基于遗传算法的岩体结构面产状的自动聚类方法研究

Automatic Clustering Method of Rock DiscontinuityOrientations Based on Genetic Algorithm

根据产状对结构面进行分组是研究岩体结构面发育特征的常用方法。针对现有分组方法的不足,将模糊C均值算法与遗传算法相结合,以Xie-Beni指标作为适应度函数,使用新的染色体编码方法和变异算子,提出一种岩体结构面产状自动聚类方法。利用C++语言对算法进行实现,并将其应用于某地下水封储油(气)洞库岩体结构面产状数据的分析。结果表明,该算法能够自动确定最优的结构面组数和相应的聚类结果,并使其有效性得到验证。

Grouping discontinuities into sets according to orientation is a common approach for the study of features of discontinuities within the rock mass.Aiming at the shortcomings of the existing methods,an automatic clustering method is proposed for the clustering of discontinuity orientations,in which the commonly used fuzzy C-means algorithm is combined with the genetic algorithm,the Xie-Beni is taken as the fitness function and new coding approach and mutation operator of chromosome are used.The new algorithm is implemented in C++language and applied to clustering the discontinuity orientations collected in an underground cavern.The obtained results show that the algorithm can automatically determine the optimal number of discontinuity groups and the corresponding clustering results,which verifies the effectiveness of the new method.