This paper introduces a novel method for modelling the influence of likely autonomous sailing craft failure conditions into the route planning algorithm. The accuracy of the original route planning algorithm is quantified using numerical error estimation techniques. It was found that over the course of a Trans Atlantic voyage a grid size of 36 km produced an error of +/- 2 hours over the course of a $36.5$ day voyage. The implementation of the failure model within the routing algorithm is verified using a control weather scenario. This verification is shown to be significant with respect to the method's numerical error. Future work will involve gathering evidence on failure criteria in order to update the failure model.

No abstract

No abstract

Quantifying the wave resistance of a swimmer as a function of depth assists in identifying the optimum depth for the glide phases of competition. Previous experiments have inferred how immersed depth influences the drag acting on a swimmer [1], but have not directly quantified the magnitude of wave resistance. This research experimentally validates the use of thin-ship theory for quantifying the wave resistance of a realistic swimmer geometry. The drag and wave pattern of a female swimmer 5 mannequin were experimentally measured over a range of depths from 0.05m to 1.00m at a speed of 2.50 m/s. Numerical simulations agree with experiment to confirm that there were negligible reductions in wave resistance below a depth of 0.40m. Larger swimming pool dimensions are shown to be significant at reducing wave resistance at speeds above 2.0 m/s and depths below 0.40m.Truncating the swimmer's body at the upper thigh increases the wave resistance at speeds below 10 2.0m/s but is not significant at higher speeds, indicating that the upper body is the main contributor to the wave system. Numerical experiments indicate that rotating the shoulders towards the surface is more influential than the feet, demonstrating the impact of the upper body on wave resistance.

Accurate modelling of the performance of a yacht in varying environmental conditions can significantly improve a yachts performance. However, a racing yacht is a highly complex multi-physics system meaning that real-time performance prediction tools are always semi-empirical, leaving significant room for improvement. In this paper we first use unsupervised machine learning to analyse full-scale yacht performance data. The widely documented ORC VPP (ORC, 2015) and the commercial Windesign VPP are compared to the data across a range of wind conditions. The data is then used to train machine learning models. A number of machine learning regression algorithms are explored including Neural Networks, Random Forests and Support Vector Machines and improvements of 82% are obtained compared to the commercial tools. The use of physics- based learning models (Weymouth and Yue, 2013) is explored in order to reduce the amount of data required to achieve accurate predictions. It is found that machine learning models can outperform empirical models even when predicting performance in environmental conditions that have not been supplied to the model as part of the training dataset.