Prediction of ship power based on variation in deep feed-forward neural network

다국어 초록 (Multilingual Abstract)

Fuel oil consumption (FOC) must be minimized to determine the economic route of a ship; hence, the ship power must be predicted prior to route planning. For this purpose, a numerical method using test results of a model has been widely used. However, predicting ship power using this method is challenging owing to the uncertainty of the model test. An onboard test should be conducted to solve this problem; however, it requires considerable resources and time. Therefore, in this study, a deep feedforward neural network (DFN) is used to predict ship power using deep learning methods that involve data pattern recognition. To use data in the DFN, the input data and a label (output of prediction) should be configured. In this study, the input data are configured using ocean environmental data (wave height, wave period, wave direction, wind speed, wind direction, and sea surface temperature) and the ship's operational data (draft, speed, and heading). The ship power is selected as the label. In addition, various treatments have been used to improve the prediction accuracy. First, ocean environmental data related to wind and waves are preprocessed using values relative to the ship's velocity. Second, the structure of the DFN is changed based on the characteristics of the input data. Third, the prediction accuracy is analyzed using a combination comprising five hyperparameters (number of hidden layers, number of hidden nodes, learning rate, dropout, and gradient optimizer). Finally, k-means clustering is performed to analyze the effect of the sea state and ship operational status by categorizing it into several models. The performances of various prediction models are compared and analyzed using the DFN in this study.

참고문헌 (Reference)

1 Bottou, L., "The tradeoffs of large scale learning" 161-168, 2009

2 Vapnik, V. N., "The Nature of Statistical Learning Theory, the Nature of Statistical Learning Theory"

3 International Maritime Organization, "Ships and Marine Technology Guidelines for the Assessment of Speed and Power Performance by Analysis of Speed Trial Data"

4 Perera, L. P., "Ship speed power performance under relative wind profiles in relation to sensor fault detection" 3 : 355-366, 2018

5 Uyanik, T., "Ship fuel consumption prediction with machine learning" 757-759, 2019

6 Rakke, S. G., "Ship Emissions Calculation from AIS-Annotated" Norwegian University of Science and Technology 2016

7 IMO, "Revised guidelines for the onboard operational use of shipborne automatic identification systems (AIS)" 1106 (1106): 2015

8 Harvald, S. A., "Resistance and Propulsion of Ships" Krieger Publishing Company 1992

9 James, B., "Random search for hyper-parameter optimization" 13 : 281-305, 2012

10 SNAME, "Principles of naval architecture"

11 Szelangiewicz, T., "Prediction power propulsion of the ship at the stage of preliminary design part II : mathematical model ship power propulsion for service speed useful in the preliminary design" 25 (25): 231-236, 2017

12 Liang, Q., "Prediction of vessel propulsion power using machine learning on AIS data, ship performance measurements and weather data" 1357-, 2019

13 Kim, K. S., "Prediction of ocean weather based on denoising autoencoder and convolutional LSTM" 8 : 2020

14 Kristensen, H. O., "Prediction of Resistance and Propulsion Power of Ships" Emissionsbeslutningsstøttesystem 2012

15 Yoo, B., "Powering performance analysis of full-scale ships under environmental disturbances" 50 : 2323-2328, 2017

16 Bialystocki, N., "On the estimation of ship's fuel consumption and speed curve : a statistical approach" 1 : 157-166, 2016

17 Lee, S. M., "Method for a simultaneous determination of the path and the speed for ship route planning problems" 157 : 301-312, 2018

18 Abebe, M., "Machine learning approaches for ship speed prediction towards energy efficient shipping" 10 (10): 2020

19 Lloyd, S. P., "Least squares quantization in PCM" 28 : 129-137, 1982

20 Hinton, G. E., "Improving Neural Networks by Preventing Co-adaptation of Feature Detectors"

21 Kim, K. S., "ISO 15016:2015-based method for estimating the fuel oil consumption of a ship" 8 : 2020

22 Panapakidis, I. P., "Forecasting the fuel consumption of passenger ships with a combination of shallow and deep learning" 9 : 2020

23 Seong-Hoon Kim, "Estimation of ship operational efficiency from AIS data using big data technology" 대한조선학회 12 : 440-454, 2020

24 Samsung Heavy Industries, "Energy Efficiency Management System" 2017

25 노명일, "Determination of an economical shipping route considering the effects of sea state for lower fuel consumption" 대한조선학회 5 (5): 246-262, 2013

26 Kim, D., "Data-driven prediction of vessel propulsion power using support vector regression with onboard measurement and ocean data" 20 (20): 2020

27 Ahlgren, F., "Auto machine learning for predicting ship fuel consumption" 2018

28 Draper, N., "Applied Regression Analysis" John Wiley & Sons 1998

29 Holtrop, J., "An approximate power prediction method" 29 : 166-170, 1982

30 Ruder, S., "An Overview of Gradient Descent Optimization Algorithms"

31 Kingma, D. P., "Adam: a method for stochastic optimization" 2015

32 Lang, X., "A semi-empirical model for ship speed loss prediction at head sea and its validation by full-scale measurements" 209 : 107494-, 2020