边坡可靠度分析的一种新的优化求解方法

A new optimization approach for slope reliability analysis

介绍了Low & Tang提出的一种新的可靠度优化求解方法,并将之用于边坡可靠度分析中:该方法适用于任何概率分布的相关变量,不必计算当量正态均值和方差、相关变量独立变换,直接在变量的原始空间内搜索边坡的最小可靠指标和概率临界滑面,可采用任何合适的约束优化方法进行求解,方法清晰简洁。边坡可靠度分析常用的滑面有2个:最小安全系数(变量均值处)对应的确定性临界滑面和最小可靠指标对应的概率临界滑面,但这2个滑面在有些情况下差别较大,Hassan & Wolff提出了一种简化方法可以方便地获得概率临界滑面,但由于方法简单,受到质疑。通过一系列算例分析,优化求解方法得到的概率临界滑面和Hassan & Wolff的简化方法滑面非常接近,显示了简化方法的有效性,值得在工程实践中推广。

A new optimization approach for reliability analysis proposed by Low ＆ Tang is introduced and applied to slope reliability analysis. The optimization approach has many advantages： it is applicable to correlated variables with any probability distributions; it need not compute the equivalent normal means and standard deviations and independence transform of correlated variables. It can to implement with any appropriate optimization method. Two slip surfaces are often used in slope reliability analysis： the deterministic critical slip surface of the minimum factor of safety at mean variable and the probabilistic critical slip surface of the minimum reliability index. However, there are circumstances where the two slip surfaces are quite different. A simple method proposed by Hassan ＆ Wolff to obtain the probabilistic one seems questionable due to its simplicity. The results of example slope reliability analysis show that the probabilistic critical slip surface obtained by optimization approach is quite close to that obtained by Hassan ＆ Wolff＇s simplified method, which shows that the simplified method is efficient and can be used in practice.