Using model reduction and data expansion techniques to improve SDM

A method designed to predict the effects of distributed modifications of structures is proposed here. This method is an evolution of the classical formulations, and distinguishes measurements and coupling points. Based on a coarse model of the structure to be modified, the proposed methodology tackles two major difficulties: efficient predictions for distributed modifications and handling of the lack of measurement points on the coupling interface. In addition, displacements bases introduced to reconstruct unmeasured behaviour of the interface limit error propagation through the process. Moreover, two indicators are introduced to select the optimal prediction. An academic stiffened plate and an industrial application (motor pump) are used to illustrate the approach and highlight its main advantages. (c) 2005 Elsevier Ltd. All rights reserved.