Diesel engine and propulsion diagnostics of a mini-cruise ship by using Artificial Neural Networks

The paper presents the application of Artificial Neural Networks (ANN)—based techniques for diagnostic purposes to a diesel engine powered mini cruise ship. A simulation model of the propulsion plant is developed in order to take into account the effect of the hull fouling and engine components degradation. The effects of weather conditions and trim changes on the hull resistance are also considered: proper formulations are implemented and experimental results, derived from towing tank trials, are adopted. The model is used to generate data in order to train a feed-forward back-propagation ANN for hull and propulsion plant diagnostics: the best set of variables to identify the health status of the plant is selected, then a ANN is trained to provide diagnostic indicators for the main plant components. Training, test and validation errors are presented, and some practical examples are described.