Reproduce “Acoustic Anomaly Detection for Early Identification of Drill Jamming” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Maria Beatriz Silva, Lucas Edson Silva de Araújo, Sergio F. Chevtchenko, Ermeson Andrade, Danilo Araujo, Saeed Afshar
The system monitors ultrasonic sound during CNC drilling and uses an autoencoder trained on healthy examples to flag departures from a learned baseline. Tested on 17 distinct 4 mm carbide drills under offline leave-one-drill-out evaluation, it achieved average F1 0.81 and global recall 1.00, with eight normal-region alerts; results do not establish real-world warning guarantees.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.