Adaptive Neural Network Control of Zero-Speed Vessel Fin Stabilizer Based on Command Filter

This paper proposes a zero-speed vessel fin stabilizer adaptive neural network control strategy based on a command filter for the problem of large-angle rolling motion caused by adverse sea conditions when a vessel is at low speed down to zero. In order to avoid the adverse effects of the high-frequency part of the marine environment on the vessel rolling control system, a command filter is introduced in the design of the controller and a command filter backstepping control method is designed. An auxiliary dynamic system (ADS) is constructed to correct the feedback error caused by input saturation. Considering that the system has unknown internal parameters and unmodeled dynamics, and is affected by unknown disturbances from the outside, the neural network technology and nonlinear disturbance observer are fused in the proposed design, which not only combines the advantages of the two but also overcomes the limitations of the single technique itself. Through Lyapunov theoretical analysis, the stability of the control system is proved. Finally, the simulation results also verify the effectiveness of the control method.

Adaptive Neural Network Control of Time Delay Teleoperation System Based on Model Approximation

A bilateral neural network adaptive controller is designed for a class of teleoperation systems with constant time delay, external disturbance and internal friction. The stability of the teleoperation force feedback system with constant communication channel delay and nonlinear, complex, and uncertain constant time delay is guaranteed, and its tracking performance is improved. In the controller design process, the neural network method is used to approximate the system model, and the unknown internal friction and external disturbance of the system are estimated by the adaptive method, so as to avoid the influence of nonlinear uncertainties on the system.

Steering angle prediction YOLOv5-based end-to-end adaptive neural network control for autonomous vehicles

The combination of steering angle prediction and control of autonomous vehicles (AVs) is a challenging task. To improve the real-time steering angle prediction accuracy and the effectiveness of steering control, a novel steering angle prediction YOLOv5-based end-to-end adaptive neural network control for AVs is proposed. Firstly, since most of the lane line datasets are simulated images and lack of diversity, a novel lane dataset derived from the real roads are made manually to train the You Only Look Once version 5 (YOLOv5) network model. To improve the detection accuracy of the network model, the Generalized Intersection over Union (GIoU) of the bounding box regression loss function is updated to a Complete Intersection over Union (CIoU) with a better convergence effect. Furthermore, the neural network-based controller and disturbance observer are proposed to effectively control the steering angle predicted by YOLOv5 and estimate the lumped uncertainty. Meanwhile, a composite adaptive updating law is constructed by utilizing the tracking error and modeling error to improve steering performance. Finally, the system stability is proved by Lyapunov theory and the effectiveness of the proposed method is verified with experiments.

Adaptive neural network control for nonlinear cyber-physical systems subject to false data injection attacks with prescribed performance

Cyber-physical systems (CPSs), as emerging products of industry 4.0 , play a key role in the development of intelligent manufacturing. This paper proposes an observer-based adaptive neural network (NN) control for nonlinear strict-feedback CPSs subject to false data injection attacks. Since there may be strict constraints on the state or output signals of nonlinear cyber-physical systems (NCPSs), we propose a time-varying asymmetric barrier Lyapunov function to realize the specific output constraints of NCPSs under cyber-attacks. Besides, since false data injection attacks will corrupt the transmitted state variables, an observer is designed to obtain observations of the exact states, and NN is used to approximate the unknown nonlinearity of NCPSs. With the proposed control strategy, the constraint control problem of NCPSs subject to false data injection attacks is settled. Finally, a numerical simulation example verifies the effectiveness of the proposed controller. This article is part of the theme issue ‘Towards symbiotic autonomous systems’.

Adaptive neural network control of second-order underactuated systems with prescribed performance constraints

This paper studies the trajectory tracking control problem of second-order underactuated system subject to system uncertainties and prescribed performance constraints. By combining radial basis function neural networks (RBFNNs) with input–output linearization methods, an adaptive neural network-based control approach is proposed and the adaptive laws are given through Lyapunov method and Taylor expansion linearization approach. The main contributions of this paper are that: (1) by introducing weight performance function and transformation function, the states never violate the prescribed performance constraints; (2) the control scheme takes the unknown control gain direction into consideration and the singular problem of control design can be avoided; (3) through rigorously stability analysis, all signal of closed-loop system are proved to be uniformly ultimately bounded. The effectiveness of the proposed control scheme was verified by comparative simulation.