
experiment. The correctness rates of fault diagnosis under 1) The EWT method breaks through the limitations of
two conditions are obtained and shown in TABLE X. traditional DWT method and allow to adaptively
segment Fourier spectrum. It can effectively extract the
AM-FM components with supporting Fourier spectrum
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2018.2834540, IEEE
Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
from vibration signals with strong noise. [15] Y. Guo, J. Na , B. Li, R.F. Fung, “Envelope extraction based
dimension reduction for independent component analysis in fault
2) Fuzzy entropy can easily and clearly calculate the diagnosis of rolling element bearing,” J. Sound Vib., vol. 333, no.13,
values of fuzzy entropy of extracted modes. pp. 2983-2994, 2014.
3) The analysis results from experimental signals with [16] S.J. Dong, B.P. Tang, Y. Zhang, “A repeated single-channel
mechanical signal blind separation method based on morphological
simulated signal indicates that the EWT method filtering and singular value decomposition,” Measurement, vol. 45,
outperforms the EMD method, and the proposed no.8, pp. 2052-2063, 2012.
EWTFSFD method can accurately and effectively [17] X.M. Xue, J.Z. Zhou, Y.H. Xu, W.L. Zhu, C.S. Li, “An adaptively
diagnose the different faults of motor bearing. fast ensemble empirical mode decomposition method and its
applications to rolling element bearing fault diagnosis,” Mech. Syst.
4) The proposed EWTFSFD method outperforms the Signal Pr., vol. 62-63, pp. 444-459, 2015.
EMDFSFD method and the method based on EWT and [18] G. Cheng, X.H. Chen, X.L. Shan, H.G. Liu , C.F. Zhou, “A new
Hilbert transform. method of gear fault diagnosis in strong noise based on multi-sensor
information fusion,” J. Vib. Control, vol.22,no.6, pp. 1504-1515,
Moreover, there are also some problems of EWT method, 2016.
such as how to adaptively segment Fourier spectrum, select [19] P. Jayaswal, S.N. Verma, A.K. Wadhwani , “Development of EBP-
the optimal filter banks, and so on. In future work, we will Artificial neural network expert system for rolling element bearing
fault diagnosis,” J. Vib. Control, vol.17,no.8, pp. 1131-1148, 2011.
continue to study how to better adaptively segment the [20] A. Widodo, E.Y. Kim, J.D. Son, B.S. Yang, A.C.C. Tan, D.S. Gu,
spectrum and further combine EWT method with other B.K. Choi, J. Mathew , “Fault diagnosis of low speed bearing based
diagnosing technologies, optimizing parameter methods and on relevance vector machine and support vector machine,” Expert
Syst. Appl., vol. 36, no.3, pp. 7252-7261, 2009.
so on. [21] Y.H. Hu, C. Gan, W.P. Cao, W.H. Li, S. Finney, “Central-tapped
node linked modular fault tolerance topology for SRM based
REFERENCES EV/HEV applications,” IEEE T. Power Electr., vol. 31, no.2, pp.
[1] R.B. Randall, J. Antoni, “Rolling element bearing diagnostics-- 1541 - 1554, 2016.
Atutorial,” Mech. Syst. Signal Pr., vol. 25, no. 2, pp. 485-520, 2011. [22] Q. Liu, W.D. Cai, J. Shen, Z.J. Fu, X.D. Liu, N. Linge , “A
[2] Y.H. Hu, C. Gan, Q.G. Sun, P. Li, J.H. Wu, “Modular tri-port high- speculative approach to spatial-temporal efficiency with multi-
power converter for SRM based plug-in hybrid electrical trucks. objective optimization in a heterogeneous cloud environment,”
IEEE T. Power Electr., vol. 33, no. 4, pp. 3247-3257, 2018. Secur . Commun. Netw., vol.9, no.17, pp. 4002-4012, 2016.
[3] S.B. Wang, G.G. Cai, Z.K. Zhu, W.G. Huang, X.W. Zhang, [23] W. Deng, H.M. Zhao, L. Zou, G.Y. Li, X.H. Yang, D.Q. Wu, “A
“Transient signal analysis based on Levenberg-Marquardt method for novel collaborative optimization algorithm in solving complex
fault feature extraction of rotating machines,” Mech. Syst. Signal Pr., optimization problems”, Soft Comput., vol. 21, no. 15, pp. 4387-
vol. 54-55, pp. 485-520, 2015. 4398,2017.
[4] S.D. Wu, P.H. Wu, C.W. Wu, J.J. Ding, C.C. Wang, “Bearing fault [24] W. Deng, H.M. Zhao, X.H. Yang, J.X. Xiong, M. Sun, B. Li, “Study
diagnosis based on multiscale permutation entropy and support on an improved adaptive PSO algorithm for solving multi-objective
vector machine,” Entropy, vol. 14, no.8, pp. 1343-1356, 2012. gate assignment”, Appl. Soft Comput., vol.59, pp. 288-302,2017.
[5] Y.H. Hu, J.F. Zhang, W.P. Cao, J.D. Wu, G.Y. Tian, S.J. Finney, [25] B. Gu, X.M. Sun, V.S. Sheng , “ Structural minimax probability
J.L .Kirtley, “Online two-section PV array fault diagnosis with machine, IEEE T. Neural Networ., vol.28, no.7, pp. 1646-1656, 2017.
optimized voltage sensor locations,” IEEE T. Ind..Electron., vol.62, [26] H. Rong, T.H. Ma, M.L. Tang, J. Cao , “A novel subgraph K+ -
no.11, pp. 7237-7246, 2015. isomorphism method in social network based on graph similarity
[6] S.D. Wu, C.W. Wu, K.Y. Lee, S.G. Lin, “Modified multiscale detection,”Soft Comput., vol.22, no.8, pp. 2583–2601, 2018.
entropy for short-term time series analysis,”Physica A, vol.392, [27] H.M. Zhao, M. Sun, W. Deng, X.H. Yang, “A new feature extraction
no.23, pp. 5865-5873, 2013. method based on EEMD and multi-scale fuzzy entropy for motor
[7] P.E. William, M.W. Hoffman, “Identification of bearing faults using bearing,” Entropy, vol.19, no.1, pp. 1-12, 2017.
time domain zero-crossings,” Mech. Syst. Signal Pr., vol. 25, no. 8, [28] B.J. Chen, J.H. Yang, B. Jeon, X.P. Zhang, “Kernel quaternion
pp. 3078-3088, 2011. principal component analysis and its application in RGB-D object
[8] A.B. Ming, Z.Y. Qin, W. Zhang, F.L. Chu, “Spectrum auto- recognition,” Neurocomputing, vol.266, pp. 293-303, 2017.
correlation analysis and its application to fault diagnosis of rolling [29] B.W. Wang, X.D. Gu, L. Ma, S.S. Yan. , “Temperature error
element bearings,” Mech. Syst. Signal Pr., vol. 41, no. 1-2, pp. 141- correction based on BP neural network in meteorological WSN,” Int.
154, 2013. J. Sens. Netw., vol.23, no.4, pp. 265-278, 2017.
[9] B.J. van Wyk, M.A. van Wyk, G. Qi, “Difference Histograms: A [30] W. Deng, R. Yao, H.M. Zhao, X.H. Yang, G.Y. Li , “A novel
new tool for time series analysis applied to bearing fault diagnosis,” intelligent diagnosis method using optimal LS-SVM with improved
Pattern Recogn. Lett., vol. 30, no.6, pp. 595-599, 2009. PSO algorithm,” Soft Comput.,2017,DOI: 10.1007/s00500-017-
[10] A.A.K. Mohsen, M.F. Abu El-Yazeed, “Selection of input stimulus 2940-9
for fault diagnosis of analog circuits using ARMA model,”AEU- Int. [31] L.Z. Xiong, Z.Q. Xu, Y.Q. Shi , “An integer wavelet transform based
J. Electron. C., vol.58, no.3, pp. 212-217, 2004. scheme for reversible data hiding in encrypted images,” Multidim.
[11] Y.K. Liu, L.W. Guo, Q.X. Wang, G.Q. An, M. Guo, H. Lian, Syst. Sign. P., vol.29, no.3, pp. 1191-1202, 2018.
“Application to induction motor faults diagnosis of the amplitude [32] Y.H. Zhang, X.M. Sun, B.W. Wang , “Efficient algorithm for K-
recovery method combined with FFT,” Mech. Syst. Signal Pr., vol. barrier coverage based on integer linear programming,” China
24, no. 8, pp. 2961-2971, 2010. Commun., vol.13, no.7, pp. 16-23, 2016.
[12] R. Rubini, U.Meneghetti , “Application of the envelope and wavelet [33] Z.G. Qu, J. Keeney, S. Robitzsch, F. Zaman, X.J. Wang, “Multilevel
transform analyses for the diagnosis of incipient faults in ball pattern mining architecture for automatic network monitoring in
bearings,” Mech. Syst. Signal Pr., vol. 15, no.2, pp. 287-302, 2001. heterogeneous wireless communication networks,” China Commun.,
[13] Q. Gao, C. Duan, H. Fan, Q. Meng, “Rotating machine fault vol.13, no.7, pp. 108-116, 2016.
diagnosis using empirical mode decomposition,” Mech. Syst. Signal [34] R.H. Jiang, S.L. Liu, Y.F. Tang, Y.H. Liu. , “A novel method of fault
Pr., vol. 22, no. 5, pp. 1072-1081, 2008. diagnosis for rolling element bearings based on the accumulated
[14] A. Widodo, B.S. Yang, T. Han, “Combination of independent envelope spectrum of the wavelet packet,” J. Vib. Control, vol.21,
component analysis and support vector machines for intelligent faults no.8, pp. 1580-1593, 2015.
diagnosis of induction motors,” Expert Syst. Appl., vol. 32, no.2, pp. [35] J.L. Chen, Z.P. Li, J. Pan, G.G. Chen, Y.Y. Zi, J. Yuan, B.Q. Chen,
299-312, 2007. Z.J. He , “Wavelet transform based on inner product in fault
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2018.2834540, IEEE
Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
diagnosis of rotating machinery: A review,” Mech. Syst. Signal Pr., artificial intelligence, optimization method and fault diagnosis.
vol. 70-71, pp. 1-35, 2016.
[36] B.M. Ebrahimi ,J. Faiz, S. Lotfi-Fard, P. Pillay, “Novel indices for SHENGJIE ZHANG (M’92), received the B.S.
broken rotor bars fault diagnosis in induction motors using wavelet degree in Electrical Engineering and Its
transform,” Mech. Syst. Signal Pr., vol. 30,no.7, pp. 131-145, 2012. Automation from Hebei University of Engineering,
[37] R.Q. Yan, R.X. Gao, X.F. Chen , “Wavelets for fault diagnosis of Handan, China, in 2015. From 2016 to now, he was
rotary machines: a review with applications,” Signal Process., vol. 96, a graduate students at School of Electronics and
pp. 1-15,2014. Information Engineering, Dalian Jiaotong
[38] N.E. Huang, Z. Shen, S.R. Long, “The empirical mode University, Dalian, China. His research interest
decomposition and the Hilbert spectrum for nonlinear and non- includes artificial intelligence, fault diagnosis.
stationary time series analysis,” Proc. R. Soc. Math. Phys. Eng. Sci.,
vol. 454, pp. 903-995,1998.
[39] J.H. Ahn, D.H. Kwak, B.H. Koh, “Fault detection of a roller-bearing HUIMIN ZHAO (F’77), received the B.S. degree in
system through the EMD of a wavelet denoised signal,”Sensors, vol. Electrical Technology from Dalian Jiaotong
14, no.8, pp. 15022-15038,2014. University, Dalian, China, in 2000, the M.S. degree
[40] J. Gilles, “ Empirical wavelet transform,” IEEE T. Signal Proces., in Traffic information engineering and control from
vol. 61, no.1, pp. 3999-4010,2013. Dalian Jiaotong University, Dalian, China, in 2004
[41] S.F. Zhao, L. Liang, G.H. Xu, J. Wang, W.M. Zhang , “Quantitative and Ph.D. degree in mechanical engineering from
diagnosis of a spall-like fault of a rolling element bearing by Dalian Maritime University, Dalian, China, in 2013.
empirical mode decomposition and the approximate entropy From 2012 to now, she was a Professor with the
method,” Mech. Syst. Signal Pr., vol. 40,no.1, pp. 154-177, 2013. Software Institute, Dalian Jiaotong University,
[42] M.D. Han, J.L. Pan , “A fault diagnosis method combined with LMD, Dalian, China. Her research interest includes artificial intelligence, signal
sample entropy and energy ratio for roller bearings,” Measurement, processing and fault diagnosis.
vol.76, pp. 7-19, 2015.
[43] Zheng JD, Cheng JS, Yang Y. , “A rolling bearing fault diagnosis
XINHUA YANG (M’69), received the B.S. degree
approach based on LCD and fuzzy entropy,” Mech. Mach. Theory,
in Mechanical Engineering from Dalian Jiaotong
vol.70, pp. 441-453, 2013.
University, Dalian, China, in 1992, the M.S. degree
[44] V. Vapnik The Nature of Statistical Learning Theory. New York;
in mechanical engineering from Dalian Jiaotong
Springer Verlag,1995.
University, Dalian, China, in 1998 and Ph.D.
[45] Y.G. Lei, J. Lin, Z.J. He, J.M. Zuo , “A review on empirical mode
degree in mechanical engineering from Dalian
decomposition in fault diagnosis of rotating machinery,” Mech. Syst.
University of Technology, Dalian, China, in 2003.
Signal Pr., vol. 35, no.1-2, pp. 108-126, 2013.
From 2007 to now, he was a Professor with the
[46] A. Grossman, J. Morlet , “Decomposition of Hardy functions into
Liaoning Key Laboratory of Welding and
square integrable wavelets of constant shape,” SIAM J. Math. Anal.,
Reliability of Rail Transportation Equipment,
vol. 15, no.4, pp. 723-736, 1984.
Dalian Jiaotong University, Dalian 116028, China. His research interest
[47] H.Y. Zhang, S.Y. Yang , “Inclusion measure for typical hesitant
includes artificial intelligence.
fuzzy sets, the relative similarity measure and fuzzy entropy,” Soft
Comput., vol. 20, no.4, pp. 1277-1287, 2016.
[48] B. Gu, V.S. Sheng, K.Y. Tay, W. Romano, S. Li, “Incremental
support vector learning for ordinal regression,” IEEE T. Neural
Networ., vol.26, no.7, pp. 1403-1416, 2015.
[49] B. Gu, V.S. Sheng , “A Robust regularization path algorithm for ν-
support vector classification,” IEEE T. Neural Networ., vol.26, no.5,
pp. 1241-1248, 2015.
[50] X.Y. Zhang, J.Z. Zhou , “Multi-fault diagnosis for rolling element
bearings based on ensemble empirical mode decomposition and
optimized support vector machines,” Mech. Syst. Signal Pr., vol.
41,no.1-2, pp. 127-140, 2013.
[51] Y. Xue, J.M. Jiang, B.P. Zhao, T.H. Ma, “A self-adaptive artificial
bee colony algorithm based on global best for global optimization,”
Soft Comput., vol. 22,no.9, pp. 2935-2952, 2018.
[52] http://csegroups.case.edu/bearingdatacenter/home
[53] X.M. Li, W. Deng, H.M. Zhao, G.H. Zheng , “Study on a novel fault
diagnosis method of rolling bearing in motor,” Recent Patents on
Mechanical Engineering, vol. 9,no.2, pp. 144-152, 2016.
[54] N.H. Chandra, A.S. Sekhar , “Fault detection in rotor bearing
systems using time frequency techniques,” Mech. Syst. Signal Pr.,
vol. 72-73, pp. 105-133, 2016.
2169-3536 (c) 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.