Neural network–based active control of a rigid–flexible spacecraft with bounded input

A novel attitude control strategy based on active disturbance rejection control (ADRC) and input shaping technique was proposed for a flexible spacecraft without angular velocity sensors. Aiming at achieving high rapidity and high pointing accuracy, we focus on the suppression of vibration of flexible appendages when the spacecraft's attitude maneuvers a large angle. In the proposed scheme, a transient process which combines path planning for attitude maneuver with input shaping is designed to reduce vibration of flexible appendages. Furthermore, an extended state observer (ESO) for the flexible spacecraft is designed to estimate the immeasurable attitude angular velocity and the disturbances, which include parameter uncertainties and external disturbances. Also a nonlinear attitude feedback control law is designed to track the desired attitude and compensate the disturbances in real time way. Simulation results demonstrate the effectiveness and robustness of the proposed control strategy.

In this paper, we propose a new control strategy for flexible spacecraft attitude maneuvers in the presence of an uncertainty inertia matrix, actuator constraints and external disturbances. The Vibration of flexible appendages, inertia matrix uncertainty and external disturbances (coming from space environmental, sensors and actuators error, etc.) are considered as the total disturbance to be estimated on-line by extended state observer. An inverse optimal control law is designed based on the Sontag-type formula and the control Lyapunov function. A radial basis function neural network based saturation compensator is embedded into the controller to reduce the effect of the control input saturation on the system. It shows that extended controller guarantees stabilization, input constraint satisfaction and achieves exact asymptotic disturbance rejection and H ∞ optimality without solving the associated Hamilton-Jacobi-Isaacs partial differential equation directly. The performance of the proposed control approaches are illustrated through numerical simulations.

In this paper, the problem of attitude tracking control for a class of vertical take-off landing (VTOL) aircraft in the presence of uncertain disturbances is addressed. The active disturbance rejection control (ADRC) method is utilized to address uncertain disturbances, while the radial basis function (RBF) neural network is considered for handling unknown nonlinear dynamics. By incorporating a modified tracking differentiator, a nonlinear state error feedback controller, and an extended state observer, the disturbance observation problem in the aircraft system is solved. These disturbances, seen as a combined disturbance in the aircraft system, are counteracted through the extended state observer. Furthermore, the unknown nonlinear dynamics within the aircraft system are approximated using the RBF neural network. Subsequently, the paper suggests adaptive ADRC strategies based on neural network and formulates adaptive control laws to estimate unknown parameters. The Lyapunov stability theory proves the effectiveness of the proposed control strategies. The simulation results show that the attitude tracking control problem of VTOL aircraft can be achieved under the proposed control strategies and adaptive control laws.

This paper introduces tracking control method for robot manipulator based on Active Disturbance Rejection Control technique (ADRC). The main purpose of the ADRC technique is to obtain a proper estimation, cancel the total disturbance along with the assurance of a good trajectory tracking. First, the equations of motion of the robot manipulator is rearranged to be suitable for the ADRC technique. Then, an extended model is derived from the dynamic model. This extended model has an extra state includes the total disturbances, which are estimated online through the extended state observer (ESO). Finally, this estimated disturbance is compensated through a simple PD feedback controller. This control strategy is tested on two-DOF serial link manipulator and compared by a simple PID controller. Simulation results show the advantage of the ADRC system over the PID controller.

The control stability and accuracy of quad tiltrotor UAVs is improved when encountering external disturbances during automatic flight by an active disturbance rejection control (ADRC) parameter self-tuning control strategy based on a radial basis function (RBF) neural network. Firstly, a nonlinear flight dynamics model of the quad tiltrotor UAV is established based on the approach of component-based mechanistic modeling. Secondly, the effects of internal uncertainties and external disturbances on the model are eliminated, whilst the online adaptive parameter tuning problem for the nonlinear active disturbance rejection controller is addressed. The superior nonlinear function approximation capability of the RBF neural network is then utilized by taking both the control inputs computed by the controller and the system outputs of the quad tiltrotor model as neural network inputs to implement adaptive parameter adjustments for the Extended State Observer (ESO) component responsible for disturbance estimation and the Nonlinear State Error Feedback (NLSEF) control law of the active disturbance rejection controller. Finally, an adaptive attitude control system for the quad tiltrotor UAV is constructed, centered on the ADRC-RBF controller. Subsequently, the efficacy of the attitude control system is validated through simulation, encompassing a range of flight conditions. The simulation results demonstrate that the Integral of Absolute Error (IAE) of the pitch angle response controlled by the ADRC-RBF controller is reduced to 37.4° in comparison to the ADRC controller in the absence of external disturbance in the full-states mode state of the quad tiltrotor UAV, and the oscillation amplitude of the pitch angle response controlled by the ADRC-RBF controller is generally reduced by approximately 50% in comparison to the ADRC controller in the presence of external disturbance. In comparison with the conventional ADRC controller, the proposed ADRC-RBF controller demonstrates superior performance with regard to anti-disturbance capability, adaptability, and tracking accuracy.

This paper presents an active disturbance rejection control (ADRC) method based on radial basis function (RBF) neural network applied to current tracking control of active power filter (APF). It is difficult to accurately model the active power filter system, and the uncertainty of the nonlinear system brings difficulties to the system analysis and control. In this paper, under the ADRC framework, a tracking differentiator (TD) is introduced to obtain the differential information of the reference signal and a nonlinear extended state observer (ESO) is constructed to estimate the state variables and the total disturbance. The nonlinear ESO realizes the feedforward compensation of disturbance, and the state feedback adopts the PD form. Further, the RBF neural network is designed to estimate the unknown parameter b of the system. The simulation results show that the proposed control method has good steady-state and dynamic performance.

This paper uses a radial basis function (RBF) neural network for star identification. A feature vector consisting of distance and angle cosine values is constructed as a library of recognition feature stars and input to the neural network. Then, the network’s output is the number of the corresponding primary star. Comparing the training efficiency and robustness of the grid algorithm with the BP neural network and radial basis function neural network for star identification, the experimental results show that the radial basis function neural network has a strong anti-interference ability against noise and pseudo-star interference. The following conclusions are drawn from the simulation tests: the sample recognition rate of radial basis function neural network algorithm can reach 96% for star position and star addition noise; when the proportion of pseudo-star reaches 20%, the sample recognition rate of radial basis function neural network algorithm is still higher than grid algorithm and BP neural network, which indicates that the radial basis function neural network algorithm has the solid anti-interference ability to both noise and pseudo-star. Therefore, the radial basis function neural network algorithm based on star Identification has specific application prospects.

Based on active disturbance rejection control technique and characteristics of electric power steering, a steering angle tracking controller is designed, which consists of an aligning moment estimator to deal with modeling error and nonlinearity of electric power steering. The aligning moment estimator is based on an extended state observer and takes steering system friction and differential drive steering torque, which is a unique phenomenon in a distributed drive electric vehicle, into consideration. According to the estimated aligning moment and tracking differentiator, the steering angle tracking controller is designed based on a nonlinear state feedback control and feedforward compensation control laws. Results of various simulations and experiments, including pivot steering, step input steering, and sinusoidal input steering, show that the proposed controller has good performance in tracking reference steering angle and is convenient to implement. With the aligning moment estimator, the proposed controller shows better results in comparative experiments than a conditional integral-based steering angle tracking controller.

This paper presents a Radial Basis Function neural network based higher-order Sliding Mode Control for robust control of a dynamical system. A conventional sliding mode controller is suffering from a chattering problem, and the Super Twisting Algorithm is a special kind of higher-order Sliding Mode Control that has the capability of minimizing the chattering problem. There are also unknown model parameters and external disturbances that exert a negative influence on the control performance. To address the issues of model uncertainties and chattering, a Radial Basis Function (RBF) neural network based Super Twisting Algorithm is designed. The RBF neural network evaluates the model parameters and uncertainties, while the Super Twisting approach mitigates chattering, hence improving the controller’s overall performance. Lyapunov stability based adaptive laws are derived for online updating of the parameters of the neural network. The proposed control algorithm was tested on a 2-degree-of-freedom serial flexible joint robotic arm to investigate its efficacy. The controller has a lower control chattering amplitude, lower control energy consumption, and a good tracking response, when compared to the RBF based conventional Sliding Mode controller and simple STA controller, as shown by the results.

In this paper, a radial basis function (RBF) neural network based sliding mode control is presented. Taking CW equation as dynamics model, the parameter perturbation and external disturbance has been considered. The controller consists of two parts, one is the feed-forward control, and the other is feedback sliding mode control using RBF neural network. Based on Lyapunov stability theory, the adaptive law of neural network has been obtained. Simulation results suggest that the control scheme can initialize the formation and maintain the relative motion according to the desired trajectory. The inherent chattering of sliding mode control has been weaken and the accuracy of trajectory tracking has greatly improved with the use of RBF neural network.

With large-scale integration of wind power in power systems, the impact of wind generation on power system stability has become an important issue. In this paper, a new power oscillation damping controller based on active disturbance rejection control technique for DFIG-based wind turbine generators is presented. The proposed power oscillation damping controller utilizes the grid frequency at the point of common coupling to generate the active power modulation, so as to damp power system oscillations. The kinetic energy of the rotating masses of wind turbine generators is utilized to provide the required damping active power. Case study on a two-area system verifies the effectiveness of the proposed power oscillation damping controller.

Fault diagnosis for wireless sensor is very important to ensure signal acquisition precision. Radial basis function (RBF) neural network has strong classification ability. However, the selection of the connection weights, the hidden centers and the widths has an important influence on the classification performance of the RBF neural network in the learning process of RBF neural network. Thus, ant colony optimization is employ to gain the parameters of radial basis function neural network. Therefore, a novel method for fault diagnosis of wireless sensor based on RBF neural network and ant colony optimization is presented. The results of computational experiments show that ACO- RBF neural network has a great higher than RBF neural network.

Digital image recognition of plant diseases could reduce the dependence of agricultural production on the professional and technical personnel in plant protection field and is conducive to the development of plant protection informatization. In order to find out a method to realize image recognition of plant diseases, four kinds of neural networks including backpropagation (BP) networks, radial basis function (RBF) neural networks, generalized regression networks (GRNNs) and probabilistic neural networks (PNNs) were used to distinguish wheat stripe rust from wheat leaf rust and to distinguish grape downy mildew from grape powdery mildew based on color features, shape features and texture features extracted from the disease images. The results showed that identification and diagnosis of the plant diseases could be effectively achieved using BP networks, RBF neural networks, GRNNs and PNNs based on image processing. For the two kinds of wheat diseases, the best prediction accuracy was 100% with the fitting accuracy equal to 100% while BP networks, GRNNs or PNNs were used, and the best prediction accuracy was 97.50% with the fitting accuracy equal to 100% while RBF neural networks were used. For the two kinds of grape diseases, the best prediction accuracy was 100% with the fitting accuracy equal to 100% while BP networks, GRNNs or PNNs were used, and the best prediction accuracy was 94.29% with the fitting accuracy equal to 100% while RBF neural networks were used.

In this paper, the problem of spacecraft attitude control using adaptive neural network disturbance compensation technique is investigated. The proposed disturbance observer is developed based on the Radial Basis Function (RBF) neural network. Firstly, the RBF neural network algorithm and spacecraft dynamic model are given. Then, the RBF neural network observer is developed to estimate the external disturbance moment. Using the estimated information, an adaptive neural network disturbance compensation controller is designed. Meanwhile, the stability of closed-loop attitude control system is analyzed by using Lyapunov approach. The simulation results show that compared with the traditional PD controller, the developed control scheme can decrease the effect of the external disturbance and has a better control performance.

Aiming at the tip trajectory tracking against system parameter uncertainty and disturbance during the painting process of the spray painting manipulator, a sliding model active disturbance rejection trajectory tracking controller is designed integrating terminal sliding mode control (SMC) approach and active disturbance rejection control (ADRC) technique. The reference curve trajectory of the tip position/velocity is planned by the kinematics equation. in which the compensation is taken into account for the deflection of the manipulator. The extended state observer (ESO) is used to estimate the total disturbance consisting of the uncertain system parameters and the uncertain interference resulting from deflection and load. Utilizing non-singular terminal sliding mode control, a feedback control law is designed to achieve fast and accurate trajectory tracking. Simultaneously, according to the actual system parameters in the engineering, the simulation validation is given to show that the proposed control strategy can guarantee good tracking performance of the closed-loop system.