Feature extraction and pattern recognition in acoustic emission monitoring of robot assisted polishing

Polishing processes are to date gradually evolving from basically manual operations to automated processes. To achieve more accurate, steadfast and dependable automated polishing processes, sensor monitoring offers as a creditable tool for process and product quality control. In this study, an acoustic emission sensor monitoring system was employed for surface roughness assessment during robot assisted polishing of steel bars. After sensor signal pre-processing, feature extraction procedures were applied to the conditioned acoustic emission signals. The scope was to extract relevant signal features to input to pattern recognition paradigms in order to identify correlations between process generated acoustic emission and polished workpiece surface roughness.