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
• ISSN: 0948-4280; 1437-8213
• DOI: 10.1007/s00773-021-00819-9

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 (LSTM) deep neural network, which is more easily trained than traditional feedforward neural network with more complicated network structure. First, multiple datasets of simulated standard maneuvers (10°/10° and 20°/20° zigzag, 35° turning circle) of a KVLCC2 model are artificially polluted with white noise of various levels and used simultaneously to train the deep neural network model. Meanwhile, the data of 15°/15° zigzag maneuver are used to facilitate the training process to alleviate overfitting problem. Second, different datasets of modified zigzag tests are used to validate the generalization performance and robustness to noise of the trained neural network model. The training and validation results demonstrate that a mapping between the dynamics of ship motion and the computation in LSTM deep neural network is correctly identified. This mapping indicates that the complex nonlinear features of ship maneuvering motion can be learned from the measured temporal data, using standard training techniques for deep neural networks. An equivalent LSTM deep neural network model with better generalization performance and robustness is established, and its accuracy in predicting ship maneuvering motion is validated.