Original scientific paper

https://doi.org/10.31803/tg-20210930051227

Hybrid of "Intersection" Algorithm for Multi-Objective Optimization with Response Surface Methodology and its Application

Maosheng Zheng orcid.org/0000-0003-3361-4060 ; School of Chemical Engineering, Northwest University, No. 229, Taibai North Road, Xi’an, 710069, Shaanxi Province, China
Yi Wang ; School of Chemical Engineering, Northwest University, No. 229, Taibai North Road, Xi’an, 710069, Shaanxi Province, China
Haipeng Teng ; School of Chemical Engineering, Northwest University, No. 229, Taibai North Road, Xi’an, 710069, Shaanxi Province, China

Abstract

Recently, a new "intersection" method for multi-objective optimization was developed in the points of view set theory and probability theory, which introduces a new idea of favorable probability to reflect the favorable degree of the utility of performance indicator in multi-objective optimization, and the product of all partial favorable probabilities of entire utilities of performance indicators makes the overall / total favorable probability of the candidate. Here, in this paper, the new "intersection" algorithm for multi-objective optimization is combined effectively with response surface methodology (RSM) by taking each response as one objective, which transfers the multi-response optimization problem into a single response one with the help of the overall / total favorable probability of each scheme. The overall / total favorable probability is the uniquely decisive index of the scheme in the optimization. Applications of the hybrid approach with two examples in material technology are given, proper predictions are obtained.

Keywords

favorable probability; "intersection" method; hybrid; multi-object optimization; response surface methodology

Hrčak ID:

283777

URI

https://hrcak.srce.hr/283777

Publication date:

23.9.2022.

Visits: 986 *