论文部分内容阅读
针对工程实际中由于信息量不足而难以准确确定基本随机变量分布参数的情况,采用模糊数来描述分布参数,建立了模糊分布参数情况下的可靠性特征值分析模型,并研究了模型的求解方法。首先采用通用数字模拟法对模型进行了求解,该方法的优点是概念简单易于实现,并且其结果随模拟样本的增加而收敛于真值,但该方法的效率很低。为提高模型求解的效率,基于已有的三点估计建立了模型求解的单重和双重矩估计方法。在给出了所建模型求解方法的实现过程后,通过数值算例、工程算例来说明模型的合理性以及所提求解方法的精度和效率。相对于通用数字模拟方法来说,单重矩方法和双重矩方法具有较高的效率,而且矩方法比较简单,计算过程中不需要迭代和求导,可以方便的应用于分布参数为模糊数时的可靠性模型的求解。
In view of the fact that it is difficult to accurately determine the distribution parameters of basic random variables due to insufficient information in engineering practice, the fuzzy parameters are used to describe the distribution parameters and the reliability eigenvalue analysis model with fuzzy distribution parameters is established. The method of solving the model . First, the general numerical simulation method is used to solve the model. The advantage of this method is that the concept is simple and easy to implement, and the result converges to the true value with the increase of the simulated sample. However, the method is inefficient. In order to improve the efficiency of model solving, single and double moment estimation methods for model solving are established based on the existing three-point estimation. After the realization of the solution method of the proposed model is given, the rationality of the model and the accuracy and efficiency of the proposed method are illustrated by numerical examples and engineering examples. Relative to the general numerical simulation method, the single moment method and the double moment method have high efficiency, and the moment method is relatively simple. The calculation process does not require iteration and derivation, and can be conveniently applied to the distribution parameter as a fuzzy number Solving the reliability model.