الأحد، ١٣ مارس ٢٠١١

DESIGNING HIGH SPEED MONOHULL SMALL CRAFTS (HSMSC) USING NEURAL NETWORKS GUIDED CFD BASED OPTIMIZATION


              IEEE OCEANS Conference Bremen, Germany, May, 2009
Mohammad Alaa El-laffy, Mohamed Abdel-Salam, Bassam Salah, Beshoy Magdy, Mohammad Tarek, Ahmad El-bastaweesy, Islam Adel , Mohammad Mahmoud, Ihab El-deen Abdel-majeed, Ahmad El-sayed
 DESIGNING HIGH SPEED MONOHULL SMALL CRAFTS (HSMSC) USING NEURAL NETWORKS GUIDED CFD BASED OPTIMIZATION
Abstract
 A new optimal design strategy for monohull vessels is proposed. The goal of the proposed procedure is
to make monohulls competitive with their multihull counterparts. The resulting designs, thus, would
combine the advantages of high speed vessels with those of simpler monohull vessels. The proposed
strategy proposes a new re-formulation of hull optimization problem objective and uses a new class of
Artificial Neural Networks (ANNs) to achieve it. Computational Fluid Dynamics (CFD) simulation is
used to provide the necessary data for ANN training. The advantage of the used ANN over classical
ones is that it adopts a one-shot lagrangian-like training procedure. The proposed design strategy is
proven to be effective through several CFD-validated design examples

ليست هناك تعليقات:

إرسال تعليق