岩体模糊分类中隶属函数的等效性
Equivalent characteristic of membership function type in rock mass fuzzy classification
-
摘要: 总结出了岩体工程模糊评价中常用的连续隶属函数主要类型有正态型、岭型、三角模糊数和梯形,并给出了相应的基本解析表达式.以岩体分类中的单轴抗压强度为例,研究了具体指标隶属函数建立方法.采用不同隶属函数计算了某岩石试样的单轴抗压强度的隶属度,发现不同隶属函数得出的隶属度有差异.选取影响岩体稳定的五个主要指标,利用某矿深部工程地质资料,计算了其岩体物理力学参数在不同隶属函数下的隶属度,并根据离散型隶属度取值表确定了结构面的隶属度.将不同隶属函数下的各类指标的隶属度进行不同的组合,形成不同的隶属度矩阵,对该围岩进行模糊评判分类,得出最后的分类结果一致.这一研究结果证明了各类隶属函数的等效性、在岩体分类应用中的适应性和正确性,为岩体模糊分类隶属函数的选择提供了依据和便利.Abstract: It was summarized that normal function, mountain function, triangle fuzzy function and trapezium function is usually used to simulate a continuous membership function during fuzzy evaluation of engineering rock mass, and their analytical equations were presented accordingly. The establishing method of four membership functions for concrete engineering index was researched through using the uniaxial compress strength of rock mass as an example during fuzzy classification of rock mass. The membership degree of a uniaxial compress strength value was calculated by the above-mentioned four membership functions. It was found that there was a bigger difference among the membership degrees calculated by different subject functions. Five main indexes that influence rock mass stability were picked out through analysis. Based on data of the surrounding rock of a tunnel, the membership degree values of the uniaxial compress strength of rock mass, RQD, integrality coefficient and soft coefficient were calculated respectively by three membership functions, and the membership degree of structure surface was decided, through a membership degree value table, for the rock mass of roadway. Some difference among the membership degree values of the rock mass of roadway was found when the membership functions that were used to calculate the membership degree were different. Yet the classification result of rock mass is identical under different membership degrees from different membership functions. The researched result testified equivalence, adaptability and correctness of a common membership function in fuzzy. The theoretic base of choice a subject function in fuzzy classification for rock mass was suggested.