Learning-based ship design optimization approach

Hao Cui, Osman Turan, Philip Sayer

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

With the development of computer applications in ship design, optimization, as a powerful approach, has been widely used in the design and analysis process. However, the running time, which often varies from several weeks to months in the current computing environment, has been a bottleneck problem for optimization applications, particularly in the structural design of ships. To speed up the optimization process and adjust the complex design environment, ship designers usually rely on their personal experience to assist the design work. However, traditional experience, which largely depends on the designer’s personal skills, often makes the design quality very sensitive to the experience and decreases the robustness of the final design. This paper proposes a new machine-learning-based ship design optimization approach, which uses machine learning as an effective tool to give direction to optimization and improves the adaptability of optimization to the dynamic design environment. The natural human learning process is introduced into the optimization procedure to improve the efficiency of the algorithm. Q-learning, as an approach of reinforcement learning, is utilized to realize the learning function in the optimization process. The multi-objective particle swarm optimization method, multiagent system, and CAE software are used to build an integrated optimization system. A bulk carrier
structural design optimization was performed as a case study to evaluate the suitability of this method for real-world application.
LanguageEnglish
Pages186–195
Number of pages10
JournalComputer-Aided Design
Volume44
Issue number3
Early online date1 Aug 2011
DOIs
Publication statusPublished - Mar 2012

Fingerprint

Ships
Learning systems
Computer applications
Computer aided engineering
Reinforcement learning
Design optimization
Multi agent systems
Structural design
Particle swarm optimization (PSO)

Keywords

  • machine learning
  • ship design
  • structure optimization
  • structure analysis
  • multi-objective optimization

Cite this

Cui, Hao ; Turan, Osman ; Sayer, Philip. / Learning-based ship design optimization approach. In: Computer-Aided Design. 2012 ; Vol. 44, No. 3. pp. 186–195.
@article{bcc2a7ed7ffb45e2b7bfa2a78f0a713b,
title = "Learning-based ship design optimization approach",
abstract = "With the development of computer applications in ship design, optimization, as a powerful approach, has been widely used in the design and analysis process. However, the running time, which often varies from several weeks to months in the current computing environment, has been a bottleneck problem for optimization applications, particularly in the structural design of ships. To speed up the optimization process and adjust the complex design environment, ship designers usually rely on their personal experience to assist the design work. However, traditional experience, which largely depends on the designer’s personal skills, often makes the design quality very sensitive to the experience and decreases the robustness of the final design. This paper proposes a new machine-learning-based ship design optimization approach, which uses machine learning as an effective tool to give direction to optimization and improves the adaptability of optimization to the dynamic design environment. The natural human learning process is introduced into the optimization procedure to improve the efficiency of the algorithm. Q-learning, as an approach of reinforcement learning, is utilized to realize the learning function in the optimization process. The multi-objective particle swarm optimization method, multiagent system, and CAE software are used to build an integrated optimization system. A bulk carrierstructural design optimization was performed as a case study to evaluate the suitability of this method for real-world application.",
keywords = "machine learning, ship design, structure optimization, structure analysis, multi-objective optimization",
author = "Hao Cui and Osman Turan and Philip Sayer",
year = "2012",
month = "3",
doi = "10.1016/j.cad.2011.06.011",
language = "English",
volume = "44",
pages = "186–195",
journal = "Computer-Aided Design",
issn = "0010-4485",
number = "3",

}

Learning-based ship design optimization approach. / Cui, Hao; Turan, Osman; Sayer, Philip.

In: Computer-Aided Design, Vol. 44, No. 3, 03.2012, p. 186–195.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Learning-based ship design optimization approach

AU - Cui, Hao

AU - Turan, Osman

AU - Sayer, Philip

PY - 2012/3

Y1 - 2012/3

N2 - With the development of computer applications in ship design, optimization, as a powerful approach, has been widely used in the design and analysis process. However, the running time, which often varies from several weeks to months in the current computing environment, has been a bottleneck problem for optimization applications, particularly in the structural design of ships. To speed up the optimization process and adjust the complex design environment, ship designers usually rely on their personal experience to assist the design work. However, traditional experience, which largely depends on the designer’s personal skills, often makes the design quality very sensitive to the experience and decreases the robustness of the final design. This paper proposes a new machine-learning-based ship design optimization approach, which uses machine learning as an effective tool to give direction to optimization and improves the adaptability of optimization to the dynamic design environment. The natural human learning process is introduced into the optimization procedure to improve the efficiency of the algorithm. Q-learning, as an approach of reinforcement learning, is utilized to realize the learning function in the optimization process. The multi-objective particle swarm optimization method, multiagent system, and CAE software are used to build an integrated optimization system. A bulk carrierstructural design optimization was performed as a case study to evaluate the suitability of this method for real-world application.

AB - With the development of computer applications in ship design, optimization, as a powerful approach, has been widely used in the design and analysis process. However, the running time, which often varies from several weeks to months in the current computing environment, has been a bottleneck problem for optimization applications, particularly in the structural design of ships. To speed up the optimization process and adjust the complex design environment, ship designers usually rely on their personal experience to assist the design work. However, traditional experience, which largely depends on the designer’s personal skills, often makes the design quality very sensitive to the experience and decreases the robustness of the final design. This paper proposes a new machine-learning-based ship design optimization approach, which uses machine learning as an effective tool to give direction to optimization and improves the adaptability of optimization to the dynamic design environment. The natural human learning process is introduced into the optimization procedure to improve the efficiency of the algorithm. Q-learning, as an approach of reinforcement learning, is utilized to realize the learning function in the optimization process. The multi-objective particle swarm optimization method, multiagent system, and CAE software are used to build an integrated optimization system. A bulk carrierstructural design optimization was performed as a case study to evaluate the suitability of this method for real-world application.

KW - machine learning

KW - ship design

KW - structure optimization

KW - structure analysis

KW - multi-objective optimization

U2 - 10.1016/j.cad.2011.06.011

DO - 10.1016/j.cad.2011.06.011

M3 - Article

VL - 44

SP - 186

EP - 195

JO - Computer-Aided Design

T2 - Computer-Aided Design

JF - Computer-Aided Design

SN - 0010-4485

IS - 3

ER -