In this paper, a component from automobile industry is considered for optimizing the end milling operation . The objective function is to minimize the total production cost subject to machine constraints such as cutting power, cutting force, tool life, surface finish of the product and the range of the operating parameters. For solving the above problem, optimization procedures were developed using Simulated Annealing (SA) and Genetic Algorithm (GA). Generally, industries use cutting parameters from the range given by machine/tool suppliers. But it is required to find the optimum point in the given range in order to reduce the cost of production. By implementing the procedures developed in this work, an average of 24.48% reduction in manufacturing cost is indicated. The optimization problem is solved very efficiently using the above procedures. They can be easily modified to suit other machining operations such as turning, cylindrical grinding, surface grinding and nontraditional machining processes.

Optimization of operating parameters is an important step in machining optimization, particularly for operating Computer Numerical Controlled (CNC) machine tools. With the general use of sophisticated and high cost CNC machines coupled with higher labor costs, optimum operating parameters are desirable for producing the part economically. Although there are handbooks that provide recommended cutting conditions, they do not consider the economic aspect of machining and are not suitable for CNC machining. The operating parameters are cutting speed, feed rate, depth of cut, etc. that do not violate any of the constraints that may apply to the process and satisfy objective criteria such as minimum machining time or minimum machining cost or the combined objective function of machining time and cost.

Many researchers have investigated machining optimization problems. Mukherjee and Ray (2006) suggest a generic framework for parameter optimization in the metal cutting process. Cus and Balic (2003) have proposed a Genetic Algorithm (GA) based procedure for solving the optimization problem. Shunmugam et al. (2000) have used GA to yield minimum total production cost. Saravanan et al. (2001a and 2003) have tried the parameter optimization for continuous profile machining and gear design optimization using GA. Kakir and Garuda (2000) have optimized the machining conditions for multi-tool milling operations using circular direction search method. Saravanan et al. (2001b) have described and analyzed conventional and non-conventional methods for the CNC turning process. Li et al. (1999) have developed and experimented a theoretical milling force simulation model. Abburi and Dixit (2007) have proposed multi-objective optimization of a multipass turning process. Savas and Ozay (2008) present an approach for optimization of cutting parameters at cylindrical work pieces leading to minimum surface roughness by using GA in the tangential turn-milling process. Yildiz (2007) has tried the hybrid approach for a case study for milling operations to show its effectiveness in machining operations.

Non-conventional techniques are used in this paper for solving the optimization of the milling process. As the optimization results will not be trapped in the local minima, SA and GA techniques have been tried in this paper. The global optimum value will be obtained by using the above techniques. They have been implemented for the manufacture of automobile components and the results are compared and analyzed.

Mechanical Engineering Journal, Simulated Annealing (SA) , Genetic Algorithm (GA), Computer Numerical Controlled (CNC), Multi-Objective Optimization, Raw Materials, Velocity, Boltzmann Probability Distribution,Optimization Techniques, Advanced Manufacturing Technology, Novel Hybrid Immune Algorithm.