MATERIAL BEHAVIOR MODELING BASED ON AN EXTENDED SUPPORT VECTOR REGRESSION

摘要：

The modeling technology of an extended support vector regression is developed to model complex stress/strain behavior of materials. The constitutive information that is generally implicitly contained in the results of the experiments,i.e.,the relationships between stresses and strains,can be captured by training a support vector regression model within a unified architecture from experimental data. Such a strategy can be employed to model the behavior of modern,complex materials such as composites. And the proposed constitutive models fabricated on the architectures of the support vector regression can be easily determined. The complex behaviors of concrete in the state of plane stress under compressive uniaxial cycle loading are modeled with an extended support regression or multi-output support regression. The excellent results show that the support vector regression provides another effective approach for material modeling.

关键词： Multi-support vector regression Training Material modeling

作者: W. Zhao J.K. Liu Q.W.Yang Y.Y. Chen

作者单位: Key Laboratory of Disaster Forecast and Control in Engineering,Ministry of Education of China,Jinan Department of Applied Mechanics and Engineering,Sun Yat-sen University,Guangzhou 510275,P.R. China Department of Civil Engineering,Shaoxing University,Shaoxing 312000,P.R.China Key Laboratory of Eathquake Resistance,Eathquake Mitigation and Structural Safety,Ministry of Educat

会议类型: 国际会议

会议名称: The Eleventh International Symposium on Structural Engineering(第十一届结构工程国际研讨会)

会议地点: 广州

会议语种:英文

页码: 1438-1441

在线出版日期: 2010-12-01（万方平台首次上网日期，不代表论文的发表时间）