A long short-term memory based deep learning algorithm for seismic response uncertainty quantification. (January 2022)

• Record Type: Journal Article
• Authors: Kundu, Anirban; Ghosh, Swarup; Chakraborty, Subrata
• Is Part Of: Probabilistic engineering mechanics. Volume 67(2022)
• Publication Date: 2022-01
• Subjects: Nonlinear seismic response -- Parameter uncertainty -- Reliability -- Deep learning -- Long short-term memory; Engineering -- Statistical methods -- Periodicals; Mechanics, Applied -- Statistical methods -- Periodicals; Probabilities -- Periodicals; Ingénierie -- Méthodes statistiques -- Périodiques; Mécanique appliquée -- Méthodes statistiques -- Périodiques; Probabilités -- Périodiques; 620.100727
• DOI: 10.1016/j.probengmech.2021.103189
• Languages: English
• ISSNs: 0266-8920

Abstract

Abstract: The application of metamodeling technique to overcome computational challenge of Monte Carlo simulation (MCS) technique for response uncertainty quantification under stochastic earthquake load is a difficult task due to the high-dimensional nature of stochastic load. Recent developments in the sequential models for forecasting and prediction have opened a new avenue in this regard. Various deep learning algorithms, particularly the convolutional neural network and recurrent neural network are quite suitable for response uncertainty quantification of nonlinear stochastic dynamic system. However, most of the existing studies consider stochastic load as the only source of uncertainty assuming the parameters characterizing a structure as deterministic. The present study proposes a long short-term memory (LSTM) based deep learning algorithm for seismic response uncertainty quantification by duly addressing both the stochastic nature of dynamic load and structural system parameter uncertainty. The functional application program interface feature of Keras that allows layers sharing to form more complex model is explored to form a response approximation model. It incorporates more than one input source i.e., stochastic dynamic excitation sequence as well as structural system parameter uncertainty. The proposed algorithm is elucidated through two numerical examples i.e., a proof-of-concept example and one realistic structural engineering problem by considering the direct MCS based results as the benchmark. The results of accuracy matrices, regression analysis results, comparison of seismic response statistics and reliability results with the results of direct MCS technique clearly revealed the enhanced prediction capability of the proposed LSTM model. Highlights: A long short term memory based deep learning algorithm for seismic response uncertainty quantification. Duly address both the stochastic nature of dynamic load and system parameter uncertainty. Exploits functional API feature of Keras for layers sharing to form more complex response approximation model. Effectiveness elucidated numerically considering the direct MCS based results as the benchmark.