Abstract：Owing to the influence of wave fluctuation，the output power of ship photovoltaic（PV）power

generation system is in the state of fluctuation，which significantly affects the quality of electricity and the

reliability of power supply，and the sun-tracking algorithm of the land-based PV system fails to adapt to the

operating conditions of ships. An optimal tilt angle predictive method of PV panels under the working conditions of

marine vessels was proposed，which took into account the influence of wave fluctuation and sun position change on the output power of ship PV power generation system，analyzed the fluctuation characteristics of the output power curves under the same solar altitude angle，different solar radiation energy and temperature conditions during the rocking cycle of the ship，and predicted the optimal working angle of photovoltaic panels by using BP neural network to adjust the PV panel to improve the output power fluctuation and increase the output power. It is

illustrated that the mean absolute percentage error（MAPE）of the proposed method is less than 0.6% and the root

mean square error（RMSE）is less than 0.1，the reliability of the proposed method was verified.

    Key words：ship rocking；BP neural network；optimal tilt angle；standardization；output power suppression