Towards the integration of smart techniques for tunnel seismic applications

被引：0

作者：

Dickmann T. ^{[1
]}

Hecht-Méndez J. ^{[1
]}

Krüger D. ^{[1
]}

Sapronova A. ^{[2
]}

Unterlaß P.J. ^{[2
]}

Marcher T. ^{[2
]}

机构：

[1] Amberg Technologies AG, Trockenloostrasse 21, Regensdorf

[2] Graz University of Technology, Institute of Rock Mechanics and Tunnelling, Rechbauerstraße 12, Graz

来源：

Geomechanik und Tunnelbau | 2021年 / 14卷 / 05期

关键词：

geological forecast; Geology; Geophysics; Innovative procedures/test techniques; machine learning; Rock mechanics; tunnel seismic prediction; wireless solutions;

D O I：

10.1002/geot.202100046

中图分类号：

学科分类号：

摘要：

Applications of seismic measurements for the prediction of hazard zones are applied practice in many tunnel drives in rock mass today. Next to a large exploration range and accurate localisation of discontinuities, seismic data provide attributes for a comprehensive characterisation of the ground conditions. A good synchronisation of all technical components is required to obtain optimum data quality and quantity while the tunnel excavation is not obstructed thereby. Firstly, the signal source must feed as much energy as possible into the rock in a very short time. Secondly, continuity of the signal generation with constant quality and its precise timing by means of wireless data transmission also ensure a reliable measurement process. Artificial intelligence is used to determine the quality of the recorded data already in the tunnel and feedback is given to the user keeping the data quality high. From the tunnel site, recorded raw data can be transferred to a cloud, from where an authorised processor collects them, wherever in the world. An immediately started data processing delivers a result within an hour that includes a geological forecast of up to 150 m of heading, depending on the rock mass condition. In addition to data quality, the quality of the results is crucial. Therefore, techniques are currently under development using machine learning to correlate and analyse seismic attributes with geological properties. This should lead to a more objective evaluation of the geological forecast in the future. © 2021 Ernst & Sohn Verlag für Architektur und technische Wissenschaften GmbH & Co. KG, Berlin.

引用

页码：609 / 615

页数：6

共 5 条

[1]

Dickmann T., Sander B.K., Drivage concurrent Tunnel Seismic Prediction (TSP), Felsbau, 14, 6, pp. 406-411, (1996)

[2]

Ghahramani Z., Unsupervised Learning in Bousquet, Advanced Lectures on Machine Learning, 3176, (2004)

[3]

Frederix K., Van Barel M., Sparse spectral clustering method based on the incomplete Cholesky decomposition, Journal of Computational and Applied Mathematics, 237, pp. 145-161, (2013)

[4]

Li Z., Liu J., Yang Y., Zhou X., Lu H., Clustering-Guided Sparse Structural Learning for Unsupervised Feature Selection, IEEE Transactions on Knowledge and Data Engineering, 26, 9, pp. 2138-2150, (2014)

[5]

Witten D.M., Tibshirani R., A framework for feature selection in clustering, J. Am Stat Assoc., 105, 490, pp. 713-726, (2010)

← 1 →