抄録
Robust parameter design (RPD) is used in the Taguchi Method to reduce variability in system outputs and enhance quality. The technology development process utilizing RPD comprises an evaluation component for assessing robustness and a mechanism analysis component for devising new systems if the objectives are unmet. In this study, we focus on the Causality Search T-Method (CS-T method), an efficient method for mechanism analysis, and its development method, Knowledge Search-Instrumental variables (KS -IV). The CS-T method is a practical technique that can improve the efficiency of system selection while maintaining the efficiency of an RPD. However, the conditions under which these methods can be used with high accuracy and validity remain unclear. In this study, we propose an extension of the CS-T and KS-IV methods for dynamic parameter design. In addition, we discuss the differences between the data aggregation methods of the two methods and the relationship between the aggregation contents and results, and based on these discussions, we improve the accuracy and interpretability of the methods.
