Radial basis artificial neural networks for screw insertions classification

Bruno Lara, Lakmal D. Seneviratne, Kaspar Althoefer

Research output: Contribution to journalConference articlepeer-review

5 Scopus citations

Abstract

The automation of screw insertions is a highly desirable task. An important part of the automation process is the monitoring of the insertion. This paper presents an application of artificial neural networks for monitoring this common manufacturing procedure. The research focuses on the insertion of self-tapping screws. A Radial Basis artificial neural network is employed to distinguish between successful and failed insertions. The network is tested with tasks of increasing complexity using simulation data. The approach is then validated with the use of experimental data, and the tests results are presented.

Original languageBritish English
Pages (from-to)1912-1917
Number of pages6
JournalProceedings - IEEE International Conference on Robotics and Automation
Volume2
StatePublished - 2000
EventICRA 2000: IEEE International Conference on Robotics and Automation - San Francisco, CA, USA
Duration: 24 Apr 200028 Apr 2000

Fingerprint

Dive into the research topics of 'Radial basis artificial neural networks for screw insertions classification'. Together they form a unique fingerprint.

Cite this