摘要
应用GM(1,1)与RBF两者去预测信息,并结合非线性预测模型中的变形数据,用其与某围岩变形的结果同简单平均定权组合、最优线性组合相对比,通过神经网络将单项模型在组合模型中所占有比重运算出来。结果显示:此模型预测隧道围岩发生变形,结果相对于传统定权方式预测结果更加可靠,精度上有比较显著的提升,在实际应用中凸显了不错的工程和实践价值。
GM （1,1） and RBF are used to predict information, and combine deformation data in nonlinear prediction models. Using the result of the deformation of a certain surrounding rock with the simple average weighted combination and the optimal linear combination, the proportion of the single model in the combined model is calculated by the neural network. The results show that the prediction result of this model is more reliable than the traditional fixed weight forecasting method, and the accuracy has a significant improvement. It highlights the good engineering and practical value in practical applications.
作者
王科甫
WANG Ke-fu(China Railway First Survey and Design Institute Group Co., Ltd., Xi＇an 710043, Chin)
出处
《煤炭技术》
CAS
2018年第6期106-107,共2页
Coal Technology
关键词
非线性分析
隧道围岩
位移序列
nonlinear analysis
tunnel surrounding rock
displacement sequence
