Robust and reliable metamodels for mechanized tunnel simulations

Model validation and calibration via back analysis for mechanized tunnel simulations – The Western Scheldt tunnel case

“…Proper Orthogonal Decomposition (POD) combined with Radial Basis Function (RBF) has been employed to construct the meta-model. By using the similar approach introduced in [33], 200 sample points from the design space of input parameters are generated using Latin Hypercube Sampling (LHS) technique. After that, the corresponding outputs which are related to the vertical displacement at the selected observation points are computed directly by FE-model.…”

A hybrid RNN-GPOD surrogate model for real-time settlement predictions in mechanised tunnelling

“…This concept is capable of improving the prediction capability of the surrogate model by combining the effectiveness of the RBF and the flexibility of non-RBF approaches. This leads to a POD-ERBF network which has been shown to produce better prediction results as compared to the POD-RBF, see [8]. In association with the POD-ERBF algorithm, the reconstruction accuracy of the GPOD approach can be enhanced by adopting iterative schemes (IGPOD) to derive the POD basis, e.g., [9][10][11][12].…”

Probabilistic Analysis of a Rock Salt Cavern with Application to Energy Storage Systems

“…In this dissertation, Proper Orthogonal Decomposition (POD) combined with Radial Basis Functions (RBF) is employed in the sensitivity analysis of a rock salt cavern to evaluate the corresponding system responses. This technique is proposed by Buljak (2010), for more details about the approach and its implementation process see Khaledi et al (2014).…”