TY  - GEN
AB  - Condition Based Maintenance on diesel engines can help to reduce maintenance load and better plan maintenance activities in order to support ships with reduced or no crew. Diesel engine performance models are required to predict engine performance parameters in order to identify emerging failures early on and to establish trends in performance reduction. In this paper, a novel approach is proposed to accurately predict engine temperatures during operational dynamic manoeuvring. In this hybrid modelling approach, the authors combine the mechanistic knowledge from physical diesel engine models with the statistic knowledge from engine measurements on a sound engine. This simulation study, using data collected from a Holland class patrol vessel, demonstrates that existing models cannot accurately predict measured temperatures during dynamic manoeuvring, and that the hybrid modelling approach outperforms a purely data driven approach by reducing the prediction error during a typical day of operation from 10% to 2%. 
AD  - Department Of Naval Architecture, Ocean & Marine Engineering - University of Strathclyde - UK
AD  - Research & Technology Support - Damen Schelde Naval Shipbuilding - the Netherlands
AD  - DIBRIS - University of Genoa - Italy
AD  - Research & Technology Support - Damen Schelde Naval Shipbuilding - the Netherlands
AD  - Department of Maritime & Transport Technology - Delft University of Technology - the Netherlands
AD  - Department of Maritime & Transport Technology - Delft University of Technology - the Netherlands
AU  - Coraddu, A
AU  - Kalikatzarakis, M
AU  - Oneto, L
AU  - Meijn, G J
AU  - Godjevac, M
AU  - Geertsma, R D
DA  - 2018-10-02
ID  - 7724
JF  - Conference Proceedings of iSCSS
KW  - Data-Drive methods
KW  - Condition Based Maintenance
KW  - Gray-Box Models
KW  - Exhaust gas temperature prediction
KW  - Machine Learning
L1  - https://library.imarest.org/record/7724/files/ISCSS%202018%20Paper%20030%20Geertsma%20FINAL.pdf
L2  - https://library.imarest.org/record/7724/files/ISCSS%202018%20Paper%20030%20Geertsma%20FINAL.pdf
L4  - https://library.imarest.org/record/7724/files/ISCSS%202018%20Paper%20030%20Geertsma%20FINAL.pdf
LK  - https://library.imarest.org/record/7724/files/ISCSS%202018%20Paper%20030%20Geertsma%20FINAL.pdf
N2  - Condition Based Maintenance on diesel engines can help to reduce maintenance load and better plan maintenance activities in order to support ships with reduced or no crew. Diesel engine performance models are required to predict engine performance parameters in order to identify emerging failures early on and to establish trends in performance reduction. In this paper, a novel approach is proposed to accurately predict engine temperatures during operational dynamic manoeuvring. In this hybrid modelling approach, the authors combine the mechanistic knowledge from physical diesel engine models with the statistic knowledge from engine measurements on a sound engine. This simulation study, using data collected from a Holland class patrol vessel, demonstrates that existing models cannot accurately predict measured temperatures during dynamic manoeuvring, and that the hybrid modelling approach outperforms a purely data driven approach by reducing the prediction error during a typical day of operation from 10% to 2%. 
PY  - 2018-10-02
T1  - Ship diesel engine performance modelling with combined physical and machine learning approach
TI  - Ship diesel engine performance modelling with combined physical and machine learning approach
UR  - https://library.imarest.org/record/7724/files/ISCSS%202018%20Paper%20030%20Geertsma%20FINAL.pdf
VL  - iSCSS 2018
Y1  - 2018-10-02
ER  -