灰色神经模型与模糊神经模型在沉降预测中的应用  

Application of Grey Neural Model and Fuzzy Neural Model in Settlement Prediction

作　　者：吕磊 成枢[1] 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)

机构地区：[1]山东科技大学测绘科学与工程学院,山东青岛266590 [2]泰安市王家寨煤矿,山东泰安271200

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

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.

关 键 词：沉降监测 灰色神经网络模型 模糊神经网络模型 

分 类 号：P25[天文地球—测绘科学与技术] TB22[天文地球—大地测量学与测量工程]