A machine-learning method for deriving state-dependent fragility curves of existing steel moment frames with masonry infills. (1st February 2023)

• Record Type: Journal Article
• Authors: Wu, Jing-Ren; Di Sarno, Luigi
• Is Part Of: Engineering structures. Volume 276(2023)
• Publication Date: 2023-02-01
• Subjects: Neural networks -- Existing steel frames -- Masonry infills -- Fragility curves; Structural engineering -- Periodicals; Structural analysis (Engineering) -- Periodicals; Construction, Technique de la -- Périodiques; Génie parasismique -- Périodiques; Pression du vent -- Périodiques; Earthquake engineering; Structural engineering; Wind-pressure; Periodicals; 624.105
• DOI: 10.1016/j.engstruct.2022.115345
• Languages: English
• ISSNs: 0141-0296

Abstract

Graphical abstract: Highlights: A machine learning-based framework for deriving state-dependent fragility curves for existing steel moment frames was presented. Feedforward neural network classification models were utilised to predict the damage state of existing steel frames with respect to prescribed limit states. The influence of masonry infills on the seismic response of existing steel moment frame was considered. Four Pre-Northridge steel frames covering low- and med-rise buildings designed for low and high seismicity were adopted to demonstrated the proposed framework. Abstract: Seismic assessment of existing buildings is usually a building-specific task that relies on refined finite element models. Such a task may require considerable computational demand, especially when predicting the seismic fragility of existing buildings under the framework of performance-based earthquake engineering. However, the computational cost can be significantly reduced by replacing the finite element model with a well-trained machine learning-based model, for example, an artificial neural network model. This paper presents the application of feedforward neural networks to derive the state-dependent fragility curves of existing steel moment frames, taking into account the effects of masonry infills. The network models can be trained to predict explicitly whether a structure exceeds the target limit state based on representative intensity measures of ground motions, which is in nature a binary classification problem. The number of non-linear time-history analysis required to generate the training data for the network models tends to be significantly lower compared to the case of conventional incremental dynamic analysis, particularly when a great number of ground motions are adopted aiming at higher accuracy of the fragility curves.