KIT | KIT-Bibliothek | Impressum | Datenschutz

A Multimodal Dataset 2 for Process Monitoring and Anomaly Detection in Industrial CNC Milling

Ströbel, Robin ORCID iD icon 1; Kuck, Maximilian 1; Oexle, Florian 1; Puchta, Alexander [Beteiligte*r] 1; Fleischer, Jürgen [Beteiligte*r] 1
1 Institut für Produktionstechnik (WBK), Karlsruher Institut für Technologie (KIT)

Abstract:

Der vorliegende Datensatz enthält Prozessdaten, die auf einer dreiachs Fräsmaschine (CMX 600V, DMG Mori) durchgeführt wurden, und ergänzt DOI:10.35097/hvvwn1kfwf7qt48z. Um die Vielfalt und Variabilität realer Fräsbearbeitungen widerzuspiegeln, wurden industrierelevante Bauteile, Werkzeuge und Bearbeitungsstrategien angewendet. Insgesamt sind 54 Fräsversuche enthalten. Um eine Reproduzierbarkeit und Benchmarking-Anwendungen zu ermöglichen, umfasst der Datensatz NC-Programme, beschriftete Bilder und eine detaillierte Dokumentation. Während der Bearbeitung wurden die Signale der SINUMERIK 840D Steuerung über die SINUMERIK Edge App „Analyse MyWorkpiece/Capture” erfasst. ... mehr

Abstract (englisch):

This dataset contains process data from milling operations performed on a three-axis milling machine (CMX 600V, DMG Mori), complementing DOI:10.35097/hvvwn1kfwf7qt48z. To reflect the diversity and variability of real-world milling scenarios, the dataset includes components, tools and machining strategies that are relevant to the industry. A total of 54 milling experiments are included. To support reproducibility and benchmarking applications, the dataset includes NC programs, labelled pictures, and detailed documentation. During processing, signals were acquired from the Siemens SINUMERIK 840D CNC system via the SINUMERIK Edge app 'Analyse MyWorkpiece/Capture', which enables the export of high-frequency data at 500 Hz in JSON format (.json). ... mehr


Zugehörige Institution(en) am KIT Institut für Produktionstechnik (WBK)
Publikationstyp Forschungsdaten
Publikationsdatum 01.10.2025
Erstellungsdatum 26.09.2025
Identifikator DOI: 10.35097/vnnu3n9z7ndsnhfd
KITopen-ID: 1000185172
Lizenz Creative Commons Namensnennung 4.0 International
Schlagwörter Machine Tool, Process Monitoring, Anomaly Detection, Machine Learning, Milling, CNC
Liesmich

This dataset contains process data from milling operations performed on a three-axis milling machine (CMX 600V, DMG Mori) and is complementary to DOI:10.35097/hvvwn1kfwf7qt48z. The data was collected in a controlled laboratory setting using industrially relevant components, tools, and machining strategies to reflect the diversity and variability of practical milling scenarios. Process signals from the machine controller were recorded using a Siemens Industrial Edge device at a sampling rate of 500 Hz. Additional high-frequency force and acceleration data were measured using a force platform (Kistler Type Z 3393) and a spindle-mounted acceleration sensor (PCB Type 356A33). The analog signals were amplified via a charge amplifier (Kistler Type 5015A1000 K) and acquired using a Data Translation DT9836 data acquisition card at 10 kHz.

Raw data from the force and acceleration sensors are provided as MATLAB timetable files (.mat). The process signals from the Siemens Industrial Edge are stored in JSON format (.json).

In addition, each experiment includes a consolidated MATLAB file in which all available signals (Edge and sensor data) are temporally aligned and stored as a single timetable object. To achieve this, the 500 Hz Edge signals were interpolated using the PCHIP method (Piecewise Cubic Hermite Interpolating Polynomial) to match the 10 kHz resolution of the sensor data. This unified file enables direct signal comparison across all sources and simplifies further analysis.

In total, 54 milling experiments are included. NC programs, labeled pictures, and detailed documentation are provided to support benchmarking applications.


Documents:

  • Dataset: All data files organized by component type and trial ID
  • Descriptive: Design of Experiment, NC programs executed during the experiments (G-code), labeled pictures organized by component type and tools

Experimental Setup:

  • Machines: CMX 600V (3-axis milling center)
  • Materials: S235JR (unalloyed structural steel), Al2007 T4 (aluminum alloy), POM-C (polyoxymethylene copolymer)
  • Cutting Tools:
    • HSS-Co8 end mill (TiAlN coating, Ø 5 mm, k10 tolerance)
    • Solid carbide end mill (TiSi coating, Ø 10 mm, f8 tolerance)
    • Solid carbide end mill (uncoated, Ø 5 mm, e8 tolerance)
  • Workspace blank dimensions: 150x75x50mm
Art der Forschungsdaten Dataset
Nachgewiesen in OpenAlex
Relationen in KITopen
Globale Ziele für nachhaltige Entwicklung Ziel 7 – Bezahlbare und saubere EnergieZiel 9 – Industrie, Innovation und Infrastruktur
KIT – Die Universität in der Helmholtz-Gemeinschaft
KITopen Landing Page