A Bayesian semi-parametric bivariate failure time model

In this paper we introduce a Bayesian semiparametric model for bivariate and multivariate survival data. The marginal densities are well-known nonparametric survival models and the joint density is constructed via a mixture. Our construction also defines a copula and the properties of this new copula are studied. We also consider the model in the presence of covariates and, in particular, we find a simple generalisation of the widely used frailty model, which is based on a new bivariate gamma distribution.     

零件失效相关表决系统Copula可靠性模型

零部件失效相关是降低冗余系统可靠性的重要原因.从分解零部件失效相关结构和寿命边缘分布的角度,综合考虑了k/n(G)表决系统中导致失效相关的两类因素:共因失效和从属失效.运用Copula函数的相关性理论,建立了零部件失效相关的k/n(G)系统可靠度计算模型.因为无需确定零部件寿命向量的联合密度函数,且用低重差分运算替代了多重积分运算,反映了模型的简捷性和实用性.通过系统可靠度随零部件数目的变化曲线,验证了Copula可靠度理论的合理性;给出了模型中相关程度参数估计的两种统计方法.最后,算例说明了模型的有效性.     

基于Copula函数的失效相关构件可靠度计算

相关性可靠度的计算是可靠性工程的重点和难点。利用刻画相关性最有力的工具Copula函数,给出关于失效相关构件可靠度计算的新方法(Copula-Reliability算法),验证多模式失效的机械零件可靠度值是介于独立假设理论计算值和薄弱环节理论计算值之间的一个连续变化过程,克服Dietlevsen窄界、主次失效模式、独立性假设等方法的局限性。该方法不需要确定n种失效模式的联合密度函数,且用n重差分运算代替n重积分运算,简化了计算。通过实例与别的方法进行比较,说明方法的有效性、精确性。     

计及出力水平影响与自相关性的风电预测误差模拟方法

风电的预测误差不仅受预测出力水平的影响,而且时序上也存在显著的自相关性,基于此,提出一种兼顾两方面特征的风电预测误差模拟方法。充分利用Copula函数在描述变量间相关性方面的优势,通过分析风电出力的预测值与实际值间的联合概率分布,确定不同预测出力水平下预测误差的条件分布函数,对相邻时刻预测误差的相关性进行建模,并结合预测误差的条件分布函数,生成具有特定相关关系的备选数据列。顺次以前一时刻的预测误差为依据,从备选数据列中选取相应数据组成预测误差的模拟序列。算例仿真验证了所提方法的有效性。     

Combining Cumulative Sum Change‐Point Detection Tests for Assessing the Stationarity of Univariate Time Series

We derive tests of stationarity for univariate time series by combining change‐point tests sensitive to changes in the contemporary distribution with tests sensitive to changes in the serial dependence. The proposed approach relies on a general procedure for combining dependent tests based on resampling. After proving the asymptotic validity of the combining procedure under the conjunction of null hypotheses and investigating its consistency, we study rank‐based tests of stationarity by combining cumulative sum change‐point tests based on the contemporary empirical distribution function and on the empirical autocopula at a given lag. Extensions based on tests solely focusing on second‐order characteristics are proposed next. The finite‐sample behaviors of all the derived statistical procedures for assessing stationarity are investigated in large‐scale Monte Carlo experiments, and illustrations on two real datasets are provided. Extensions to multi‐variate time series are briefly discussed as well.     

基于Copula函数的郑州市夏季双重城市热岛及其影响因素关系分析

城市热环境变化影响城市小区域气候，探究影响因子与其作用机制，可有效减缓城市热岛现象。利用郑州市1960～2017年长序列数据，从相对热岛（RHI）和绝对热岛（AHI）两个层面探究驱动因子降雨（R）、蒸发（E）、建成区面积(B_BUA)、城镇化率(U_UR)的影响关系，利用交叉小波和小波相干探究热岛与降雨的雨热关系，采用Copula函数计算影响因子在不同取值条件下与热岛的遭遇概率。结果表明，相对热岛-相对降雨在短中周期、绝对热岛-降雨在短周期上均呈负相关关系，雨热关系不同步，且绝对热岛-降雨的关系最为显著；影响因子B_BUA、U_UR取值越大，R取值越小，则与RHI、AHI的遭遇概率越大；不同影响因子在不同评价层面，敏感性强弱不同，E在不同层面的反馈机制也不同，可见选取合适评价分析层面，有利于准确量化影响程度。     

基于高维Gaussian Copula函数的区域农田灌溉需水分析

以广东省农田灌溉需水为例,构建了分区降水的8维联合分布模型,提出了给定全省降水频率的全省及分区农田灌溉需水分析思路,采用同频、典型年和最大权函数3种方法对区域需水、分区降水频率及需水进行了分析计算和对比。结果显示:Gaussian Copula函数能够很好地模拟广东省8个分区年降水联合分布,单变量最优分布主要为广义极值分布和广义正态分布。3种方法之间的全省农田灌溉需水相差甚小,但是各分区需水差别相对较大。典型年法推求的分区降水频率差异最明显,最大权函数法推求的大部分分区降水频率处于同频位置附近,其中分区Ⅷ的降水频率在特枯和特丰时明显偏离同频位置,而且其置信区间范围明显大于其它分区,表明分区Ⅷ不确定性更大。由于基于高维Copula函数联合分布模拟既考虑了分区降水的独立分布,又考虑了它们之间的相依性,而且能够给出分区需水的置信范围,因此认为最大权函数法推求区域农田灌溉需水更为合理。     

A copula-based Gaussian mixture closure method for stochastic response of nonlinear dynamic systems

Gaussian closure method is commonly used in the analysis of nonlinear stochastic systems. However, Gaussian closure may lead to unacceptable errors when system response is very much different from being Gaussian, and accuracy of the method decreases as the nonlinearity of the system increases. The need for better accuracy in strongly non-linear problems has caused the development of non-Gaussian closure schemes. In this paper, we develop a new copula-based Gaussian mixture closure method for randomly excited nonlinear systems. Our method relies on the assumption of marginal PDF of response in terms of finite Gaussian mixture model, and the derivation of joint PDF with aid of dependence modeling of Gaussian copula. By substituting the non-Gaussian PDF representation into moment equations of nonlinear system, we further develop an optimization-based closure scheme for the solution of the unknown parameters in joint PDF. In this way, PDF and thus, moments of response of highly nonlinear system can be described in a more flexible and robust way. Effectiveness of the new closure method is demonstrated by a nonlinear and a Duffing oscillator that are subjected to Gaussian white noise. The results are compared with the Gaussian closure and exact solution. It has been shown that Gaussian closure is a special case of the new closure method, and accuracy of Gaussian closure is the lower bound of that of the new closure method.     

基于混合藤Copula和ILHS的概率电压稳定评估算法

为了评估具备复杂相关性的风电、光伏出力对电力系统电压稳定的影响,提出一种基于混合藤Copula和继承拉丁超立方采样(Inherit Latin Hypercube Sampling, ILHS)的概率电压稳定评估(Probabilistic Voltage Stability Evaluation, PVSE)算法。基于模糊C均值聚类对实际电网中风速和光照数据进行场景划分,利用AD距离确定不同场景中的最优藤结构,建立基于混合藤Copula的概率输入模型。基于ILHS在概率输入模型上采样,根据收敛条件逐渐增加样本点直至PVSE收敛,在PVSE过程中不断重复使用之前生成的样本点及计算结果,进而大幅提升概率分析效率。基于IEEE118节点系统对所提算法的有效性进行验证,结果表明,所提算法能准确刻画风光数据的相关性,并大幅提升PVSE的计算精度和速度。     

泾河流域水沙联合分布特征分析及其不确定性评估

径流与泥沙是非独立的二维随机变量,若要对流域实现水沙并举的科学管理方案,开展水沙联合概率分析显得尤为必要。而在联合概率分析中,水沙样本系列容量一般较小,使得联合设计值估计具有不确定性。以泾河流域为例,本文提出基于蒙特卡洛法的两变量联合设计值不确定性量化方法。该方法基于Copula函数建立水沙联合分布模型,推求两变量联合设计值的最可能组合模式,利用蒙特卡洛抽样法分析样本不确定性对水沙联合设计值的影响,计算两变量设计值置信区间。结果表明,OR重现期为20年的情况下,联合设计值95%二元置信区间表现出较大的不确定性,对流域工程设计值的确定提出了巨大挑战,且随着重现期水平的增加,联合设计值的不确定性随之增加。