Artificial Intelligence Design for Ship Structures: A Variant Multiple-Input Neural Network-Based Ship Resistance Prediction

Abstract

Abstract In this work, we have developed a data-driven artificial intelligence (AI) solution to assist the ship hull design process. Specifically, we have developed and implemented an AI-based multiple-input neural network model to realize the real-time prediction of the total resistance of the ship hull structure while avoiding the inconsistent estimates from different types of design input parameters. It is demonstrated that the developed AI-based machine learning algorithm as a prediction tool can assist the ship hull design process by accurately providing the total resistance of ship hulls in real time. Moreover, we have conducted design tasks to validate the proposed method, and the validation results show that a well-trained artificial neural network model can avoid the problem of different sensitivities due to the different degrees of influence of the input parameters on the output parameter. The proposed AI-based data-driven solution provides a real-time hydrodynamic performance calculation, which can predict the hyperdynamic performances of ship hulls based on their geometry modification parameters. This approach gives a consistent prediction in terms of accuracy when facing different geometry modification parameters, and it in turn provides a fast and accurate AI-based method to assist ship hull design to achieve an optimum forecast accuracy in the entire design space, making an advance to artificial intelligence assist design in naval architecture engineering.