Artificial Neural Network Approach for Parameter Estimation in PI Self Tunning Regulator (PI-STR) method on Process Rig 38-714 Pressure Control

Eka Iskandar, mochammad rameli, Ali Fatoni

Abstract

In a pressure process control system when the system is loaded or when the load is released from the system, there will be a change in the system response form. Changes in the form of the response because the load or release of the load changes the dynamics of the system. In the controller industry commonly used are conventional PI or PID. However, due to the large variations in load, the PID controller is unable to meet the specifications. Adaptive settings are one of the regulatory methods in which controllers can respond to modify their behavior due to changes in dynamics due to loading and characteristics of interference. Self-Tunning Regulator (STR) is an adaptive arrangement scheme. Parameter estimation is one part of STR. In this paper the implementation of STR with parameter estimation using the neural network approach (NN STR) is carried out on the pressure regulation system in the Process Rig 38-741. The test results showed that the nominal load condition of NN STR with learning rate = 25 had the closest performance to the design results with a overshoot value of 23.7% and the settling time of 283.8 seconds was in accordance with the specifications of the desired range. In testing with the condition of changes in NN STR load with a learning rate = 20 shows the best performance against all the criteria used. While for testing the nominal load on the variation of NN set-point STR with learning rate = 10 shows the best performance on all the criteria used.

Keywords: PI, Self-Tunning Regulator, Pressure Process Rig 38-714, Artificial Neural Network

Full Text:

PDF

References

Massarudin, S. Nurjanah and R. B. Furner, “The Deepening of Structure of Industries Having Global Competitivenesss : Competititveness In Automotive, Electronics & Electric and Heavy Equipment Industries,” pp. 1-1, 2007.

K. J. Astroom and B. Wittenmark, Adaptive Control, Second ed., Dover Publication, 1994.

T. D.A. and D. R.H., “Comparative Analysis of Concentration Control for Nonlinear Continuous Stirred Tank Reactor,” in International Conference on Advanced in Computing Communication and Informatics(ICACCI), Jaipur, India, 2016.

Feedback Instrument Ltd, Process Control Trainer Level, Flow, & Temperature, Crowborough, pp. 1-1.

D. R. Patrick and S. W. Fardo, Industrial Process Control System, 2nd ed., CRC Press, 2009.

Feedback Instrument Ltd, Pressure Control Trainer Instruction Manual, Crowborough: FI Ltd.

K. J. Astrom and T. Hagglund, Advanced PID Control, United States of America: Instrumentation, Systems, and Automation Society, 2006.

J. Curtis D, “Data-Acquisition System,” in Process Control Instrumentation Technology, 7th ed., New Jersey, Hyderabad: Pearson Prentice Hall, 2016, pp. 153-156.

S. Haykin, “Introduction,” in Neural Network and Learning Machine, 3rd ed., New Jersey, Pearson, 2009, pp. 31-76.

National Instrument, LabVIEW User Manual, Austin, Texas: National Instrument.

Advantech, ADAM-5000/TCP Distributed DA&C System Based on Ethernet, Taiwan: Advantech Industrial Automation, 2001, pp. 1524-1530.

K. Ogata, Modern Control Engineering, 4th ed., Prentice Hall, 2002.

T. A. Tutunji, “Parametric System Identification Using Neural Networks,” Applied Soft Computing, pp. 2-4, 2016.

C. J. Zarowski, An Introduction to Numerical Analysis for Electrical and Computer Engineers, New Jersey: John Wiley & Sons,, 2004, pp. 78-96.

A. V. Oppenheim, R. W. Schafer and J. R. Buck, Discrete Time Signal Processing, 2nd ed., New Jersey: Prentice Hall, 1999, pp. 450-454.

J. Han and M. Kamber, Data Mining: Concepts and Techniques, 2 ed., British Columbia: Morgan Kaufmann, 2006, p. 71.

M. B. A. M. J. O. A. Vasickaninova, “Fuzzy Controller Design for Heat Exchanger,” in 19th International Conference on Intelligent Engineering System, Bratislava, Slovakia, 2015.

Refbacks

  • There are currently no refbacks.