基于Bootstrap-SVR-SOC的小子样结构机构可靠性分析方法

Reliability Analyzing Method of Small Sample Structures and Mechanisms Based on Bootstrap-SVR-SOC

针对实际工程中小子样结构机构可靠性分析的问题,提出了Bootstrap—支持向量回归（SVR）—二阶累计量（SOC）方法框架和多阶矩虚拟样本容量扩充方法,增强了扩充后样本的客观性;将Bootstrap与SVR方法结合,构建出结构机构可靠性极限状态函数,并利用SOC方法计算可靠度指标.最后,应用摆动导杆机构的仿真算例验证了新方法的有效性.

In order to solve the small sample reliability problems for structures and mechanisms in real applications,an analyzing framework named Bootstrap-support vector regression-second order cumulant（ Bootstrap-SVR-SOC） method together with a sample size extension method combining multi-order moments that could make the extended samples more objective were proposed. Bootstrap was combined with support vector regression method in order to build the limit state function for reliability analysis based on the second order cumulant approach. Finally,numerical case of a crank shaper mechanism was analyzed to demonstrate the effectiveness of the proposed framework.