Data-Driven system identification of 6-DoF ship motion in waves with neural networks. (August 2022)

• Record Type: Journal Article
• Authors: Silva, Kevin M.; Maki, Kevin J.
• Is Part Of: Applied ocean research. Volume 125(2022)
• Publication Date: 2022-08
• Subjects: Neural networks -- Machine learning -- System identification -- Ship motion forecasting -- Seakeeping -- Maneuvering -- 6-DoF -- Ship hydrodynamics; Ocean engineering -- Periodicals; 620.416205
• DOI: 10.1016/j.apor.2022.103222
• Languages: English
• ISSNs: 0141-1187

Abstract

Abstract: Critical evaluation of ship responses in the ocean is important for not only the design and engineering of future platforms but also the operation and safety of those that are currently deployed. Short-term temporal predictions of ship responses given the current wave environment and ship state would enable enhanced decision-making onboard and reduce the overall risk for both manned and unmanned vessels, especially as the marine industry trends towards more autonomy. However, state-of-the-art numerical hydrodynamic simulation tools are too computationally expensive to be employed for real-time ship motion forecasting. Thus, a methodology is needed to provide fast predictions with levels of accuracy closer to the higher-fidelity tools. A methodology is developed with long short-term memory (LSTM) neural networks to represent the motions of a free running David Taylor Model Basin (DTMB) 5415 destroyer operating at 20 knots in Sea State 7 stern-quartering long-crested irregular seas. Case studies are performed for both course-keeping and turning circle scenarios. An estimate of the vessel's encounter frame is made with the trajectories observed in the training dataset. Wave elevation time histories are given by artificial wave probes that travel with the estimated encounter frame and serve as input into the neural network, while the output is the 6-DOF temporal ship motion response. Overall, the neural network is able to predict the temporal response of the ship due to unseen wave sequences accurately. The methodology, the dependence of model accuracy on wave probe and training data quantity and the estimated encounter frame are all detailed.