Abstract
A syntactic pattern recognition system for recognition of normal/abnormal vibration spectral patterns of machines is described. Vibrational spectral data is preprocessed and reduced to sentences of terminal strings. A general purpose software ‘shell’ infers a regular grammar from a set of sample patterns and converts the inferred production rules into a parser in the form of a finite state automaton. A search algorithm based on depth-first method with backtracking extracts those patterns from noisy input data which conform to the inferred grammar rules. Large amounts of periodic vibration data can be analysed efficiently for the occurrence or nonoccurrence of abnormal conditions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Carey, J. (1987) The role of software in predictivemaintenance. Maintenance conference, 1987.
Dyer, D; Stewart, R.M. (1978) Detection of rolling element bearing damage by statistical vibration analysis. Journal of Mechanical Design, April, pp 229–235.
Fu, K.S. (1982) Application of pattern recognition. CRC Press, 1982.
Mathew, J. (1987) Machine condition monitoring using vibration analysis. Accoustic Australia, Vol 15, part 1, April, pp 7–3.
Nichollis, C. (1986) Condition monitoring using data collectors. CME Chart Mech, Vol 33, Part 5.
O’Dea, D.M. (1975) User experience with computerized machinery vibration analysis. Hydrocarbon Processing, Dec, pp 81–84.
Stewart, R.tt. (1984) Machinery management based on the application of modern diagnostics, control theory and artificial intelligence. Condition monitoring Conf Proc, April 10–13, Swansea, pp 33–55.
Tait, A.J. etal. (1986) Condition monitoring of electrical drives. IEE Proc, Vol:13, Part-B, No:3, May, pp 142–148.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1990 Chapman and Hall
About this chapter
Cite this chapter
Ahmed, M.M., Pringle, R.D. (1990). Application of syntactic pattern recognition techniques to condition monitoring of machines. In: Rao, R.B.K.N., Au, J., Griffiths, B. (eds) Condition Monitoring and Diagnostic Engineering Management. Springer, Dordrecht. https://doi.org/10.1007/978-94-009-0431-6_38
Download citation
DOI: https://doi.org/10.1007/978-94-009-0431-6_38
Publisher Name: Springer, Dordrecht
Print ISBN: 978-0-412-38560-5
Online ISBN: 978-94-009-0431-6
eBook Packages: Springer Book Archive