선형변수 기계학습 기법을 활용한 저속비대선의 잉여저항계수 추정
Prediction of Residual Resistance Coefficient of Low-Speed Full Ships Using Hull Form Variables and Machine Learning Approaches
1
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
In this study, machine learning techniques were applied to predict the residual resistance coefficient (Cr) of low-speed full ships. The used machine learning methods are Ridge regression, support vector regression, random forest, neural network and their ensemble model. 19 hull form variables were used as input variables for machine learning methods. The hull form variables and Cr data obtained from 139 hull forms of KRISO database were used in analysis. 80 % of the total data were used as training models and the rest as validation. Some non-linear models showed the overfitted results and the ensemble model showed better results than others.
Abstract
In this study, machine learning techniques were applied to predict the residual resistance coefficient (Cr) of low-speed full ships. The used machine learning methods are Ridge regression, support vector regression, random forest, neural network and their ensemble model. 19 hull form variables were used as input variables for machine learning methods. The hull form variables and Cr data obtained from 139 hull forms of KRISO database were used in analysis. 80 % of the total data were used as training models and the rest as validation. Some non-linear models showed the overfitted results and the ensemble model showed better results than others.
참고문헌 (19)
- Breiman, L., "Random forests", Machine Learning, 45, pp.5~32 (2001)
- 조영인, "딥러닝을 이용한 선형 설계 초기 단계에서의 저항 추정", 한국CDE학회 논문집, 24(2), pp.203~210 (2019), 한국CDE학회[DOI]
- A reanalysis of the original test data for the Taylor standard series, "Gertler, M.", Navy Department The David W. Taylor Model Basin, ~, pp.Report 806 (1954)
- Guldhammer, H.E., "Ship resistance effect of form and principal dimensions" (1965), Akademisk Forlag
- Holtrop, J., "A statistical re-analysis of resistance and propulsion data", International Shipbuilding Progress, 31, pp.272~276 (1984)
- Holtrop, J., "A statistical power prediction method", International Shipbuilding Progress, 25, pp.253~ (1978)
- Holtrop, J., "An approximate power prediction method", International Shipbuilding Progress, 29, pp.166~170 (1982)
- 김현철, "선박의 성능 요소 추정을 위한 신경망의 실용화 연구", 한국해양공학회지, 29(2), pp.111~119 (2015), 한국해양공학회
- 김희정, "CFD를 이용한 선미선형 최적화 기법 개발", 대한조선학회 논문집, 44(6), pp.564~571 (2007), 대한조선학회
- 김진, "선박의 저항 및 자항성능 해석을 위한 수치기법 개발", 대한조선학회 논문집, 48(2), pp.147~157 (2011), 대한조선학회
- 김유철, "선형변수 및 모형시험결과 데이터베이스를 활용한 저속비대선의 잉여저항계수 추정", 대한조선학회 논문집, 56(5), pp.447~456 (2019), 대한조선학회[DOI]
- Kingma, D. P., "Adam : A method for stochastic optimization, International Conference on Learning Representations(ICLR), San Diego", International Conference on Learning Representations (ICLR) (2015)
- Lap, A. J. W., "Resistance(Fundamentals of ship resistance and propulsion)", International Shipbuilding Progress, 3(24), pp.441~ (1956)
- 박종헌, "Hull-form optimization of KSUEZMAX to enhance resistance performance", International Journal of Naval Architecture and Ocean Engineering, 7(1), pp.100~114 (2015), 대한조선학회
- 박상훈, "CFD 저항 해석을 이용한 컨테이너선 최적 트림추정법에 대한 연구", 대한조선학회 논문집, 51(5), pp.429~434 (2014), 대한조선학회
- Raschka, S., "Python machine learning" (2019), Packt
- Notes on regularized least squares, "Rifkin, R. M.", Computer Science and Artificial Intelligence Laboratory, ~ (2007)
- Smola A. J., "A tutorial on support vector regression", Statistics and Computing, 14, pp.199~222 (2003)
- Taylor, DW., "Speed and power of ships" (1933), Press of Ransdell