Abstract

Abstract A neural network based adaptive controller for smart structures is designed and validated experimentally. For a truly adaptive control system, the neurocontroller learns online in real time. The Levernberg-Marquardt backpropagation algorithm is implemented for fast learning. Piezoelectric actuators are employed to suppress the vibrations of a cantilevered beam subject to impulse, sine wave, and band-limited white noise disturbances. Experimental results demonstrate excellent closed-loop performance and robustness of the adaptive neurocontroller.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call