Design optimization of fork and join open assembly systems via simulation metamodeling and genetic algorithms

• Main Author: Shastri, Mayur Nishikant
• Format: Others
• Published: 2004
• Online Access: http://spectrum.library.concordia.ca/8244/1/MR04430.pdf; Shastri, Mayur Nishikant <http://spectrum.library.concordia.ca/view/creators/Shastri=3AMayur_Nishikant=3A=3A.html> (2004) Design optimization of fork and join open assembly systems via simulation metamodeling and genetic algorithms. Masters thesis, Concordia University.

Fork and Join Assembly Systems are increasingly being used in modern manufacturing systems. Due to the complexities in their configurations, designing such systems for an optimal performance may pose a number of challenges. Because of the involvement of large system parameters and variables, designing an assembly system is not an easy task. This study presents a design optimization approach in Fork and Join Open Assembly Systems. Optimal buffer allocations to accommodate the work-in-process inventories in such systems are optimized in an attempt to maximize the overall system production rate. Fundamentally the problem is a stochastic, nonlinear, combinatorial optimization problem with discrete decision variables. Because of the nature of the problem, it is extremely difficult to find any closed-form expression to determine the expected value of the production rate. Hence discrete event simulation is used to estimate the expected value of the production rate. Then simulation model coupled with genetic algorithms is used to find optimal buffer configuration for maximum production rate. Results obtained proved the efficiency of simulation optimization method. However, simulation is extremely time consuming due to lengthy computational requirements for most of the real life problems. (Abstract shortened by UMI.)