Akademik Veri Yönetim Sistemi
JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY, cilt.37, sa.4, ss.1783-1792, 2022 (SCI-Expanded)
Purpose: This study, which is based on least square (LS), weighted least square (WLS) and maximum likelihood (ML) estimation methods, proposes the use of a multi-objective programming approach to estimate the parameters of the Weibull distribution. Thus, it is aimed to obtain better estimation results by evaluating the parameter estimation process of these methods together. Theory and Methods: The NSGA-II method, which is a multi-objective heuristic approach, was used to solve the multi-objective programming estimation model. As the multi-objective estimation model, the cases of LS-WLS, LS-ML and WLS-ML were taken into consideration and these cases were compared with the classical LS, WLS and ML methods. Results: The Kevlar 49 / Epoxy dataset was used to demonstrate the applicability of the proposed approach. According to the results, the best parameter estimation results were given in cases where the ML method was evaluated only and together, LS-ML and WLS-ML multi-objective parameter estimation models. Conclusion: If it is desired to use a multi-objective optimization problem in estimating the parameters of a data set with Weibull distribution, a model including ML method will give better results.