A comprehensive mathematical model for dynamic cellular manufacturing system design and Linear Programming embedded hybrid solution techniques. (January 2016)

• Record Type: Journal Article
• Authors: Bayram, Hüsamettin; Şahin, Ramazan
• Is Part Of: Computers & industrial engineering. Volume 91(2016)
• Page Start: 10
• Page End: 29
• Publication Date: 2016-01
• Subjects: Dynamic cellular manufacturing system design -- Simulated Annealing -- Genetic Algorithm -- Linear Programming -- Group layout -- Cell formation; Engineering -- Data processing -- Periodicals; Industrial engineering -- Periodicals; 620.00285
• DOI: 10.1016/j.cie.2015.10.014
• Languages: English
• ISSNs: 0360-8352

Abstract

Highlights: A comprehensive linear mathematical model for dynamic cellular manufacturing system design. A Linear Programming embedded Simulated Annealing technique. A Linear Programming embedded Genetic Algorithm technique. Samples taken from the literature were solved and compared with previous results. A lower bound mathematical model is also proposed. Abstract: Considering the ever changing market conditions, it is essential to design responsive and flexible manufacturing systems. This study addresses the multi-period Dynamic Cellular Manufacturing System (DCMS) design problem and introduces a new mathematical model. The objective function of the mathematical model considers inter-cell and intra-cell material handling, machine purchasing, layout reconfiguration, variable and constant machine costs. Machine duplication, machine capacities, operation sequences, alternative processing routes of the products, varying demands of products and lot splitting are among the most important issues addressed by the mathematical model. It makes decisions on many system related issues, including cell formation, inter- and intra-cell layout, product routing and product flow between machines. Due to the complexity of the problem, we suggest two heuristic solution approaches that combine Simulated Annealing (SA) with Linear Programming and Genetic Algorithm (GA) with Linear Programming. The developed approaches were tested using a data set from the literature. In addition, randomly generated test problems were also used to investigate the performance of the hybrid heuristic approaches. A problem specific lower bound mathematical model was also proposed to observe the solution quality of the developed approaches. The suggested approaches outperformed the previous study in terms of both computational time and the solution quality by reducing the overall system cost.