Performance Comparison of Moisture Control in Paper Industry Using Soft Computing Techniques

Abstract:

In this paper, Genetic Algorithm (GA) method has been applied in the moisture control system for auto tuning (PID) parameters. Proportional – Integral – Derivatives control scheme is used to provide an efficient and quiet easier in control engineering applications. Most of the PID tuning methods are used as manually which is difficult and time consuming. Genetic Algorithm which leads to improve the efficiency of tuning of process. The proposed algorithm is used to tune the PID parameters and its performance has been compared with Fuzzy logic techniques.Compare to the fuzzy logic technique dynamic performance specfications such as rise time, peak time and peak overshoot optimal values produced by GA. The plant model represented by the transfer function is obtained by the system identification tool box.

• Periodical: Applied Mechanics and Materials (Volume 573)
• Pages: 322-327
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.573.322
• Online since: June 2014
• Authors: M. Senthil Kumar*, K. Mahadevan
• Keywords: Fuzzy Logic, Genetic Algorithm (GA), Moisture, Paper Machine, PID Controller

References

[1] Johan Akesson, Ola Sl¨atteke, Modeling, Calibration and Control of a Paper Machine Dryer Section, Modelica 2006, September 4–5.

[2] Paavo viitamaki, HYBRID MODELING OF PAPER MACHINE GRADE CHANGES, Espoo May (2004).

[3] Chang Hoe Heo, Hyunjun Cho, and Yeong-Koo Yeo, Dynamic modeling of paper drying processes, Korean J. Chem. Eng., pp- 1651-1657, (2011).

DOI: 10.1007/s11814-011-0046-0

[4] Johan Akesson, Ola Sl¨atteke, A modelica library for paper machine dryer Section modelling, August (2006).

[5] Yeong-Koo Yeo†, Ki-Seok Hwang, Sung Chul Yi and Hong Kang, Modeling of the Drying Process in Paper Plants, Korean J. Chem. Eng., pp-761-766, (2004).

DOI: 10.1007/bf02705517

[6] Anita Zvolinschi, Eivind Johannessen, Signe Kjelstrup, The second-lawoptimal operation of a paper drying machine, Chemical Engineering Science, pp-3653 – 3662, (2006).

DOI: 10.1016/j.ces.2005.12.030

[7] Danlei Chu, Michael Forbes, Johan Backström, Cristian Gheorghe and Stephen Chu, Model Predictive Control and Optimization for Papermaking processes, Advanced model predictive control.

DOI: 10.5772/18535

[8] Tutorial of paper making process, SCA Publication Papers Technical Support.

[9] Ola Slätteke, Modeling and Control of the paper machine drying section, Lund, January (2006).

[10] Teo Lian Seng, Marzuki Bin Khalid, and Rubiyah Yusof, Tuning of a Neuro-fuzzy controller by genetic algorithm, IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART B: CYBERNETICS, VOL. 29, NO. 2, April, (1999).

DOI: 10.1109/3477.752795

[11] H. Sayoud, K. Takahashi, Senior Member, IEEE, and B. Vaillant, A Genetic Local Tuning Algorithm for a class of combinatorial Networks Design Problems, IEEE COMMUNICATIONS LETTERS, Vol. 5, No. 7, JULY (2001).

DOI: 10.1109/4234.935756

[12] Jinn-Tsong Tsai, Jyh-Horng Chou, Senior Member, IEEE, and Tung-Kuan Liu, Tuning the Structure and Parameters of a Neural Network by Using Hybrid Taguchi-Genetic Algorithm, IEEE TRANSACTIONS ON NEURAL NETWORKS, Vol. 17, No. 1, January (2006).

DOI: 10.1109/tie.2006.874280

[13] Michael J. Neath, Student Member, Akshya K. Swain, Member, Udaya K. Madawala, Senior Member, and Duleepa J. Thrimawithana, Member, An optimal PID controller for a bidirectional inductive power transfer system using multiobjective genetic algorithm, IEEE TRANSACTIONS ON POWER ELECTRONICS, VOL. 29, No. 3, March (2014).

DOI: 10.1109/tpel.2013.2262953