Neural Network-Based Engine Propeller Matching (NN-EPM) for Trimaran Patrol Ship

Abstract

In recent years efforts on reducing fuel consumption has become the greatest issue related to energy crisis and global warming. The reduction of fuel consumption can be obtained, if the ship propulsion could be operated in its best performance level. Generally this is done by an appropriate analysis of engine propeller matching (EPM). In this study an EPM based on neural-network method, or NN-EPM, is established to predict the best performance of main engines, leading at minimum fuel oil consumption. A trimaran patrol ship is selected as a case study. This patrol ship is equipped with two 2720 kW main engines each connected to a controllable pitch propeller (CPP) through a reduction gear. The input parameters are ship speed V and service margin SM, with the corresponding output parameters comprise of engine speed nE, engine break horse power PB, propeller pitch P/D, and the fuel consumption FC. An NN-EPM 2-20-15-4 configuration has been constructed out of 100 training data and then validated by 30 testing data. The maximum relative error between results from NN-EPM and EPM analysis is 2.1%, that is in term of the fuel consumption. For other parameters the errors are well below 1.0%. These facts indicate that the use of NN-EPM to predict the main engines's performance for trimaran patrol ship is satisfactory.