Support Vector Regression-based Multidisciplinary Design Optimization in Aircraft Conceptual Design

2013 ◽  
Author(s):  
Keshi Zhang ◽  
Zhonghua Han
Keyword(s):  
Design Optimization ◽  
Support Vector Regression ◽  
Conceptual Design ◽  
Multidisciplinary Design Optimization ◽  
Multidisciplinary Design ◽  
Support Vector ◽  
Aircraft Conceptual Design

Support Vector Regression-Based Multidisciplinary Design Optimization for Ship Design

2012 ◽  
Author(s):  
Dongqin Li ◽  
Yifeng Guan ◽  
Qingfeng Wang ◽  
Zhitong Chen
Keyword(s):  
Design Optimization ◽  
Support Vector Regression ◽  
Design Process ◽  
Multidisciplinary Design Optimization ◽  
Initial Point ◽  
Ship Design ◽  
Collaborative Optimization ◽  
Multidisciplinary Design ◽  
Support Vector ◽  
Independent Design

The design of ship is related to several disciplines such as hydrostatic, resistance, propulsion and economic. The traditional design process of ship only involves independent design optimization within each discipline. With such an approach, there is no guarantee to achieve the optimum design. And at the same time improving the efficiency of ship optimization is also crucial for modem ship design. In this paper, an introduction of both the traditional ship design process and the fundamentals of Multidisciplinary Design Optimization (MDO) theory are presented and a comparison between the two methods is carried out. As one of the most frequently applied MDO methods, Collaborative Optimization (CO) promotes autonomy of disciplines while providing a coordinating mechanism guaranteeing progress toward an optimum and maintaining interdisciplinary compatibility. However there are some difficulties in applying the conventional CO method, such as difficulties in choosing an initial point and tremendous computational requirements. For the purpose of overcoming these problems, Design Of Experiment (DOE) and a new support vector regression algorithm are applied to CO to construct statistical approximation model in this paper. The support vector regression algorithm approximates the optimization model and is updated during the optimization process to improve accuracy. It is shown by examples that the computing efficiency and robustness of this CO method are higher than with the conventional CO method. Then this new Collaborative Optimization (CO) method using approximate technology is discussed in detail and applied in ship design which considers hydrostatic, propulsion, weight and volume, performance and cost. It indicates that CO method combined with approximate technology can effectively solve complex engineering design optimization problem. Finally, some suggestions on the future improvements are proposed.

Multidisciplinary Design Optimization on Conceptual Design of Aero-engine

2016 ◽  
Vol 33 (2) ◽  
Author(s):  
Xiao-bo Zhang ◽  
Zhan-xue Wang ◽  
Li Zhou ◽  
Zeng-wen Liu
Keyword(s):  
Design Optimization ◽  
Conceptual Design ◽  
Multidisciplinary Design Optimization ◽  
System Level ◽  
Multidisciplinary Design ◽  
Design Stage ◽  
Surface Model ◽  
Coupled Problem ◽  
Aero Engine ◽  
Integrated Performance

AbstractIn order to obtain better integrated performance of aero-engine during the conceptual design stage, multiple disciplines such as aerodynamics, structure, weight, and aircraft mission are required. Unfortunately, the couplings between these disciplines make it difficult to model or solve by conventional method. MDO (Multidisciplinary Design Optimization) methodology which can well deal with couplings of disciplines is considered to solve this coupled problem. Approximation method, optimization method, coordination method, and modeling method for MDO framework are deeply analyzed. For obtaining the more efficient MDO framework, an improved CSSO (Concurrent Subspace Optimization) strategy which is based on DOE (Design Of Experiment) and RSM (Response Surface Model) methods is proposed in this paper; and an improved DE (Differential Evolution) algorithm is recommended to solve the system-level and discipline-level optimization problems in MDO framework. The improved CSSO strategy and DE algorithm are evaluated by utilizing the numerical test problem. The result shows that the efficiency of improved methods proposed by this paper is significantly increased. The coupled problem of VCE (Variable Cycle Engine) conceptual design is solved by utilizing improved CSSO strategy, and the design parameter given by improved CSSO strategy is better than the original one. The integrated performance of VCE is significantly improved.

Towards the automation of concurrent space systems conceptual design through multidisciplinary design optimization

2015 ◽  
Author(s):  
Ronan Arraes Jardim Chagas ◽  
Bráulio Fonseca Carneiro de Albuquerque ◽  
Rafael Anderson Martins Lopes ◽  
Fabiano Luis de Sousa
Keyword(s):  
Design Optimization ◽  
Conceptual Design ◽  
Multidisciplinary Design Optimization ◽  
Multidisciplinary Design ◽  
Space Systems
Sign in / Sign up

Export Citation Format

Share Document