Optimization of Seakeeping Behavior of Fishing Ships by Artificial Neural Networks

Abstract

Seakeeping behavior assessment is paramount in ship operation. Traditionally analyzed through experimental trials or numerical models, both methods demand significant testing or calculation time. However, the advent of Artificial Intelligence (AI) presents an opportunity to leverage AI techniques for predicting seakeeping behavior. This study employs a pre-trained Artificial Neural Network (ANN) to assess seakeeping behavior. One of the primary advantages of using these algorithms is their ability to quickly predict a vast array of scenarios, in stark contrast to traditional methods. This work sets out to identify fishing ship geometries tailored to marine conditions, optimizing specific metrics related to operability. The paper concludes by presenting the most salient findings.

Download the full paper here

Authors & Affiliations

• Pablo Romero Tello
  Universidad Politécnica de Cartagena
  Cartagena, Spain

• José Enrique Gutiérrez Romero
  Universidad Politécnica de Cartagena
  Cartagena, Spain

• Borja Serván Camas
  Centre Internacional de Mètodes Numèrics en Enginyeria CIMNE
  Barcelona, Spain

• Antonio José Lorente López
  Universidad Politécnica de Cartagena
  Cartagena, Spain