Engineering, 2010, 2, 60-64
doi:10.4236/eng.2010.21008 lished Online January 2010 (http://www.SciRP.org/journal/eng/). Pub
Research on Early Fault Self-Recovery Monitoring of
Aero-Engine Rotor System
Zhongsheng WANG, Shiwe MA
School of Aeronautics Northwestern Polytechnical University Xi’an, China
Received August 19, 2009; revised September 14, 2009; accepted September 20, 2009
Abstract
In order to increase robustness of the AERS (Aero-engine Rotor System) and to solve the problem of lacking
fault samples in fault diagnosis and the difficulty in identifying early weak fault, we proposed a new method
that it not only can identify the early fault of AERS but also it can do self-recovery monitoring of fault. Our
method is based on the analysis of the early fault features on AERS, and it combined the SVM (Support
Vector Machine) with the stochastic resonance theory and the wavelet packet decomposition and fault
self-recovery. First, we zoom the early fault feature signals by using the stochastic resonance theory. Second,
we extract the feature vectors of early fault using the multi-resolution analysis of the wavelet packet. Third,
we input the feature vectors to a fault classifier, which can be used to identify the early fault of AERS and
carry out self-recovery monitoring of fault. In this paper, features of early fault on AERS, the zoom of early
fault characteristics, the extraction method of early fault characteristics, the construction of multi-fault clas-
sifier and way of fault self-recovery monitoring are studied. Results show that our method can effectively
identify the early fault of AERS, especially for identifying of fault with small samples, and it can carry on
self-recovery monitoring of fault.
Keywords: AERS, Early Fault, Support Vector Machine, Classification Identification of Fault, Self-Recovery
Monitoring of Fault
1. Introduction
With the development of the modern aviation industry,
the safety of aircraft and reliability are more and more
attracted. The engine is heart of aircraft and AERS is
central part of engine. If AERS has fault in flight, the
aircraft would be severely threatened in safety. Because
the structure of AERS is complex, load is bigger and the
change of operation conditions is frequency, it will be
the more difficult in the fault identification. Especially in
the early failures occurred, if we can catch timely the fault
information, and can effectively identify it and carry on
self-recovery monitoring of fault, it will have important
significance to eradicate or eliminate the potential fault
caused of an accident. Fault identification on AERS is
widely studied and many results are obtained [1−3]. At
present now, effective identification of early fault has
more difficulty. In particular, obtaining of the early fault
information is more difficulty, and effectiveness of fault
identification is not satisfactory. Because operation of
AERS is in strong noise density, the early fault informa-
tion is very weak and signals are easily flooded in noises,
satisfactory results are very difficult by general methods.
Our method can not only fast identify the early fault of
the AERS but also carry on self-recovery monitory of
fault.
2. Features of Early Fault on AERS
In the flight, the wear, deformation, corrosion and frac-
ture of structure components and effects of work stress,
external environment and human factors will lead to
faults of AERS. The early fault of AERS often shows a
form in micro-cracks, micro-creeping, micro-corrosion
and micro-wear. These faults, with the exception of little
sudden faults, the majority have a development process
from nothing to fault, minor to general, evolution to fast.
In this process, the structure of system, properties and
internal energy will change. We can monitor the early
faults through catching these fault information in time,
*Project (50675178, 60472116) Supported by National Natural Science
Foundation of China

Z. S. WANG ET AL. 61
and it can be identified and be self-recovery. These early
faults of AERS have the following features:
1) Fault signal is very weak. When fault is at early
stage or just sprouted, the changes of the fault signal is
very weak in amplitude, phase and time-frequency char-
acteristics, and the little fault characterization is often
difficult to detect.
2) Fault signal will be drowned by noise signal. Dur-
ing the flight, the noise signal is usually among the fault
signal. When the fault signal is very weak and the noise
signal is very strong, the early fault signal will be
drowned by noise signal. In order to detect the early fault,
we must reduce noise or extracted early fault information
from the noise signal.
3) Fault signal is often a transient one. The damage
structure components of aircraft is generated by impact
loading, and this fault is manifested by transient signal,
such as expansion of early cracks, is a process from
gradual to mutation.
4) Fault occurred in the area of stress concentration.
When area of stress concentration is acted by strong re-
gional load, the fault of structural part is easy occurrence
in the creeping. For the ferromagnetic metal part, the
magnetic memory method can be used for the early fault
detection and localization [4].
5) Fault has volatile. That means sometimes we can
not find the fault trace in fault condition. But with the
change of action or time, the system can recover auto-
matically. Volatile fault can be shown by eventuality
fault, transient fault and interruption fault.
3. Extraction of Early Fault Characreristic
Because the vibration of engine is larger in operation,
fault characteristics of the AERS will be submerged in
the strong background noise in the early. In order to ex-
tract characteristics of early fault from being submerged
signals by noise, we use the stochastic resonance theory
to zoom characteristic signals of early fault [5].
In the failure, the energy of AERS will change in all
frequency bands and different faults have different ef-
fects to the signal energy in each frequency band. So, we
can use wavelet packet to decompose the output signal in
stochastic resonance and select signal energy in the char-
acteristics frequency band as a feature vector.
If the data length of original signal is , the
data length of discrete signals is reduced to
by decomposition of wavelet packet and its en-
ergy can be expressed as:

tx

N
ix mk,
N
k
2
  





N
i
mk
k
mk
n
k
ix
N
xE
2
1
2
,,
12
1
 (1)
where, = the length of original data, = layer num-
ber by wavelet packet decomposition, m = the serial
number of decomposition frequency band location = 0, 1,
2, ...
N k
12

k
m
f
.
The energy within the each frequency band can be cal-
culated by Equation (1) and the feature vector can be
constructed by the energy.
4. Classification Identification of Fault
The SVM can do the classification very well in the few
numbers of fault samples and it can solve the identifica-
tion problems on nonlinear and high-dimensional pattern.
The fault identification of the AERS belongs to prob-
lem of multi-classification and it needs to construct multi-
fault classifier. In this paper, we adopt improved classi-
fication algorithm of the “one-to-many”.
To the classification of K type, way of “one-to-many”
is need to construct K two classifiers. In this way con-
structing every two classifiers, all n training samples of
K type should be operated. In the testing and classifica-
tion, the scale of classifiers is larger and speed is slower.
An improved the “one-to-many” classification algo-
rithm is to construct two classifiers of K, and the training
sample of m type in the K classifiers is and other
types marking is . Established output function
in M classifiers can be expressed as:
1
m
i
y
1
m
i
y
 









 m
SVM
i
m
i
mbxxyx Ksgn i
 (2)
The algorithm overcomes defects that “one-on-one”
approach needs to establish many number classifiers and
it can control the training samples number in traditional
“one-to-many”. Its operate speed is fast and effect of fault
classification is well.
5. Self-Recovery Monitoring of Fault
Fault monitor process of AERS is shown in Figure 1.
Fault self-recovery database consist of many intelligent
models. It can carry on self-recovery monitoring based
on different fault sources and fault characteristics.
Self-recovery monitoring of fault can be realized by
smart structure [6], affixing magnetic field [7], regener-
ating materials [8], etc.
When AERS has fault, the system can not work nor-
mally. Self-recovery model based on the fault compensa-
tion can restore original function of system by means of
the fault self-recovery compensator. If system equations
under normal condition are
)()()( tButAxtx 

 (3)
)()( tCxty

(4)
Compensator equations are
C opyright © 2010 SciRes. ENGINEERING

Z. S. WANG ET AL. 62
AERS
Fault Detection
Classification Identification
Fault
Identification
Database
Can Do
Self-recovery ?
Self-recovery Repair
Fault
Self-recovery
Database
Module Replace
Parts Repair
y
n
Figure 1. Fault self-recovery monitor process of AERS.
When the sensor module detects the fault information,
the signals will transmit to self-recovery module and act
to the controller. Fault of AERS will be restored by smart
structure. It is based on different fault sources and fault
feature, and the fault self-recovery tactics is adopted.
)()()(tEytDztz


 (5)
)()()( tHytFztu  (6)
The system loop equations depicted in (3) and (4) are
)()()()( tBFztxBHCAtx 
 (7) 6. Experimental Results and Its Analysis
)()()( tDztECxtz

  (8)
In order to verify the usefulness of the method, we choose
the four conditions of the AERS. They are normal condi-
tion, early rotor misalignment, early rotor unbalance and
early rotor crack. These signals are preprocessed and the
fault features are extracted. Fault is identified by the
multi-fault classifiers and fault is monitored by self-re-
covery module.
When fault of component or sub-system occurred dur-
ing the flight, the loop feedback equations are
)()()()( tzFBtxCHBAtxffff
 (9)
)()()( tzDtxCEtzf
 (10)
To make the performance of fault system as close as
possible to the performance of the original system, we can
design the appropriate self-recovery compensator

,D
 HFE ,, to achieve the fault self-recovery compensation.
During flight, when the aircraft cockpit, wings and other
important components have severe vibration or chatter,
distributed piezoelectric driver compensator can weaken
or offset the impact of vibration by vibration control and
active vibration absorber.
In the experiment, according to the character of AERS,
we collected 10 group data by the acceleration sensor. They
respectively correspond to the over four conditions in the
1800 rpm. The sampling frequency is 256 Hz and the rota-
tion frequency is 30 Hz. The characteristic frequency of
fault and its concomitant frequency are shown in Table 1.
Figure 3 shows the output waveform of the stochastic
resonance system and its spectrum. The frequency com-
ponent in 30 Hz is obvious in Figure 2. Because the fun-
damental frequency is 30 Hz, the rotor misalignment
fault is often accompanied by 1x

(30 Hz), 2 x

(60
Hz) and 3x

(90 Hz).
Self-recovery monitoring based on intelligent structure
is shown in Figure 2.
Controller Self-recovery AERS
Self-recovery model
Detect module
Table 1. 2x

(60Hz) crossed concomitant frequency and
unbalance.
Type MisalignmentUnbalance Crack
Characteristic
frequency
1x

(30Hz),
2 x

(60Hz) 1x

(30Hz) 2x

(60Hz)
Concomitant
frequency 3 x

(90Hz) 4x

(120Hz)
Figure 2. Self-recovery monitoring based on smart structure.

Z. S. WANG ET AL. 63
Figure 3. The output waveform of stochastic resonance sys-
tem and its spectrum.
Figure 4. Energy distribution of rotor misalignment.
Table 2. Test results of stochastic resonance system.
Fault type Misjudgment
samples
Diagnosis
samples Diagnosis rate
Misalignment 1 40 97.5 %
Unbalance 0 40 100 %
Crack 2 40 95 %
The energy feature extraction is done by the wavelet
packet analysis. It is based on the signal waveform of
stochastic resonance system. Seven-layer wavelet packet
is resolved in the db3 wavelet and we obtained 64 fre-
quency bands. In order to reduce the amount of computa-
tion, we divide the frequency bands as 6 segments: 0 ~
0.4X, 0.4 ~ 0.8X, 0.8 ~ 1.2 X, 1.8 ~ 2.2X, 2.8 ~ 3.2X and
greater than 3.6X. Thus 64 frequency bands will be
composed of the 6 groups: 1 ~ 4 bands, 5 ~ 8 bands, 9 ~
11 bands, 12 ~ 15 bands, 16 ~ 30 bands and 55 ~ 64
bands. Energy value of each group is added together and
they are processed on the normalization. The energy dis-
tribution of rotor misalignment fault will be acquired. It
is shown in Figure 4.
(a) Waveform before monitoring
(b) Waveform after monitoring
Figure 5. Frequency domain waveform of rotor misalign-
ment.
Repeated the above process, the energy distribution of
each condition can be obtained and it is taken as training
samples of SVM.
According to the training samples obtained from four
conditions, we take 40 groups energy distributions from
each condition as training samples and input to the im-
proved fault classifier of “one-to-many”. We choose
Gaussian RBF kernel function as a classification function
and make the parameters01.0

, punishment factor C
= 100. The classification results are shown in Table 2.
We can see that classification results by the stochastic
resonance system are significantly high than classifica-
tion result by direct wavelet packet feature extraction.
The classification time of the each testing samples is
smaller (in 0.05s, 1.8 GHZ computers). Its accuracy is
higher and speed is quick in early fault identification.
In order to monitor misalignment, we adopt a principle
of the electromagnetic effect [9]. The number of mis-
alignment is detected by four acceleration sensors, and
four electromagnetic sets are controlled by the output
signal of four sensor. When misalignment occurred, the
misalignment force F by rotor produced can be adjusted
by alignment force F’ of electromagnet produced. The
alignment force F’ is equal to the misalignment force F
in number and they are contrary in direction. Figure 5
shows the result of self-recovery monitoring on rotor
misalignment.
C opyright © 2010 SciRes. ENGINEERING

Z. S. WANG ET AL. 64
We can find out that vibration of rotor is obviously
reduced in Figure 5(a) and Figure 5(b). Because of the
misalignment fault of rotor is counteracted by the elec-
tromagnet force, the rotor misalignment is inhibited and
the normal operation condition is restored well.
7. Conclusions
1) Our method can effectively extract the early fault fea-
ture of the AERS by combination the stochastic reso-
nance with the wavelet packet resolving. Energy eigen-
vectors of constructed by this methods can accurately
reflect the condition changes of AERS.
2) Multi-fault classifier based on the SVM has charac-
teristics that its algorithm is simpler, the classification
effect is well and identification efficiency is higher. It
particularly suits to the classification identification of
small sample and self-recovery monitoring of early fault
on AERS.
3) The fault diagnosis is aimed at finding failure in
time and to ensure safe operation of plant. The method of
fault self-recovery monitoring provides an effective way.
8. References
[1] D. Simon, “A comparison of filtering approaches for
aircraft engine health estimation,” Aerospace Science and
Technology, Vol. 12, No. 4, pp. 276–284, 2008.
[2] S. Borguet and O. Léonard, “Coupling principal compo-
nent analysis and Kalman filtering algorithms for on-line
aircraft engine diagnostics,” Control Engineering Practice,
Vol. 17, No. 4, pp. 494–502, 2009.
[3] T. Ramesh Babu and A. S. Sekhar, “Detection of two
cracks in a rotor-bearing system using amplitude devia-
tion curve,” Journal of Sound and Vibration, Vol. 314,
No. 3–5, pp. 457–464, 2008.
[4] A. Dubov and S. Kolokoinikov, “Review of welding pro-
blems and allied processes and their solution using the
metal magnetic memory effect,” Welding in the World,
Vol. 49, No .9, pp. 306–313, 2005.
[5] K. Tanaka and M. Kawakatsu, “Stochastic resonance in
auditory steady-state responses in a magnetoencephalo-
gram,” Clinical Neurophysiology, Vol. 119, No. 9, pp.
2104–2110, 2008.
[6] S. Hurlebaus and L. Gaul, “Smart structure dynamics,”
Mechanical Systems and Signal Processing, Vol. 20, No.
2, pp. 255–281, 2006.
[7] A. Ignatios and B. Alexey, “Anomaly induced effects in a
magnetic field,” Nuclear Physics B, Vol. 793, No. 1–2,
pp. 246–259, 2008.
[8] Mueller and S. N. Sokolova, “Characteristics of light-
weight aggregate from primary and recycled raw materi-
als,” Construction and Building Materials, Vol. 22, No. 4,
pp. 703–712, 2008.
[9] Y. Asher, P. Yosef, and L. Yuri, “Spectral and variational
principles of electromagnetic field excitation in wave
guides,” Physics Letters A, Vol. 344, No. 1, pp. 18–28,
2005.