摘要
针对地铁站基坑沉降监测问题,研究了灰色神经网络和模糊神经网络两种模型,并利用佛山地铁3号线某地铁站沉降监测数据,分别利用灰色神经网络模型和模糊神经网络模型进行建模与预测。经过对比分析发现,两种神经网络模型都具有较高的预测精度,但灰色神经网络模型只适合于短期预测,预测周期越长则精度越差,而模糊神经网络模型更适合长周期预测。
The monitoring problem of foundation pit subsidence in subway station,this paper studies two models of grey neural network and fuzzy neural network. Based on the settlement monitoring data of a subway station of Foshan metro line 3,the grey neural network model and the fuzzy neural network model are used to model and predict. It is found that both neural network models have high prediction accuracy. However,the grey neural network model is only suitable for short-term prediction,and the longer the prediction cycle is,the worse the accuracy is,while the fuzzy neural network model is more suitable for long period prediction.
作者
吕磊
成枢
高秀明
查天宇
LYU Lei;CHENG Shu;GAO Xiuming;ZHA Tianyu(College of Geomatics,Shandong University of Science and Technology,Qingdao 266590,China;Wangjiazhai Coal Mine of Tai′an,Tai′an 271200,China)
出处
《测绘与空间地理信息》
2019年第12期236-238,共3页
Geomatics & Spatial Information Technology
关键词
沉降监测
灰色神经网络模型
模糊神经网络模型
settlement monitoring
grey neural network model
fuzzy neural network model