Tool wear monitoring in microdrilling through the fusion of features obtained from acoustic and vibration signals

The acoustic signals used by tool wear monitoring systems adopted in microdrilling are degraded by the noise present in manufacturing environments. To overcome this problem, the present study designed a system containing a 4 × 4 microelectromechanical system microphone array and a three-axis accelerometer to achieve accurate tool wear monitoring in noisy manufacturing environments. Features that were moderately to strongly correlated with tool wear were selected as inputs for this system’s one-dimensional (1D) convolutional neural network (CNN) model for predicting tool wear. Pearson correlation analysis revealed that the frequency-domain signal features captured by a 4 × 4 microphone array with minimum variance distortion-less response (MVDR) beamforming had stronger correlations with tool wear than did those captured by a 4 × 4 or 1 × 2 microphone array with delay-and-sum beamforming or by a single microphone; this was because the signals captured by the 4 × 4 array with MVDR beamforming were less noisy. For the aforementioned microphone configurations, under the presence of noise, the 1D CNN model predicted severe wear with higher accuracy when it was trained using fused high-correlation features obtained from the signals captured by the 4 × 4 microphone array with MVDR beamforming and an accelerometer (97.6%) than when it was trained using unfused signal features captured by the accelerometer (86.7%) or the 4 × 4 microphone array with MVDR beamforming (90.3%) alone. The tool wear prediction accuracy obtained using the aforementioned fused features was close to that obtained using fused features acquired from the signals of one microphone and an accelerometer in a quiet environment (97.0%).