Neural Network-Based Adaptive Boundary Control of a Flexible Riser With Input Deadzone and Output Constraint

• Published in: IEEE transactions on cybernetics Vol. 52; no. 12; pp. 13120 - 13128
• Main Authors: Liu, Yu, Wang, Yinna, Feng, Yanghe, Wu, Yilin
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.12.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptive boundary control; Adaptive control; Adaptive systems; Backstepping; backstepping technique; Boundary control; Control design; Control systems design; Control theory; flexible riser; Flexible structures; input deadzone and output constraint; Liapunov functions; neural network; Neural networks; Systems stability; Uncertainty; Vibration control
• ISSN: 2168-2267; 2168-2275; 2168-2275
• DOI: 10.1109/TCYB.2021.3102160

In this article, vibration abatement problems of a riser system with system uncertainty, input deadzone, and output constraint are considered. For obtaining better control precision, a boundary control law is constructed by employing the backstepping method and Lyapunov's theory. The output constraint is guaranteed by utilizing a barrier Lyapunov function. Adaptive neural networks are designed to cope with the uncertainty of the riser and compensate for the effect caused by the asymmetric deadzone nonlinearity. With the designed controller, the output constraint is satisfied, and the system stability is guaranteed through Lyapunov synthesis. In the end, numerical simulation results are provided to display the performance of the developed adaptive neural network boundary control law.