J. V. R. Prasad

Analysis of Adaptive Neural Networks for Helicopter Flight Control

The design of online adaptive neural networks for use in a nonlinear helicopter e ight control architecture is treated. Emphasis is given to network architecture and the effect that varying the adaptation gain has on performance. Conclusionsarebasedon asix-degree-of-freedom nonlinearevaluation model ofan attackhelicopter and ametricthatmeasuresthenetwork’ sability tocancel theeffectofmodeling errorsforacomplicated maneuver. Thenetwork isshownto providenearlyperfecttracking in thefaceofsignie cantmodelingerrorsand,additionally, to cancel the model inversion error after a short initial period of learning. Furthermore, it is shown that the performance varies gracefully and monotonically improves as the adaptation gain parameter is increased. The effect on control effort is modest and is mainly perceptible only during a short training episode that can be associated with transition from hover to forward e ight.

Adaptive nonlinear controller synthesis and flight test evaluation on an unmanned helicopter

Numerous simulation studies have recently revealed the potential benefits of a neural network-based approach to direct adaptive control in the design of flight control systems. Foremost among the potential benefits is greatly reduced dependence on high-fidelity modeling of system dynamics. However, the methodology has only recently been proven practical by demonstration in an actual flight system. This paper begins with an overview of the design of a nonlinear adaptive control system for flight test on an unmanned helicopter test bed. Next, the design of an outer loop trajectory tracking controller as well as simulation results are presented. The paper concludes with the presentation of preliminary flight test results of the rate command system that document the actual performance of the control system in flight.

Adaptive Output Feedback for High-Bandwidth Flight Control

Adaptive Output Feedback for High-Bandwidth Flight Control A novel adaptive output feedback approach for high-bandwidth flight-control system design is introduced. The approach permits adaptation to both parametric uncertainty and unmodeled dynamics. Of particular interest here is the interaction with poorly modeled high-frequency dynamics. An approximate output feedback linearizing controller is augmented with a neural network. Adaptation is achieved using input/output sequences of the uncertain system. Actuation limits and time delays are also addressed. The approach is illustrated by the design of a pitch-angle flight-control system for a linearized model of an R-50 experimental helicopter.

An open control platform for reconfigurable, distributed, hierarchical control systems

Complex control systems for autonomous vehicles require integrating new control algorithms with a variety of different component technologies and resources. These components are often supported on different types of hardware platforms and operating systems and often must interact in a distributed environment (e.g., in communication with a groundstation, mothership, or other UAVs in a swarm). At the same time, the configuration and integration of components must be flexible enough to allow rapid online reconfiguration and adaptation to react to environmental changes and respond to unpredictable events during flight, such as avoiding a moving obstacle or recovering from vehicle equipment failures. This paper describes an open software architecture, called the open control platform, for integrating control technologies and resources. The specific driving application is supporting autonomous control of VTOL uninhabited autonomous vehicles.

Methodologies for Adaptive Flight Envelope Estimation and Protection

This paper reports the latest development of several techniques for adaptive flight envelope estimation and protection system for aircraft under damage upset conditions. Through the integration of advanced fault detection algorithms, real-time system identification of the damage/faulted aircraft and flight envelop estimation, real-time decision support can be executed autonomously for improving damage tolerance and flight recoverability. Particularly, a bank of adaptive nonlinear fault detection and isolation estimators were developed for flight control actuator faults; a real-time system identification method was developed for assessing the dynamics and performance limitation of impaired aircraft; online learning neural networks were used to approximate selected aircraft dynamics which were then inverted to estimate command margins. As off-line training of network weights is not required, the method has the advantage of adapting to varying flight conditions and different vehicle configurations. The key benefit of the envelope estimation and protection system is that it allows the aircraft to fly close to its limit boundary by constantly updating the controller command limits during flight. The developed techniques were demonstrated on NASA s Generic Transport Model (GTM) simulation environments with simulated actuator faults. Simulation results and remarks on future work are presented.

Development and Demonstration of a Stability Management System for Gas Turbine Engines

Rig and engine test processes and in-flight operation and safety for modem gas turbine engines can be greatly improved with the development of accurate on-line measurement to gauge the aerodynamic stability level for fans and compressors. This paper describes the development and application of a robust real-time algorithm for gauging fan/ compressor aerodynamic stability level using over-the-rotor dynamic pressure sensors. This real-time scheme computes a correlation measure through signal multiplication and integration. The algorithm uses the existing speed signal from the engine control for cycle synchronization. The algorithm is simple and is implemented on a portable computer to facilitate rapid real-time implementation on different experimental platforms as demonstrated both on a full-scale high-speed compressor rig and on an advanced aircraft engine. In the multistage advanced compressor rig test, the compressor was moved toward stall at constant speed by closing a discharge valve. The stability management system was able to detect an impending stall and trigger opening of the valve so as to avoid compressor surge. In the full-scale engine test, the engine was configured with a one-per-revolution distortion screen and transients were run with a significant amount of fuel enrichment to facilitate stall. Test data from a series of continuous rapid transients run in the engine test showed that in all cases, the stability management system was able to detect an impending stall and manipulated the enrichment part of the fuel schedule to provide stall-free transients.

Approximate loop transfer recovery method for designing fixed-order compensators

An approach is outlined for designing fixed-order dynamic compensators for multivariable time-invariant linear systems, based on minimizing a linear quadratic performance index. The formulation is done in an output feedback setting that exploits an observer canonical form to represent the compensator dynamics. The formulation also precludes the use of direct feedback of the plant output. The main contribution lies in defining a method for penalizing the states of the plant and of the compensator, and for choosing the distribution on initial conditions so that the loop transfer matrix approximates that of a full-state feedback design. When linear quadratic regulator theory is used to do the full-state feedback design, the approach can result in good gain and phase margin characteristics. Two examples are given to illustrate the effectiveness of the approach. The first treats the problem of pointing a flexible structure, and the second is a helicopter flight control problem using a tenth-order model for the fuselage and rotor dynamics. Both of the examples considered in this paper are for nonsquare plants.

Nonlinear adaptive control of a twin lift helicopter system

The tracking control of a twin-lift helicopter system in the presence of parametric uncertainty is considered. A nonlinear model is used to describe the dynamics of a twin-lift helicopter configuration in the lateral/vertical plane, and a controller is synthesized using an input-output feedback linearization technique in conjunction with an adaptation algorithm. The control scheme does not require any knowledge of the bound of uncertainties present and drives the output tracking error to zero asymptotically. The performance of the controller is illustrated by simulating the nonlinear model of the twin-lift system.<<ETX>>

Implementation of adaptive nonlinear control for flight test on an unmanned helicopter

Numerous simulation studies have revealed the potential benefits of a neural network-based approach to direct adaptive control in the design of flight control systems. Foremost among the potential benefits is greatly reduced dependence on modeling of system dynamics. However, the methodology has yet to be proven practical by demonstration in an actual flight system. The paper presents an overview of the design of a practical control system for flight test on an unmanned helicopter testbed. Included is a description of the control system hardware and software, as well as the real-time, hardware-in-the-loop simulation facility assembled to prepare for flight testing. Hardware-in-the-loop test results are presented, and flight test plans for the forth quarter of 1998 are discussed.

An open software infrastructure for reconfigurable control systems

Recent advances in software technology have the potential to revolutionize control system design. This paper describes a new software infrastructure for complex control systems, which exploits new and emerging software technologies. It presents an open control platform (OCP) for complex systems, including those that must be reconfigured or customized in real-time for extreme-performance applications. An application of the OCP to the control system design of an autonomous aerial vehicle is described.