Cluster Analysis for Drilling-Quality Based on the Modified Algorithm of InDBSCAN
To detect the quality of batch drilling quickly，a new approach based on Acoustic Emission signals is presented. The signals’ statistical characteristics are extracted from acoustic emission signals in Time-domain, and then the signals’ eigenvectors are constructed to reflect each drilling process. A modified incremental clustering algorithm InDBSCAN is used to cluster these eigenvectors，and the batch drilling-quality can be analysed indirectly. Calculation and analysis results show that: the conclusion of incremental cluster analysis is more reasonable by the modified incremental clustering method of InDBSCAN. The detection accuracy of the batch drilling-quality is up to 84.3% according to the manual quality inspection.
Y. H. Zhou et al., "Cluster Analysis for Drilling-Quality Based on the Modified Algorithm of InDBSCAN", Key Engineering Materials, Vols. 480-481, pp. 877-882, 2011