Abstract
A significant method of artificial intelligence (AI) is artificial neural networks (ANN). It is a data-based approach, which allows for mathematically capturing multidimensional relationships. Studying approaches that can reflect dynamic non-linear processes, the sample of diesel particle generation was chosen, where standard map representations or polynomial approaches quickly become impractical. ANN as universal approximators offer a possibility which, if sufficient training data is available, provides a good assignment of input data to output data. The computing time is very small so it is possible to use this ANN method for rapid predictions during ship manoeuvres. The example of ship engine particle emissions is used to demonstrate how methods of AI may potentially support people in competent decision-making for manoeuvring action. Having a better idea of the impact of intended manoeuvres may support navigational officers to take more easily decisions in the sense of sustainable shipping.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
E. Konrad, Zur Geschichte der Künstlichen Intelligenz in der Bundesrepublik Deutschland, in Sozialgeschichte der Informatik, ed. by D. Siefkes, P. Eulenhöfer, H. Stach, K. Städtler, (Studien zur Wissenschafts- und Technikforschung. Deutscher Universitätsverlag, Wiesbaden, 1998)
W.S. McCulloch, W. Pitts, A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 4, 115–133 (1943)
O. Nelles, Nonlinear System identification, from Classical Approaches to Neural Networks and Fuzzy Models (Springer, Berlin, 2001)
R. Isermann, S. Ernst, O. Nelles, Identification with Dynamic Neural Networks – Architectures, Comparisons, Applications, in IFAC Proceedings, vol. 11, pp. 947–972, 1997
ISSIMS GmbH: SAMMON, Simulation Augmented Manoeuvring Design & Monitoring System. Version 1.4, https://www.issims-gmbh.com/yoomla/products/sammon
M. Schaub, G. Finger, T. Riebe, F. Dahms, E. Hassel, M. Baldauf, Data-Based Modelling of Ship Emissions and Fuel Oil Consumption for Transient Engine Operation, in OCEANS Proceedings, 2019
ISSIMS GmbH: SAMMON, Simulation Augmented Manoeuvring Design & Monitoring System. Version 1.4, https://www.issims-gmbh.com/yoomla/products/simopt
https://pegasor.fi/site/attachments/Pegasor_Mi3_web.pdf (2020)
Acknowledgements
The approach described above is derived from a German research project (03SX423E), granted by the German Ministry of Economic Affairs and Energy. The herein presented software tools SAMMON and SIMOPT were provided by ISSIMS GmbH. Further acknowledgement goes to the ERASMUS+ project EURO-ZA, funded by the European Commission, which supports the international establishment of the described assistance software at maritime institutions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Schaub, M., Benedict, K., Kirchhoff, M. (2021). Artificial Intelligence as a Practical Approach to Represent Complex Dynamic Relationships in Maritime Navigation. In: Bauk, S., Ilčev, S.D. (eds) The 1st International Conference on Maritime Education and Development. Springer, Cham. https://doi.org/10.1007/978-3-030-64088-0_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-64088-0_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-64087-3
Online ISBN: 978-3-030-64088-0
eBook Packages: EngineeringEngineering (R0)