radial basis function
Recently Published Documents


TOTAL DOCUMENTS

4802
(FIVE YEARS 930)

H-INDEX

91
(FIVE YEARS 12)

Author(s):  
Parviz Ghadimi ◽  
Amin Nazemian

Marine industrial engineering face crucial challenges because of environmental footprint of vehicles, global recession, construction, and operation cost. Meanwhile, Shape optimization is the key feature to improve ship efficiency and ascertain better design. Accordingly, the present paper proposes an automated optimization framework for ship hullform modification to reduce total resistance at two cruise and sprint speeds. The case study is a bow shape of a wave-piercing bow trimaran hull. To this end, a multi-objective hydrodynamic problem needs to be solved. A combined optimization strategy using CFD hullform optimization is presented using the software tools STAR-CCM+ and SHERPA algorithm as optimizer. Furthermore, a comparison is made between CAD-based and Mesh-based parametrization techniques. Comparison between geometry regeneration methods is performed to present a practical and efficient parametrization tool. Design variables are control points of FreeForm Deformation (FFD) for CAD-based method and Radial Basis Function (RBF) for Mesh-based method. The optimization results show a 4.77% and 2.47% reduction in the total resistance at cruise and sprint speed, respectively.


Processes ◽  
2022 ◽  
Vol 10 (1) ◽  
pp. 140
Author(s):  
Yanxia Yang ◽  
Pu Wang ◽  
Xuejin Gao

A radial basis function neural network (RBFNN), with a strong function approximation ability, was proven to be an effective tool for nonlinear process modeling. However, in many instances, the sample set is limited and the model evaluation error is fixed, which makes it very difficult to construct an optimal network structure to ensure the generalization ability of the established nonlinear process model. To solve this problem, a novel RBFNN with a high generation performance (RBFNN-GP), is proposed in this paper. The proposed RBFNN-GP consists of three contributions. First, a local generalization error bound, introducing the sample mean and variance, is developed to acquire a small error bound to reduce the range of error. Second, the self-organizing structure method, based on a generalization error bound and network sensitivity, is established to obtain a suitable number of neurons to improve the generalization ability. Third, the convergence of this proposed RBFNN-GP is proved theoretically in the case of structure fixation and structure adjustment. Finally, the performance of the proposed RBFNN-GP is compared with some popular algorithms, using two numerical simulations and a practical application. The comparison results verified the effectiveness of RBFNN-GP.


Sign in / Sign up

Export Citation Format

Share Document