A genetic algorithm-based grouping method for a cell formation problem with the efficacy measure

Abstract

Over the past 25 years, the machine–part cell formation problem (CFP) has been the subject of numerous studies. The CFP consists of constructing a set of machine cells and their corresponding product families with the objective of minimising the inter-cell movement of parts while maximising the machine utilisation. This article presents a grouping genetic algorithm for the CFP that uses the grouping efficacy measure. We solve the CFP without pre-determining the number of cells. We also make some effort to improve the efficiency of our algorithm with respect to initialisation of the population, keeping a crossover operator from cloning. The computational results using the grouping efficacy measure for a set of CFPs from the literature are presented. The proposed algorithm performs well on all the test problems, exceeding or matching the solution quality of the results presented in the previous literature for most problems.