Attention-based LSTM predictive model for the attitude and position of shield machine in tunneling
Shield machine may deviate from its design axis during excavation due to the uncertainty of geological environment and the complexity of operation. This study therefore introduced a framework to predict the attitude and position of shield machine by combining long short-term memory (LSTM) model with...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2023-12-01
|
| Series: | Underground Space |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2467967423000880 |
| _version_ | 1827788630005907456 |
|---|---|
| author | Qing Kang Elton J. Chen Zhong-Chao Li Han-Bin Luo Yong Liu |
| author_facet | Qing Kang Elton J. Chen Zhong-Chao Li Han-Bin Luo Yong Liu |
| author_sort | Qing Kang |
| collection | DOAJ |
| description | Shield machine may deviate from its design axis during excavation due to the uncertainty of geological environment and the complexity of operation. This study therefore introduced a framework to predict the attitude and position of shield machine by combining long short-term memory (LSTM) model with attention mechanism. The data obtained from the Wuhan Rail Transit Line 6 project were utilized to verify the feasibility of the proposed method. By adding the attention mechanism into the LSTM model, the proposed model can focus more on parameters with higher weights. Sensitivity analysis based on Pearson correlation coefficient was conducted to improve the prediction efficiency and reduce the irrelevant input parameters. Compared with LSTM model, LSTM-attention model has higher accuracy. The mean value of coefficient of determination (R2) increases from 0.625 to 0.736, and the mean value of root mean square error (RMSE) decreases from 3.31 to 2.24. The proposed LSTM-attention model can provide an effective prediction for attitude and position of shield machine in practical tunneling engineering. |
| first_indexed | 2024-03-11T17:09:13Z |
| format | Article |
| id | doaj.art-4e5c9fd174c843af9dde39022bedd3e0 |
| institution | Directory Open Access Journal |
| issn | 2467-9674 |
| language | English |
| last_indexed | 2024-03-11T17:09:13Z |
| publishDate | 2023-12-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Underground Space |
| spelling | doaj.art-4e5c9fd174c843af9dde39022bedd3e02023-10-20T06:40:15ZengKeAi Communications Co., Ltd.Underground Space2467-96742023-12-0113335350Attention-based LSTM predictive model for the attitude and position of shield machine in tunnelingQing Kang0Elton J. Chen1Zhong-Chao Li2Han-Bin Luo3Yong Liu4State Key Laboratory of Water Resources Engineering and Management, Wuhan University, Wuhan 430072, ChinaSchool of Civil & Hydraulic Engineering, Huazhong University of Science & Technology, Wuhan 430074, China; Corresponding author.Tunnel Engineering Company, Wuhan Municipal Construction Group Co. Ltd, Wuhan 430023, ChinaSchool of Civil & Hydraulic Engineering, Huazhong University of Science & Technology, Wuhan 430074, ChinaState Key Laboratory of Water Resources Engineering and Management, Wuhan University, Wuhan 430072, ChinaShield machine may deviate from its design axis during excavation due to the uncertainty of geological environment and the complexity of operation. This study therefore introduced a framework to predict the attitude and position of shield machine by combining long short-term memory (LSTM) model with attention mechanism. The data obtained from the Wuhan Rail Transit Line 6 project were utilized to verify the feasibility of the proposed method. By adding the attention mechanism into the LSTM model, the proposed model can focus more on parameters with higher weights. Sensitivity analysis based on Pearson correlation coefficient was conducted to improve the prediction efficiency and reduce the irrelevant input parameters. Compared with LSTM model, LSTM-attention model has higher accuracy. The mean value of coefficient of determination (R2) increases from 0.625 to 0.736, and the mean value of root mean square error (RMSE) decreases from 3.31 to 2.24. The proposed LSTM-attention model can provide an effective prediction for attitude and position of shield machine in practical tunneling engineering.http://www.sciencedirect.com/science/article/pii/S2467967423000880LSTMShield machineAttitude and position predictionAttention mechanismTunnel excavation |
| spellingShingle | Qing Kang Elton J. Chen Zhong-Chao Li Han-Bin Luo Yong Liu Attention-based LSTM predictive model for the attitude and position of shield machine in tunneling Underground Space LSTM Shield machine Attitude and position prediction Attention mechanism Tunnel excavation |
| title | Attention-based LSTM predictive model for the attitude and position of shield machine in tunneling |
| title_full | Attention-based LSTM predictive model for the attitude and position of shield machine in tunneling |
| title_fullStr | Attention-based LSTM predictive model for the attitude and position of shield machine in tunneling |
| title_full_unstemmed | Attention-based LSTM predictive model for the attitude and position of shield machine in tunneling |
| title_short | Attention-based LSTM predictive model for the attitude and position of shield machine in tunneling |
| title_sort | attention based lstm predictive model for the attitude and position of shield machine in tunneling |
| topic | LSTM Shield machine Attitude and position prediction Attention mechanism Tunnel excavation |
| url | http://www.sciencedirect.com/science/article/pii/S2467967423000880 |
| work_keys_str_mv | AT qingkang attentionbasedlstmpredictivemodelfortheattitudeandpositionofshieldmachineintunneling AT eltonjchen attentionbasedlstmpredictivemodelfortheattitudeandpositionofshieldmachineintunneling AT zhongchaoli attentionbasedlstmpredictivemodelfortheattitudeandpositionofshieldmachineintunneling AT hanbinluo attentionbasedlstmpredictivemodelfortheattitudeandpositionofshieldmachineintunneling AT yongliu attentionbasedlstmpredictivemodelfortheattitudeandpositionofshieldmachineintunneling |