【摘要】 本文以单桨肥大型船回转性能为例，探讨应用改进的ＢＰ神经网络建立船舶操纵性预报 数学模型的方法。研究结果表明，只要选择适当的学习样本、网络结构和学习算法，该数学模 型的预报精度在工程上可以接受。更多还原

【Abstract】 In this paper, the prediction of ship maneuverability based on an improved artificial neural network is studied, and the turning performance of single screw full form ships are taken for an example. It is verified that the prediction accuracy of this method is acceptable in engineering practice, if the learning samples, network’s structure and learning algorithm are reasonable.更多还原