Single input-single output identification thermal response model of bridge using nonlinear ARX with wavelet networks

Abstract

Model identification of a system can be used for a variety of purposes, including model updates, damage assessment, active control and original design evaluation. We used single input-single output (SISO) nonlinear regression with least square solution and nonlinear AutoRegresive with eXogenous inputs (NLARX) with wavelet neural networks models to identify the thermal response of a bridge under hard environmental effects and estimated the nonlinearity model parameters. Fu-Sui Bridge strain structural health monitoring measurements were used as a case study. Nonlinear regression analysis showed that the thermal response is a nonlinear effect with temperature changes; and the NLARX with wavelet network solution is capable of accurately predicting thermal response and can help with interpreting measurements from continuous bridge health monitoring systems.