Machine Learning solution for machining quality prediction using acoustic emissions, accelerometers and current data
Authors/Creators
- 1. Haute Ecole Arc Ingénierie, HES-SO Saint-Imier, Switzerland
Description
This record contains a dataset used to train tool wear & quality prediction algorithms in a milling manufacturing process context. The data model is composed of three data sources (acoustics emission, accelerometers & currents). The acoustics emissions and accelerometers are recorded on an external machine which needs a post-synchronization. The currents are recorded by the system that directly monitors the machine.
The dataset is describe in the article:
Dreyer, J., Carrino, S., Ghorbel, H. et al. In production system for tool wear prediction using multi-sensor time series and machine learning models. Discov Appl Sci 8, 776 (2026). https://doi.org/10.1007/s42452-025-07096-w
Technical info
Acoustics emission (file: toolwear_2020_ae.zip): AE data from one sensor positioned inside the machine. The sampling rate is 200kHz.
Accelerometers (file: toolwear_2020_acc.zip): The accelerometer dataset is composed of nine different sensors with an acquisition frequency of 20kHz. One signal is dedicated to the synchronization between other data sources (acoustics emission & currents). Five signals are installed on the spindle axis, two (XY directions) on the top of the spindle and three (XYZ directions) on the bottom of the axis. The last three (XYZ directions) are located on the axis nearest to the part.
Currents (file: toolwear_2020_axes.zip): The machine is composed of five axes and one spindle. For each motor, the current is acquired and stored into the monitoring system of the CNC. The frequency of data acquisition is 1kHz.
Notes
This work was developed in the framework of CHIST-ERA programme supported by the Future and Emerging Technologies (FET) programme of the European Union through the ERA-NET Cofund funding scheme under the grant agreements, title Social Network of Machines (SOON). This work was supported by Swiss National Fund (SNF), project number 20CH21_180431. This work was also supported by HES-SO.
Files
toolwear_2020_acc.zip
Additional details
Related works
- Is described by
- Journal article: 10.1007/s42452-025-07096-w (DOI)
- Is supplemented by
- Software: https://github.com/soon-project/MillingToolWear (URL)