High-fidelity models capable of accurately predicting ship motion are critical for promoting innovation and efficiency in the maritime industry. However, creating an advanced model that comprehensively represents the system and its interaction with dynamic environments has always been challenging. Many models provide partial knowledge about a system. To handle the deficiency and improve model fidelity, in this artile, we propose a hybrid modeling methodology, in which prior knowledge describing the ship dynamic effects is incorporated into a data-driven calibrator, yielding a representative model with high predictive capability. Enabled by the integration of model estimated ship states into the calibrator, the informative information could be interpreted and carried forward. Simulation and full-scale experiments are conducted on the research vessel Gunnerus to exemplify the concept. A best available numerical model and a neural network are prepared to be the foundation and calibrator, respectively. Experiment results show that the cooperative model greatly improves the predictive capability of the research vessel. From the ship modeling perspective, this study provides new insights by bridging the gap between two separate domains: 1) model-based and 2) data-driven.

Digitalization has become a key aspect of making maritime industries more innovative, efficient, and fit for future operations. One of the most attractive aspects is the concept of digital twins , which refers to digital replicas of physical assets, processes, and systems that can be used as advanced tools for design, operation, and maintenance. This article introduces the development of the digital twin of the research vessel (RV) Gunnerus in Norway, which will be a significant scientific and operational achievement for the maritime industry, making efficient and safe offshore operations possible. It enables data exchange safely and easily among different subsystems, modules, and various applications. Thus, the twin ship can provide an integrated view of the ship’s various physical and behavioral aspects in different stages and allow simultaneous optimization of functional performance requirements. In addition, it enables advanced control and optimization, e.g., creating more reliable prediction for flexible objectives (time, output, emissions, fuel consumption), and executing day-ahead and long-term planning for operations. Several related applications are presented in the end to confirm the effectiveness of the digital twin ship system.

Demanding marine operations increase the complexity of manoeuvring. A highly accurate ship model promotes predicting ship motions and advancing control safety. It is crucial to identify the unknown hydrodynamic coefficients under environmental disturbance to establish accurate mathematical models. In this paper, the identification procedure for a 3 degree of freedom hydrodynamic model under disturbance is completed based on the support vector machine with multiple manoeuvres datasets. The algorithm is validated on the clean ship model and the results present good fitness with the reference. Experiments in different sea states are conducted to investigate the effects of the turbulence on the identification performance. Generalisation results show that the models identified in the gentle and moderate environments have less than 10% deviations and are considered allowable. The higher perturbations, the lower fidelity the identified model has. Models identified under disturbance could provide different levels of reliable support for the operation decision system.

Parameter identification in nonlinear offshore ship dynamics is crucial yet challenging, especially when measurement noise complicates the process. Differential models are particularly susceptible to large errors due to the discrete numerical differentiation of noisy data. To enhance noise resilience and achieve accurate parameter estimates, this article proposes the use of physics-informed neural networks (PINN) to identify ship roll dynamics. Constrained by physical principles, the PINN learns ship parameters with physical interpretability, employing automatic differentiation to circumvent the noise issues inherent in discrete differentiation. Leveraging the periodic nature of roll motion, a novel activation function is introduced to improve training efficiency. Robustness is validated through simulations of ship roll dynamics under regular and random wave excitations at various noise levels. Full-scale experiments conducted in open sea conditions confirm the practical effectiveness of the proposed approach in real-world scenarios.