Viva Presentation Final 08.06.2012

DESIGN AND IMPLEMENTATION OF INTELLIGENT CONTROLLER FOR PLASTIC EXTRUSION PROCESS

USING EMBEDDED SYSTEMS

DESIGN AND IMPLEMENTATION OF INTELLIGENT CONTROLLER FOR PLASTIC EXTRUSION PROCESS

USING EMBEDDED SYSTEMS

S.RaviReg. No. 4083042120

S.RaviReg. No. 4083042120

UNDER THE GUIDENCE OF

Dr. M.SUDHA Ph.D.,

PROFESSOR & HOD/ECE

Karpagam Institute of Technology, Coimbatore.

Doctoral Committee Members

Dr.V.Subbiah Dr.K.PorkumaranDean, Electrical Sciences Vice PrincipalSri Krishna College of Dr.N.G.P . Institute of Tech.Engineering and Technology CoimbatoreCoimbatore

INDIAN EXAMINER

Dr.N.SivakumaranAssociate ProfessorDepartment of Instrumentation and Control Engg.National Institute of TechnologyTiruchirappalli

FOREIGN EXAMINER

Dr. James Arthur SwartLecturerVaal University of TechnologySouth Africa

OUTLINE OF THE PRESENTATION

Introduction about Plastic Extrusion plant.Problems in controlling the temperature of the

plastic extruder.Literature Survey.Design of conventional and proposed controllers

using MATLAB/Simulink.Neuro Fuzzy controller design using LabVIEW.Real time implementation.Result analysis and Conclusion.

INTRODUCTION

Extrusion is a high volume manufacturing process.

Used in the different industries.

Plastic extrusion process is chosen which is widely used in polymerization industry.

The industrial data is collected from the Arya Plastics Industry, SIPCOT, Perundurai

The temperature control of the plastic machine decides the quality of the plastic products.

Three to five heating stages-Coupling problem.

Plastic Extrusion barrel temperatures have slow responses.

Transitions between the machine’s idle state and the operation state.

Inconsistent and inhomogeneous product quality.

Product Development Process.

BLOCK DIAGRAM of PVC PLANT

PLASTIC EXTRUSION PIPELINE

PLANT HEATER DETAILS

LITERATURE REVIEW

Title Author Details Consolidated Results

Control of Plastic Extruders with Multiple Temperature Zones Using a Microprocessor Based Programmable Controller System

WilliamWare .E (1984), IEEE Transactions on Industry Applications, Vol.IA-20, No.4, pp.912917.

The problem is eliminated by an integration of the variety of individual controllers into a single system accomplishes a high degree of co-ordination and extruder performance.

Temperature Controlof a Plastic ExtrusionBarrel Using PIDFuzzy Controllers

Taur .J.S, Tao .C.W and Tsai .C.C (1995), Proceedings of the International IEEE/IAS conference on Industrial Automation and Control Emerging Technologies, Taipei, Taiwan, May 22-27, pp.370-375.

Temperature control of a plastic extrusion barrel using proportional integral derivative fuzzy controllers implies a traditional fuzzy controller.

FuzzySupervisory Predictive PID Control of a Plastic Extruder Barrel

Ching Chih Tsai and Chi-Huang Lu (1998), Journal of the Chinese Institute of Engineers, Vol.21, No.5, pp.619-624.

The problem of tuning of PID controllers eliminated and proposes a method that makes the weighting term of the PID control and its gains are adjusted by fuzzy controller.

Title Author Details Consolidated ResultsAdaptive Decoupling Predictive Temperature Control for an Extrusion Barrel in a Plastic Injection Molding Process

Chi Huang Lu and Ching Chih Tsai (2001), IEEE Transactions on Industrial Electronics, Vol.48, No.5, pp.968-975.

A recursive least square estimation method is implemented by TMS320C31 processor. This improves the capabilities of set-point tracking, disturbance rejection, and robustness by appropriate adjustments to the tuning parameters in the criterion function.

Hybrid Fuzzy Logic Control with Input Shaping for Input Tracking and Sway Suppression of a Gantry Crane System

Ahmad .M.A and Mohamed .Z (2009), American Journal of Engineering and Applied Sciences, Vol.2, No.4, pp.241-251.

The hybrid Fuzzy PI for the temperature control improves the performance of industrial process by supplementing conventional controls

A Genetic Based Neuro-Fuzzy Controller for Thermal Processes

Ashok Kumar Goel, Suresh Chandra Saxena and Surekha Bhanot 2005, Journal of computer science and Technology, Vol.5, No.1, April 2005.

The method has effectively built accurate linguistic neuro fuzzy models and competes well with other existing approaches.

LITERATURE REVIEW

Title Author Details Consolidated ResultsMold Temperature Control of a Rubber Injection Molding Machine by TSK Type Recurrent Neural Fuzzy Network

Chia Feng Juang, Shui Tien Huang and Fun Bin Duh (2006), Journal of Neurocomputing, Vol.70, No.3, pp.559–567.

The recurrent structure eliminates the need of prior knowledge of molding machine order and with the use of simple gradient, descent algorithm, practical experiments results in the elimination of the complicated time delay property and make the sampling interval even.

Implementation of MATLAB-SIMULINK Based Real Time Temperature Control for Set Point Changes

Emine Dogru Bolat (2007), International Journal of Circuits, Systems and Signal Processing, Vol.1, No.1, 2007, pp.54-61.

The temperature set point with Ziegler Nichols step response method, relay tuning method, integral square time error, and disturbance criterion method. The relay based PID controller provides the best response among other methods.

LITERATURE REVIEW

FINDINGS FROM THE LITERATURE REVIEW The effect of coupling with a large peak time, delay time with

peak overshoot , more number of heaters are not considered.

The fine tuning of the controller with the controlled variable to achieve the set point temperature is not obtained.

Not provide contented results for non linear and dead time process.

Real time implementation for multistage is not achieved.

None of these papers has jointly focused on a intelligent controller with the embedded system and considering the effect of coupling effects, set point tracking for more number of heaters with real time experimental set up.

PROPOSED METHODOLOGY

A real time intelligent temperature controller for plastic extrusion process is developed using PIC microcontroller considering the coupling effects, set point tracking, more number of heaters to eliminate the temperature control problem.

PID CONTROLLER DESIGN

The PID control is designed to ensure the specifying desired nominal operating point.

The PID control gain values and time constant values are designed using Zeigler – Nichols tuning method.

The delay time and time constant are determined by drawing a tangent line.

S- SHAPED CURVE OF STEP RESPONSE OF TEMPERATURE CONTROL MODEL

Delay time L=10S and time constant T=50s

The Ziegler-Nichols tuning rules suggest the PID control optimal setting values. The simulation uses the first order transfer function for the simulation work.

100.92( )

1 144sG s e

s

SIMULINK MODEL OF PID CONTROLLER

RESULTS FOR PID CONTROLLER

PERFORMANCE SPECIFICATION OF PID CONTROLLER

Performance Specification PID Controller Output

Delay Time(td) 170 Seconds

Rise Time(tr) 250 Seconds

Peak Time(tp) 400 Seconds

Settling Time(ts) 1900 Seconds

Peak Overshoot 21%

DRAWBACKS OF PID CONTROLLER

Self tuning of PID Control. Lagging in identify process variations. The timing specification of the controller takes more

time. Intelligent controllers are implemented to control the

temperature.

NEURAL NETWORK CONTROLLER

Alternative for classical controllers. Interconnection of simple processing element. Data processing system consisting of large number of

simple highly interconnected processing elements in architecture.

FEED FORWARD NEURAL NETWORK

Feed forward improves reference tracking Stabilize the system. Suppress the disturbances. Modifiable.

SIMULINK MODEL OF NEURAL NETWORK CONTROLLER

NEURAL NETWORK SIMULATED OUTPUT AT DIFFERENT

TEMPERATURE SET POINTS

PERFORMANCE SPECIFICATION FOR THE NEURAL NETWORK CONTROLLER

Performance Specification Neural Network Controller

Output





Peak Overshoot 6%

FUZZY LOGIC CONTROLLER

Fuzzy classification. Two dimensional fuzzy controller model Fuzzification, Fuzzy Inference Engine, Defuzzification

DESIGN OF FUZZY LOGIC CONTROLLER

FUZZY RULE BASE IF – THEN rules. NB, NS, Z, PS, and PB.

FUZZY CONTROL MODEL IN SIMULINK

RESULTS OF FUZZY CONTROLLER

PERFORMANCE SPECIFICATION FOR THE FUZZY LOGIC CONTROLLER

Performance Specification Fuzzy Logic

Controller Output





Peak Overshoot 5.25%

PERFORMANCE COMPARISONPerformance Specification

Fuzzy Logic Controller

Rise Time(tr) 3.13 times less than PID controller

1.88 times less than Neural Network controller

Peak Time(tp) 4 times less than PID controller


Settling Time(ts) 1.06 times less than PID controller


The disturbance rejection and set point tracking is achieved effectively.

FLC control is with minimum overshoot

Take a time delay to settle with reference value.

FUZZY PID CONTROLLER

Tuning of the PID controllers are Difficult. Optimized gain values can be obtained through fuzzy logic

controller. Combining the fuzzy with PID controller produces a good

control output.

FUZZY PID CONTROLLER DESIGN PROCEDURE

1) Identification of input and output variables.

2) Construction of control rules.

3) Describing system state in terms of fuzzy sets

4) Establishing fuzzification method and fuzzy membership functions.

4) Selection of the compositional rule of inference.

5) Defuzzification

CONTROLLER DESIGN

The outputs of fuzzy controller are Kp, Ki, Kd.

The fuzzy subsets of e and ec are {NB, NM, NS, ZE, PS, PM, PB}.

Fuzzy subsets of output for Kp, Ki, Kd are {ZE, VS, MS,ME, MB, VB,VL}.

The membership functions of each language values are triangular membership functions.

The triangular membership function is with minimum steady state error.

Due to the simplest formulation the triangular membership function is chosen.

Membership functions of input fuzzy variable errorMembership functions of input fuzzy variable error

Membership functions of input fuzzy variable change in error.Membership functions of input fuzzy variable change in error.

Membership functions of fuzzy controller output variable KpMembership functions of fuzzy controller output variable Kp

Membership functions of fuzzy controller output variable KiMembership functions of fuzzy controller output variable Ki

Membership functions of fuzzy controller output variable Kd Membership functions of fuzzy controller output variable Kd

SIMULINK MODEL OF FUZZY TUNED PID CONTROL

SIMULINK MODEL OF FUZZY TUNED PID CONTROL

SIMULINK RESULT OF FUZZY TUNED PID CONTROL

SIMULINK RESULT OF FUZZY TUNED PID CONTROL

PERFORMANCE SPECIFICATION OF FUZZY LOGIC TUNED PID CONTROLLER

PERFORMANCE SPECIFICATION OF FUZZY LOGIC TUNED PID CONTROLLER

Performance Specification Fuzzy Logic Tuned PID

Controller Output





Peak Overshoot 5.25 %

PERFORMANCE COMPARISONPERFORMANCE COMPARISON

Performance Specification

Fuzzy PID Controller






Settling time is equal with Neural Network controller

FLC tuned PID controller elimination of overshoot is less.

Considering the percentage of peak overshoot, the proposed method provides negligible value.

The set point tracking is achieved effectively compared to other controllers

The disturbance rejection is obtained effectively for the proposed FLC tuned PID controller.

NEURO FUZZY CONTOLLER

Neuro Fuzzy Controller is used in the form of sugeno model.

Integrate the best features of fuzzy systems and neural networks.

Representation of prior knowledge.

PROPOSED NEURO FUZZY CONTROL RULES

DESIGN OF NEURO FUZZY CONTROLLER

DESIGN STEPS FOR THE NEURO FUZZY CONTROLLER

Training data of a desired input/output pair of the target system to be modeled.

Input FIS Structure is designed. The error tolerance and number of training epochs are

designed. The training fuzzy data is exported to workspace as

a .Mat file.The ANFIS window is opened. The data is trained from

workspace. The .MAT file imported to workspace.The FIS is selected loaded from file.

NEURO FUZZY CONTROLLER MODEL TRAINING DATA

SIMULINK MODEL OF NEURO FUZZY CONTROLLER

NEURO FUZZY CONTROL SIMULATED OUTPUT

Performance Specification Neuro Fuzzy

Controller Output



Peak Time (tp) No Peak Time


Peak Overshoot No Peak Overshoot

PERFORMANCE SPECIFICATIONOF NEURO FUZZY CONTROLLER

PERFORMANCE SPECIFICATIONOF NEURO FUZZY CONTROLLER

COMPARISON OF SIMULATION RESULTS OF DIFFERENT CONTROLLERS

Performance

Specification

PID

Controller

Neural

Controller

Fuzzy

Controller

FLC

PID

Controller

Neuro

Fuzzy

Controller

Delay Time(td) 170 sec 127 sec 25 sec 152 sec 20 sec

Rise Time(tr) 250 sec 150 sec 80 sec 175 sec 37 sec

Peak Time (tp) 400 sec 120 sec 100 sec 100 sec No Peak

Time

Settling

Time(ts)

1900 sec 1820 sec 1800 sec1830 sec

1370 sec

Peak Overshoot 21% 6% 5.25% 5.25% No Peak

Overshoot

PERFORMANCE SPECIFICATION OF CONVENTIONAL AND PROPOSED

CONTROLLERS


Neuro Fuzzy Controller

Delay Time( td) 8.5 times less than PID controller


1.25 times less than Fuzzy Logic controller

7.6 times less than Fuzzy tuned PID controller






Neuro Fuzzy Controller


120 times less than Neural Network controller

100 times less than Fuzzy Logic controller

100 times less than Fuzzy tuned PID controller





RESULTS OF THE PROPOSED CONTROLLER The simulation result for the temperature control of plastic extruder using neuro fuzzy controller is outperformed i) In terms of overshootii) Disturbance rejectioniii) Set point tracking

The performance of the temperature control of plastic extrusion is greatly improved in terms of steady state response as well as stability.

Delay time of neuro fuzzy controller is 20seconds and the time required is less.

Neuro fuzzy controller is without peak overshoot.

LabVIEW NEURO FUZZY CONTROLLER LabVIEW is a powerful and versatile graphical development platform of virtual instrument.

Used mostly in industrial control .

SIMULATION INTERFACE TOOLKIT

SIMULATION INTERFACE TOOLKIT

The LabVIEW/SIT interface behaves differently when data acquisition is involved in the Simulink model. The LabVIEW Simulation Interface Toolkit integrates Simulink and real-time workshop with LabVIEW in a way that allows developing and testing control systems first developed in the simulink simulation environment.

FRONT PANEL OF LABVIEW FOR NEURO FUZZY CONTROLLER

BLOCK DIAGRAM OF LABVIEW FOR NEURO FUZZY CONTROLLER

LabVIEW SIMULATION RESULTS FOR CONVENTIONAL AND PROPOSED CONTROLLERS

Results without any transient overshoots and takes less time to settle with reference temperature.

The proposed controller identifies the process variations quickly and makes the temperature to settle with reference value.

Real time plastic extrusion model temperature can be controlled through by proper interface by using LabVIEW.

BLOCK DIAGRAM OF PIC16F877A MICROCONTROLLER BASED TEMPERATURE

CONTROLLER FOR PLASTIC EXTRUSION SYSTEM

BLOCK DIAGRAM OF PIC16F877A MICROCONTROLLER BASED TEMPERATURE

CONTROLLER FOR PLASTIC EXTRUSION SYSTEM

Embedded systems are highly specialized, often reactive, sub systems that provide information processing and control.

Embedded systems are highly specialized, often reactive, sub systems that provide information processing and control.

CIRCUIT DIAGRAM OF THE TEMPERATURE CONTROL FOR THE PLASTIC EXTRUDER

Picture of the temperature controller set up for plastic extruder

Picture of the temperature controller set up for plastic extruder

HARDWARE IMPLEMENTATION RESULTSThe proposed controller is implemented through the PIC16F877A microcontroller.

The control algorithm was written in Hi Tech C code in MPLAB software.

After developing the application program, it has been downloaded in to selected target machine.

The set points temperatures 700C, 1000C are applied for the experimental setup.

COMPILING MPLAB hitech CCOMPILING MPLAB hitech C

EXPERIMENTAL RESULTS FOR THE PROPOSED NEURO FUZZY CONTROLLER

EXPERIMENTAL RESULTS FOR THE PROPOSED NEURO FUZZY CONTROLLER

FINDINGS OF THE HARDWARE RESULTS

Temperature control for set points can be achieved effectively.

Digital neuro fuzzy controllers are effective in dealing with the highly nonlinear characteristics.

The hardware significantly decreases at runtimes.

The controller provides a quick, accurate set point tracking with reference temperature.

COMPARISON OF SIMULATION AND HARDWARE RESULTS OF NEURO FUZZY CONTROLLER FOR

DIFFERENT SET POINTS

COMPARISON OF SIMULATED AND EXPERIMENTAL RESULTS

Performance

Specification

Neuro Fuzzy

Controller

Simulation Results

Neuro Fuzzy

Controller

Hardware Results

Delay Time(td) 20 Seconds 25 Seconds

Rise Time(tr) 37 Seconds 43 Seconds

Peak Time(tp) No Peak Time 5 Seconds

Settling Time(ts) 1370 Seconds 1395 Seconds

Peak Overshoot No Peak Overshoot 0.26%

RESULTS AND DISCUSSION

The comparison results show the neuro fuzzy controller output is efficient.

Good tracking capability.Two different temperature set points 70°C,

100°C is used.PID controller output is with very high initial

transient overshoot.Oscillating and takes more time to settle with the

reference temperature. The other proposed controllers are without

initial transient overshoots.

Neuro Fuzzy controller is without overshoot. It eliminates the initial transient overshoot and

oscillations. Proposed Neuro Fuzzy controller is suitable for

set points changes and for stability.The proposed controller identifies the process

variations quickly and provides good control for the set point changes and for sudden disturbances.

The set points tracking and disturbance rejection is obtained in the proposed method.

The hardware results are closer to the simulation results.

The proposed controller implemented through the embedded system and shows the desired outstanding performance in terms of achieving the desired value with very small values for the delay, rise, peak, settling time both in hardware and in simulation.

CONCLUSION

This research work demonstrates the design, analysis and suitability of neuro fuzzy controller for plastic extrusion by neuro fuzzy control.

Different type of controller like PID, Neural, Fuzzy, Fuzzy tuned PID, Neuro Fuzzy controller are simulated.

From the simulation results it is found that the Neuro Fuzzy controller is suitable for plastic extrusion system.

The neuro fuzzy controller is suitable for set points changes and for stability with the aid of the supervisory technique.

The proposed controller identifies the process variations quickly.

76

Provides good control for the set point changes and for sudden disturbances.

This temperature controller can provide accurate temperature control over a wide range of temperature variations; can also perform accurately at different operating conditions and avoiding disturbances.

Earlier works on the temperature control for plastic extruder have not paid much emphasis on more number of set point temperatures.

The main advantage of the proposed temperature controller is considering the coupling properties and real time implementation and it is achieved through the PIC controller.

77

The neuro fuzzy controller performs better than conventional and other intelligent controllers when the controllers are subjected to the same operating conditions.

The simulation and experimental results show that the proposed controller takes less time to eliminate sudden disturbances and tracking the set point and more robust to load variations.

The simulation results and the performance of the hardware implementation show that the optimal neuro fuzzy controller functions better than other controllers in terms of time domain specification, set point tracking, and disturbance rejection with optimum stability.

The neuro fuzzy controller will prove especially efficacious in the case temperature control in plastic extrusion system.

78

FUTURE SCOPEFUTURE SCOPE

The neuro fuzzy temperature controller can be implemented using ARM processor.

The developed embedded based neuro fuzzy controller can be implemented for Aluminum extrusion process with required modifications.

The graphical user interface developed using LabVIEW can transfer information to the networked clients through web server and monitoring of the set points may be achieved.

The tuning of neuro fuzzy controller done through the genetic algorithm.

The neuro fuzzy temperature controller can be implemented using ARM processor.

The developed embedded based neuro fuzzy controller can be implemented for Aluminum extrusion process with required modifications.

The graphical user interface developed using LabVIEW can transfer information to the networked clients through web server and monitoring of the set points may be achieved.

The tuning of neuro fuzzy controller done through the genetic algorithm.

REFERENCES1. Alipoor .M et. al. (2009), “Fuzzy Temperature Control in a Batch Polymerization Reactor

Using ANFIS Method” International Journal of Engineering and Technology, Vol.1, No.1, pp.7-12.

2. Ali Reza Mehrabian .Y and Morteza Mohammad Zaheri (2007) “Design of a Genetic Algorithm Based Steam Temperature Controller in Thermal Power Plants”, IAENG Engineering Letters, Vol.15, No.1, pp.13-20.

3. Ashok Kumar Goel et. al. (2005), “A Genetic Based Neuro-Fuzzy Controller for Thermal Processes”, Journal of computer science and Technology, Vol.5, No. 1, April 2005, pp-37-43.

4. Bhogle .P.P., et. al. (2007), “Neuro Fuzzy Temperature Controller”, Proceedings of the 2007 IEEE International Conference On Mechatronics and Automation, Harbin, China, August 5 - 8, pp.3344-3348.

5. Chi Huang Lu et. al. (2001), “Adaptive Decoupling Predictive Temperature Control for an Extrusion Barrel in a Plastic Injection Molding Process”, IEEE Transactions on Industrial Electronics, Vol.48, No.5, pp.968-975.

6. Chia Feng Juang et. al. (2006), “Mold Temperature Control of a Rubber Injection Molding Machine by TSK Type Recurrent Neural Fuzzy Network”, Journal of Neurocomputing, Vol.70, No.3, pp.559–567.

7. Chia Feng Juang and Chao Hsin Hsu (2005), “Temperature Control by Chip-Implemented Adaptive Recurrent Fuzzy Controller Designed by Evolutionary Algorithm”, IEEE Transactions on Circuits and Systems-1, Vol. 52, No.11, pp.2376-2384. 80

8. Ching Chih Tsai and Chi-Huang Lu (1998), “Fuzzy Supervisory Predictive PID Control of a Plastic Extruder Barrel”, Journal of the Chinese Institute of Engineers, Vol.21, No.5, pp.619-624.

9. Ching Chih Tsai and Chi-Huang Lu (1998), “Multivariable Self-Tuning Temperature Control for Plastic Injection Molding Process”, IEEE Transactions on Industry Applications, Vol.34, No.2, pp.310-318.

10.Emine Dogru Bolat (2007), “Implementation of Matlab-SIMULINK Based Real Time Temperature Control for Set Point Changes”, International Journal of Circuits, Systems and Signal Processing, Vol. 1, No.1, 2007, pp-54-61

11.Giriraj Kumar .S.M et. al. (2008), “Genetic Algorithm Based PID Controller Tuning for a Model Bioreactor”, Indian Chemical Engineer Indian Institute of Chemical Engineers, Vol. 50, No.3, pp. 214-226.

12.Hongfu Zhou (2008), “Simulation on Temperature Fuzzy Control in Injection Mould Machine by simulink”, Proceedings of the IEEE International Conference on Networking, Sensing and Control: ICNSC 2008, Hainan, China, April 6-8, pp.123-128.

13.Huailin Shu and Youguo Pi (2005), “Decoupled Temperature Control System Based on PID Neural Network”, Proceedings of the International Conference: ACSE 05, Cairo, Egypt, December 19-21, pp.107-111.

81

14.Ismail Yusuf et. al. (2010), “A Temperature Control for Plastic Extruder Used Fuzzy Genetic Algorithms”, Proceedings of the International Multiconference of Engineers and Computer Scientists 2010: IMECS 2010, Hong Kong, March 17-19, Vol. II, pp.1075-1080

15.Jaswinder Singh and Aman Ganesh (2008), “Design and Analysis of GA based Neural/Fuzzy Optimum Adaptive Control”, WSEAS Transactions on Systems and Control, Vol.3, No.5, pp.375-382.

16.Javier Causa et. al. (2008), “Hybrid Fuzzy Predictive Control Based on Genetic Algorithms for the Temperature Control of a Batch Reactor”, Computers and Chemical Engineering Journal, Vol.32, No.12, pp.254-3263.

17.Jiun-Hong Lai and Chin-Teng Lin (1999), “Application of Neural Fuzzy Network to Pyrometer Correction and Temperature Control in Rapid Thermal Processing”, IEEE Transactions on Fuzzy Systems, Vol.7, No.2, pp.160-175.

18.Kanagaraj .N et. al. (2008), “Fuzzy Coordinated PI Controller: Application to the Real-Time Pressure Control Process”, Advances in Fuzzy Systems Volume 2008, Article ID 691808, doi:10.1155/2008/691808, pp.1-8.

19.Kangling Fang and Lei Yao (1996), “Application of Multivariable Fuzzy Control in Heating System of Injection Molding Machine”, Proceedings of the IEEE International Conference on Industrial Technology, Shanghai, China, December 2-6, pp.603-606.

82

20.Keller .J.P (2000) “Teaching PID and Fuzzy controllers with LabVIEW”, International Journal of Engineering Education, Vol.16, No.3, pp.202-211.

21.Leehter Yao and Chin-Chin Lin (2009), “On a Genetic Algorithm Based Scheduled Fuzzy PID Controller”, International Journal of Innovative Computing Information and Control, Vol.5, No.10, pp.3593–3602.

22.Lin .C.A. and Hsieh .T.F (1991), “Decoupling Controller Design for Linear Multivariable Plants”, IEEE Transactions on Automatic Control, Vol. 36, No.4, pp.485-489.

23.Liu Yucheng et. al. (2009), “A Method of Synthetic Optimizing Adjustment Based on Fuzzy Genetic Arithmetic for Control of Electric Heater”, Proceedings of the International Forum on Computer Science Technology and Applications: IFCSTA.2009, Chongqing, December 25-27, pp:89-92

24.Melba Mary .P et. al. (2007), “Design of Intelligent Self-Tuning Temperature Controller for Water Bath Process”, International Journal of Imaging Science and Engineering, Vol.1, No.4, pp.121-124.

25.Mialli.F.S et. al. (2010), “Multivariable Adaptive Predictive Model Based Control of a Biodiesel Transesterification Reactor”, Journal of Applied Sciences, Vol.10, No.12, pp.1019-1027. 83

26.Mohammed Hassan .Y and Waleed Sharif .F (2007), “Design of FPGA based PID like Fuzzy Controller for Industrial Applications”, IAENG International Journal of Computer Science, Vol.34, No.2, pp.5-12.

27.Mohammed Obaid Ali et. al. (2009) “Genetic Algorithm Tuning Based PID Controller for Liquid-Level Tank System”, Proceedings of the International Conference on Man-Machine System: ICOMMS 2009, Penang, Malaysia, October 11-13, pp.4A5-1-4A5-5.

28.Mohammadi S.M.A et. al. (2009), “A Novel Fast and Efficient Evolutionary Method for Optimal Design of Proportional Integral Derivative Controllers for Automatic Voltage Regulator Systems”, Asian. Journal of Applied Sciences, Vol.2, No.3, pp.275-295.

29.Mou.Lin Jin and Ming Chun Ho (2009), “Labview Based Fuzzy Controller for Design of a Lighting Control System”, Journal of Marine Science and Technology, Vol.17, No.2, pp.116-121.

30.Mudi .R.K and Pal .N.R (1999), “A Robust Self-Tuning Scheme for PI and PD Type Fuzzy Controllers”, IEEE Transaction on Fuzzy Systems, Vol.7, No.1, pp.2-16.

31.Oreste .P (2009), “The Convergence Confinement Method: Roles and Limits in Modern Geomechanical Tunnel Design”, American Journal of Applied Science, Vol.6, No.4, pp.757-771.

84

32.Ougli .A.El and Boumhidi .I (2009), “Fuzzy Logic PI Controller for a class of MIMO Nonlinear Systems”, International Journal on Automatic Control and System Engineering, Vol. 9, No.1, pp.17-23.

33.Pedro Ponce et. al. (2008), “A Novel Neuro-Fuzzy Controller Genetically Enhanced Using LabVIEW”, Proceedings of the annual conference on industrial electronics IECON 2008, Orlando, 10-13 Nov. 2008, pp.1559-1565.

34.Pivonka .P (2002), “Comparative Analysis of Fuzzy PI/PD/PID Controller Based on Classical PID Controller Approach”, Proceedings of the 2002 IEEE International Conference on Fuzzy Systems, USA, May 12-17, pp.541-546.

35.Pratumsuwan .P et. al. (2010) “A Hybrid of Fuzzy and Proportional-Integral-Derivative Controller for Electro-Hydraulic Position Servo System”, Energy Research Journal, Vol.1, No.2, pp.62-67.

36.Saini.J et. al. (2005), “Genetic algorithm based PID tuner”, Institution of Engineers Journal, Vol.50, No.3, pp.216-221.

37.Saravanakumar .G and WahidhaBanu .R.S.D (2006) “An Adaptive Controller Based on System Identification for Plants with Uncertainties Using Well Known Tuning formulas”, International Journal on Automatic Control and System Engineering, Vol.6, No.3, pp.17-22.

85

38.Sheroz Khan et. al. (2008), “Design and Implementation of an Optimal Fuzzy Logic Controller Using Genetic Algorithm”, Journal of Computer Science, Vol.4, No.10, pp.799-806.

39.Seema Nara et. al. (2010), “Proportional Integral Derivative Controller Tuning Of Temperature Control System Using Genetic Algorithm”, International Journal of Electronics, Information and Systems, Vol.12, No.2, pp 37-42.

40.Suja Mani Malar .R and Thyagarajan .T (2009), “Artificial Neural Networks Based Modeling and Control of Continuous Stirred Tank Reactor”, American Journal of Engineering Applied Science, Vol.2, No.1, pp.229-235.

41.Syed Faiz Ahmed (2007), “A New Approach in Industrial Automation Application Embedded System Design for Injection Molding Machine”, Proceedings of the IEEE International Multi topic Conference: INMIC 2007, Lahore, December 28-30, pp.1-5.

42.Talel Korkobi et. al. (2008), “Stability Analysis of Neural Networks Based System Identification”, Modelling and simulation in Engineering Journal, Vol. 2008, Article ID.343940, pp.1-8.

43.Taur .J.S et. al. (1995), “Temperature Control of a Plastic Extrusion Barrel Using PID Fuzzy Controllers”, Proceedings of the International IEEE/IAS conference on Industrial Automation and Control Emerging Technologies, Taipei, Taiwan, May 22-27, pp.370-375.

86

List of publicationsPaper Publication International Journals

1.S.Ravi, M.Sudha and P.A.Balakrishnan, “Design of Intelligent Self Tuning GA ANFIS Temperature Controller for Plastic Extrusion System”, Modelling and Simulation in Engineering Journal, Vol.2011, Article ID 101437, DOI. 10.1155/2011/101437.2.S.Ravi and P.A.Balakrishnan, “Design of Synthetic Optimizing Neuro Fuzzy Temperature Controller for Dual Screw Profile Plastic Extruder Using LabVIEW”, Journal of Computer Science, Vol.7, No.5, pp.671-677, May 2011.3.S.Ravi and P.A.Balakrishnan, “Modelling and Control of an ANFIS Temperature Controller for Plastic Extrusion Process”, Proceedings of the IEEE Xplore on Communication Control and Computing Technologies (ICCCCT), 2010, Ramanathapuram, India ,October 2010, pp.314-320. 4.S.Ravi and P.A.Balakrishnan, “Temperature Response Control of Multistage Process Plant Using Matlab/Simulink”, Journal of Instrument Society of India, Vol.40, No.3, pp177-178, September 2010.

5. S.Ravi and P.A.Balakrishnan, “Genetic Algorithm Based Temperature Controller For Plastic Extrusion System”, International Journal on Automatic Control and System Engineering, Vol.11, No.1, pp1-8, June 2011.

6. S.Ravi and P.A.Balakrishnan, “Dual Screw Profile Extruder Temperature Control Using LabVIEW Enhanced Genetic Fuzzy Algorithm”, European Journal of Scientific Research, Vol.50, No.1, pp.35-47, April 2011.

7. S.Ravi and P.A.Balakrishnan, “Intelligent Self Tuning ANFIS Temperature Regulator for Plastic Extrusion System”, CiiT International Journal of Artificial Intelligent Systems and Machine Learning, Vol.2, No.11, pp.333-339, November 2010.

8. S.Ravi and P.A.Balakrishnan, “Stable Self Tuning Genetic Fuzzy Temperature Controller for Plastic Extrusion System”, International Journal of Reviews in Computing, Vol.5, No.4, pp.21-28, January 2011.

9. S.Ravi and P.A.Balakrishnan, “Temperature Response Control of Plastic Extrusion Plant Using Matlab/Simulink”, International Journal of Recent Trends in Electrical Engineering, Vol.3, No.4, pp.135-140, May 2010.

Paper Accepted for Publication in International Journals

1. S.Ravi, M.Sudha and P.A.Balakrishnan, “Modelling of Embedded Based Neuro Fuzzy Temperature Controller For Plastic Extrusion System accepted for the publication in Intelligent Automation and Soft Computing Journal.

Paper Presented in International Conferences

1.S.Ravi and P.A.Balakrishnan, “Temperature Response Control of Plastic

Extrusion Plant Using Matlab/Simulink”, International Conference on

Instrumentation (ICI-2009), 2010, 21-23 January 2010, pp.116-117.

2.S.Ravi and P.A.Balakrishnan, “Modelling and Control of an ANFIS

Temperature Controller for Plastic Extrusion Process”, 2010 IEEE

International Conference on Communication Control and Computing

Technologies’, ICCCCT’10, 7-9 October 2010, pp.473-479.

THANK YOU

Viva Presentation Final 08.06.2012

Documents

chia feng

emine dogru

injection

ashok kumar

process variations

ching chih

plastic extrusion

plastic extrusion