The double-bay layout problem

The layout of a semiconductor manufacturing facility can play a significant role in reducing operating costs and improving productivity. This paper introduces the double-bay layout problem that is encountered in semiconductor fabrication. This new problem not only considers the assignment and relative ordering of machines in two bays but also determines the exact location of each machine, and incorporates two objectives of minimizing material handling cost and layout area. A hybrid methodology combining a multi-objective genetic algorithm with linear programming is proposed to solve this problem. The genetic algorithm effectively identifies the set of non-dominated machine sequences, while the linear program uses the relative assignments obtained by the genetic algorithm to determine optimal absolute machine locations. Experimental results indicate that the proposed hybrid methodology finds Pareto-optimal solutions for small-scale problems and high-quality solutions for problems of practical size.