Adaptive tracking control for stochastic nonlinear systems with time-varying delays using multi-dimensional Taylor network

Adaptive global predefined-time control of robotic systems with output constraints via multiple multidimensional Taylor network

Adaptive global predefined-time control is examined for the n-link robotic system, which involves output constraints. The primary challenge in designing the controller is not only to guarantee that the output constraints are never violated, but also to achieve global convergence of the tracking error within a predefined time. First, a barrier function is introduced to transform the output constrained system into an unconstrained system. Then, the command filtering technique is incorporated into the adaptive multiple multidimensional Taylor network (MMTN) control process. Furthermore, a compensation system is constructed to alleviate for errors arising from filtering. Notably, the designed multi-switching-based adaptive MMTN controller realizes the global stability of robotic systems. Finally, a two-link robotic system simulation is presented to demonstrate the feasibility of the proposed control strategy.

Periodic self-triggered strategy for highly non-linear hybrid stochastic delayed networks based on impulsive control

This article investigates the stabilization issue of highly non-linear hybrid stochastic delayed networks (HSDNs) via periodic self-triggered control under impulse (PS-TCI). Firstly, the existence of a unique global solution for highly non-linear HSDNs under PS-TCI is studied. Then, a stabilization criterion for highly non-linear HSDNs is established, by combining a graph-theoretic approach with a novel Lyapunov-based analysis, based on a 'genuine' Lyapunov function defined by introducing an auxiliary timer. Therein, the less conservative polynomial growth condition and local Lipschitz condition for the drift and diffusion coefficients are used than the linear growth condition and global Lipschitz condition. Meanwhile, the design idea of PS-TCI is based on the evolution of an upper bound of the mathematical expectation for Lyapunov function (not directly Lyapunov function or system state), which implies that the triggered instant of PS-TCI is not a random variable. Finally the theoretical results are employed to study the stability of a class of FitzHugh-Nagumo circuits networks and the central pattern generators networks of a hexapod robot, and correlative numerical simulations are provided for demonstration.

Fuzzy-based collective pitch control for wind turbine via deep reinforcement learning

Wind turbines (WTs) have highly nonlinear and uncertain dynamics due to aerodynamic complexity, mechanical factors, and fluctuations in wind conditions. Turbulence and wind shear add complexity to modelling, especially in constant power region (region 3). Thus, an effective control design demands a deep understanding of the nonlinearities and uncertainties. This paper suggests a novel model-free reinforcement learning (RL) collective pitch angle controller to operate efficiently in region 3. The proposed controller stabilizes generator speed, maximizes power output, and minimizes fluctuations while accommodating system uncertainties, nonlinearity, and pitch limits. The disparity between WT dynamics due to wind speed perturbations and uncertainties is measured using a gap-metric criterion. The controller design adopts a deep deterministic policy gradient (DDPG) algorithm to train six agents in a medium-fidelity WT environment at different mean wind speeds to ensure the controller's robustness. Initially, imitation learning is used for efficient sample collection to fasten training convergence. Afterwards, the agent learns by interacting with the environment. After the training, the pitch control outputs from multi-trained agents are processed by a fuzzy system to have smooth transitions under different operating conditions. The resulting fuzzy DDPG (F-DDPG) controller is deployed to obtain the optimal pitch control action. The performance of the proposed F-DDPG controller is compared to the gain-scheduled PI (GSPI), Linear-Quadratic-Regulator (LQR), and single-DDPG-agent controllers. The controllers are simulated in high-fidelity onshore and offshore 5-MW WT environments using the OpenFAST/MATLAB simulation tools. The results reveal the superiority of the proposed controller in generalizing its optimal performance in different operating conditions.