Date of Award

Summer 2013

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Mechanical & Aerospace Engineering

Program/Concentration

Mechanical Engineering

Committee Director

Miltiadis Kotinis

Committee Member

Gene Hou

Committee Member

Han Bao

Call Number for Print

Special Collections; LD4331.E56 W433 2013

Abstract

The differential evolution (DE) algorithm is an evolutionary algorithm that has been utilized as a metaheuristic optimizer in the last few years. A recently developed multi-objective version of DE is utilized in this research in order to optimize the preliminary design of planing craft. The craft performance is evaluated using the planing hull preliminary design software PHAST. The optimization problem objectives are the craft acquisition cost and the overall measure of effectiveness; the latter comprises various performance aspects: ride quality, transportability, payload, and mobility. Static stability and operating constraints are also considered. Each of the aforementioned four measures of effectiveness and the craft acquisition cost is approximated using a surrogate model based on artificial neural networks (ANNs) and generated using the data mining software WEKA. The constraints are modeled via a single surrogate model that performs classification between feasible and infeasible designs. The proposed methodology is applied to the design of a riverine combat craft at two design speeds. It is shown that the surrogate-assisted multi-objective DE optimizer is capable of finding accurate Pareto-optimal solutions in only two optimization cycles.

Rights

In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).

DOI

10.25777/g91g-bg76

Download

Share

COinS