透過您的圖書館登入
IP:18.119.131.72
  • 學位論文

以基因演算法求解製鞋業針車線之生產線平衡問題

Applying Genetic Algorithm to the Assembly Line Balancing Problem of Sewing Lines in Footwear Manufacturing Industry

指導教授 : 陳建良

摘要


製鞋業屬於勞力密集產業,在劇烈的國際競爭及邊際利益遞減的情況下,業者紛紛尋求更好的生產規劃,以提昇自身競爭力。針車作業需要大量的人力及物力,是鞋業製程中的關鍵作業,使用的設備視工序而定,且需考量工序間之先行關係限制,上述特性更加深了製鞋業針車作業生產線平衡的難度。 本研究以基因演算法發展製鞋業針車線生產線平衡模組,所提出之模組主要分為工作站數模組以及負荷平衡模組。限制週期時間在滿足客戶需求之前提下,工作站數模組利用基因演算法 (Genetic Algorithm, GA),指派工序至各工作站,使工作站機台能執行所分派之工序,求解最小的工作站數。接著在負荷平衡模組利用群組基因演算法 (Grouping Genetic Algorithm, GGA),平衡工作站負荷,提高生產效率。本研究以實際製鞋業之生產數據及實驗設計驗證所發展演算法之績效。在不同的生產目標下如週期時間的縮短與提高人員使用率,生產管理者可依本研究之演算法進行快速的生產線設計。

並列摘要


Footwear manufacturing is a labor intensive industry. Due to intense global competition and declining profit margins, most footwear manufacturers need to improve productivity with better planning. The most critical process is sewing, as it generally involves a great number of operations processed by tens of operators. There exists precedence relationship among operations, and different operations require different sewing equipment. These characteristics increase the difficulty of line balancing in footwear manufacturing industry. This thesis develops a heuristic algorithm for assembly line balancing problem of sewing lines in footwear industry. The algorithm first uses Genetic Algorithm to determine the number of workstations based on the cycle time satisfying customer demands. It then uses Grouping Genetic Algorithm to balance the workload at different workstations. Real data from footwear manufacturers and experimental design are used to verify the performance of the proposed algorithm. Production managers can use the research results to quickly design sewing lines for important targets such as short cycle time and high labour utilization.

參考文獻


47. 吳政俊,「具平行機器與迴流特性之零工式工廠排程研究」,中原大學工業工
49. 張文靖,「粗略產能規劃於製鞋產業之運用」,中原大學工業工程研究所碩士
52. 簡珍珍,「製鞋業者實施責任中心制度之研究-以個案公司為例-」,中原大學
22. Kao, E. P. C. and Queyranne, M., “On dynamic programming methods for
7. Chang, P. C., Hsieh, J. C., and Hsiao, C. H., “Application of genetic algorithm to the unrelated parallel machine problem scheduling”, Journal of the Chinese Institute of Industrial Engineering, 19 (2), pp.79-95, 2002.

延伸閱讀