Optimizing Boiler Combustion System in a Petrochemical Plant Using Neuro-Fuzzy Inference System and Genetic Algorithm

Authors: Yul Y. Nazaruddin, Anas Y. Widiaribowo, Satriyo Nugroho

Abstract:

Boiler is one of the critical unit in a petrochemical plant. Steam produced by the boiler is used for various processes in the plant such as urea and ammonia plant. An alternative method to optimize the boiler combustion system is presented in this paper. Adaptive Neuro-Fuzzy Inference System (ANFIS) approach is applied to model the boiler using real-time operational data collected from a boiler unit of the petrochemical plant. Nonlinear equation obtained is then used to optimize the air to fuel ratio using Genetic Algorithm, resulting an optimal ratio of 15.85. This optimal ratio is then maintained constant by ratio controller designed using inverse dynamics based on ANFIS. As a result, constant value of oxygen content in the flue gas is obtained which indicates more efficient combustion process.

Keywords: ANFIS, boiler, combustion process, genetic algorithm, optimization.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1130213

References:

[1] B. G. Liptak, Optimization of Industrial Unit Processes, CRC Press LLC, USA, 1999.
[2] S. G. Dukelow, S. G., The Control of Boiler 2nd Edition, Instrument Society of America, USA, 2001.
[3] Y. Y. Nazaruddin, N.A. Aziz, and W. Sudibjo, “Improving the Performance of Industrial Boiler Using Artificial Neural Network Modeling and Advanced Combustion Control,” in Proc. Int. Conf. on Control, Automation and Systems, Oct. 14-17, 2008, in COEX Seoul, Korea.
[4] H. Santoso, Y. Y. Nazaruddin, and F. I. Muchtadi, “Boiler Performance Optimization Using Fuzzy Logic Controller,” in Proc. of 16th IFAC World Congress on Automatic Control, Praque, Czech Republic, July 3-8, 2005.
[5] D. E. Goldberg, Genetic Algorithm In Search Optimization and Machine Learning, Addison-Wesley Publishing Co., 1989.
[6] M. Gen and R. Chang, Genetic Algorithms and Engineering Optimization, Willey Interscience Publication, 2000.
[7] J.S.R. Jang, C.T. Sun, and E. Mizutani, Neuro-Fuzzy and Soft Computing, Prentice Hall, Upper Saddle River, NJ, USA, 1997.
[8] Y. Yildirim and M. Bayramoglu, “Adaptive Neuro-Fuzzy based Modelling for Prediction of Air Pollution Daily Levels in City of Zonguldak,” Chemosphere 63, 2006, pp. 1575–1582.
[9] Y. Y. Nazaruddin and Sudarto, “Neuro-Fuzzy and Wavelet Network (Wavenet) Based Modeling of an Ammonia Converter Unit,” in Proc. the 4th International Conference on Computational Intelligence, Robotics and Autonomous System (CIRAS’2007), Palmerston North, New Zealand, November 28-30, 2007.