Neural Network Dynamic Control Research Articles

Application of LSTM neural network based UAV attitude control in attitude estimation

From now on, Unmanned Aerial Vehicle (UAV) technologies have become more mature, and UAV has been skillfully used in various regions under this mature technology. However, during UAV flight, they often encounter interference from external factors such as airflow, wind and temperature changes, which pose challenges to their stability and flight accuracy. This paper proposes an algorithm what is based on LSTM (Long, Short-Term Memory network), aiming that the flight attitude is affected when it is subject to external interference, while still ensuring the robustness of its flight performance in this state. In this paper, the optimization method of anti-jamming adaptive adjustment based on LSTM. In the meantime, a UAV dynamic model and neural network control based on dynamic modeling are established. Then article established the LSTM rule and designed the PID controller of LSTM. And to prove the effectiveness of the designed PID controller by pilot experiments with Matlab / simulated link simulation and flight experiments. Finally, step size response, autonomous tracking, robustness and anti-interference were tested by experimental simulations.

Robot skill learning system of multi-space fusion based on dynamic movement primitives and adaptive neural network control

This article develops a robot skill learning system with multi-space fusion, simultaneously considering motion/stiffness generation and trajectory tracking. To begin with, surface electromyography (sEMG) signals from the human arm is captured based on the MYO armband to estimate endpoint stiffness. Gaussian Process Regression (GPR) is combined with dynamic movement primitive (DMP) to extract more skills features from multi-demonstrations. Then, the traditional DMP formulation is improved based on the Riemannian metric to encode the robot’s quaternions with non-Euclidean properties. Furthermore, an adaptive neural network (NN)-based finite-time admittance controller is designed to track the trajectory generated by the motion model and to reflect the learned stiffness characteristics. In this controller, a radial basis function neural network (RBFNN) is employed to compensate for the uncertainty of the robot dynamics. Finally, experimental validation is conducted using the ROKAE collaborative robot, confirming the effectiveness of the proposed approach. In summary, the presented framework is suitable for human-robot skill transfer method that require simultaneous consideration of position and stiffness in Euclidean space, as well as orientation on Riemannian manifolds.

Dynamic surface adaptive RBF neural network control for a class of non‐linear uncertain systems

AbstractAn adaptive neural network dynamic surface control method for strict feedback non‐linear systems with model uncertainty is proposed in this paper. The uncertain parts are approached by RBF neural network; meanwhile, the virtual controller is designed to make system stable according to dynamic surface control. The method of Lyapunov is used to prove the stability and convergence of the system. The simulation results prove the feasibility of this controller and prove that the controller has an advantage to approach the uncertain non‐linear system and make system have well convergence and traceability.

Distributed Adaptive Path-Following Control for Distance-Based Formation of Fixed-Wing UAVs under Input Saturation

This paper investigates the distance-based formation and cooperative path-following control problems for multiple fixed-wing unmanned aerial vehicles (UAVs). In this study, we design the distance-based formation control structure to achieve the virtual leader and followers pre-defined rigid formation pattern, ensuring simultaneously relative localization. A path-following control strategy based on adaptive dynamic surface and neural network control technology is proposed to approximate the uncertain disturbances of the environment and unmodeled dynamics. And the longitudinal and lateral subsystems’ adaptive fault-tolerant controllers are designed, respectively, to achieve the fault-tolerant control of UAVs’ formation in three-dimensional environments. Furthermore, the adaptive sliding mode controller with an auxiliary controller is designed to realize the UAVs path following with limited input saturation. Finally, simulation examples are given to clarify and verify the effectiveness of the theoretical results.

Dynamic Output Feedback and Neural Network Control of a Non-Holonomic Mobile Robot.

This paper presents the design and synthesis of a dynamic output feedback neural network controller for a non-holonomic mobile robot. First, the dynamic model of a non-holonomic mobile robot is presented, in which these constraints are considered for the mathematical derivation of a feasible representation of this kind of robot. Then, two control strategies are provided based on kinematic control for this kind of robot. The first control strategy is based on driftless control; this means that considering that the velocity vector of the mobile robot is orthogonal to its restriction, a dynamic output feedback and neural network controller is designed so that the control action would be zero only when the velocity of the mobile robot is zero. The Lyapunov stability theorem is implemented in order to find a suitable control law. Then, another control strategy is designed for trajectory-tracking purposes, in which similar to the driftless controller, a kinematic control scheme is provided that is suitable to implement in more sophisticated hardware. In both control strategies, a dynamic control law is provided along with a feedforward neural network controller, so in this way, by the Lyapunov theory, the stability and convergence to the origin of the mobile robot position coordinates are ensured. Finally, two numerical experiments are presented in order to validate the theoretical results synthesized in this research study. Discussions and conclusions are provided in order to analyze the results found in this research study.

Application of Dynamic Neural Network Model for Magneto- Coulombic Attitude Control of Earth-Pointing Satellite

An active control of the satellite attitude using magneto-Coulombic actuators is proposed along the circular orbit. Equation for the required charges on the Coulomb shells is derived, which is used to find the available control torque along the three body axes. It is proved that the eigenvalues of the averaged control matrix of the magneto-Coulombic system in the body reference frame for different orientations and angular velocities components will converge to the same values as in the case of the eigenvalues of the averaged control matrix in the orbital reference frame. A dynamic neural network based control law is adapted and trained for the proposed system. The neural network based dynamic neural network controller has the advantages of handling the non-linearity, adaptation and on-board training, and robust to large changes in the parameters in the plant, such as the moments of inertia. It is shown that the stabilization accuracy of the dynamic neural controller is higher as compared to the proportional-derivative based controller.

Dynamic Event-Triggered Adaptive NN Control for Switched Uncertain Nonlinear Systems.

This article is concerned with the problem of dynamic event-triggered adaptive neural network (NN) control for a class of switched strict-feedback uncertainty nonlinear systems. A novel switched command filter-based dynamic event-triggered adaptive NN control approach is set up by exploiting the backstepping and command filter and the common Lyapunov function method. Since adaptive controllers of subsystems are event triggered, then if the switching happens between any two consecutive triggering instants, asynchronous switching will arise between candidate controllers of subsystems and subsystems. Unlike the existing literature, where maximum asynchronous time is restricted, without any strict limitations on maximum asynchronous time being needed in this article, the asynchronous switching problem is directly handled by proposing a novel switching dynamic event-triggered mechanism (DETM) and event-triggered adaptive controllers of subsystems. Moreover, a piecewise constant variable is introduced into the switching DETM, which overcomes the difficulty of switched measurement error being discontinuous. Also, a strictly positive lower bound of interevent times is obtained. Finally, a continuous stirred tank reactor system and a numerical example are presented to demonstrate the effectiveness of the developed approach.

Composing Diverse Policies for Temporally Extended Tasks

Robot control policies for temporally extended and sequenced tasks are often characterized by discontinuous switches between different local dynamics. These change-points are often exploited in hierarchical motion planning to build approximate models and to facilitate the design of local, region-specific controllers. However, it becomes combinatorially challenging to implement such a pipeline for complex temporally extended tasks, especially when the sub-controllers work on different information streams, time scales and action spaces. In this letter, we introduce a method that can automatically compose diverse policies comprising motion planning trajectories, dynamic motion primitives and neural network controllers. We introduce a global goal scoring estimator that uses local, per-motion primitive dynamics models and corresponding activation state-space sets to sequence diverse policies in a locally optimal fashion. We use expert demonstrations to convert what is typically viewed as a gradient-based learning process into a planning process without explicitly specifying preand post-conditions. We first illustrate the proposed framework using an MDP benchmark to showcase robustness to action and model dynamics mismatch, and then with a particularly complex physical gear assembly task, solved on a PR2 robot. We show that the proposed approach successfully discovers the optimal sequence of controllers and solves both tasks efficiently.

Hybrid Dynamic Neural Network and PID Control of Pneumatic Artificial Muscle Using the PSO Algorithm

Pneumatic artificial muscles (PAM) have been recently considered as a prominent challenge regarding pneumatic actuators specifically for rehabilitation and medical applications. Since accomplishing accurate control of the PAM is comparatively complicated due to time-varying behavior, elasticity and ambiguous characteristics, a high performance and efficient control approach should be adopted. Besides of the mentioned challenges, limited course length is another predicament with the PAM control. In this regard, this paper proposes a new hybrid dynamic neural network (DNN) and proportional integral derivative (PID) controller for the position of the PAM. In order to enhance the proficiency of the controller, the problem under study is designed in the form of an optimization trend. Considering the potential of particle swarm optimization, it has been applied to optimally tune the PID-DNN parameters. To verify the performance of the proposed controller, it has been implemented on a real-time system and compared to a conventional sliding mode controller. Simulation and experimental results show the effectiveness of the proposed controller in tracking the reference signals in the entire course of the PAM.

Prescribed performance dynamic neural network control for a flexible hypersonic vehicle with unknown control directions

In this article, we examine the system control design of a flexible hypersonic vehicle with an unknown direction control. Prescribed performance controls, backstepping controls, and radial basis function neural network are used to design the controllers. Different from a traditional radial basis function neural network, the fully tuned dynamic radial basis function neural network has a better approximation ability; and the weight vector, respective centers, and width of the Gaussian function of neural network are regulated by adaptive laws designed in the controller. The proof and analysis of stability are taken in this article for the fully tuned dynamic neural network introduced to control the system. Furthermore, prescribed performance control can guarantee the tracking errors satisfy the specified conditions. The unknown control direction is solved with the Nussbaum function in the controller. Finally, the simulations demonstrate the effectiveness and corrective measures of the control strategy.

Adaptive dynamic surface neural network control for nonstrict-feedback uncertain nonlinear systems with constraints

This paper presents an adaptive dynamic surface neural network control for a class of nonstrict-feedback uncertain nonlinear systems subjected to input saturation, dead zone and output constraint. The problem of input saturation is solved by designing an anti-windup compensator, and the issue of output constraint is addressed by introducing tan-type Barrier Lyapunov function. Furthermore, based on adaptive backstepping technique, a series of novel stabilizing functions are derived. First-order sliding mode differentiator is introduced into backstepping design to obtain the first-order derivative of virtual control. The real control input is obtained using dead-zone inverse method. It is proved that the proposed control scheme can achieve finite time convergence of the output tracking error into a small neighbor of the origin and guarantee all the closed-loop signals are bounded. Simulation results demonstrate the effectiveness of the proposed control scheme.

Optimal hybrid scheme of dynamic neural network and PID controller based on harmony search algorithm to control a PWM-driven pneumatic actuator position

In this paper, the position of a pulse width modulation (PWM)-driven pneumatic actuator has been controlled using a dynamic neural network (DNN) and Proportional Integral Derivative (PID) controller. The harmony search algorithm (HSA) has been used to unravel the optimization problem. The DNN controller is optimally designed to control the position of the actuator. As to the performance of the PID controller, it can assist the DNN controller to give better results. Therefore, an optimal hybrid scheme with both DNN and PID controllers based on HSA is suggested. A pneumatic circuit containing a fast-switching valve is used to reduce the complexity of the PWM-driven servo pneumatic system along with its cost price.

Adaptive Tracking in Mobile Robots With Input-Output Linearization

This paper presents a neural network adaptive controller for trajectory tracking of nonholonomic mobile robots. By defining a point to follow (look-ahead control), the path-following problem is solved with input-output linearization. A computed torque plus derivative (PD) controller and a dynamic inversion neural network controller are responsible for reducing tracking error and adapting to unmodeled external perturbations. The adaptive controller is implemented through a hidden layer feed-forward neural network, with weights updated in real time. The stability of the whole system is analyzed using Lyapunov theory, and control errors are proven to be bounded. Simulation results demonstrate the good performance of the proposed controller for trajectory tracking under external perturbations.

A Novel Trajectory Tracking Control Method for a Nonholonomic Mobile Robot with System Uncertainties and Disturbances

This paper focuses on the trajectory tracking problem of mobile robots with system uncertainties and disturbances. With the integration of a kinematic controller and a dynamic controller, a hybrid control method is presented. Firstly, an adaptive kinematic controller is proposed through the kinematic model and backstepping method. Secondly, a neural network dynamic controller is proposed, with the consideration of system uncertainties and disturbances. The stability of the proposed control scheme is verified via the Lyapunov method and Barbalat lemma. Finally, results of circular trajectory simulation have illustrated the effectiveness of the present control scheme.

Comparative Study between Robust Control of Robotic Manipulators by Static and Dynamic Neural Networks

A comparative study between static and dynamic neural networks for robotic systems control is considered. So, two approaches of neural robot control were selected, exposed, and compared. One uses a static neural network; the other uses a dynamic neural network. Both compensate the nonlinear modeling and uncertainties of robotic systems. The first approach is direct; it approximates the nonlinearities and uncertainties by a static neural network. The second approach is indirect; it uses a dynamic neural network for the identification of the robot state. The neural network weight tuning algorithms, for the two approaches, are developed based on Lyapunov theory. Simulation results show that the system response, equipped by dynamic neural network controller, has better tracking performance, has faster response time, and is more reliable to face disturbances and robotic uncertainties.

Tracking Control of Underactuated Unmanned Surface Vessels Based on the Dynamic Fuzzy Neural Network

This paper proposes a dynamic fuzzy neural network (DFNN) for the tracking control of the underactuated unmanned surface vessels. The dynamic fuzzy neural network control algorithm has the advantages of both fuzzy logical and neural network. The algorithm adjusts the structure and parameters on line at the same time to make the tracking effect of the system being fast and accurate, while it doesn’t need confirm the fuzzy rules and the nodes of hidden layer. The simulation experiments based on the proposed control algorithm are carried out and the simulation results validate its effectiveness.

Adaptive dynamic output feedback neural network control of uncertain MIMO nonlinear systems with prescribed performance.

An adaptive dynamic output feedback neural network controller for a class of multi-input/multi-output affine in the control uncertain nonlinear systems is designed, capable of guaranteeing prescribed performance bounds on the system's output as well as boundedness of all other closed loop signals. It is proved that simply guaranteeing a boundedness property for the states of a specifically defined augmented closed loop system is necessary and sufficient to solve the problem under consideration. The proposed dynamic controller is of switching type. However, its continuity is guaranteed, thus alleviating any issues related to the existence and uniqueness of solutions. Simulations on a planar two-link articulated manipulator illustrate the approach.

Effect of SMES unit in load following contract in a restructured power system

The purpose of this paper is to analyze the effect of SMES unit on the Dynamic Neural Network (DNN) based multi area AGC scheme. The advantage of the DNN controller is that it does not require extensive and rigorous model for optimal tuning. It requires a set of training data. The training data can be generated from the system model. The developed DNN controller has been tested on a practical Indian power system network representing 75- bus system. A deregulated electricity market scenario has been assumed in the 75- bus system, which has been divided into four control areas. Mixed transaction (Poolco and bilateral) has been considered in the frequency regulation.

Chaos Synchronization Using Adaptive Dynamic Neural NetworkController with Variable Learning Rates

This paper addresses the synchronization of chaotic gyros with unknown parameters and external disturbance via an adaptive dynamic neural network control (ADNNC) system. The proposed ADNNC system is composed of a neural controller and a smooth compensator. The neural controller uses a dynamic RBF (DRBF) network to online approximate an ideal controller. The DRBF network can create new hidden neurons online if the input data falls outside the hidden layer and prune the insignificant hidden neurons online if the hidden neuron is inappropriate. The smooth compensator is designed to compensate for the approximation error between the neural controller and the ideal controller. Moreover, the variable learning rates of the parameter adaptation laws are derived based on a discrete‐type Lyapunov function to speed up the convergence rate of the tracking error. Finally, the simulation results which verified the chaotic behavior of two nonlinear identical chaotic gyros can be synchronized using the proposed ADNNC scheme.

Dynamic neural network controller model of PEM fuel cell system

This paper presents the artificial intelligence techniques to control a proton exchange membrane fuel cell system process, using particularly a methodology of dynamic neural network. In this work a dynamic neural network control model is obtained by introducing a delay line in the input of the neural network. A static production system including a PEMFC is subjected to variations of active and reactive power. Therefore the goal is to make the system follow these imposed variations. The simulation requires the modelling of the principal element (PEMFC) in dynamic mode. The simulation results demonstrate that the model-based dynamic neural network control scheme is appropriate for controlling, the stability of the identification and the tracking error were analyzed, and some reasons for the usefulness of this methodology are given.