论文部分内容阅读
本文介绍了人工神经网络的基本内容以及前馈网络反向传播的训练方法，并应用单隐含层网络做舰船运动包络的实时预报。文中就一段海上实测舰船运动数据进行了实例计算，结果表明本方法有效，且明显好于其它模型的自适应预报结果。
This paper introduces the basic content of artificial neural network and the training method of backpropagation of feedforward network, and uses single hidden layer network to make real-time forecast of ship motion envelope. In this paper, a case study of a section of marine surveyed ship motion data is carried out. The results show that this method is effective and obviously better than other models’ adaptive forecasting results.