Deep Learning Based Prediction of Hydrodynamic Forces on Offshore Platforms

Abstract

Abstract Irregular ocean waves cause fluctuating non-linear hydrodynamic forces on the body, which is an importance factor to account for in offshore and marine applications. While physical experimental and computational techniques provide valuable physics insight, they are generally time-consuming and expensive for design space exploration. We present an efficient Long Short Time Memory (LSTM) based deep-learning technique to predict unsteady hydrodynamic forces on slender bodies, where drag forces are more dominant than inertia forces. A leaky non-linear rectification is employed to approximate the mapping between surface elevation time series and hydrodynamic (drag) force time series. The deep neural network is fed with irregular waves based on JONSWAP spectrum as the input and the target data generated by the full-order Navier-Stokes computations using a generic offshore jack-up platform. The LSTM is trained using a stochastic gradient descent method to predict time series of the hydrodynamic forces on the jack-up and the results are compared with the full-order computations. Within the error threshold, the predictions based on our deep convolutional network have a speed-up of nearly 2 orders of magnitude compared to the full-order results and consume an insignificant fraction of computational resources. Overall, the proposed LSTM-based approximation procedure has the potential to be used for parametric design and digital twinning of jack-up platforms.