C15031 - System for Dragline Rope Condition Monitoring
C16032 - Application of StressVision® Technology in Dragline Booms
C15031 - System for Dragline Rope Condition Monitoring
C13039 - In-situ Inspection of Dragline Boom Suspension Ropes
C12029 - Advanced signal processing tools for shafTest®
Postgraduate Research Projects
The University of Newcastle and the CCI Pope Product Development Centre have
jointly been awarded an Australian Research Council - Strategic Partnerships
with Industry - Research and Training (ARC-SPIRT) grant. This grant will
support a PhD project, titled: Discrimination of echoes in computer based
ultrasonic flaw detection for CAD modelled steel pieces. This project commenced
in January 2002. To date, this project has produced 5 papers:
-
K. Lee and V. Estivill-Castro "Classification
of Ultrasonic Shaft Inspection Data Using Discrete Wavelet Transform"
The Third IASTED International Conference on Artificial Intelligence and
Applications (AIA 2003) September 8-10, 2003 Benalmdena, Spain. Hamza, M.H.
(ed.) ACTA Press pages 673-678. ISBN 0-88986-890-3, ISSN 1482-7913.
-
K. Lee and V. Estivill-Castro "Feature
Extraction Techniques for Ultrasonic Shaft Signal Classification"
Third International Conference on Hybrid Intelligent Systems (HIS03).
Melbourne, Australia. Abraham, A., Koppen, M. and Franke K. (editors) IOS Press
(Amsterdam, The Netherlands) pages 479-488 ISBN 1-58603-394-8.
-
K. Lee and V. Estivill-Castro
"Support Vector Machine Classification of Ultrasonic Shaft Inspection Data
using Discrete Wavelet Transform"
The 2004 International Conference on Machine Learning;Models, Technologies and
Applications (MLMTA'04) June 21-24, 2004, Las Vegas, Nevada, USA.
-
K. Lee and V. Estivill-Castro "A
Hybrid Classification Approach to Ultrasonic Shaft Signals"
The 17th Australasian Joint Conference on Artificial Intelligence (AusAI) Dec.
6 10, 2004, Cairns, Australia, Geoffrey I.Webb and Xinghuo Yu (editors),
Lecture Notes in Computer Science, Vol3339/2004, Springer-Verlag. Pages
284-295, ISBN 3-540-24059-4.
-
K. Lee and V. Estivill-Castro "Classification
Ensembles for Shaft Test Data: Empirical Evaluation."
The 4th International Conference on Hybrid Intelligent System (HIS), Dec. 5 8,
2004, Kitakyushu, Japan, IEEE Computer Society. (In press)
Artificial Intelligence Applied to Ultrasonic Testing of Shafts
The commercial shafTest® system
started out as an ACARP funded research project to develop an improved method
of ultrasonically testing large shafts and pins. The shafTest® system utilizes
a novel approach to the collection and presentation of ultrasonic shaft defect
information. In this way the normally complex task of monitoring the condition
of large shafts and pins is not only simplified but also made more accurate and
reproducible. The system now allows us to provide a much-improved ultrasonic
inspection service.
In 2001 we additionally completed an extension project funded by ACARP to
research the feasibility of using artificial intelligence techniques to
automatically analyse and discriminate different types of echoes from within
the ultrasonic signature of a shaft. In particular, we have shown that it is
possible using neural networks to identify mode-converted echoes, and
discriminate between different types of reflectors, i.e. cracks, from their
characteristic ultrasonic signatures. This result is a world first and we
believe that an ultrasonic flaw detector that can aid the operator by
indicating the position of defects from a complex ultrasonic trace is
realisable.
CCI Pope enjoys a strong relationship with science and engineering departments
of The University of Newcastle. Through this association we benefit both from
opportunities for education and training, we gain access to academic expertise
supporting our research interests and we are able to satisfy our commitment to
our community by supporting the training and professional development of
undergraduate engineers.
Sponsored Undergraduate Projects
Accelerometer Calibration System
William Van De Linde
Dept. of Electrical Engineering & Computer Science, Newcastle University, 2006.
AI Based Classification of Ultrasound Reflection Data
Heath Raftery
Dept. of Electrical & Computer Engineering, Newcastle University, 2004.
Portable Solution for the Storage and Analysis of Broad Spectrum
Vibration Data.
James Palmowski.
Dept. of Electrical & Computer Engineering, Newcastle University, 2001.
One of four final year projects (of over 40) short listed in competition for
the Australian Institute of Engineers award for project excellence.
Applying Artificial Neural Networks To The Ultrasonic Testing Of Shafts
John Perceval.
Dept. of Computer Science & Software Engineering, Newcastle University,
2000.
EMAT Pipe Weld Test
Luke Hellowell & Adam Van Dyck.
Dept. of Electrical & Computer Engineering, Newcastle University, 1999.