Prediction of penetration rate by GRU neural network

Mechanised tunnelling projects using boring machines (TBM) are becoming widespread. Here in Singapore multiple projects are underway that expands our subterranean space. The productivity and financial viability of these projects have since become an important topic. Much research, past and ongoing,...

Full description

Saved in:
Bibliographic Details
Main Author: Leo, Kew Xun Wei
Other Authors: Zhao Zhiye
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2022
Subjects:
Online Access:https://hdl.handle.net/10356/158680
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-158680
record_format dspace
spelling sg-ntu-dr.10356-1586802022-06-06T07:25:27Z Prediction of penetration rate by GRU neural network Leo, Kew Xun Wei Zhao Zhiye School of Civil and Environmental Engineering CZZHAO@ntu.edu.sg Engineering::Civil engineering::Geotechnical Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Mechanised tunnelling projects using boring machines (TBM) are becoming widespread. Here in Singapore multiple projects are underway that expands our subterranean space. The productivity and financial viability of these projects have since become an important topic. Much research, past and ongoing, are focused on accurately predicting the penetration rate of a TBM because of its importance. Of the multitude of prediction models, neural networks showed great potential for practical use. This study proposes an approach to develop and deploy a neural network based on the Gated Recurrent Unit (GRU), a type of neural network that is suited to prediction of time-based datasets. The network model is trained and tuned for accuracy, and the mean absolute error (MAE) and root-mean squared error (RMSE) analysed to set the most optimal combinations of hyperparameters. The analysis from the results based on a case study of DTSS2 Project T10 indicates that the network model is sufficiently accurate for prediction – with MAE and RMSE at 4.63mm/min and 5.76mm/min respectively. Sensitivity analysis suggest that uniaxial compressive strength, duration of excavation, and grout volumes, are key input parameters that contribute most to the accuracy of the model. As such, there can be further studies to examine the corresponding relationships with a view on extending theoretical understanding of the kinematic behaviours and responses of a TBM during excavation. Introducing larger datasets to the network model can enhance the accuracy of the network model. Additionally, the design of the network model can be improved by incorporating theoretical frameworks to augment the hyperparameters and refine the overall performance of the network. Bachelor of Engineering (Civil) 2022-06-06T07:25:27Z 2022-06-06T07:25:27Z 2022 Final Year Project (FYP) Leo, K. X. W. (2022). Prediction of penetration rate by GRU neural network. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/158680 https://hdl.handle.net/10356/158680 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Civil engineering::Geotechnical
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
spellingShingle Engineering::Civil engineering::Geotechnical
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Leo, Kew Xun Wei
Prediction of penetration rate by GRU neural network
description Mechanised tunnelling projects using boring machines (TBM) are becoming widespread. Here in Singapore multiple projects are underway that expands our subterranean space. The productivity and financial viability of these projects have since become an important topic. Much research, past and ongoing, are focused on accurately predicting the penetration rate of a TBM because of its importance. Of the multitude of prediction models, neural networks showed great potential for practical use. This study proposes an approach to develop and deploy a neural network based on the Gated Recurrent Unit (GRU), a type of neural network that is suited to prediction of time-based datasets. The network model is trained and tuned for accuracy, and the mean absolute error (MAE) and root-mean squared error (RMSE) analysed to set the most optimal combinations of hyperparameters. The analysis from the results based on a case study of DTSS2 Project T10 indicates that the network model is sufficiently accurate for prediction – with MAE and RMSE at 4.63mm/min and 5.76mm/min respectively. Sensitivity analysis suggest that uniaxial compressive strength, duration of excavation, and grout volumes, are key input parameters that contribute most to the accuracy of the model. As such, there can be further studies to examine the corresponding relationships with a view on extending theoretical understanding of the kinematic behaviours and responses of a TBM during excavation. Introducing larger datasets to the network model can enhance the accuracy of the network model. Additionally, the design of the network model can be improved by incorporating theoretical frameworks to augment the hyperparameters and refine the overall performance of the network.
author2 Zhao Zhiye
author_facet Zhao Zhiye
Leo, Kew Xun Wei
format Final Year Project
author Leo, Kew Xun Wei
author_sort Leo, Kew Xun Wei
title Prediction of penetration rate by GRU neural network
title_short Prediction of penetration rate by GRU neural network
title_full Prediction of penetration rate by GRU neural network
title_fullStr Prediction of penetration rate by GRU neural network
title_full_unstemmed Prediction of penetration rate by GRU neural network
title_sort prediction of penetration rate by gru neural network
publisher Nanyang Technological University
publishDate 2022
url https://hdl.handle.net/10356/158680
_version_ 1735491206310264832