Principal component analysis for characterising homogeneity in powder mixing using image processing techniques
Résumé
The many methods which exist to characterise the quality of a powder mixture have been recently reviewed and linked with mixing mechanisms in current literature. In this paper, we try to develop a novel methodology for defining and characterising homogeneity using principal component analysis (PCA) as an alternative to well‐known statistical methods, such as auto‐correlation functions or variances. We apply this to image analysis for the case of a powder mixture flowing out of a continuous mixing device. An emphasis is placed on the calculation in real‐time of the degree of homogeneity of loose materials on the conveyor belt, carrying this mixture. Mass flow disturbances applied to a binary mixture are studied by the proposed methodology, which is found to be sensitive to small structural defaults.
Fichier principal
Principal_component_analysis_for_characterising.pdf (544.82 Ko)
Télécharger le fichier
Origine | Fichiers produits par l'(les) auteur(s) |
---|
Loading...