Application of Statistical Signal Processing Techniques to Ultrasound Signals for Automatic Microstructural Characterization and Classification

During the gas tungsten arc welding of nickel based superalloys, the secondary phases such as Laves and carbides are formed in final stage of solidification. But, other phases such as 紘′′ and 絞 phases can precipitate in the microstructure, during aging at high temperatures. However, it is possible to minimize the formation of the Nb-rich Laves phases and therefore reduce the possibility of solidification cracking by adopting the appropriate welding conditions. This paper aims at the automatic microstructurally characterizing the kinetics of phase transformations on a Nb-base alloy, thermally aged at 650 °C for 10, 100 and 200 h, through backscattered ultrasound signals at frequency of 4 MHz. For this, a decision support system was designed using statistical signal processing techniques. Indeed, three dimensionality reduction methods; Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and Independent Component Analysis (ICA) were independently applied on the Discrete Cosine Transform (DCT) coefficients. These dimensionality reduced features were fed to the k-Nearest Neighbor (k-NN) and Decision Tree (DT) classifiers to automatic microstructure characterization. DCT coupled with ICA and k-NN yielded the highest average accuracy of 95.5%. Thus, the proposed decision support system provides high reliability to be used for microstructure characterization through ultrasound signals.