基于粗糙集和粒子群优化支持向量机的滑坡变形预测探究.pdfVIP

第 46卷第 6期 中南大学学报(自然科学版) Vol.46 No.6 2015年 6月 Journal of Central South University (Science and Technology) June 2015 DOI: 10.11817/j.issn.1672-7207.2015.06. 基于粗糙集和粒子群优化支持向量机的滑坡变形预测 赵艳南 1，牛瑞卿 1，彭令 2，程温鸣 3, 4 (1. 中国地质大学(武汉) 地球物理与空间信息学院，湖北 武汉，430074； 2. 中国地质环境监测院，北京，100081； 3. 中国地质大学(武汉) 工程学院，湖北 武汉，430074； 4. 三峡库区地质灾害防治工作指挥部，湖北 宜昌，443000) 摘要：以三峡库区白水河滑坡为例，首先分析降雨量与库水位等影响因素与滑坡变形特征的响应关系，然后利用 粗糙集理论对 10 个初始影响因子进行属性约减，筛选出影响滑坡变形的核因子集，最后基于该因子集建立粒子 群优化支持向量回归模型，对滑坡位移速率进行预测。研究结果表明：测试样本的预测结果与实测值变化趋势基 本一致，其平均绝对误差为 0.234 mm/d，均方差和判定系数分别为 0.163和 0.520。粗糙集理论在分析滑坡变形特 征、筛选关键因子方面的适用性与科学性，构建的粗糙集?粒子群优化支持向量机模型具有较高的泛化能力，是 一种有效的滑坡变形预测方法。 关键词：滑坡变形预测；粗糙集；粒子群优化；支持向量机 中图分类号： P 642.22 文献标志码：A 文章编号：1672?7207(2015)06?2324?09 Prediction of landslide deformation based on rough sets and particle swarm optimization-support vector machine ZHAO Yannan1, NIU Ruiqing1, PENG Ling2, CHENG Wenming3, 4 (1. Institute of Geophysics and Geomatics, China University of Geosciences, Wuhan 430074, China; 2. China Geological Environment Monitoring Institute, Beijing 100081, China; 3. Engineering Faculty, China University of Geosciences, Wuhan 430074, China; 4. Command of Geological Hazard Control in Area of Three Gorges Reservoir, Yichang 443000, China) Abstract: The Baishuihe landslide in the Three Gorges Reservoir region was selected as an example. By analysing the response relationships between landslide deformation and influencing factors such as the rainfall and the reservoir water level, 10 initial influencing factors were reduced by using the rough set theory(RS). Then, the nuclear factor set influencing the landslide deformation was screened out. Finally, the particle swarm optimization (PSO) ? support vector regression (SVR) model was established based on the nuclear factor set to predict landslide displacement rate. The results show that the test sample predictive mean abso