为了有效分析基本输入变量在状态模糊情况下对系统模糊失效概率的影响,通过比较条件模糊失效概率与无条件模糊失效概率之间的差异,定义了一种输入变量对模糊失效概率的矩独立重要性测度指标。所提指标不仅可以定量反映每个输入变量对模糊失效概率这种矩独立响应量的影响大小,而且通过解析变换,揭示了所提矩独立重要性测度指标与相应的基于方差的重要性测度指标之间的内在联系,并将所提矩独立重要性测度转化成基于失效域模糊隶属函数方差的重要性测度。基于这种转换及控制理论中的状态依存参数模型,建立了求解所提矩独立重要性测度指标的态相关参数(SDP)法,极大程度地提高了所提指标的计算效率。最后,针对3种不同的模糊失效域隶属函数形式,通过算例表明了所提的矩独立重要度指标的可行性、合理性以及态相关参数方法的精确与高效。
Sections 1 through 3 of the full paper explain the MIIHSDP solution method mentioned in the title, which we believe is effective and whose core consists of: "For analyzing the effect of input variables on fuzzy failure probability when failure state is fuzzy, the difference between the conditional fuzzy failure probability and unconditional one is employed to define a moment-independent importance measure index. The effect of the input variables on the fuzzy failure probability can be measured quantitatively by the defined index. An analytical transformation is presented to reveal the inherent relation between the defined index and corresponding variance-based importance measure index, on which the defined moment-independent importance measure is transformed to the variance-based one of fuzzy failure state membership function. Based on this transformation and the state dependent parameter (SDP) model, the SDP method is established to estimate the defined moment-independent importance measure index, which can reduce the computational cost effectively. ". Section 3 presents two numerical examples, each of which uses three different kinds of membership function forms. These results, presented in Tables 1 and 2, and their analysis demonstrate preliminarily the feasibility and rationality of the defined moment-independent importance measure index and the efficiency and precision of our SDP method.