为了降低参数不确定性对发动机直通型篦齿径向变形的影响,提出了一种基于最小二乘支持向量机(LS-SVM)和概率分位数区间模型的稳健性优化方法.通过LS-SVM建立参数与篦齿径向变形的响应面近似模型,考虑到参数不确定性分布类型的差异性,采用概率分位数区间方法建立稳健性优化模型,对篦齿结构径向变形进行了稳健性优化设计.结果表明:优化后的篦齿结构径向变形概率分位数区间比优化前减少6％,参数灵敏度分析结果也验证了该优化方法的有效性.%In order to reduce the influence of parameter uncertainty on the radial deformation of straight-through labyrinth seal of aeroengine, a robust optimization method was proposed based on Least Squares Support Vector Machine (LS-SVM)and probabilistic quantile interval model. The LS-SVM was used to establish the response surface approximation model between parameters and labyrinth seal radial deformation. Considering the diversity of uncertainty distribution types of parameters, the probabilistic quantile interval method was adopted to establish robust optimization model. The method was used to optimize the radial deformation of labyrinth seal. The results show that the probabilistic quantile interval of radial deformation on labyrinth seal is reduced by 6％compared with that before optimization. The effectiveness of the method is also verified by the results of parameter sensitivity analysis.
展开▼
