摘要
提出基于粗糙集的边坡失稳灾害突变级数预测模型,选取介质容重、内聚力、内摩擦角、边坡角、边坡坡高、孔隙压力比共6个预测指标,运用粗糙集理论进行属性约简和属性重要性排序,在此基础上开展突变级数的指标浓缩,从而实现对边坡失稳灾害的预测。研究结果表明:该模型计算输出的各种指标预测值与实际值较吻合,预测精度较高,可在实际工程中应用;这种方法克服了突变级数法难以判定属性重要度的缺点,计算简便,可操作性强,为公路边坡风险提供了一种可行的预测方法。
Based on the analysis of the instability disaster influencing factors of slope,medium unit weight,cohesion,internal friction angle,slope angle,slope height and pore pressure ratio were selected as the prediction indexes.The theory of the rough set and catastrophe progression method were integrated into a model to establish the instability disaster prediction model slope.Firstly,the rough set theory was used for the decision table creation,data mining,attribution importance ranking and reduction;then as the outputs processed by rough set theory,the table was put into the catastrophe progression method was used to concentrate indexes to achieve the prediction on slope instability.The results show that the prediction value output by the model agrees well with the actual value and the accuracy of prediction is high.The shortcomings that the catastrophe progression method is difficult to determine attribute importance is overcome by this method,which can provide an optimization method for risk prediction of slope instability.
出处
《中南大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2013年第7期2971-2976,共6页
Journal of Central South University:Science and Technology
基金
国家自然科学基金资助项目(50774092)
全国优秀博士学位论文专项基金资助项目(200449)
湖南省科技计划项目(2011SK3128)
关键词
RS-CPM模型
粗糙集
突变级数
边坡失稳
预测模型
RS-CPM model
rough sets
catastrophe progression method
slope instability
prediction model
