A Deep Neural Network to Predict the Residual Hull Girder Strength

• DOI: 10.5957/smc-2022-074
• Publication Date: 2022-09-19T00:06:50Z
• Authors: Alessandro La Fer...; Emanuel Di Nardo; Massimo Macera; Thomas Lindemann; Angelo Ciaramella; Nikolaos Koulianos
• Keywords: Residual strength; Activation function

The main purpose of this study is to apply a Deep Neural Network (DNN) method linear systems and predict in relatively short time span the ultimate vertical bending moment (VBM) for damaged ships. A approach, which composed multiple fully connected layers with Rectified Linear Unit (ReLU) non-linear activation function, has been applied more than 6000 samples validated using leave-one-out technique. strength predicted set completely new damage scenarios different cross sections, enhancing that deep neural network can estimate residual hull girder correlated index general (DIG). as well shift neutral axis are against Smith’s method-based results.