Element level parametric identification using axial macro-strain time series

The increasing use of advanced sensing technologies for strain measurements necessitates the development of strain-based identification methodologies. In this study, a three-step neural network strategy, called direct soft parametric identification (DSPI), is presented to identify the member stiffness and damping parameters of a truss structure directly from free vibration-induced strains. The rationality of the proposed methodology is explained and the theory basis for the construction of strain-based emulator neural network(SENN) and parametric evaluation neural network(PENN) are described according to the discrete time solution of the state space equation of structural free vibration. The performance of the proposed strategy is examined.