Self-learning based ship onboard decision support system

Cui, H. and Banks, C. and Lazakis, I. and Turan, O. and Incecik, A. (2011) Self-learning based ship onboard decision support system. In: LCS 2011: International Conference on Technological and Operational Advances for Low Carbon Shipping, 2011-06-22 - 2011-06-24.

Full text not available in this repository.Request a copy


Shipping contributes to about 3.3% of global carbon emissions equating to about 1,000 million tons of C02 being emitted into the atmosphere each year. Action therefore needs to be taken to reduce this amount considerably within the coming years. This can be achieved immediately, cost effectively and efficiently by increasing the energy efficiency through crew’s every day operations onboard. An Onboard Decision Support tool to aid crew in making the correct energy efficient decisions can significantly contribute towards reducing emissions. Voyage optimization (route, heading, speed, propeller trim, etc) and maintenance optimization of the main energy consuming systems onboard, are all factors that will be addressed by the proposed Decision Support System framework discussed within this paper. Automatic analytical methods, such as artificial intelligence, are developed for analysis of the historic and real time monitoring of data and ship performance data. Predictive methods are also adopted for forecasting future ship performance. The construction of a unique system framework with an Energy Efficiency Knowledge Bank, which will provide innovative experience sharing based on the analysed data, is presented by utilising a distributed database management system (DDBMS). A numerical optimization is required and the HCPSO and NSGAII optimisation methods are considered for application. The Decision Support takes its basis from an in-house integrated fuzzy decision support method. A few essential attributes and their corresponding importance weightings are used to perform the decision support after the optimization has been carried out; thus providing the crew members with clear and informative suggested best operational (voyage and maintenance) practices.


Cui, H., Banks, C., Lazakis, I. ORCID logoORCID:, Turan, O. and Incecik, A.;