Search

The traditional microstructure detecting methods such as metallography and electron backscatter diffraction are destructive to the sample and time-consuming and they cannot meet the needs of rapid online inspection. In this paper, a random forest regression microstructure characterization method based on a laser ultrasound technique is investigated for evaluating the microstructure of a titanium alloy (Ti-6Al-4V). Based on the high correlation between the longitudinal wave velocity of ultrasonic waves, the average grain size of the primary α phase, and the volume fraction of the transformed β matrix of the titanium alloy, and with the longitudinal wave velocity as the input feature and the average grain size of the primary α phase and the volume fraction of the transformed β matrix as the output features, prediction models for the average grain size of the primary α phase and the volume fraction of the transformed β matrix were developed based on a random forest regression. The results show that the mean values of the mean relative errors of the predicted mean grain size of the native α phase and the volume fraction of the transformed β matrix for the six samples in the two prediction models were 11.55% and 10.19%, respectively, and the RMSE and MAE obtained from both prediction models were relatively small, which indicates that the two established random forest regression models have a high prediction accuracy. [ABSTRACT FROM AUTHOR]

• The ultrasonic velocity is very sensitive to a slight variation of porosity. • The ultrasonic signal peak frequency-shift occurs when the porosity increases. • The wavelet packet energy increases linearly with the increase of porosity. A noncontact and nondestructive method based on laser ultrasound is proposed for evaluation of porosity in additive manufacturing components. The 304L stainless steel samples with porosities in the range of 0.1%–5.7 % were fabricated using selective laser melting. Laser ultrasonic surface wave was used to characterize the porosity by the wave speed, peak frequency and wavelet packet energy. The result indicates that the surface wave speed, peak frequency and wavelet packet energy are sensitive to the slight variation of porosity in the samples. Good R-squares of fitting between surface wave velocity and porosity were obtained when it considers the pore irregular morphology. The peak frequency of surface wave decreases as the disappearance of high-frequency signals induced by the scattering attenuation. The wavelet packet analysis result shows that the sum of the percentage energy of the ninth layer of wavelet packet decomposition nodes 2–4 is linearly related to the porosity, and exhibits the highest coefficient of determination (R = 0.98) among the proposed characteristics. It is concluded that the laser ultrasonic surface wave based on wavelet packet energy is recommended to be a promising candidate for the quantitative nondestructive evaluation of the porosity of additive manufacturing components. [ABSTRACT FROM AUTHOR]