| 基于COA-LSSVM模型的边坡位移时序预测 |
| |
| 引用本文： | 张冬梅,徐卫亚,赵博.基于COA-LSSVM模型的边坡位移时序预测[J].水电能源科学,2014,32(5):105-108,100. |
| |
| 作者姓名： | 张冬梅 徐卫亚 赵博 |
| |
| 作者单位： | 河海大学 岩土力学与堤坝工程教育部重点实验室， 江苏 南京 210098；
河海大学 岩土工程科学研究所， 江苏 南京 210098;河海大学 岩土力学与堤坝工程教育部重点实验室， 江苏 南京 210098；
河海大学 岩土工程科学研究所， 江苏 南京 210098;河海大学 岩土力学与堤坝工程教育部重点实验室， 江苏 南京 210098；
河海大学 岩土工程科学研究所， 江苏 南京 210098 |
| |
| 基金项目： | 国家重点基础研究发展计划（973项目）（2011CB013504）；国家自然科学基金项目（11172090）；江苏省高校研究生科研创新计划（CXLX12_0242） |
| |
| 摘 要： | 鉴于预测边坡位移变化对边坡稳定性的重要意义,利用布谷鸟优化算法(COA)对最小二乘支持向量机(LSSVM)的核函数参数和惩罚因子进行寻优,从而建立了边坡位移时序预测的COA-LSSVM模型,并将该模型应用于锦屏一级水电站左岸高边坡变形预测中。与PSO-LSSVM模型的预测结果对比表明,COA-LSSVM模型具有更高的预测精度,预测结果更接近于实际的监测数据。
|
| 关 键 词： | 边坡 预测 位移时序 最小二乘支持向量机 布谷鸟优化算法 |
Forecasting of Slope Displacement Time-series Based on COA-LSSVM Model |
| |
| ZHANG Dongmei,XU Weiya and ZHAO Bo.Forecasting of Slope Displacement Time-series Based on COA-LSSVM Model[J].International Journal Hydroelectric Energy,2014,32(5):105-108,100. |
| |
| Authors: | ZHANG Dongmei XU Weiya and ZHAO Bo |
| |
| Affiliation: | Key Laboratory of Ministry of Education for Geomechanics and Embankment Engineering, Hohai University, Nanjing 210098, China; Geotechnical Research Institute, Hohai University, Nanjing 210098, China;Key Laboratory of Ministry of Education for Geomechanics and Embankment Engineering, Hohai University, Nanjing 210098, China; Geotechnical Research Institute, Hohai University, Nanjing 210098, China;Key Laboratory of Ministry of Education for Geomechanics and Embankment Engineering, Hohai University, Nanjing 210098, China; Geotechnical Research Institute, Hohai University, Nanjing 210098, China |
| |
| Abstract: | As the prediction of slope displacement has great significance of the slope stability, cuckoo optimization algorithm(COA) is used to optimize the parameters of LSSVM and COA-LSSVM prediction model based on the slope displacement time-series is established. This model is applied to the left bank slope in Jinping I Hydropower Station. Compared with the forecasting results of PSO-LSSVM model, it shows that the proposed model has higher forecast precision and the forecast results are closer to the actual monitor values than that of PSO-LSSVM. |
| |
| Keywords: | slope prediction displacement time series least squares support vector machine cuckoo optimization algorithm |
| 本文献已被 CNKI 等数据库收录！ |
|
