Output-only modal analysis (OMA) is an indispensable alternative to experimental modal analysis for engineering structures while in operation. Conventional OMA often fails to identify the underlying modal structure with insufficient modal participation. Such low participation is expected when the sampled response is subjected to sensor nonlinearity or when specific modes are not well excited. A novel subband decomposition (SBD) method proposed here resolves modal parameters even with biased modal energy distribution. It isolates the system response within a narrow frequency subband through a finite-impulse-response analysis filter bank. Whenever the filter subband captures a resonance, the filtered system response is close-to-singular and contains mainly the resonant mode contribution. A modal cluster metric is defined to identify the resonant normal modes automatically. The modal parameters are identified and extracted within the subband possessing the locally maximal clustering measure. The proposed method assumes no a priori knowledge of the structure under operation other than the system should have no repeated natural frequencies. Therefore, the SBD algorithm is entirely data-driven and requires minimal user intervention. To illustrate the concept and the accuracy of the proposed SBD, numerical experiments of a linear cantilevered beam with various stationary and non-stationary loading are conducted and compared to other OMA methods. Furthermore, physical experiments on an aluminum cantilever beam examine the method's applicability in field modal testing. Compared to traditional OMA methods, the numerical and physical experiments show orders of magnitude improvement in modal identification error using the proposed SBD.

This content is only available via PDF.
You do not currently have access to this content.