It is reported that many modern approaches to damage identification are "based on the idea of pattern recognition (PR)." (Worden and Barton, 2003) A PR algorithm is stated to be one that assigns to a sample of measured data a class label, usually from a finite set. In the case of damage identification, the measured data could be vibration modeshapes, full-field thermoelastic data, scattered wave profiles etc. The appropriate class labels would encode damage type, location etc. In order to carry out the higher levels of identification using PR, it will almost certainly be necessary to construct examples of data corresponding to each class." (Worden and Barton, 2003, p.3) It is additionally reported that the "holistic approach to fault identification "requires that the diagnostic system should be carefully designed with the objectives in mind." (Worden and Barton, 2003, p.3)

Prior to this a pre-planning or evaluation stage is desirable and is defined by Farrar and Doebling (2000) which requires the architect of the monitoring system to first: (1) provide economic and/or life safety jurisdictions for performing the monitoring; (2) define system-specific damage including types of damage and expected locations (e.g. Failure Modes Effects Analysis (FMEA) and Failure Modes Effects and Criticality Analysis (FMECA); (3) Define the operational and environmental conditions under which the system functions; (4) define the operational and environmental conditions under which the system functions; (5) define the limitations on data acquisition in the operational environment. (Worden and Barton, 2003, p.3)

The work of Lin and Makis (2003) entitled: "Recursive Filters for a Partially Observable System Subject to Random Failure" reports the consideration of a failure-prone system which operates in continuous time and is subject to condition monitoring at discrete time epochs..." And states that the assumption made is that "the state of the system evolves as a continuous-time Markov process with a finite state space." (Lin and Makis, 2003, p.1) It is reported that the observation process is "stochastically related to the state process which is unobservable, except for the failure state." (Lin and Makis, 2003, p.1)

Combination of the information on failure and the information contained from condition monitoring and the use of the change of measure approach results in derivation of a general recursive filter and it is related that in special cases that obtained were recursive formulae for the state estimation and other quantities of interest. Up-dated parameter estimates are obtained using the EM algorithm." (Lin and Makis, 2003, p.1)

The work of Farrar and Lieven (2006) entitled: "Damage Prognosis: The Future of Structural Health Monitoring" states that "some of the most rapidly evolving technologies that will impact the ability to perform DP are associated with sensing, processing and telemetry hardware. There are extensive efforts underway at both academic and corporate research centers to develop large-scale, self-organizing and embedded sensing networks...

(Farrar and Lieven, 2006)
Farrar and Lieven (2006) conclude by stating that DP is developing and integrating sensing hardware, data interrogation software and predictive modeling software that will prove more robust than the component and system level hardware the DP system is intended to identify."

Bibliography

Dale, A.K. (1984) The Analysis of Gear Noise Excitation. Journal of the Society of Environmental Engineers.

Dempsey, P.J., Afjeh, A.A. (2003) Integrating Oil Debris and Vibration Gear Damage Detection Technologies Using Fuzzy Logic." International 58th Annual Forum and Technology Display, Quebec (Canada) June 11 -- 13, 2002.

Farrar, Charles R. And Lieven, Nick A. (2007) Damage Prognosis: The Future of Structural Health Monitoring. Phil. Trans. R. Soc. A. 12 Dec 2007. Online available at: http://institutes.lanl.gov/ei/shm/pubs/PTRS%20Prognosis%2006.pdf

Hauser, G. (1985) A New Analysis Procedure for Noise and Vibration Diagnosis of Rotating Machinery. Paper presented at the INgenieurburo fur Technische Adkustik, West Germany.

International, 1979, p. 51 -- 59.

Liao, G., Liu, S., Shi, T., and Zhang, G. (2004) Gearbox Condition Monitoring Using Self-Organizing Feature Maps. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science. Vol. 218, Number 1, 2004. Online available at: http://journals.pepublishing.com/content/f343n26023856353/

Lin, Daming and Makis, Viliam (2003) Recursive Filters for a Partially Observable System Subject to Random Failure. Adv. In Appl. Probab. Vol. 35, No. 1(2003). Online available at: http://projecteuclid.org/DPubS?service=UI&version=1.0&verb=Display&handle=euclid.aap/1046366106

Online available at:

http://tiau.ac.ir/media/File/library/ieee/ASME%20PAPERS/Vibration%20Journal/helicopter%20gearbox.pdf

Roger, L.M. (1979) The Application of Vibration Analysis and Acoustic Emission Source Location to Online Condition Monitoring of Anti-Friction Bearings." Tribology

Tumer, Irem Y. And Huff, Edward M. (2003) Analysis of Triaxial Vibration Data for Health Monitoring of Helicopter Gearboxes. Vol. 125. January 2003. ASME.

Vecer, P., Kreidl, M. And Smid, R. (2005) Condition Indicators for Gearbox Condition Monitoring Systems. Acta Polytechnica. Vol. 45 No. 6. http://tiau.ac.ir/media/File/library/ieee/ASME%20PAPERS/Vibration%20Journal/helicopter%20gearbox.pdf

Worden, Keith and Barton, Janice (2003) Condition Monitoring: Lecture 1 -- Intelligent Fault Detection in Systems and Structures I. Sheffield 2003. Online available at: http://www.dynamics.group.shef.ac.uk/people/keith/mec415/lecture_1.pdf