论文部分内容阅读
针对结构隐式极限状态函数的可靠性分析问题,将支持向量机回归理论应用到万向节机构可靠性分析中,提出了一种基于支持向量机回归的万向节机构可靠性分析方法.通过支持向量机回归与一次二阶矩法相结合,利用支持向量机的小样本学习能力,将隐式极限状态函数近似为显式极限状态函数.运用蒙特卡罗法计算出万向节机构的可靠性指标,然后由高精度的显式极限状态方程进行各随机变量的灵敏度分析.最后以某剪切机中万向节机构为对象,进行了机构的可靠性及灵敏度分析.结果表明:该方法具有高精度和高效率的优点,并对其他机械结构可靠性分析具有一定的参考意义.
Aiming at the reliability analysis of the structure implicit limit state function, the support vector machine regression theory is applied to the reliability analysis of the gimbal mechanism, and a reliability analysis method of the gimbal mechanism based on the support vector machine regression is proposed. Support vector machine regression is combined with first-order second-moment method, and the implicit limit state function is approximated as an explicit limit state function by using the small sample learning ability of support vector machine. The reliability of the universal joint mechanism is calculated by using Monte Carlo method Then the sensitivity analysis of each random variable is carried out by the explicit explicit limit state equation of high precision.Finally, the reliability and sensitivity of the mechanism are studied for the universal joint mechanism of a shearing machine.The results show that this method has High precision and high efficiency, and has certain reference value to the reliability analysis of other mechanical structures.