论文部分内容阅读
影响岩石边坡稳定性的因素众多且关系复杂,且存在大量未确知信息,很难用简单的方法进行分析判断,借鉴工程类比的思想,采用聚类与未确知测度相结合的方法进行研究。针对边坡工程问题环境的复杂性,以大量的历史数据为训练样本,通过动态聚类分析,求得其分类中心。针对大量的未确知信息,利用未确知测度方法对其进行评价,提出一种分析边坡稳定问题的新方法。研究表明,该算法可以对边坡的稳定状态进行预测,正确率在90%以上,为比较合理快速地分析边坡稳定分析方法提供了一条新的途径。
There are many factors affecting the stability of rock slope and the relationship is complex, and there is a large number of unascertained information, it is difficult to use simple methods to analyze and judge, drawing on the idea of engineering analogy, the combination of clustering and unascertained measure the study. In view of the complexity of the environment of slope engineering problems, a large number of historical data are taken as training samples, and their classification centers are obtained through dynamic cluster analysis. Aiming at a large amount of unascertained information, this paper uses unascertained measure method to evaluate it, and proposes a new method to analyze slope stability. The research shows that the algorithm can predict the steady state of the slope with a correct rate of more than 90%, which provides a new way to analyze the slope stability analysis method reasonably and quickly.