Development of a Fuel Consumption Prediction Model Based on Machine Learning Using Ship In-Service Data

Journal of Marine Science and Engineering - Tập 9 Số 2 - Trang 137
Young-Rong Kim1, Min Jung2, Jun-Bum Park3
1Department of Marine Technology, Norwegian University of Science and Technology, 7052, Trondheim, Norway
2Faculty of Korea Institute of Maritime and Fisheries Technology, Busan 49111, Korea
3Division of Navigation Science, Korea Maritime and Ocean University, Busan 49112, Korea

Tóm tắt

As interest in eco-friendly ships increases, methods for status monitoring and forecasting using in-service data from ships are being developed. Models for predicting the energy efficiency of a ship in real time need to effectively process the operational data and be optimized for such an application. This paper presents models that can predict fuel consumption using in-service data collected from a 13,000 TEU class container ship, along with statistical and domain-knowledge methods to select the proper input variables for the models. These methods prevent overfitting and multicollinearity while providing practical applicability. To implement the prediction model, either an artificial neural network (ANN) or multiple linear regression (MLR) were applied, where the ANN-based models showed the best prediction accuracy for both variable selection methods. The goodness of fit of the models based on ANN ranged from 0.9709 to 0.9936. Furthermore, sensitivity analysis of the draught under normal operating conditions indicated an optimal draught of 14.79 m, which was very close to the design draught of the target ship, and provides the optimal fuel consumption efficiency. These models could provide valuable information for ship operators to support decision making to maintain efficient operating conditions.

Từ khóa


Tài liệu tham khảo

Olmer, N., Comer, B., Roy, B., Mao, X., and Rutherford, D. (2017). Greenhouse Gas Emissions from Global Shipping, 2013–2015, ICCT (The International Council on Clean Transportation).

Committee, M.E.P. (2009). Guideline for Voluntary Use of the Ship Energy Efficiency Operational Indicator (EEOD), International Maritime Organization.

(2018). International Maritime Organization Resolution MEPC, International Maritime Organization.

Haites, 2018, Carbon taxes and greenhouse gas emissions trading systems: What have we learned?, Clim. Policy, 18, 955, 10.1080/14693062.2018.1492897

Gu, 2019, Integrated maritime fuel management with stochastic fuel prices and new emission regulations, J. Oper. Res. Soc., 70, 707, 10.1080/01605682.2017.1415649

Barnard, B. (2011). Maersk says slow steaming here to stay. J. Commer. Online, Available online: http://www.joc.com/maritime/maersk-says-slow-steaming-here-stay.

Eide, 2011, Future cost scenarios for reduction of ship CO2 emissions, Marit. Policy Manag., 38, 11, 10.1080/03088839.2010.533711

Branch, A., and Stopford, M. (2013). Maritime Economics, Routledge.

ABS (2020, September 09). Ship Energy Efficiency Measures Advisory. Available online: https://ww2.eagle.org/content/dam/eagle/advisories-and-debriefs/ABS_Energy_Efficiency_Advisory.pdf.

Hellio, C., and Yebra, D. (2009). Advances in Marine Antifouling Coatings and Technologies, Elsevier.

Schultz, 2011, Economic impact of biofouling on a naval surface ship, Biofouling, 27, 87, 10.1080/08927014.2010.542809

Turan, O., Demirel, Y.K., Day, S., and Tezdogan, T. (2016, January 18–21). Experimental determination of added hydrodynamic resistance caused by marine biofouling on ships. Proceedings of the 6th European Transport Research Conference, Warsaw, Poland.

Arslan, 2016, An artificial neural network based decision support system for energy efficient ship operations, Comput. Oper. Res., 66, 393, 10.1016/j.cor.2015.04.004

Kim, 2017, A statistical procedure of analyzing container ship operation data for finding fuel consumption patterns, Korean J. Appl. Stat., 30, 633, 10.5351/KJAS.2017.30.5.633

Coraddu, 2017, Vessels fuel consumption forecast and trim optimisation: A data analytics perspective, Ocean Eng., 130, 351, 10.1016/j.oceaneng.2016.11.058

Wang, 2018, Predicting ship fuel consumption based on LASSO regression, Transp. Res. Part Transp. Environ., 65, 817, 10.1016/j.trd.2017.09.014

Gkerekos, 2019, Machine learning models for predicting ship main engine Fuel Oil Consumption: A comparative study, Ocean Eng., 188, 106282, 10.1016/j.oceaneng.2019.106282

Yuan, 2018, Ship energy consumption prediction with Gaussian process metamodel, Energy Procedia, 152, 655, 10.1016/j.egypro.2018.09.226

Jeon, 2018, Prediction of ship fuel consumption by using an artificial neural network, J. Mech. Sci. Technol., 32, 5785, 10.1007/s12206-018-1126-4

Uyanik, T., Arslanoglu, Y., and Kalenderli, O. (2019, January 25–27). Ship Fuel Consumption Prediction with Machine Learning. Proceedings of the 4th International Mediterranean Science and Engineering Congress, Antalya, Turkey.

Hu, 2019, Prediction of fuel consumption for enroute ship based on machine learning, IEEE Access, 7, 119497, 10.1109/ACCESS.2019.2933630

Farag, 2020, The development of a ship performance model in varying operating conditions based on ANN and regression techniques, Ocean Eng., 198, 106972, 10.1016/j.oceaneng.2020.106972

Gujarati, D., and Porter, D. (2003). Multicollinearity: What happens if the regressors are correlated. Basic Econometrics, McGraw-Hill. [4th ed.].

Harrell, J., and Frank, E. (2015). Regression Modeling Strategies: With Applications to Linear Models, Logistic Furthermore, ordinal Regression, and Survival Analysis, Springer.

Bakar, Z.A., Mohemad, R., Ahmad, A., and Deris, M.M. (2006, January 7–9). A comparative study for outlier detection techniques in data mining. Proceedings of the 2006 IEEE Conference on Cybernetics and Intelligent Systems, Bangkok, Thailand.

Hair, J., Babin, B., Anderson, R., and Black, W. (2018). Multivariate Data Analysis, Cengage Learning EMEA. [8th ed.].

Yu, 2018, Study on Prediction of Ship Navigation Efficiency Using Open Source-based Big Data Platform, Korean J. Comput. Des. Eng., 23, 275, 10.7315/CDE.2018.275

Soares, 1996, Probabilistic models of still-water load effects in containers, Mar. Struct., 9, 287, 10.1016/0951-8339(95)00041-0

Ichinose, 2012, Decrease of ship speed in actual seas of a bulk carrier in full load and ballast conditions, J. Jpn. Soc. Nav. Archit. Ocean. Eng., 15, 37

Pratt, W.K. (2013). Introduction to Digital Image Processing, CRC Press.

Pedersen, B.P., and Larsen, J. (2009, January 10–12). Prediction of full-scale propulsion power using artificial neural networks. Proceedings of the 8th International Conference on Computer and IT Applications in the Maritime Industries (COMPIT’09), Budapest, Hungary.

Perera, 2016, Marine engine operating regions under principal component analysis to evaluate ship performance and navigation behavior, IFAC-PapersOnLine, 49, 512, 10.1016/j.ifacol.2016.10.487

IMO (1999). Guidelines for Voyage Planning, IMO.

Bowditch, N. (2010). American Practical Navigator-Bowditch, Paradise Cay Publications.

Du, 2019, Two-phase optimal solutions for ship speed and trim optimization over a voyage using voyage report data, Transp. Res. Part B Methodol., 122, 88, 10.1016/j.trb.2019.02.004

Amini, 2015, Optimal partial ridge estimation in restricted semiparametric regression models, J. Multivar. Anal., 136, 26, 10.1016/j.jmva.2015.01.005

Ferrero, 2015, Prognostic scores in heart failure—Critical appraisal and practical use, Int. J. Cardiol., 188, 1, 10.1016/j.ijcard.2015.03.154

Armstrong, 2013, Vessel optimisation for low carbon shipping, Ocean Eng., 73, 195, 10.1016/j.oceaneng.2013.06.018

Solas Chapter, V. (2020, September 09). Safety of Navigation, Available online: https://www.gov.uk/government/uploads/system/uploads/attachment-data/file/343175/solas-v-on-safety-of-navigation.pdf.

Pierson, 1964, A proposed spectral form for fully developed wind seas based on the similarity theory of SA Kitaigorodskii, J. Geophys. Res., 69, 5181, 10.1029/JZ069i024p05181

Bales, S.L., Lee, W.T., and Voelker, J.M. (1981). Standardized Wave and Wind Environments for NATO Operational Areas, David w Taylor Naval Ship Research and Development Center Bethesda md Ship. Technical Report.

Tan, S.G. (1995, January 7–8). Seakeeping considerations in ship design and operations. Proceedings of the MARIN, Wageningen, Presented at Regional Maritime Conference, Report 635001-Paper, Jakarta, Indonesia.

Adland, 2018, Dynamic speed choice in bulk shipping, Marit. Econ. Logist., 20, 253, 10.1057/s41278-016-0002-3

Newman, J.N. (2018). Marine Hydrodynamics, The MIT Press.

Hastie, T., Tibshirani, R., and Wainwright, M. (2015). Statistical Learning with Sparsity: The Lasso and Generalizations, CRC Press.

Rosenblatt, 1958, The perceptron: A probabilistic model for information storage and organization in the brain, Psychol. Rev., 65, 386, 10.1037/h0042519

Cybenko, 1992, Approximation by superpositions of a sigmoidal function, Math. Control. Signals Syst., 5, 455, 10.1007/BF02134016

Hahnloser, 2000, Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit, Nature, 405, 947, 10.1038/35016072

Glorot, X., Bordes, A., and Bengio, Y. (2011, January 11–13). Deep sparse rectifier neural networks. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, Ft. Lauderdale, FL, USA.

Chollet, F. (2020, September 09). Keras Documentation. Available online: https://keras.io/.

Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.

Saltelli, A., Ratto, M., Andres, T., Campolongo, F., Cariboni, J., Gatelli, D., Saisana, M., and Tarantola, S. (2008). Global Sensitivity Analysis: The Primer, John Wiley & Sons.

Pianosi, 2016, Sensitivity analysis of environmental models: A systematic review with practical workflow, Environ. Model. Softw., 79, 214, 10.1016/j.envsoft.2016.02.008

ABS (2020, September 09). Guide for ’Safehull-Dynamic Loading Approach’ for Vessels. Available online: https://ww2.eagle.org/content/dam/eagle/rules-and-guides/current/design_and_analysis/140_safehulldlaforvessels/DLA-Vessels_Guide_e-May18.pdf.

DNV (2020, September 09). Classification Notes: CSA-Direct Analysis of Ship Structures. Available online: http://rules.dnvgl.com/docs/pdf/DNV/cn/2013-01/CN34-1.pdf.

Yan, 2018, Energy-efficient shipping: An application of big data analysis for optimizing engine speed of inland ships considering multiple environmental factors, Ocean Eng., 169, 457, 10.1016/j.oceaneng.2018.08.050

Thông tin
Thông tin xuất bản

Journal of Marine Science and Engineering

Tập 9 Số 2

137

Thông tin tác giả