Expert system development for vibration analysis in machine condition monitoring
Ebersbach, Stephan, and Peng, Zhongxiao (2008) Expert system development for vibration analysis in machine condition monitoring. Expert Systems with Applications, 34 (1). pp. 291-299.
PDF (Published Version)
Restricted to Repository staff only
Expert systems can be utilised for machine condition monitoring data interpretation due to the ability to identify a systematic reasoning process, and conventional methods requiring highly trained professional labour. The expert system developed in conjunction with this paper has been designed for interpreting vibration spectra in machine condition monitoring. The methods employed by the expert system’s analysis algorithm include spectral analysis as the primary technique, and time domain as well as demodulated spectral analysis as the secondary techniques. The secondary techniques are used for improved interpretation confidence, if the data is available. The algorithm has been developed for industries operating constant speed gearboxes, as is common in the power generation, mining and mineral processing sectors.
The vibration analysis expert system operates from a knowledge base that was designed using a combination of common handbook reasoning logic for frequency spectra interpretation, and extracted knowledge of experts in the vibration analysis field. The expert system has been tested as a stand-alone system using data obtained from numerous laboratory tests, as well as industry data from a grain auger. The tests showed good flexibility in early detection as well as fault monitoring capability. This was achieved by a number of user changeable variables which govern the detection sensitivity.
|Item Type:||Article (Refereed Research - C1)|
|Keywords:||expert system; vibration analysis; condition monitoring|
|Funders:||ARC Linkage Grant|
|Projects and Grants:||Artificial intelligent system for integrated wear debris analysis and vibration analysis in machine condition monitoring (LP0348873)|
|Date Deposited:||17 Feb 2010 04:23|
|FoR Codes:||09 ENGINEERING > 0913 Mechanical Engineering > 091309 Tribology @ 100%|
|SEO Codes:||86 MANUFACTURING > 8614 Machinery and Equipment > 861403 Industrial Machinery and Equipment @ 100%|
|Citation Count from Web of Science||