Applying Neural Networks in Quality Function Deployment Process for Conceptual Design

産品概念設計階段品質機能展開與類神經綱路之整合運用

週宇超(Yu-Chao Chou)

《工業工程學刊》 21卷6期 (2004/11) Pp. 587-596

https://doi.org/10.29977/JCIIE.200411.0008

摘要

現代大型工程系統之設計與製造日益複雜，然而衆人對於提高品質、增進效能、降低成本與縮短研發時程之要求卻與日俱增。一般而言，産品之性能與成本往往決定於概念設計階段(conceptual design)。概念設計之主要任務係在成本限制狀況下，將顧客對産品之功能需求，精凖轉換成理想之主要設計參數值，致得以進行接續之各項評比與設計作業，而産生一個設計基凖方案(design baseling)，以爲後續設計階段據以展開細部設計之用。本研究所發展之循序漸進的概念設計作業程序，運用品質機能展開(Quality Function Deployment, QFD)進行設計2則之分析(design criteria analysis)，先運用類神經綱路(neural networks)産生主要的設計參數值(principle parameters)，並形成數個基本設計方案(neural networks)産生主要的設計參數值(principle parameters),並形成數個基本設計方案(design alternatives)，再分別運用試算表及專家系統進行可行性分析(feasibility study)，最後再以分析層級程序法(Analytic Hierarchy Process, AHP)就此等設計方案予以評比，而獲得本設計階段之最終成果－設計基凖方案。本論文另以最爲複雜之船舶設計爲例，依據前述各項步驟循序推進，以驗證此一設計作業之便利與可行性。

關鍵字

品質機能展開 ； 類神經綱路 ； 概念設計

並列摘要

Quality Function Deployment(QFD) with applied statistics techniques are employed to facilitate the translation of prioritized set of customer requirements into a set of system-level requirements during conceptual design. Engineering systems have become increasingly complex to desing and build while the demand for quality and effective development at lower cost and shorter time continues. The aim of this research is to present neural networks based approach in QFD process to prescribe a new methodology to generate a conceptual design baseling. A generalized neural networks oriented conceptual design process in introduced and a hybrid intelligent system combining neural networks and expert systems for conceptual design is illustrated as well.

並列關鍵字

Quality Function Deployment(QFD) ； Neural networks ； Conceptual design

參考文獻

Anderson, J. A.,E. Rosenfeld(1988).Neurocomputing: Foundations of Research.Cambridge, MA:MIT Press.

Brower, K. S.,K. W. Walker(1986).Ship design computer programs-an interpolative technique.Naval Engineers Journal.98(3),74-87.

Canada, J. R.,W. G. Sullivan(1989).(Economic and Multiattribute Evaluation of Advanced Manufacturing Systems).

Cheng, B.,D. M. Titterington(1994).Neural network: A review from a statistical perspective (with discussion).Statistical Science.9,2-54.

Chiu, C. C.,D. F. Cook,J. L. Kao,Y. C. Chou(1997).Combing neural network and rule-based expert system for short term load forecasting.Computers and Industrial Engineering.32(4),787-797.