TY - GEN
T1 - Physics-Informed Neural Network for Nonlinear Structural System Identification
AU - Liu, Tong
AU - Meidani, Hadi
N1 - This material is based in part upon work supported by the National Science Foundation under Grant No. CMMI-1752302 and USDOT under Grant No. 69A3551747105.
PY - 2023
Y1 - 2023
N2 - Structural system identification is a critical task in resilience assessments, especially following a natural hazard. In this paper, we propose PIDynNet, a novel physics-informed approach that produces an ordinary differential equation-constrained neural network model for structural system identification. PIDynNet improves the estimation of structural parameters of nonlinear structural systems by embedding an auxiliary physics-based loss term into the overall loss function as well as a supervised data-driven loss term. The proposed framework has the generalization capability to predict nonlinear structural response given unseen ground excitations. Two nonlinear numerical experiments are conducted to demonstrate the advantage of PIDynNet over other identification methods in problems with or without latent variables.
AB - Structural system identification is a critical task in resilience assessments, especially following a natural hazard. In this paper, we propose PIDynNet, a novel physics-informed approach that produces an ordinary differential equation-constrained neural network model for structural system identification. PIDynNet improves the estimation of structural parameters of nonlinear structural systems by embedding an auxiliary physics-based loss term into the overall loss function as well as a supervised data-driven loss term. The proposed framework has the generalization capability to predict nonlinear structural response given unseen ground excitations. Two nonlinear numerical experiments are conducted to demonstrate the advantage of PIDynNet over other identification methods in problems with or without latent variables.
UR - http://www.scopus.com/inward/record.url?scp=85182261821&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85182261821&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85182261821
T3 - Structural Health Monitoring 2023: Designing SHM for Sustainability, Maintainability, and Reliability - Proceedings of the 14th International Workshop on Structural Health Monitoring
SP - 3001
EP - 3011
BT - Structural Health Monitoring 2023
A2 - Farhangdoust, Saman
A2 - Guemes, Alfredo
A2 - Chang, Fu-Kuo
PB - DEStech Publications
T2 - 14th International Workshop on Structural Health Monitoring: Designing SHM for Sustainability, Maintainability, and Reliability, IWSHM 2023
Y2 - 12 September 2023 through 14 September 2023
ER -