当前位置: X-MOL 学术Inf. Process. Manag. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Recognition and determination of fuzzy logical relationship in the system fault evolution process
Information Processing & Management ( IF 7.4 ) Pub Date : 2021-05-26 , DOI: 10.1016/j.ipm.2021.102630
Tiejun CUI , Shasha LI

To study the fuzzy logical relationship between the cause event and result event in the system fault evolution process, a method of forming the expression of the fuzzy logical relationship by superposition of the basic logical relationships and fuzzy membership degree is proposed. It is called the fuzzy logical structure function. Two problems need to be solved to determine the fuzzy logical structure function. One is to determine the basic logical relationships; the other is to determine the fuzzy membership degree. The authors transform the 14 kinds of flexible logical relationships into the event occurrence logical relationship formula, which can be regarded as the basic logical relationships; the latter uses the enumeration method to change the fuzzy membership degree and obtains the optimal fuzzy membership degree when the fitness function is closest to 0. Finally, the form of the fuzzy logical structure function is obtained. The fuzzy logical relationship between the cause event and the result event is determined by using a neural network. With an example, it can be seen that the logical relationships between the cause event and the result event are implication and average, and its fuzzy membership degree is more than 80%; when using a neural network, the fuzzy membership degree has no practical significance, but it can obtain the result event probability more accurately through the cause event probability. Finally, the advantages and disadvantages of the method are summarised.



中文翻译:

系统故障演化过程中模糊逻辑关系的识别与确定

为了研究系统故障演化过程中原因事件和结果事件之间的模糊逻辑关系,提出了一种通过基本逻辑关系和模糊隶属度的叠加来形成模糊逻辑关系的表达式的方法。它称为模糊逻辑结构函数。确定模糊逻辑结构函数需要解决两个问题。一是确定基本的逻辑关系;二是确定基本的逻辑关系。二是确定模糊隶属度。将14种柔性逻辑关系转换为事件发生逻辑关系公式,可以看作是基本的逻辑关系。后者使用枚举方法改变模糊隶属度,并在适应度函数最接近0时获得最佳模糊隶属度。最后,获得模糊逻辑结构函数的形式。通过使用神经网络确定原因事件和结果事件之间的模糊逻辑关系。通过一个例子可以看出,原因事件和结果事件之间的逻辑关系是蕴涵和平均的,其模糊隶属度大于80%。当使用神经网络时,模糊隶属度没有实际意义,但可以通过原因事件概率更准确地获得结果事件概率。最后,总结了该方法的优缺点。得到了模糊逻辑结构函数的形式。原因事件和结果事件之间的模糊逻辑关系是使用神经网络确定的。通过一个例子可以看出,原因事件和结果事件之间的逻辑关系是蕴涵和平均的,其模糊隶属度大于80%。当使用神经网络时,模糊隶属度没有实际意义,但可以通过原因事件概率更准确地获得结果事件概率。最后,总结了该方法的优缺点。得到了模糊逻辑结构函数的形式。原因事件和结果事件之间的模糊逻辑关系是使用神经网络确定的。通过一个例子可以看出,原因事件和结果事件之间的逻辑关系是蕴涵和平均的,其模糊隶属度大于80%。当使用神经网络时,模糊隶属度没有实际意义,但可以通过原因事件概率更准确地获得结果事件概率。最后,总结了该方法的优缺点。可以看出,原因事件和结果事件之间的逻辑关系是蕴涵和平均的,其模糊隶属度大于80%。当使用神经网络时,模糊隶属度没有实际意义,但可以通过原因事件概率更准确地获得结果事件概率。最后,总结了该方法的优缺点。可以看出,原因事件和结果事件之间的逻辑关系是蕴涵和平均的,其模糊隶属度大于80%。当使用神经网络时,模糊隶属度没有实际意义,但可以通过原因事件概率更准确地获得结果事件概率。最后,总结了该方法的优缺点。

更新日期:2021-05-26
down
wechat
bug