Improved FRF Estimation from Noisy High-Speed Camera Data Using SEMM

Abstract

Vibration measurements with a high-speed camera are becoming a compelling alternative to accelerometers and laser vibrometers. However, estimated FRFs from the high-speed camera are usually displaying relatively high levels of noise. The noise has proven to be problematic especially in the higher frequency range, where the amplitude of the displacements are generally very small. Using the hybrid method the mode shapes can be identified even at higher frequencies, where the amplitude of the response is close to overall noise level. The identification is obtained by using eigenvalues from accelerometer in the Least Square Complex Frequency (LSCF) identification. The identified mode shapes were proven to be consistent; however, the synthesised full field FRFs after least-square frequency-domain LSFD method are erroneous, especially in the higher frequency range. In this paper the possibility of improving the estimation of full-field FRFs from noisy high-speed camera data using the System Equivalent Model Mixing (SEMM) is explored. The SEMM is normally used with a numerical model (as a parent model) with a large number of DoF which is then mixed with an experimental model which is a subset of the parent model DoF. With the proposed method the FRFs obtained from the high-speed camera data are used as a parent model and a few experimental FRFs from the accelerometers are used as an overlay model. Experimental research on the hybrid model shows an increased accuracy in the estimation of the FRFs.