Skip to main content

Advertisement

Log in

A genetic algorithm-based grey-box model for ship fuel consumption prediction towards sustainable shipping

  • S.I.: OR for Sustainability in Supply Chain Management
  • Published:
Annals of Operations Research Aims and scope Submit manuscript

Abstract

In order to enhance sustainability in maritime shipping, shipping companies spend good efforts in improving the operational energy efficiency of existing ships. Accurate fuel consumption prediction model is a prerequisite of such operational improvements. Existing grey-box models (GBMs) are found with significant performance potential for ship fuel consumption prediction, although having a limitation of separating weather directions. Aiming to overcome this limitation, we propose a novel genetic algorithm-based GBM (GA-based GBM), where ship fuel consumption is modelled in a procedure based on basic principles of ship propulsion and the unknown parameters in this model are estimated with a GA-based procedure. Real ship operation data from a crude oil tanker over a 7-year sailing period are used to demonstrate the accuracy and reliability of the proposed model. To highlight the contribution of this work, we compare the proposed model against the latest GBM. The results show that the fitting performance of the proposed model is remarkably better, especially for oblique weather directions. The proposed model can be employed as a basis of ship energy efficiency management programs to reduce fuel consumption and greenhouse gas (GHG) emissions of a ship. This is beneficial to achieve the goal of sustainable shipping.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  • Alam, D. F., Yousri, D. A., & Eteiba, M. B. (2015). Flower pollination algorithm based solar PV parameter estimation. Energy Conversion and Management, 101, 410–422.

    Article  Google Scholar 

  • Aldous, L. G. (2016). Ship operational efficiency: performance models and uncertainty analysis. Ph.D. thesis, Department of Mechanical Engineering, University College London, London, United Kingdom.

  • Bal Beşikçi, E., Arslan, O., Turan, O., & Ölçer, A. I. (2016). An artificial neural network based decision support system for energy efficient ship operations. Computers & Operations Research, 66, 393–401.

    Article  Google Scholar 

  • Baldi, F. (2016). Modelling, analysis and optimisation of ship energy systems. Ph.D. thesis, Department of Shipping and Marine Technology, Chalmers University of Technology, Gothenburg, Sweden.

  • Bertram, V. (2012). Practical ship hydrodynamics (2nd ed.). Oxford: Butterworth-Heinemann.

    Google Scholar 

  • Bialystocki, N., & Konovessis, D. (2016). On the estimation of ship’s fuel consumption and speed curve: A statistical approach. Journal of Ocean Engineering and Science, 1(2), 157–166.

    Article  Google Scholar 

  • Blendermann, W. (1994). Parameter identification of wind loads on ships. Journal of Wind Engineering and Industrial Aerodynamics, 51(3), 339–351.

    Article  Google Scholar 

  • Blendermann, W. (1996). Wind loading of ships—collected data from wind tunnel tests in uniform flow. Report, Hamburg, germany: Bericht/Institut für Schiffbau der Universität Hamburg.

  • Carlton, J. (2012). Marine propellers and propulsion (3rd ed.). Oxford: Butterworth-Heinemann.

    Google Scholar 

  • Chen, G., & Jiang, L. (2016). Managing customer arrivals with time windows: A case of truck arrivals at a congested container terminal. Annals of Operations Research, 244(2), 349–365.

    Article  Google Scholar 

  • Chen, J., Liu, X., Zhang, X., He, J., & Luo, L. (2017). Optimal bilateral cooperative slot allocation for two liner carriers under a co-chartering agreement. Journal of Navigation, 70(05), 1170–1182.

    Article  Google Scholar 

  • Chen, J., & Yahalom, S. (2013). Container slot co-allocation planning with joint fleet agreement in a round voyage for liner shipping. Journal of Navigation, 66(04), 589–603.

    Article  Google Scholar 

  • Cheng, T. C. E., Lai, K., Venus Lun, Y. H., & Wong, C. W. Y. (2013). Green shipping management. Transportation Research Part E: Logistics and Transportation Review, 55, 1–2.

    Article  Google Scholar 

  • Christiansen, M., Fagerholt, K., Nygreen, B., & Ronen, D. (2013). Ship routing and scheduling in the new millennium. European Journal of Operational Research, 228(3), 467–483.

    Article  Google Scholar 

  • Christiansen, M., Fagerholt, K., & Ronen, D. (2004). Ship routing and scheduling: Status and perspectives. Transportation Science, 38(1), 1–18.

    Article  Google Scholar 

  • Coraddu, A., Oneto, L., Baldi, F., & Anguita, D. (2017). Vessels fuel consumption forecast and trim optimisation: A data analytics perspective. Ocean Engineering, 130, 351–370.

    Article  Google Scholar 

  • Coraddu, A., Oneto, L., Baldi, F., & Anguita, D. (2018). Vessels fuel consumption: A data analytics perspective to sustainability. In C. Cruz Corona (Ed.), Soft computing for sustainability science (Vol. 358, pp. 11–48). Cham: Springer.

    Chapter  Google Scholar 

  • Epstein, M. J. (2008). Making sustainability work: Best practices in managing and measuring corporate social environmental and economic impacts. London: Routledge.

    Google Scholar 

  • Eshelman, L. J., & Schaffer, J. D. (1993). Real-coded genetic algorithms and interval-schemata. In Proceedings of the II workshop on foundation of genetic algorithms (FOGA-1992) (pp. 187–202).

  • Fagerholt, K., Laporte, G., & Norstad, I. (2010). Reducing fuel emissions by optimizing speed on shipping routes. Journal of the Operational Research Society, 61(3), 523–529.

    Article  Google Scholar 

  • Guan, C., Theotokatos, G., Zhou, P., & Chen, H. (2014). Computational investigation of a large containership propulsion engine operation at slow steaming conditions. Applied Energy, 130, 370–383.

    Article  Google Scholar 

  • Guldhammer, H. E., & Harvald, S. A. (1974). Ship resistance: Effect of form and principal dimensions (Revised ed.). Copenhagen: Akademisk Forlag.

    Google Scholar 

  • Haranen, M., Pakkanen, P., Kariranta, R., & Salo, J. (2016). White, grey and black-box modelling in ship performance evaluation. In 1st Hull performence & insight conference (HullPIC) (pp. 115–127). Turin, Italy.

  • Holtrop, J. (1977). A statistical analysis of performance test results. International Shipbuilding Progress, 24(270), 23–28.

    Article  Google Scholar 

  • Holtrop, J. (1978). Statistical data for the extrapolation of model performance tests. International Shipbuilding Progress, 25(285), 122–126.

    Article  Google Scholar 

  • Holtrop, J. (1984). A statistical re-analysis of resistance and propulsion data. International Shipbuilding Progress, 31(363), 272–276.

    Google Scholar 

  • Holtrop, J., & Mennen, G. G. J. (1978). A statistical power prediction method. International Shipbuilding Progress, 25(290), 253–256.

    Article  Google Scholar 

  • Holtrop, J., & Mennen, G. G. J. (1982). An approximate power prediction method. International Shipbuilding Progress, 29(335), 166–170.

    Article  Google Scholar 

  • IMO. (2015). Third IMO greenhouse gasses study 2014. London: International Maritime Organization (IMO).

    Google Scholar 

  • Isherwood, R. M. (1972). Wind resistance of merchant ships. Transactions of the Royal Institution of Naval Architects, 115, 327–338.

    Google Scholar 

  • Jalkanen, J.-P., Brink, A., Kalli, J., Pettersson, H., Kukkonen, J., & Stipa, T. (2009). A modelling system for the exhaust emissions of marine traffic and its application in the Baltic Sea area. Atmospheric Chemistry and Physics Discussions, 9(4), 15339–15373.

    Article  Google Scholar 

  • Journée, J. M. J., Rijke, R. J., & Verleg, G. J. H. (1987). Marine performance surveillance with a personal computer (technical report no. 753–P). Delft, The Netherlands: Delft University of Technology, Ship Hydromechanics Laboratory.

  • Kanellos, F. D., Prousalidis, J. M., & Tsekouras, G. J. (2014). Control system for fuel consumption minimization—gas emission limitation of full electric propulsion ship power systems. Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment, 228(1), 17–28.

    Google Scholar 

  • Kristensen, H. O., & Lützen, M. (2012). Prediction of resistance and propulsion power of ships (project no. 2010-56, Emissionsbeslutningsstøttesystem work package 2, report no. 04). Copenhagen, Denmark: Technical University of Denmark and University of Southern Denmark.

  • Kwon, Y. J. (1982). The effect of weather, particularly short sea waves on ship speed performance. Ph.D. thesis, University of Newcastle upon Tyne.

  • Kwon, Y. J. (2008). Speed loss due to the added resistance in wind and waves. The Naval Architect, 3, 14–16.

    Google Scholar 

  • Leifsson, L. Þ., Sævarsdóttir, H., Sigurðsson, S. Þ., & Vésteinsson, A. (2008). Grey-box modeling of an ocean vessel for operational optimization. Simulation Modelling Practice and Theory, 16(8), 923–932.

    Article  Google Scholar 

  • Ljung, L. (2001). Black-box models from input-output measurements. In IMTC 2001. Proceedings of the 18th IEEE instrumentation and measurement technology conference. Rediscovering measurement in the age of informatics (Cat. No.01CH 37188) (Vol. 1, pp. 138–146). IEEE.

  • Lu, R., Turan, O., Boulougouris, E., Banks, C., & Incecik, A. (2015). A semi-empirical ship operational performance prediction model for voyage optimization towards energy efficient shipping. Ocean Engineering, 110, 18–28.

    Article  Google Scholar 

  • Maloni, M., Paul, J. A., & Gligor, D. M. (2013). Slow steaming impacts on ocean carriers and shippers. Maritime Economics & Logistics, 15(2), 151–171.

    Article  Google Scholar 

  • MAN Diesel & Turbo. (2011). Basic principles of ship propulsion. Publication no: 5510-0004-02ppr. Denmark: MAN Diesel & Turbo.

    Google Scholar 

  • Mansouri, S. A., Lee, H., & Aluko, O. (2015). Multi-objective decision support to enhance environmental sustainability in maritime shipping: A review and future directions. Transportation Research Part E: Logistics and Transportation Review, 78(2015), 3–18.

    Article  Google Scholar 

  • Meng, Q., Du, Y., & Wang, Y. (2016). Shipping log data based container ship fuel efficiency modeling. Transportation Research Part B: Methodological, 83, 207–229.

    Article  Google Scholar 

  • Moles, C. G., Mendes, P., & Banga, J. R. (2003). Parameter estimation in biochemical pathways: A comparison of global optimization methods. Genome Research, 13(11), 2467–2474.

    Article  Google Scholar 

  • Molland, A. F. (Ed.). (2012). The maritime engineering reference book: A guide to ship design, construction and operation. Oxford: Butterworth-Heinemann.

    Google Scholar 

  • Nikopoulou, Z. (2017). Incremental costs for reduction of air pollution from ships: a case study on North European emission control area. Maritime Policy & Management, 44(8), 1056–1077.

    Article  Google Scholar 

  • Orouji, H., Bozorg Haddad, O., Fallah-Mehdipour, E., & Mariño, M. A. (2013). Estimation of Muskingum parameter by meta-heuristic algorithms. Proceedings of the Institution of Civil Engineers - Water Management, 166(6), 315–324.

    Article  Google Scholar 

  • Paul, S. K., Asian, S., Goh, M., & Torabi, S. A. (2017). Managing sudden transportation disruptions in supply chains under delivery delay and quantity loss. Annals of Operations Research, 273(1–2), 783–814.

    Google Scholar 

  • Pedersen, B. P., & Larsen, J. (2009a). Modeling of ship propulsion performance. In World maritime technology conference (WMTC2009) (Vol. Session 4A, pp. 1–10). Mumbai, India: The Institute of Marine Engineers.

  • Pedersen, B. P., & Larsen, J. (2009b). Prediction of full-scale propulsion power using artificial neural networks. In Proceedings of the 8th international conference on computer and IT applications in the maritime industries (COMPIT’09) (pp. 537–550). Budapest, Hungary.

  • Pedersen, B. P., & Larsen, J. (2013). Gaussian process regression for vessel performance monitoring. In 12th International conference on computer and IT applications in the maritime industries (COMPIT 13). Cortona, Italy.

  • Petersen, J. P., Jacobsen, D. J., & Winther, O. (2012a). Statistical modelling for ship propulsion efficiency. Journal of Marine Science and Technology, 17(1), 30–39.

    Article  Google Scholar 

  • Petersen, J. P., Winther, O., & Jacobsen, D. J. (2012b). A machine-learning approach to predict main energy consumption under realistic operational conditions. Ship Technology Research, 59(1), 64–72.

    Article  Google Scholar 

  • Qiu, X., Wong, E. Y. C., & Lam, J. S. L. (2018). Evaluating economic and environmental value of liner vessel sharing along the maritime silk road. Maritime Policy & Management, 45(3), 336–350.

    Article  Google Scholar 

  • Ruckstuhl, A. (2010). Introduction to Nonlinear Regression. https://stat.ethz.ch/~stahel/courses/cheming/nlreg10E.pdf.

  • Rudzki, K., & Tarelko, W. (2016). A decision-making system supporting selection of commanded outputs for a ship’s propulsion system with a controllable pitch propeller. Ocean Engineering, 126, 254–264.

    Article  Google Scholar 

  • Sarkis, J. (Ed.). (2006). Greening the supply chain. London: Springer.

    Google Scholar 

  • Schneekluth, H., & Bertram, V. (1998). Ship design for efficiency and economy (2nd ed.). Oxford: Butterworth-Heinemann.

    Google Scholar 

  • Schwaab, M., Biscaia, E. C., Jr., Monteiro, J. L., & Pinto, J. C. (2008). Nonlinear parameter estimation through particle swarm optimization. Chemical Engineering Science, 63(6), 1542–1552.

    Article  Google Scholar 

  • Scrucca, L. (2013). GA: A package for genetic algorithms in R. Journal of Statistical Software, 53(4), 1–37.

    Article  Google Scholar 

  • Somarin, A. R., Chen, S., Asian, S., & Wang, D. Z. W. (2017). A heuristic stock allocation rule for repairable service parts. International Journal of Production Economics, 184, 131–140.

    Article  Google Scholar 

  • Tillig, F., Mao, W., & Ringsberg, J. W. (2015). Systems modelling for energy-efficient shipping (report no. 15:153). Gothenburg, Sweden: Chalmers University of Technology.

  • Tillig, F., Ringsberg, J., Mao, W., & Ramne, B. (2017). A generic energy systems model for efficient ship design and operation. Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment, 231(2), 649–666.

    Google Scholar 

  • Townsin, R. L., & Kwon, Y. J. (1983). Approximate formulae for the speed loss due to added resitance in wind and waves. Transactions of the Royal Institution of Naval Architects, 125, 199–207.

    Google Scholar 

  • Townsin, R. L., Moss, B., Wynne, J. B., & Whyte, I. M. (1975). Monitoring the speed performance of ships. North East Coast Institution of Engineers & Shipbuilders Transactions, 91(5), 159–175.

    Google Scholar 

  • Vettor, R., & Guedes Soares, C. (2016). Development of a ship weather routing system. Ocean Engineering, 123, 1–14.

    Article  Google Scholar 

  • Wang, H., & Nguyen, S. (2017). Prioritizing mechanism of low carbon shipping measures using a combination of FQFD and FTOPSIS. Maritime Policy & Management, 44(2), 187–207.

    Article  Google Scholar 

  • Yuen, K. F., Wang, X., Wong, Y. D., & Zhou, Q. (2017). Antecedents and outcomes of sustainable shipping practices: The integration of stakeholder and behavioural theories. Transportation Research Part E: Logistics and Transportation Review, 108(June), 18–35.

    Article  Google Scholar 

  • Zhao, J., & Yang, L. (2018). A bi-objective model for vessel emergency maintenance under a condition-based maintenance strategy. Simulation, 94(7), 609–624.

    Article  Google Scholar 

Download references

Acknowledgements

This work has been conducted as part of the Danish societal partnership Blue INNOship and is partly funded by the Innovation Fund Denmark under File No. 155-2014-10, the Danish Maritime Fund and Orient’s Fund. As a visiting Ph.D. student in Aalborg University, one of the authors, Liqian Yang is also funded by the Fundamental Research Funds for the Central Universities (Project No. HEU CFW170902) and the China Scholarship Council (No. 201606680043) from China.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Liqian Yang.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendices

Appendix A

See Table 10.

Table 10 Beaufort number related to wind speed at the standard height (Townsin et al. 1975)

Appendix B

See Table 11.

Table 11 Data fields of noon reports that are related to this study

Appendix C: The detailed extraction processes of the research data

  1. 1.

    Fuel consumption rate

The fuel consumption rate reflects the ship’s daily fuel consumption of main engines. It is calculated based on the fields of “Main engine fuel consumption” and “Report duration” in the corresponding noon reports:

$$ r = 24 \times \frac{{{\text{Main}}\;{\text{engine}}\;{\text{fuel}}\;{\text{consumption}}}}{{{\text{Report}}\;{\text{duration}}}} $$
(C.1)
  1. 2.

    Ship speed

The speed through water (STW) is calculated by dividing “Distance through water” by “Report duration”. Therefore, it is an average value for the corresponding report duration. Another speed, known as speed over ground (SOG), is also commonly used in the shipping industry. It is derived from “Distance over ground” and “Report duration”. Here, in order to take the influences of current and tides into account, we choose STW as the ship speed:

$$ V = \frac{{{\text{Distance}}\;{\text{through}}\;{\text{water}}}}{{{\text{Report}}\;{\text{duration}}}} $$
(C.2)
  1. 3.

    Displacement

We cannot obtain the displacement from noon reports directly. However, a ship’s hydrostatic table is provided by the shipping company, in which the corresponding relationship between displacement and mean draft can be obtained. The mean draft can be calculated based on the fields of “Forward draft” and “Aft draft”:

$$ {\text{mean}}\;{\text{draft}} = \frac{{{\text{Forward}}\;{\text{draft}} + {\text{Aft}}\;{\text{draft}}}}{2} $$
(C.3)
  1. 4.

    Weather direction

The weather direction is derived from the wind/waves direction angle (with respect to the ship’s bow) and can be defined as four different directions depending on the angle degree: head sea, bow sea, beam sea and following sea, as presented in Fig. 1. In practice, loading due to wind and waves is assumed to be from the same angle with respect to the ship’s bow. Here, \( \theta \) represents the wind/waves direction angle with respect to the ship’s bow. In noon reports, the field of “Wind direction” means the angle with respect to the True North, as well as the field of “Ship heading”. \( \theta \) can be calculated according to the following logical statement (Bialystocki and Konovessis 2016):

$$ \theta = \left\{ \begin{aligned} & \left| {{\text{Wind}}\;{\text{direction}} - {\text{Ship}}\;{\text{heading}} - 360^\circ } \right|,\;{\text{IF}}\;{\text{Wind}}\;{\text{direction}} - {\text{Ship}}\;{\text{heading}} > 180^\circ \\ & \left| {{\text{Wind}}\;{\text{direction}} - {\text{Ship}}\;{\text{heading}} + 360^\circ } \right|,\;{\text{IF}}\;{\text{Wind}}\;{\text{direction}} - {\text{Ship}}\;{\text{heading}} < - 180^\circ \\ & \left| {{\text{Wind}}\;{\text{direction}} - {\text{Ship}}\;{\text{heading}}} \right|,\;{\text{Otherwise}} \\ \end{aligned} \right.$$
(C.4)
  1. 5.

    Beaufort number

The Beaufort number can be obtained directly from noon reports.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yang, L., Chen, G., Rytter, N.G.M. et al. A genetic algorithm-based grey-box model for ship fuel consumption prediction towards sustainable shipping. Ann Oper Res (2019). https://doi.org/10.1007/s10479-019-03183-5

Download citation

  • Published:

  • DOI: https://doi.org/10.1007/s10479-019-03183-5

Keywords

Navigation