Abstract—The objective of this work is to make use of conventional response surface methodologies and basic elements from metaheuristic algorithms in the design of influential variables for engineering systems. A method of steepest ascent and integrated approaches of the method of steepest ascent with firefly and ant colony optimisation algorithms, are compared on a simulated continuous stirred tank reactor or CSTR with various levels of signal noise. The experimental results suggest that the conventional method of steepest ascent seems to be the most efficient on the CSTR surface at the lower levels of noise. However, the integrated approaches with both firefly and ant colony optimisation elements work well when the standard deviation of the noise is at higher levels. Although the average, the standard deviation of the greatest actual concentration of the product and percentage of sequences ended at the optimum from the integrated algorithm are better, they need more average design points, especially with ant colony optimisation element, to converge to the optimum when compared.
Index Terms—Firefly, ant colony optimisation, steepest ascent, continuous stirred tank reactor.
Pongchanun Luangpaiboon is with the Industrial Statistics and Operational Research Unit (ISO-RU), Department of Industrial Engineering, Faculty of Engineering, Thammasat University, 12120, Thailand (tel.: (662)564-3002-9; fax: (662)564-3017; e-mail: lpongch@engr.tu.ac.th).
[PDF]
Cite:Pongchanun Luangpaiboon, "Process Optimisation via Firefly and Ant Colony Optimisation Elements on the Path of Steepest Ascent for a CSTR," International Journal of Computer Theory and Engineering vol. 5, no. 3, pp. 730, 2013.