[an error occurred while processing this directive]
   
 
���¿��ټ��� �߼�����
   ��ҳ  �ڿ�����  ��ί��  Ͷ��ָ��  �ڿ�����  ��������  �� �� ��  ��ϵ����
�������պ����ѧѧ�� 2006, Vol. 32 Issue (08) :926-929    DOI:
���� ����Ŀ¼ | ����Ŀ¼ | ������� | �߼����� << | >>
���ϲ��ϸ�դ�ṹ�Ż�����еļ������ܼ���
������, ��Ԫ��, ��²�*
�������պ����ѧ ���տ�ѧ�빤��ѧԺ, ���� 100083
Computational intelligence technology for optimal design of grid-stiffened composite structure
Rong Xiaomin, Xu Yuanming, Wu Decai*
School of Aeronautic Science and Technology, Beijing University of Aeronautics and Astronautics, Beijing 100083, China

ժҪ
�����
�������
Download: PDF (0KB)   HTML 1KB   Export: BibTeX or EndNote (RIS)      Supporting Info
ժҪ ��Ը��ϲ��ϸ�դ�ṹ�Ż���ƶ��������Լ������������ɢ��ϱ������߶ȷ����Ե��ѵ�,������ý�����������ʵ�ֽṹ��Ʋ���(����)��ṹ��Ӧ����(���)��ȫ�ַ�����ӳ���ϵ,�Դ��������Ż������е�����Ԫ����,������Ż�Ч��.���Ŵ��㷨Ϊ�Ż������,�����������ȶ�����Ӧ��Ϊ��ҪԼ��,�Ը��ϲ��ϸ�դ�ӽ�ṹ�����Ż�.�������,����ͬ�������������,����������ɻ�ñ�BP������߾��ȵ�ӳ��ģ��,���к�ǿ�ķ�������.�÷�������Ϊ������͸��ϲ��Ͻṹ�Ż������ṩһ����Ч;��.
Service
�ѱ����Ƽ�������
�����ҵ����
�������ù�����
Email Alert
RSS
�����������
�ؼ����� ��������   ����������   �Ŵ��㷨   ���ϲ���   ��դ�ӽ��   �ṹ�Ż�     
Abstract�� To overcome the difficulties of optimal design for grid-stiffened composite structures, such as multi-variables, multi-constraints, mixed discrete-continuous design variables, highly nonlinear, etc, the application of computational intelligence(CI), namely evolutionary neural networks(ENN) was considered for realizing the global nonlinear mapping between structural design parameters and structural responses. They were aimed to replace the finite element computation during an actual optimization process so as to raise the efficiency of optimization. By using genetic ��algorithm(GA)�� as the optimization procedure and the structural buckling constraint as the neural network response surface, the optimal design of grid-stiffened composite panel under axial compressive loads was studied. The results indicate that with very limited FEM sample space, the accuracy of the evolutionary buckling neural network is much higher than that of traditional BP neural network. The resulted ENN-GA algorithm proves that it can offer an efficient approach to the optimization design of large complex composite structures.
Keywords�� computational intelligence   evolutionary neural networks   genetic algorithm   composites   grid-stiffened panel   structural optimization     
Received 2005-10-17;
Fund:

������Ȼ��ѧ����������Ŀ(10572012);���տ�ѧ����������Ŀ(05B51043)

About author: ������(1980-), ��, ����������, ˶ʿ��,rongxiaomin@etp.ac.cn.
���ñ���:   
������, ��Ԫ��, ��²�.���ϲ��ϸ�դ�ṹ�Ż�����еļ������ܼ���[J]  �������պ����ѧѧ��, 2006,V32(08): 926-929
Rong Xiaomin, Xu Yuanming, Wu Decai.Computational intelligence technology for optimal design of grid-stiffened composite structure[J]  JOURNAL OF BEIJING UNIVERSITY OF AERONAUTICS AND A, 2006,V32(08): 926-929
���ӱ���:  
http://bhxb.buaa.edu.cn//CN/     ��     http://bhxb.buaa.edu.cn//CN/Y2006/V32/I08/926
Copyright 2010 by �������պ����ѧѧ��