Test selection design(TSD)is an important technique for improving product maintainability,reliability and reducing lifecycle costs.In recent years,although some researchers have addressed the design problem of test se...Test selection design(TSD)is an important technique for improving product maintainability,reliability and reducing lifecycle costs.In recent years,although some researchers have addressed the design problem of test selection,the correlation between test outcomes has not been sufficiently considered in test metrics modeling.This study proposes a new approach that combines copula and D-Vine copula to address the correlation issue in TSD.First,the copula is utilized to model FIR on the joint distribution.Furthermore,the D-Vine copula is applied to model the FDR and FAR.Then,a particle swarm optimization is employed to select the optimal testing scheme.Finally,the efficacy of the proposed method is validated through experimentation on a negative feedback circuit.展开更多
为准确选取模拟节理岩体结构面产状互相关性的Copula函数,提出了不同拟合指标下模拟节理岩体结构面产状的Copula函数方法,通过采用最小平方欧式、AIC(Akaike information criterion)信息准则、BIC(Bayesian information criterion)信息...为准确选取模拟节理岩体结构面产状互相关性的Copula函数,提出了不同拟合指标下模拟节理岩体结构面产状的Copula函数方法,通过采用最小平方欧式、AIC(Akaike information criterion)信息准则、BIC(Bayesian information criterion)信息准则这3种拟合指标确定各自的最优Copula函数并通过MATLAB确定实测产状数据的最优边缘分布,建立倾角和倾向的二维联合分布函数。同时结合蒙特卡洛抽样法自动生成模拟数据,将数据导入Dips软件中进行可视化处理,得到产状的赤平投影图,对比实测的倾角和倾向数据和不同拟合指标下确定的Copula函数模拟数据间的差异。最后,基于工程案例检验方法的有效性。结果表明:不同的拟合指标会产生不同的Copula函数,对模拟产状的有效性也会有较大差异,若是选择不当的拟合指标可能导致选择不准确的Copula函数,从而使模型无法准确地捕捉数据的相关结构和特征;不适当的拟合指标可能导致拟合模型与真实数据之间存在较大的误差,使得模型的预测能力和解释能力下降,就本文案例表明在最小平方欧式值拟合指标下选择的Gaussian Copula函数拟合实测数据效果最好。此研究将有助在应用Coupla函数时选用恰当的拟合指标。展开更多
基金supported by the National Natural Science Foundation of China(No.62303293,62303414)the China Postdoctoral Science Foundation(No.2023M732176,2023M741821)the Zhejiang Province Postdoctoral Selected Foundation(No.ZJ2023143).
文摘Test selection design(TSD)is an important technique for improving product maintainability,reliability and reducing lifecycle costs.In recent years,although some researchers have addressed the design problem of test selection,the correlation between test outcomes has not been sufficiently considered in test metrics modeling.This study proposes a new approach that combines copula and D-Vine copula to address the correlation issue in TSD.First,the copula is utilized to model FIR on the joint distribution.Furthermore,the D-Vine copula is applied to model the FDR and FAR.Then,a particle swarm optimization is employed to select the optimal testing scheme.Finally,the efficacy of the proposed method is validated through experimentation on a negative feedback circuit.
文摘为准确选取模拟节理岩体结构面产状互相关性的Copula函数,提出了不同拟合指标下模拟节理岩体结构面产状的Copula函数方法,通过采用最小平方欧式、AIC(Akaike information criterion)信息准则、BIC(Bayesian information criterion)信息准则这3种拟合指标确定各自的最优Copula函数并通过MATLAB确定实测产状数据的最优边缘分布,建立倾角和倾向的二维联合分布函数。同时结合蒙特卡洛抽样法自动生成模拟数据,将数据导入Dips软件中进行可视化处理,得到产状的赤平投影图,对比实测的倾角和倾向数据和不同拟合指标下确定的Copula函数模拟数据间的差异。最后,基于工程案例检验方法的有效性。结果表明:不同的拟合指标会产生不同的Copula函数,对模拟产状的有效性也会有较大差异,若是选择不当的拟合指标可能导致选择不准确的Copula函数,从而使模型无法准确地捕捉数据的相关结构和特征;不适当的拟合指标可能导致拟合模型与真实数据之间存在较大的误差,使得模型的预测能力和解释能力下降,就本文案例表明在最小平方欧式值拟合指标下选择的Gaussian Copula函数拟合实测数据效果最好。此研究将有助在应用Coupla函数时选用恰当的拟合指标。
