Image segmentation and robust edge detection for collision avoidance in machine tools-Reference-Cited by-同舟云学术

Image segmentation and robust edge detection for collision avoidance in machine tools

Published:2021-05-14 Issue:6 Volume:88 Page:374-385
ISSN:2196-7113
Container-title:tm - Technisches Messen
language:en
Short-container-title:

Author:

Barton David¹^ORCID,Hess Felix¹,Männle Patrick¹,Odendahl Sven²,Stautner Marc²,Fleischer Jürgen¹

Affiliation:

1. 150232 Karlsruhe Institute of Technology , wbk Institute of Production Science , Kaiserstraße 12 , Karlsruhe , Germany

2. 355285 Moduleworks GmbH , Henricistraße 50 , Aachen , Germany

Abstract

Abstract Collisions are a major cause of unplanned downtime in small series manufacturing with machine tools. Existing solutions based on geometric simulation do not cover collisions due to setup errors. Therefore a solution is developed to compare camera images of the setup with the simulation, thus detecting discrepancies. The comparison focuses on the product being manufactured (workpiece) and the fixture holding the workpiece, thus the first step consists in segmenting the corresponding region of interest in the image. Subsequently edge detection is applied to the image to extract the relevant contours. Additional processing steps in the spatial and frequency domain are used to alleviate effects of the harsh conditions in the machine, including swarf, fluids and sub-optimal illumination. The comparison of the processed images with the simulation will be presented in a future publication.

Publisher

Walter de Gruyter GmbH

Subject

Electrical and Electronic Engineering,Instrumentation

Link

https://www.degruyter.com/document/doi/10.1515/teme-2021-0028/pdf

Reference26 articles.

1. F. Piller and A. Kumar, Mass customization: Providing custom products and services with mass production efficiency, Journal of Financial Transformation, vol. 18, no. 3, pp. 125–131, 2006.

2. E.-M. Jakobs, C. Digmayer, S. Vogelsang and M. Servos, Not ready for industry 4.0: Usability of CAx systems, in: Advances in Usability and User Experience, 2018, pp. 51–62.

3. B. Schleich, M.-A. Dittrich, T. Clausmeyer, R. Damgrave, J. A. Erkoyuncu, B. Haefner, J. de Lange, D. Plakhotnik, W. Scheidel and T. Wuest, Shifting value stream patterns along the product lifecycle with digital twins, Procedia CIRP, vol. 86, pp. 3–11, 2019.

4. D. Barton, P. Gönnheimer, F. Schade, C. Ehrmann, J. Becker and J. Fleischer, Modular smart controller for Industry 4.0 functions in machine tools, Procedia CIRP, vol. 81, pp. 1331–1336, 2019.

5. D. Barton, R. Stamm, S. Mergler, C. Bardenhagen and J. Fleischer, Industrie 4.0 Nachrüstkit für Werkzeugmaschinen: Modulare Lösung für zustandsorientierte Instandhaltung und Prozessüberwachung, WT Werkstattstechnik, vol. 110, no. 7-8, 2020.

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Collision avoidance and adaptive path planning in machine tools by matching live image data with a geometric simulation;Procedia CIRP;2023