Cross-Contamination Identification of Additive Manufacturing Metal Powders Using Spatially Confined Particle-Flow LIBS and Machine Learning.

Laser-induced breakdown spectroscopy (LIBS) offers rapid, in situ, and multi-element detection, and therefore shows strong potential for quality monitoring of metal powders in additive manufacturing. However, direct LIBS analysis of flowing metal powders is often affected by particle splashing, unstable laser-particle coupling, and plasma fluctuations, which reduce signal repeatability and detection reliability. To address these issues, this study developed an integrated measurement and classification framework for identifying cross-contamination in additive-manufacturing metal powders. A stable powder particle stream was generated through vibratory feeding and particle-flow focusing, while a hollow quartz tube with a side opening was introduced to provide cylindrical spatial confinement, thereby improving the stability of laser-particle interaction and enabling in situ spectral acquisition without pellet preparation. TC4 powder was used as the base material and AlSi10Mg powder as the contaminant, and samples with contamination levels of 0, 0.5, 1, 2, and 5 wt.% were prepared. Two independent batches of single-shot LIBS spectra were collected. To reduce the influence of strong spectral fluctuations, outlier spectra were removed using full-spectrum total-intensity quantile filtering, followed by asymmetric least-squares baseline correction and standard normal variate transformation. PCA combined with multiple machine-learning models was then applied for contamination identification. The results showed that LIBS spectra at different contamination levels exhibited distinguishable distributions in principal-component space, and the spectral differences between clean and contaminated powders became more pronounced with increasing contamination level. In binary classification, several models achieved high classification accuracy at medium and high contamination levels, while PCA-SVM-RBF showed the best performance at low concentrations. In five-class cross-validation, the 5 wt.% class exhibited the clearest decision boundary, whereas confusion remained among low and adjacent contamination levels, indicating that contamination-induced spectral responses followed a more continuous transition. These results demonstrate that the proposed spatially confined particle-flow LIBS framework combined with machine-learning classification can effectively achieve rapid identification of cross-contamination in additive-manufacturing metal powders and provides a feasible technical route for online powder quality monitoring.