An efficient artificial neural network model to predict the structural failure of high-density polyethylene offshore net cages in typhoon waves. (15th January 2020)

• Record Type: Journal Article
• Authors: Bi, Chun-Wei; Zhao, Yun-Peng; Sun, Xiong-Xiong; Zhang, Yao; Guo, Zhi-Xing; Wang, Bin; Dong, Guo-Hai
• Is Part Of: Ocean engineering. Volume 196(2020)
• Publication Date: 2020-01-15
• Subjects: Prediction model -- Structural failure -- Offshore net cage -- Artificial neural network -- Field survey; Ocean engineering -- Periodicals; Ocean engineering; Periodicals; 620.4162
• DOI: 10.1016/j.oceaneng.2019.106793
• Languages: English
• ISSNs: 0029-8018

Abstract

Abstract: Offshore net cages are aquaculture facilities that can provide satisfactory volumes of stocked fish. The safety of these structures is of great importance to aquaculture companies. Typhoons are considered to be the main cause of damage to offshore net cages. In this study, an artificial neural network (ANN) model was developed to predict the structural failure of high-density polyethylene offshore net cages in typhoon waves. A case study was conducted where the ANN model was used to predict the structural failure of the offshore net cages around Nanji Island, Wenzhou, China, during Typhoon Maria. Field survey was performed to study the hydrodynamics of the offshore net cages in different wave conditions and the results were used as the training data for the ANN model. By classifying the structural failure, the damage levels of offshore net cages can be predicted and used with wave forecasting before typhoon landing. Field survey was carried out immediately after the typhoon. The prediction and field survey results showed that the proposed ANN model can accurately predict the damage levels of offshore net cages under the influence of typhoon waves. Highlights: A model is proposed to predict the structural failure of fish cages in typhoon waves. The damage levels of fish cages can be predicted rapidly and accurately. The prediction model is validated against field survey results after Typhoon Maria.