REAL-TIME ENHANCEMENT OF REFERENCE SIGNALS FOR FEEDFORWARD CONTROL OFRANDOM NOISE DUE TO MULTIPLE UNCORRELATED SOURCES

The problem envisaged in this paper is the optimization of the referen ce set for broadband feedforward control of sound and vibration in the presence of multiple, uncorrelated primary sources, A real-time algor ithm is presented that generates a set of orthogonal virtual reference s out of a given set of reference signals, The algorithm is based on r ecursive singular value decomposition (SVD) techniques, The technique simplifies controller design in the sense that primarily, comparable c ontrol performance can be achieved using a reduced set of virtual refe rences instead of the extensive original reference set, Hence, control ler dimensions (and, thus, the memory requirements for implementation) and the computational burden reduce accordingly, Second, it is shown that convergence speed of the adaptive filtered-X LMS feedforward cont rol algorithm is enhanced. The technique is applied to active control of structure-borne road noise inside a car cabin, Time domain simulati on of a control configuration, utilizing either an extensive set of or iginal references as well as a reduced virtual reference set, shows th at in the frequency ranges of interest, a set of four virtual referenc es yields the same noise reductions as the original set of 12 referenc es.