Predicting TBM penetration rate with the coupled model of partial least squares regression and deep neural network
The scientific prediction of the TBM penetration rate is of great significance to the selection of hydraulic tunnel construction methods, construction schedule and cost estimation. In view of the high nonlinearity, fuzziness and complexity of TBM excavation process, and in order to improve the predi...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SCIENCE PRESS , 16 DONGHUANGCHENGGEN NORTH ST, BEIJING, PEOPLES R CHINA, 100717
2021-02-01
|
| Series: | Rock and Soil Mechanics |
| Subjects: | |
| Online Access: | http://rocksoilmech.whrsm.ac.cn/EN/10.16285/j.rsm.2020.5164 |
| _version_ | 1811339280722690048 |
|---|---|
| author | YAN Chang-bin WANG He-jian YANG Ji-hua CHEN Kui ZHOU Jian-jun GUO Wei-xin |
| author_facet | YAN Chang-bin WANG He-jian YANG Ji-hua CHEN Kui ZHOU Jian-jun GUO Wei-xin |
| author_sort | YAN Chang-bin |
| collection | DOAJ |
| description | The scientific prediction of the TBM penetration rate is of great significance to the selection of hydraulic tunnel construction methods, construction schedule and cost estimation. In view of the high nonlinearity, fuzziness and complexity of TBM excavation process, and in order to improve the prediction accuracy and computational efficiency, the partial least squares regression (PLSR) has been applied to extract the principal components of the influencing parameters. Then the deep neural network (DNN) is employed to train and forecast the TBM penetration rate. A prediction model of TBM penetration rate based on the coupled method of PLSR and DNN is proposed. Based on the measured data of the double-shield TBM construction of a water conveyance tunnel in the Lanzhou water source construction project, six impact parameters including the rock uniaxial compressive strength, rock uniaxial tensile strength, cutter head thrust, cutter head speed, rock mass integrity coefficient and rock Cerchar abrasiveness index are selected to verify the prediction reasonability of the model. The fitting and prediction accuracy of the different prediction methods are compared and analyzed. The research results show that the PLSR can effectively overcome the problem of multiple collinearity between the independent variables. The extracted principal components are trained as the input layer of the DNN, which simplifies the structure of the neural network. The PLSR-DNN coupled model effectively avoids the over-fitting and inadequate fitting problems. It has the characteristics of fast convergence, stable solution and high fitting accuracy. The average relative fitting error of the PLSR-DNN prediction model is 2.96%, and the average relative prediction error is 3.27%. The fitting accuracy and prediction accuracy of the PLSR-DNN prediction model is significantly higher than those of PLSR model alone, BP neural network model and SVR model, respectively. |
| first_indexed | 2024-04-13T18:24:02Z |
| format | Article |
| id | doaj.art-eb37f0a9a2e041a9b927ee9aaf681344 |
| institution | Directory Open Access Journal |
| issn | 1000-7598 |
| language | English |
| last_indexed | 2024-04-13T18:24:02Z |
| publishDate | 2021-02-01 |
| publisher | SCIENCE PRESS , 16 DONGHUANGCHENGGEN NORTH ST, BEIJING, PEOPLES R CHINA, 100717 |
| record_format | Article |
| series | Rock and Soil Mechanics |
| spelling | doaj.art-eb37f0a9a2e041a9b927ee9aaf6813442022-12-22T02:35:19ZengSCIENCE PRESS , 16 DONGHUANGCHENGGEN NORTH ST, BEIJING, PEOPLES R CHINA, 100717Rock and Soil Mechanics1000-75982021-02-0142251952810.16285/j.rsm.2020.5164Predicting TBM penetration rate with the coupled model of partial least squares regression and deep neural network YAN Chang-bin0WANG He-jian1YANG Ji-hua2CHEN Kui3 ZHOU Jian-jun4GUO Wei-xin5 School of Civil Engineering, Zhengzhou University, Zhengzhou, Henan 450001, China School of Civil Engineering, Zhengzhou University, Zhengzhou, Henan 450001, ChinaYellow River Engineering Consulting Co., Ltd., Zhengzhou, Henan 450003, ChinaState Key Laboratory of Shield Machine and Boring Technology, China Railway Tunnel Group Co., Ltd., Zhengzhou, Henan 450001, China State Key Laboratory of Shield Machine and Boring Technology, China Railway Tunnel Group Co., Ltd., Zhengzhou, Henan 450001, ChinaYellow River Engineering Consulting Co., Ltd., Zhengzhou, Henan 450003, ChinaThe scientific prediction of the TBM penetration rate is of great significance to the selection of hydraulic tunnel construction methods, construction schedule and cost estimation. In view of the high nonlinearity, fuzziness and complexity of TBM excavation process, and in order to improve the prediction accuracy and computational efficiency, the partial least squares regression (PLSR) has been applied to extract the principal components of the influencing parameters. Then the deep neural network (DNN) is employed to train and forecast the TBM penetration rate. A prediction model of TBM penetration rate based on the coupled method of PLSR and DNN is proposed. Based on the measured data of the double-shield TBM construction of a water conveyance tunnel in the Lanzhou water source construction project, six impact parameters including the rock uniaxial compressive strength, rock uniaxial tensile strength, cutter head thrust, cutter head speed, rock mass integrity coefficient and rock Cerchar abrasiveness index are selected to verify the prediction reasonability of the model. The fitting and prediction accuracy of the different prediction methods are compared and analyzed. The research results show that the PLSR can effectively overcome the problem of multiple collinearity between the independent variables. The extracted principal components are trained as the input layer of the DNN, which simplifies the structure of the neural network. The PLSR-DNN coupled model effectively avoids the over-fitting and inadequate fitting problems. It has the characteristics of fast convergence, stable solution and high fitting accuracy. The average relative fitting error of the PLSR-DNN prediction model is 2.96%, and the average relative prediction error is 3.27%. The fitting accuracy and prediction accuracy of the PLSR-DNN prediction model is significantly higher than those of PLSR model alone, BP neural network model and SVR model, respectively. http://rocksoilmech.whrsm.ac.cn/EN/10.16285/j.rsm.2020.5164tunnel boring machinepenetration ratiopartial least square regressiondeep neural nerworkcoupling prediction model |
| spellingShingle | YAN Chang-bin WANG He-jian YANG Ji-hua CHEN Kui ZHOU Jian-jun GUO Wei-xin Predicting TBM penetration rate with the coupled model of partial least squares regression and deep neural network Rock and Soil Mechanics tunnel boring machine penetration ratio partial least square regression deep neural nerwork coupling prediction model |
| title | Predicting TBM penetration rate with the coupled model of partial least squares regression and deep neural network |
| title_full | Predicting TBM penetration rate with the coupled model of partial least squares regression and deep neural network |
| title_fullStr | Predicting TBM penetration rate with the coupled model of partial least squares regression and deep neural network |
| title_full_unstemmed | Predicting TBM penetration rate with the coupled model of partial least squares regression and deep neural network |
| title_short | Predicting TBM penetration rate with the coupled model of partial least squares regression and deep neural network |
| title_sort | predicting tbm penetration rate with the coupled model of partial least squares regression and deep neural network |
| topic | tunnel boring machine penetration ratio partial least square regression deep neural nerwork coupling prediction model |
| url | http://rocksoilmech.whrsm.ac.cn/EN/10.16285/j.rsm.2020.5164 |
| work_keys_str_mv | AT yanchangbin predictingtbmpenetrationratewiththecoupledmodelofpartialleastsquaresregressionanddeepneuralnetwork AT wanghejian predictingtbmpenetrationratewiththecoupledmodelofpartialleastsquaresregressionanddeepneuralnetwork AT yangjihua predictingtbmpenetrationratewiththecoupledmodelofpartialleastsquaresregressionanddeepneuralnetwork AT chenkui predictingtbmpenetrationratewiththecoupledmodelofpartialleastsquaresregressionanddeepneuralnetwork AT zhoujianjun predictingtbmpenetrationratewiththecoupledmodelofpartialleastsquaresregressionanddeepneuralnetwork AT guoweixin predictingtbmpenetrationratewiththecoupledmodelofpartialleastsquaresregressionanddeepneuralnetwork |