A data-driven metamodel-based approach for point force localization

This paper introduces a novel strategy for point force localization in the frequency domain, based on metamodeling techniques and independent of excitation level. More precisely, ability well-established techniques, such as Polynomial Chaos expansion or Universal Kriging, providing accurate surrogate models locating through an optimization procedure is evaluated. The proposed methodology applied purely data-driven context. Obtained results highlight good performance relatively small data sets, well its robustness to noise both training deployment phases.