ESTIMATION OF ACOUSTIC SOURCE STRENGTH BY INVERSE METHODS: PART II, EXPERIMENTAL INVESTIGATION OF METHODS FOR CHOOSING REGULARIZATION PARAMETERS

Two regularization methods, Tikhonov regularization and singular value discarding, are used to improve the accuracy of reconstruction of acoustic source strength by inverse techniques. In this paper, some methods are investigated for choosing the Tikhonov regularization parameter and the singular values to be discarded. Of these, we concentrate on the use of ordinary cross-validation and generalized cross-validation. These methods can provide an appropriate regularization parameter without prior knowledge of either the acoustic source strength or the contaminating measurement noise. Some experimental results obtained using a randomly vibrating simply supported plate mounted in a baffle are presented to illustrate the performance of the methods for choosing the regularization parameters.