Integration of system process information obtained through an image processing system with an evolving knowledge database to improve the accuracy and predictability of wear debris analysis is the main focus of the paper. The objective is to automate intelligently the analysis process of wear particle using classification via self-organizing maps. This is achieved using relationship measurements among corresponding attributes of various measurements for wear debris. Finally, visualization technique is proposed that helps the viewer in understanding and utilizing these relationships that enable accurate diagnostics. ICROSCOPIC applications have been one of the important areas in the field of automation for on- line/off-line visual inspection systems in industry and for long-term availability of inventory in warehouses. These systems include analysis of microscopic wear debris. Any change in the steady state operation of the machine creates a change in the normal wear mechanism. This change once transported by a lubricant from wear sites carries important information relating to the condition of engines and other machinery. Researchers have used this information to diagnose wear-producing modes and thus attempt to predict wear failures in machines (1-2). For the purpose of objective diagnosis, the identification and analysis of these wear debris have been reported in literature using various automation techniques. The interested reader is referred to the work of authors in (3-5) for further study. The aim of the overall research has been to develop an image analysis and in some cases knowledge based system to classify wear debris for the objective under study. The authors in (6) have discussed an intelligent expert system via Internet using combination of an expert system and a neural network. The respective authors have only discussed classifications where desired ones are known and corresponding mapping is
[1]
D. Hammerstrom,et al.
Neural networks at work
,
1993,
IEEE Spectrum.
[2]
Mohammad Shakeel Laghari.
Recognition of texture types of wear particles
,
2003,
Neural Computing & Applications.
[3]
B. J. Roylance.
Wear debris analysis for condition monitoring
,
1994
.
[4]
Igor Aleksander,et al.
Introduction to Neural Computing
,
1990
.
[5]
Gulzar A. Khuwaja,et al.
Computer vision techniques for wear debris analysis (CVTWDA)
,
2002
.
[6]
Farzin Deravi,et al.
Comparison of shape features for the classification of wear particles
,
1997
.
[7]
Panayiotis Zaphiris,et al.
Introduction to Social Network Analysis
,
2009,
INTERACT.
[8]
Slawomir Przylucki,et al.
An analysis of self-organization process for data classification in multisensor systems
,
2003,
Optoelectronic and Electronic Sensors.
[9]
Anke Meyer-Baese,et al.
Model-free functional MRI analysis using cluster-based methods
,
2003,
SPIE Defense + Commercial Sensing.
[10]
T. Hunt.
Wear Debris Analysis
,
1991
.
[11]
Panayiotis Zaphiris,et al.
Introduction to social network analysis
,
2007,
BCS HCI.
[12]
V. C. Westcott,et al.
A method for the study of wear particles in lubricating oil
,
1972
.
[13]
Trevor M. Hunt,et al.
Handbook of Wear Debris Analysis and Particle Detection in Liquids
,
1993
.
[14]
Xianmei Kong,et al.
A Web-Based Remote Intelligent Expert System for Ferrography Diagnosis
,
2003
.
[15]
H. Jost,et al.
Tribology — Origin and future
,
1990
.