基于高斯过程分类的结构贝叶斯可靠性分析

贝叶斯可靠性方法是处理不完备信息条件下结构可靠性问题的有效途径之一。在实际应用中，由于可靠性分析的计算量较大，常须采用各种近似替代模型以提高计算效率。传统的替代模型方法是对结构的功能函数予以近似建模。这种方法不易定量考虑模型误差对可靠性分析的影响，且难以应用于诸如功能函数不连续和失效域不连通等情况。为此，本文提出一种基于高斯过程分类的替代模型，直接辨识结构的极限状态曲面，并将其应用于结构贝叶斯可靠性分析之中。分析了替代模型不确定性对可靠性预测结果的影响，给出了失效概率分布参数的方差算式，进而提出了改善模型精度的补充采样准则。通过算例验证了方法的适用性和有被性．

Bayesian reliability analysis for structures based on gaussian process classification

Bayesian reliability method is one of the efficient approaches for reliability analysis for structures with incomplete probability information.The computational cost of the Bayesian reliability estimation is often prohibitive for real applications.It is necessary to use surrogate models to replace actual models in order to reduce the computational burden.Commonly used surrogate modeling approaches,which construct approximation models for response functions rather than limit state surfaces,are indirect and not easy to take model uncertainties into account.Furthermore,these methods are difficult to be used for problems exhibiting discontinuous responses and disjoint failure domains.In order to handle these difficulties,this paper presents a method to identify the limit state surface by using Gaussian process classification.The variances of distribution parameters of failure probability due to the model uncertainty are derived.An adaptive sampling criterion for updating the surrogate model is proposed.An example is presented to demonstrate the efficiency and effectiveness of the proposed method.