A Novel Approach for Real-Time Quality Monitoring in Machining of Aerospace Alloy through Acoustic Emission Signal Transformation for DNN

Gamma titanium aluminide (γ-TiAl) is considered a high-performance, low-density replacement for nickel-based superalloys in the aerospace industry due to its high specific strength, which retained at temperatures above 800 °C. However, low damage tolerance, i.e., brittle material behavior with propensity rapid crack propagation, has limited application of γ-TiAl. Any cracks introduced during manufacturing would dramatically lower useful (fatigue) life γ-TiAl components, making workpiece surface’s quality from finish machining critical component product and performance. To address this issue enable more widespread use γ-TiAl, research aims develop real-time non-destructive evaluation (NDE) monitoring technique based on acoustic emission (AE) signals, wavelet transform, deep neural networks (DNN). Previous efforts have opted traditional approaches AE signal analysis, using statistical feature extraction classification, face challenges such as good/relevant features classification accuracy. Hence, work proposes novel AI-enabled method that uses convolutional network (CNN) extract rich relevant two-dimensional image representation 1D time-domain signals (known scalograms), subsequently classifying signature pedigreed experimental data finally predicting process-induced surface quality. The results present show good accuracy 80.83% scalogram images, in-situ data, VGG-19 pre-trained network, establishing significant potential processes.