Predicting Model of Dual-Mode Shield Tunneling Parameters in Complex Ground Using Recurrent Neural Networks and Multiple Optimization Algorithms
Based on the left tunnel of the Liuxiandong Station to Baimang Station section of Shenzhen Metro Line 13 (China), a prediction model for the advanced rate of dual-mode shield tunneling in complex strata was established to explore intelligent tunneling technology in complex ground. Firstly, geologica...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/2/581 |
| _version_ | 1797340163384279040 |
|---|---|
| author | Taihua Yang Tian Wen Xing Huang Bin Liu Hongbing Shi Shaoran Liu Xiaoxiang Peng Guangzu Sheng |
| author_facet | Taihua Yang Tian Wen Xing Huang Bin Liu Hongbing Shi Shaoran Liu Xiaoxiang Peng Guangzu Sheng |
| author_sort | Taihua Yang |
| collection | DOAJ |
| description | Based on the left tunnel of the Liuxiandong Station to Baimang Station section of Shenzhen Metro Line 13 (China), a prediction model for the advanced rate of dual-mode shield tunneling in complex strata was established to explore intelligent tunneling technology in complex ground. Firstly, geological parameters of the complex strata and on-site monitoring parameters of EPB/TBM dual-mode shield tunneling were collected, with tunneling parameters, shield tunneling mode, and strata parameters selected as input features. Subsequently, the Isolation Forest algorithm was employed to remove outliers from the original advance parameters, and an improved mean filtering algorithm was applied to eliminate data noise, resulting in the steady-state phase parameters of the shield tunneling process. The base model was chosen as the Long-Short Term Memory (LSTM) recurrent neural network. During the model training process, particle swarm optimization (PSO), genetic algorithm (GA), differential evolution (DE), and Bayesian optimization (BO) algorithms were, respectively, combined to optimize the model’s hyperparameters. Via rank analysis based on evaluation metrics, the BO-LSTM model was found to have the shortest runtime and highest accuracy. Finally, the dropout algorithm and five-fold time series cross-validation were incorporated into the BO-LSTM model, creating a multi-algorithm-optimized recurrent neural network model for predicting tunneling speed. The results indicate that (1) the Isolation Forest algorithm can conveniently identify outliers while considering the relationship between tunneling speed and other parameters; (2) the improved mean filtering algorithm exhibits better denoising effects on cutterhead speed and tunneling speed; and (3) the multi-algorithm optimized LSTM model exhibits high prediction accuracy and operational efficiency under various geological parameters and different excavation modes. The minimum Mean Absolute Percentage Error (MAPE) prediction result is 8.3%, with an average MAPE prediction result below 15%. |
| first_indexed | 2024-03-08T09:59:03Z |
| format | Article |
| id | doaj.art-9bd1abde9b9e4bf5b16e5651eebb0c18 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-08T09:59:03Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-9bd1abde9b9e4bf5b16e5651eebb0c182024-01-29T13:42:53ZengMDPI AGApplied Sciences2076-34172024-01-0114258110.3390/app14020581Predicting Model of Dual-Mode Shield Tunneling Parameters in Complex Ground Using Recurrent Neural Networks and Multiple Optimization AlgorithmsTaihua Yang0Tian Wen1Xing Huang2Bin Liu3Hongbing Shi4Shaoran Liu5Xiaoxiang Peng6Guangzu Sheng7School of Urban Construction, Wuhan University of Science and Technology, Wuhan 430083, ChinaSchool of Urban Construction, Wuhan University of Science and Technology, Wuhan 430083, ChinaState Key Laboratory of Geomechanics and Geotechnical Engineering, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences, Wuhan 430071, ChinaState Key Laboratory of Geomechanics and Geotechnical Engineering, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences, Wuhan 430071, ChinaChina Construction Civil Infrastructure Corp., Ltd., Beijing 100029, ChinaChina Construction South Investment Co., Ltd., Shenzhen 518000, ChinaSchool of Urban Construction, Wuhan University of Science and Technology, Wuhan 430083, ChinaWuhan Urban Construction Group Construction Management Co., Ltd., Wuhan 430040, ChinaBased on the left tunnel of the Liuxiandong Station to Baimang Station section of Shenzhen Metro Line 13 (China), a prediction model for the advanced rate of dual-mode shield tunneling in complex strata was established to explore intelligent tunneling technology in complex ground. Firstly, geological parameters of the complex strata and on-site monitoring parameters of EPB/TBM dual-mode shield tunneling were collected, with tunneling parameters, shield tunneling mode, and strata parameters selected as input features. Subsequently, the Isolation Forest algorithm was employed to remove outliers from the original advance parameters, and an improved mean filtering algorithm was applied to eliminate data noise, resulting in the steady-state phase parameters of the shield tunneling process. The base model was chosen as the Long-Short Term Memory (LSTM) recurrent neural network. During the model training process, particle swarm optimization (PSO), genetic algorithm (GA), differential evolution (DE), and Bayesian optimization (BO) algorithms were, respectively, combined to optimize the model’s hyperparameters. Via rank analysis based on evaluation metrics, the BO-LSTM model was found to have the shortest runtime and highest accuracy. Finally, the dropout algorithm and five-fold time series cross-validation were incorporated into the BO-LSTM model, creating a multi-algorithm-optimized recurrent neural network model for predicting tunneling speed. The results indicate that (1) the Isolation Forest algorithm can conveniently identify outliers while considering the relationship between tunneling speed and other parameters; (2) the improved mean filtering algorithm exhibits better denoising effects on cutterhead speed and tunneling speed; and (3) the multi-algorithm optimized LSTM model exhibits high prediction accuracy and operational efficiency under various geological parameters and different excavation modes. The minimum Mean Absolute Percentage Error (MAPE) prediction result is 8.3%, with an average MAPE prediction result below 15%.https://www.mdpi.com/2076-3417/14/2/581shield tunnelingcomplex strataEPB/TBM dual-mode shield tunnelingtunneling parameter predictionrecurrent neural network |
| spellingShingle | Taihua Yang Tian Wen Xing Huang Bin Liu Hongbing Shi Shaoran Liu Xiaoxiang Peng Guangzu Sheng Predicting Model of Dual-Mode Shield Tunneling Parameters in Complex Ground Using Recurrent Neural Networks and Multiple Optimization Algorithms Applied Sciences shield tunneling complex strata EPB/TBM dual-mode shield tunneling tunneling parameter prediction recurrent neural network |
| title | Predicting Model of Dual-Mode Shield Tunneling Parameters in Complex Ground Using Recurrent Neural Networks and Multiple Optimization Algorithms |
| title_full | Predicting Model of Dual-Mode Shield Tunneling Parameters in Complex Ground Using Recurrent Neural Networks and Multiple Optimization Algorithms |
| title_fullStr | Predicting Model of Dual-Mode Shield Tunneling Parameters in Complex Ground Using Recurrent Neural Networks and Multiple Optimization Algorithms |
| title_full_unstemmed | Predicting Model of Dual-Mode Shield Tunneling Parameters in Complex Ground Using Recurrent Neural Networks and Multiple Optimization Algorithms |
| title_short | Predicting Model of Dual-Mode Shield Tunneling Parameters in Complex Ground Using Recurrent Neural Networks and Multiple Optimization Algorithms |
| title_sort | predicting model of dual mode shield tunneling parameters in complex ground using recurrent neural networks and multiple optimization algorithms |
| topic | shield tunneling complex strata EPB/TBM dual-mode shield tunneling tunneling parameter prediction recurrent neural network |
| url | https://www.mdpi.com/2076-3417/14/2/581 |
| work_keys_str_mv | AT taihuayang predictingmodelofdualmodeshieldtunnelingparametersincomplexgroundusingrecurrentneuralnetworksandmultipleoptimizationalgorithms AT tianwen predictingmodelofdualmodeshieldtunnelingparametersincomplexgroundusingrecurrentneuralnetworksandmultipleoptimizationalgorithms AT xinghuang predictingmodelofdualmodeshieldtunnelingparametersincomplexgroundusingrecurrentneuralnetworksandmultipleoptimizationalgorithms AT binliu predictingmodelofdualmodeshieldtunnelingparametersincomplexgroundusingrecurrentneuralnetworksandmultipleoptimizationalgorithms AT hongbingshi predictingmodelofdualmodeshieldtunnelingparametersincomplexgroundusingrecurrentneuralnetworksandmultipleoptimizationalgorithms AT shaoranliu predictingmodelofdualmodeshieldtunnelingparametersincomplexgroundusingrecurrentneuralnetworksandmultipleoptimizationalgorithms AT xiaoxiangpeng predictingmodelofdualmodeshieldtunnelingparametersincomplexgroundusingrecurrentneuralnetworksandmultipleoptimizationalgorithms AT guangzusheng predictingmodelofdualmodeshieldtunnelingparametersincomplexgroundusingrecurrentneuralnetworksandmultipleoptimizationalgorithms |