ISSN 2096-4498
CN 44-1745/U
Tunnel Construction ›› 2021, Vol. 41 ›› Issue (5): 758-763.DOI: 10.3973/j.issn.2096-4498.2021.05.008
Previous Articles Next Articles
LI Zengliang
Online:
Published:
Abstract: To accurately predict the vertical posture of shields, a deeplearning combination prediction model based on long shortterm memory (LSTM) neural network and support vector regression (SVR) is proposed. The LSTM and SVR verticalposture prediction models are developed by performing the corresponding data preprocessing operations on the collected verticalposture data. Further, the prediction results of the two models are weighted by the optimal combination of weights to obtain a LSTMSVR combined prediction model. Finally, to verify the reliability of the developed LSTMSVR combined deeplearning prediction model, the prediction results are compared with those of the LSTM, SVR, and BP models based on the Kunming metro project. The results show that the LSTMSVR combined deeplearning prediction model has high prediction accuracy.
Key words: metro tunnel, combined prediction model, deep learning, shield vertical posture, long shortterm memory (LSTM) neural network, support vector regression (SVR)
CLC Number:
U 45
LI Zengliang. Combined Prediction Model for Shield Vertical Posture Based on Deep Learning[J]. Tunnel Construction, 2021, 41(5): 758-763.
0 / / Recommend
Add to citation manager EndNote|Ris|BibTeX
URL: http://www.suidaojs.com/EN/10.3973/j.issn.2096-4498.2021.05.008
http://www.suidaojs.com/EN/Y2021/V41/I5/758
Case Study on Effect of Soil Filling Grouting Reinforcement on Deep Foundation Pit Support Structure and Adjacent Tunnels
Analysis on Surface Settlement Induced by Shield Tunneling Based on Stress Release
Experimental Effect Prediction of Ground Conditioning of Water rich Sandy Stratum Based on BP Neural Network
Research on Soil Conditioning of WaterRich Sandy Gravel Strata Based on Shield Tunneling Effect