Options
Research Data for the Publication: Generalization of LSTM and CNN Autoencoders for Anomaly Detection Across Orthogonal and Longitudinal Turning
Citation Link: https://doi.org/10.15480/882.16923
Type
Dataset
Version
1
Date Issued
2026-04-07
Author(s)
Wu, Ya-Jing
Data Curator
Language
English
Used equipment
9129AA (Kistler Instrumente AG)
Index ABC 65
Abstract
The dataset consists of several turning tests and is supplementary to the paper 'Generalization of LSTM and CNN Autoencoders for Anomaly Detection Across Orthogonal and Longitudinal Turning'. The experiments cover two datasets by Hamburg University of Technology and TU Dortmund University. The experiments include cutting edges of various indexable inserts, each of which was used with constant process parameters until failure. The three-axis force data is available as in-situ online measurements.
Subjects
Turning
Indexable inserts
In-Situ Measurement
DDC Class
670: Manufacturing
Funding(s)
Funding Organisations
More Funding Information
This work was supported by the German Research Foundation (Deutsche Forschungsgemeinschaft, DFG) projects “Extrapolative digital grey-box models for describing and predicting the macroscopic system behavior of TiAlN-coated cutting tools” (project no. 521385417) and “Greybox model-based prediction of wear evolution of coated tools through experimental and model-driven identification of relevant loads” (project no. 521377466) within the priority program SPP2402 “Greybox models for the qualification of coated tools for high-performance machining”.
Technical information
Tar archives contain .npz files which require the NumPy package for the Python programming language.
No Thumbnail Available
Name
OT.tar.gz
Size
39.51 MB
Format
GNU Zip
No Thumbnail Available
Name
LT.tar.gz
Size
41.97 MB
Format
GNU Zip
No Thumbnail Available
Name
Readme.md
Size
2.76 KB
Format
Markdown