Structural Health Monitoring and Damage Assessment Using Measured FRFs from Multiple Sensors, Part II: Decision Making with RBF Networks

Abstract

This paper is the second part of structural health monitoring and damag e assessment using measured FRFs from multiple sensors, discussing the decision m aking technique with radial basis function (RBF) neural networks. In PART 1 of the paper, the corre lation criteria showed their capability to indicate various changes to the structure's state. P ART 2, presented here, develops the methodology of decision theory to identify precisely all of the struc ture states. Although, the statistical approach can be used for classification, interpreting the information is difficult. Neural network techniques have been proven to possess many advantages for classif ication due to their learning ability and good generalization. In this paper, the radial bas is function neural network is applied for function approximation and recognition. The key idea is to parti tion the input space (the indicators of the correlation criteria) into a number of subspaces t hat are in the form of hyper spheres. Then, the widely used k-mean clustering algorithm was sel ected as a logical approach to detecting the structure states. A bookshelf structure with measure d frequency responses from 24 accelerometers was used to demonstrate the effectiveness of the method. The results show the successful classification of all structure states, for instanc e, the undamaged and damage states, damage locations and damage levels, and the environmental variability.