Structural Damage Detection Using Artificial Neural Networks
Abstract
Artificial neural networks are efficient computing techniques that are widely used to solve complex problems in many fields. In this study, a counterpropagation neural network is used to locate structural damage for a beam, a frame, and support movements of a beam in its axial direction. The investigation considers a variety of diagnostic parameters, including static displacements, natural frequencies, mode shapes, and other parameters based on mode shapes. The method is first demonstrated on a plane frame, based on static displacements. It is then applied to continuous beams using dynamic properties of structures. The required data are obtained through computer simulation by finite-element analysis. The results demonstrate that these parameters can be used as diagnostic parameters for artificial neural networks in structural engineering. An anticipated application to bridge monitoring is discussed.