Data-driven real-time prediction for attitude and position of super-large diameter shield using a hybrid deep learning approach
The presented research introduces a novel hybrid deep learning approach for the dynamic prediction of the attitude and position of super-large diameter shields - a critical consideration for construction safety and tunnel lining quality. This study proposes a hybrid deep learning approach for predic...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
KeAi Communications Co., Ltd.
2024-04-01
|
Series: | Underground Space |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2467967423001332 |
_version_ | 1797377874977619968 |
---|---|
author | Yanbin Fu Lei Chen Hao Xiong Xiangsheng Chen Andian Lu Yi Zeng Beiling Wang |
author_facet | Yanbin Fu Lei Chen Hao Xiong Xiangsheng Chen Andian Lu Yi Zeng Beiling Wang |
author_sort | Yanbin Fu |
collection | DOAJ |
description | The presented research introduces a novel hybrid deep learning approach for the dynamic prediction of the attitude and position of super-large diameter shields - a critical consideration for construction safety and tunnel lining quality. This study proposes a hybrid deep learning approach for predicting dynamic attitude and position prediction of super-large diameter shield. The approach consists of principal component analysis (PCA) and temporal convolutional network (TCN). The former is used for employing feature level fusion based on features of the shield data to reduce uncertainty, improve accuracy and the data effect, and 9 sets of required principal component characteristic data are obtained. The latter is adopted to process sequence data in predicting the dynamic attitude and position for the advantages and potential of convolution network. The approach’s effectiveness is exemplified using data from a tunnel construction project in China. The obtained results show remarkable accuracy in predicting the global attitude and position, with an average error ratio of less than 2 mm on four shield outputs in 97.30% of cases. Moreover, the approach displays strong performance in accurately predicting sudden fluctuations in shield attitude and position, with an average prediction accuracy of 89.68%. The proposed hybrid model demonstrates superiority over TCN, long short-term memory (LSTM), and recurrent neural network (RNN) in multiple indexes. Shapley additive exPlanations (SHAP) analysis is also performed to investigate the significance of different data features in the prediction process. This study provides a real-time warning for the shield driver to adjust the attitude and position of super-large diameter shields. |
first_indexed | 2024-03-08T19:58:41Z |
format | Article |
id | doaj.art-ec547b6459b24394beda465475646131 |
institution | Directory Open Access Journal |
issn | 2467-9674 |
language | English |
last_indexed | 2024-03-08T19:58:41Z |
publishDate | 2024-04-01 |
publisher | KeAi Communications Co., Ltd. |
record_format | Article |
series | Underground Space |
spelling | doaj.art-ec547b6459b24394beda4654756461312023-12-24T04:46:13ZengKeAi Communications Co., Ltd.Underground Space2467-96742024-04-0115275297Data-driven real-time prediction for attitude and position of super-large diameter shield using a hybrid deep learning approachYanbin Fu0Lei Chen1Hao Xiong2Xiangsheng Chen3Andian Lu4Yi Zeng5Beiling Wang6Key Laboratory of Coastal Urban Resilient Infrastructures (MOE), Shenzhen University, Shenzhen 518060, Guangdong, China; College of Civil and Transportation Engineering, Shenzhen University, Shenzhen 518060, Guangdong, China; Shenzhen Key Laboratory of Green, Efficient and Intelligent Construction of Underground Metro Station, Shenzhen University, Shenzhen 518060, Guangdong, ChinaKey Laboratory of Coastal Urban Resilient Infrastructures (MOE), Shenzhen University, Shenzhen 518060, Guangdong, China; College of Civil and Transportation Engineering, Shenzhen University, Shenzhen 518060, Guangdong, China; Shenzhen Key Laboratory of Green, Efficient and Intelligent Construction of Underground Metro Station, Shenzhen University, Shenzhen 518060, Guangdong, ChinaKey Laboratory of Coastal Urban Resilient Infrastructures (MOE), Shenzhen University, Shenzhen 518060, Guangdong, China; College of Civil and Transportation Engineering, Shenzhen University, Shenzhen 518060, Guangdong, China; Shenzhen Key Laboratory of Green, Efficient and Intelligent Construction of Underground Metro Station, Shenzhen University, Shenzhen 518060, Guangdong, China; Corresponding author at: Key Laboratory of Coastal Urban Resilient Infrastructures (MOE), Shenzhen University, Shenzhen 518060, Guangdong, China.Key Laboratory of Coastal Urban Resilient Infrastructures (MOE), Shenzhen University, Shenzhen 518060, Guangdong, China; College of Civil and Transportation Engineering, Shenzhen University, Shenzhen 518060, Guangdong, China; Shenzhen Key Laboratory of Green, Efficient and Intelligent Construction of Underground Metro Station, Shenzhen University, Shenzhen 518060, Guangdong, ChinaGuangdong Yuehai Pearl River Delta Water Supply Limited Company, Guangzhou 511458, ChinaShanghai Tunnel Engineering and Rail Transit Design and Research Institute, Shanghai 200235, ChinaKey Laboratory of Coastal Urban Resilient Infrastructures (MOE), Shenzhen University, Shenzhen 518060, Guangdong, China; College of Civil and Transportation Engineering, Shenzhen University, Shenzhen 518060, Guangdong, China; Shenzhen Key Laboratory of Green, Efficient and Intelligent Construction of Underground Metro Station, Shenzhen University, Shenzhen 518060, Guangdong, ChinaThe presented research introduces a novel hybrid deep learning approach for the dynamic prediction of the attitude and position of super-large diameter shields - a critical consideration for construction safety and tunnel lining quality. This study proposes a hybrid deep learning approach for predicting dynamic attitude and position prediction of super-large diameter shield. The approach consists of principal component analysis (PCA) and temporal convolutional network (TCN). The former is used for employing feature level fusion based on features of the shield data to reduce uncertainty, improve accuracy and the data effect, and 9 sets of required principal component characteristic data are obtained. The latter is adopted to process sequence data in predicting the dynamic attitude and position for the advantages and potential of convolution network. The approach’s effectiveness is exemplified using data from a tunnel construction project in China. The obtained results show remarkable accuracy in predicting the global attitude and position, with an average error ratio of less than 2 mm on four shield outputs in 97.30% of cases. Moreover, the approach displays strong performance in accurately predicting sudden fluctuations in shield attitude and position, with an average prediction accuracy of 89.68%. The proposed hybrid model demonstrates superiority over TCN, long short-term memory (LSTM), and recurrent neural network (RNN) in multiple indexes. Shapley additive exPlanations (SHAP) analysis is also performed to investigate the significance of different data features in the prediction process. This study provides a real-time warning for the shield driver to adjust the attitude and position of super-large diameter shields.http://www.sciencedirect.com/science/article/pii/S2467967423001332Shield attitude and positionSuper-large diameter shieldPCA-TCNDeep learningReal-time warning |
spellingShingle | Yanbin Fu Lei Chen Hao Xiong Xiangsheng Chen Andian Lu Yi Zeng Beiling Wang Data-driven real-time prediction for attitude and position of super-large diameter shield using a hybrid deep learning approach Underground Space Shield attitude and position Super-large diameter shield PCA-TCN Deep learning Real-time warning |
title | Data-driven real-time prediction for attitude and position of super-large diameter shield using a hybrid deep learning approach |
title_full | Data-driven real-time prediction for attitude and position of super-large diameter shield using a hybrid deep learning approach |
title_fullStr | Data-driven real-time prediction for attitude and position of super-large diameter shield using a hybrid deep learning approach |
title_full_unstemmed | Data-driven real-time prediction for attitude and position of super-large diameter shield using a hybrid deep learning approach |
title_short | Data-driven real-time prediction for attitude and position of super-large diameter shield using a hybrid deep learning approach |
title_sort | data driven real time prediction for attitude and position of super large diameter shield using a hybrid deep learning approach |
topic | Shield attitude and position Super-large diameter shield PCA-TCN Deep learning Real-time warning |
url | http://www.sciencedirect.com/science/article/pii/S2467967423001332 |
work_keys_str_mv | AT yanbinfu datadrivenrealtimepredictionforattitudeandpositionofsuperlargediametershieldusingahybriddeeplearningapproach AT leichen datadrivenrealtimepredictionforattitudeandpositionofsuperlargediametershieldusingahybriddeeplearningapproach AT haoxiong datadrivenrealtimepredictionforattitudeandpositionofsuperlargediametershieldusingahybriddeeplearningapproach AT xiangshengchen datadrivenrealtimepredictionforattitudeandpositionofsuperlargediametershieldusingahybriddeeplearningapproach AT andianlu datadrivenrealtimepredictionforattitudeandpositionofsuperlargediametershieldusingahybriddeeplearningapproach AT yizeng datadrivenrealtimepredictionforattitudeandpositionofsuperlargediametershieldusingahybriddeeplearningapproach AT beilingwang datadrivenrealtimepredictionforattitudeandpositionofsuperlargediametershieldusingahybriddeeplearningapproach |