Data

Ultrasonic Acoustic Dataset of Industrial Drill Degradation and Failure

Western Sydney University
Chevtchenko, Sergio ; Ibnul, Naqib ; Afshar, Saeed
Viewed: [[ro.stat.viewed]] Cited: [[ro.stat.cited]] Accessed: [[ro.stat.accessed]]
ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rfr_id=info%3Asid%2FANDS&rft_id=info:doi10.26183/v7kh-b648&rft.title=Ultrasonic Acoustic Dataset of Industrial Drill Degradation and Failure&rft.identifier=10.26183/v7kh-b648&rft.publisher=Western Sydney University&rft.description=This dataset was collected to support research on remaining useful life estimation and tool condition monitoring in CNC drilling using ultrasonic acoustic sensing. Recordings were acquired on a CNC machining centre during the drilling of iron plates with 4 mm carbide drills, with each tool operated until critical failure. To ensure statistical robustness and capture operational variability, 17 physically distinct industrial drills were monitored across their full life cycle and used in model training and evaluation. This allows the dataset to reflect a range of degradation patterns rather than the behaviour of a single tool type or run. Based on the total number of holes drilled until failure, the tools span three service life profiles: short life tools failing after 18 to 30 holes, medium life tools lasting 31 to 60 holes, and one long life tool reaching 107 holes. The instrumentation focused on ultrasonic MEMS microphones positioned inside the machining area to capture high-frequency signatures associated with progressive wear, including friction-related spectral changes and transient impulsive events above 20 kHz that are often masked in the audible range by industrial background noise. The resulting dataset is intended for the development and evaluation of robust prognostic models under realistic tool-life uncertainty and manufacturing variability. This dataset contains WAV audio files of ultrasonic recordings. The folders are organised by drill ID (1 to 17).&rft.creator=Chevtchenko, Sergio &rft.creator=Ibnul, Naqib &rft.creator=Afshar, Saeed &rft.date=2026&rft.coverage=150.740817,-33.765308 150.7407,-33.765877 150.741115,-33.765985 150.741147,-33.765477 150.740817,-33.765308&rft.coverage=&rft_rights=Copyright Western Sydney University&rft_rights=CC BY-NC-SA 4.0: Attribution-Noncommercial-Share Alike 4.0 International http://creativecommons.org/licenses/by-nc-sa/4.0&rft_subject=ultrasonic acoustics&rft_subject=tool wear&rft_subject=remaining useful life&rft_subject=CNC drilling&rft_subject=predictive maintenance&rft_subject=SDG: 9 - Industry, Innovation and Infrastructure&rft_subject=Manufacturing engineering&rft_subject=ENGINEERING&rft_subject=MANUFACTURING&rft.type=dataset&rft.language=English Access the data

Licence & Rights:

Non-Commercial Licence view details
CC-BY-NC-SA

CC BY-NC-SA 4.0: Attribution-Noncommercial-Share Alike 4.0 International
http://creativecommons.org/licenses/by-nc-sa/4.0

Copyright Western Sydney University

Access:

Open view details

Open

Contact Information



Full description

This dataset was collected to support research on remaining useful life estimation and tool condition monitoring in CNC drilling using ultrasonic acoustic sensing. Recordings were acquired on a CNC machining centre during the drilling of iron plates with 4 mm carbide drills, with each tool operated until critical failure. To ensure statistical robustness and capture operational variability, 17 physically distinct industrial drills were monitored across their full life cycle and used in model training and evaluation. This allows the dataset to reflect a range of degradation patterns rather than the behaviour of a single tool type or run. Based on the total number of holes drilled until failure, the tools span three service life profiles: short life tools failing after 18 to 30 holes, medium life tools lasting 31 to 60 holes, and one long life tool reaching 107 holes. The instrumentation focused on ultrasonic MEMS microphones positioned inside the machining area to capture high-frequency signatures associated with progressive wear, including friction-related spectral changes and transient impulsive events above 20 kHz that are often masked in the audible range by industrial background noise. The resulting dataset is intended for the development and evaluation of robust prognostic models under realistic tool-life uncertainty and manufacturing variability. This dataset contains WAV audio files of ultrasonic recordings. The folders are organised by drill ID (1 to 17).

Created: 2026-04-24

Data time period: 11 2024 to 31 01 2025

This dataset is part of a larger collection

Click to explore relationships graph

150.74082,-33.76531 150.7407,-33.76588 150.74112,-33.76599 150.74115,-33.76548 150.74082,-33.76531

150.7409235,-33.7656465

Subjects

User Contributed Tags    

Login to tag this record with meaningful keywords to make it easier to discover

Identifiers
  • DOI : 10.26183/V7KH-B648
  • Local : research-data.westernsydney.edu.au/published/eb7b78503f7f11f1a4923741fec30ff7