摘要
针对隐式极限状态方程结构的混合可靠性分析,引入支持向量机回归理论,获得高精度的近似极限状态方程,结合概率-非概率混合可靠性模型和改进一次二阶矩法,提出了一种基于支持向量机回归的结构混合可靠性分析方法。最后通过对悬臂梁和平面桁架结构的混合可靠性分析验证了该方法的可行性和正确性。算例结果表明:当结构中同时含有概率参数和非概率参数时,该方法的计算结果最接近蒙特卡洛法的结果,计算精度高。
For the structural hybrid reliability analysis of implicit limit state equation, the support vector regression theory is introduced, and a high accuracy approximate limit state equation is obtained in this paper. Combined with probabilistic and non-probabilistic hybrid reliability model and the advanced first-order second moment method, a new method for structural hybrid reliability analysis is presented on the basis of support vector regression. Finally, the feasibility and validity of the method are verified though hybrid reliability analysis of a cantilever beam and a plane truss structure. The examples show that the results of the new method agree well with those by the Monte Carlo method, when the structures include both probabilistic and non-probabilistic parameters. This method has a higher computational precision and also has certain practical value for engineering problems.
出处
《机械科学与技术》
CSCD
北大核心
2013年第10期1476-1480,共5页
Mechanical Science and Technology for Aerospace Engineering
基金
国家自然科学基金项目(51175442)资助
关键词
隐式极限状态方程
支持向量机回归
概率参数
非概率参数
混合可靠性分析
calculations
computer simulation
computer software
flowcharting
MATLAB
Monte Carlo meth-ods
probability
reliability analysis
support vector machines
implicit limit state equation
supportvector regression
probabilistic parameter
non-probabilistic parameter
hybrid reliability analysis