BLIND SYSTEM IDENTIFICATION USING MATRIX MEAN DIFFERENTIAL CEPSTRUM WITH QR-CHOLESKY DECOMPOSITION

Abstract

A further development of the matrix mean differential cepstrum technique for blind identification of convolved mixtures in multiple-input-multiple-output mechanical systems is presented. The stability of the technique for application on the whitened response measurements can be improved with the use of the QR-Cholesky decomposition instead of the SVD-EVD set. Two simulated two-input two-output, two degree of freedom systems of differing damping coefficients are tested. The improved results with smoother frequency response functions of the system are presented and compared to prior results.