Abstract
Based on the modeling method of the co-operation between the characteristic maps and the mathematical equations, a propulsion system simulation model which includes model for large low speed two-stroke diesel engine (MAN B&W 10L90MC) and model for shaft, propeller and ship hull dynamics is proposed. To calculate propeller's characteristic, the regression functions are adopted. The simulation experiments demonstrate the model can be used for engine performance prediction as well as investigating control schedules of marine propulsion system. The increased use of digital electronic technology for marine diesel propulsion control leads to more reliable and efficient propulsion power plants. Neural networks have been used for the implementation of continuous propeller torque demand prediction that can be exploited by engine control preventively in order to avoid excessive overspeed at near-MCR engine running under rough sea conditions. The neural predictor has been validated through simulation, using data recorded during scheduled operation of a large containership, as well as, from simulation.