Decision Layer by Fusion of Diagnostic Algorithms
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
For manufacturers systems monitoring or production equipment optimization solutions are founded on specific algorithms that produce low level local information about risk of degradation or production loss. In either case local results are combined in synthetic reports aimed to help decision taking at higher level. This work is about the description of an automatic fusion mechanism able to build expert output with direct understanding of the system behavior and help to infer causes of efficiency loss. An example application was built and tested in a semiconductor fab. The algorithms diagnosed yield degradation in different subsystems or work-area and were digested in a weekly report that highlighted the main production problems. We deployed the same methodology for condition based maintenance of aircraft engines on a test platform. The first part of this document sketches out some notations, the second part describes the semiconductor application and the conclusion is dedicated to the transfer in the aeronautic domain for the decision level of an engine fleet health monitoring system.
How to Cite
##plugins.themes.bootstrap3.article.details##
neural network, diagnostics, fusion, decision, genetic algorithm
Figueiras-Vidal, A. R., & Rokach, L. (2012). An Exploration o f Research Directions in Machine Ensemble Theory and Applications. In ESANN (pp. 25– 27). Bruges.
Flandrois, X., Lacaille, J., Masse, J.-R., & Ausloos, A. (2009). Expertise Transfer and Automatic Failure Classification for the Engine Start Capability System. In AIAA InfoTech.
Jacobs, R. A., Jordan, M. I., Nowlan, S. J., & Hinton, G. E. (1991). Adaptive Mixtures of Local Experts. Neural Computation, 3(1), 79–87. doi:10.1162/neco.1991.3.1.79
Klein, R., Rudyk, E., & Masad, E. (2011). Decision and Fusion for Diagnostics of Mechanical Components. In PHM (pp. 1–9). Montreal (Canada): PHMSociety.
Lacaille, J. (2005). Mathematical Solution to Identify the Causes of Yield Deterioration. In International Sematech Manufacturing Initiative (ISMI). Austin, TX: Sematech.
Lacaille, J. (2008). Global Predictive Monitoring System for a Manufacturing Facility. PDF Solutions. Patent US 2008082197 A1.
Lacaille, J. (2009). Standardized failure signature for a turbofan engine. In IEEE Aerospace conference (p. 11/0505). Big Sky (MT): IEEE Aerospace society. doi:10.1109/AERO.2009.4839670
Lacaille, J. (2010). Identification of Defects in an Aircraft Engine. Patent WO 2010076469 A1.
Lacaille, J. (2012). Validation Environment of Engine Health Monitoring Algorithms. In Snecma (Ed.), IEEE Aerospace conference. Big Sky (MT).
Lacaille, J., & Dubus, H. (2005). Defectivity Analysis by a Swarm of Intelligent Distributed Agents. In AEC-APC. Indian Wells (CA), Sematech.
Lacaille, J., & Nya Djiki, R. (2010). Detection of Anomalies in an Aircraft Engine. Patent WO 2010061136 A1.
Ricordeau, J., & Lacaille, J. (2010). Application of Random Forests to Engine health Monitoring. In ICAS.
Romessis, C., Kyriazis, A., & Mathioudakis, K. (2007). Fusion of Gas Turbines Diagnostic Inference - The Dempster-Schafer Approach. In ASME & GT (Vol. 1). Montreal.
Singh, S., & Holland, S. W. (2010). Trends in the Development o f System-Level Fault Dependency Matrices. In IEEE Aerospace conference. IEEE Aerospace society.
Tang, L., Kacprzynski, G. J., Goebel, K., Vachtsevanos, G., Odel, B. A. M., & Echniques, S. E. T. (2009). Methodologies for Uncertainty Management in Prognostics. In IEEE Aerospace conference. IEEE Aerospace society.
Yu, L., Cleary, D., Osborn, M., & Rajiv, V. (2007). Information Fusion Strategy for Aircraft Engine Health Management. In ASME & GT (pp. 1–8). Montreal.
Yuksel, S. E., Wilson, J. N., & Gader, P. D. (2012). Twenty Years of Mixture of Experts. IEEE Transactions on Neural Networks and Learning Systems, 23(8), 1177– 1193. doi:10.1109/TNNLS.2012.2200299
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.