Data processing: artificial intelligence – Neural network – Learning task
Reexamination Certificate
2007-06-19
2007-06-19
Starks, Jr., Wilbert L. (Department: 2129)
Data processing: artificial intelligence
Neural network
Learning task
Reexamination Certificate
active
11362426
ABSTRACT:
A system and method for fault detection is provided. The fault detection system provides the ability to detect symptoms of fault in turbine engines and other mechanical systems that have nonlinear relationships between two or more variables. The fault detection system uses a neural network to perform feature extraction from data for representation of faulty or normal conditions. The values of extracted features, referred to herein as scores, are then used to determine the likelihood of fault in the system. Specifically, the lower order scores, referred to herein as “approximate null space” scores can be classified into one or more clusters, where some clusters represent types of faults in the turbine engine. Classification based on the approximate null space scores provides the ability to classify faulty or nominal conditions that could not be reliably classified using higher order scores.
REFERENCES:
patent: 5377305 (1994-12-01), Russo
patent: 5442729 (1995-08-01), Kramer et al.
patent: 5455892 (1995-10-01), Minot et al.
patent: 5479571 (1995-12-01), Parlos et al.
patent: 5485908 (1996-01-01), Wang et al.
patent: 6868325 (2005-03-01), Menon et al.
patent: 2005/0096873 (2005-05-01), Klain
patent: 1363005 (2003-11-01), None
patent: 06114570 (2006-10-01), None
Tolani, et al, Anomaly detection for health management of aircraft gas turbine engines, American Control Conference, 2005, Proceedings of the 2005, Jun. 8-10, 2005, vol. 1, pp. 459-464.
Menon, S., et al., Startup Fault Detection and Diagnosis in Turbine Engines, Proc IEEE Aerospace Conference, vol. 7, Mar. 8, 2003, p. 3069-3074.
U.S. Appl. No. 10/379,413, filed Mar. 3, 2003, Uluyol.
U.S. Appl. No. 11/288,818, filed Nov. 28, 2005, Foslien et al.
U.S. Appl. No. 11/165,985, filed Jun. 24, 2005, Mukherjee et al.
Mark A. Kramer, Nonlinear Principal Component Analysis Using Autoassociative Neural Networks, AlChE Journal, Feb. 1991, 11 pages, vol. 37, No. 2, Cambridge, Massachusetts.
Namrata Vaswani and Rama Chellappa, Classification Probablity Analysis of Principal Component Null Space Analysis, University of Maryland,4 pages, College Park, Maryland.
Leon French, Alioune Ngom, and Luis Rueda, Fast Protein Superfamily Classification using Principal Component Null Space Analysis, University of Windsor, 12 pgs Windsor, Onterio.
Namrata Vaswani and Rama Chellappa, Principal Components Null Space Analysis for Image and Video Classification, University of Maryland, 30 pages, College Park, Maryland.
Kini Venkataramana B.
Menon Sunil K.
Mukherjee Joydeb
Mylaraswamy Dinkar
Honeywell International , Inc.
Ingrassia Fisher & Lorenz
Starks, Jr. Wilbert L.
LandOfFree
Fault detection system and method using approximate null... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Fault detection system and method using approximate null..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Fault detection system and method using approximate null... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3821994