Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Efficient seismic fragility analysis method utilizing ground motion clustering and probabilistic machine learning
https://orcid.org/0000-0003-0374-0066
https://orcid.org/0000-0002-9702-8186
https://orcid.org/0000-0002-1374-0732
Highlights An integrated ground motion clustering and probabilistic ML framework is proposed for structural fragility analysis. To demonstrate the proposed framework, a 3-span, 6-storey reinforced concrete frame system is studied. The ground motion clustering base on time series K-means algorithm effectively reduces the prediction variability. The probabilistic ML method is capable of simplifying the acquisition process of seismic fragility curves.
Abstract Machine learning (ML) techniques have been recently adopted in engineering practice to define the relationship between seismic intensity measure (IM) and structural damage measure (DM) based on a limited set of numerical simulations. However, they only offer deterministic prediction, which failing to reflect the aleatoric uncertainty related to input variables (e.g. seismic excitation and structural properties) and the epistemic uncertainty associated with modeling. This paper proposes a probabilistic ML method combined with ground motion clustering for seismic fragility analysis of structures. In the probabilistic ML method, by the natural gradient boosting (NGBoost), the conditional probability distribution can be evaluated for each structural response instead of producing point estimation. In addition, ground motion clustering is based on the time series K-means, which can capture the hidden features and select the representative subset of ground motions. The proposed framework was implemented for seismic fragility analysis of a typical 3-span, 6-storey reinforced concrete (RC) frame system. Analysis results indicated that the point estimation accuracy of the NGBoost was comparable to that based on excellent deterministic ML techniques, e.g. artificial neural network (ANN), random forest (RF), extreme gradient boosting (XGBoost). Moreover, the probabilistic prediction can efficiently provide the conditional probability of exceeding a damaged state in the structure given an IM level, eliminating the need for additional input of uncertainties from structural properties in traditional ML methods. Ultimately, the cluster-based ground motion selection reduced the model uncertainty and improves the prediction accuracy of the probabilistic ML model.
Efficient seismic fragility analysis method utilizing ground motion clustering and probabilistic machine learning
https://orcid.org/0000-0003-0374-0066
https://orcid.org/0000-0002-9702-8186
https://orcid.org/0000-0002-1374-0732
Highlights An integrated ground motion clustering and probabilistic ML framework is proposed for structural fragility analysis. To demonstrate the proposed framework, a 3-span, 6-storey reinforced concrete frame system is studied. The ground motion clustering base on time series K-means algorithm effectively reduces the prediction variability. The probabilistic ML method is capable of simplifying the acquisition process of seismic fragility curves.
Abstract Machine learning (ML) techniques have been recently adopted in engineering practice to define the relationship between seismic intensity measure (IM) and structural damage measure (DM) based on a limited set of numerical simulations. However, they only offer deterministic prediction, which failing to reflect the aleatoric uncertainty related to input variables (e.g. seismic excitation and structural properties) and the epistemic uncertainty associated with modeling. This paper proposes a probabilistic ML method combined with ground motion clustering for seismic fragility analysis of structures. In the probabilistic ML method, by the natural gradient boosting (NGBoost), the conditional probability distribution can be evaluated for each structural response instead of producing point estimation. In addition, ground motion clustering is based on the time series K-means, which can capture the hidden features and select the representative subset of ground motions. The proposed framework was implemented for seismic fragility analysis of a typical 3-span, 6-storey reinforced concrete (RC) frame system. Analysis results indicated that the point estimation accuracy of the NGBoost was comparable to that based on excellent deterministic ML techniques, e.g. artificial neural network (ANN), random forest (RF), extreme gradient boosting (XGBoost). Moreover, the probabilistic prediction can efficiently provide the conditional probability of exceeding a damaged state in the structure given an IM level, eliminating the need for additional input of uncertainties from structural properties in traditional ML methods. Ultimately, the cluster-based ground motion selection reduced the model uncertainty and improves the prediction accuracy of the probabilistic ML model.
Efficient seismic fragility analysis method utilizing ground motion clustering and probabilistic machine learning
https://orcid.org/0000-0003-0374-0066
https://orcid.org/0000-0002-9702-8186
https://orcid.org/0000-0002-1374-0732
Highlights An integrated ground motion clustering and probabilistic ML framework is proposed for structural fragility analysis. To demonstrate the proposed framework, a 3-span, 6-storey reinforced concrete frame system is studied. The ground motion clustering base on time series K-means algorithm effectively reduces the prediction variability. The probabilistic ML method is capable of simplifying the acquisition process of seismic fragility curves.
Abstract Machine learning (ML) techniques have been recently adopted in engineering practice to define the relationship between seismic intensity measure (IM) and structural damage measure (DM) based on a limited set of numerical simulations. However, they only offer deterministic prediction, which failing to reflect the aleatoric uncertainty related to input variables (e.g. seismic excitation and structural properties) and the epistemic uncertainty associated with modeling. This paper proposes a probabilistic ML method combined with ground motion clustering for seismic fragility analysis of structures. In the probabilistic ML method, by the natural gradient boosting (NGBoost), the conditional probability distribution can be evaluated for each structural response instead of producing point estimation. In addition, ground motion clustering is based on the time series K-means, which can capture the hidden features and select the representative subset of ground motions. The proposed framework was implemented for seismic fragility analysis of a typical 3-span, 6-storey reinforced concrete (RC) frame system. Analysis results indicated that the point estimation accuracy of the NGBoost was comparable to that based on excellent deterministic ML techniques, e.g. artificial neural network (ANN), random forest (RF), extreme gradient boosting (XGBoost). Moreover, the probabilistic prediction can efficiently provide the conditional probability of exceeding a damaged state in the structure given an IM level, eliminating the need for additional input of uncertainties from structural properties in traditional ML methods. Ultimately, the cluster-based ground motion selection reduced the model uncertainty and improves the prediction accuracy of the probabilistic ML model.
Efficient seismic fragility analysis method utilizing ground motion clustering and probabilistic machine learning
Ding, Jia-Yi (Autor:in) / Feng, De-Cheng (Autor:in) / Brunesi, Emanuele (Autor:in) / Parisi, Fulvio (Autor:in) / Wu, Gang (Autor:in)
Engineering Structures ; 294
04.08.2023
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Seismic fragility analysis , Probabilistic prediction , Natural gradient boosting , Time series clustering , Ground motion selection , ANN , Artificial neural network , CD , Curvature ductility , CRPS , Continuous ranked probability score , DM , Damage measure , DT , Decision tree , EDP , Engineering demand parameter , <italic>EPA</italic> , Effective peak acceleration , GBoost , Gradient boosting , GMR , Ground motion record , IDA , Incremental dynamic analysis , IM , Intensity measure , LHS , Latin hypercube sampling , <italic>MAE</italic> , Mean absolute error , <italic>MARE</italic> , Mean absolute relative error , MCS , Monte Carlo simulation , MIDR , Maximum inter-story drift ratio , ML , Machine learning , MLE , Maximum likelihood estimation , MSA , Multi-stripe analysis , NGBoost , <italic>PGA</italic> , Peak ground acceleration , <italic>PGV</italic> , Peak ground velocity , <italic>R</italic> <sup>2</sup> , Coefficient of determination , RC , Reinforced concrete , RF , Random forest , <italic>RMSE</italic> , Root mean squared error , RV , Random variable , <italic>ASI</italic> , Acceleration spectral intensity , <italic>Sa</italic>(<italic>T</italic> <inf>1</inf>) , Spectral acceleration at fundamental period (<italic>T</italic> <inf>1</inf>) with 5% damping ratio , SVM , Support vector machines , TK-means , Time series K-means , XGBoost , Extreme gradient boosting