RESONAM will study the mechanisms and origins of variability in AM part quality. The effect of modifying printing conditions on the AM material will be investigated with vibrational NDT techniques as well as with various traditional material characterization techniques (metallography, X-CT, …). Additionally, novel (nonlinear) vibrational techniques, coupled to learning algorithms, will be researched to predict the AM material quality, and to understand the contributing factors to print variability. A (data-driven) simulation model will be setup to populate a virtual database which will be employed in the learning algorithms. The learning algorithms will enable the prediction of the quality of AM parts, and will provide insight on the process variability (e.g. intra-build, inter-build, inter-machine). The developed framework will lead to a faster qualification of print process parameters as well as to a better AM material qualification.