SlideShare a Scribd company logo
International Journal of Technical Research and Applications e-ISSN: 2320-8163,
www.ijtra.com Volume 3, Issue 2 (Mar-Apr 2015), PP. 07-11
7 | P a g e
FAULT DETECTION AND DIAGNOSIS IN
CONTINUOUS STIRRED TANK REACTOR
(CSTR)
R. Gowthami, Dr. S. Vijayachitra
Department of EIE
Kongu Engineering College
Erode, India
gowthami.ei@gmail.com, dr.svijayachitra@gmail.com
Abstract—Continuous Stirred Tank Reactor (CSTR) here is
considered as a nonlinear process. The CSTR is widely used in
many chemical plants. Due to changes in process parameters the
accuracy of final product can be reduced. In order to get accurate
final product the faults developed in CSTR during the chemical
reaction need to be diagnosed. If not, the faults may lead to
degrade the performance of the system. For this purpose there
are various fault diagnosis methods are to be considered. Among
the methods, the neural network predictive controller can be used
to detect faults in CSTR. Servo response is performed to
understand the behavior of CSTR. By detecting various faults
and with suitable control techniques, the accuracy of the
desirable products in CSTR can be improved.
Index Terms—Continuous Stirred Tank Reactor, Neural
Network Predictive Controller, Fuzzy Logic Controller, Fault
detection and estimation.
I. INTRODUCTION
The Continuous Stirred Tank Reactor (CSTR) system is
highly nonlinear, exothermic, irreversible first order process.
In CSTR, when the reactants are added into the tank the stirrer
will stir the reactants to give desired product. Once the
equipment is running, it is usually operated at steady state and
designed to achieve well mixing. The CSTR also known as
back mix reactor is commonly used as perfect reactor type in
chemical engineering. A CSTR is a model which is used to
estimate individual operation variables while using a
continuous agitated tank reactor in order to obtain the required
output. CSTR is widely used in the organic chemicals industry
for medium and large scale production. The reactor is widely
operated by three control loops that will regulate the outlet
temperature and the inlet flow rate of the reactant tank level.
During the process the heat will be generated and hence the
heat of reaction can be removed by a coolant medium that
flows through a jacket around the reactor. During the CSTR
process the faults occur which further leads to inaccurate
result. A fault is defined as an unexpected change of the
system functionality which may be related to a failure in a
physical component such as sensor and actuator. In order to
detect various types of faults in CSTR the Neural Network
Predictive Controller can be applied.
Figure 1. Continuous Stirred Tank Reactor
II. MATHEMATICAL MODELING OF CSTR
A reaction will create new components while
simultaneously reducing reactant concentrations. The reaction
may give off heat or give required energy to progress the
process [2]. Figure 1. shows the CSTR consists of one inlet
reactants and one outlet flow rate. In CSTR the outlet
concentration is controlled by changing the volumetric flow
rate [8]. Figure 2. shows the characteristic of the concentration
and volumetric flow rate. Figure 3. shows the servo response
of Continuous Stirred Tank Reactor. If the outlet concentration
is not equal to the set point then the volumetric flow rate is
adjusted in order to make outlet concentration to reach the
desired set point.
By the mass balance (typical unit, Kg/s),
The Rate of change of mass in the system=The Rate of mass
flow in –Rate of mass flow out
(1)
= Inlet reactant concentration in reactor
= Outlet reactant concentration in reactor
=Inlet feed flow rate
=Volume of reactor
=Frequency factor
=Activation energy
=Universal gas constant
=Reactor temperature
0 2 4 6 8 10 12 14 16 18 20
1.4
1.6
1.8
2
Time
C
A
0 2 4 6 8 10 12 14 16 18 20
19
19.5
20
20.5
21
time
volumetricflowofcoolant
Figure 2. Behavior of Manipulated Variable- Controller Variable in
Continuous Stirred Tank Reactor
 
RT
E
RT
E
eKra
CaeKCaCai
V
F
dt
dCa




0
0
Cai
Ca
F
V
0K
E
R
T
International Journal of Technical Research and Applications e-ISSN: 2320-8163,
www.ijtra.com Volume 3, Issue 2 (Mar-Apr 2015), PP. 07-11
8 | P a g e
0 10 20 30 40 50 60
0
0.5
1
1.5
2
Time
C
A
0 10 20 30 40 50 60
0
5
10
15
20
time
volumetricflowofcoolant
Figure 3. Servo Response of Continuous Stirred Tank Reactor
III. METHOD OF FAULT DIAGNOSIS
The term fault is generally defined as a departure from an
acceptance range of an observed variable [6], [7]. Figure 4.
shows that the faults developed in the plant diagnosed by the
sensor and the sensor value will then be compared with the set
point in the comparator. If there is any error in the sensor then
the feedback controller generates a signal to the actuator. The
actuator signal will be given to the diagnosis system. If any
error occurs in the actuator, the diagnosis system will provide
an alarm. The fault diagnosis system provides the supervision
system with information about the onset, location and severity
of the faults. Based on the system inputs and outputs together
it will make fault decision information from the fault diagnosis
system.
Figure 4. General Components of Fault Diagnosis Framework
FUZZY LOGIC CONTROLLER
Fuzzy logic is an extension of crisp set. A fuzzy logic
system is a type of control system that work based on fuzzy
logic. The fuzzy logic controller is based on mathematical
system that evaluates input values for fuzzy logic system in
terms of sensible variables. The logical variables take values
in two ways they are continuous and discrete values. If the
logical variable uses continuous value which ranges from 0 to
1 in contrast to digital logic and if logical variables for fuzzy
logic operate on discrete values which is either 1 or 0 that is
true or false respectively. Fuzzy system is useful in any
situation in which the measurement depends strongly on the
context or human opinion. A fuzzy reasoning algorithm
establishes a preliminary fuzzy diagnosis system.
Fuzzy logic controller is commonly used in machine
control operations. When the logic involved in fuzzy logic
controller can deal with concepts which can be expressed in
terms as neither true nor false but considerably as partially
true. In such cases the rules are created to deal both with true,
partially true, false and partially false. Fuzzy sets mean the
input variables. The input variables in a fuzzy operating
machine can be obtained by mapping the sets of membership
functions. Fuzzificaion means the series of action for
converting a crisp value to a fuzzy value.
The fuzzy logic controller uses inaccurate or not precise
input and output variables by using membership function. The
membership function can be expressed in terms of linguistic
variables. In the fuzzy logic controller the if-then rules are
used to identify the fault and fault free data. At the same time
it provide the symptoms for faulty and fault less data by
predefined fuzzy sets. The amount of fault that present is
obtained by comparing the rules of reference model and with
the rules of fuzzy reference model which is identified by using
data obtained from CSTR plant [2],[3]. Here the process
historical data is used [7]. The process historical data means
data obtained from CSTR plant.
IV. FUZZY DECISION MAKING
The fuzzy logic controller is used for direct integration of
the human operator into the fault detection and supervision of
CSTR process. Changes in any variable in the process will
reduce the accuracy of the final product. It also provides
supervision of entire process. In the supervision of the process
the alarm will be provided. If any error occurs in the process
the alarm will be generated. For this purpose the fuzzy
decision making is necessary. In order to avoid any incorrect
decision which may cause false alarm then the fuzzy decision
making is used to decide whether the fault has occurred and at
which place in the process the fault has occurred. The fuzzy
decision making is similar to the expert system and
supervisory control.
V. FAULT ESTIMATION BY FUZZY LOGIC CONTROLLER
The fuzzy logic system handles the imprecision of input
and output variables directly by defining them with
memberships and sets that can be expressed in linguistic
terms. The fuzzy reference models are made up from if-then
rules which describe the symptoms of faulty and fault free of
predefined fuzzy reference sets. A particular model is defined
by specifying the values of the elements of its associated fuzzy
relational array. Each element of the array is a measure of the
credibility that the associated rules correctly describes the
behavior of the system around the particular operating point.
For fault detection and estimation in CSTR using Fuzzy Logic
Controller. The fault level in CSTR depends on four variables
such as feed flow rate (F0), outlet reactant concentration (CA0),
coolant temperature (TC0) and feed temperature (T0). These
four variables fault level depends on the volume of reactor
(V), reactant concentration in the reactor (CA), reactor
temperature (T) and Jacket temperature (TC) [5]. Based on
these fault range the Fuzzy Logic Controller is developed. The
Fuzzy Logic Controller consists of four inputs and four
outputs. The membership function is developed for those four
inputs and four outputs. The rules are created for these
variables. Based on the input fault range the fault level is
estimated by using Fuzzy Logic Controller.
The figure.5 shows various inputs to the Fuzzy Inference
System such as volume of reactor (V), reactant concentration
in the reactor (CA), reactor temperature (T) and jacket
temperature (TC) and the fault outputs considered for Fuzzy
Inference System are feed flow rate (F0), outlet reactant
concentration (CA0), coolant temperature (TC0) and feed
temperature (T0).
Figure 5. Fuzzy Inference System Editor for overall fault
International Journal of Technical Research and Applications e-ISSN: 2320-8163,
www.ijtra.com Volume 3, Issue 2 (Mar-Apr 2015), PP. 07-11
9 | P a g e
With the help of Fuzzy Logic Controller, various faults
considered are detected and estimated and the results obtained
are shown in Table 1
Table 1: Fuzzy Logic Based Fault Estimation in CSTR
Similarly the fault level for individual variable can also be
obtained. Figure.6 shows the fault in feed flow rate (F0)
depends on volume of reactor (V), reactant concentration in
the reactor (CA), reactor temperature (T) and jacket
temperature (TC). After developing the fuzzy logic controller
the estimation of fault level in feed flow rate (F0) can be done
is shown in table 2.
Figure 6. Fuzzy Inference System Editor for fault in feed flow rate (F0)
Table 2: Fuzzy Logic Based Fault Estimation for Feed Flow Rate
Similarly the fault level in outlet reactant concentration
(CA0) is based on volume of reactor (V), reactant concentration
in the reactor (CA), reactor temperature (T) and jacket
temperature (TC) as shown in the figure 7. Table 3 shows the
estimation of fault level in outlet reactant concentration (CA0).
Figure 7. Fuzzy Inference System Editor for fault in outlet reactant
concentration (CA0)
Table 3: Fuzzy Logic Based Fault Estimation for Outlet Reactant
Concentration
Similarly the fault level in coolant temperature (TC0)
depends on volume of reactor (V), reactant concentration in
the reactor (CA), reactor temperature (T) and jacket
temperature (TC) as shown in the figure.8. After developing
the fuzzy logic controller the estimation of fault level in
coolant temperature (TC0) can be obtained as shown in table 4.
Figure 8. Fuzzy Inference System Editor for fault in coolant temperature
(TC0)
Table 4: Fuzzy Logic Based Fault Estimation for Coolant Temperature
(TC0)
Similarly the fault level in feed temperature (T0) depends
on volume of reactor (V), reactant concentration in the reactor
(CA), reactor temperature (T) and jacket temperature (TC) as
shown in the figure 9. Table 5 shows the estimation of fault
level in feed temperature (T0).
Figure 9. Fuzzy Inference System Editor for fault in feed temperature
(T0)
Table.5 Fuzzy Logic Based Fault Estimation for feed temperature (T0)
VI. NEURO PREDICTIVE XL SOFTWARE
Prediction means estimate, forecast and predict the future
condition for this purpose the neural predictive XL software is
used. In Microsoft excel the predictions can be done by a built
in tool but the correctness of its results is greatly decreased
when non-linear relationship occur or if any missing data are
present. Neural networks are a tried, tested and most
commonly used technology for most complex prediction
operation. It is modeled by considering the human brain. The
neural network is joined onto one another networks of separate
processors [1], [4]. By changing the connections of these
neural networks the finding answer to a problem can be
identified. One of the major reasons that the analysts not using
these latest methods such as neural networks in order to
improve forecasts because the neural network method is very
difficult to monitor. Neuro XL Predictor removes the mental
process and practical limit by hiding the complicated nature of
its latest neural network based methods while taking profit of
analysts having present information in mind. Since users make
the act of predicting the future through the commonly seen
International Journal of Technical Research and Applications e-ISSN: 2320-8163,
www.ijtra.com Volume 3, Issue 2 (Mar-Apr 2015), PP. 07-11
10 | P a g e
excel point of interaction, it reduces the learning time, greatly
decreasing the intervening period between loading the
software and performing useful predictions. The application is
extremely known automatically and not difficult to use this
neuro XL predictor software. In neural predictive XL by the
knowledge of previous inputs and outputs it is able to predict
what the future output for present input can be identified. In
this neural predictive XL the sensor fault input and output data
is loaded in the excel sheet by using neural predictive XL
software the future output is predicted. Table.6 the fault in the
output can be predicted by using neuro predictor XL. In
Continuous Stirred Tank Reactor the sensor fault is
considered. Neuro predictor XL is a spreadsheet which is used
to detect fault in Continuous Stirred Tank Reactor. The sensor
fault in CSTR is used [9]. In the sensor fault the flow rate of
the liquid at the inlet ( ), control valve opening
( ), temperature of the inlet reactant ( ), control valve
opening ( ), temperature of the tank ( ), temperature of
the outlet coolant ( ), flow rate of coolant ( ), liquid
level ( L ) are the variables considered in CSTR. By loading
the sensor faults of CSTR in the spread sheet the neuro
predictor XL software is used to predict future fault in CSTR.
The neuro predictor XL software predict future fault in CSTR
by seeing present and past faults in sensor of CSTR. So this
neuro predictor XL software is useful for analysts to predict
future fault in CSTR. By predicting the future fault the
analysts can take some preventive measure to reduce the fault
before its effect felt in the process. By doing these measure the
final outcome of the process can be maintained.
Table.6 Prediction of Fault in CSTR
Where,
= Flow rate of liquid at inlet ( )
= Control valve opening
= Temperature of the inlet reactant(ºC)
= Control valve opening
= Temperature of the tank (ºC)
= Temperature of the outlet coolant
water (ºC)
= Flow rate of coolant ( scm /3
)
L = Liquid level (cm)
VII. NEURAL NETWORK PREDICTIVE CONTROLLER
The Mathematical Model of CSTR for two tank system is
A reaction will create new components while simultaneously
reducing reactant concentrations [9]. The reaction may give
off heat or give required energy to proceeds the process.
Figure 10. shows the CSTR consists of two inlet reactants and
one outlet flow rate. The two inlet reactants are W1 which is
inlet flow rate of concentrated feed and W2 is inlet flow rate of
diluted feed [2], [7].
By the mass balance (typical unit, Kg/s),
The Rate of change of mass in the system=The Rate of mass
flow in –Rate of mass flow out
0
W
2
W
1
W
dt
dh
 (1)
hCV
0
W  (2)
)hCV(
2
W
1
W
dt
dh
 (3)
Where CV =0.2
)h0.2(
2
W
1
W
dt
dh
 (4)
Where
h =Liquid level (cm)
1
W =Inlet flow rate of the concentrated feed /s)(cm3
2
W =Inlet flow rate of the diluted feed /s)(cm3
0
W =Outlet flow rate /s)(cm3
The concentration of the continuous stirred tank reactor is
given in the following equation
b
r)
h
2
W
)(
b
C
b2
(C)
h
1
W
)(
b
C
b1
(C
dt
b
dC

(5)
Where,
2)
b
C
2
k(1
b
C
1
k
b
r

 (6)
Where,
b
C =The concentration of product at the output of the
process (
3
mol/cm )
b1
C =Inlet concentration feed (
3
mol/cm )
b2
C =Outlet concentration feed (
3
mol/cm )
1
W =Inlet flow rate of the concentrated feed ( /scm3
)
2
W =Outlet flow rate of the diluted feed ( /scm3
)
2
k,
1
k =The constants associate with the rate of consumption
h =Liquid level (cm)
Figure 10.Continuous Stirred Tank Reactor
cvL
jF
iF scm /3
cvF
iT
cvL
0T
0jT
jF
iF
cvF iT
0jT
0T
Predicted
Output
International Journal of Technical Research and Applications e-ISSN: 2320-8163,
www.ijtra.com Volume 3, Issue 2 (Mar-Apr 2015), PP. 07-11
11 | P a g e
Figure 11. Neural Network Predictive Controller
The neural network predictive controller is a graphical
user interface tool as shown in figure 11. From that neural
network predictive controller select the plant identification
which consists of neural network plant model. The plant
model predicts the future plant outputs. The neural network
plant model consists of one hidden layer. By generating
training data by giving series of random reference signal the
plant input and output data will be generated. By using trainlm
the plant model training is done from this the training data for
NN predictive controller will be obtained as shown in figure
12. and Validation data for NN predictive controller will be
generated as shown in figure 13.
0 500 1000
0
1
2
3
4
Input
0 500 1000
20
21
22
23
Plant Output
0 500 1000
-0.05
0
0.05
0.1
0.15
Error
time (s)
0 500 1000
20
21
22
23
NN Output
time (s)
Figure 12. Training Data for NN Predictive Controller
0 100 200 300
0
1
2
3
4
Input
0 100 200 300
20
21
22
23
Plant Output
0 100 200 300
-0.02
0
0.02
0.04
Error
time (s)
0 100 200 300
20
21
22
23
NN Output
time (s)
Figure 13. Validation Data for NN Predictive Controller
Figure 14. shows the servo response of CSTR. By using the
neural network predictive controller plant model the
characteristic of concentration in CSTR is obtained.
0 20 40 60 80 100 120
20
20.5
21
21.5
22
22.5
23
Time in Secs
Concentrationinmol/(cm)
3
Servo Response ofCSTR
Plant Output
Reference Signal
Figure 14. Servo Response of CSTR
VIII. CONCLUSION AND FUTURE SCOPE
The application of Continuous Stirred Tank Reactor is
very essential nowadays. Using material balance condition, the
CSTR process is effectively modeled which provides a better
understanding of its characteristic behavior of the process. The
modeling is effectively verified by its servo response. Various
sensor faults considered in CSTR are detected and estimated in
percentage by means of using Neural Network Predictive
Controller and Fuzzy Logic Controller and found good results.
This fault detection and estimation work can be further
extended to actuator faults also.
IX. REFERENCES
[1] Dong-Juan Li., 2014, Neural network control for a class of
continuous stirred tank reactor process with dead-zone input,
Elsevier Journal of Neurocomputing, Vol.131, pp.453-459.
[2] Kanse Nitin G., Dhanke P.B. and Thombare Abhijit ., 2012,
Modeling and Simulation Study for Complex Reaction by
Using Polymath, Research Journal of Chemical Sciences,
Vol.2, No.4, pp.79-85.
[3] Manikandan P., Geetha M., Jubi K., Jovitha Jerome.,2013,
Fault Tolerant Fuzzy Gain Scheduling Proportional-Integral-
Derivative Controller for Continuous Stirred Tank Reactor,
Australian Journal of Basic and Applied Sciences, Vol.7,
No.13, pp.84-93.
[4] Ribhan Zafira Abdul Rahman, Azura Che Soh, Noor Fadzlina
binti Muhammad.,2010, Fault Detection and Diagnosis for
Continuous Stirred Tank Reactor Using Neural Network,
Kathmandu University Journal of Science, Engineering and
Technology, Vol.5, No.2, pp. 66-74.
[5] Souragh Dash, Raghunathan Rengaswamy, Venkat
Venkatasubramanian.,2003, Fuzzy- logic based trend
classification for fault diagnosis of chemical processes, Elsevier
Journal of Computers and Chemical Engineering, Vol.27,
pp.347-362.
[6] Venkat Venkatasubramanian, Raghunathan Rengaswamy,
Kewen Yin, Surya N. Kavuri., 2003, A review of process fault
detection and diagnosis Part I:Quantitative model-based
methods’, Elsevier Journal of Computers and Chemical
Engineering, Vol.27, pp.293-311.
[7] Venkat Venkatasubramanian, Raghunathan Rengaswamy,
Surya N. Kavuri, Kewen Yin., 2003, A review of process fault
detection and diagnosis Part III: Process history based methods,
Elsevier Journal of Computers and Chemical Engineering,
Vol.27, pp.327-346.
[8] Vishal Vishnoi, Subhransu Padhee, Gagandeep Kaur., 2012,
Controller Performance Evaluation for Concentration of
Isothermal Continuous Stirred Tank Reactor, International
Journal of Scientific and Research Publication, Vol.2, No.6,
pp.2250-3153.
[9] Yunosuke Maki and Kenneth A. Loparo.,1997, A Neural-
Network Approach to Fault Detection and Diagnosis in
Industrial Processes, IEEE Transactions on Control Systems
Technology, Vol.5, No.6, pp.529-541.

More Related Content

DOC
Mse procedure delta
PPTX
Operating system 26 monitors
PDF
Shimadzu hplc standard_operation_procedure_by_dr._sana_mustafa
PDF
EFFECT OF PRUNING AND SKIFFING ON GROWTH AND PRODUCTIVITY OF DARJEELING TEA (...
PDF
DYNAMIC MONITORING OF THE EFFECT OF SPECIAL KINESITHERAPEUTIC PROGRAM ON PAIN...
PDF
IDENTIFICATION OF SUPPLY CHAIN MANAGEMENT PROBLEMS: A REVIEW
PDF
MECHANISMS OF PHOTOPERIOD IN REGULATION OF RICE FLOWERING
PDF
PHYSICO-CHEMICAL AND BACTERIOLOGICAL ASSESSMENT OF RIVER MUDZIRA WATER IN MUB...
Mse procedure delta
Operating system 26 monitors
Shimadzu hplc standard_operation_procedure_by_dr._sana_mustafa
EFFECT OF PRUNING AND SKIFFING ON GROWTH AND PRODUCTIVITY OF DARJEELING TEA (...
DYNAMIC MONITORING OF THE EFFECT OF SPECIAL KINESITHERAPEUTIC PROGRAM ON PAIN...
IDENTIFICATION OF SUPPLY CHAIN MANAGEMENT PROBLEMS: A REVIEW
MECHANISMS OF PHOTOPERIOD IN REGULATION OF RICE FLOWERING
PHYSICO-CHEMICAL AND BACTERIOLOGICAL ASSESSMENT OF RIVER MUDZIRA WATER IN MUB...

Viewers also liked (20)

PDF
ROLE OF ICT IN ACHIEVING COMPLETE GENDER EQUALITY IN INDIA
PDF
STUDY OF CARBOHYDRATE METABOLISM IN SEVERE ACUTE MALNUTRITION AND CORRELATION...
PDF
OPEN LOOP ANALYSIS OF CASCADED HBRIDGE MULTILEVEL INVERTER USING PDPWM FOR PH...
PDF
TRACKING AND CHECKING CARGO CONTAINERS PILFERAGE USING ELECTRONIC LOCK
PDF
STATE OF ART IN MODERN RESISTANCE SPOT WELDING
PDF
AN INSIDE LOOK IN THE ELECTRICAL STRUCTURE OF THE BATTERY MANAGEMENT SYSTEM T...
PDF
EFFICIENT EMBEDDED SURVEILLANCE SYSTEM WITH AUTO IMAGE CAPTURING AND EMAIL SE...
PDF
IMPACT ANALYSIS OF DUST POLLUTION WITHIN KATRAJ
PDF
UNDERSTANDING ENTREPRENEURSHIP: IMPACT OF OVERCONFIDENCE ON ENTREPRENEURSHIP
PDF
STUDIES ON THE ANTIBIOTIC RESISTANCE USING URINARY TRACT ISOLATES OF E.COLI.
PDF
AN EXPERIMENTAL STUDY ON SEPARATION OF WATER FROM THE ATMOSPHERIC AIR
PDF
COMPARATIVE STUDY OF BELL PEPPER ON THE ASPECTS OF THEIR APPROXIMATE ANALYSIS...
PDF
IDENTIFICATIONS OF ELECTRICAL AND ELECTRONIC EQUIPMENT POLYMER WASTE TYPES US...
PDF
FACTORS AFFECTING PROJECT SUSTAINABILITY BEYOND DONOR’S SUPPORT. THE CASE OF ...
PDF
EVALUATION OF DRAINAGE WATER QUALITY FOR IRRIGATION BY INTEGRATION BETWEEN IR...
PDF
EFFECT OF DIFFERENT CONCENTRATIONS OF AUXINS AND COMBINATION WITH KINETIN ON ...
PDF
COMMODITY DERIVATIVE MARKETS IN INDIA
PDF
SCANNING ELECTRON MICROSCOPE OF DISINFECTANTS EXPOSED PSEUDOMONAS AERUGINOSA ...
PDF
ERROR ESTIMATION IN DEVELOPING GIS MAPS USING DIFFERENT INPUT METHODS OF LAND...
ROLE OF ICT IN ACHIEVING COMPLETE GENDER EQUALITY IN INDIA
STUDY OF CARBOHYDRATE METABOLISM IN SEVERE ACUTE MALNUTRITION AND CORRELATION...
OPEN LOOP ANALYSIS OF CASCADED HBRIDGE MULTILEVEL INVERTER USING PDPWM FOR PH...
TRACKING AND CHECKING CARGO CONTAINERS PILFERAGE USING ELECTRONIC LOCK
STATE OF ART IN MODERN RESISTANCE SPOT WELDING
AN INSIDE LOOK IN THE ELECTRICAL STRUCTURE OF THE BATTERY MANAGEMENT SYSTEM T...
EFFICIENT EMBEDDED SURVEILLANCE SYSTEM WITH AUTO IMAGE CAPTURING AND EMAIL SE...
IMPACT ANALYSIS OF DUST POLLUTION WITHIN KATRAJ
UNDERSTANDING ENTREPRENEURSHIP: IMPACT OF OVERCONFIDENCE ON ENTREPRENEURSHIP
STUDIES ON THE ANTIBIOTIC RESISTANCE USING URINARY TRACT ISOLATES OF E.COLI.
AN EXPERIMENTAL STUDY ON SEPARATION OF WATER FROM THE ATMOSPHERIC AIR
COMPARATIVE STUDY OF BELL PEPPER ON THE ASPECTS OF THEIR APPROXIMATE ANALYSIS...
IDENTIFICATIONS OF ELECTRICAL AND ELECTRONIC EQUIPMENT POLYMER WASTE TYPES US...
FACTORS AFFECTING PROJECT SUSTAINABILITY BEYOND DONOR’S SUPPORT. THE CASE OF ...
EVALUATION OF DRAINAGE WATER QUALITY FOR IRRIGATION BY INTEGRATION BETWEEN IR...
EFFECT OF DIFFERENT CONCENTRATIONS OF AUXINS AND COMBINATION WITH KINETIN ON ...
COMMODITY DERIVATIVE MARKETS IN INDIA
SCANNING ELECTRON MICROSCOPE OF DISINFECTANTS EXPOSED PSEUDOMONAS AERUGINOSA ...
ERROR ESTIMATION IN DEVELOPING GIS MAPS USING DIFFERENT INPUT METHODS OF LAND...
Ad

Similar to FAULT DETECTION AND DIAGNOSIS IN CONTINUOUS STIRRED TANK REACTOR (CSTR) (20)

PDF
FUZZY LOGIC Control of CONTINUOUS STIRRED TANK REACTOR
PDF
Design of Controllers for Continuous Stirred Tank Reactor
PDF
Intelligent Controller Design for a Chemical Process
PDF
Iaetsd design and implementation of intelligent
PDF
SENSOR FAULT IDENTIFICATION IN COMPLEX SYSTEMS | J4RV3I12007
PDF
Class 10 mathematical modeling of continuous stirred tank reactor systems (...
PDF
INDUCTIVE LOGIC PROGRAMMING FOR INDUSTRIAL CONTROL APPLICATIONS
PDF
PERFORMANCE ASSESSMENT OF ANFIS APPLIED TO FAULT DIAGNOSIS OF POWER TRANSFORMER
PDF
40220130405010 2-3
PDF
76201948
PDF
Enhancing the Performance of An Industrial Boiler Using Fuzzy Logic Controller
PDF
Enhancing the Performance of An Industrial Boiler Using Fuzzy Logic Controller
PDF
STABILITY ANALYSIS AND CONTROL OF A 3-D AUTONOMOUS AI-YUAN-ZHI-HAO HYPERCHAOT...
PDF
Brain emotional learning based intelligent controller and its application to ...
PDF
Comparison of pid and mpc controllers for continuous stirred tank reactor (cs...
PDF
Comparison of pid and mpc controllers for continuous stirred tank reactor (cs...
PDF
TUNING OF GAINS IN BASIS WEIGHT USING FUZZY CONTROLLERS
PDF
Br4301389395
PPTX
Mathematical modeling of continuous stirred tank reactor systems (cstr)
PDF
Db36619623
FUZZY LOGIC Control of CONTINUOUS STIRRED TANK REACTOR
Design of Controllers for Continuous Stirred Tank Reactor
Intelligent Controller Design for a Chemical Process
Iaetsd design and implementation of intelligent
SENSOR FAULT IDENTIFICATION IN COMPLEX SYSTEMS | J4RV3I12007
Class 10 mathematical modeling of continuous stirred tank reactor systems (...
INDUCTIVE LOGIC PROGRAMMING FOR INDUSTRIAL CONTROL APPLICATIONS
PERFORMANCE ASSESSMENT OF ANFIS APPLIED TO FAULT DIAGNOSIS OF POWER TRANSFORMER
40220130405010 2-3
76201948
Enhancing the Performance of An Industrial Boiler Using Fuzzy Logic Controller
Enhancing the Performance of An Industrial Boiler Using Fuzzy Logic Controller
STABILITY ANALYSIS AND CONTROL OF A 3-D AUTONOMOUS AI-YUAN-ZHI-HAO HYPERCHAOT...
Brain emotional learning based intelligent controller and its application to ...
Comparison of pid and mpc controllers for continuous stirred tank reactor (cs...
Comparison of pid and mpc controllers for continuous stirred tank reactor (cs...
TUNING OF GAINS IN BASIS WEIGHT USING FUZZY CONTROLLERS
Br4301389395
Mathematical modeling of continuous stirred tank reactor systems (cstr)
Db36619623
Ad

More from International Journal of Technical Research & Application (20)

PDF
STUDY & PERFORMANCE OF METAL ON METAL HIP IMPLANTS: A REVIEW
PDF
EXPONENTIAL SMOOTHING OF POSTPONEMENT RATES IN OPERATION THEATRES OF ADVANCED...
PDF
POSTPONEMENT OF SCHEDULED GENERAL SURGERIES IN A TERTIARY CARE HOSPITAL - A T...
PDF
STUDY OF NANO-SYSTEMS FOR COMPUTER SIMULATIONS
PDF
ENERGY GAP INVESTIGATION AND CHARACTERIZATION OF KESTERITE CU2ZNSNS4 THIN FIL...
PDF
POD-PWM BASED CAPACITOR CLAMPED MULTILEVEL INVERTER
PDF
DIGITAL COMPRESSING OF A BPCM SIGNAL ACCORDING TO BARKER CODE USING FPGA
PDF
MODELLING THE IMPACT OF FLOODING USING GEOGRAPHIC INFORMATION SYSTEM AND REMO...
PDF
LI-ION BATTERY TESTING FROM MANUFACTURING TO OPERATION PROCESS
PDF
QUALITATIVE RISK ASSESSMENT AND MITIGATION MEASURES FOR REAL ESTATE PROJECTS ...
PDF
SCOPE OF REPLACING FINE AGGREGATE WITH COPPER SLAG IN CONCRETE- A REVIEW
PDF
IMPLEMENTATION OF METHODS FOR TRANSACTION IN SECURE ONLINE BANKING
PDF
EFFECT OF TRANS-SEPTAL SUTURE TECHNIQUE VERSUS NASAL PACKING AFTER SEPTOPLASTY
PDF
THE CONSTRUCTION PROCEDURE AND ADVANTAGE OF THE RAIL CABLE-LIFTING CONSTRUCTI...
PDF
TIME EFFICIENT BAYLIS-HILLMAN REACTION ON STEROIDAL NUCLEUS OF WITHAFERIN-A T...
PDF
A STUDY ON THE FRESH PROPERTIES OF SCC WITH FLY ASH
PDF
PERFORMANCE ANALYSIS OF MICROSTRIP PATCH ANTENNA USING COAXIAL PROBE FEED TEC...
PDF
OVERVIEW OF TCP PERFORMANCE IN SATELLITE COMMUNICATION NETWORKS
PDF
PARAMETRIC MODELING OF VOLTAGE DROP IN POWER DISTRIBUTION NETWORKS
PDF
INVESTIGATION OF COVERAGE LEVEL AND THE AVAILABILITY OF GSM SIGNAL IN EKPOMA,...
STUDY & PERFORMANCE OF METAL ON METAL HIP IMPLANTS: A REVIEW
EXPONENTIAL SMOOTHING OF POSTPONEMENT RATES IN OPERATION THEATRES OF ADVANCED...
POSTPONEMENT OF SCHEDULED GENERAL SURGERIES IN A TERTIARY CARE HOSPITAL - A T...
STUDY OF NANO-SYSTEMS FOR COMPUTER SIMULATIONS
ENERGY GAP INVESTIGATION AND CHARACTERIZATION OF KESTERITE CU2ZNSNS4 THIN FIL...
POD-PWM BASED CAPACITOR CLAMPED MULTILEVEL INVERTER
DIGITAL COMPRESSING OF A BPCM SIGNAL ACCORDING TO BARKER CODE USING FPGA
MODELLING THE IMPACT OF FLOODING USING GEOGRAPHIC INFORMATION SYSTEM AND REMO...
LI-ION BATTERY TESTING FROM MANUFACTURING TO OPERATION PROCESS
QUALITATIVE RISK ASSESSMENT AND MITIGATION MEASURES FOR REAL ESTATE PROJECTS ...
SCOPE OF REPLACING FINE AGGREGATE WITH COPPER SLAG IN CONCRETE- A REVIEW
IMPLEMENTATION OF METHODS FOR TRANSACTION IN SECURE ONLINE BANKING
EFFECT OF TRANS-SEPTAL SUTURE TECHNIQUE VERSUS NASAL PACKING AFTER SEPTOPLASTY
THE CONSTRUCTION PROCEDURE AND ADVANTAGE OF THE RAIL CABLE-LIFTING CONSTRUCTI...
TIME EFFICIENT BAYLIS-HILLMAN REACTION ON STEROIDAL NUCLEUS OF WITHAFERIN-A T...
A STUDY ON THE FRESH PROPERTIES OF SCC WITH FLY ASH
PERFORMANCE ANALYSIS OF MICROSTRIP PATCH ANTENNA USING COAXIAL PROBE FEED TEC...
OVERVIEW OF TCP PERFORMANCE IN SATELLITE COMMUNICATION NETWORKS
PARAMETRIC MODELING OF VOLTAGE DROP IN POWER DISTRIBUTION NETWORKS
INVESTIGATION OF COVERAGE LEVEL AND THE AVAILABILITY OF GSM SIGNAL IN EKPOMA,...

Recently uploaded (20)

PPTX
Lecture Notes Electrical Wiring System Components
DOCX
573137875-Attendance-Management-System-original
PDF
TFEC-4-2020-Design-Guide-for-Timber-Roof-Trusses.pdf
PDF
keyrequirementskkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkk
PPTX
CH1 Production IntroductoryConcepts.pptx
PPTX
CARTOGRAPHY AND GEOINFORMATION VISUALIZATION chapter1 NPTE (2).pptx
PDF
Digital Logic Computer Design lecture notes
PPTX
MCN 401 KTU-2019-PPE KITS-MODULE 2.pptx
PPTX
KTU 2019 -S7-MCN 401 MODULE 2-VINAY.pptx
PPTX
Internet of Things (IOT) - A guide to understanding
PPTX
OOP with Java - Java Introduction (Basics)
PPTX
IOT PPTs Week 10 Lecture Material.pptx of NPTEL Smart Cities contd
PDF
Enhancing Cyber Defense Against Zero-Day Attacks using Ensemble Neural Networks
PPTX
bas. eng. economics group 4 presentation 1.pptx
PPTX
web development for engineering and engineering
PPT
CRASH COURSE IN ALTERNATIVE PLUMBING CLASS
PPTX
Geodesy 1.pptx...............................................
PDF
July 2025 - Top 10 Read Articles in International Journal of Software Enginee...
PPTX
Engineering Ethics, Safety and Environment [Autosaved] (1).pptx
PPTX
Foundation to blockchain - A guide to Blockchain Tech
Lecture Notes Electrical Wiring System Components
573137875-Attendance-Management-System-original
TFEC-4-2020-Design-Guide-for-Timber-Roof-Trusses.pdf
keyrequirementskkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkk
CH1 Production IntroductoryConcepts.pptx
CARTOGRAPHY AND GEOINFORMATION VISUALIZATION chapter1 NPTE (2).pptx
Digital Logic Computer Design lecture notes
MCN 401 KTU-2019-PPE KITS-MODULE 2.pptx
KTU 2019 -S7-MCN 401 MODULE 2-VINAY.pptx
Internet of Things (IOT) - A guide to understanding
OOP with Java - Java Introduction (Basics)
IOT PPTs Week 10 Lecture Material.pptx of NPTEL Smart Cities contd
Enhancing Cyber Defense Against Zero-Day Attacks using Ensemble Neural Networks
bas. eng. economics group 4 presentation 1.pptx
web development for engineering and engineering
CRASH COURSE IN ALTERNATIVE PLUMBING CLASS
Geodesy 1.pptx...............................................
July 2025 - Top 10 Read Articles in International Journal of Software Enginee...
Engineering Ethics, Safety and Environment [Autosaved] (1).pptx
Foundation to blockchain - A guide to Blockchain Tech

FAULT DETECTION AND DIAGNOSIS IN CONTINUOUS STIRRED TANK REACTOR (CSTR)

  • 1. International Journal of Technical Research and Applications e-ISSN: 2320-8163, www.ijtra.com Volume 3, Issue 2 (Mar-Apr 2015), PP. 07-11 7 | P a g e FAULT DETECTION AND DIAGNOSIS IN CONTINUOUS STIRRED TANK REACTOR (CSTR) R. Gowthami, Dr. S. Vijayachitra Department of EIE Kongu Engineering College Erode, India gowthami.ei@gmail.com, dr.svijayachitra@gmail.com Abstract—Continuous Stirred Tank Reactor (CSTR) here is considered as a nonlinear process. The CSTR is widely used in many chemical plants. Due to changes in process parameters the accuracy of final product can be reduced. In order to get accurate final product the faults developed in CSTR during the chemical reaction need to be diagnosed. If not, the faults may lead to degrade the performance of the system. For this purpose there are various fault diagnosis methods are to be considered. Among the methods, the neural network predictive controller can be used to detect faults in CSTR. Servo response is performed to understand the behavior of CSTR. By detecting various faults and with suitable control techniques, the accuracy of the desirable products in CSTR can be improved. Index Terms—Continuous Stirred Tank Reactor, Neural Network Predictive Controller, Fuzzy Logic Controller, Fault detection and estimation. I. INTRODUCTION The Continuous Stirred Tank Reactor (CSTR) system is highly nonlinear, exothermic, irreversible first order process. In CSTR, when the reactants are added into the tank the stirrer will stir the reactants to give desired product. Once the equipment is running, it is usually operated at steady state and designed to achieve well mixing. The CSTR also known as back mix reactor is commonly used as perfect reactor type in chemical engineering. A CSTR is a model which is used to estimate individual operation variables while using a continuous agitated tank reactor in order to obtain the required output. CSTR is widely used in the organic chemicals industry for medium and large scale production. The reactor is widely operated by three control loops that will regulate the outlet temperature and the inlet flow rate of the reactant tank level. During the process the heat will be generated and hence the heat of reaction can be removed by a coolant medium that flows through a jacket around the reactor. During the CSTR process the faults occur which further leads to inaccurate result. A fault is defined as an unexpected change of the system functionality which may be related to a failure in a physical component such as sensor and actuator. In order to detect various types of faults in CSTR the Neural Network Predictive Controller can be applied. Figure 1. Continuous Stirred Tank Reactor II. MATHEMATICAL MODELING OF CSTR A reaction will create new components while simultaneously reducing reactant concentrations. The reaction may give off heat or give required energy to progress the process [2]. Figure 1. shows the CSTR consists of one inlet reactants and one outlet flow rate. In CSTR the outlet concentration is controlled by changing the volumetric flow rate [8]. Figure 2. shows the characteristic of the concentration and volumetric flow rate. Figure 3. shows the servo response of Continuous Stirred Tank Reactor. If the outlet concentration is not equal to the set point then the volumetric flow rate is adjusted in order to make outlet concentration to reach the desired set point. By the mass balance (typical unit, Kg/s), The Rate of change of mass in the system=The Rate of mass flow in –Rate of mass flow out (1) = Inlet reactant concentration in reactor = Outlet reactant concentration in reactor =Inlet feed flow rate =Volume of reactor =Frequency factor =Activation energy =Universal gas constant =Reactor temperature 0 2 4 6 8 10 12 14 16 18 20 1.4 1.6 1.8 2 Time C A 0 2 4 6 8 10 12 14 16 18 20 19 19.5 20 20.5 21 time volumetricflowofcoolant Figure 2. Behavior of Manipulated Variable- Controller Variable in Continuous Stirred Tank Reactor   RT E RT E eKra CaeKCaCai V F dt dCa     0 0 Cai Ca F V 0K E R T
  • 2. International Journal of Technical Research and Applications e-ISSN: 2320-8163, www.ijtra.com Volume 3, Issue 2 (Mar-Apr 2015), PP. 07-11 8 | P a g e 0 10 20 30 40 50 60 0 0.5 1 1.5 2 Time C A 0 10 20 30 40 50 60 0 5 10 15 20 time volumetricflowofcoolant Figure 3. Servo Response of Continuous Stirred Tank Reactor III. METHOD OF FAULT DIAGNOSIS The term fault is generally defined as a departure from an acceptance range of an observed variable [6], [7]. Figure 4. shows that the faults developed in the plant diagnosed by the sensor and the sensor value will then be compared with the set point in the comparator. If there is any error in the sensor then the feedback controller generates a signal to the actuator. The actuator signal will be given to the diagnosis system. If any error occurs in the actuator, the diagnosis system will provide an alarm. The fault diagnosis system provides the supervision system with information about the onset, location and severity of the faults. Based on the system inputs and outputs together it will make fault decision information from the fault diagnosis system. Figure 4. General Components of Fault Diagnosis Framework FUZZY LOGIC CONTROLLER Fuzzy logic is an extension of crisp set. A fuzzy logic system is a type of control system that work based on fuzzy logic. The fuzzy logic controller is based on mathematical system that evaluates input values for fuzzy logic system in terms of sensible variables. The logical variables take values in two ways they are continuous and discrete values. If the logical variable uses continuous value which ranges from 0 to 1 in contrast to digital logic and if logical variables for fuzzy logic operate on discrete values which is either 1 or 0 that is true or false respectively. Fuzzy system is useful in any situation in which the measurement depends strongly on the context or human opinion. A fuzzy reasoning algorithm establishes a preliminary fuzzy diagnosis system. Fuzzy logic controller is commonly used in machine control operations. When the logic involved in fuzzy logic controller can deal with concepts which can be expressed in terms as neither true nor false but considerably as partially true. In such cases the rules are created to deal both with true, partially true, false and partially false. Fuzzy sets mean the input variables. The input variables in a fuzzy operating machine can be obtained by mapping the sets of membership functions. Fuzzificaion means the series of action for converting a crisp value to a fuzzy value. The fuzzy logic controller uses inaccurate or not precise input and output variables by using membership function. The membership function can be expressed in terms of linguistic variables. In the fuzzy logic controller the if-then rules are used to identify the fault and fault free data. At the same time it provide the symptoms for faulty and fault less data by predefined fuzzy sets. The amount of fault that present is obtained by comparing the rules of reference model and with the rules of fuzzy reference model which is identified by using data obtained from CSTR plant [2],[3]. Here the process historical data is used [7]. The process historical data means data obtained from CSTR plant. IV. FUZZY DECISION MAKING The fuzzy logic controller is used for direct integration of the human operator into the fault detection and supervision of CSTR process. Changes in any variable in the process will reduce the accuracy of the final product. It also provides supervision of entire process. In the supervision of the process the alarm will be provided. If any error occurs in the process the alarm will be generated. For this purpose the fuzzy decision making is necessary. In order to avoid any incorrect decision which may cause false alarm then the fuzzy decision making is used to decide whether the fault has occurred and at which place in the process the fault has occurred. The fuzzy decision making is similar to the expert system and supervisory control. V. FAULT ESTIMATION BY FUZZY LOGIC CONTROLLER The fuzzy logic system handles the imprecision of input and output variables directly by defining them with memberships and sets that can be expressed in linguistic terms. The fuzzy reference models are made up from if-then rules which describe the symptoms of faulty and fault free of predefined fuzzy reference sets. A particular model is defined by specifying the values of the elements of its associated fuzzy relational array. Each element of the array is a measure of the credibility that the associated rules correctly describes the behavior of the system around the particular operating point. For fault detection and estimation in CSTR using Fuzzy Logic Controller. The fault level in CSTR depends on four variables such as feed flow rate (F0), outlet reactant concentration (CA0), coolant temperature (TC0) and feed temperature (T0). These four variables fault level depends on the volume of reactor (V), reactant concentration in the reactor (CA), reactor temperature (T) and Jacket temperature (TC) [5]. Based on these fault range the Fuzzy Logic Controller is developed. The Fuzzy Logic Controller consists of four inputs and four outputs. The membership function is developed for those four inputs and four outputs. The rules are created for these variables. Based on the input fault range the fault level is estimated by using Fuzzy Logic Controller. The figure.5 shows various inputs to the Fuzzy Inference System such as volume of reactor (V), reactant concentration in the reactor (CA), reactor temperature (T) and jacket temperature (TC) and the fault outputs considered for Fuzzy Inference System are feed flow rate (F0), outlet reactant concentration (CA0), coolant temperature (TC0) and feed temperature (T0). Figure 5. Fuzzy Inference System Editor for overall fault
  • 3. International Journal of Technical Research and Applications e-ISSN: 2320-8163, www.ijtra.com Volume 3, Issue 2 (Mar-Apr 2015), PP. 07-11 9 | P a g e With the help of Fuzzy Logic Controller, various faults considered are detected and estimated and the results obtained are shown in Table 1 Table 1: Fuzzy Logic Based Fault Estimation in CSTR Similarly the fault level for individual variable can also be obtained. Figure.6 shows the fault in feed flow rate (F0) depends on volume of reactor (V), reactant concentration in the reactor (CA), reactor temperature (T) and jacket temperature (TC). After developing the fuzzy logic controller the estimation of fault level in feed flow rate (F0) can be done is shown in table 2. Figure 6. Fuzzy Inference System Editor for fault in feed flow rate (F0) Table 2: Fuzzy Logic Based Fault Estimation for Feed Flow Rate Similarly the fault level in outlet reactant concentration (CA0) is based on volume of reactor (V), reactant concentration in the reactor (CA), reactor temperature (T) and jacket temperature (TC) as shown in the figure 7. Table 3 shows the estimation of fault level in outlet reactant concentration (CA0). Figure 7. Fuzzy Inference System Editor for fault in outlet reactant concentration (CA0) Table 3: Fuzzy Logic Based Fault Estimation for Outlet Reactant Concentration Similarly the fault level in coolant temperature (TC0) depends on volume of reactor (V), reactant concentration in the reactor (CA), reactor temperature (T) and jacket temperature (TC) as shown in the figure.8. After developing the fuzzy logic controller the estimation of fault level in coolant temperature (TC0) can be obtained as shown in table 4. Figure 8. Fuzzy Inference System Editor for fault in coolant temperature (TC0) Table 4: Fuzzy Logic Based Fault Estimation for Coolant Temperature (TC0) Similarly the fault level in feed temperature (T0) depends on volume of reactor (V), reactant concentration in the reactor (CA), reactor temperature (T) and jacket temperature (TC) as shown in the figure 9. Table 5 shows the estimation of fault level in feed temperature (T0). Figure 9. Fuzzy Inference System Editor for fault in feed temperature (T0) Table.5 Fuzzy Logic Based Fault Estimation for feed temperature (T0) VI. NEURO PREDICTIVE XL SOFTWARE Prediction means estimate, forecast and predict the future condition for this purpose the neural predictive XL software is used. In Microsoft excel the predictions can be done by a built in tool but the correctness of its results is greatly decreased when non-linear relationship occur or if any missing data are present. Neural networks are a tried, tested and most commonly used technology for most complex prediction operation. It is modeled by considering the human brain. The neural network is joined onto one another networks of separate processors [1], [4]. By changing the connections of these neural networks the finding answer to a problem can be identified. One of the major reasons that the analysts not using these latest methods such as neural networks in order to improve forecasts because the neural network method is very difficult to monitor. Neuro XL Predictor removes the mental process and practical limit by hiding the complicated nature of its latest neural network based methods while taking profit of analysts having present information in mind. Since users make the act of predicting the future through the commonly seen
  • 4. International Journal of Technical Research and Applications e-ISSN: 2320-8163, www.ijtra.com Volume 3, Issue 2 (Mar-Apr 2015), PP. 07-11 10 | P a g e excel point of interaction, it reduces the learning time, greatly decreasing the intervening period between loading the software and performing useful predictions. The application is extremely known automatically and not difficult to use this neuro XL predictor software. In neural predictive XL by the knowledge of previous inputs and outputs it is able to predict what the future output for present input can be identified. In this neural predictive XL the sensor fault input and output data is loaded in the excel sheet by using neural predictive XL software the future output is predicted. Table.6 the fault in the output can be predicted by using neuro predictor XL. In Continuous Stirred Tank Reactor the sensor fault is considered. Neuro predictor XL is a spreadsheet which is used to detect fault in Continuous Stirred Tank Reactor. The sensor fault in CSTR is used [9]. In the sensor fault the flow rate of the liquid at the inlet ( ), control valve opening ( ), temperature of the inlet reactant ( ), control valve opening ( ), temperature of the tank ( ), temperature of the outlet coolant ( ), flow rate of coolant ( ), liquid level ( L ) are the variables considered in CSTR. By loading the sensor faults of CSTR in the spread sheet the neuro predictor XL software is used to predict future fault in CSTR. The neuro predictor XL software predict future fault in CSTR by seeing present and past faults in sensor of CSTR. So this neuro predictor XL software is useful for analysts to predict future fault in CSTR. By predicting the future fault the analysts can take some preventive measure to reduce the fault before its effect felt in the process. By doing these measure the final outcome of the process can be maintained. Table.6 Prediction of Fault in CSTR Where, = Flow rate of liquid at inlet ( ) = Control valve opening = Temperature of the inlet reactant(ºC) = Control valve opening = Temperature of the tank (ºC) = Temperature of the outlet coolant water (ºC) = Flow rate of coolant ( scm /3 ) L = Liquid level (cm) VII. NEURAL NETWORK PREDICTIVE CONTROLLER The Mathematical Model of CSTR for two tank system is A reaction will create new components while simultaneously reducing reactant concentrations [9]. The reaction may give off heat or give required energy to proceeds the process. Figure 10. shows the CSTR consists of two inlet reactants and one outlet flow rate. The two inlet reactants are W1 which is inlet flow rate of concentrated feed and W2 is inlet flow rate of diluted feed [2], [7]. By the mass balance (typical unit, Kg/s), The Rate of change of mass in the system=The Rate of mass flow in –Rate of mass flow out 0 W 2 W 1 W dt dh  (1) hCV 0 W  (2) )hCV( 2 W 1 W dt dh  (3) Where CV =0.2 )h0.2( 2 W 1 W dt dh  (4) Where h =Liquid level (cm) 1 W =Inlet flow rate of the concentrated feed /s)(cm3 2 W =Inlet flow rate of the diluted feed /s)(cm3 0 W =Outlet flow rate /s)(cm3 The concentration of the continuous stirred tank reactor is given in the following equation b r) h 2 W )( b C b2 (C) h 1 W )( b C b1 (C dt b dC  (5) Where, 2) b C 2 k(1 b C 1 k b r   (6) Where, b C =The concentration of product at the output of the process ( 3 mol/cm ) b1 C =Inlet concentration feed ( 3 mol/cm ) b2 C =Outlet concentration feed ( 3 mol/cm ) 1 W =Inlet flow rate of the concentrated feed ( /scm3 ) 2 W =Outlet flow rate of the diluted feed ( /scm3 ) 2 k, 1 k =The constants associate with the rate of consumption h =Liquid level (cm) Figure 10.Continuous Stirred Tank Reactor cvL jF iF scm /3 cvF iT cvL 0T 0jT jF iF cvF iT 0jT 0T Predicted Output
  • 5. International Journal of Technical Research and Applications e-ISSN: 2320-8163, www.ijtra.com Volume 3, Issue 2 (Mar-Apr 2015), PP. 07-11 11 | P a g e Figure 11. Neural Network Predictive Controller The neural network predictive controller is a graphical user interface tool as shown in figure 11. From that neural network predictive controller select the plant identification which consists of neural network plant model. The plant model predicts the future plant outputs. The neural network plant model consists of one hidden layer. By generating training data by giving series of random reference signal the plant input and output data will be generated. By using trainlm the plant model training is done from this the training data for NN predictive controller will be obtained as shown in figure 12. and Validation data for NN predictive controller will be generated as shown in figure 13. 0 500 1000 0 1 2 3 4 Input 0 500 1000 20 21 22 23 Plant Output 0 500 1000 -0.05 0 0.05 0.1 0.15 Error time (s) 0 500 1000 20 21 22 23 NN Output time (s) Figure 12. Training Data for NN Predictive Controller 0 100 200 300 0 1 2 3 4 Input 0 100 200 300 20 21 22 23 Plant Output 0 100 200 300 -0.02 0 0.02 0.04 Error time (s) 0 100 200 300 20 21 22 23 NN Output time (s) Figure 13. Validation Data for NN Predictive Controller Figure 14. shows the servo response of CSTR. By using the neural network predictive controller plant model the characteristic of concentration in CSTR is obtained. 0 20 40 60 80 100 120 20 20.5 21 21.5 22 22.5 23 Time in Secs Concentrationinmol/(cm) 3 Servo Response ofCSTR Plant Output Reference Signal Figure 14. Servo Response of CSTR VIII. CONCLUSION AND FUTURE SCOPE The application of Continuous Stirred Tank Reactor is very essential nowadays. Using material balance condition, the CSTR process is effectively modeled which provides a better understanding of its characteristic behavior of the process. The modeling is effectively verified by its servo response. Various sensor faults considered in CSTR are detected and estimated in percentage by means of using Neural Network Predictive Controller and Fuzzy Logic Controller and found good results. This fault detection and estimation work can be further extended to actuator faults also. IX. REFERENCES [1] Dong-Juan Li., 2014, Neural network control for a class of continuous stirred tank reactor process with dead-zone input, Elsevier Journal of Neurocomputing, Vol.131, pp.453-459. [2] Kanse Nitin G., Dhanke P.B. and Thombare Abhijit ., 2012, Modeling and Simulation Study for Complex Reaction by Using Polymath, Research Journal of Chemical Sciences, Vol.2, No.4, pp.79-85. [3] Manikandan P., Geetha M., Jubi K., Jovitha Jerome.,2013, Fault Tolerant Fuzzy Gain Scheduling Proportional-Integral- Derivative Controller for Continuous Stirred Tank Reactor, Australian Journal of Basic and Applied Sciences, Vol.7, No.13, pp.84-93. [4] Ribhan Zafira Abdul Rahman, Azura Che Soh, Noor Fadzlina binti Muhammad.,2010, Fault Detection and Diagnosis for Continuous Stirred Tank Reactor Using Neural Network, Kathmandu University Journal of Science, Engineering and Technology, Vol.5, No.2, pp. 66-74. [5] Souragh Dash, Raghunathan Rengaswamy, Venkat Venkatasubramanian.,2003, Fuzzy- logic based trend classification for fault diagnosis of chemical processes, Elsevier Journal of Computers and Chemical Engineering, Vol.27, pp.347-362. [6] Venkat Venkatasubramanian, Raghunathan Rengaswamy, Kewen Yin, Surya N. Kavuri., 2003, A review of process fault detection and diagnosis Part I:Quantitative model-based methods’, Elsevier Journal of Computers and Chemical Engineering, Vol.27, pp.293-311. [7] Venkat Venkatasubramanian, Raghunathan Rengaswamy, Surya N. Kavuri, Kewen Yin., 2003, A review of process fault detection and diagnosis Part III: Process history based methods, Elsevier Journal of Computers and Chemical Engineering, Vol.27, pp.327-346. [8] Vishal Vishnoi, Subhransu Padhee, Gagandeep Kaur., 2012, Controller Performance Evaluation for Concentration of Isothermal Continuous Stirred Tank Reactor, International Journal of Scientific and Research Publication, Vol.2, No.6, pp.2250-3153. [9] Yunosuke Maki and Kenneth A. Loparo.,1997, A Neural- Network Approach to Fault Detection and Diagnosis in Industrial Processes, IEEE Transactions on Control Systems Technology, Vol.5, No.6, pp.529-541.