Data processing: vehicles – navigation – and relative location – Vehicle control – guidance – operation – or indication – Aeronautical vehicle
Reexamination Certificate
2000-05-22
2001-12-18
Camby, Richard M. (Department: 3661)
Data processing: vehicles, navigation, and relative location
Vehicle control, guidance, operation, or indication
Aeronautical vehicle
C700S048000, C244S075100
Reexamination Certificate
active
06332105
ABSTRACT:
TECHNICAL FIELD
The present invention is generally related to vehicle control systems and, more particularly, is related to a system and method for using a neural network to provide predictive vehicle performance envelope limit information.
BACKGROUND OF THE INVENTION
Modern rotorcraft are constrained by a variety of complex limits, or boundaries, on their flight envelopes. Often the onset of such limits are difficult to detect and not easily perceived by the pilot. It is common practice to impose simplified operational limits that restrict the true performance and maneuverability of the aircraft. The need to monitor operational limits using conventional cues such as cockpit instruments can result in excessive pilot workload. In some cases, direct sensor measurement of a limit may not be available.
A flight envelope limiting or carefree handling control system must perform two functions: (1) detection; and (2) limit avoidance. The system must detect the encroachment of an envelope limit, and then it must take appropriate action to prevent the violation of the limit.
There are two current methods proposed to overcome the problem of envelope limiting. One known approach is to take advantage of modern fly-by-wire (FBW) control Systems and use sensor-feedback to prevent limit violation. This form of “carefree” control is currently used on modern fixed-wing aircraft and is being studied for use on helicopters and advanced V/STOL aircraft. Such studies are discussed in the following three references, which are herein fully incorporated by reference, Howett, J., “Carefree Handling for Super-Agility”, American Helicopter Society Aero Mechanics Specialists Conference, Fairfield County, Conn., October 1995; King, D. W., et al., “V-22 Load Limiting Control law Development”, American Helicopter Society 49
th
Annual Forum, St. Louis, Miss., May 1993; and Miller, D. G. and Black, T. M. “Tilt Rotor Control Law Design for Rotor Loads Alleviation Using Modern Control Techniques”, American Control Conference, June 1991. More specifically, this approach has been applied to fixed-wing aircraft for load factor and stall protection, as disclosed in Corps, S. G., “Airbus A320 Side Stick and Fly By Wire—an Update”, proceedings of SAE 5
th
Aerospace Behavioral Engineering Technology Conference, Long Beach, Calif. 1987; and Ilopueaife, O., “Design of Deep Stall Protection for the C-17A”, AIAA Guidance, Navigation, and (Control Conference, San Diego, Calif., July 1996, both of which are herein fully incorporated by reference. The “carefree” control is also known to be applied to rotorcraft for torque and rotor speed protection, as disclosed in Howitt, J., “Carefree Maneuvering in Helicopter Flight Control”, American Helicopter Society 51
st
Annual Forum, Ft. Worth, Tex., May, 1995; and Kimball, D. F., “Recent Tilt Rotor Flight Control Law Innovations”, 88AHS Journal, 1987, both of which are herein fully incorporated by reference. Similar techniques have been applied for structural load limiting control laws on vehicles, such as the V-22 aircraft. This approach has been shown to effectively prevent envelope violations in a way that is transparent to the pilot. However, for some applications, the use of feedback control to provide envelope limiting has certain limitations, including but not limited to: the fact that necessary sensor data is not always available, that limiting feedback can change the response characteristics of the aircraft and thereby confuse the pilot or degrade handling qualities; there is no inherent override capability if the pilot needs to violate a limit in an emergency situation; the pilot may not be aware of approaching limits; and many rotorcraft are not equipped with a full authority FBW control systems. The direct feedback approach tends to further disassociate the pilot from the envelope limits. In fact, the use of fill-authority FBW control system introduces new envelope limit problems in the form of control saturation limits.
In such a system, the normal control response of the aircraft will be altered resulting in either a reduction in stick sensitivity or an effective deadband in control response.
An alternative known approach to limit avoidance is to provide some form of enhanced cueing to the pilot. Simulation studies have shown that tactile feedback in the pilot control inceptors is the most effective means of envelope limit cueing, as disclosed in Whalley, M. S. in Achache, M. “Joint U.S./France Investigation of Helicopter Flight Envelope Limit Cueing”, American Helicopter Society 52
nd
Annual Forum, Washington, D.C., June 1996; and Whalley, M. S., “A Piloted Simulation Investigation of a Helicopter Limit Avoidance System Using a Polynomial Neural Network”, NASA/TM-1988-112220, January 1998, both of which are herein incorporated by reference.
The tactile cueing can take the form of a “soft stop” in the force-feel curve of the control stick. When using such an approach it is critical to ensure that the cueing clearly enunciates the onset of the limit while not distracting from the performance of the pilot task.
As such, when using a pilot cueing system, it is desirable that the limit detection algorithm estimate future values of a limited parameter in order to provide a sufficient time margin for the pilot to react to the cue. Certain combinations of large control inputs might create a situation where a limit violation is unavoidable. Because there is a time lag between the pilot control input and the aircraft response, a limit avoidance cueing system based on instantaneous data would allow such input and therefore would not be a reliable envelope protection system.
Thus, it is desirable to achieve a prediction lead time. This approach has the advantage that the pilot has overriding capability to exceed the limit in an emergency. The disadvantage of this approach is that limits may still be easily exceeded if the pilot is distracted and workload may be increased if pilot attention is required to monitor the cueing device.
In either of the methods discussed above, it is necessary to extract some sort of information about the limited parameter, using sensor data, in order to cue the pilot or to drive the flight control system. In some cases, the desired information is not directly obtainable from available sensors. Furthermore, if a particular parameter changes rapidly, instantaneous sensor data may not be effective as the flight control system or pilot cueing cannot respond quickly enough to prevent the limit from being exceeded.
Thus, it is desirable to develop a system that can predict the future value of a limited parameter based on the available sensor data and current control positions. Such a system must be constructed based on data from a flight test aircraft or from an accurate simulation model.
The feasibility of using neural networks to synthesize complex envelope limit information and to provide control limit information has been demonstrated in the field.
Two factors drive the demand for the use of neural networks in conjunction with envelope protection systems. One driving factor is the need to synthesize limit information where there is no direct sensor measurement. Another factor is the need to predict the future response of a limit parameter in order to have adequate lead time to avoid the limit.
Studies have shown the capability of neural networks to synthesize complex loads data by training the network with flight test data from instrumented aircraft, such as disclosed in Haas, D. J., Flitter, L. A., and Milano, J., “Helicopter Flight Data Feature Extraction or Component Load Monitoring”, AIAA 35
th
Structures, Structural Dynamics, and Materials Conference, Hilton Head, S.C., April 1994; and Haas, D. J., McCool, K., and Flitter, L. A., “Development and Flight Test Evaluation of a Rotor System Load Monitoring Technology”, American Helicopter Society 54
th
Annual Forum, Washington, D.C. May 1998, which are herein fully incorporated by reference.
In these studies, neural networks were trained to generate instantaneous data. It was shown that a predi
Calise Anthony J.
Horn Joseph F.
Prasad Jonnalagadda V. R.
Camby Richard M.
Georgia Tech Research Corporation
Thomas Kayden Horstemeyer & Risley LLP
LandOfFree
Neural network based automatic limit prediction and... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Neural network based automatic limit prediction and..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network based automatic limit prediction and... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2591192