Decision and Fusion for Diagnostics of Mechanical Components



Published Sep 25, 2011
Renata Klein Eduard Rudyk Eyal Masad


Detection of damaged mechanical components in their early stages is crucial in many applications. The diagnostics of mechanical components is achieved most effectively using vibration and/or acoustical measurements, sometimes accompanied by oil debris indications. The paper describes a concept for fusion and decision for mechanical components, based on vibroacoustic signatures. Typically in diagnostics of complex machinery, there are numerous records from normally operating machines and few recordings with damaged components. Diagnostics of each mechanical component requires consideration of a large number of features. Learning classification algorithms cannot be applied due to insufficient examples of damaged components. The proposed system presents a solution by introducing a hierarchical decision scheme. The proposed architecture is designed in layers imitating expert’s decision reasoning. The architecture and tools used allow incorporation of expert’s knowledge along with the ability to learn from examples. The system was implemented and tested on simulated data and real-world data from seeded tests. The paper describes the proposed architecture, the algorithms used to implement it and some examples.

How to Cite

Klein, R. ., Rudyk, E. ., & Masad, E. . (2011). Decision and Fusion for Diagnostics of Mechanical Components. Annual Conference of the PHM Society, 3(1).
Abstract 166 | PDF Downloads 147



decisioning, diagnostic algorithm, feature extraction, vibration analysis, bearing fault detection, fusion

Antoni, J., Randall, R. B., (2002, April), Differential Diagnosis of Gear and Bearing Faults, Journal of Vibration and Acoustics, Vol. 124 pp. 165-171.

Bhavaraju, K. M, Kankar, K., Sharma, S. C., Harsha, S. P., (2010). A Comparative Study on Bearings Faults Classification by Artificial Neural Networks and Self- Organizing Maps using Wavelets, International Journal of Engineering Science and Technology, Vol. 2(5), 2010, pp. 1001-1008.

García-Prada, J., C., Castejón, C., Lara, O. J., (2007). Incipient bearing fault diagnosis using DWT for feature extraction, 12th IFToMM World Congress, Besançon (France), June18-21, 2007.

Hariharan, V., Srinivasan, PSS. (2009). New Approach of Classification of Rolling Element Bearing Fault using Artificial Neural Network, Journal of Mechanical Engineering, Vol. ME 40, No. 2, December 2009, Transaction of the Mech. Eng. Div., The Institution of Engineers, Bangladesh, pp. 119-130.

Klein, R., Rudyk, E., Masad, E., Issacharoff M., (2009a). Emphasizing bearings’ tones for prognostics, The Sixth International Conference on Condition Monitoring and Machinery Failure Prevention Technologies, pp. 578- 587.

Klein, R., Rudyk, E., Masad, E., Issacharoff M., (2009b). Model Based Approach for Identification of Gears and Bearings Failure Modes, International Journal of
Prognostics and Health Management.

Klein, R., Rudyk, E., Masad, E. (2011). Methods for diagnostics of bearings in non-stationary environment, CM2011-MFPT2011 Conference Proceedings. June 20- 22, Cardiff, UK.

Li, R., Sopon, P., He, D., (2009). Fault features extraction for bearing prognostics, Journal of Intelligent Manufacture, DOI 10.1007/s10845-009-0353-z.

MIMOSA, OSA-CBM V3.1L: Open Systems Architecture for Condition-Based Maintenance,

Neapolitan, R.E., (2003). Learning Bayesian Networks, Prentice Hall Series in Artificial Intelligence, Prentice Hall (April 6, 2003), ISBN-13: 978-0130125347.

Ocak, H., Loparo, K. A., (2001). A new bearing fault detection and diagnosis scheme based on hidden Markov modeling of vibration signals, IEEE International Conference on Acoustics, Speech, and Signal Processing, 2001 Proceedings (ICASSP '01). May 07-11, Salt Lake City, UT, USA.
Technical Research Papers

Most read articles by the same author(s)