Monitoring of casting quality using principal component analysis and self-organizing map

The monitoring of casting quality is very important to ensure the safe operation processes. In this paper, in order improve accurate detection defects, a combined method based on principal component analysis (PCA) and self-organizing map (SOM) presented. proposed reduces dimensionality original data by projection onto smaller subspace through PCA. It uses Hotelling’s T2 Q statistics as essential features for characterizing process functionality. SOM used separation between defects. computes metric distances similarity, using (T2Q) input. A comparative study conventional SOM, with reduced data, selected examined. identify running conditions low pressure lost foam process. results indicate that T2Q feature vectors remains comparatively data.