摘要
GM(1,1)模型是沉降预测中应用较为广泛的模型之一,在实际应用当中发现其预测效果有时候较差甚至完全失效。将指数平滑技术引入到灰色预测模型中,该方法既充分利用了观测序列中的有用信息,又大大减少其随机性,将平均斜率法对灰色模型的背景值计算方法进行了改进,将原始观测数据序列变换成规律性强的呈指数变化的序列。某公路试验段实测沉降数据计算表明,新方法有满意的拟合和预测效果,为提高建模精度提供了新的途径。
GM （ 1, 1 ） model is one of the most widely used methods in settlement prediction, and it is found that the precision is low even defect. Based on exponential smoothing method, a new grey prediction model was put forward. This method can not only make full use of the available information but also greatly diminish the randomness of deformation surveying data sequential. Then the average slope method is used to improve the background value of grey model, and the original surveying data sequential can be transformed to a regular exponential variety sequential. An actual example is used, and it show that the new model has satisfactory fitting effects and thus points a novel direction to higher modeling procedure.
出处
《中南公路工程》
2007年第3期120-123,共4页
Central South Highway Engineering
关键词
指数平滑
灰色模型
平均斜率
沉降预测
exponential smoothing
grey model
average slope
settlement prediction
