Data processing: vehicles – navigation – and relative location – Vehicle control – guidance – operation – or indication – With indicator or control of power plant
Reexamination Certificate
2003-09-05
2004-10-12
Black, Thomas G (Department: 3663)
Data processing: vehicles, navigation, and relative location
Vehicle control, guidance, operation, or indication
With indicator or control of power plant
C123S479000, C060S039010, C702S104000, C702S115000, C700S029000
Reexamination Certificate
active
06804600
ABSTRACT:
FIELD OF THE INVENTION
This invention generally relates to diagnostic systems, and more specifically relates to sensor fault detection in turbine engines.
BACKGROUND OF THE INVENTION
Modern aircraft are increasingly complex. The complexities of these aircraft have led to an increasing need for fault detection systems. These fault detection systems are designed to monitor the various systems of the aircraft in an effort to detect potential faults. These systems are designed to detect these potential faults such that the potential faults can be addressed before the potential faults lead to serious system failure and possible in-flight shutdowns, take-off aborts, and delays or cancellations.
Engines are, of course, a particularly critical part of the aircraft. As such, fault detection for aircraft engines are an important part of an aircrafts fault detection system. Engine sensors play a critical role in fault detection. Typical modem turbine engine systems include several sets of engine sensors, such as engine speed sensors, fuel sensors, pressure sensors and temperature sensors. These sensors provide critical data to the operation of the turbine engine, and provide the core data used in fault detection.
Because of the critical importance of turbine engine sensors there is a strong need for sensor performance validation and compensation. Sensor validation generally includes fault detection and isolation, the determination of when one of the sensors is faulty and the isolation of which particular sensor in a group of sensor is at fault. Current practice in sensor fault detection generally relies upon range and rate checks for individual sensors. This technique, while acceptable for some circumstances, may not be able to consistently detect engine sensor faults that can occur, especially in-range sensor faults. Likewise, the current practice of fault isolation relies upon qualitative cause-effect relationships based on design documents and expressed in terms of fault trees. These qualitative cause-effect relationships are typically based on a baseline of a new engine, and thus can become obsolete as sensor aging, engine wear, deterioration and other variations cause inconsistencies in sensor readings. Thus, the current systems used for sensor fault detection and isolation have had limited effectiveness.
Thus, what is needed is an improved system and method for detecting and isolating sensor faults in turbine engines.
BRIEF SUMMARY OF THE INVENTION
The present invention provides a sensor error compensation system and method that provides improved sensor anomaly detection and compensation. The sensor error compensation system includes an expected value generator and a sensor fault detector. The expected value generator receives sensor data from a plurality of sensors in a turbine engine. From the sensor data, the expected value generator generates an expected sensor value for a sensor under test. The expected sensor value is passed to the sensor fault detector. The sensor fault detector compares the expected sensor value to a received sensor value to determine if a sensor error has occurred in the sensor under test. If an error has occurred, the error can be compensated for by generating a replacement sensor value to substitute for erroneous received sensor value.
In one embodiment, the expected value generator comprises an auto-associative model configured to generate expected sensor values from the plurality of sensor values received from the engine sensors. In another embodiment, the expected value generator comprises a hetero-associative model that is configured to generate an expected sensor value from a plurality of sensor values from other
The foregoing and other objects, features and advantages of the invention will be apparent from the following more particular description of a preferred embodiment of the invention, as illustrated in the accompanying drawings.
REFERENCES:
patent: 3902315 (1975-09-01), Martin
patent: 4058975 (1977-11-01), Gilbert et al.
patent: 4161101 (1979-07-01), Drummond
patent: 4212161 (1980-07-01), Newirth et al.
patent: 4228650 (1980-10-01), Camp
patent: 5497751 (1996-03-01), Ohtake
patent: 5570300 (1996-10-01), Henry et al.
patent: 5680409 (1997-10-01), Qin et al.
patent: 6067032 (2000-05-01), Anderson et al.
patent: 6098011 (2000-08-01), Scott
patent: 6298718 (2001-10-01), Wang
patent: 6347289 (2002-02-01), VanderLeest
patent: 6393355 (2002-05-01), Muramatsu
patent: 2004/0030417 (2004-02-01), Gribble et al.
patent: 09257034 (1997-09-01), None
patent: 569873 (1977-09-01), None
Nwadiogbu Emmanuel O.
Uluyol Onder
Black Thomas G
Honeywell International , Inc.
Robert Desmond, Esq.
To Tuan C
LandOfFree
Sensor error detection and compensation system and method does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Sensor error detection and compensation system and method, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Sensor error detection and compensation system and method will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3273954