Detail publikačního výsledku

Machine Learning-Driven Detection of Repetitive Manufacturing Processes Using Radar Sensor

MARTINÍK, T.

Originální název

Machine Learning-Driven Detection of Repetitive Manufacturing Processes Using Radar Sensor

Anglický název

Machine Learning-Driven Detection of Repetitive Manufacturing Processes Using Radar Sensor

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

This paper presents a non-invasive system for detecting repetitive manufacturing cycles using pulse-coherent radar and machine learning. The Acconeer A111 radar sensor, combined with an Arducam USB camera, is integrated within a ROS2-based data acquisition framework. The system operates in Envelope and Sparse radar modes, optimized for tracking static and dynamic motion. A YOLO-based model analyzes radar heatmaps to detect repetitive cycles automatically. The approach was validated through controlled experiments and in an industrial setting. Results demonstrate the system’s potential to accurately detect production cycles without modifying existing machinery, highlighting its potential for real-time process monitoring and optimization.

Anglický abstrakt

This paper presents a non-invasive system for detecting repetitive manufacturing cycles using pulse-coherent radar and machine learning. The Acconeer A111 radar sensor, combined with an Arducam USB camera, is integrated within a ROS2-based data acquisition framework. The system operates in Envelope and Sparse radar modes, optimized for tracking static and dynamic motion. A YOLO-based model analyzes radar heatmaps to detect repetitive cycles automatically. The approach was validated through controlled experiments and in an industrial setting. Results demonstrate the system’s potential to accurately detect production cycles without modifying existing machinery, highlighting its potential for real-time process monitoring and optimization.

Klíčová slova

data collection | machine learning | production monitoring | Radar sensing | ROS2

Klíčová slova v angličtině

data collection | machine learning | production monitoring | Radar sensing | ROS2

Autoři

MARTINÍK, T.

Rok RIV

2026

Vydáno

01.01.2025

Nakladatel

Brno University of Technology

ISBN

9788021463202

Kniha

Proceedings II of the 31st Conference STUDENT EEICT 2025: Selected papers.

Strany od

136

Strany do

139

Strany počet

4

BibTex

@inproceedings{BUT201498,
  author="{} and Tomáš {Martiník}",
  title="Machine Learning-Driven Detection of Repetitive Manufacturing Processes Using Radar Sensor",
  booktitle="Proceedings II of the 31st Conference STUDENT EEICT 2025: Selected papers.",
  year="2025",
  pages="136--139",
  publisher="Brno University of Technology",
  doi="10.13164/eeict.2025.136",
  isbn="9788021463202"
}