Comparison of artificial neural networks for TBM data classification

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandForschungBegutachtung

Abstract

The past decade has shown a rapid increase in the successful application of Machine Learning techniques for a variety of challenging tasks. Potential for this is also seen in the automatic rockmass behavior classification of tunnel boring machine (TBM) advance-data. This study compares the performance of two kinds of Artificial Neural Networks (ANN) - a Multilayer Perceptron (MLP) vs. a Long-Short-Term Memory (LSTM) Network - for this task. The data originates from the exploratory tunnel Ahrental – Pfons of the Brenner Base Tunnel which is currently under construction. The goal of gathering as much data as possible from the encountered geology is to transfer this knowledge from the exploratory tunnel to the main tunnel tubes. Results show that both ANNs are capable of classifying rockmass behavior only based on TBM advance data, however, the LSTM outperforms the MLP in several of the test-data samples.
Originalspracheenglisch
TitelRock Mechanics for Natural Resources and Infrastructure Development
UntertitelFull Papers: Proceedings of the 14th International Congress on Rock Mechanics and Rock Engineering (ISRM 2019)
Redakteure/-innenSergio A.B. da Fontoura, Ricardo Jose Rocca, José Pavón Mendoza
Herausgeber (Verlag)CRC Press
ISBN (elektronisch)9780367823177
PublikationsstatusVeröffentlicht - 2019

Fingerprint

Tunnels
Neural networks
Multilayer neural networks
Geology
Learning systems
Long short-term memory

Dies zitieren

Erharter, G. H., Marcher, T., & Reinhold, C. (2019). Comparison of artificial neural networks for TBM data classification. in S. A. B. da Fontoura, R. J. Rocca, & J. Pavón Mendoza (Hrsg.), Rock Mechanics for Natural Resources and Infrastructure Development: Full Papers: Proceedings of the 14th International Congress on Rock Mechanics and Rock Engineering (ISRM 2019) CRC Press.

Comparison of artificial neural networks for TBM data classification. / Erharter, Georg Hermann; Marcher, Thomas; Reinhold, Chris.

Rock Mechanics for Natural Resources and Infrastructure Development: Full Papers: Proceedings of the 14th International Congress on Rock Mechanics and Rock Engineering (ISRM 2019). Hrsg. / Sergio A.B. da Fontoura; Ricardo Jose Rocca; José Pavón Mendoza. CRC Press, 2019.

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandForschungBegutachtung

Erharter, GH, Marcher, T & Reinhold, C 2019, Comparison of artificial neural networks for TBM data classification. in SAB da Fontoura, RJ Rocca & J Pavón Mendoza (Hrsg.), Rock Mechanics for Natural Resources and Infrastructure Development: Full Papers: Proceedings of the 14th International Congress on Rock Mechanics and Rock Engineering (ISRM 2019). CRC Press.
Erharter GH, Marcher T, Reinhold C. Comparison of artificial neural networks for TBM data classification. in da Fontoura SAB, Rocca RJ, Pavón Mendoza J, Hrsg., Rock Mechanics for Natural Resources and Infrastructure Development: Full Papers: Proceedings of the 14th International Congress on Rock Mechanics and Rock Engineering (ISRM 2019). CRC Press. 2019
Erharter, Georg Hermann ; Marcher, Thomas ; Reinhold, Chris. / Comparison of artificial neural networks for TBM data classification. Rock Mechanics for Natural Resources and Infrastructure Development: Full Papers: Proceedings of the 14th International Congress on Rock Mechanics and Rock Engineering (ISRM 2019). Hrsg. / Sergio A.B. da Fontoura ; Ricardo Jose Rocca ; José Pavón Mendoza. CRC Press, 2019.
@inproceedings{117c89bbdfeb4f3d847c83b1246cb04c,
title = "Comparison of artificial neural networks for TBM data classification",
abstract = "The past decade has shown a rapid increase in the successful application of Machine Learning techniques for a variety of challenging tasks. Potential for this is also seen in the automatic rockmass behavior classification of tunnel boring machine (TBM) advance-data. This study compares the performance of two kinds of Artificial Neural Networks (ANN) - a Multilayer Perceptron (MLP) vs. a Long-Short-Term Memory (LSTM) Network - for this task. The data originates from the exploratory tunnel Ahrental – Pfons of the Brenner Base Tunnel which is currently under construction. The goal of gathering as much data as possible from the encountered geology is to transfer this knowledge from the exploratory tunnel to the main tunnel tubes. Results show that both ANNs are capable of classifying rockmass behavior only based on TBM advance data, however, the LSTM outperforms the MLP in several of the test-data samples.",
author = "Erharter, {Georg Hermann} and Thomas Marcher and Chris Reinhold",
year = "2019",
language = "English",
editor = "{da Fontoura}, {Sergio A.B.} and Rocca, {Ricardo Jose} and {Pav{\'o}n Mendoza}, Jos{\'e}",
booktitle = "Rock Mechanics for Natural Resources and Infrastructure Development",
publisher = "CRC Press",

}

TY - GEN

T1 - Comparison of artificial neural networks for TBM data classification

AU - Erharter, Georg Hermann

AU - Marcher, Thomas

AU - Reinhold, Chris

PY - 2019

Y1 - 2019

N2 - The past decade has shown a rapid increase in the successful application of Machine Learning techniques for a variety of challenging tasks. Potential for this is also seen in the automatic rockmass behavior classification of tunnel boring machine (TBM) advance-data. This study compares the performance of two kinds of Artificial Neural Networks (ANN) - a Multilayer Perceptron (MLP) vs. a Long-Short-Term Memory (LSTM) Network - for this task. The data originates from the exploratory tunnel Ahrental – Pfons of the Brenner Base Tunnel which is currently under construction. The goal of gathering as much data as possible from the encountered geology is to transfer this knowledge from the exploratory tunnel to the main tunnel tubes. Results show that both ANNs are capable of classifying rockmass behavior only based on TBM advance data, however, the LSTM outperforms the MLP in several of the test-data samples.

AB - The past decade has shown a rapid increase in the successful application of Machine Learning techniques for a variety of challenging tasks. Potential for this is also seen in the automatic rockmass behavior classification of tunnel boring machine (TBM) advance-data. This study compares the performance of two kinds of Artificial Neural Networks (ANN) - a Multilayer Perceptron (MLP) vs. a Long-Short-Term Memory (LSTM) Network - for this task. The data originates from the exploratory tunnel Ahrental – Pfons of the Brenner Base Tunnel which is currently under construction. The goal of gathering as much data as possible from the encountered geology is to transfer this knowledge from the exploratory tunnel to the main tunnel tubes. Results show that both ANNs are capable of classifying rockmass behavior only based on TBM advance data, however, the LSTM outperforms the MLP in several of the test-data samples.

M3 - Conference contribution

BT - Rock Mechanics for Natural Resources and Infrastructure Development

A2 - da Fontoura, Sergio A.B.

A2 - Rocca, Ricardo Jose

A2 - Pavón Mendoza, José

PB - CRC Press

ER -