Tool Health Monitoring Using Airborne Acoustic Emission and Convolutional Neural Networks: A Deep Learning Approach

Tool health monitoring (THM) is in great focus nowadays from the perspective of predictive maintenance. It prevents increased downtime due to breakdown maintenance, resulting reduced production cost. The paper provides a novel approach tool computer numeric control (CNC) machine for turning process using airborne acoustic emission (AE) and convolutional neural networks (CNN). Three different work-pieces aluminum, mild steel, Teflon are used experimentation classify carbide high-speed steel (HSS) tools into three categories new, average (used), worn-out tool. Acoustic signals machining produce time–frequency spectrograms then fed tri-layered CNN architecture that has been carefully crafted high accuracies faster trainings. Different sizes numbers filters, combinations, multiple trainings compare classification accuracy. A with four each size 5 × 5, gives best results all cases accuracy 99.2%. proposed promising emission.