Application of artificial neural networks for Underground construction – Chances and challenges: Insights from the BBT exploratory tunnel Ahrental Pfons

Publikation: Beitrag in einer FachzeitschriftArtikelForschungBegutachtung

Abstract

The interaction of tunnel boring machines with the rock mass is highly influenced by human, technical and geological factors. Interpretation of geological observations and TBM data is currently done on a subjective basis. Technologies based on Artificial Intelligence research, can be used to automatically classify TBM data into rock mass behaviour types. Albeit first results look promising, any technology poses the threat of malicious use that deliberately harms / benefits one or another party. This paper shows how an Artificial Neural Network (ANN) can be trained to achieve the best possible rock mass behaviour classification, or how such a system can be misused to yield a more optimistic, respectively pessimistic classification to fortify the interests of one party. However, ANN also pose the chance to serve as an independent objective opinion and to improve the self‐consistency of geological classifications.
Originalspracheenglisch
Seiten (von - bis)472-477
Seitenumfang6
FachzeitschriftGeomechanics and Tunnelling
Jahrgang12
Ausgabenummer5
DOIs
PublikationsstatusVeröffentlicht - Okt 2019

Fingerprint

underground construction
TBM
artificial neural network
Tunnels
tunnel
Rocks
Neural networks
rock
artificial intelligence
Artificial intelligence

Dies zitieren

Application of artificial neural networks for Underground construction – Chances and challenges : Insights from the BBT exploratory tunnel Ahrental Pfons. / Erharter, Georg Hermann; Marcher, Thomas; Reinhold, Chris.

in: Geomechanics and Tunnelling , Jahrgang 12, Nr. 5, 10.2019, S. 472-477.

Publikation: Beitrag in einer FachzeitschriftArtikelForschungBegutachtung

@article{1b9226cb4c6745cd9723d1706fe4e439,
title = "Application of artificial neural networks for Underground construction – Chances and challenges: Insights from the BBT exploratory tunnel Ahrental Pfons",
abstract = "The interaction of tunnel boring machines with the rock mass is highly influenced by human, technical and geological factors. Interpretation of geological observations and TBM data is currently done on a subjective basis. Technologies based on Artificial Intelligence research, can be used to automatically classify TBM data into rock mass behaviour types. Albeit first results look promising, any technology poses the threat of malicious use that deliberately harms / benefits one or another party. This paper shows how an Artificial Neural Network (ANN) can be trained to achieve the best possible rock mass behaviour classification, or how such a system can be misused to yield a more optimistic, respectively pessimistic classification to fortify the interests of one party. However, ANN also pose the chance to serve as an independent objective opinion and to improve the self‐consistency of geological classifications.",
author = "Erharter, {Georg Hermann} and Thomas Marcher and Chris Reinhold",
year = "2019",
month = "10",
doi = "10.1002/geot.201900027",
language = "English",
volume = "12",
pages = "472--477",
journal = "Geomechanics and Tunnelling",
issn = "1865-7362",
publisher = "Ernst & Sohn",
number = "5",

}

TY - JOUR

T1 - Application of artificial neural networks for Underground construction – Chances and challenges

T2 - Insights from the BBT exploratory tunnel Ahrental Pfons

AU - Erharter, Georg Hermann

AU - Marcher, Thomas

AU - Reinhold, Chris

PY - 2019/10

Y1 - 2019/10

N2 - The interaction of tunnel boring machines with the rock mass is highly influenced by human, technical and geological factors. Interpretation of geological observations and TBM data is currently done on a subjective basis. Technologies based on Artificial Intelligence research, can be used to automatically classify TBM data into rock mass behaviour types. Albeit first results look promising, any technology poses the threat of malicious use that deliberately harms / benefits one or another party. This paper shows how an Artificial Neural Network (ANN) can be trained to achieve the best possible rock mass behaviour classification, or how such a system can be misused to yield a more optimistic, respectively pessimistic classification to fortify the interests of one party. However, ANN also pose the chance to serve as an independent objective opinion and to improve the self‐consistency of geological classifications.

AB - The interaction of tunnel boring machines with the rock mass is highly influenced by human, technical and geological factors. Interpretation of geological observations and TBM data is currently done on a subjective basis. Technologies based on Artificial Intelligence research, can be used to automatically classify TBM data into rock mass behaviour types. Albeit first results look promising, any technology poses the threat of malicious use that deliberately harms / benefits one or another party. This paper shows how an Artificial Neural Network (ANN) can be trained to achieve the best possible rock mass behaviour classification, or how such a system can be misused to yield a more optimistic, respectively pessimistic classification to fortify the interests of one party. However, ANN also pose the chance to serve as an independent objective opinion and to improve the self‐consistency of geological classifications.

U2 - 10.1002/geot.201900027

DO - 10.1002/geot.201900027

M3 - Article

VL - 12

SP - 472

EP - 477

JO - Geomechanics and Tunnelling

JF - Geomechanics and Tunnelling

SN - 1865-7362

IS - 5

ER -