Combined neural network and reduced FRF techniques for slight damage detection using measured response data

Abstract

This paper deals with structural damage detection using measured frequency response functions (FRF) as input data to arti®cial neural networks (ANN). A major obstacle, the impracticality of using full-size FRF data with ANNs, was circumvented by applying a datareduction technique based on principal component analysis (PCA). The compressed FRFs, represented by their projection onto the most signi®cant principal components, were used as the ANN input variables instead of the raw FRF data. The output is a prediction of the actual state of the specimen, i.e. healthy or damaged. A further advantage of this particular approach is its ability to deal with relatively high measurement noise, which is a common occurrence when dealing with industrial structures. The methodology was applied to detect three different states of a space antenna: reference, slight mass damage and slight stiffness damage. About 600 FRF measurements, each with 1024 spectral points, were included in the analysis. Six 2-hidden layer networks, each with an individually-optimised architecture for a speci®c FRF reduction level, were used for damage detection. The results showed that it was possible to distinguish between the three states of the antenna with good accuracy, subject to using an adequate number of principal components together with a suitable neural network con®guration. It was also found that the quality of the raw FRF data remained a major consideration, though the method was able to ®lter out some of the measurement noise. The convergence and detection properties of the networks were improved signi®cantly by removing those FRFs associated with measurement errors.

Damage identification in plate-like structure using mode shape derivatives

“…(9) and (10), respectively. N is the number of elements of the structure and E j is the eigenvalue of the system corresponding to jth mode.…”

Damage detection by statistical analysis of vibration signature

“…It can be viewed as a statistical technique for data compression and information extraction, which has wide application in the fields of image compression, time-series analysis and pattern recognition, etc [11][12][13]. PCA application to structural dynamics has received considerable attentions in recent years [14][15][16][17]. Hasselman and Anderson [15] developed a frequency-domain tool for vibro-acoustic response predictions over a wide frequency range by principal component analysis.…”

Multi-source information fusion applied to structural damage diagnosis

“…Therefore, damage identification methods, based on modal strain energy (Shi et al 1998), modal curvature (Dutta and Talukdar 2004), flexibility (Catbas et al 2004) and the ratio of frequency variety squared, were put forward by researchers. On the other hand, wavelet analysis (Sun andChang 2002, Ding et al 2008b), artificial neural networks (Zang and Imregun 2004), genetic algorithms (Goldberg 1989) and statistics (Fasel et al 2005) have yet been applied to detecting structural damage by transforming modal parameters and dynamic responses. Sohn et al (2003) summarised comprehensive historic developments of damage identification methodologies and pointed out their applicabilities and potential limitations.…”