Keywords and Phrases
Backstepping; Event-Sampling; Lyapunov Method; Neural Network; Output-Feedback; Quadrotor UAV
"Neural networks (NNs) are utilized in the backstepping approach to design a control input by approximating unknown dynamics of the strict-feedback nonlinear system with event-sampled inputs. The system state vector is assumed to be unknown and an observer is used to estimate the state vector. By using the estimated state vector and backstepping design approach, an event-sampled controller is introduced. As part of the controller design, first, input-to-state-like stability (ISS) for a continuously sampled controller that has been injected with bounded measurement errors is demonstrated and, subsequently, an event-execution control law is derived such that the measurement errors are guaranteed to remain bounded. Lyapunov theory is used to demonstrate that the tracking errors, the observer estimation errors, and the NN weight estimation errors for each NN are locally uniformly ultimately bounded (UUB) in the presence bounded disturbances, NN reconstruction errors, as well as errors introduced by event-sampling. Simulation results are provided to illustrate the effectiveness of the proposed controllers.
Subsequently, the output-feedback neural network (NN) controller that was presented above is considered for an underactuated quadrotor UAV application. The flexibility for the control of a quadrotor UAV is extended by incorporating notions of event-sampling and by designing an appropriate event-execution law. First, the continuously sampled controller is considered in the presence of bounded measurement errors and it is shown that the system generates a local ISS-like Lyapunov function. Next, by designing an appropriate event-execution law, the measurement errors that result from event-sampling are shown to be bounded for all time. Finally, the effectiveness of the proposed event-sampled controller is demonstrated with simulation results"--Abstract, page iv.
Sarangapani, Jagannathan, 1965-
Stanley, R. Joe
Electrical and Computer Engineering
M.S. in Electrical Engineering
National Science Foundation (U.S.)
Missouri University of Science and Technology. Intelligent Systems Center
Intelligent Systems Center
Missouri University of Science and Technology
Journal article titles appearing in thesis/dissertation
- Event-sampled direct adaptive nn output- and state-feedback control of uncertain strict-feedback system
- Event-sampled control of quadrotor unmanned aerial vehicle
x, 114 pages
© 2016 Nathan Szanto
Thesis - Open Access
Drone aircraft -- Control systems -- Design and construction
Drone aircraft -- Control systems -- Mathematical models
Neural networks (Computer science)
Electronic OCLC #
Szanto, Nathan, "Event-sampled direct adaptive neural network control of uncertain strict-feedback system with application to quadrotor unmanned aerial vehicle" (2016). Masters Theses. 7616.