论文部分内容阅读
结合灰色系统思想与最小二乘支持向量机构成灰色最小二乘支持向量机,根据目前灰色模型与最小二乘支持向量机结合的方法,提出并联型、串联型和残差型三种预测模型的结构。将上述三种灰色最小二乘支持向量机模型用于对三峡库区石佛寺滑坡垂直位移进行预测,模型精度和预测结果比较理想,优于单一预测模型。试验表明:灰色最小二乘支持向量机可提高预测精度,用于滑坡变形预测是有效可行的。
Combining gray system theory and least square support vector machine into gray least square support vector machine, according to the combination of gray model and least squares support vector machine, three prediction models of parallel type, tandem type and residual type are proposed structure. The above three models of gray least square support vector machine are used to predict the vertical displacement of Shifushi landslide in the Three Gorges Reservoir Area. The model accuracy and prediction results are better than the single prediction model. Experiments show that the gray least square support vector machine can improve the prediction accuracy and is effective and feasible for landslide deformation prediction.