Wireless Sensor Network Simulation for Fault Detection in Industrial
Processes
Rui Pinto
1
, Rosaldo J. F. Rossetti
1,2
and Gil Gonc¸alves
1
1
Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias s/n, 4200-465 Porto, Portugal
2
Artificial Intelligence and Computer Science Lab, University of Porto,
Rua Dr. Roberto Frias s/n, 4200-465 Porto, Portugal
Keywords:
Castalia, Sensor Diagnosis and Validation, Industrial Wireless Sensor Networks.
Abstract:
Sensor data is extremely important to monitor machines at the shop-floor level and its environmental surround-
ing conditions for condition-based monitoring, machine diagnosis and process adaptation to new requirements.
Based on the described scope, self-diagnostics and self-organizing capabilities are core functionalities of any
Industrial Wireless Sensor Network (IWSN). In the present work, a simulated case study was developed with
the main intent of validating techniques implemented for sensor data diagnosis of error detection and equip-
ment failure. The scenarios explored try to mimic some common situations of a manufacturing environment
when dealing with WSNs, where a piece of sensor equipment suddenly stops working or an unpredictable
change in the environment leads to faulty data readings. This paper introduces Castalia and describes how
it was used to simulate a direct application of an Optical Metrology System on an industrial Resistance Spot
Welding process, which is composed of a camera and several luminosity sensors. More specifically, a sensor
data validation module was proposed, implemented and used to extend Castalia functionalities.
1 INTRODUCTION
Nowadays, several European initiatives towards smart
manufacturing systems and Industry 4.0 are a cur-
rent subject of research, aiming at the improvement
of the European Industry competitiveness regarding
other leading markets. This can be achieved by turn-
ing shop-floor production methods more flexible and
efficient facing the constant changes in production,
which is driven by consumer demands. Since con-
sumers’ preferences are becoming more customized
and competitiveness between companies is extremely
high, manufacturers must quickly adapt their product
to new trends. Usually, the company pioneer on hav-
ing a new product available on the market have the
upper hand over the competition. When a mass pro-
duction model is used, maintaining a large envelope
of products or enlarging it with more product vari-
ants is extremely difficult and entails a great effort and
cost due to the inflexibility of mass production man-
ufacturing systems. To support the mass customiza-
tion paradigm at the shop-floor level, the production
systems should be capable of rapidly reconfiguring as
product demand varies, as well as does machine pa-
rameter calibration during all production stages. The
time spent to calibrate and to adjust the machine pro-
cess parameters when a new product variation should
be performed, or after a maintenance phase, can be re-
duced if the machines’ parameter adjustment is done
automatically instead of the usual trial-and-error ap-
proach, by performing destructive tests to evaluate
the process quality. Monitoring machine’s execution
is extremely important and, to do so, sensors are de-
ployed on the shop-floor to infer surrounding environ-
mental conditions and adapt the machine execution
accordingly.
An Optical Metrology System (OMS) is a system
where optical measurements are used for several in-
dustrial applications, e.g. for robot guidance when
optical metrology sensors are mounted on a robot
arm. In this case, a OMS is used on a Resistance Spot
Welding (RSW) process, to infer if the metal parts to
be weld are well positioned. In order to insure the
correct setting up and easy ramping up of the system,
in site factory sensor positioning adjustment and im-
age setup is a significant procedure, which involves
configuration of camera parameters, such as exposure
and gain. With help of luminosity sensors by mea-
suring the luminosity conditions in site, the camera
parameters can be adjusted on the fly, according to
Pinto, R., Rossetti, R. and Gonçalves, G.
Wireless Sensor Network Simulation for Fault Detection in Industrial Processes.
DOI: 10.5220/0006011003330338
In Proceedings of the 6th International Conference on Simulation and Modeling Methodologies, Technologies and Applications (SIMULTECH 2016), pages 333-338
ISBN: 978-989-758-199-1
Copyright
c
2016 by SCITEPRESS Science and Technology Publications, Lda. All rights reserved
333
the context. This work focus on the simulation of an
OMS applied to a RSW process using Castalia. The
goal was to understand the behaviour of the luminos-
ity sensors, specially when they are malfunctioning.
A sensor data detection module was implemented in
Castalia and used on a simulated version of the de-
scribed environment.
The paper is organized in four more different sec-
tions. Section 2 details the approaches regarding
IWSN, the main methods for sensor data validation
and categorize WSN simulators, specially Castalia.
Section 3 identifies the case study used to develop the
simulation scenario. Section 4 depicts all the results
obtained, whereas in Section 5 final remarks about the
overall work exposed in the paper and further steps to
be followed are presented.
2 INDUSTRIAL WIRELESS
SENSOR NETWORKS
In the past few years WSNs have become more in-
teresting to be explored in and applied to several do-
mains. Their use was motivated mainly due to lat-
est advances in wireless communications as well as
in more reliable, robust and long-lasting hardware.
These factors have a great impact on the feasibility
of installation, when it is difficult to use wired so-
lutions, either by harsh location or high number of
sensor nodes used and also because of the easy main-
tenance and cabling reduced costs. As main advan-
tages, Chen et al. (Chen et al., 2015) pinpoints the
large coverage area, ubiquitous information, fast com-
munication via RF and self-organisation throughout
the direct communication between entities. A Smart
Sensor Platform (Ramamurthy et al., 2007) was de-
veloped, which applies the plug and play concept by
means of hardware interface, payload, communica-
tion between sensors and actuators, and ultimately
allows for software update using ’over-the-air’ pro-
gramming. Cao et al. (Cao et al., 2008) developed a
distributed approach to put closer sensors and actua-
tors in a collaborative environment using WSNs and,
Chen et al. (Chen et al., 2015), push this approach
forward considering the same methodology, but tak-
ing into account all the industrial domain restrictions.
Despite the huge potential of WSNs, these so-
lutions still have several issues and future research
challenges. Data collected from WSNs is prone
to be faulty due to internal and external influences,
such as environmental effects, hardware malfunc-
tions, software problems, energy constrains, net-
work issues, security threats, among others, as shown
elsewhere (Tolle et al., 2005), (Barrenetxea et al.,
2008), (Ramanathan et al., 2006) and (Szewczyk
et al., 2004). IWSNs are used to monitor real-
time production equipment in the factory and the
surrounding environmental conditions, acting accord-
ingly when changes are observed. According to Neu-
mann (Neumann, 2007), there are important restric-
tions in industrial applications to be met, such as real-
timeliness, functional safety, security, energy effi-
ciency, and Quality of Service (QoS). So, IWSNs face
some challenges, such as safety-critical functions, se-
curity and privacy of collected data, availability to
avoid complete production stop when failures occur,
latency/retransmission of messages, support for ac-
tuators (by using the same sensor controller), effi-
cient integration with existing automation infrastruc-
tures, scalability, coexistence and wireless communi-
cation interference avoidance and energy harvesting
(
˚
Akerberg et al., 2011).
2.1 Sensor Data Validation
To maintain QoS, one should be able to detect and
deal with compromised sensor nodes during opera-
tion. To determine whether a sensor node is mal-
functioning, validation methods are applied to sen-
sor data, aiming to find devious sensor readings from
normal ones. There is no such an ideal validation
method, because they are very dependent on sensor
measurement conditions and the overall environment
context (Freitas et al., 2010), (Branisavljevi
´
c et al.,
2011), (Bertrand-Krajewski et al., 2003), (Vasconce-
los et al., 2012), and (Liu et al., 2013). Usually, sev-
eral methods are applied successively to the sensor
data, because each method is suitable to detect par-
ticular types of faulty data. Sensor data validation
methods are typically divided into online and offline
methods, where online methods are efficient, simpler
to implement and demand less data processing, and
offline techniques, such as Bayesian Networks, Ar-
tificial Neural Networks and Regression Techniques,
are more robust and complex techniques, which are
suitable to process data not in real-time.
The most common WSNs’ data fault types are:
Out-of-range faults - values out of predefined mini-
mum and maximum boundaries; Struck-at-fault se-
quence of values that have little or no variation for a
large period of time; Outliers misplaced data sam-
ples that represent a sensor misbehaviour, which can
be caused by sensor malfunctioning or changes in sur-
rounding environment; Stop Communication gaps in
the dataset caused by an absence of sensor informa-
tion on the gateway, due to power outage or commu-
nication problems; Devious Data when the behaviour
of a certain sensor is devious from the majority, and it
SIMULTECH 2016 - 6th International Conference on Simulation and Modeling Methodologies, Technologies and Applications
334
persists for a large period of time. A graphical exam-
ple of these faults’ behaviour (on a temperature sen-
sor) is presented in Figure 1.
According to Sharma et al. (Sharma et al.,
2010), Ravichandran and Arulappan (Ravichandran
and Arulappan, 2013), the most common techniques
used to perform online detection of the described sen-
sor data faults are Min/Max Detection, Flat Line De-
tection, Modified Z-Score, No value Detection and
Spatial Correlation. The Min/Max Detection finds
out-of-range faults using upper and lower limits that
are defined by process limitations. On the other hand,
the Modified Z-Score finds outliers faults which, de-
spite being inside the process limitations, are values
that are unusual when compared to the sensor data
history. The Flat Line Detection finds struck-at-faults,
which are characterized by little or no variation in
data and the No value Detection detects situations
when the data stops being communicated. Finally, the
Spatial Correlation is the technique used to compare
datasets of several sensors nodes physically located
near to one another, and if one of them presents a de-
vious dataset in comparison to its neighbours, then the
corresponding sensor node is probably faulty.
2.2 WSN Simulation
A WSN simulation consists in using simulators
specifically designed to imitate WSNs behaviour.
Traditionally, the three main methodologies for
analysing the performance of WSNs are physical
measurements, which consists in setting up all the
physical nodes and collecting sensor data, analytical
methods, and computer simulation. Since deploying
a WSNs requires a huge effort, due to constrains re-
garding the cost associated with hardware and the fact
that analytical models are not effective, because of the
complexity of the models for WSNs regarding energy
limitation, decentralized collaboration and fault toler-
ance, simulation is the only feasible approach to the
quantitative analysis of sensor networks, getting ac-
cess to fine grained results easier than with real world
experiments (Dwivedi et al., 2010). Because there
are so many simulators with many different charac-
teristics, Eriksson (Eriksson, 2009) proposes to cat-
egorize WSNs as Generic Network Simulators - fo-
cus more on network aspects, such as radio protocols,
network stacks and channel distortions; Code Level
Simulators - focus more on the simulation of the sen-
sor nodes, such as deployable code and functional-
ity logic; Firmware Level Simulators - focus more on
emulating the sensor node, such as microprocessor,
radio chip and other peripherals.
Song (Song et al., 2011) implemented a fault de-
tection mechanism to analyse the stability and relia-
bility of data transmission in a ZigBee network, which
was simulated on the NS-2 simulator. Results focus
on the data loss rate in the communication between
sensor nodes. Dai (Dai et al., 2011) also proposed
a fault detection mechanism, but focused more on
the delays introduced by the wireless communication
networks, where the control system was simulated in
MATLAB and the network-induced delays were sim-
ulated in OMNeT++. Both Song and Dai focused
more on faults with root cause on network aspects. On
the other hand, Zhang (Zhang et al., 2009) and Szc-
zodrak (Szczodrak et al., 2008) used Castalia to im-
plement a fault detection algorithm based on temporal
and spatial correlations of sensor data from neighbour
sensor nodes, classifying each node as good or faulty.
2.2.1 Castalia
Castalia (Boulis, 2007) was the simulator chosen
for this work. Figure 2 presents Castalia’s architec-
ture, where each module accepts messages from other
modules or itself and, according to the message, it ex-
ecutes a given code. The nodes do not connect to
each other directly, but through the Wireless Chan-
nel module, which estimate the average path loss be-
tween two nodes using the Lognormal Shadowing.
The nodes are also linked through Physical Process
modules that they monitor, which ”feed” the sensors
with data. For every physical process there is one
module which holds the ”truth” on the quantity of the
physical process that is representing. The nodes sam-
ple the physical process in space and time to get their
sensor readings.
The Physical Process modules are based on an ar-
bitrary number of point sources whose ’influence’ is
diffused over space and they can change their posi-
tion and their value over time. The effect of multiple
sources in a certain point is additive. Calculating the
value of the physical process at a certain location and
at a certain time is represented in Equation (1), where
V (p, t) denotes the value of the physical process at
point p and at time t, V
i
(t) denotes the value of the i
th
source at time t, d
i
(p, t) denotes the distance of point
p from the i
th
source at time t, K and a are parame-
ters that determine how the value from a source is dif-
fused. N(0, θ) is a zero-mean Gaussian random vari-
able with standard deviation θ. The ”ground truth”
offered by the physical process is distorted by the in-
accuracies of the sensing devices, implemented by the
Sensor Manager.
V (p, t) =
i
V
i
(t)
(Kd
i
(p, t) + 1)
a
+ N(0, θ) (1)
Regarding the internal structure of a node, the Appli-
Wireless Sensor Network Simulation for Fault Detection in Industrial Processes
335
Figure 1: Sensor Data Faults Characterization.
Figure 2: Model Structure of Castalia.
cation module is the one that specifies the algorithm
that receives sensor data and acts accordingly. The
MAC and Routing modules define several communi-
cation protocols, which can be used by the nodes. The
Mobility module defines the nodes position and mo-
bility pattern. The Sensor Manager defines the sens-
ing devices present in each node, by introducing a
distortion of the ground truth offered by the physical
process. The Resource Manager defines the energy
consumed by the different components of the node.
3 METHODOLOGY
The simulation scenario tried to mimic a OMS,
which is composed by an IWSN, where all nodes are
equipped with luminosity sensors and a central node
is equipped with a camera. This OMS is used to anal-
yse the quality of a RSW process, namely if both parts
to be weld are correctly placed and, in the end of the
welding cycle, evaluates the quality of the weld. This
analysis consists in capturing and processing a camera
image captured, which must have a minimum quality,
otherwise, image analysis will be impossible. In order
to avoid excessive darkness/clarity in the image, the
exposure index of the camera must be calibrated ac-
cording to the luminosity conditions in the surround-
ing environment. This process consists in controlling
the lightness and darkness of the image, which can be
done by the camera light meter. Since the camera light
meter may have a lower accuracy and, it measures
only one single point of luminosity per sample, sev-
eral luminosity sensors are used to infer the luminos-
ity conditions around the welding area and improve
the control of the camera exposure index.
In this case, a camera is placed right on top of the
two electrodes that will weld the parts together. In or-
der to evaluate the luminosity conditions, nine lumi-
nosity sensors were placed around the electrodes. All
the sensor data is processed on a gateway node, result-
ing on an average of the nine luminosity points. The
simulation of this scenario will allow to implement
and test a sensor fault detection module before being
deployed in a real environment. Figure 3 represents
a real application of this scenario and the schema of
the virtual world to be simulated. There are eight sen-
sor nodes (represented by the green circles), each one
equipped with a luminosity sensor that outputs val-
ues between 0 and 100%. At the center of the world
are placed the luminosity source and sensor node 0.
Even numbered sensor nodes are placed at 20 cm dis-
tance around the center, so their output should be sim-
ilar. The same is true for odd numbered sensor nodes,
which are placed at 50 cm distance and, in conse-
quence, their output should be smaller than the even
numbered sensor nodes.
Regarding the simulation scenario, only one lumi-
nosity source was considered (placed at the center of
the world), which had default parametrization values,
namely K equals 0.25, a equals 1.0 and θ equals 0.2.
The output of the source was defined at a theoretical
value of 65%. According to the simulated world im-
SIMULTECH 2016 - 6th International Conference on Simulation and Modeling Methodologies, Technologies and Applications
336
Figure 3: OMS used on a RSW process: a) real prototype;
b) simulation.
plemented, sensor node 0 outputs higher luminosity
values (around 65%), because it is the one closest to
the luminosity source. Then, even numbered sensor
nodes output values around 55% and odd numbered
sensor nodes output values around 30%. For the com-
munication module, the radio’s parameters used are
the ones proposed in the IEEE 802.15 Task Group 6
documents, the routing protocol is the Multipath Ring
Routing and the MAC protocol is the IEEE 802.15.4.
4 TESTS AND PRELIMINARY
RESULTS
Some tests were performed in order to simulate devi-
ations in sensor readings. The sensor manager’s de-
vice noise property was changed accordingly, which
is by default as low as possible (but larger than 0).
When this value increases, the difference of sensor
output values compared to normal outputs also in-
creases. Bigger deviations resulted on out-of-range
and outlier faults. On the other hand, a device noise
equals to 0 corresponds to a null variation, resulting
on struck-at-fault samples. Figure 4 plots the percent-
age of simulated errors in the dataset of sensor node
0 and the efficiency of the techniques for error detec-
tion, calculated by determining the false positives and
false negatives.
The considered dataset had 18% of out-of-range
faults, 36% of outliers and spikes and 14% of struck-
at-faults. The remaining 32% of the dataset is normal
data. The Min/Max Detection pinpointed all out-of-
range faults, presenting zero false positive and nega-
tive. The Flat Line Detection technique missed one
out of 14 stuck-at-faults present in the data set, pre-
senting 1 false positive and zero false negatives. The
Modified Z-Score detected only 12 out of 18 outliers
present in the sensor data set, having 6 false positives
and zero false negatives. The Modified Z-Score tech-
niques efficiency depends greatly on the data set his-
tory, namely the rate between the number of normal
samples and the number of outliers, and the differ-
Figure 4: Efficiency of techniques for sensor data error de-
tection.
ence between the normal and outlier sample values.
In order to improve the efficiency of this method, the
number of normal samples must be much larger than
the number of outliers.
5 CONCLUSIONS AND FUTURE
WORK
The present work simulates an OMS applied to an in-
dustrial RSW process, which analyses the position of
materials to be welded by means of a camera and sev-
eral luminosity sensors. The simulation implements
an IWSN whose nodes have a luminosity sensor. In
Castalia, sensors are ”fed” by a luminosity physical
process and run a sensor data validation module to
detect failing sensors. Such a sensor data validation
module implements Min/Max Detection, Flat Line
Detection and Modified Z-Score, which are used to
detect out-of-range faults, struck-at-faults, and out-
liers and spikes, respectively. All techniques per-
formed as expected, even though the Modified Z-
Score accuracy demonstrated to depend greatly on the
history of dataset samples, as well as on the mean dif-
ference between normal and outlier samples as dis-
cussed in the result analysis.
Regarding future steps, the sensor data validation
module can be improved by implementing the Spatial
Correlation method, considering complex scenarios
with different location luminosity sources and detect-
ing the presence and location of a sensor fault. This
complex feature implies the use of online sensor fu-
sion techniques of several heterogeneous sensor data
or offline complex methods, such as machine learn-
ing techniques. Such an approach to using multiple
data types and sources is the essence of a multi-agent
methodology (Passos et al., 2011) and architecture
(Rossetti et al., 2007) currently under development,
also with applications to the industrial domain (Braga
et al., 2008).
Wireless Sensor Network Simulation for Fault Detection in Industrial Processes
337
REFERENCES
˚
Akerberg, J., Gidlund, M., and Bj
¨
orkman, M. (2011). Fu-
ture research challenges in wireless sensor and actu-
ator networks targeting industrial automation. In In-
dustrial Informatics (INDIN), pages 410–415. IEEE.
Barrenetxea, G., Ingelrest, F., Schaefer, G., Vetterli, M.,
Couach, O., and Parlange, M. (2008). Sensorscope:
Out-of-the-box environmental monitoring. In Infor-
mation Processing in Sensor Networks (IPSN’08),
pages 332–343. IEEE.
Bertrand-Krajewski, J.-L., Bardin, J.-P., Mourad, M., and
Beranger, Y. (2003). Accounting for sensor calibra-
tion, concentration heterogeneity, measurement and
sampling uncertainties in monitoring urban drainage
systems. Water Science & Technology, 47:95–102.
Boulis, A. (2007). Castalia: revealing pitfalls in design-
ing distributed algorithms in wsn. In 5th International
Conference on Embedded networked sensor systems,
pages 407–408. ACM.
Braga, R., Rossetti, R., Reis, L. P., and Oliveira, E. C.
(2008). Applying multi-agent systems to simulate dy-
namic control in flexible manufacturing scenarios. In
Cybernetics and Systems 2008, pages 488–493, Vi-
enna. OSGK.
Branisavljevi
´
c, N., Kapelan, Z., and Prodanovi
´
c, D. (2011).
Improved real-time data anomaly detection using con-
text classification. Journal of Hydroinformatics,
13(3):307–323.
Cao, X., Chen, J., Xiao, Y., and Sun, Y. (2008). Distributed
collaborative control using wireless sensor and actu-
ator networks. In Future Generation Communication
and Networking (FGCN’08), pages 3–6. IEEE.
Chen, J., Li, H., Sheng, D., and Li, W. (2015). A hy-
brid data-driven modeling method on sensor condi-
tion monitoring and fault diagnosis for power plants.
International Journal of Electrical Power & Energy
Systems, 71:274–284.
Dai, X., Long, Z., Yang, B., and Tan, X. (2011). Robust
fault detection observer in wireless networked control
systems. In Chinese Control and Decision Conference
(CCDC), pages 2147–2152. IEEE.
Dwivedi, A., Patle, V., and Vyas, O. (2010). Investigation
on effectiveness of simulation results for wireless sen-
sor networks. Information Processing and Manage-
ment, pages 202–208.
Eriksson, J. (2009). Detailed simulation of heterogeneous
wireless sensor networks. Licentiate thesis, Uppsala
University, Sweden.
Freitas, T. R., Coelho, A., and Rossetti, R. (2010). Correct-
ing routing information through GPS data processing.
In Intelligent Transportation Systems (ITSC), pages
706–711. IEEE.
Liu, S., Araujo, M., Brunskill, E., Rossetti, R., Barros,
J., and Krishnan, R. (2013). Understanding sequen-
tial decisions via inverse reinforcement learning. In
Mobile Data Management (MDM), pages 177–186.
IEEE.
Neumann, P. (2007). Communication in industrial automa-
tionwhat is going on? Control Engineering Practice,
15(11):1332–1347.
Passos, L. S., Rossetti, R., and Gabriel, J. (2011). An agent
methodology for processes, the environment, and ser-
vices. In Intelligent Transportation Systems (ITSC),
pages 2124–2129. IEEE.
Ramamurthy, H., Prabhu, B., Gadh, R., and Madni, A. M.
(2007). Wireless industrial monitoring and control us-
ing a smart sensor platform. Sensors Journal, IEEE,
7(5):611–618.
Ramanathan, N., Balzano, L., Burt, M., Estrin, D., Harmon,
T., Harvey, C., Jay, J., Kohler, E., Rothenberg, S., and
Srivastava, M. (2006). Rapid deployment with confi-
dence: Calibration and fault detection in environmen-
tal sensor networks. Center for Embedded Network
Sensing.
Ravichandran, J. and Arulappan, A. I. (2013). Data valida-
tion algorithm for wireless sensor networks. Interna-
tional Journal of Distributed Sensor Networks, 2013.
Rossetti, R., Oliveira, E. C., and Bazzan, A. (2007). To-
wards a specification of a framework for sustainable
transportation analysis. In 13th Portuguese Confer-
ence on Artificial Intelligence, EPIA, Guimar
˜
aes, Por-
tugal, pages 179–190. APPIA.
Sharma, A. B., Golubchik, L., and Govindan, R. (2010).
Sensor faults: Detection methods and prevalence in
real-world datasets. ACM Transactions on Sensor Net-
works (TOSN), 6(3):23.
Song, C.-C., Feng, C.-F., Wang, C.-H., and Liaw, D.-C.
(2011). Simulation and experimental analysis of a
zigbee sensor network with fault detection and recon-
figuration mechanism. In Asian Control Conference
(ASCC), pages 659–664. IEEE.
Szczodrak, M., Zahedi, S., Ji, P., Mylaraswamy, D., Sri-
vastava, M., and Young, R. (2008). Simulation frame-
work for qoi characterization of sensor networks in the
presence of faults.
Szewczyk, R., Mainwaring, A., Polastre, J., Anderson, J.,
and Culler, D. (2004). An analysis of a large scale
habitat monitoring application. In 2nd International
Conference on Embedded networked sensor systems,
pages 214–226. ACM.
Tolle, G., Polastre, J., Szewczyk, R., Culler, D., Turner,
N., Tu, K., Burgess, S., Dawson, T., Buonadonna,
P., Gay, D., et al. (2005). A macroscope in the red-
woods. In 3rd International Conference on Embedded
networked sensor systems, pages 51–63. ACM.
Vasconcelos, G., Petry, M., Almeida, J. E., Rossetti, R., and
Coelho, A. L. (2012). Using UWB for human tra-
jectory extraction. In 24th European Modeling and
Simulation Symposium, EMSS, pages 428–433.
Zhang, C., Ren, J., Gao, C., Yan, Z., and Li, L. (2009). Sen-
sor fault detection in wireless sensor networks. In IET
International Communication Conference on Wireless
Mobile and Computing, pages 66–69.
SIMULTECH 2016 - 6th International Conference on Simulation and Modeling Methodologies, Technologies and Applications
338