A data-driven approach for linear and nonlinear damage detection using variational mode decomposition and GARCH model

In this article, an original data-driven approach is proposed to detect both linear and nonlinear damage in structures using output-only responses. The method deploys variational mode decomposition (VMD) generalized autoregressive conditional heteroscedasticity (GARCH) model for signal processing feature extraction. To end, VMD decomposes the response signals that are first decomposed intrinsic functions (IMFs), then, GARCH utilized represent statistics of IMFs. coefficients’ IMFs construct primary vector. Kernel-based principal component analysis (PCA) discriminant (LDA) reduce redundancy from features by mapping them new space. informative then fed separately into three supervised classifiers: support vector machine (SVM), k-nearest neighbor (kNN), fine tree. performance evaluated on two experimental scaled models terms assessment. Kurtosis ARCH tests proved compatibility model. results demonstrate technique reaches accuracy 100% 98.82% classifying damage, respectively. Also, its higher than 80% presence noise with a signal-to-noise ratio (SNR) more 10 dB.