Identification modeling and prediction of ship maneuvering motion based on LSTM deep neural network

• Published in: Journal of marine science and technology Vol. 27; no. 1; pp. 125 - 137
• Main Authors: Jiang, Yan, Hou, Xian-Rui, Wang, Xue-Gang, Wang, Zi-Hao, Yang, Zhao-Long, Zou, Zao-Jian
• Format: Journal Article
• Language: English
• Published: Tokyo Springer Japan 01.03.2022; Springer; Springer Nature B.V
• Subjects: Analysis; Artificial neural networks; Automotive Engineering; Computation; Datasets; Engineering; Engineering Design; Engineering Fluid Dynamics; Identification; Learning; Maneuvers; Mapping; Mechanical Engineering; Neural networks; Noise; Offshore Engineering; Original Article; Robustness; Ship handling; Ship motion; System identification; Training; White noise; Deep learning; System identification; Ship maneuvering; LSTM network

This paper proposes a novel system identification scheme to obtain a MIMO model of ship maneuvering motion, which can leverage the temporal correlation from the constructed training data to learn the underlying feasible model robust to extraneous noise. The scheme is based on long–short-term-memory...