Comprehensive deformation study in the new Austrian tunneling technique tunnel utilising artificial neural network model
Ground deformation during tunneling projects is one of the complicated concerns that must be constantly monitored to prevent unanticipated damages and human losses. In addition to conventional approaches, several intelligent methods, like ANN, have recently been used for different tunnel challenges...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universidad de Santander
2024-01-01
|
| Series: | AiBi Revista de Investigación, Administración e Ingeniería |
| Subjects: | |
| Online Access: | https://revistas.udes.edu.co/aibi/article/view/3631 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850108830818500608 |
|---|---|
| author | Shubham Kanojiya Gopal Krishna Mehta |
| author_facet | Shubham Kanojiya Gopal Krishna Mehta |
| author_sort | Shubham Kanojiya |
| collection | DOAJ |
| description |
Ground deformation during tunneling projects is one of the complicated concerns that must be constantly monitored to prevent unanticipated damages and human losses. In addition to conventional approaches, several intelligent methods, like ANN, have recently been used for different tunnel challenges. Geological elements such as thrust zones, folded rock sequences, shear zones, rock cover, in-situ tensions, water ingress, gas ingress, geothermal gradient, and significant seismicity all present difficulties during digging. These difficulties have a substantial influence on the routine functioning of the tunnel as well as traffic safety. To address these issues, the authors recommended using ANNs from many elements of tunnel engineering. The new Austrian tunneling technique (NATM) has shown to be a highly affordable and versatile mode of construction, and as a result, it has become the most common tunneling construction method utilized in the building of the double-arched tunnel. In this work, the MATLAB program was utilized to generate the results, which comprised training and testing datasets. The experimental results demonstrate that the suggested model's values for R2, Bias, Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE), with training data are 18.56, 0.98, 1.05, and 0.08, respectively. The suggested RMSE, R2, Bias, and MAPE values for the test dataset were 19.89, 0.98, 1.05, and 0.09.
|
| format | Article |
| id | doaj-art-d6dbed25b2bd47efb9ff76d30f069ae0 |
| institution | OA Journals |
| issn | 2346-030X |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Universidad de Santander |
| record_format | Article |
| series | AiBi Revista de Investigación, Administración e Ingeniería |
| spelling | doaj-art-d6dbed25b2bd47efb9ff76d30f069ae02025-08-20T02:38:15ZengUniversidad de SantanderAiBi Revista de Investigación, Administración e Ingeniería2346-030X2024-01-0112110.15649/2346030X.3631Comprehensive deformation study in the new Austrian tunneling technique tunnel utilising artificial neural network modelShubham Kanojiya0https://orcid.org/0000-0003-4753-6411Gopal Krishna Mehta1https://orcid.org/0000-0003-3327-0042Shri Venkateshwara University - Uttar Pradesh, IndiaShri Venkateshwara University - Uttar Pradesh, India Ground deformation during tunneling projects is one of the complicated concerns that must be constantly monitored to prevent unanticipated damages and human losses. In addition to conventional approaches, several intelligent methods, like ANN, have recently been used for different tunnel challenges. Geological elements such as thrust zones, folded rock sequences, shear zones, rock cover, in-situ tensions, water ingress, gas ingress, geothermal gradient, and significant seismicity all present difficulties during digging. These difficulties have a substantial influence on the routine functioning of the tunnel as well as traffic safety. To address these issues, the authors recommended using ANNs from many elements of tunnel engineering. The new Austrian tunneling technique (NATM) has shown to be a highly affordable and versatile mode of construction, and as a result, it has become the most common tunneling construction method utilized in the building of the double-arched tunnel. In this work, the MATLAB program was utilized to generate the results, which comprised training and testing datasets. The experimental results demonstrate that the suggested model's values for R2, Bias, Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE), with training data are 18.56, 0.98, 1.05, and 0.08, respectively. The suggested RMSE, R2, Bias, and MAPE values for the test dataset were 19.89, 0.98, 1.05, and 0.09. https://revistas.udes.edu.co/aibi/article/view/3631new austrian tunnelling techniqueroot mean squared errorartificial neural networktunnelmean absolute percentage error |
| spellingShingle | Shubham Kanojiya Gopal Krishna Mehta Comprehensive deformation study in the new Austrian tunneling technique tunnel utilising artificial neural network model AiBi Revista de Investigación, Administración e Ingeniería new austrian tunnelling technique root mean squared error artificial neural network tunnel mean absolute percentage error |
| title | Comprehensive deformation study in the new Austrian tunneling technique tunnel utilising artificial neural network model |
| title_full | Comprehensive deformation study in the new Austrian tunneling technique tunnel utilising artificial neural network model |
| title_fullStr | Comprehensive deformation study in the new Austrian tunneling technique tunnel utilising artificial neural network model |
| title_full_unstemmed | Comprehensive deformation study in the new Austrian tunneling technique tunnel utilising artificial neural network model |
| title_short | Comprehensive deformation study in the new Austrian tunneling technique tunnel utilising artificial neural network model |
| title_sort | comprehensive deformation study in the new austrian tunneling technique tunnel utilising artificial neural network model |
| topic | new austrian tunnelling technique root mean squared error artificial neural network tunnel mean absolute percentage error |
| url | https://revistas.udes.edu.co/aibi/article/view/3631 |
| work_keys_str_mv | AT shubhamkanojiya comprehensivedeformationstudyinthenewaustriantunnelingtechniquetunnelutilisingartificialneuralnetworkmodel AT gopalkrishnamehta comprehensivedeformationstudyinthenewaustriantunnelingtechniquetunnelutilisingartificialneuralnetworkmodel |