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

被引：18
作者：
Erharter G.H. [1 ,2 ]
Marcher T. [1 ]
Reinhold C. [3 ]
机构：
[1] Graz University of Technology, Institute of Rock Mechanics and Tunnelling, Rechbauerstraße 12, Graz
[2] geo.zt gmbh poscher beratende geologen, Saline 17, Hall in Tirol
[3] BBT SE, Handlhofweg 82, Innsbruck
来源：
Geomechanik und Tunnelbau | 2019年 / 12卷 / 05期
关键词：
Artificial Intelligence; automatic classification; Engineering geology; malicious use; Mechanised tunnelling; Reconnaissance;
D O I：
10.1002/geot.201900027
中图分类号：
学科分类号：
摘要：
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. © 2019 Ernst & Sohn Verlag für Architektur und technische Wissenschaften GmbH & Co. KG, Berlin
引用
收藏
页码：472 / 477
页数：5
相关论文
共 17 条
  • [1] Bergmeister K., Reinhold C., earning and optimization from the exploratory tunnel – Brenner Base Tunnel / Lernen und Optimieren vom Erkundungsstollen – Brenner Basistunnel, Geomechanics and Tunnelling, 10, 5, pp. 467-476, (2017)
  • [2] Reinhold C., Schwarz C., Bergmeister K., Development of holistic prognosis models using exploration techniques and seismic prediction / Die Entwicklung holistischer Prognosemodelle mit Vorauserkundungen und seismischen Messungen, Geomechanics and Tunnelling, 10, 6, pp. 767-778, (2017)
  • [3] Alimoradi A., Et al., Prediction of geological hazardous zones in front of a tunnel face using TSP-203 and artificial neural networks, Tunnelling and Underground Space Technology, 23, 6, pp. 711-717, (2008)
  • [4] Zhang Q., Liu Z., Tan J., Prediction of geological conditions for a tunnel boring machine using big operational data, Automation in Construction, 100, pp. 73-83, (2019)
  • [5] Amodei D., Et al., Concrete Problems in AI Safety, (2016)
  • [6] Brundage M., Et al., The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation, (2018)
  • [7] Erharter G.H., Marcher T., Reinhold C., Comparison of artificial neural networks for TBM data classification, (2019)
  • [8] Erharter G.H., Marcher T., Reinhold C., Artificial Neural Network based Online Rockmass Behavior Classification of TBM Data, (2019)
  • [9] Radoncic N., Hein M., Moritz B., Determination of the system behaviour based on data analysis of a hard rock shield TBM / Analyse der Maschinenparameter zur Erfassung des Systemverhaltens beim Hartgesteins-Schildvortrieb, Geomechanics and Tunnelling, 7, 5, pp. 565-576, (2014)
  • [10] Mahalanobis P.C., On the generalized distance in statistics, pp. 49-55, (1936)
12