Premium
Surrogate Modelling for Real‐time Predictions of Mechanised Tunnelling Processes with Interval Data
Author(s) -
Freitag Steffen,
Cao BaTrung,
Meschke Günther
Publication year - 2016
Publication title -
pamm
Language(s) - English
Resource type - Journals
ISSN - 1617-7061
DOI - 10.1002/pamm.201610010
Subject(s) - surrogate model , interval (graph theory) , computation , settlement (finance) , artificial neural network , midpoint , quantum tunnelling , finite element method , computer science , field (mathematics) , algorithm , engineering , mathematics , artificial intelligence , structural engineering , machine learning , physics , geometry , optoelectronics , combinatorics , world wide web , payment , pure mathematics
Finite element simulations are commonly used to investigate the soil‐structure interactions of mechanised tunnelling processes, such as to provide predictions on the expected surface settlement field. For real‐time predictions during the tunnel construction, the finite element model is substituted by a hybrid surrogate model combining Artificial Neural Network and Proper Orthogonal Decomposition approaches. The surrogate model is employed to predict time‐variant interval surface settlement fields for selected scenarios of the tunnelling process steering parameters in real‐time considering uncertain geotechnical parameters as intervals. For this purpose, the surrogate model in [1], which is based on a Recurrent Neural Network and Gappy Proper Orthogonal Decomposition technique, is split into surrogate models for midpoint and radius computations of the interval data. The online computation time of the new surrogate modelling approach is only a few seconds, which enables tu apply it for real‐time predictions and to support the Tunnel Boring Machine steering. (© 2016 Wiley‐VCH Verlag GmbH & Co. KGaA, Weinheim)