Premium
Optimizing Multiple Quality Responses in the Taguchi Method Using Fuzzy Goal Programming: Modeling and Applications
Author(s) -
AlRefaie Abbas
Publication year - 2015
Publication title -
international journal of intelligent systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.291
H-Index - 87
eISSN - 1098-111X
pISSN - 0884-8173
DOI - 10.1002/int.21722
Subject(s) - taguchi methods , grey relational analysis , fuzzy logic , computer science , process (computing) , quality (philosophy) , product (mathematics) , industrial engineering , goal programming , process capability index , data mining , operations research , reliability engineering , machine learning , artificial intelligence , work in process , engineering , mathematics , operations management , statistics , philosophy , geometry , epistemology , operating system
The Taguchi method is only an effective approach for optimizing process performance with a single quality response. However, customers are concerned about multiple quality responses on a product. Furthermore, process engineers have preferences on process settings. Consequently, collaboration between product and process engineers is required to satisfy customers as well as process requirements. This research proposes a collaborative approach for optimizing process performance with multiple quality responses on manufactured products in the applications of the Taguchi method using the Min–Max fuzzy goal programming model. Requirements on quality responses and process factors are described by proper membership functions. Then, an optimization model is developed and then solved to minimize the maximal deviation from each goal. Four case studies are provided for illustration, where it is noted that the proposed approach (a) considers preferences on quality responses and factor settings, which are ignored by grey relational analysis, multi‐response signal‐to‐noise (MRSN) technique, and grey–fuzzy logic approach, (b) develops mathematical relationships between each quality response and process factors, contrary to MRSN and grey analysis that combine all responses into one index, and (c) involves process knowledge about preferred process settings, which is ignored by grey relational analysis. In conclusion, the proposed collaborative optimization model may provide great support to process/product engineers in robust design.