Simple Adaptive Neural Network Controller Design for Modern Agricultural Mechanical Systems

The study presents an adaptive neural network output feedback tracking control scheme for a class of complicated agricultural mechanical systems. The scheme includes a dynamic gain observer to estimate the un-measurable states of the system. The main advantages of the authors scheme are that by introducing non-separation principle design neural network controller and the observer gain are simultaneously tuned according to output tracking error, the semi-globally ultimately bounded of output tracking error and all the states in the closed-loop system can be achieved by Lyapunov approach. With the universal approximation property of NN and the simultaneous parametrisation, no Lipschitz assumption and SPR condition are employed which makes the system construct simple. Finally the simulation results are presented to demonstrate the efficiency of the control scheme.

The adaptive quantised tracking problem is addressed for a class of switched stochastic strict-feedback non-linear systems with asymmetrical input saturation in this study. With the aid of a Gaussian error function-based continuous differentiable switching model and some special techniques, the technical difficulties from dealing with the switching asymmetric saturation non-linearities and the sector-bounded quantisation errors are overcome. Then, by combining the common Lyapunov function method, backstepping technique and neural network approximation-based approach, a simple common adaptive tracking control scheme involving one adaptive parameter only is presented for such systems under arbitrary switching. The given quantised control scheme guarantees that all signals of the closed-loop system are semi-globally bounded in probability while the tracking error can converge to a small neighbourhood of the origin. Finally, simulation studies are provided to illustrate the effectiveness and applicability of the proposed control design.

A crucial role is played by steering-angle prediction in the control of autonomous vehicles (AVs). It mainly includes the prediction and control of the steering angle. However, the prediction accuracy and calculation efficiency of traditional YOLOv5 are limited. For the control of the steering angle, angular velocity is difficult to measure, and the angle control effect is affected by external disturbances and unknown friction. This paper proposes a lightweight steering angle prediction network model called YOLOv5Ms, based on YOLOv5, aiming to achieve accurate prediction while enhancing computational efficiency. Additionally, an adaptive output feedback control scheme with output constraints based on neural networks is proposed to regulate the predicted steering angle using the YOLOv5Ms algorithm effectively. Firstly, given that most lane-line data sets consist of simulated images and lack diversity, a novel lane data set derived from real roads is manually created to train the proposed network model. To improve real-time accuracy in steering-angle prediction and enhance effectiveness in steering control, we update the bounding box regression loss function with the generalized intersection over union (GIoU) to Shape-IoU_Loss as a better-converging regression loss function for bounding-box improvement. The YOLOv5Ms model achieves a 30.34% reduction in weight storage space while simultaneously improving accuracy by 7.38% compared to the YOLOv5s model. Furthermore, an adaptive output feedback control scheme with output constraints based on neural networks is introduced to regulate the predicted steering angle via YOLOv5Ms effectively. Moreover, utilizing the backstepping control method and introducing the Lyapunov barrier function enables us to design an adaptive neural network output feedback controller with output constraints. Finally, a strict stability analysis based on Lyapunov stability theory ensures the boundedness of all signals within the closed-loop system. Numerical simulations and experiments have shown that the proposed method provides a 39.16% better root mean squared error (RMSE) score than traditional backstepping control, and it achieves good estimation performance for angles, angular velocity, and unknown disturbances.

Indirect adaptive control of multi-input-multi-output nonlinear singularly perturbed systems with model uncertainties

Data-based adaptive neural network optimal output feedback control for nonlinear systems with actuator saturation

Deterministic learning-based neural control for output-constrained strict-feedback nonlinear systems

This paper is concerned with the problem of adaptive neural output-feedback control for a class of nonlinear strict-feedback systems. In this research, radial basis function (RBF) neural networks (NNs) are used to approximate the unknown nonlinear functions and a state observer is constructed to estimate the immeasurable state variables. An adaptive neural output feedback control scheme is proposed via backstepping technique. The proposed design method can guarantee semi-global uniform ultimate boundedness (SGUUB) of all signals in the closed-loop system, and ensures the observer errors converge to a small neighborhood. At last, a simulation example is included to show the effectiveness of the proposed method.

Adaptive control of compressor surge instability

This paper discusses the problem of adaptive neural network output feedback control for a class of stochastic nonlinear strict-feedback systems. The concerned systems have certain characteristics, such as unknown nonlinear uncertainties, unknown dead-zones, unmodeled dynamics and without the direct measurements of state variables. In this paper, the neural networks (NNs) are employed to approximate the unknown nonlinear uncertainties, and then by representing the dead-zone as a time-varying system with a bounded disturbance. An NN state observer is designed to estimate the unmeasured states. Based on both backstepping design technique and a stochastic small-gain theorem, a robust adaptive NN output feedback control scheme is developed. It is proved that all the variables involved in the closed-loop system are input-state-practically stable in probability, and also have robustness to the unmodeled dynamics. Meanwhile, the observer errors and the output of the system can be regulated to a small neighborhood of the origin by selecting appropriate design parameters. Simulation examples are also provided to illustrate the effectiveness of the proposed approach.

The Sixth International Symposium on Neural Networks (ISNN 2009)

In this paper, a simple adaptive control strategy is suggested for temperature tracking control of batch processes. A nonlinear controller, which is in structure very simple and consists of a single parameter, is proposed. To enable this controller to control a batch process adaptively, a simple parameter tuning algorithm is derived based on the Lyapunov stability theorem. The proposed adaptive control scheme is directly operational, which does not depend on process model and the only a priori process information required is the system response direction. To demonstrate the effectiveness and applicability of the proposed scheme, illustrative examples are provided. Extensive simulation results reveal that the proposed adaptive control strategy appears to be a simple and effective approach to batch process control, which provides robust control despite the wide range of operating conditions and nonlinear dynamics of the system.

In this paper, an adaptive neural network (NN) constraint control method is studied for a class of uncertain nonlinear nonstrict feedback systems with state constraints. The restrictive assumption that the unknown internal dynamics must possess the monotonically increasing characteristics in previous results is removed. The property of radial basis function (RBF)NNs is used to solve the algebraic loop problem based on the approximation structure. In order to achieve full state constraint satisfactions, the barrier Lyapunov functions (BLFs) are employed in each design procedure. Based on the backstepping and less adjustable parameters techniques, the controllers and the adaptive laws are obtained. By using the Lyapunov stability theory, the boundedness of all signals in the closed-loop system is proved. Therefore, the scheme not only solves the stability problem of the nonstrict feedback system but also overcomes the influence of the state constraint on the control performance. Finally, the effectiveness of the control method is verified by two simulation examples.

An adaptive control scheme is developed for the optimization of a fed-batch ethanol production process. The fermentation process is modeled by an hybrid neural model combining mass balance equations and neural networks, used to represent the kinetic rates. The networks used, the functional link networks (FLN), allow the linear estimation of their parameters; this enables the re-estimation of the parameters at each sampling time, and thus the development of an adaptive optimal control scheme.

Decentralized adaptive neural control of nonlinear interconnected large-scale systems with unknown time delays and input saturation

A robust adaptive NN-based output feedback control scheme is presented for a dynamic positioning ship with uncertainties and unknown external disturbances. We tackle the problem that velocity vector of a ship is not available by employing a high-gain observer, and develop the proposed control approach by combing vectorial backstepping with dynamic surface control approach, which is simpler and easier to implement in engineering practice. The neural network (NN) approximation technique is used to compensate for the uncertainties and unknown external disturbances, and it removes the requirement for the prior knowledge about the vessel parameters and external disturbances. Also, it is demonstrated that the proposed control strategy can force the position and yaw angle of a dynamic positioning ship to approach the desired point while guaranteeing all singles of the designed closed-loop dynamic positioning system semi-globally uniformly ultimately bounded by means of the Lyapunov function. Simulation results of a supply ship illustrate the effectiveness of the proposed scheme.