Development of a real-time monitoring system

Abstract This paper describes a pattern recognition (PR) technique, which uses learning vector quantization (LVQ). This method is adapted for practical application to solve problems in the area of condition monitoring and fault diagnosis where a number of fault signatures are involved. In these situations, the aim is health monitoring, including identification of deterioration of the healthy condition and identification of causes of the failure in real-time. For this reason a fault database is developed which contains the collected information about various states of operation of the system in the form of pattern vectors. The task of the real-time monitoring system is to correlate patterns of unknown faults with the known fault signatures in the fault database. This will determine cause of failure and degree of deterioration of the system under test. The problem of fault diagnosis may involve a large number of patterns and large sampling time, which affects the learning stage of neural networks. The study here also aims to find a fast learning model of neural networks for instances when a high number of patterns and numerous processing elements are involved. It begins searching for an appropriate solution. The study is extended to the enforcement learning models and considers LVQ as a network emerged from the competitive learning model through enforcement training. Finally, tests show an accuracy of 92.3 per cent in the fault diagnostic capability of the technique.

[1]  Moonis Ali,et al.  Pattern-based fault diagnosis using neural networks , 1988, IEA/AIE '88.

[2]  Heikki N. Koivo,et al.  APPLICATION OF ARTIFICIAL NEURAL NETWORKS IN PROCESS FAULT DIAGNOSIS , 1991 .

[3]  S. Grossberg,et al.  Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectors , 1976, Biological Cybernetics.

[4]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[5]  Sylvia Goldsmith.  A practical guide to real-time systems development , 1993 .

[6]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[7]  O. J. Murphy,et al.  Nearest neighbor pattern classification perceptrons , 1990, Proc. IEEE.

[8]  Heikki N. Koivo,et al.  Application of artificial neural networks in process fault diagnosis , 1991, Autom..

[9]  David Zipser,et al.  Feature Discovery by Competive Learning , 1986, Cogn. Sci..

[10]  James L. McClelland,et al.  Explorations in parallel distributed processing: a handbook of models, programs, and exercises , 1988 .

[11]  Martin T. Hagan,et al.  Neural network design , 1995 .

[12]  Venkat Venkatasubramanian,et al.  On the nature of fault space classification structure developed by neural networks , 1992 .

[13]  K F Martin,et al.  Diagnostics of a coolant system via neural networks , 1999 .

[14]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

[15]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[16]  Venkat Venkatasubramanian,et al.  Representing and diagnosing dynamic process data using neural networks , 1992 .

[17]  Régis Lengellé,et al.  Pattern Recognition Using Neural Networks. Comparison to the Nearest Neighbour Rule , 1989 .