Swarm Intelligence for Multiobjective Optimization of Extraction Process

Introduction

Multi-criteria or multi-objective (MO) scenarios have become increasingly prevalent in industrial engineering environments (Statnikov & Matusov, 1995; Zhang and Li, 2007; Li and Zhou, 2011). MO optimization problems are commonly tackled using the concept of Pareto-optimality to trace-out the non-dominated solution options at the Pareto curve (Zitzler & Thiele, 1998; Deb et al., 2002). Other methods include the weighted techniques which involve objective function aggregation resulting in a master weighted function. This master weighted function is then solved for various weight values (which are usually fractional) (Fishburn, 1967; Triantaphyllou, 2000; Luyben. & Floudas, 1994; Das & Dennis, 1998). Using these techniques, the weights are used to consign relative importance or priority to the objectives in the master aggregate function. Hence, alternative near-optimal solution options are generated for various values of the scalars. In this chapter, the Normal Boundary Intersection (NBI) scheme (Das & Dennis, 1998) was used as a scalarization tool to construct the Pareto frontier. In Sandgren (1994) and Statnikov & Matusov (1995), detail examples and analyses on MO techniques for problems in engineering optimization are presented.

Many optimization techniques have been implemented for solving the extraction process problem (e.g. Hismath et al., 2011; Jie and Wei, 2008). In addition, evolutionary techniques such as DE have also been employed for extraction process optimization (Ubaidullah et al., 2012). The MO problem considered in this work was formulated by Shashi et al, (2010). This problem involves the optimization of the yields of certain chemical products which are extracted from the Gardenia Jasminoides Ellis fruit. The MO optimization model was developed in Shashi et al, (2010) to maximize the extraction yields which are the three bioactive compounds; crocin, geniposide and total phenolic compounds. The optimal extraction parameters which construct the most dominant Pareto frontier are then identified such that the process constraints remain unviolated. In Shashi et al., (2010), the MO problem was tackled using the real-coded Genetic Algorithm (GA) approach to obtain a single individual optima and not a Pareto frontier. In that work, measurement metrics were not employed to evaluate the solution quality in detail. In addition, the work done in Shashi et al., (2010) focused on modeling the system rather than optimizing it. The authors of that work employed only one optimization technique and did not carry out extensive comparative analysis on the optimization capabilities. Due to this setbacks, these factors are systematically addressed in this chapter to provide some insights on the optimization of the extraction process.