An Application of Unsupervised Neural Networks Based Condition Monitoring System
Integrated condition monitoring for fault identification and maintenance planing is increasingly becoming an indispensable activity in today’s industrial environment. Expert systems and neural networks are emerging to be the latest tools to be applied for condition monitoring. This paper briefly reviews these techniques and describes applications of artificial neural networks in diagnosing the health of various systems.
The application of neural networks discussed here contemplates to devise an intelligent, self-adaptive monitoring module which can be employed in a wider range of industrial environments. The paper describes a general purpose unsupervised neural networks based monitoring system which categorises the operational routines within the individual application environments of a wide range of industrial machinery. The monitor classifies the sensed data into its respective clusters and demonstrate its potential diagnostic capabilities.
KeywordsNeural Network Artificial Neural Network Condition Monitoring Cluster Centre Adaptive Resonance Theory
Unable to display preview. Download preview PDF.
- .R.P. Lippman. ‘An Introduction to Computing with Neural Networks’. IEEE ASSP Magazine April 1987.Google Scholar
- .D.E. Rumelhart, G.E. Hinton, R.J, Williams. ‘Parallel Distributed Processing’. MIT Press, Cambridge MA. 1986.Google Scholar
- .M.A. Javed, S.A.C. Sanders, M. Kopp. “Numerical Optimisation of the Learning Process in Multilayer Perceptron Type Neural Networks”. IEE Colloquium on Neural Networks: Design Techniques and Tools. IEE Savoy Place. March 1991.Google Scholar
- .P.J.C. Skitt, M.A. Javed, S.A.C. Sanders, A.M. Higginson. “Artificial Neural Networks based Quality Monitor for Resistance Welding of Coated Steel”. The 3rd. International Conference on Condition Monitoring & Diagnostic Engineering Management. July 1991. Southampton, U.K.Google Scholar
- .P.J.C. Skitt, M.A. Javed, S.A.C. Sanders, A.M. Higginson. “Process Monitoring Using Auto-Associative, Feed-Forward Artificial Neural Networks.” Journal of Intelligent Manufacturing. Special Issue On ‘Intelligent Manufacturing Systems.’ Vol. 4, No. 1. 1992. ASME, U.S.A.Google Scholar
- .M.A. Javed, S.A.C. Sanders. “An Adaptive Learning Procedure for Neural Networks in Engineering.” International Conference on the Application of Neural Networks in Engineering.” St. Louis, Missouri, USA. Nov. 1991.Google Scholar
- .H. Schram, H. Kolb. “Acoustic quality control using a multi-layer neural network”. 22nd. Int. Symposium on Automotive Technology and Automation. 1990 Florence, Italy.Google Scholar
- .S. Kharpade. “Feasible application of neural networks in energy management system”. Int. conference on Automation, Robotics and Computer Vision”. 1990 Singapore.Google Scholar
- .M.A. Javed, S.A.C. Sanders. “Training Artificial Neural Networks for Applications in Automated Industrial Systems.” International Conference on Industrial Electronics, Control and Instrumentation. IECON 91. Kobe, Japan. November 1991.Google Scholar
- .M.A. Javed, S.A. Sanders. “Neural Networks Based Learning and Adaptive Control for Manufacturing Systems.” IEEE/RSJ International Workshop on Intelligent Robots and Systems.” IROS 91. Osaka, Japan. November 1991.Google Scholar
- .M.A. Javed, S.A. Sanders. “Artificial Neural Networks as Intelligent Condition Monitoring Devices”. ‘Condition Monitoring and Diagnostic Technology’, Vol. 2, No. 1, July 1991.Google Scholar
- .P. Skitt, R. Witcomb. “The analysis of the acoustic emission of jet engines using neural networks”. Condition Monitoring and Diagnostic Technology. Vol. 1. No. 1. June 1990.Google Scholar