Proposed Neural Network Control Research Articles

Online learning based neural network adaptive controller for efficient power tracking of PWR type reactor with unknown internal dynamics

An online learning neural network (NN) based adaptive scheme has been proposed for tracking the power level of higher order point kinetic pressurized water reactor (PWR) with unknown dynamics under local and global load following conditions and emergency conditions. The PWR type of nuclear reactors are linear parameter varying (LPV) systems whose parameters vary with power, ageing effects and changes in nuclear core reactivity with fuel burn up. The drastic changes in plant parameters should be accommodated in a reactor control system through on-line identification to ensures safe operation for the power plant which demands for adaptive control system. To track the demand changes which happens during the load following and emergency conditions considered, the PID controller parameters needs to be varied. However, the proposed NN controller is based on feedback linearisation of nonlinear discrete time system with unknown internal dynamics by using a multilayer neural network acting as function approximator. Online weight tuning algorithm based on a modified delta rule and projection algorithm are used for the update of the weights of the proposed neural network controller along with conventional PID controller. Simulation studies with the proposed controller on a non linear PWR core shows that the proposed algorithm exhibits improved performance in terms of lesser ISE/ IAE/ ITAE over using PID controller under load following conditions. This new proposed power level controller has self learning capability and it needs the measurement of all the state variables and the desired trajectory.

Development and Control of Magnetorheological Elastomer-Based Semi-active Seat Suspension Isolator Using Adaptive Neural Network

The present study aims at development of a magnetorheological elastomer (MRE) based semi-active seat suspension isolator and its adaptive control using neural network (NN) control scheme. Isotropic MRE samples with 25% volume fraction of iron particles have been fabricated and then characterized under shear mode using a rotary magneto-rheometer to obtain MRE’s viscoelastic properties (shear storage and loss moduli) under different levels of applied magnetic flux density. Results reveal a significant change in the storage and loss moduli with respect to the varied magnetic field. The viscoelastic properties of the MRE are then utilized to design an MRE-based seat suspension isolator in order to attenuate the transmitted vibration to the driver. For this purpose, the modeling of the seat incorporated with the MRE-based isolator is derived and subsequently, a novel NN control scheme is proposed for the semi-active control of the MRE-based isolator. The convergence and stability of the proposed control strategy have been mathematically verified using the Lyapunov method. Finally, the performance of the proposed control strategy is compared with those obtained using passive and widely used sky-hook controllers under different types of excitation including harmonic motion, road bump, and random profile. It is shown that the proposed NN controller considerably mitigates the vibration of the driver seat and outperforms the passive and skyhook controllers over the frequency range of interest.

DSP Implementation of a Neural Network Vector Controller for IPM Motor Drives

This paper develops a neural network (NN) vector controller for an interior mounted permanent magnet (IPM) motor by using a Texas Instrument TMS320F28335 digital signal processor (DSP). The NN controller is developed based on the complete state-space equation of an IPM motor and it is trained to achieve optimal control according to approximate dynamic programming (ADP). A DSP-based NN control system is built for an IPM motor drives system, and a high efficient DSP program is developed to implement the NN control algorithm while considering the limited memory and computing capability of the TMS320F28335 DSP. The DSP-based NN controller is able to manage IPM motor control in linear, over, and six-step modulation regions to improve the efficiency of IPM drives and to allow for the full utilization of DC bus voltage with space-vector pulse-width modulation (SVPWM). The experiment results show that the proposed NN controller is able to operate with a sampling period of 0.1ms, even with limited DSP resources of up to 150 MHz cycle time, which is applicable in practical motor industrial implementations. The NN controller has demonstrated a better current and speed tracking performance than the conventional standard vector controller for IPM operation in both the linear and over-modulation regions.

Visual Servoing of Humanoid Dual-Arm Robot with Neural Learning Enhanced Skill Transferring Control

This paper presents a novel combination of visual servoing (VS) control and neural network (NN) learning on humanoid dual-arm robot. A VS control system is built by using stereo vision to obtain the 3D point cloud of a target object. A least square-based method is proposed to reduce the stochastic error in workspace calibration. An NN controller is designed to compensate for the effect of uncertainties in payload and other parameters (both internal and external) during the tracking control. In contrast to the conventional NN controller, a deterministic learning technique is utilized in this work, to enable the learned neural knowledge to be reused before current dynamics changes. A skill transfer mechanism is also developed to apply the neural learned knowledge from one arm to the other, to increase the neural learning efficiency. Tracked trajectory of object is used to provide target position to the coordinated dual arms of a Baxter robot in the experimental study. Robotic implementations has demonstrated the efficiency of the developed VS control system and has verified the effectiveness of the proposed NN controller with knowledge-reuse and skill transfer features.

Adaptive Neural Control for Robotic Manipulators With Output Constraints and Uncertainties.

This paper investigates adaptive neural control methods for robotic manipulators, subject to uncertain plant dynamics and constraints on the joint position. The barrier Lyapunov function is employed to guarantee that the joint constraints are not violated, in which the Moore-Penrose pseudo-inverse term is used in the control design. To handle the unmodeled dynamics, the neural network (NN) is adopted to approximate the uncertain dynamics. The NN control based on full-state feedback for robots is proposed when all states of the closed loop are known. Subsequently, only the robot joint is measurable in practice; output feedback control is designed with a high-gain observer to estimate unmeasurable states. Through the Lyapunov stability analysis, system stability is achieved with the proposed control, and the system output achieves convergence without violation of the joint constraints. Simulation is conducted to approve the feasibility and superiority of the proposed NN control.

Vibration Control of a Flexible Robotic Manipulator in the Presence of Input Deadzone

In this paper, a neural network (NN) controller is designed to suppress the vibration of a flexible robotic manipulator system with input deadzone. The NN aims to approximate the unknown robotic manipulator dynamics and eliminate the effects of input deadzone in the actuators. In order to describe the system more accurately, the model of the flexible manipulator is constructed based on the lumping spring-mass method. Full state feedback NN control is proposed first and output feedback NN control with a high-gain observer is then devised to make the proposed control scheme more practical. The effect of input deadzone is approximated by a radial basis function neural network (RBFNN) and the unknown dynamics of the manipulator is approximated by another RBFNN. The proposed NN control is able to compensate for the estimated deadzone effect and track the desired trajectory. For the stability analysis, the Lyapunov's direct method is used to ensure uniform ultimate boundedness (UUB) of the closed-loop system. Simulations are given to verify the control performance of the NN controllers comparing with the proportional derivative (PD) controller. At last, the experiments are conducted on the Quanser platform to further prove the feasibility and control performance of the NN controllers.

Online learning control of surface vessels for fine trajectory tracking

This paper presents an adaptive neural network (NN) controller for fine trajectory tracking of surface vessels with uncertain environmental disturbances. Regarding to the new demands for fine trajectory tracking, especially to the requirement of high-accuracy tracking in limited working space, the proposed NN controller is designed to contain a tracking error control component and a velocity error control component, aiming to converge both types of error to zero, separately. It utilizes radial basis functions to approximate a vessel’s unknown nonlinear dynamics. Therefore, there is no need of any explicit knowledge of the vessel. The online learning ability is obtained during the stability analysis using the backstepping technique and the Lyapunov theory. Theoretical results guarantee both the convergence of tracking error and velocity error and the boundedness of NN update. Through simulation and tracking performance study based on the CyberShip II model, the proposed controller is verified effective in fine trajectory tracking.

Hybrid trigonometric compound function neural networks for tracking control of a nonholonomic mobile robot

The purpose of this paper is to propose a hybrid trigonometric compound function neural network (NN) to improve the NN-based tracking control performance of a nonholonomic mobile robot with nonlinear disturbances. In the mobile robot control system, two NN controllers embedded in the closed-loop control system have the simple continuous learning and rapid convergence capability without the dynamics information of the mobile robot to realize the tracking control of the mobile robot. The neuron functions of the hidden layer in the three-layer feedforward network structure consist of the compound cosine function and the compound sine function combining a cosine or a sine function with a unipolar sigmoid function. The main advantages of this NN-based mobile robot control system are better real-time control capability and control accuracy by use of the proposed NN controllers for a nonholonomic mobile robot with nonlinear disturbances. Through simulation experiments applied to the nonholonomic mobile robot with the nonlinear disturbances of dynamics uncertainty and external disturbances, the simulation results show that the proposed NN control system of a nonholonomic mobile robot has better real-time control capability and control accuracy than the compound cosine function NN control system of a nonholonomic mobile robot and then verify the effectiveness of the proposed hybrid trigonometric compound function NN controller for improving the tracking control performance of a nonholonomic mobile robot with nonlinear disturbances.

Tracking control of a nonholonomic mobile robot using compound cosine function neural networks

The purpose of this paper is to propose a compound cosine function neural network with continuous learning algorithm for the velocity and orientation angle tracking control of a nonholonomic mobile robot with nonlinear disturbances. Herein, two neural network (NN) controllers embedded in the closed-loop control system have the simple continuous learning and rapid convergence capability without the dynamics information of the mobile robot to realize the adaptive control of the mobile robot. The neuron function of the hidden layer in the three-layer feed-forward network structure is on the basis of combining a cosine function with a unipolar sigmoid function. The developed neural network controllers have simple algorithm and fast learning convergence because the weight values are only adjusted between the nodes in hidden layer and the output nodes, while the weight values between the input layer and the hidden layer are one, i.e. constant, without the weight adjustment. Therefore, the main advantages of this control system are the real-time control capability and the robustness by use of the proposed neural network controllers for a nonholonomic mobile robot with nonlinear disturbances. Through simulation experiments applied to the nonholonomic mobile robot with the nonlinear disturbances which are considered as dynamics uncertainty and external disturbances, the simulation results show that the proposed NN control system of nonholonomic mobile robots has real-time control capability, better robustness and higher control precision. The compound cosine function neural network provides us with a new way to solve tracking control problems for mobile robots.

Tracking control of two-wheel driven mobile robot using compound sine function neural networks

The purpose of this paper is to propose a compound sine function neural network (NN) with continuous learning algorithm for the velocity and orientation angle tracking control of a mobile robot. Herein, two NN controllers embedded in the closed-loop control system are capable of on-line continuous learning and do not require any knowledge of the dynamics model. The neuron function of the hidden layer in the three-layer feed-forward network structure is on the basis of combining a sine function with a unipolar sigmoid function. In the NN algorithm, the weight values are only adjusted between the nodes in hidden layer and the output nodes, while the weight values between the input layer and the hidden layer are one, that is, constant, without the weight adjustment. The developed NN controllers have simple algorithm and fast learning convergence. Therefore, the proposed NN controllers can be suitable for the real-time tracking control of the mobile robots. The simulation results show that the proposed NN controller has better control performance in the tracking control of the mobile robot. The compound sine function NN provides a new way to solve tracking control problems for a mobile robot.

Reinforcement Learning Neural-Network-Based Controller for Nonlinear Discrete-Time Systems With Input Constraints

A novel adaptive-critic-based neural network (NN) controller in discrete time is designed to deliver a desired tracking performance for a class of nonlinear systems in the presence of actuator constraints. The constraints of the actuator are treated in the controller design as the saturation nonlinearity. The adaptive critic NN controller architecture based on state feedback includes two NNs: the critic NN is used to approximate the "strategic" utility function, whereas the action NN is employed to minimize both the strategic utility function and the unknown nonlinear dynamic estimation errors. The critic and action NN weight updates are derived by minimizing certain quadratic performance indexes. Using the Lyapunov approach and with novel weight updates, the uniformly ultimate boundedness of the closed-loop tracking error and weight estimates is shown in the presence of NN approximation errors and bounded unknown disturbances. The proposed NN controller works in the presence of multiple nonlinearities, unlike other schemes that normally approximate one nonlinearity. Moreover, the adaptive critic NN controller does not require an explicit offline training phase, and the NN weights can be initialized at zero or random. Simulation results justify the theoretical analysis.

Rudder roll stabilization for fishing vessel using neural network approach

This paper presents a neural network (NN) controller for a fishing vessel rudder roll system. The aim of this study is to build a NN controller which uses rudder to regulate both the yaw and roll motion. The neural controller design is accomplished with using the classical back-propagation algorithm (CBA). Effectiveness of the proposed NN control scheme is compared with linear quadratic regulator (LQR) results by simulations carried out a fishing vessel rudder roll stabilizer system.

Further results on adaptive control for a class of nonlinear systems using neural networks

Zhang et al. presented an excellent neural-network (NN) controller for a class of nonlinear control designs. The singularity issue is completely avoided. Based on a modified Lyapunov function, their lemma illustrates the existence of an ideal control which is important in establishing the NN approximator. In this paper, we provide a Lyapunov function to realize an alternative ideal control which is more direct and simpler. The major contributions of this paper are divided into two parts. First, it proposes a control scheme which results in a smaller dimensionality of NN than that of Zhang et al. In this way, the proposed NN controller is easier to implement and more reliable for practical purposes. Second, by removing certain restrictions from the design reported by Zhang et al., we further develop a new NN controller, which can be applied to a wider class of systems.

Analogue implementation of a neural network controller for UPS inverter applications

An analogue neural-network controller for UPS inverter applications is presented. The proposed neural-network controller is trained off-line using patterns obtained from a simulated controller, which had an idealized load-current-reference. Simulation results show that the proposed neural-network controller can achieve low total harmonic distortion under nonlinear loading condition and good dynamic responses under transient loading condition. To verify the performance of the proposed NN controller, a hardware inverter with an analogue neural network (NN) controller (using mainly operational amplifiers and resistors) is built. Additionally, for comparison purposes, a PI controller with optimized parameters is built. Experimental results confirm the simulation results and show the superior performance of the NN controller especially under rectifier-type loading condition. Implementing the analogue neural-network controller using programmable integrated circuits is also discussed.

Simulations for a Closed-Chain Multiple Robot Systems by Application of Neural Network Controllers

This paper considers the simulations for a closed-chain multiple robot systems by application of neural network (NN) controllers and the well-known computer torque method to the manipulation of a single rigid object by two redundant manipulators. The structures of the neural network controllers of multiple robot systems have been discussed.The two three-link redundant manipulators grasping a common object is adopted as an example mechanism to demonstrate proposed NN control scheme associated with computed-torque method. Back-propagation training algorithms for the NN controller have been developed.An illustrative example is included. The simulation results show that both of the redundant manipulators can maintain the contacts and manipulate the common object to follow the desired motion with the proposed scheme.

Neural network-based control of balanced robotic manipulators with joint flexibility

This paper addresses an improvement on the controlled performance of balanced manipulators in a practical level by implementing neural network based controller. The mass balancing of robotic manipulators has been shown to have favorable effects on the dynamic characteristics. However, it was also pointed out that for the manipulators having a certain degree of flexibility at the joints, due to the lowered structural natural frequencies and reduced velocity related terms, mass balancing results in vibratory motion at high speed operation. Such a vibratory tendency of the balanced flexible joint manipulator limits the admissible range of servo gains of the conventional controllers, making those controllers unsuitable for controlling the manipulator at high speeds. To avoid such difficulty, an artificial neural network (NN) controller is introduced to realize the dynamic control of the balanced flexible joint manipulators. A feedforward type of NN controller is proposed and its performance is evaluated through a series of numerical simulations. The proposed NN controller showed much better tracking performances over the conventional PD controller.