Design Of Neural Network Controller Research Articles

Design of Neural Network Controllers for the Horizontal Positioning of an Industrial Manipulator

This paper presents the design of neural network controllers for the electro-hydraulically driven positioning system of an industrial manipulator. The manipulator is represented by an unloading machine that extracts the billets from a rotary hearth furnace. The design of a Narma-L2 controller and a Model-reference controller is presented. Neural network controllers can be used for the modeling and control of dynamical systems as long as a suitable neural network is chosen. The obtained controllers are compared on the basis of overall performances. The assessment of the results is done by means of simulation.

Adaptive output feedback neural network control of uncertain non-affine systems with unknown control direction

This paper deals with the problem of adaptive output feedback neural network controller design for a SISO non-affine nonlinear system. Since in practice all system states are not available in output measurement, an observer is designed to estimate these states. In comparison with the existing approaches, the current method does not require any information about the sign of control gain. In order to handle the unknown sign of the control direction, the Nussbaum-type function is utilized. In order to approximate the unknown nonlinear function, neural network is firstly exploited, and then to compensate the approximation error and external disturbance a robustifying term is employed. The proposed controller is designed based on strict-positive-real (SPR) Lyapunov stability theory to ensure the asymptotic stability of the closed-loop system. Finally, two simulation studies are presented to demonstrate the effectiveness of the developed scheme.

Neural Network Based Diagonal Decoupling Control of Powered Wheelchair Systems

This paper proposes an advanced diagonal decoupling control method for powered wheelchair systems. This control method is based on a combination of the systematic diagonalization technique and the neural network control design. As such, this control method reduces coupling effects on a multivariable system, leading to independent control design procedures. Using an obtained dynamic model, the problem of the plant's Jacobian calculation is eliminated in a neural network control design. The effectiveness of the proposed control method is verified in a real-time implementation on a powered wheelchair system. The obtained results confirm that robustness and desired performance of the overall system are guaranteed, even under parameter uncertainty effects.

Neural Network Control for Uncertain Nonlinear Time-Delay Systems

Based on stability theory, a class of neural network controller design of uncertain nonlinear time-delay systems is studied. Using the ability that neural network can approximate any nonlinear function, a kind of weights correction law based on radial basis function (RBF) neural network (NN) and the adaptive controller design scheme are proposed. According to Lyapunov stability analysis method, this paper gives the sufficient conditions that neural network controller can make this kind of uncertain nonlinear time-delay systems stable in the sense of Lyapunov. At last, the proposed neural network controller is verified to be correct and effective by the simulation examples.

Hybrid Neural Network Controller Design for a Batch Reactor to Produce Methyl Methacrylate

Methyl methacrylate (MMA) production in an exothermic batch reactor provides a challenging problem for studying its dynamics behavior and temperature control. This work presents a neural network forward model (NN) to predict a concentration of methyl methacrylate, a jacket temperature and temperature profile in the reactor. An optimal NN model has been employed to predict state variables incorporating into a model predictive control (MPC) algorithm to determine optimal control actions. To control the temperature, neural network based control approaches: a neural network direct inverse control (NNDIC) and a neural network based model predictive control (NNMPC) have been formulated. In addition, a dynamic optimization approach has been applied to find out an optimal operating temperature to achieve maximizing the MMA product at specified final time. Simulation results have indicated that the NNMPC is robust and gives the best control results among the PID and NNDIC in all cases.

A Neural Network Controller for Variable-Speed Variable-Pitch Wind Energy Conversion Systems Using Generalized Minimum Entropy Criterion

This paper considers the neural network controller design problem for variable pitch wind energy conversion systems (WECS) with non-Gaussian wind speed disturbances in the stochastic distribution control framework. The approach here is used to directly model the unknown control law based on a fixed neural network (the number of layers and nodes in a neural network is fixed) without the need to construct a separate model for the WECS. In order to characterize the randomness of the WECS, a generalized minimum entropy criterion is established to train connection weights of the neural network. For the train purpose, both kernel density estimation method and sliding window technique are adopted to estimate the PDF of tracking error and entropies. Due to the unknown process dynamics, the gradient of the objective function in a gradient-descent-type algorithm is estimated using an incremental perturbation method. The proposed approach is illustrated on a simulated WECS with non-Gaussian wind speed.

Study on Chaotic Operation and Control System of Ultrasonic Motor

Ccording to the running speed of ultrasonic motor instability, design a motor testing system, the closed-loop controller embedded improved neural networkalgorithm, to suppress chaos. In open-loop state, input constant parameters to the motor, the motor rotating speed detection, the test data is chaotic analysis,found the speed has chaotic characteristics; in the closed-loop state, the feedback signal through the controller for processing, effectively inhibited theultrasonic motor speed jitter phenomenon, so as to improve the smoothness of motion motor. Experimental results show that, the neural network controller design not only significantly inhibited motor chaotic jitter phenomenon, but also has good anti-interference ability.

Design of Neural Network Controller for Space Robot with Flexible Manipulators

Neural network self-learning optimization PID control algorithm is put forward for free-floating space robot with flexible manipulators. Firstly, dynamics model of space flexible robot is established, then, neural network with good learning ability is used to approach non-linear system. Optimization algorithm of network weights is designed to speed up the learning speed and the adjustment velocity. Error function is offered by PID controller. The neural network self-learning PID control method can improve the control precision.

Design of an Adaptive Neural Network Controller for Robot Manipulators

This paper brings forward a kind of adaptive neural-sliding model control schemes for uncertain robot trajectory tracking. The first scheme consists of a PD feedback and a dynamic compensator which is composed of RBF neural network and variable structure. The adaptive laws of Network weights are based on Lyapunov function method. This controller can guarantee stability of closed-loop system and asymptotic convergence of tracking errors.

Design of Neural Network Controller Based on FPGA Distillation Column

A study based on FPGA controller, is used to solve the problems of control mechanism of this kind of dynamic process of coal chemical distillation process complex, process variables, controlled variables, it is difficult to establish mathematics model.

Switching Based Recurrent Fuzzy Neural Network Control Design

Switching Based Recurrent Fuzzy Neural Network Control Design

Research on Intelligent Variable Frequency of Air-Conditioner Control System Based on Fuzzy Control

In this paper, we determine the fuzzy control strategy of inverter air conditioner, the fuzzy control model structure, the neural network and fuzzy control technology, structural design of the fuzzy neural network controller as well as the neural network predictor FNNC NNP. Simulation results show that the fuzzy neural network controller can control the accuracy greatly improved the compressor, and the control system has strong adaptability to achieve a truly intelligent; model of the controller design and implementation of technology are mainly from the practical point of view, which is practical and feasible.

Novel design of adaptive neural network controller for a class of non-affine nonlinear systems

The tracking control problem is studied for a class of uncertain non-affine systems. Based on the principle of sliding mode control (SMC), using the neural networks (NNs) and the property of the basis function, a novel adaptive design scheme is proposed. A novel Lyapunov function, which depends on both system states and control input variable, is used for the development of the control law and the adaptive law. The approach overcomes the drawback in the literature. In addition, the lumped disturbances are taken in account. By theoretical analysis, it is proved that tracking errors asymptotically converge to zero. Finally, simulation results demonstrate the effectiveness of the proposed approach.

Global adaptive neural network control for a class of uncertain non-linear systems

The study considers the problem of global adaptive stabilisation for a class of uncertain non-linear systems in which the uncertainty may not be parameterised. With the aid of the partition technique of unity in differential topology, global approximation of a function using neural networks is obtained. The usefulness of the approximation theory is shown in the design of a global adaptive neural network controller. It is proved that the proposed design method is able to ensure boundedness of all the signals in the closed loop, and the state variables converge to zero asymptotically.

Design of an adaptive self-organizing fuzzy neural network controller for uncertain nonlinear chaotic systems

Though the control performances of the fuzzy neural network controller are acceptable in many previous published papers, the applications are only parameter learning in which the parameters of fuzzy rules are adjusted but the number of fuzzy rules should be determined by some trials. In this paper, a Takagi–Sugeno-Kang (TSK)-type self-organizing fuzzy neural network (TSK-SOFNN) is studied. The learning algorithm of the proposed TSK-SOFNN not only automatically generates and prunes the fuzzy rules of TSK-SOFNN but also adjusts the parameters of existing fuzzy rules in TSK-SOFNN. Then, an adaptive self-organizing fuzzy neural network controller (ASOFNNC) system composed of a neural controller and a smooth compensator is proposed. The neural controller using the TSK-SOFNN is designed to approximate an ideal controller, and the smooth compensator is designed to dispel the approximation error between the ideal controller and the neural controller. Moreover, a proportional-integral (PI) type parameter tuning mechanism is derived based on the Lyapunov stability theory, thus not only the system stability can be achieved but also the convergence of tracking error can be speeded up. Finally, the proposed ASOFNNC system is applied to a chaotic system. The simulation results verify the system stabilization, favorable tracking performance, and no chattering phenomena can be achieved using the proposed ASOFNNC system.

Design of Adaptive Neural Network Controller for Thermal Power System Frequency Control

This paper deals with analytical and simulation approach for choice of activation functions and instead of a number of nodes for a class of neural network controllers for frequency control of thermal power systems. Neural network update laws are derived via Lyapunov like stability analysis. When number of nodes is fixed, then simulation analysis is conducted to find the best performer activation function. Best performance is chosen using integral error criteria and proper statistical tests.

The Intelligent Controller Design of Parallel Online Mixing and Supplying Glue System

In this paper, a novel control method by using parallel online mixing and supplying technology for glue system with multi-input, strong coupling and nonlinear was provided. The neural network controller design method is adopted to design the intelligent controller, in which one as the main controller and the other one as the identifier to revise main controller. Both advantages and disadvantages of the two neural network controllers were analyzed. Simulation results showed that both methods obtained a more favorable effect than the traditional control method.

Design of intelligent controllers for wind generation system with sensorless maximum wind energy control

This paper presents the design of an on-line training recurrent fuzzy neural network (RFNN) controller with a high-performance model reference adaptive system (MRAS) observer for the sensorless control of a induction generator (IG). The modified particle swarm optimization (MPSO) is adopted in this study to adapt the learning rates in the back-propagation process of the RFNN to improve the learning capability. By using the proposed RFNN controller with MPSO, the IG system can work for stand-alone power application effectively. The proposed output maximization control is achieved without mechanical sensors such as the wind speed or position sensor, and the new control system will deliver maximum electric power with light weight, high efficiency, and high reliability. The estimation of the rotor speed is based on the MRAS control theory. A sensorless vector-control strategy for an IG operating in a grid-connected variable speed wind energy conversion system can be achieved.

Robust Adaptive Neural Network Control for a Class of Uncertain MIMO Nonlinear Systems With Input Nonlinearities

In this paper, robust adaptive neural network (NN) control is investigated for a general class of uncertain multiple-input-multiple-output (MIMO) nonlinear systems with unknown control coefficient matrices and input nonlinearities. For nonsymmetric input nonlinearities of saturation and deadzone, variable structure control (VSC) in combination with backstepping and Lyapunov synthesis is proposed for adaptive NN control design with guaranteed stability. In the proposed adaptive NN control, the usual assumption on nonsingularity of NN approximation for unknown control coefficient matrices and boundary assumption between NN approximation error and control input have been eliminated. Command filters are presented to implement physical constraints on the virtual control laws, then the tedious analytic computations of time derivatives of virtual control laws are canceled. It is proved that the proposed robust backstepping control is able to guarantee semiglobal uniform ultimate boundedness of all signals in the closed-loop system. Finally, simulation results are presented to illustrate the effectiveness of the proposed adaptive NN control.

Fuzzy neural network output maximization control for sensorless wind energy conversion system

This paper presents the design of an online training fuzzy neural network (FNN) controller with a high-performance speed observer for the induction generator (IG). The proposed output maximization control is achieved without mechanical sensors such as the wind speed or position sensor, and the new control system will deliver maximum electric power with light weight, high efficiency, and high reliability. The estimation of the rotor speed is designed on the basis of the sliding mode control theory.