Many, if not most, real-world decision-making problems from operations research/management science are very complex in nature and quite hard to solve by classical optimization techniques. Such problems are often confronted with multi-objective decision-making problems, which involve multiple objectives and may produce tradeoffs among different objectives. A solution that is extreme with respect to one objective requires a compromise in other objectives. This restricts choosing a solution which is optimal with respect to only one objective. In this paper, for solving the problem, micro-Genetic Algorithm procedures are used, which are characterized as one of the Evolutionary Algorithms (EA) conceptual tools, to obtain the pareto-optimal zone. In this zone, the decision maker has to choose the best solution after he has made a ranking with all potential solutions. A decision support system shell is developed in order to classify all solutions. Further, the nonlinear relationship between the selected parameters from the process and the tool life and Material Removal Rate (MRR), which are mutually dependent objectives, needs to be optimized simultaneously.

Many real-world problems corresponding to search and optimization naturally involve multiple objectives and may produce tradeoffs among different objectives. A solution that is extreme with respect to one objective requires a compromise in other objectives. This restricts choosing a solution which is optimal with respect to only one objective. In today’s competitive manufacturing environment, globally, simultaneously increasing productivity is highly appreciated, while improving and maintaining high quality surfaces in finish turning of hardened parts is required to gain a competent advantage for manufacturers. The turning processes demand the use of advanced tools with specially made cutting edges as referred and reported in the earlier literature. Koenig et al. (1984) presented the advantages of using turning over grinding and its potential to control surface integrity by optimizing tool geometry and machining parameters. Matsumoto et al. (1999) addressed the issue of obtaining favorable surface integrity in turning processes for tough, abrasive nonferrous and nonmetallic materials. It is also evident from a large number of other experimental works that the tool geometry and selected machining parameters have complex relations with cutting forces, tool life, surface roughness and integrity of the finished surfaces. Whitney (1994) and Chou et al. (2002) showed the influence of using various cutting tools on tool wear and surface integrity. Thiele et al. (2000) showed that cutting edge geometry has a great influence on the residual stresses induced.

Multi-Objective Optimization (MOO) process that mimics and simulates the natural evolutionary processes of human beings (Goldberg and Richardson, 1987; Goldberg, 1989; and Lawrence, 1991) results in stochastic Optimization Techniques (OT) called Evolutionary Algorithms (EAs) that can often outperform conventional OT applied to real-world problems. EAs mostly involve meta-heuristic optimization algorithms such as Genetic Algorithms (GA), Evolutionary Programming (EP), Evolutionary Strategies (ES), Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO). Also, Evolutionary Multi-Objective Optimization (EMOO) and innovations were introduced by Deb.KalyanMoy in his works (Lawrence, 1991; and Forest, 1996). In this paper, for solving the problem, micro-GA procedures, which are characterized as one of the EA conceptual tools, are used to obtain the pareto-optimal zone.

Mechanical Engineering Journal, Decision-making process, Multi-objective optimization, Evolutionary Algorithms (EA), Micro-genetic algorithms, Turning Process, Material Removing Rate (MRR), Tool life.