系统工程理论与实践
繫統工程理論與實踐
계통공정이론여실천
Systems Engineering—Theory & Practice
2009年
8期
56~63
,共null页
试验设计 关联因子 裂区设计 嵌套效应建模
試驗設計 關聯因子 裂區設計 嵌套效應建模
시험설계 관련인자 렬구설계 감투효응건모
design of experiments (DOE); related factor; split-plot design; nested effects modeling
针对试验设计的关联因子中存在难以改变因子(HTC)的问题,提出了将嵌套效应建模引入裂区试验设计的处理方法,为存在关联因子的裂区试验设计问题提供了可行的解决方案.通过对裂区的设计,可以解决当因子水平的改变比较困难时,试验顺序不能随机化处理所带来的问题,而嵌套效应建模的引入使得试验设计的区域更符合实际需求,模型的解释也更合理.最后应用案例说明此方法可以更好地解决存在关联因子的裂区试验这类特殊的试验设计.
針對試驗設計的關聯因子中存在難以改變因子(HTC)的問題,提齣瞭將嵌套效應建模引入裂區試驗設計的處理方法,為存在關聯因子的裂區試驗設計問題提供瞭可行的解決方案.通過對裂區的設計,可以解決噹因子水平的改變比較睏難時,試驗順序不能隨機化處理所帶來的問題,而嵌套效應建模的引入使得試驗設計的區域更符閤實際需求,模型的解釋也更閤理.最後應用案例說明此方法可以更好地解決存在關聯因子的裂區試驗這類特殊的試驗設計.
침대시험설계적관련인자중존재난이개변인자(HTC)적문제,제출료장감투효응건모인입렬구시험설계적처리방법,위존재관련인자적렬구시험설계문제제공료가행적해결방안.통과대렬구적설계,가이해결당인자수평적개변비교곤난시,시험순서불능수궤화처리소대래적문제,이감투효응건모적인입사득시험설계적구역경부합실제수구,모형적해석야경합리.최후응용안례설명차방법가이경호지해결존재관련인자적렬구시험저류특수적시험설계.
This paper concentrates on dealing with the existence of hard-to-change (HTC) factor among related factors in design of experiments (DOE). Based on the discussion and comparative study of some approaches of experimental design with related factor, a viable solution is proposed for split-plot design containing related factors by combining split-plot design and nested effects modeling. By appealing to split-plot design, the problem that experimental order cannot be randomized with HTC factors is resolved. The application of nested effects modeling gives rise to more correspondence of the experimental region to industrial practice, and correspondingly more reasonable explanation of model. Finally, a real example application reveals that the proposed method can be successfully applied to resolve experimental design with HTC factors.