A comparative analysis of artificial neural network predictive and multiple linear regression models for ground settlement during tunnel construction
Ground settlement during and after tunnelling using TBM results in varying dynamic and static load action on the geo-stratum. It is an undesirable effect of tunnel construction causing damage to the surface and subsurface infrastructure, safety risk, and increased construction cost and quality issue...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Polish Academy of Sciences
2023-06-01
|
| Series: | Archives of Civil Engineering |
| Subjects: | |
| Online Access: | https://journals.pan.pl/Content/127769/PDF/art33_int.pdf |
| _version_ | 1797791531413798912 |
|---|---|
| author | Baoping Zou Musa Chibawe Bo Hu Yansheng Deng |
| author_facet | Baoping Zou Musa Chibawe Bo Hu Yansheng Deng |
| author_sort | Baoping Zou |
| collection | DOAJ |
| description | Ground settlement during and after tunnelling using TBM results in varying dynamic and static load action on the geo-stratum. It is an undesirable effect of tunnel construction causing damage to the surface and subsurface infrastructure, safety risk, and increased construction cost and quality issues. Ground settlement can be influenced by several factors, like method of tunnelling, tunnel geometry, location of tunnelling machine, machine operational parameters, depth & its changes, and mileage of recording point from starting point. In this study, a description and evaluation of the performance of the arti?cial neural network (ANN)was undertaken and a comparison with multiple linear regression (MLR) was carried out on ground settlement prediction. The performance of these models was evaluated using the coefficient of determination R2, root mean square error (RMSE) and mean absolute percentage error (MAPE). For ANN model, the R2, RMSE and MAPE were calculated as 0.9295, 4.2563 and 3.3372, respectively, while for MLR, the R2, RMSE and MAPE, were calculated as 0.5053, 11.2708, 6.3963 respectively. For ground settlement prediction, bothANNandMLRmethodswere able to predict significantly accurate results. It was further noted that the ANN performance was higher than that of the MLR. |
| first_indexed | 2024-03-13T02:20:10Z |
| format | Article |
| id | doaj.art-956ea3cc4ce7465ba7d930592dadf579 |
| institution | Directory Open Access Journal |
| issn | 1230-2945 2300-3103 |
| language | English |
| last_indexed | 2024-03-13T02:20:10Z |
| publishDate | 2023-06-01 |
| publisher | Polish Academy of Sciences |
| record_format | Article |
| series | Archives of Civil Engineering |
| spelling | doaj.art-956ea3cc4ce7465ba7d930592dadf5792023-06-30T10:08:31ZengPolish Academy of SciencesArchives of Civil Engineering1230-29452300-31032023-06-01vol. 69No 2503515https://doi.org/10.24425/ace.2023.145281A comparative analysis of artificial neural network predictive and multiple linear regression models for ground settlement during tunnel constructionBaoping Zou0https://orcid.org/0000-0003-3729-2425Musa Chibawe1https://orcid.org/0000-0002-9451-6459Bo Hu2https://orcid.org/0000-0002-5119-869XYansheng Deng3https://orcid.org/0000-0002-4329-1827School of Civil Engineering and Architecture, Zhejiang University of Science and Technology, Hangzhou 310023, ChinaSchool of Civil Engineering and Architecture, Zhejiang University of Science and Technology, Hangzhou 310023, ChinaSchool of Civil Engineering and Architecture, Zhejiang University of Science and Technology, Hangzhou 310023, ChinaSchool of Civil Engineering and Architecture, Zhejiang University of Science and Technology, Hangzhou 310023, ChinaGround settlement during and after tunnelling using TBM results in varying dynamic and static load action on the geo-stratum. It is an undesirable effect of tunnel construction causing damage to the surface and subsurface infrastructure, safety risk, and increased construction cost and quality issues. Ground settlement can be influenced by several factors, like method of tunnelling, tunnel geometry, location of tunnelling machine, machine operational parameters, depth & its changes, and mileage of recording point from starting point. In this study, a description and evaluation of the performance of the arti?cial neural network (ANN)was undertaken and a comparison with multiple linear regression (MLR) was carried out on ground settlement prediction. The performance of these models was evaluated using the coefficient of determination R2, root mean square error (RMSE) and mean absolute percentage error (MAPE). For ANN model, the R2, RMSE and MAPE were calculated as 0.9295, 4.2563 and 3.3372, respectively, while for MLR, the R2, RMSE and MAPE, were calculated as 0.5053, 11.2708, 6.3963 respectively. For ground settlement prediction, bothANNandMLRmethodswere able to predict significantly accurate results. It was further noted that the ANN performance was higher than that of the MLR.https://journals.pan.pl/Content/127769/PDF/art33_int.pdftunneling constructionground settlementmlrann |
| spellingShingle | Baoping Zou Musa Chibawe Bo Hu Yansheng Deng A comparative analysis of artificial neural network predictive and multiple linear regression models for ground settlement during tunnel construction Archives of Civil Engineering tunneling construction ground settlement mlr ann |
| title | A comparative analysis of artificial neural network predictive and multiple linear regression models for ground settlement during tunnel construction |
| title_full | A comparative analysis of artificial neural network predictive and multiple linear regression models for ground settlement during tunnel construction |
| title_fullStr | A comparative analysis of artificial neural network predictive and multiple linear regression models for ground settlement during tunnel construction |
| title_full_unstemmed | A comparative analysis of artificial neural network predictive and multiple linear regression models for ground settlement during tunnel construction |
| title_short | A comparative analysis of artificial neural network predictive and multiple linear regression models for ground settlement during tunnel construction |
| title_sort | comparative analysis of artificial neural network predictive and multiple linear regression models for ground settlement during tunnel construction |
| topic | tunneling construction ground settlement mlr ann |
| url | https://journals.pan.pl/Content/127769/PDF/art33_int.pdf |
| work_keys_str_mv | AT baopingzou acomparativeanalysisofartificialneuralnetworkpredictiveandmultiplelinearregressionmodelsforgroundsettlementduringtunnelconstruction AT musachibawe acomparativeanalysisofartificialneuralnetworkpredictiveandmultiplelinearregressionmodelsforgroundsettlementduringtunnelconstruction AT bohu acomparativeanalysisofartificialneuralnetworkpredictiveandmultiplelinearregressionmodelsforgroundsettlementduringtunnelconstruction AT yanshengdeng acomparativeanalysisofartificialneuralnetworkpredictiveandmultiplelinearregressionmodelsforgroundsettlementduringtunnelconstruction AT baopingzou comparativeanalysisofartificialneuralnetworkpredictiveandmultiplelinearregressionmodelsforgroundsettlementduringtunnelconstruction AT musachibawe comparativeanalysisofartificialneuralnetworkpredictiveandmultiplelinearregressionmodelsforgroundsettlementduringtunnelconstruction AT bohu comparativeanalysisofartificialneuralnetworkpredictiveandmultiplelinearregressionmodelsforgroundsettlementduringtunnelconstruction AT yanshengdeng comparativeanalysisofartificialneuralnetworkpredictiveandmultiplelinearregressionmodelsforgroundsettlementduringtunnelconstruction |