DocumentCode :
3205858
Title :
Assessment of data and knowledge fusion strategies for prognostics and health management
Author :
Roemer, Michael J. ; Kacprzynski, G.J. ; Orsagh, Rolf F.
Author_Institution :
Impact Technol. LLC, Rochester, NY, USA
Volume :
6
fYear :
2001
fDate :
2001
Firstpage :
2979
Abstract :
Various data, feature and knowledge fusion strategies and architectures have been developed over the last several years for improving upon the accuracy, robustness and overall effectiveness of anomaly, diagnostic and prognostic technologies. Fusion of relevant sensor data, maintenance database information, and outputs from various diagnostic and prognostic technologies has proven effective in reducing false alarm rates, increasing confidence levels in early fault detection, and predicting time to failure or degraded condition requiring maintenance action. The data fusion strategies discussed are principally probabilistic in nature and are used to aid in directly identifying confidence bounds associated with specific component fault identifications and predictions. Dempster-Shafer fusion, Bayesian inference, fuzzy-logic inference, neural network fusion and simple weighting/voting are the algorithmic approaches that are discussed. Data fusion architectures such as centralized fusion, autonomous fusion, and hybrid fusion are described in terms of their applicability to fault diagnosis and prognosis. The final goal is to find the optimal combination of measured system data, data fusion algorithms, and associated architectures for obtaining the highest overall prediction/detection confidence levels associated with a specific application. To achieve this goal, a set of metrics has been developed for gauging the performance and effectiveness of a fusion strategy. Specifically, this paper demonstrates how various metrics are used for assessing individual and fused vibration-based diagnostic algorithms. Evaluation of the diagnostic strategies was performed using gearbox seeded-fault and accelerated failure data
Keywords :
backpropagation; belief networks; computerised monitoring; condition monitoring; diagnostic expert systems; diagnostic reasoning; fault diagnosis; feature extraction; fuzzy logic; machine testing; maintenance engineering; neural nets; sensor fusion; uncertainty handling; vibration measurement; Bayesian inference; Dempster-Shafer fusion; a priori probability; accelerated failure data; autonomous fusion; backpropagation; centralized fusion; component fault identification; confidence level; data fusion strategies; degraded condition; early fault detection; false alarm rates reduction; fault diagnosis; feature extraction; fuzzy-logic inference; gearbox seeded-fault; health management; hybrid fusion; knowledge fusion strategies; maintenance database information; neural network fusion; optimal combination; prognostic technologies; simple weighting/voting; time to failure; vibration-based diagnostic algorithms; Bayesian methods; Degradation; Fault detection; Fault diagnosis; Inference algorithms; Neural networks; Robustness; Sensor fusion; Spatial databases; Voting;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Aerospace Conference, 2001, IEEE Proceedings.
Conference_Location :
Big Sky, MT
Print_ISBN :
0-7803-6599-2
Type :
conf
DOI :
10.1109/AERO.2001.931318
Filename :
931318
Link To Document :
بازگشت