Health Monitoring and Failure Detection of Electronic and Structural Components in Small Unmanned Aerial Vehicles
Fully autonomous small Unmanned Aerial Vehicles
(UAVs) are increasingly being used in many commercial applications.
Although a lot of research has been done to develop safe, reliable
and durable UAVs, accidents due to electronic and structural failures
are not uncommon and pose a huge safety risk to the UAV operators
and the public. Hence there is a strong need for an automated health
monitoring system for UAVs with a view to minimizing mission
failures thereby increasing safety. This paper describes our approach
to monitoring the electronic and structural components in a small
UAV without the need for additional sensors to do the monitoring.
Our system monitors data from four sources; sensors, navigation
algorithms, control inputs from the operator and flight controller
outputs. It then does statistical analysis on the data and applies
a rule based engine to detect failures. This information can then
be fed back into the UAV and a decision to continue or abort the
mission can be taken automatically by the UAV and independent of
the operator. Our system has been verified using data obtained from
real flights over the past year from UAVs of various sizes that have
been designed and deployed by us for various applications.
A Comparison of Inverse Simulation-Based Fault Detection in a Simple Robotic Rover with a Traditional Model-Based Method
Robotic rovers which are designed to work in
extra-terrestrial environments present a unique challenge in terms
of the reliability and availability of systems throughout the mission.
Should some fault occur, with the nearest human potentially millions
of kilometres away, detection and identification of the fault must
be performed solely by the robot and its subsystems. Faults in
the system sensors are relatively straightforward to detect, through
the residuals produced by comparison of the system output with
that of a simple model. However, faults in the input, that is, the
actuators of the system, are harder to detect. A step change in
the input signal, caused potentially by the loss of an actuator,
can propagate through the system, resulting in complex residuals
in multiple outputs. These residuals can be difficult to isolate or
distinguish from residuals caused by environmental disturbances.
While a more complex fault detection method or additional sensors
could be used to solve these issues, an alternative is presented here.
Using inverse simulation (InvSim), the inputs and outputs of the
mathematical model of the rover system are reversed. Thus, for a
desired trajectory, the corresponding actuator inputs are obtained.
A step fault near the input then manifests itself as a step change
in the residual between the system inputs and the input trajectory
obtained through inverse simulation. This approach avoids the need
for additional hardware on a mass- and power-critical system such
as the rover. The InvSim fault detection method is applied to a
simple four-wheeled rover in simulation. Additive system faults and
an external disturbance force and are applied to the vehicle in turn,
such that the dynamic response and sensor output of the rover
are impacted. Basic model-based fault detection is then employed
to provide output residuals which may be analysed to provide
information on the fault/disturbance. InvSim-based fault detection
is then employed, similarly providing input residuals which provide
further information on the fault/disturbance. The input residuals are
shown to provide clearer information on the location and magnitude
of an input fault than the output residuals. Additionally, they can
allow faults to be more clearly discriminated from environmental
Application of Computer Aided Engineering Tools in Performance Prediction and Fault Detection of Mechanical Equipment of Mining Process Line
Nowadays, to decrease the number of downtimes in the industries such as metal mining, petroleum and chemical industries, predictive maintenance is crucial. In order to have efficient predictive maintenance, knowing the performance of critical equipment of production line such as pumps and hydro-cyclones under variable operating parameters, selecting best indicators of this equipment health situations, best locations for instrumentation, and also measuring of these indicators are very important. In this paper, computer aided engineering (CAE) tools are implemented to study some important elements of copper process line, namely slurry pumps and cyclone to predict the performance of these components under different working conditions. These modeling and simulations can be used in predicting, for example, the damage tolerance of the main shaft of the slurry pump or wear rate and location of cyclone wall or pump case and impeller. Also, the simulations can suggest best-measuring parameters, measuring intervals, and their locations.
Elman Neural Network for Diagnosis of Unbalance in a Rotor-Bearing System
The operational life of rotating machines has to be extended using a predictive condition maintenance tool. Among various condition monitoring techniques, vibration analysis is most widely used technique in industry. Signals are extracted for evaluating the condition of machine; further diagnostics is carried out with detected signals to extend the life of machine. With help of detected signals, further interpretations are done to predict the occurrence of defects. To study the problem of defects, a test rig with various possibilities of defects is constructed and experiments are performed considering the unbalanced condition. Further, this paper presents an approach for fault diagnosis of unbalance condition using Elman neural network and frequency-domain vibration analysis. Amplitudes with variation in acceleration are fed to Elman neural network to classify fault or no-fault condition. The Elman network is trained, validated and tested with experimental readings. Results illustrate the effectiveness of Elman network in rotor-bearing system.
Actuator Fault Detection and Fault Tolerant Control of a Nonlinear System Using Sliding Mode Observer
In this work, we use the Fault detection and isolation and the Fault tolerant control based on sliding mode observer in order to introduce the well diagnosis of a nonlinear system. The robustness of the proposed observer for the two techniques is tested through a physical example. The results in this paper show the interaction between the Fault tolerant control and the Diagnosis procedure.
Dynamic Fault Diagnosis for Semi-Batch Reactor under Closed-Loop Control via Independent Radial Basis Function Neural Network
In this paper, a robust fault detection and isolation
(FDI) scheme is developed to monitor a multivariable nonlinear
chemical process called the Chylla-Haase polymerization reactor,
when it is under the cascade PI control. The scheme employs a radial
basis function neural network (RBFNN) in an independent mode to
model the process dynamics, and using the weighted sum-squared
prediction error as the residual. The Recursive Orthogonal Least
Squares algorithm (ROLS) is employed to train the model to
overcome the training difficulty of the independent mode of the
network. Then, another RBFNN is used as a fault classifier to isolate
faults from different features involved in the residual vector. Several
actuator and sensor faults are simulated in a nonlinear simulation of
the reactor in Simulink. The scheme is used to detect and isolate the
faults on-line. The simulation results show the effectiveness of the
scheme even the process is subjected to disturbances and
uncertainties including significant changes in the monomer feed rate,
fouling factor, impurity factor, ambient temperature, and
measurement noise. The simulation results are presented to illustrate
the effectiveness and robustness of the proposed method.
A Comprehensive Method of Fault Detection and Isolation Based On Testability Modeling Data
Testability modeling is a commonly used method in
testability design and analysis of system. A dependency matrix will be
obtained from testability modeling, and we will give a quantitative
evaluation about fault detection and isolation.
Based on the dependency matrix, we can obtain the diagnosis tree.
The tree provides the procedures of the fault detection and isolation.
But the dependency matrix usually includes built-in test (BIT) and
manual test in fact. BIT runs the test automatically and is not limited
by the procedures. The method above cannot give a more efficient
diagnosis and use the advantages of the BIT.
A Comprehensive method of fault detection and isolation is
proposed. This method combines the advantages of the BIT and
Manual test by splitting the matrix. The result of the case study shows
that the method is effective.
Fault Detection and Isolation in Attitude Control Subsystem of Spacecraft Formation Flying Using Extended Kalman Filters
In this paper, the problem of fault detection and
isolation in the attitude control subsystem of spacecraft formation
flying is considered. In order to design the fault detection method, an
extended Kalman filter is utilized which is a nonlinear stochastic state
estimation method. Three fault detection architectures, namely,
centralized, decentralized, and semi-decentralized are designed based
on the extended Kalman filters. Moreover, the residual generation
and threshold selection techniques are proposed for these
A Study of Adaptive Fault Detection Method for GNSS Applications
This study is purposed to develop an efficient fault
detection method for Global Navigation Satellite Systems (GNSS)
applications based on adaptive noise covariance estimation. Due to the
dependence on radio frequency signals, GNSS measurements are
dominated by systematic errors in receiver’s operating environment.
In the proposed method, the pseudorange and carrier-phase
measurement noise covariances are obtained at time propagations and
measurement updates in process of Carrier-Smoothed Code (CSC)
filtering, respectively. The test statistics for fault detection are
generated by the estimated measurement noise covariances. To
evaluate the fault detection capability, intentional faults were added to
the filed-collected measurements. The experiment result shows that
the proposed method is efficient in detecting unhealthy measurements
and improves GNSS positioning accuracy against fault occurrences.
Applied Actuator Fault Accommodation in Flight Control Systems Using Fault Reconstruction Based FDD and SMC Reconfiguration
Historically, actuators’ redundancy was used to deal
with faults occurring suddenly in flight systems. This technique was
generally expensive, time consuming and involves increased weight
and space in the system. Therefore, nowadays, the on-line fault
diagnosis of actuators and accommodation plays a major role in the
design of avionic systems. These approaches, known as Fault
Tolerant Flight Control systems (FTFCs) are able to adapt to such
sudden faults while keeping avionics systems lighter and less
expensive. In this paper, a (FTFC) system based on the Geometric
Approach and a Reconfigurable Flight Control (RFC) are presented.
The Geometric approach is used for cosmic ray fault reconstruction,
while Sliding Mode Control (SMC) based on Lyapunov stability
theory is designed for the reconfiguration of the controller in order to
compensate the fault effect. Matlab®/Simulink® simulations are
performed to illustrate the effectiveness and robustness of the
proposed flight control system against actuators’ faulty signal caused
by cosmic rays. The results demonstrate the successful real-time
implementation of the proposed FTFC system on a non-linear 6 DOF
On the Representation of Actuator Faults Diagnosis and Systems Invertibility
In this work, the main problem considered is the
detection and the isolation of the actuator fault. A new formulation of
the linear system is generated to obtain the conditions of the actuator
fault diagnosis. The proposed method is based on the representation
of the actuator as a subsystem connected with the process system in
cascade manner. The designed formulation is generated to obtain the
conditions of the actuator fault detection and isolation. Detectability
conditions are expressed in terms of the invertibility notions. An
example and a comparative analysis with the classic formulation
illustrate the performances of such approach for simple actuator fault
diagnosis by using the linear model of nuclear reactor.
An Anomaly Detection Approach to Detect Unexpected Faults in Recordings from Test Drives
In the automotive industry test drives are being conducted
during the development of new vehicle models or as a part of
quality assurance of series-production vehicles. The communication
on the in-vehicle network, data from external sensors, or internal
data from the electronic control units is recorded by automotive
data loggers during the test drives. The recordings are used for fault
analysis. Since the resulting data volume is tremendous, manually
analysing each recording in great detail is not feasible.
This paper proposes to use machine learning to support domainexperts
by preventing them from contemplating irrelevant data and
rather pointing them to the relevant parts in the recordings. The
underlying idea is to learn the normal behaviour from available
recordings, i.e. a training set, and then to autonomously detect
unexpected deviations and report them as anomalies.
The one-class support vector machine “support vector data description”
is utilised to calculate distances of feature vectors. SVDDSUBSEQ
is proposed as a novel approach, allowing to classify subsequences
in multivariate time series data. The approach allows to
detect unexpected faults without modelling effort as is shown with
experimental results on recordings from test drives.
Fault Detection and Isolation using RBF Networks for Polymer Electrolyte Membrane Fuel Cell
This paper presents a new method of fault detection and isolation (FDI) for polymer electrolyte membrane (PEM) fuel cell (FC) dynamic systems under an open-loop scheme. This method uses a radial basis function (RBF) neural network to perform fault identification, classification and isolation. The novelty is that the RBF model of independent mode is used to predict the future outputs of the FC stack. One actuator fault, one component fault and three sensor faults have been introduced to the PEMFC systems experience faults between -7% to +10% of fault size in real-time operation. To validate the results, a benchmark model developed by Michigan University is used in the simulation to investigate the effect of these five faults. The developed independent RBF model is tested on MATLAB R2009a/Simulink environment. The simulation results confirm the effectiveness of the proposed method for FDI under an open-loop condition. By using this method, the RBF networks able to detect and isolate all five faults accordingly and accurately.
Multi-agent On-line Monitor for the Safety of Critical Systems
Operational safety of critical systems, such as nuclear power plants, industrial chemical processes and means of transportation, is a major concern for system engineers and operators. A means to assure that is on-line safety monitors that deliver three safety tasks; fault detection and diagnosis, alarm annunciation and fault controlling. While current monitors deliver these tasks, benefits and limitations in their approaches have at the same time been highlighted. Drawing from those benefits, this paper develops a distributed monitor based on semi-independent agents, i.e. a multiagent system, and monitoring knowledge derived from a safety assessment model of the monitored system. Agents are deployed hierarchically and provided with knowledge portions and collaboration protocols to reason and integrate over the operational conditions of the components of the monitored system. The monitor aims to address limitations arising from the large-scale, complicated behaviour and distributed nature of monitored systems and deliver the aforementioned three monitoring tasks effectively.
Time-Domain Stator Current Condition Monitoring: Analyzing Point Failures Detection by Kolmogorov-Smirnov (K-S) Test
This paper deals with condition monitoring of electric switch machine for railway points. Point machine, as a complex electro-mechanical device, switch the track between two alternative routes. There has been an increasing interest in railway safety and the optimal management of railway equipments maintenance, e.g. point machine, in order to enhance railway service quality and reduce system failure. This paper explores the development of Kolmogorov- Smirnov (K-S) test to detect some point failures (external to the machine, slide chairs, fixing, stretchers, etc), while the point machine (inside the machine) is in its proper condition. Time-domain stator Current signatures of normal (healthy) and faulty points are taken by 3 Hall Effect sensors and are analyzed by K-S test. The test is simulated by creating three types of such failures, namely putting a hard stone and a soft stone between stock rail and switch blades as obstacles and also slide chairs- friction. The test has been applied for those three faults which the results show that K-S test can effectively be developed for the aim of other point failures detection, which their current signatures deviate parametrically from the healthy current signature. K-S test as an analysis technique, assuming that any defect has a specific probability distribution. Empirical cumulative distribution functions (ECDF) are used to differentiate these probability distributions. This test works based on the null hypothesis that ECDF of target distribution is statistically similar to ECDF of reference distribution. Therefore by comparing a given current signature (as target signal) from unknown switch state to a number of template signatures (as reference signal) from known switch states, it is possible to identify which is the most likely state of the point machine under analysis.
Fault Detection of Pipeline in Water Distribution Network System
Water pipe network is installed underground and once equipped, it is difficult to recognize the state of pipes when the leak or burst happens. Accordingly, post management is often delayed
after the fault occurs. Therefore, the systematic fault management system of water pipe network is required to prevent the accident and
minimize the loss. In this work, we develop online fault detection system of water pipe network using data of pipes such as flow rate
or pressure. The transient model describing water flow in pipelines
is presented and simulated using MATLAB. The fault situations such
as the leak or burst can be also simulated and flow rate or pressure data when the fault happens are collected. Faults are detected using
statistical methods of fast Fourier transform and discrete wavelet transform, and they are compared to find which method shows the
better fault detection performance.
Performance Analysis of Expert Systems Incorporating Neural Network for Fault Detection of an Electric Motor
In this paper, an artificial neural network simulator is
employed to carry out diagnosis and prognosis on electric motor as
rotating machinery based on predictive maintenance. Vibration data
of the primary failed motor including unbalance, misalignment and
bearing fault were collected for training the neural network. Neural
network training was performed for a variety of inputs and the motor
condition was used as the expert training information. The main
purpose of applying the neural network as an expert system was to
detect the type of failure and applying preventive maintenance. The
advantage of this study is for machinery Industries by providing
appropriate maintenance that has an essential activity to keep the
production process going at all processes in the machinery industry.
Proper maintenance is pivotal in order to prevent the possible failures
in operating system and increase the availability and effectiveness of
a system by analyzing vibration monitoring and developing expert
Light Tracking Fault Tolerant Control System
A fault detection and identification (FDI) technique is
presented to create a fault tolerant control system (FTC). The fault
detection is achieved by monitoring the position of the light source
using an array of light sensors. When a decision is made about the
presence of a fault an identification process is initiated to locate the
faulty component and reconfigure the controller signals. The signals
provided by the sensors are predictable; therefore the existence of a
fault is easily identified. Identification of the faulty sensor is based on
the dynamics of the frame. The technique is not restricted to a
particular type of controllers and the results show consistency.
Fault Detection via Stability Analysis for the Hybrid Control Unit of HEVs
Fault detection determines faultexistence and detecting
time. This paper discusses two layered fault detection methods to
enhance the reliability and safety. Two layered fault detection methods
consist of fault detection methods of component level controllers and
system level controllers. Component level controllers detect faults by
using limit checking, model-based detection, and data-driven
detection and system level controllers execute detection by stability
analysis which can detect unknown changes. System level controllers
compare detection results via stability with fault signals from lower
level controllers. This paper addresses fault detection methods via
stability and suggests fault detection criteria in nonlinear systems. The
fault detection method applies tothe hybrid control unit of a military
hybrid electric vehicleso that the hybrid control unit can detect faults
of the traction motor.
Implementation of an Innovative Simplified Sliding Mode Observer-Based Robust Fault Detection in a Drum Boiler System
One of the robust fault detection filter (RFDF)
designing method is based on sliding-mode theory. The main purpose
of our study is to introduce an innovative simplified reference
residual model generator to formulate the RFDF as a sliding-mode
observer without any manipulation package or transformation matrix,
through which the generated residual signals can be evaluated. So the
proposed design is more explicit and requires less design parameters
in comparison with approaches requiring changing coordinates. To
the best author's knowledge, this is the first time that the sliding
mode technique is applied to detect actuator and sensor faults in a
real boiler. The designing procedure is proposed in a drum boiler in
Synvendska Kraft AB Plant in Malmo, Sweden as a multivariable
and strongly coupled system. It is demonstrated that both sensor and
actuator faults can robustly be detected. Also sensor faults can be
diagnosed and isolated through this method.
Self-Sensing versus Reference Air Gaps
Self-sensing estimates the air gap within an electro
magnetic path by analyzing the bearing coil current and/or voltage
waveform. The self-sensing concept presented in this paper has been
developed within the research project “Active Magnetic Bearings
with Supreme Reliability" and is used for position sensor fault
Within this new concept gap calculation is carried out by an alldigital
analysis of the digitized coil current and voltage waveform.
For analysis those time periods within the PWM period are used,
which give the best results. Additionally, the concept allows the
digital compensation of nonlinearities, for example magnetic
saturation, without degrading signal quality. This increases the
accuracy and robustness of the air gap estimation and additionally
reduces phase delays.
Beneath an overview about the developed concept first
measurement results are presented which show the potential of this
all-digital self-sensing concept.
Detection of Actuator Faults for an Attitude Control System using Neural Network
The objective of this paper is to develop a neural
network-based residual generator to detect the fault in the actuators
for a specific communication satellite in its attitude control system
(ACS). First, a dynamic multilayer perceptron network with dynamic
neurons is used, those neurons correspond a second order linear
Infinite Impulse Response (IIR) filter and a nonlinear activation
function with adjustable parameters. Second, the parameters from the
network are adjusted to minimize a performance index specified by
the output estimated error, with the given input-output data collected
from the specific ACS. Then, the proposed dynamic neural network
is trained and applied for detecting the faults injected to the wheel,
which is the main actuator in the normal mode for the communication
satellite. Then the performance and capabilities of the proposed
network were tested and compared with a conventional model-based
observer residual, showing the differences between these two
methods, and indicating the benefit of the proposed algorithm to
know the real status of the momentum wheel. Finally, the application
of the methods in a satellite ground station is discussed.
Application of Machine Learning Methods to Online Test Error Detection in Semiconductor Test
As in today's semiconductor industries test costs can make up to 50 percent of the total production costs, an efficient test error detection becomes more and more important. In this paper, we present a new machine learning approach to test error detection that should provide a faster recognition of test system faults as well as an improved test error recall. The key idea is to learn a classifier ensemble, detecting typical test error patterns in wafer test results immediately after finishing these tests. Since test error detection has not yet been discussed in the machine learning community, we define central problem-relevant terms and provide an analysis of important domain properties. Finally, we present comparative studies reflecting the failure detection performance of three individual classifiers and three ensemble methods based upon them. As base classifiers we chose a decision tree learner, a support vector machine and a Bayesian network, while the compared ensemble methods were simple and weighted majority vote as well as stacking. For the evaluation, we used cross validation and a specially designed practical simulation. By implementing our approach in a semiconductor test department for the observation of two products, we proofed its practical applicability.
A New Method for Identifying Broken Rotor Bars in Squirrel Cage Induction Motor Based on Particle Swarm Optimization Method
Detection of squirrel cage induction motor (SCIM) broken bars has long been an important but difficult job in the detection area of motor faults. Early detection of this abnormality in the motor would help to avoid costly breakdowns. A new detection method based on particle swarm optimization (PSO) is presented in this paper. Stator current in an induction motor will be measured and characteristic frequency components of faylted rotor will be detected by minimizing a fitness function using pso. Supply frequency and side band frequencies and their amplitudes can be estimated by the proposed method. The proposed method is applied to a faulty motor with one and two broken bars in different loading condition. Experimental results prove that the proposed method is effective and applicable.
Identification, Prediction and Detection of the Process Fault in a Cement Rotary Kiln by Locally Linear Neuro-Fuzzy Technique
In this paper, we use nonlinear system identification method to predict and detect process fault of a cement rotary kiln. After selecting proper inputs and output, an input-output model is identified for the plant. To identify the various operation points in the
kiln, Locally Linear Neuro-Fuzzy (LLNF) model is used. This model is trained by LOLIMOT algorithm which is an incremental treestructure
algorithm. Then, by using this method, we obtained 3
distinct models for the normal and faulty situations in the kiln. One of the models is for normal condition of the kiln with 15 minutes
prediction horizon. The other two models are for the two faulty situations in the kiln with 7 minutes prediction horizon are presented.
At the end, we detect these faults in validation data. The data collected from White Saveh Cement Company is used for in this study.
An Investigative Study into Observer based Non-Invasive Fault Detection and Diagnosis in Induction Motors
A new observer based fault detection and diagnosis
scheme for predicting induction motors- faults is proposed in this
paper. Prediction of incipient faults, using different variants of
Kalman filter and their relative performance are evaluated. Only soft
faults are considered for this work. The data generation, filter
convergence issues, hypothesis testing and residue estimates are
addressed. Simulink model is used for data generation and various
types of faults are considered. A comparative assessment of the
estimates of different observers associated with these faults is
A Comparative Study into Observer based Fault Detection and Diagnosis in DC Motors: Part-I
A model based fault detection and diagnosis
technique for DC motor is proposed in this paper. Fault detection
using Kalman filter and its different variants are compared. Only
incipient faults are considered for the study. The Kalman Filter
iterations and all the related computations required for fault detection
and fault confirmation are presented. A second order linear state
space model of DC motor is used for this work. A comparative
assessment of the estimates computed from four different observers
and their relative performance is evaluated.
Computation of Probability Coefficients using Binary Decision Diagram and their Application in Test Vector Generation
This paper deals with efficient computation of
probability coefficients which offers computational simplicity as
compared to spectral coefficients. It eliminates the need of inner
product evaluations in determination of signature of a combinational
circuit realizing given Boolean function. The method for computation
of probability coefficients using transform matrix, fast transform
method and using BDD is given. Theoretical relations for achievable
computational advantage in terms of required additions in computing
all 2n probability coefficients of n variable function have been
developed. It is shown that for n ≥ 5, only 50% additions are needed
to compute all probability coefficients as compared to spectral
coefficients. The fault detection techniques based on spectral
signature can be used with probability signature also to offer
An Approach in the Improvement of the Reliability of Impedance Relay
The distance protection mainly the impedance relay which is considered as the main protection for transmission lines can be subjected to impedance measurement error which is, mainly, due to the fault resistance and to the power fluctuation. Thus, the impedance relay may not operate for a short circuit at the far end of the protected line (case of the under reach) or operates for a fault beyond its protected zone (case of overreach). In this paper, an approach to fault detection by a distance protection, which distinguishes between the faulty conditions and the effect of overload operation mode, has been developed. This approach is based on the symmetrical components; mainly the negative sequence, and it is taking into account both the effect of fault resistance and the overload situation which both have an effect upon the reliability of the protection in terms of dependability for the former and security for the latter.
Fault Classification of Double Circuit Transmission Line Using Artificial Neural Network
This paper addresses the problems encountered by conventional distance relays when protecting double-circuit transmission lines. The problems arise principally as a result of the mutual coupling between the two circuits under different fault conditions; this mutual coupling is highly nonlinear in nature. An adaptive protection scheme is proposed for such lines based on application of artificial neural network (ANN). ANN has the ability to classify the nonlinear relationship between measured signals by identifying different patterns of the associated signals. One of the key points of the present work is that only current signals measured at local end have been used to detect and classify the faults in the double circuit transmission line with double end infeed. The adaptive protection scheme is tested under a specific fault type, but varying fault location, fault resistance, fault inception angle and with remote end infeed. An improved performance is experienced once the neural network is trained adequately, which performs precisely when faced with different system parameters and conditions. The entire test results clearly show that the fault is detected and classified within a quarter cycle; thus the proposed adaptive protection technique is well suited for double circuit transmission line fault detection & classification. Results of performance studies show that the proposed neural network-based module can improve the performance of conventional fault selection algorithms.