Rotor dynamic force coefficients of gas seals strongly depend on the machine operational conditions. These force coefficients influence the overall dynamical response and modal properties of machines, consequently defining the machine vibration levels. Accurate estimations of the rotor dynamic coefficients are required for designing machines with low vibration amplifications and well-defined stability margins throughout the operational range. Experimental methods applied to test benches are used to validate such force coefficients and they normally rely on (i) the quality of the measurements and (ii) the assumption that the mathematical model is able to capture the whole system dynamics. If relevant dynamical contributions in a system are neglected by the mathematical model, the contribution will erroneously be concluded to originate from the seal being tested. The theoretical and experimental investigation in this paper focuses on quantifying and qualifying the effect of neglected system dynamics modelling on the estimation of seals force coefficients and stability margins. The in-situ identification of seal forces shows that the direct stiffness, cross-coupling stiffness, and direct damping coefficient estimations for a gas seal with high preswirl are statistically significantly affected by the baseline model. Nevertheless, the baseline model leads to small deviations of the seal force coefficient estimations. The prediction accuracy of stability margins is found to be more influenced by the baseline model describing the system dynamics than by the deviations between the seal force coefficient estimations.
Digital Twins have much attention in the shipping industry, attempting to support all phases of a vessel’s life cycle. With several tools appearing in Digital Twin software suites, high-quality manoeuvring and performance prediction remain cornerstones. Propulsion efficiency is in focus while in service. Simulator-based training is in focus to ensure safety of manoeuvring in confined waters and harbours. Prediction of ships’ velocity and turn rate are essential for correct look and feel during training, but phenomena like dynamic inflow to propellers, bank and shallow water effects limit simulators’ accuracy, and master mariners often comment that simulations could be in better agreement with actual behaviours of their vessel. This paper focuses on digital twin enhancements to better match reality. Using data logged during in-service operation, we first consider a system identification perspective, employing a first-principles model structure. Showing that a complete firstprinciples model is not identifiable under the excitation met in service, we employ a Recurrent Neural Network to predict deviations between measured velocities and the model output. The outcome is a hybrid of a first-principles model with a machine learning generic approximator add-on. The paper demonstrates significant improvements in prediction accuracy of both in-harbour manoeuvring and shallow water passage conditions.