For operations at sea it is important to have a good estimate of the current local sea state. Often, sea state information comes from wave buoys or weather forecasts. Sometimes wave radars are used. These sources are not always available or reliable. Being able to reliably use ship motions to estimate sea state characteristics reduces the dependency on external and/or expensive sources. In this paper, we present a method to estimate sea state characteristics from time series of 6-DOF ship motions using machine learning. The available data consists of ship motion and wave scanning radar measurements recorded for a period of two years on a frigate type vessel. The research focused on estimating the relative wave direction, since this is most difficult to estimate using traditional methods. Time series are well suited as input, since the phase differences between motion signals hold the information relevant for this case. This type of input data requires machine learning algorithms that can capture both the relation between the input channels and the time dependence. To this end, convolutional neural networks (CNN) and recurrent neural networks (RNN) are adopted in this study for multivariate time series regression. The results show that the estimation of the relative wave direction is acceptable, assuming that the data set is large enough and covers enough sea states. Investigating the chronological properties of the data set, it turned out that this is not yet the case. The paper will include discussions on how to interpret the results and how to treat temporal data in a more general sense.

Experimental or numerical analysis of the response of ships and other floating structures starts with correct environmental modelling. The capabilities of numerical tools are rapidly expanding, but presently the evaluation of extreme events in waves (such as slamming, green water, air-gap exceedance) still requires a combination of experiments and different levels of numerical tools. The present paper describes recent efforts within the Maritime Research Institute Netherlands (MARIN) to improve experimental and numerical wave modelling and especially their combination. The ultimate objective is to be able to reproduce any wave condition from a basin or from sea in numerical tools and vice versa, including a sound treatment of basin effects, numerical effects and statistical variability. The aspects that are of importance in both types of wave modelling are first introduced, after which a number of examples of recent projects is discussed. It can be concluded that important steps were made towards linking experimental and numerical wave modelling, but there are some challenges common to all wave reproductions. Some future planned studies focussing on how to deal with them are discussed as well.

Being able to give real time on-board advice, without depending on extensive sets of measured data, is the ultimate goal of the digital twin concept. Ideally, the models used in a digital twin only rely on current in-service data, although they have been built using simulated and possibly some measured data. Working with just the 6-DOF motions of a ship, can the local sea state reliably be estimated using the digital twin concept? Does a general model exist to do so, without the need to measure or simulate the particular ship? In this paper, we discuss how simulations of an advancing ship, subjected to various sea states, can be used to estimate the relative wave direction from in-service motion measurements of the corresponding ship. Various types of neural networks are used and evaluated with simulated data and measured data. In order to study the generalization power of the neural networks, a range of ships has been simulated, with varying lengths, drafts and geometries. Neural networks have been trained on selections of the ships in this extended training set and evaluated on the remaining ships. Results show that the developed neural networks give a remarkable performance in simulation data. Furthermore, generalization over geometry is very good, opening the door to train a general model for estimating sea state characteristics. Using the same model for in-service measurements does not perform well enough yet and further research is required. The paper will include discussion on possible causes for this performance gap and some promising ideas for future work.

The recently finalised Second Generation Intact Stability Criteria (SGISC), produced by the International Maritime Organisation (IMO), contain a level 3 assessment, the so-called Direct Stability Assessment (DSA). This assessment can be carried out using either model experiments or simulations. The fact that such a choice is given implies that the methods are equivalent in accuracy. This assumption has been verified, for one case, by the Cooperative Research Ships (CRS) community. The verification was based on new model experiments and calculated results, using four different programs owned by different CRS members. Results of the verification of the parametric roll failure mode in regular waves were published before, but this study concerns results in irregular seas. The experimental and numerical results are compared in both probabilistic and deterministic manners. The probabilistic comparison showed that the simulation programs considered are sometimes conservative and sometimes non-conservative in the prediction of the probability of an extreme value. The deterministic comparison in head seas showed that parametric roll events were predicted in the simulations in a wave train that showed no sign of important roll events in the measurement. The deterministic comparison in the following seas, on the other hand, showed an accurate fit of experimental and numerical results. It is suggested that predictions could possibly be improved by adding non-linear diffraction forces to the numerical model.