摘要
将时间序列分析的思想与BP神经网络模型结合起来,预测了某城市地铁的地表沉降规律,并与时间序列分析、基于反演理论BP神经网络分析的结果进行了比较,结果表明,基于时序思想BP神经网络模型具有很高的精度,能够为地铁沉降变形监测提供参考依据。
In this paper,combined with time series,BP neural network is adopted to predict the settlement of a city metro. The result are compared with that of time series and BP neural network based on back analysis respectively. It indicates that BP neural network which is based on time series has high precision,and can provide a reference to the motoring of metro’s settlement.
出处
《山西建筑》
2016年第20期170-172,共3页
Shanxi Architecture
关键词
神经网络
时间序列
预测模型
地表沉降
neural network
time series
predicting model
surface settlement
