| 基于灰色最小二乘支持向量机的大坝变形预测 |
| |
| 引用本文： | 任超,梁月吉,庞光锋,蓝岚.基于灰色最小二乘支持向量机的大坝变形预测[J].大地测量与地球动力学,2015,35(4):608-612. |
| |
| 作者姓名： | 任超 梁月吉 庞光锋 蓝岚 |
| |
| 摘 要： | 提出一种基于灰色最小二乘支持向量机的大坝变形预测新算法。通过对原始大坝序列进行一次累加,弱化序列中随机扰动的影响,增强数据的规律性,进而建立最小二乘支持向量机预测模型,并采用网格搜索法选取最优参数。算法充分利用了最小二乘支持向量机泛化能力强、非线性拟合性好等优良特性,避免了灰色方法及模型存在的理论缺陷。与灰色GM(1,1)和单一最小二乘支持向量机对比表明,新算法能保证较优的局部预测值和较好的全局预测精度,应用于短期大坝变形预测是可行的。
|
| 关 键 词： | 大坝变形 灰色模型 最小二乘支持向量机 网格搜索算法 精度评定 |
Dam Deformation Prediction Based on Grey Least Square Support Vector Machines |
| |
| REN Chao,LIANG Yueji,PANG Guangfeng,LAN Lan.Dam Deformation Prediction Based on Grey Least Square Support Vector Machines[J].Journal of Geodesy and Geodynamics,2015,35(4):608-612. |
| |
| Authors: | REN Chao LIANG Yueji PANG Guangfeng LAN Lan |
| |
| Abstract: | A new algorithm based on gray least squares support vector machine for dam deformation prediction is presented. First, the algorithm of the original dam sequence is summed to weaken the impact of the random disturbance factors sequence and enhance the data regularity. Second, the least squares support vector machine model is established. The grid search method is used to select the optimal parameters. This method makes full use of least squares support vector machine generalization ability| the nonlinear fitting of good quality characteristics avoids defects of the theoretical methods and gray models. The calculation result is analyzed and compared with GM (1, 1) and a single least squares support vector machine. The results show that the new algorithm can guarantee the optimum value of the local forecasts and better overall prediction accuracy in dam deformation. It is feasible to apply the model in short-term forecasts. |
| |
| Keywords: | dam deformation grey model least square support vector machines 〖JP2〗grid search algorithm accuracy assessment |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《大地测量与地球动力学》浏览原始摘要信息 |
| 点击此处可从《大地测量与地球动力学》下载免费的PDF全文 |
|
