Optimal Design of a U-Shaped Oscillating Water Column Device Using an Artificial Neural Network Model

A U-shaped oscillating water column (U-OWC) device has been investigated to enhance power extraction by placing the bottom-mounted vertical barrier in front of a conventional OWC. Then, optimal design U-OWC attempted using an artificial neural network (ANN) model. First, analytical model is developed matched eigenfunction expansion method (MEEM) based on linear potential theory. Using model, input and output features for training ANN are identified, then database containing established Latin hypercube sampling (LHS) method. With 200 samples, trained with data (70%) validated remaining test (30%). The predictions made 4000 random combinations given significant wave heights energy periods irregular waves. From these predictions, geometric values determined considering both conversion efficiency force barrier. It found that well-trained shows good prediction accuracy provides suitable conditions at installation site.