Professional Documents
Culture Documents
The Use of Kalman Filter and Neural Network Methodologies in Gas Turbine Performance Diagnostics - A Comparative Study
The Use of Kalman Filter and Neural Network Methodologies in Gas Turbine Performance Diagnostics - A Comparative Study
net/publication/239399796
The Use of Kalman Filter and Neural Network Methodologies in Gas Turbine
Performance Diagnostics: A Comparative Study
Article in Journal of Engineering for Gas Turbines and Power · October 2003
DOI: 10.1115/1.1419016
CITATIONS READS
197 1,250
4 authors, including:
Ranjan Ganguli
Indian Institute of Science
345 PUBLICATIONS 6,651 CITATIONS
SEE PROFILE
All content following this page was uploaded by Ranjan Ganguli on 16 May 2014.
Introduction will briefly describe this procedure, however, for a more detailed
discussion we refer the reader to the following sources: 关4 –13兴.
The goal of gas turbine performance diagnostics is to accurately
The general approach taken for engine fault diagnostics typi-
detect, isolate, and assess the changes in engine module perfor-
cally involves the use of a linearized model approximation evalu-
mance, engine system malfunctions, and instrumentation prob-
ated at a selected engine operating point. This provides a matrix
lems from knowledge of measured parameters taken along the
relationship between changes in engine component performance
engine’s gas path. Discernable shifts in engine speeds, tempera-
共independent parameters兲 and the attendant changes in typically
tures, pressures, fuel flow, etc., provide the requisite information
measured engine parameters such as spool speeds, internal tem-
for determining the underlying shift in engine operation from a
peratures and pressures, fuel flow, etc. 共dependent parameters兲.
presumed nominal state. Historically, this type of analysis was
This relationship may be succinctly represented as
performed through the use of a Kalman filter or one of its deriva-
tives to simultaneously estimate a plurality of engine faults. In the z⫽Hx⫹ (1)
past decade, artificial neural networks 共ANN兲 have been em-
ployed as a pattern recognition device to accomplish the same where z is a vector of measured parameter deltas, x is a vector of
task. Both methods have enjoyed a reasonable success. fault deltas, H is a matrix of fault influence coefficients, and is
The purpose of this paper is to outline the two methodologies, a random vector representing the uncertainties inherent in the
discuss their relative merits and weaknesses, and provide a direct measurement process. In addition to the precision of the indi-
comparison of the two techniques via a controlled computer simu- vidual sensors, it has been customary to address the potential for
lation study. In the sequel, we will provide a brief general descrip- sensor bias and drift. Consequently, the fault vector given in the
tion of both the Kalman filter and ANN as applied to the diagnos- model above is often configured to contain components directly
tic problem. For the purpose of conducting a comparison, we will related to sensor error in addition to engine fault deltas.
limit the framework of the diagnostic system to the problem of The fault vector x given in the model can be thought of as the
isolating a single fault to the component level. The single faults concatenation of an engine fault vector (x e ) and a sensor 共error兲
under consideration will be comprised of engine module, engine fault vector x S , i.e., x⫽ 关 x e ]x s 兴 T where
冋 册 冋 册
system, and instrumentation faults.
⌬ FAN ⌬N1 err
Kalman Filter Approach ⌬⌫ FAN ⌬ P3 err
Kalman filter methods were introduced as a fault isolation and x e ⫽ ⌬ CH and x s ⫽ ⌬W f err . (2)
assessment technique for relative engine performance diagnostics ] ]
in the late 1970s and early 1980s 共关1–3兴兲. The success enjoyed in ⌬A 5 ⌬T49err
these early programs promoted the use of these techniques in sub-
sequent years to become the central methodology utilized in many We may rewrite Eq. 共1兲 as
冋册
current engine performance analysis programs. In the sequel we
xe
Contributed by the International Gas Turbine Institute 共IGTI兲 of THE AMERICAN z⫽H e x e ⫹H s x s ⫹ ⫽ 关 H e ] H s 兴 ¯ ⫹ ⫽Hx⫹ . (3)
SOCIETY OF MECHANICAL ENGINEERS for publication in the ASME JOURNAL OF xs
ENGINEERING FOR GAS TURBINES AND POWER. Paper presented at the Interna-
tional Gas Turbine and Aeroengine Congress and Exhibition, Munich, Germany, May
8 –11, 2000; Paper 2000-GT-0547. Manuscript received by IGTI November 1999;
The matrix H has been partitioned into two parts; a matrix of
final revision received by ASME Headquarters February 2000. Associate Editor: D. engine fault influence coefficients (H e ) and a matrix of sensor
Wisler. fault influence coefficients (H S ). The generation of these matrices
Journal of Engineering for Gas Turbines and Power OCTOBER 2003, Vol. 125 Õ 917
Copyright © 2003 by ASME
Table 1 Sample root cause influences
and their interpretation have been discussed in great detail in Single Fault Isolation. The Kalman filter can be configured
关4,14兴 and elsewhere in the literature and will not be pursued in to emulate a single fault isolator (SFI). This is a snapshot type of
this paper. analysis in the sense that it operates on a set of measurement
The model, as configured above, has often been used for the deltas without any a priori information or pre-history. The object
purpose of tracking slowly occurring changes in engine perfor- of the analysis is to flag a root cause on the basis of a single
mance from revenue flight data, through the use of a Kalman measurement delta set. Root causes are single fault occurrences
filter-based methodology. An estimate for these performance and are pre-defined for the system. They consist of coupled faults
shifts, x̂, would be given by within the major modules of the engine, certain system faults such
冋册 冋 册 冋 册冉 冋 册冊
as handling and ECS bleed leaks and failures, variable stator vane
x̂ e x̄ e De x̄ e malfunctions, TCC malfunctions as well as certain instrumenta-
¯ ⫽x̂⫽x̄⫹D 共 z⫺Hx̄ 兲 ⫽ ¯ ⫹ ¯ z⫺ 关 H e ]H s 兴 ¯ tion faults. These faults are assumed to occur in isolation, i.e.,
x̂ s x̄ s Ds x̄ s there will be one and only one root cause occurrence at any given
time. The purpose of the single fault isolator is to identify the
correct root cause once a trend shift is detected.
x̂⫽prediction⫹GAIN共residual兲⫽prediction⫹correction (4)
Root Causes. Root Causes can be thought of as state vari-
where x̄ represents an a priori estimate of the engine/sensor fault ables, x 1 ,x 2 , . . . ,x n . They are represented within this system as
deltas and D is the 共Kalman兲 gain matrix referred to as the diag- vectors of measurement deltas, z * 1 ,z *
2 , . . . ,z n* , which are calcu-
nostic matrix. The diagnostic matrix is computed as a function of lated by applying influence coefficients. As an illustration, we can
several quantities; the engine/sensor influence coefficients H, the consider the following 12 root causes. These root causes may exist
measurement covariance matrix R, and a positive semidefinite
at varying levels. The state representation of the root cause will be
weighting matrix P0 . The diagnostic matrix is computed as
in the form of a one percent cause to be consistent with other
冋册 冋 册
influences.
De P e0 H Te 共 H e P e0 H Te ⫹R 兲 ⫺1 1. FAN coupled FAN 共⫺1 percent , ⫺1.25 percent FC兲
D⫽ ¯ ⫽ P 0 H 共 H P 0 H ⫹R 兲 ⫽
T T ⫺1 ¯¯ 2. LPC coupled LPC 共⫺1 percent , ⫺1.10 percent FC兲
3. HPC coupled HPC 共⫺1 percent , ⫺0.80 percent FC兲
Ds P s0 H sT 共 H s P s0 H sT ⫹R 兲 ⫺1 4. HPT coupled HPT 共⫺1 percent , ⫹0.75 percent FP4兲
(5) 5. LPT coupled LPT 共⫺1 percent , ⫹1.65 percent FP45兲
6. 2.5 BLD stability bleed leak 共one percent兲
7. 2.9 BLD start bleed 共one percent兲
where P (0e )andP 0(s )
are weighting submatrices for the engine and 8. FP14 fan discharge area 共one percent兲
sensor fault estimation, respectively. An in-depth report on the 9. FP8 core discharge area 共one percent兲
generation of the P 0 and R matrices can be found in references 10. TCC turbine case cooling 共on兲
11. HPCSVM HPC stator vane misrigging
关4,5兴. 12. P49 Error P49 indication problem 共two percent兲
The use of the predictor/corrector methods like the Kalman An example of the influences for these root causes is depicted in
filter to estimate sensor error has made possible a more reliable
Table 1.
and consistent gas turbine module performance analysis. The pro-
cedure outlined above can be applied in a snapshot analysis or as The actual root cause may appear as some multiple of the in-
a continuing recursive analysis as new engine data are made avail- fluences represented in Table 1. For instance, a 2.5 bleed root
able over time. In either scenario, the simultaneous determination cause may manifest itself as a stuck open bleed 共⬇15 percent 2.5
of both engine faults and measurement errors by this methodology bleed fault兲 or a partial bleed leak, say two percent 2.5 bleed fault.
has been successfully applied to a large number of commercial These two faults will be treated as the same by the Kalman esti-
and military families of engines with varying instrumentation mator. The difference between the two faults is one of magnitude.
suites for two decades. The magnitude is estimated by the Kalman filter. Its ability to
In the sequel, we shall alter our emphasis to consider the prob- estimate correctly will depend on the signal to noise ratio for the
lem of fault isolation, given the premise that a fault event has been given fault. In this particular case, a two percent 2.5 bleed is
detected. The problem of detection becomes one of recognizing a
sometimes confused with an LPC fault or a 2.9 Bleed fault. On the
step or rate change in a gas path parameter or a collection of
parameters. The problems associated with fault detection and the other hand, a stuck 2.5 Bleed 共14.77 percent兲 has a significantly
mechanisms which can be applied to accomplish this task have higher S/N ratio and is estimated correctly. Another factor which
been reported by 关15兴. The types of faults that will be considered impacts accuracy of the estimator is the number of measured pa-
in this discussion include engine performance faults, engine sys- rameters. We will consider systems that have between four and
tem faults, and instrumentation faults. eight measurements in flight.
冋 册
lated as follows:x̂ n ⫽SFI estimate for the nth root cause
P k⫹1 ⫽ 关 I⫺D k⫹1 H k⫹1 兴 P 共 k⫹1 兩 k 兲 .
冉 冊
8 1/2
z k ⫺z k* 2
For the single fault isolator we make the following adjustments:
兺 k
⌽ k⫹1 ⫽I e n⫽
k⫽1
(7)
8
Q k⫹1 ⫽0 兺
k⫽1
z 2k
H k⫹1 ⫽M c 共 H * 兲 T
k ⫽kth element of the vector M c (H * ) x̂ n .
T
z*
M c ⫽measurement configuration vector⫽diag共 m 1 ,m 2 , . . . ,m 8 兲 It is possible for the estimated values for some single faults to
be opposite in polarity than what would be reasonably expected.2
共diagonal matrix assuming eight potential measurements兲 For example, an HPT SF of magnitude ⫺2 percent might yield an
where m j ⫽ 再 1
0
if jth measurement is available
otherwise.
estimated value of ⫹0.5 percent for an LPC SFI. Given that a
sudden shift in observed gas path parameters has taken place dur-
ing engine operation, it is not likely that the condition of any
The effect of the measurement configuration matrix is to zero given module has improved and thus a positive shift in perfor-
the rows of the root cause influence matrix corresponding to the mance would not be given serious consideration. Thus, some pre-
measurements that are NOT available. The resulting matrix of processing is mandated before the error ranking is performed.
influences is 8⫻9 for this example. This takes the form of perusing each of the SFI estimates and
The single fault isolation is obtained by processing the general considering only those which admit a reasonable polarity. Order-
Kalman equations iteratively to provide a snapshot analysis for ing the errors from min to max we obtain
each of the root causes under consideration 共11 in this example兲. e i 1 ⭐e i 2 ⭐¯⭐e i n (8)
Each ‘‘call’’ to the Kalman filter will be made with a different P 0
matrix chosen to accentuate the kth root cause. Since these are corresponding to the single fault estimates
snapshot analyses, the covariance update calculation is not re-
quired. The a priori state estimate is also assumed to be zero. An x̂ i 1 ⭐x̂ i 2 ⭐¯⭐x̂ i n (9)
SFI analysis is performed typically after a trend shift has been in order of likelihood. In most cases, the first of these ranked
detected in the measurement deltas at some discrete time, say, single faults is deemed to be the underlying fault and is reported
between time k and k⫹1. The ‘‘delta-delta’’ (Z k⫹1 ⫺Z k ) consti- to the user. In some instances, however, it may be prudent to
tutes the input measurement delta, Z, to the SFI. report the first and second SFs, since there exists the possibility
The SFI is evaluated iteratively for each single fault 共11 in the for an erroneous fault identification, especially if the associated
above example兲. This process will yield estimates for each single error norms are ‘‘close.’’
fault under consideration. It is necessary to rank each of these Depending on the circumstances, the SFI may experience a
estimates and determine the top two or three single faults. The confusion between two single faults. The aliasing of SFs depends
measure used to compare estimates for this purpose of ranking is on the single faults themselves, their relative magnitude with re-
a normalized measurement error norm which we will describe spect to the nonrepeatability of the measurements and the number
below. The single fault admitting the minimum error is deemed of measurements available for the analysis. All of these factors
the most likely, the second smallest error, the next likely, and so can contribute to a confounding of the underlying SF with another
forth.
2
Although this is not a common occurrence, it is possible for an SF estimate
1
The row dimension of H * is 9 共and not 11兲 since the BLD25 and BLD29 root indicating an improvement in performance to admit the minimum measurement error
causes are used to model the two different magnitude faults being considered. norm and hence win the isolation selection.
Journal of Engineering for Gas Turbines and Power OCTOBER 2003, Vol. 125 Õ 919
Table 3 SFI accuracy: Kalman filter, 8 measurements entries indicate the percentage of time the implanted fault is cor-
rectly annunciated as first, second, and third choice.
8 Measurement Set
The results demonstrate a 96.9 percent and 91.1 percent accu-
FAULT 1st Top 2 Top 3 racy for the first choice fault isolation for eight and four measure-
ment systems, respectively. If we weaken the accuracy criteria to
FAN 100% 100% 100%
LPC 90% 100% 100% that of being correct within the top two choices, the relative pre-
HPC 100% 100% 100% cision of the isolation increases to 100 percent and 96.1 percent.
HPT 100% 100% 100% In either case, the isolation accuracy is quite good.
LPT 100% 100% 100% The fact that we can obtain a 91 percent hit rate with only four
2.5 BLD 85% 100% 100%
2.9 BLD 96.7% 100% 100% measurements raises the question as to why one would ever con-
HPCSVM 100% 100% 100% sider adding more instrumentation. There are several answers to
P49err 100% 100% 100% this question, one being that a multiple fault performance assess-
Total 96.9% 100% 100% ment would not perform as well with fewer measurements. But
even within the constraints of this study 共i.e., single fault annun-
ciation兲, the ‘‘more the better’’ argument still holds if we consider
Table 4 SFI accuracy: Kalman filter, 4 measurements the robustness of the system. One measure of robustness would be
to vary the module couplings 共flow capacity versus efficiency,
4 Measurement Set hard coupled relationship兲 in the implanted faults beyond that
FAULT 1st Top 2 Top 3 which is assumed in the numerical model 共i.e., the influences co-
efficients H * ). Figures 1 and 2 depict the impact on first choice
FAN 100% 100% 100% accuracy for eight and four measurement systems, respectively,
LPC 90% 90% 100%
HPC 100% 100% 100% when the coupling factor for the compression modules 共FAN,
HPT 100% 100% 100% LPC, HPC兲 are randomly varied.4
LPT 100% 100% 100% The LPC and HPC clearly exhibit greater robustness to model-
2.5 BLD 50% 75% 95% ing assumptions in the 8 measurement system.
2.9 BLD 80.0% 100.0% 100%
HPCSVM 100% 100% 100% In the sequel, we will briefly discuss artificial neural networks
P49err 100% 100% 100% 共ANNs兲, and their usage in engine performance diagnostics. The
Total 91.1% 96.1% 99.4% discussion will be intentionally brief since there already exists
ample documentation of this methodology in the literature, and
the reader is directed to the references for additional detail. For
the purpose of making a direct comparison with the Kalman
SF. To mitigate the possibility of a false identification, some post- filter methodology, we will confine much of the discussion to the
processing of the SFI results may be required. This will improve single fault isolation problem introduced in the prelude. The iden-
the overall accuracy of the system. The rules to be applied would tical computer simulation test will be used as the vehicle for the
be empirically motivated and would be suggested by computer evaluation.
simulation test cases. For the problem set considered in this study
共Table 2兲, it was not necessary to undergo this type of post- Artificial Neural Network Approach
processing.
The fault isolation problem can be considered to be a pattern
Computer Simulation Results. Using Equation 共1兲, we can classification problem. N-dimensional vectors in an
generate a set of hypothetical ‘‘noisy’’ measurements for each of N-dimensional space represent the system response. The system
the 11 single faults under consideration (x i ,i⫽1,2, . . . 11). These response for different faults tends to be partitioned into different
noisy measurement vectors (z k ) are then passed through the SFI regions of this space and can be regarded as patterns. Pattern
process, the results ranked and tabulated for first, second, and recognition involves learning these partitions, from simulated or
third ranked faults. These results appear in Table 3 and 4 for real data, so that a given system response can be classified as a
eightand four measurement set3 systems, respectively, where the particular fault. Neural networks represent a powerful pattern rec-
four bleed leak faults have been combined into two faults. The ognition technique, and have been applied for fault detection of
3
4
The turbine modules’ 共HPT and LPT兲 isolation accuracy was essentially unaf-
The four measurements set used in this study consisted of the flight required fected and hence were not plotted.
parameters (T49, Wf, N1 and N2).
complex systems such as aerospace vehicles 共关16兴兲, nuclear power The discussion below involves the use of two types of neural
plants 共关17兴兲, and chemical process facilities 共关18兴兲 among others. networks for engine fault diagnostics, a feed forward ANN trained
A key advantage of neural networks over other methods is their using back-propagation 共BP兲 algorithm and a hybrid neural
ability to recognize relationships between patterns despite the network.
presence of noise contamination and/or partial information 共关19兴兲.
Most applications of ANN to fault diagnostics follow a com- Back-Propagation „BP… Algorithm. While there are several
mon process. The ANN is trained off-line on fault signatures re- types of neural networks, multilayer feedforward networks trained
lating the changes in system measurements from a ‘‘good’’ base- using the backpropagation algorithm have emerged as the most
line to system faults. Typically, faults are embedded into the widely used. Figure 3 illustrates the schematic of a feedforward
computer simulations, or real fault data is used, or a combination neural network, which consists of an input layer, an output layer,
of both. In case simulated data is used, noise must be added to and one or more hidden layers. The number of neurons in the
make the simulations realistic. Such a training process where the input and output layers is determined by the number of input
ANN is presented input and output data by the system designer is measurements and output parameters. The number of hidden layer
known as supervised learning. Once the ANN has been properly nodes is selected based on convergence criterion and the charac-
trained using this process of supervised learning, it can analyze teristic of the input-output mapping relationship.
data that are different from those it was originally exposed to A three-layer feedforward network is used for the present work,
during the training sessions. When the trained ANN is placed as shown in Fig. 1. The feedforward network is trained using
on-line, it recognizes a similar response from the actual system. supervised learning, which involves presenting input-output pairs
to the ANN and then using the BP algorithm to learn the relation-
ships between the inputs and outputs by minimizing the following
error measure:
N
E⫽ 兺E
k⫽1
k (10)
8 Measurement Set
FAULT 1st Top 2 Top 3
FAN 100% 100% 100%
LPC 60% 80% 90%
HPC 100% 100% 100%
HPT 100% 100% 100%
LPT 100% 100% 100%
2.5 BLD 80% 85% 85%
2.9 BLD 86.7% 86.7% 86.7%
HPCSVM 90% 100% 100%
P49err 100% 100% 100%
Total 90.7% 94.6% 95.7%
Fig. 3 Architecture of three layer feedforward ANN
Journal of Engineering for Gas Turbines and Power OCTOBER 2003, Vol. 125 Õ 921
Table 6 SFI accuracy: ANN, 4 measurements Table 8 SFI accuracy: hybrid NN, 4 measurements
Journal of Engineering for Gas Turbines and Power OCTOBER 2003, Vol. 125 Õ 923
关18兴 Wantanabe, K. et al., 1989, ‘‘Incipient Fault Diagnosis of Chemical Processes 关23兴 Kirkpatrick, S., 1984, ‘‘Optimization by Simulated Annealing: Quantitative
via Artificial Neural Network,’’ AIChE J., 35, No. 11. Studies,’’ J. Stat. Phys., 34.
关19兴 Holmstrom, L., and Koistinen, P., 1992, ‘‘Using Additive Noise in Back Propa- 关24兴 Ackley, D. H., Hinton, G. E., and Sejnowski, T. J., 1985, ‘‘A Learning Algo-
gation Training,’’ IEEE Trans. Neural Netw., 3, No. 1. rithm for Boltzmann Machines,’’ Cognitive Science, Vol. 9, Cognitive Science
关20兴 Haykin, S., 1994, Neural Networks—A Comprehensive Foundation, Macmil- Society, Cincinnati, OH.
lian, New York. 关25兴 Broomhead, D. S., and Lowe, D., 1988, ‘‘Multivariate Function Interpolation
关21兴 Dasarathy, B. V., 1991, Nearest Neighbor (NN) Norms: NN Pattern Classifi- and Adaptive Networks,’’ Complex Systems, Vol. 2, Complex Systems Publi-
cation Techniques, IEEE Computer Society Press, New York. cations, Champaign, IL.
关22兴 Kohonen, T., 1990, ‘‘The Self-Organizing Map,’’ Proc. IEEE, 78, IEEE, New 关26兴 Cybenko, G., 1989, ‘‘Approximations of Superposition of a Sigmoidal Func-
York. tion,’’ Mathematics of Control, Signals and Systems, Vol. 2.