Transfer Learning-Based Surrogate Modeling for Nonlinear Time-History Response Analysis of High-Fidelity Structural Models

TL;DR

This work tackles the prohibitive cost of high-fidelity NLTHA in PBEE by introducing a transfer-learning framework that learns a high-fidelity surrogate from a low-fidelity model. A novel masked neural network (MNN) architecture facilitates temporal data learning, with physics-informed loss helping nonlinear response accuracy. The approach is demonstrated on a 20-story SMF, where high-fidelity responses are predicted from as few as 20 targeted simulations, and hazard-consistent exceedance probabilities are accurately captured. The results indicate a practical pathway for efficient, probabilistic seismic risk assessment using high-fidelity models within PBEE.

Abstract

In a performance based earthquake engineering (PBEE) framework, nonlinear time-history response analysis (NLTHA) for numerous ground motions are required to assess the seismic risk of buildings or civil engineering structures. However, such numerical simulations are computationally expensive, limiting the real-world practical application of the framework. To address this issue, previous studies have used machine learning to predict the structural responses to ground motions with low computational costs. These studies typically conduct NLTHAs for a few hundreds ground motions and use the results to train and validate surrogate models. However, most of the previous studies focused on computationally-inexpensive response analysis models such as single degree of freedom. Surrogate models of high-fidelity response analysis are required to enrich the quantity and diversity of information used for damage assessment in PBEE. Notably, the computational cost of creating training and validation datasets increases if the fidelity of response analysis model becomes higher. Therefore, methods that enable surrogate modeling of high-fidelity response analysis without a large number of training samples are needed. This study proposes a framework that uses transfer learning to construct the surrogate model of a high-fidelity response analysis model. This framework uses a surrogate model of low-fidelity response analysis as the pretrained model and transfers its knowledge to construct surrogate models for high-fidelity response analysis with substantially reduced computational cost. As a case study, surrogate models that predict responses of a 20-story steel moment frame were constructed with only 20 samples as the training dataset. The responses to the ground motions predicted by constructed surrogate model were consistent with a site-specific time-based hazard.

Figures (19)

• Figure 1: Framework using transfer learning to construct surrogate models of high-fidelity response analysis models. Each dataset contains ground acceleration time-history as input and response analyses results as output.
• Figure 2: Soil parameters in ground amplification analysisAIJ2006. $V_{s}$ is seismic shear-wave velocity; $\gamma_{0.5}$ is standard shear strain; $h_{max}$ and $h_{min}$ are the maximum and minimum damping ratios; and $\rho$ is soil density.
• Figure 3: Schematic of the ground motion selection process for training and validation datasets
• Figure 4: Ground motion distributions of PGA and PGV
• Figure 5: Masked connection used in $\mathcal{M}_\mathrm{s}$ and $\mathcal{M}_\mathrm{t}$