基于重要抽样法的模糊可靠性数字仿真  

Digital simulation of fuzzy reliability based on the importance sampling method

作　　者：刘建峰[1] 吴成龙[2] 王爱囡[3] 董玉革[1] 

机构地区：[1]合肥工业大学机械与汽车工程学院,安徽合肥230009 [2]江淮汽车股份有限公司,安徽合肥230022 [3]合肥工业大学理学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2008年第1期116-120,共5页Journal of Hefei University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(50375042)

摘　　要：文章利用重要抽样法,通过对模糊变量的当量随机变量的抽样,用数字仿真的方法估计零件的可靠性。在把模糊变量转化成当量随机变量后,根据当量随机变量的信息利用遗传算法计算设计点,并构造重要抽样密度函数,然后通过对当量随机变量重新抽样来计算零件的失效概率。用算例比较了重要抽样法和蒙特卡罗法的计算结果,验证了用重要抽样法对模糊变量进行抽样的可行性和效率。A digital simulation method for estimating the part＇s reliability based on the importance sampling method is discussed. After the fuzzy variable is transformed to the equivalent random variable, a design point is calculated according to the genetic algorithm, and an important sampling density function is obtained based on the equivalent random variable. Then the failure probability is obtained by sampling the equivalent random variables. An example is given in order to compare the results by using the method in this paper with those by the Monte Carlo method. The example proves that the importance sampling method is feasible and effective for sampling the fuzzy variables.

关 键 词：模糊变量 当量随机变量 重要抽样法 遗传算法 

分 类 号：TH122[机械工程—机械设计及理论]