Multistage Random Key Genetic Algortihm Optimization for Scheduling Flexible Flow Lines with Sequence Depenedent Setup Times

This thesis proposes a new variation to the Random Key Genetic Algorithm (RKGA) for scheduling optimization in flexible flow line manufacturing with sequence dependent setup times. The proposed RKGA representation decodes scheduling information independently at each stage, unlike the traditional RKGA, which is only sequenced based on the first stage, limiting flexibility. The proposed method's performance is compared to the traditional method with varying numbers of jobs and stages. It is compared regarding performance ratio and statistical significance of differences through the Wilcoxon Signed Rank Test. Results show that the proposed RKGA outperformed traditional RKGA in high complexity (8 Stage system) and low complexity scenarios, and the traditional RKGA performs better and more consistently. This thesis demonstrates that a dynamic chromosome can impact solution quality.