Damage Detection Using Principal Component Analysis Based on Wavelet Ridges

TL;DR: In this article, a combination of principal component analysis (PCA) and wavelet transform (WT) was used for damage detection in an aluminum beam with piezoelectric transducers.

Abstract: Principal Component Analysis (PCA) and Wavelet Transform (WT) aretwo well-known signal processing tools that are widely used indifferent fields. PCA playsa vital role in statistical analysis as a dimensional reduction tool. Besides, WT has proven its abilityto overcome many of the limitation of the others among various time-frequencyanalyzers. The present work attempts to use the properties and advantagesof both methodologies together in damage detection. To achieve thisaim, PCA is applied on ridges of wavelet transform of measured signalsfrom the structure. The results show that the proposed combination improvesthe accuracy of detection comparing with PCA damage detection basedon original data captured from sensors. According to the result, when PCA uses the ridges of transformed data, theidentifications of damages are more clear and accurate. This work involvesexperiments with an aluminum beam using piezoelectrictransducers as sensors and actuators. Damages are introduced intothe structure as a cut in several steps enlarging the depthof cut.