Session: 09-02-05 Wave Energy: Design and Innovation 2

Paper Number: 129671

129671 - A Hybrid Deep Learning Approach to Predict Dynamic Mooring Tension of a Wave Energy Converter 

Enhancing the precision of short-term mooring tension prediction holds the key to bolstering safety measures within marine operations. In this study, a hybrid model which takes the advantages of convolutional neural networks (CNN) and Bi-directional long short-term memory neural networks (BiLSTM) is developed to predict dynamic mooring tension time series of a wave energy converter. The datasets used to train the hybrid model were collected from model tests conducted in a wave flume. The hybrid model is trained using motion responses of a wave energy converter. The study explores and discusses the impact of various factors on the performance of the hybrid CNN-BiLSTM model, including the number of layers, the number of neurons, the choice of optimizer, the length of memory, and the duration of training. Optimal model parameters are determined through an assessment of error indexes. To evaluate the effectiveness of the hybrid model, a comparison is made between its performance in dynamic mooring tension prediction and that of other existing models, including Bi-LSTM, Support Vector Machine (SVM), and Extreme Learning Machine (ELM). It is found that the presented model gives more accurate predictions of mooring tensions that that of other models. This research offers highlights the substantial potential of the proposed method in predicting mooring tensions for other offshore floating structures.

Presenting Author: Sheng Xu Jiangsu University of Science and Technology

Presenting Author Biography: Sheng Xu is currently serving as an Associate Professor within the School of Naval Architecture and Ocean Engineering at Jiangsu University of Science and Technology. He successfully completed his Ph.D. degree in 2021 at Instituto Superior Técnico, University of Lisbon, under the guidance of Professor Carlos Guedes Soares. Throughout the course of his doctoral studies, Sheng Xu actively participated in various research projects pertaining to hydrodynamic analysis and mooring design for offshore renewable energy devices. His primary research interests focus on the mooring design, offshore renewable energy devices, using both experimental and numerical methods.

Authors:

Sheng Xu Jiangsu University of Science and Technology
Shan Wang Instituto Superior Técnico, Universidade de Lisboa
Carlos Guedes Soares Instituto Superior Técnico,Universidade de Lisboa