0
TECHNICAL BRIEFS

Monitoring of Self-Tapping Screw Fastenings Using Artificial Neural Networks

[+] Author and Article Information
Kaspar Althoefer

Department of Mechanical Engineering, King’s College London, Strand, London WC2R 2LS, United Kingdom e-mail: k.althoefer@kcl.ac.uk

Bruno Lara

Cognitive Robotics, Max Planck Institute for Psychological Research, Amalienstrasse 33, D-80799 Munich, Germany e-mail: lara@psy.mpg.de

Lakmal D. Seneviratne

Department of Mechanical Engineering, King’s College London, Strand, London WC2R 2LS, United Kingdome-mail: lakmal.seneviratne@kcl.ac.uk

J. Manuf. Sci. Eng 127(1), 236-243 (Mar 21, 2005) (8 pages) doi:10.1115/1.1831286 History: Received December 05, 2002; Revised April 21, 2004; Online March 21, 2005
Copyright © 2005 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Key stages during an insertion of a self-tapping screw, progressing in the following order: T0, TE, TP, TB, TF, TF2
Grahic Jump Location
Experimental torque profiles for 12 insertions on polycarbonate plate (thin lines) and the corresponding theoretical prediction (bold line)
Grahic Jump Location
Output values as training evolves (simulated insertion signals). Single case experiment.
Grahic Jump Location
Output values as training evolves (simulated insertion signals). Variation of hole diameter experiment.
Grahic Jump Location
Activation output on test set after 20 training cycles. Four-output classification experiment using simulated signals.
Grahic Jump Location
The screwdriver, torque sensor, and instrumentation used for the acquisition of experimental data
Grahic Jump Location
Output values as training evolves (real insertion signals). Single case experiment.
Grahic Jump Location
Insertion signals from screwdriver. Variation of hole diameter.
Grahic Jump Location
Output values as training evolves (real insertion signals). Variation of hole diameter experiment.
Grahic Jump Location
Insertion signals from screwdriver. Four-output classification experiment.
Grahic Jump Location
Network activation output for the test set after 200 training cycles. Four-output classification experiment using real insertion signals. All signals are correctly attributed.

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In