Artificial Neural Networks for Generic Predictive Maintenance

  • C. Kirkham
  • T. Harris
Conference paper


This paper outlines a research project to develop artificial neural networks as a diagnostic tool for the automatic identification of rotating machine faults. This work was instigated by the DTI Neural Computing Learning Solutions Campaign’s AXON Neural Projects Club. Industrial sponsors are Entek/IRD, Diagnostic Instruments Ltd., and Arjo Wiggins Paper Mills. The biggest problem encountered by developers of SMART software systems is that examples of all conditions to be identified are required. In practice this is not possible due to the routine method of plant machinery data collection, and due to the individual behaviour of the machinery. A method is required which is capable of diagnosing a previously unseen fault upon any bearing. This paper proposes a hybrid neural network approach which first determines a novel condition, then a knowledge base categorises the condition. The system is currently working off-line in support of the maintenance technician at the sponsors paper mill plant.


Paper Mill Fault Data Fault Class Roller Element Bearing Predictive Maintenance 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    A.J. Hanna. Predictive Maintenance via Vibration Analysis. TAPPI.Google Scholar
  2. [2]
    T.J. Harris. A Kohonen SOM based, machine health monitoring system which enables diagnosis of faults not seen in the training set. In IJCNN, 1993.Google Scholar
  3. [3]
    A.G. Herraty. Bearing vibration — failures and diagnosis. Mining Technology, pages 51–53, February 1993.Google Scholar
  4. [4]
    D.D. Howieson. A Practical Introduction to Condition Monitoring of Roller Element Bearings Using Envelope Signal Processing. Diagnostic Instruments Ltd., Scotland, UK.Google Scholar
  5. [5]
    R.J. Kershaw and B. Robertson. Condition-based maintenance program increases production. Paper Trade Journal, pages 34–36, February 1995.Google Scholar
  6. [6]
    M. Serridge. What makes vibration condition monitoring reliable? Noise and Vibration Worldwide, pages 17–24, September 1991.Google Scholar

Copyright information

© Springer-Verlag Wien 1998

Authors and Affiliations

  • C. Kirkham
    • 1
  • T. Harris
    • 1
  1. 1.The Centre for Neural Computing ApplicationsBrunel UniversityEgham, SurreyUK

Personalised recommendations