Utilizing the Axiomatic Design (AD) principles to develop a perfect product, design of a manufacturing system with minimal complexity is required. For the purpose of reducing the manufacturing system complexity, theoretically, it is preferred to integrate multiple Process Variables (PVs) of the product into a single process unit. However, due to significant presence of some active noise factors, this integration practice may result in failing to maintain the independence among some of

more »

... Requirements (FRs) of the product. This event is the result of statistical causal relationships unintentionally developed among a subset of the integrated PVs. In such a condition, the AD's Independence Axiom cannot be successfully satisfied and reaching a system with minimal complexity is inconceivable, even though an uncoupled or decoupled system design is apparently presented. To mitigate this kind of FRs coupling generated from the PVs integration, this study proposes partial & semi-partial correlation analysis as a statistical solution to identify the most appropriate integration choices where integrating a subset of the PVs is inevitable. Furthermore, based on the Taguchi's loss function, a quantitative criterion is established to fairly compare any two non-ideal manufacturing system designs and choose the one with relatively lower loss. The proposed approach explained in this study is verified based on hypothetical data.