Adaptive Control of a 3 Dof Helicopter Model Using Neural Networks (original) (raw)

Adaptive neural flight control system for helicopter

2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications, 2009

This paper presents an adaptive neural flight control design for helicopters performing nonlinear maneuver. The control strategy uses a neural controller aiding an existing conventional controller. The neural controller uses a real-time learning dynamic radial basis function network, which uses Lyapunov based on-line update rule integrated with the neuron growth criterion. The real-time learning dynamic radial basis function network does not require a priori training and also find a compact network for implementation. The proposed adaptive law provide necessary global stability and better tracking performance. The simulation studies are carried-out using a nonlinear desktop simulation model. The performances of the proposed adaptive control mechanism clearly show that it is very effective when the helicopter is performing nonlinear maneuver.

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

1999

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 Control Based on Neural Networks for an Uncertain 2-DOF Helicopter System With Input Deadzone and Output Constraints

IEEE/CAA Journal of Automatica Sinica, 2019

In this paper, a study of control for an uncertain 2-degree of freedom (DOF) helicopter system is given. The 2-DOF helicopter is subject to input deadzone and output constraints. In order to cope with system uncertainties and input deadzone, the neural network technique is introduced because of its capability in approximation. In order to update the weights of the neural network, an adaptive control method is utilized to improve the system adaptability. Furthermore, the integral barrier Lyapunov function (IBLF) is adopt in control design to guarantee the condition of output constraints and boundedness of the corresponding tracking errors. The Lyapunov direct method is applied in the control design to analyze system stability and convergence. Finally, numerical simulations are conducted to prove the feasibility and effectiveness of the proposed control based on the model of Quanser's 2-DOF helicopter.

Adaptive Control via Backstepping Technique and Neural Networks of a Quadrotor Helicopter

IFAC Proceedings Volumes, 2008

A nonlinear adaptive controller for the quadrotor helicopter is proposed using backstepping technique mixed with neural networks. The backstepping strategy is used to achieve good tracking of desired translation positions and yaw angle while maintaining the stability of pitch and roll angles simultaneously. The knowledge of all physical parameters and the exact model of the quadrotor are not required for the controller, only some properties of the model are needed. In fact, online adaptation of neural networks and some parameters is used to compensate some unmodeled dynamics including aerodynamic effects. Under certain relaxed assumptions, the proposed control scheme can guarantee that all the signals in the closedloop system are Uniformly Ultimately Bounded (UUB). The design methodology is based on Lyapunov stability. One salient feature of the proposed approach is that the controller can be applied to any type of quadrotor helicopter of different masses and lengths within the same class. The feasibility of the control scheme is demonstrated through simulation results.

Robust neural network control of a quadrotor helicopter

Electrical and Computer …, 2008

This paper proposes a new adaptive neural network control to stabilize a quadrotor helicopter against modeling error and considerable wind disturbance. The new method is compared to both deadzone and e-modification adaptive techniques and through simulation demonstrates a clear improvement in terms of achieving a desired attitude and reducing weight drift.

Adaptive trajectory based control for autonomous helicopters

2002

For autonomous helicopters it is common to design a high-performance tracking controller for the attitude dynamics (innerloop) followed by a simpler, lower bandwidth design that tracks commanded position and velocity (outerloop). Separating these two designs places restrictions on the maximum bandwidth of the outerloop. This paper continues to make a conceptual separation between inner and outerloop designs, but, the final choice of compensator gains is made by treating both loops together. The controller design for both loops use feedback linearization with an adaptive element (neural network) to account for model inversion error. Pseudo Control Hedging is used to protect the adaptive element from actuator saturation nonlinearities and also from inner-outerloop interaction. The resulting control system allows position, velocity, attitude and angular rate commands. The outerloop however augments an attitude correction, that allows tracking of position and velocity in addition to attitude and angular rate.

An Adaptive Neural Network Model for Vibration Control in a Blackhawk Helicopter

Journal of the American Helicopter Society, 2005

This work presents an adaptive neural network approach for the identification of a model for the control of the vibration in a Blackhawk helicopter. A feedforward neural network is used to identify a nonlinear model relating the higher harmonic blade pitch motion to the vibration state. An optimal linearization approach is applied at every operating point of interest to obtain a linear model that is locally equivalent to the neural network model at that particular operating point. This linear model can be used to obtain optimal vibration control commands. The data used for development of the model were obtained during the wind tunnel testing of the Blackhawk (UH-60A) rotor in the NASA 80-by-120-foot wind tunnel. Two different modeling approaches were used, linear quasi-static and state-space. The proposed neural-network method of system identification was compared to the least squares method. This comparison showed that the neural network consistently produced lower identification errors. The results obtained also reveal that the approximation performance improves when both the coefficients of the blade pitch motion control commands and the flight parameters are used as inputs.

Modeling and Neural Control of Quadrotor Helicopter

Quadrotor Helicopter or simply quadrotor is rotorcraft that has four lift-generating propellers. Two of the propellers spin clock wise and the other two counter-clockwise. Control of the machine can be achieved by varying relative speed of the propellers. Quadrotor concept is not new, however the modern quadrotors are mostly unmanned. Advancement in miniaturized IMU technology, availability of high speed brushless motors and high power to weight ratio Li-Polymer battery technology, quadrotors can now be successfully designed and fabricated.