透過您的圖書館登入
IP:3.144.97.187
  • 學位論文

應用案例式推論法與基因演算法建構跨廠區元件組裝次序規劃

Applying Case-Based Reasoning and Genetic Algorithm to Construct an Assembly Sequences Planning in Multi-Plant Manufacturing Environment

指導教授 : 鄭元杰
若您是本文的作者,可授權文章由華藝線上圖書館中協助推廣。

摘要


為了滿足市場上需求的多變,產品中元件的分群及子組裝組合變得比以往更為複雜,且在客製化環境下,模組化為必然的趨勢。在產品組裝過程中,模組化乃是結合相同功能與特性之元件,以符合特定之組裝順序,因具有彈性化、經濟性,且可簡化產品組裝和零組件共用等優點,已成為企業突破困境的趨勢,因此,模組化的觀念日益受到重視。而產品的需求以追求客戶滿意度為目標,除了規格與設計日漸多樣且複雜化之外,在高品質與高良率的要求下,為了增加企業間競爭力,必須整合多個廠區的資源,以完成生產。 本研究嘗試整合案例式推論法和基因演算法,利用案例式推理技術結合模組化設計的人工智慧,從過去的案例中找到相關知識的特性,使產品中所有的元件根據過去的案例,利用最短的時間,得到最符合組裝次序需求的子組裝模組化,以便在產品組裝的過程中,以子組裝為單位指派給可行組裝工廠進行組裝,提供給基因演算法作為演算的基礎;再利用基因演算法的特性,透過染色體基因編碼的技巧,在單一條染色體中包含子組裝、元件組裝次序以及工廠指派的編碼,再經過轉譯之後即可得到經過工廠指派的最佳組裝次序,提高搜尋的效率,並得到最小的組裝成本。

並列摘要


In order to fulfill the various marketing requirements, the classification of product components into subassemblies becomes more complicated; therefore, it is a tendency to have modular design of product components under customize manufacturing environment. In product assembly process, modular design is provided with flexible and economic specialties, also integrate components with similar function and characteristic to simple modules for complete the specific assembly sequence. Customers’ satisfaction is the main propose of product requirement, either varied regulation and design, or the demand of high quality and high yield rate in the manufacturing environment, enterprises must integrate multi-plant resource planning to enhance the competitiveness. In this thesis, attempting to construct an assembly sequences planning in multi-plant manufacturing environment by integrating Case-Based Reasoning(CBR)with Genetic Algorithm(GA). By applying CBR approach solving new problem by adapting solution that were used to solve previous similar problems, to modularized product components quickly and be suitable for assigning subassemblies in multi-plant assembly sequence. Afterwards, using GA with a special encoding rule solving assembly sequence problem and multi-plant subassembly assignment problem at the same time, then decoding the chromosome to obtain the assembly sequences planning in multi-plant manufacturing environment with the minimize total assembly cost.

參考文獻


2. Ahn, H., Kim, K. J., and Han, I., “Hybrid Genetic Algorithms and Case-Based Reasoning Systems,” Lecture Notes in Computer Science, Vol. 3314, 2005.
3. Baldwin, D.F., Abell, T.E., Lui, M. C. M., De Fazio, T.L., and Whitney, D.E., “An integrated computer aid for generating and evaluating assembly sequences for mechanical products,”IEEE Transactions on Robotics and Automation, Vol. 7, Issue 1, pp. 78-94, 1991.
4. Bonneville, F., Perrard, C., and Henrioud, J. M., “A genetic algorithm to generate and evaluate assembly plans,” Proceedings of the IEEE Symposium on Emerging Technology and Factory Automation, Vol. 2, pp. 231-239, 1995.
8. Chen, R. S., Lu, K. Y., and Tai, P. H., “Optimizing assembly planning through a three-stage integrated approach,” International Journal of Production Economics, Vol. 88, No. 3, pp. 243-256, 2004.
14. Heiko M., and Wahl, F. M., “Automatic decomposition of planned assembly sequences into skill primitives,” IEEE Transactions on Robotics and Automation, Vol. 17, No. 5, pp. 709-718, 2001.

延伸閱讀