Abstract
Abstract Many modern real-world designs rely on the optimization of multiple competing goals. For example, most components designed for the aerospace industry must meet some conflicting expectations. In such applications, low weight, low cost, high reliability, and easy manufacturability are desirable. In some cases, bounds for these requirements are not clear, and performing mono-objective optimizations might not provide a good landscape of the required optimal design choices. For these cases, finding a set of Pareto optimal designs might give the designer a comprehensive set of options from which to choose the best design. This article shows the main features and functionalities of an open source package, developed by the present authors, to solve constrained multi-objective problems. The package, named moko (acronym for Multi-Objective Kriging Optimization), was built under the open source programming language R. Popular Kriging based multi-objective optimization strategies, as the expected volume improvement and the weighted expected improvement, are available in the package. In addition, an approach proposed by the authors, based on the exploration using a predicted Pareto front is implemented. The latter approach showed to be more efficient than the two other techniques in some case studies performed by the authors with moko.
Highlights
Multi-objective optimization is a field of interest in many real-world applications
The installation of ‘moko’ package can be done by downloading it from Comprehensive R Archive Network (CRAN) servers and running the following commands: install.packages('moko') library(moko) To make use of any of the three multi-objective optimization algorithms implemented in moko package, the first step is to create a set of initial sampling points
Since most computer aided engineering (CAE) software do not provide an application programming interface (API) to communicate with external tools, the easiest way to do this task is by the usage of plain text files (‘.txt’) or even comma separated files (‘.csv’)
Summary
Multi-objective optimization is a field of interest in many real-world applications. Engineering design has multiple and conflicting goals and, most of the time, the relationship between the decision space (design variables domain) and the outcome is highly complex. Even when using such efficient frameworks, if the evaluation of the designs is too time consuming, a surrogate approach is usually used to alleviate the computational burden To address this issue, the present authors have developed an open-source package based on Kriging interpolation models. Adriano Gonçalves dos Passos et al Multi-objective optimization with Kriging surrogates using “moko”, an open source package authors followed the guidelines and good practices provided by Wickham (2015). This resulted in a package that has been accepted and is available at the Comprehensive R Archive Network (CRAN), the official public repository for R packages. We highlight that the present paper is a revised and extended version of the work presented in the conference MecSol2017 (Passos and Luersen, 2017b)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
