An intelligent structural damage detection approach based on self-powered wireless sensor data

This study presents the results of an ongoing research project conducted by the U.S. Federal Highway Administration (FHWA) on developing an intelligent approach for structural damage detection. The proposed approach is established upon the simulation of the compressed data stored in memory chips of a newly developed self powered wireless sensor. An innovative data interpretation system integrating finite element method (FEM) and probabilistic neural network (PNN) based on Bayesian decision theory is developed for damage detection. Several features extracted from the cumulative limited static strain data are used as damage indicator variables. Another contribution of this paper is to define indicator variables that simultaneously take into account the effect of array of sensors. The performance of the proposed approach is first evaluated for the case of a simply supported beam under three-point bending. Then, the efficiency of the method is tested for the complicated case of a bridge gusset plate. The beam and gusset plate structures are analyzed as 3D FE models. The static strain data from the FE simulations for different damage scenarios is used to calibrate the sensor-specific data interpretation algorithm. The viability and repeatability of the method is demonstrated by conducting a number of simulations. Furthermore, a general scheme is presented for finding the optimal number of data acquisition points (sensors) on the structure and the associated optimal locations. An uncertainty analysis is performed through the contamination of the damage indicator features with different Gaussian noise levels. (C) 2015 Elsevier B.V. All rights reserved.