수산해양기술연구 (Journal of the Korean Society of Fisheries and Ocean Technology)

  • 제58권3호
  • /
  • Pages.272-280
  • /
  • 2022
  • /
  • 2671-9940(pISSN)
  • /
  • 2671-9924(eISSN)
한국수산해양기술학회 (The Korean Society of Fisheries and Ocean Technology)
권호 표지
DOI QR코드

DOI QR Code

딥러닝을 이용한 연안 소형 어선 주요 치수 추정 연구

A study on estimating the main dimensions of a small fishing boat using deep learning

  • 장민성 (부경대학교 조선해양시스템공학과) ;
  • 김동준 (부경대학교 조선해양시스템공학과) ;
  • 자오양 (부경대학교 마린융합디자인공학과)
  • JANG, Min Sung (Department of Naval Architecture and Marine Systems Engineering, Pukyong National University) ;
  • KIM, Dong-Joon (Department of Naval Architecture and Marine Systems Engineering, Pukyong National University) ;
  • ZHAO, Yang (Department of Marine design Convergence engineering, Pukyong National University)
  • 투고 : 2022.07.11
  • 심사 : 2022.08.05
  • 발행 : 2022.08.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

The first step is to determine the principal dimensions of the design ship, such as length between perpendiculars, beam, draft and depth when accomplishing the design of a new vessel. To make this process easier, a database with a large amount of existing ship data and a regression analysis technique are needed. Recently, deep learning, a branch of artificial intelligence (AI) has been used in regression analysis. In this paper, deep learning neural networks are used for regression analysis to find the regression function between the input and output data. To find the neural network structure with the highest accuracy, the errors of neural network structures with varying the number of the layers and the nodes are compared. In this paper, Python TensorFlow Keras API and MATLAB Deep Learning Toolbox are used to build deep learning neural networks. Constructed DNN (deep neural networks) makes helpful in determining the principal dimension of the ship and saves much time in the ship design process.

키워드

과제정보

이 논문은 부경대학교 자율창의학술연구비(2021년)에 의하여 연구되었음.

참고문헌

  1. Cho YI, Oh MJ, Seok YS, Lee SJ, and Roh MI. 2019. Resistance estimation of a ship in the initial hull design using deep learning. Korean Journal of Computational Design and Engineering 24, 203-210. https://doi.org/10.7315/CDE.2019.203.
  2. ChosunBiz. 2019. https://biz.chosun.com/site/data/html_dir/2019/03/04/2019030401387.html. Accessed 4 Mar 2019.
  3. Kim BS. 2020. Development of a prediction system for shell plate forming information based on machine learning. Ph.D. Thesis, Seoul National University, Korea, 113.
  4. Kim GY, Ban IJ, Park BC, Oh SJ, Lim CO, and Shin SC. 2019. Estimation of lightweight in the initial design of ships using deep neural networks. Journal of Korean Institute of Intelligent Systems 29, 416-423. https://doi.org/10.5391/JKIIS.2019.29.6.416
  5. Kim HH. 2020. Get started! TensorFlow 2.0 programming, Wikibooks, 1-484.
  6. Lee DK. 1988. On the application of artificial Intelligence to ship design. Bulletin of the Society of Naval Architects of Korea 25, 56-62.
  7. Lim JH and Jo HJ 2020. Prediction of barge ship roll response amplitude operator using machine learning techniques. Journal of Ocean Engineering and Technology 34, 167-179. https://doi.org/10.26748/KSOE.2019.107.
  8. Park HS trnslation. 2018. Deep learning with Python by Francois Chollet. Gilbut, 1-476.
  9. Shin DS, Park BC, Lim CO, Oh SJ, Kim GY, and Shin SC. 2020. Pipe routing using reinforcement learning on initial design stage. Journal of the Society of Naval Architects of Korea 57, 191-197. https://doi.org/10.3744/SNAK.2020.57.4.191.