This paper summarizes a data fusion approach for utilizing conventional lubrication parameters in an unconventional method for identifying deterioration in a thermally coupled system. Complex machines are composed of multiple systems that are intrinsically dependent. Design of these systems requires expertise in distinct disciplines with a determined focus on meeting system-specific requirements. This expertise focused approach promotes a silo mindset to system design, which is then carried through to the design and implementation of the health management system of these machines. These multidisciplinary interacting systems are traditionally monitored as independent entities, with little advantage taken of the direct and cross-coupled effects. For example, parameters required for lubrication health monitoring include, but are not limited to, oil pressure and temperature. These parameters are critical in determining the health of the lubrication system. However, how these parameters change can be an indicative of the health of interacting systems otherwise considered independent and isolated. By exploring the rationale of the cross-system impacts, physical interactions between these systems (albeit empirical knowledge) can be used for cross-system monitoring. A means of achieving this objective is to utilize parameters that are measured in one system to determine the diagnostic state of another coupled system with limited, or no, system observability. A fuzzy logic fusion approach is employed in this task and was designed and implemented for the above-mentioned purpose. The focus of interest was on the lubrication and hot section interactions with parameters obtained from real machines. Fuzzy membership functions and rules were determined and tuned appropriately from real data and applied to nominal and defective machines.

References

References
1.
Kyriacos
,
U.
,
Jelsma
,
J.
, and
Jordan
,
S.
,
2011
, “
Monitoring Vital Signs Using Early Warning Scoring Systems: A Review of the Literature
,”
J. Nurs. Manag.
,
19
(
3
), pp.
311
330
.
2.
Dvorák
,
A.
, and
Novák
,
V.
,
2004
, “Fuzzy Logic as a Methodology for the Treatment of Vagueness,”
The Logica Yearbook
,
L.
Behounek
, and
M.
Bilkova
, eds.,
Filosofia
,
Prague
, pp.
141
151
.
3.
Rajora
,
R.
, and
Dixit
,
H. K.
,
2013
, “
Effect of Lube Oil Temperature on Turbine Shaft Vibration
,”
J. Mech. Eng. Robot. Res.
,
2
(
2
), pp.
324
334
.
4.
Volponi
,
A.
,
Brotherton
,
T.
, and
Luppold
,
R.
,
2004
, “
Development of an Information Fusion System for Engine Diagnostics and Health Management
,”
AIAA 1st Intelligent Systems Technical Conference
,
Chicago, IL
,
Sept. 20–22
.
5.
Zadeh
,
L. A.
,
1997
, “
Toward a Theory of Fuzzy Information Granulation and its Centrality in Human Reasoning and Fuzzy Logic
,”
Fuzzy Sets Syst.
,
90
(
2
), pp.
111
127
.
6.
Dempsey
,
P. J.
, and
Afjeh
,
A. A.
,
2004
, “
Integrating Oil Debris and Vibration Gear Damage Detection Technologies Using Fuzzy Logic
,”
J. Am. Helicopter. Soc.
,
49
(
2
), pp.
109
116
.
7.
Byington
,
C. S.
,
Merdes
,
T. A.
, and
Kozlowski,
,
J. D.
,
1999
, “
Fusion Techniques for Vibration and Oil Debris/Quality in Gearbox Failure Testing
,”
Proceedings of International Condition Monitoring Conference
,
University of Wales, Swansea
,
Apr. 12–16
,
M. H.
Jones
and
D. G.
Sleeman
, eds.,
Coxmoor Publishing
,
Oxford
.
You do not currently have access to this content.