Premium
A multiresponse model for reliability‐based simulation optimization in systems subjected to random external stresses
Author(s) -
Hejazi TahaHossein
Publication year - 2017
Publication title -
quality and reliability engineering international
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.913
H-Index - 62
eISSN - 1099-1638
pISSN - 0748-8017
DOI - 10.1002/qre.2183
Subject(s) - reliability (semiconductor) , computer science , measure (data warehouse) , stress (linguistics) , reliability engineering , multivariate statistics , work (physics) , mathematical optimization , engineering , mathematics , data mining , mechanical engineering , machine learning , power (physics) , linguistics , physics , philosophy , quantum mechanics
Systems with multiple output characteristics are very difficult to optimize, especially where outputs are interrelated and some external factors affect their performance. In many systems, some correlations and/or conflicts exist between performance measures. Multiple response optimization is a mathematical‐statistical technique that helps experts improve all the system's outputs, simultaneously. The present work aims to derive a stress‐strength reliability measure for multiresponse problems, so the strength criteria of a system are optimized against external stresses. To achieve this purpose, multivariate normal‐normal stress‐strength models are developed and applied for optimization of ( s , S ) inventory systems in which demands and lead times are random. At the end, a numerical example is also studied to illustrate the efficacy of the proposed approach.