Neural-network-based modeling of structural parametric evaluation with dynamic responses in time domain

Abstract

A neural networks based modeling of structural parametric identification strategy with the direct use of dynamic measurements in time domain is developed. Without any eigenvalue analysis, the structural parameter of stiffness and Rayleigh damping coefficients can be identified simultaneously. A shear frame structural model with known mass distribution is considered as an object structure. First a reference structure with assumed structural parameters is chosen. The assumed reference structure has the same degree of freedoms and topology with the object structure. An emulator neural network is constructed and trained to identify the reference structure by the use of dynamic measurements under dynamic excitation. The trained emulator neural network can be used to forecast dynamic measurements of the reference structure with enough precision and decide the difference between the dynamic measurements of other assumed structure with different structural parameters and those of the reference structure. The root mean square (RMS) error vector is presented to evaluate the difference. Subsequently, corresponding to each assumed structure with different structural parameters, the RMS error vector can be calculated. By using the training data sets composed of the structural parameters and the corresponding RMS error vector, a parametric evaluation neural network is trained for the purpose of forecasting the structural stiffness and the Rayleigh damping coefficients.