Prediction of ship fuel consumption by using an artificial neural network
- 21 Downloads
A smart ship collects various data with large volume, such as voyage, machinery, and weather data. Thus, big data analysis for smart ships is an important technology that can be widely applied to improve ship maintenance, operational efficiency, and equipment life management. In this study, an accurate regression model for the fuel consumption of the main engine by using an artificial neural network (ANN) was proposed by big data analysis including data collection, clustering, compression, and expansion. To obtain an accurate regression model, various numbers of hidden layers and neurons and different types of activation functions were tested in the ANN, and their effects on the accuracy and efficiency of the regression analysis were studied. The proposed regression model using ANN is a more accurate and efficient model to predict the fuel consumption of the main engine than polynomial regression and support vector machine.
KeywordsArtificial neural network Big data analysis Ship fuel consumption Smart ship Regression analysis
Unable to display preview. Download preview PDF.
- M. Haranen, P. Pakkanen, R. Kariranta and J. Salo, White, grey and black–box modeling in ship performance evaluation, Hull Performance and Insight Conference, Pavone Canavese, Torino, Italy (2016).Google Scholar
- C. Jonge, Data–driven analysis of vessel performance, Master Thesis, Norwegian University of Science and Technology (2017).Google Scholar
- B. Kawan, H. Wang, G. Li and K. Chhantyal, Data–driven modeling of ship motion prediction based on support vector regression, Proc. of the 58th Conference on Simulation and Modelling (SIMS 58), Reykjavik, Iceland (2017) 350–354.Google Scholar
- A. S. Aisjah and S. Arifin, Maritime weather prediction using fuzzy logic in java sea for shipping feasibility, International Journal of Artificial Intelligence, 10 (S13) (2013) 112–122.Google Scholar
- W. S. Sarle, Neural networks and statistical models, Proc. of the Nineteenth Annual SAS Users Group International Conference, Cary, NC, USA (1994) 1538–1550.Google Scholar
- G. Li, H. Zhang, B. Kawan, H. Wang, O. L. Osen and A. Styve, Analysis and modeling of sensor data for ship motion prediction, Proc. of the Oceans Conference, Shanghai, China (2016) 10–13.Google Scholar
- L. P. Perera and B. Mo, Marine engine operating regions under principal component analysis to evaluate ship performance and navigation behavior, IFAC–PapersOnLine, 49 (23) (2016a) 512–517.Google Scholar
- L. P. Perera and B. Mo, Data compression of ship performance and navigation information under deep learning, Proc. of the 35th International Conference on Ocean, Offshore and Arctic Engineering (OMAE 2016), Busan, Korea (2016b) OMAE2016–54093.Google Scholar
- M. Jeon, J. Lim and Y. Noh, A study on big data technology and collection, processing and analysis method for ship, The Korean Society of Mechanical Engineers Annual Conference, Korea, 3083–3085.Google Scholar
- R. Sridharan, Gaussian mixture models and the EM algorithm, https://people.csail.mit.edu/rameshvs/content/gmm–em. pdf (2018).Google Scholar
- A. L. Maas, A. Y. Hannun and A. Y. Ng, Rectifier nonlinearities improve neural network acoustic models, International Conference on Machine Learning, 30 (1) (2013) 3.Google Scholar