Journal ArticleDOI
Some new results on system identification with dynamic neural networks
TLDR
The passivity approach is applied to access several new stable properties of neuro identification and it is concluded that the gradient descent algorithm for weight adjustment is stable in an L(infinity) sense and robust to any bounded uncertainties.Abstract:
Nonlinear system online identification via dynamic neural networks is studied in this paper. The main contribution of the paper is that the passivity approach is applied to access several new stable properties of neuro identification. The conditions for passivity, stability, asymptotic stability, and input-to-state stability are established in certain senses. We conclude that the gradient descent algorithm for weight adjustment is stable in an L/sub /spl infin// sense and robust to any bounded uncertainties.read more
Citations
More filters
Journal ArticleDOI
Fuzzy identification using fuzzy neural networks with stable learning algorithms
TL;DR: New learning laws for Mamdani and Takagi-Sugeno-Kang type fuzzy neural networks based on input-to-state stability approach are suggested, which employ a time-varying learning rate that is determined from input-output data and model structure.
Journal ArticleDOI
Passivity analysis of neural networks with time delay
Chunguang Li,Xiaofeng Liao +1 more
TL;DR: The passivity condition for DNNs without uncertainties is derived, and the result is extended to the case with time-varying parametric uncertainties using a Lyapunov-Krasovskii functional construction.
Journal ArticleDOI
Nonlinear system identification using discrete-time recurrent neural networks with stable learning algorithms
TL;DR: In this article, an input-to-state stability approach is applied to access robust training algorithms of discrete-time recurrent neural networks and the authors conclude that for nonlinear system identification, the gradient descent law and the backpropagation-like algorithm for the weights adjustment are stable in the sense of L∞ and robust to any bounded uncertainties.
Journal ArticleDOI
Reinforcement learning for adaptive optimal control of unknown continuous-time nonlinear systems with input constraints
Xiong Yang,Derong Liu,Ding Wang +2 more
TL;DR: An adaptive reinforcement learning-based solution is developed for the infinite-horizon optimal control problem of constrained-input continuous-time nonlinear systems in the presence of nonlinearities with unknown structures by using Lyapunov’s direct method.
Journal ArticleDOI
Adaptive Critic Designs for Event-Triggered Robust Control of Nonlinear Systems With Unknown Dynamics
Xiong Yang,Haibo He +1 more
TL;DR: By using Lyapunov method, it is proved that the derived optimal event-triggered control (ETC) guarantees uniform ultimate boundedness of all the signals in the original system.
References
More filters
Proceedings ArticleDOI
Robust adaptive control
Petros Ioannou,Jing Sun +1 more
TL;DR: In this article, the authors present a model for dynamic control systems based on Adaptive Control System Design Steps (ACDS) with Adaptive Observers and Parameter Identifiers.
Journal ArticleDOI
Neural networks for control systems: a survey
TL;DR: In this paper, the authors focus on the promise of artificial neural networks in the realm of modelling, identification and control of nonlinear systems and explore the links between the fields of control science and neural networks.
Journal ArticleDOI
On characterizations of the input-to-state stability property
Eduardo D. Sontag,Yuan Wang +1 more
TL;DR: In this paper, the Lyapunov sufficient condition for "input-to-state stability" (ISS) is also shown to be necessary and sufficient, which is an open question raised by several authors.
Journal ArticleDOI
Least squares stationary optimal control and the algebraic Riccati equation
TL;DR: In this paper, the optimal control of linear systems with respect to quadratic performance criteria over an infinite time interval is treated, and the integrand of the performance criterion is allowed to be fully quadratically in the control and the state without necessarily satisfying the definiteness conditions which are usually assumed in the standard regulator problem.
Journal ArticleDOI
Passivity, feedback equivalence, and the global stabilization of minimum phase nonlinear systems
TL;DR: In this paper, it was shown that weakly minimum phase nonlinear systems with relative degree one can be globally asymptotically stabilized by smooth state feedback, provided that suitable controllability-like rank conditions are satisfied.