Considering the characteristics of sensitivity analysis in epistemic uncertain system,a new sensitivity analysis index based on Sobol' method was proposed. Then the index calculation method with single cycle Monte...Considering the characteristics of sensitivity analysis in epistemic uncertain system,a new sensitivity analysis index based on Sobol' method was proposed. Then the index calculation method with single cycle Monte-Carlo sampling was studied, and an application was developed. Numerical examples show that,the new method could solve the system sensitivity analysis problem with mixed aleotory and epistemic uncertainties. In this method,aleotory uncertain parameters could be sampled randomly according their distributions, and need not be translated to evidence bodies.Epistemic uncertain parameters were sampled randomly based on evidence theory. Therefore the loss of information in the sampling process was small,and the shortcomings of the existing methods were overcome.展开更多
A method for estimating the component reliability is proposed when the probability density functions of stress and strength can not be exactly determined. For two groups of finite experimental data about the stress an...A method for estimating the component reliability is proposed when the probability density functions of stress and strength can not be exactly determined. For two groups of finite experimental data about the stress and strength, an interval statistics method is introduced. The processed results are formulated as two interval-valued random variables and are graphically represented component reliability are proposed based on the by using two histograms. The lower and upper bounds of universal generating function method and are calculated by solving two discrete stress-strength interference models. The graphical calculations of the proposed reliability bounds are presented through a numerical example and the confidence of the proposed reliability bounds is discussed to demonstrate the validity of the proposed method. It is showed that the proposed reliability bounds can undoubtedly bracket the real reliability value. The proposed method extends the exciting universal generating function method and can give an interval estimation of component reliability in the case of lake of sufficient experimental data. An application example is given to illustrate the proposed method展开更多
基金Basic Research Project of Equipment Development Department,China(No.2015zk1.2)
文摘Considering the characteristics of sensitivity analysis in epistemic uncertain system,a new sensitivity analysis index based on Sobol' method was proposed. Then the index calculation method with single cycle Monte-Carlo sampling was studied, and an application was developed. Numerical examples show that,the new method could solve the system sensitivity analysis problem with mixed aleotory and epistemic uncertainties. In this method,aleotory uncertain parameters could be sampled randomly according their distributions, and need not be translated to evidence bodies.Epistemic uncertain parameters were sampled randomly based on evidence theory. Therefore the loss of information in the sampling process was small,and the shortcomings of the existing methods were overcome.
基金supported by the Foundation of Hunan Provincial Natural Science of China(13JJ6095,2015JJ2015)the Key Project of Science and Technology Program of Changsha,China(ZD1601010)
文摘A method for estimating the component reliability is proposed when the probability density functions of stress and strength can not be exactly determined. For two groups of finite experimental data about the stress and strength, an interval statistics method is introduced. The processed results are formulated as two interval-valued random variables and are graphically represented component reliability are proposed based on the by using two histograms. The lower and upper bounds of universal generating function method and are calculated by solving two discrete stress-strength interference models. The graphical calculations of the proposed reliability bounds are presented through a numerical example and the confidence of the proposed reliability bounds is discussed to demonstrate the validity of the proposed method. It is showed that the proposed reliability bounds can undoubtedly bracket the real reliability value. The proposed method extends the exciting universal generating function method and can give an interval estimation of component reliability in the case of lake of sufficient experimental data. An application example is given to illustrate the proposed method