Ultrasonic evaluation of porosity under microstructures-induced coupling effects in LPBF-fabricated alloys

The designability of Laser powder bed fusion (LPBF) technology for material microstructure enables the fabrication of high-performance additive manufactured (AM) components. However, challenges remain due to inevitable pores induced by laser shock and parameter fluctuations during manufacturing, which introduce uncertainties in both porosity and microstructures. In this work, ultrasonic bulk wave is employed to evaluate porosity within the context of coupled pore-microstructure effects. Utilizing the distinct frequency-domain characteristics of pore scattering versus grain scattering, we propose a spectral covariance parameter that is sensitive to both mechanisms. Numerical studies involving multiple physical variables related to pores and microstructures reveal that the correlation between spectral covariance and porosity differs from that observed with ultrasonic attenuation. This distinction enables the joint decoupling and evaluation of porosity using both spectral covariance and ultrasonic attenuation measurements. In this study, a deep neural network (DNN) is trained using a combination of numerical and experimental data, yielding prediction results with an absolute porosity error of less than 0.3% across all experimental samples. The findings demonstrate that the proposed method effectively evaluates porosity in LPBF-fabricated alloys with the coupling effects from microstructures, offering a robust ultrasonic-based approach for assessing the structural integrity and safety of LPBF products.