On neural network identification for low-speed ship maneuvering model
On neural network identification for low-speed ship maneuvering model
复制标题
低速船舶操纵模型的神经网络辨识
DOI：
10.1007/s00773-021-00867-1
复制
发表时间：
2022
影响因子：
2.6
通讯作者：
Akimoto Youhei
中科院分区：
文献类型：
--
作者：
Wakita Kouki;Maki Atsuo;Umeda Naoya;Miyauchi Yoshiki;Shimoji Tohga;Rachman Dimas M.;Akimoto Youhei
利用系留模型试验或计算流体动力学（CFD）和物理模型（如操纵模型组（MMG）模型）对船舶操纵模型进行了一些研究。提出了一种新的系统辨识方法，用于利用递归神经网络（RNNs）和自由运行模型测试生成低速机动模型。我们特别关注低速机动，如靠泊的最后阶段，以实现自动靠泊控制。为了建立基于模型的控制系统，迫切需要精确的动态建模和最小的建模误差。我们提出了一个新的损失函数，减少了训练数据中包含的噪声的影响。此外，我们还发现了以下事实-与“标准”RNN相比，忽略一定时间之前的记忆的RNN提高了预测精度，并且手动随机操纵测试在获得准确的靠泊操纵模型方面是有效的。此外，还对M. V. Esso Osaka的比例模型进行了几次低速自由运行模型试验。结果表明，所提出的方法使用神经网络模型可以准确地表示低速机动运动。
Several studies on ship maneuvering models have been conducted using captive model tests or computational fluid dynamics (CFD) and physical models, such as the maneuvering modeling group (MMG) model. A new system identification method for generating a low-speed maneuvering model using recurrent neural networks (RNNs) and free running model tests is proposed in this study. We especially focus on a low-speed maneuver such as the final phase in berthing to achieve automatic berthing control. Accurate dynamic modeling with minimum modeling error is highly desired to establish a model-based control system. We propose a new loss function that reduces the effect of the noise included in the training data. Besides, we revealed the following facts—an RNN that ignores the memory before a certain time improved the prediction accuracy compared with the “standard” RNN, and the manual random maneuver test was effective in obtaining an accurate berthing maneuver model. In addition, several low-speed free running model tests were performed for the scale model of the M.V. Esso Osaka. As a result, this paper showed that the proposed method using a neural network model could accurately represent low-speed maneuvering motions.