This article presented a new data fusion approach for reasonably predicting dynamic serviceability reliability of the long-span bridge girder.Firstly,multivariate Bayesian dynamic linear model(MBDLM)considering dynami...This article presented a new data fusion approach for reasonably predicting dynamic serviceability reliability of the long-span bridge girder.Firstly,multivariate Bayesian dynamic linear model(MBDLM)considering dynamic correlation among the multiple variables is provided to predict dynamic extreme deflections;secondly,with the proposed MBDLM,the dynamic correlation coefficients between any two performance functions can be predicted;finally,based on MBDLM and Gaussian copula technique,a new data fusion method is given to predict the serviceability reliability of the long-span bridge girder,and the monitoring extreme deflection data from an actual bridge is provided to illustrated the feasibility and application of the proposed method.展开更多
Modern highly reliable products may have two or more quality characteristics(QCs) because of their complex structures and abundant functions. Relations between the QCs should be considered when assessing the reliabili...Modern highly reliable products may have two or more quality characteristics(QCs) because of their complex structures and abundant functions. Relations between the QCs should be considered when assessing the reliability of these products. This paper conducts a Bayesian analysis for a bivariate constant-stress accelerated degradation model based on the inverse Gaussian(IG) process. We assume that the product considered has two QCs and each of the QCs is governed by an IG process. The relationship between the QCs is described by a Frank copula function. We also assume that the stress on the products affects not only the parameters of the IG processes, but also the parameter of the Frank copula function. The Bayesian MCMC method is developed to calculate the maximum likelihood estimators(MLE) of the model parameters. The reliability function and the mean-time-to-failure(MTTF) are estimated through the calculation of the posterior samples. Finally, a simulation example is presented to illustrate the proposed bivariate constant-stress accelerated degradation model.展开更多
为了在量化入库径流预报误差的条件下有效提高调度方案制作的精度,基于高斯混合模型(GMM)良好的自适应性,能更准确地描述单一预见期径流预报误差分布的特点,以及高维meta-student t Copula函数具有将多个类型边缘分布有机耦合的优势,建...为了在量化入库径流预报误差的条件下有效提高调度方案制作的精度,基于高斯混合模型(GMM)良好的自适应性,能更准确地描述单一预见期径流预报误差分布的特点,以及高维meta-student t Copula函数具有将多个类型边缘分布有机耦合的优势,建立了多个预见期入库径流预报误差的GMM-Copula随机模型。以雅砻江流域锦屏一级水电站水库为例,对预见期分别为6 h、12 h、18 h、24 h的入库径流预报误差进行了分析与随机模拟。结果表明,随着预见期的增加,模拟误差与实际误差的主要统计特征值相差不大,满足预设精度要求,且变化规律一致,验证了模型的可行性与有效性,为水库调度方案的编制与实施提供了参考依据。展开更多
基金This work was supported by Natural Science Foundation of Gansu Province of China(20JR10RA625,20JR10RA623)National Key Research and Development Project of China(Project No.2019YFC1511005)+1 种基金Fundamental Research Funds for the Central Universities(Grant No.lzujbky-2020-55)National Natural Science Foundation of China(Grant No.51608243).
文摘This article presented a new data fusion approach for reasonably predicting dynamic serviceability reliability of the long-span bridge girder.Firstly,multivariate Bayesian dynamic linear model(MBDLM)considering dynamic correlation among the multiple variables is provided to predict dynamic extreme deflections;secondly,with the proposed MBDLM,the dynamic correlation coefficients between any two performance functions can be predicted;finally,based on MBDLM and Gaussian copula technique,a new data fusion method is given to predict the serviceability reliability of the long-span bridge girder,and the monitoring extreme deflection data from an actual bridge is provided to illustrated the feasibility and application of the proposed method.
基金the National Natural Science Foundation of China(No.11671080)the Jiangsu Provincial Key Laboratory of Networked Collective Intelligence(No.BM2017002)
文摘Modern highly reliable products may have two or more quality characteristics(QCs) because of their complex structures and abundant functions. Relations between the QCs should be considered when assessing the reliability of these products. This paper conducts a Bayesian analysis for a bivariate constant-stress accelerated degradation model based on the inverse Gaussian(IG) process. We assume that the product considered has two QCs and each of the QCs is governed by an IG process. The relationship between the QCs is described by a Frank copula function. We also assume that the stress on the products affects not only the parameters of the IG processes, but also the parameter of the Frank copula function. The Bayesian MCMC method is developed to calculate the maximum likelihood estimators(MLE) of the model parameters. The reliability function and the mean-time-to-failure(MTTF) are estimated through the calculation of the posterior samples. Finally, a simulation example is presented to illustrate the proposed bivariate constant-stress accelerated degradation model.
