Adaptive Neural Network Control Scheme Research Articles

NEURAL ADAPTIVE CONTROL FOR VIBRATION SUPPRESSION IN COMPOSITE FIN-TIP OF AIRCRAFT

In this paper, we present a neural adaptive control scheme for active vibration suppression of a composite aircraft fin tip. The mathematical model of a composite aircraft fin tip is derived using the finite element approach. The finite element model is updated experimentally to reflect the natural frequencies and mode shapes very accurately. Piezo-electric actuators and sensors are placed at optimal locations such that the vibration suppression is a maximum. Model-reference direct adaptive neural network control scheme is proposed to force the vibration level within the minimum acceptable limit. In this scheme, Gaussian neural network with linear filters is used to approximate the inverse dynamics of the system and the parameters of the neural controller are estimated using Lyapunov based update law. In order to reduce the computational burden, which is critical for real-time applications, the number of hidden neurons is also estimated in the proposed scheme. The global asymptotic stability of the overall system is ensured using the principles of Lyapunov approach. Simulation studies are carried-out using sinusoidal force functions of varying frequency. Experimental results show that the proposed neural adaptive control scheme is capable of providing significant vibration suppression in the multiple bending modes of interest. The performance of the proposed scheme is better than the H(infinity) control scheme.

Adaptive Neural Network Control of Free-floating Space Manipulator With an Attitude Controlled Base

讨论了载体位置无控、姿态受控情况下,空间机械臂姿态及关节协调运动的自适应神经网络控制问题.由拉格朗日第二类方法及系统动量守恒关系,建立了漂浮基空间机械臂的系统动力学方程.以此为基础,借助于RBF神经网络技术和GL矩阵及乘积算子定义,对空间机械臂系统进行了神经网络系统建模;之后针对空间机械臂所有惯性参数未知的情况,设计了空间机械臂载体姿态与机械臂各关节协调运动的自适应神经网络控制方案.提出的控制方案不要求系统动力学方程具有关于惯性参数的线性性质,且无需预知系统惯性参数的任何信息,也无需对神经网络进行离线训练和学习,因此更适于实时应用.通过对一个平面两杆自由漂浮空间机械臂系统的数值仿真,证实了方法的有效性.

Exponential /spl epsiv/-regulation for multi-input nonlinear systems using neural networks

This paper considers the problem of robust exponential epsilon-regulation for a class of multi-input nonlinear systems with uncertainties. The uncertainties appear not only in the feedback channel but also in the control channel. Under some mild assumptions, an adaptive neural network control scheme is developed such that all the signals of the closed-loop system are semiglobally uniformly ultimately bounded and, under the control scheme with initial data starting in some compact set, the states of the closed-loop system is guaranteed to exponentially converge to an arbitrarily specified epsilon-neighborhood about the origin. The important contributions of the present work are that a new exponential uniformly ultimately bounded performance is proposed and that the design parameters and initial condition set can be determined easily. The development generalizes and improves earlier results for the single-input case.

A new recurrent neural network adaptive approach for host-gate way rate control protocol within intranets using ATM ABR service

In this paper, a new neural network adaptive control strategy based on Host Gate Way Rate Control Protocol (HGRCP) is proposed for intranet congestion management. The control algorithm is based on the Elman recurrent neural network via using the ABR service of an ATM backbone network. Simulations confirm that the proposed algorithm will produce lower queue level variance at the gateway. Meanwhile, the learning capability can be improved significantly.

Adaptive backstepping control for a class of nonlinear systems using neural network approximations

AbstractIn this paper, an adaptive neural network (NN) backstepping technique is developed for tracking control of a class of nonlinear systems. NNs are used to compensate for the unknown nonlinear functions in the system. A systematic backstepping approach is established to synthesize the adaptive NN control scheme that ensures the boundedness of all the signals in the closed‐loop system, and yields a small tracking error. The issue of transient performance is also addressed under an analytical framework. The effectiveness of the proposed scheme is demonstrated by computer simulations. Copyright © 2004 John Wiley & Sons, Ltd.

Neural network modeling and control of cement mills using a variable structure systems theory based on-line learning mechanism

It is well known that the major cause of instability in industrial cement ball mills is the so-called plugging phenomenon. A novel neural network adaptive control scheme for cement milling circuits that is able to fully prevent the mill from plugging is presented. Estimates of the one-step-ahead errors in control signals are calculated through a neural predictive model and used for controller tuning. A robust on-line learning algorithm, based on sliding mode control (SMC) theory is applied to both: to the controller and to the model as well. The proposed approach allows handling of mismatches, uncertainties and parameter changes in the model of the mill. The simulation results from indicate that both the neural model and the controller inherit the major advantages of SMC, i.e. robustness. Furthermore, learning is achieved in a rapid manner.

Adaptive Neural Network Controller for Non-Affine Nonlinear Systems and its Application to CSTR

In this paper; a new robust adaptive neural network controller (RANNC) is presented for a class of non-affine nonlinear systems in the presence of unknown nonlinearities and disturbances. Firstly, the existence of an ideal implicit feedback linearisation control (IFLC) is established based on implicit function theory. Using Taylor series expansion, it is shown that the control of non-affine nonlinear systems is equivalent to the control ofaffine nonlinear systems in the neighbourhood of the operating trajectory under mild conditions. Then, a robust adaptive neural network control scheme is presented for the transformed nonlinear systems by using neural networks as universal approximators for the unknown system nonlinearities. The proposed RANNC can guarantee that all the signals in the closed-loop system are bounded and the tracking error asymptotically converges to zero. Simulation studies on the control of a continuously stirred tank reactor (CSTR) system are used to show the effectiveness of the scheme.

Adaptive Neural Network Controller for Non-affine Nonlinear Systems and Its Application to CSTR

In this paper, a new robust adaptive neural network controller (RANNC) is presented for a class of non-affine nonlinear systems in the presence of unknown nonlinearities and disturbances. Firstly, the existence of an ideal implicit feedback linearization control (IFLC) is established based on implicit function theory. Using Taylor series expansion, it is shown that the control of non-affine nonlinear systems is equivalent to the control of affine nonlinear systems in the neighborhood of the operating trajectory under mild conditions. Then, a robust adaptive neural network control scheme is presented for the transformed nonlinear systems by using neural networks as universal approximators for the unknown system nonlinearities. The proposed RANNC can guarantee that all the signals in the closed-loop system are bounded and the tracking error asymptotically converges to zero. Simulation studies on the control of a continuously stirred tank reactor (CSTR) system are used to show the effectiveness of the scheme.

10.1109/ETFA.2010.5641337

This paper considers the problem of robust exponential e -regulation for a class of multi-input nonlinear systems with uncertainties. The uncertainties appear not only in the feedback channel but also in the control channel. Under some mild assumptions, an adaptive neural network control scheme is developed such that all the signals of the closed-loop system are semi globally uniformly ultimately bounded and, under the control scheme with initial data starting in some compact set, the states of the closed-loop system is guaranteed to exponentially converge to an arbitrarily specified -neighborhood about the origin. The important contributions of the present work are that a new exponential uniformly ultimately bounded performance is proposed and that the design parameters and initial condition set can be determined easily.

An Adaptive Fuzzy Neural Network Controller and its Application

Using the fuzzy control and artificial neural network methodologies, an adaptive frizzy neural network control scheme was presented. In this scheme the fuzzy control rule is described in the form of an analytical formula instead of common fuzzy rule table, so the fuzzy control rule can be adaptive modified. In this way, one can overcome the difficulties of choosing fuzzy rule by human experiences or trial-and-error. The experiment results show the control scheme is available

A direct adaptive neural-network control for unknown nonlinear systems and its application

In this paper a direct adaptive neural-network control strategy for unknown nonlinear systems is presented. The system considered is described by an unknown NARMA model, and a feedforward neural network is used to learn the system. Taking the neural network as a neural model of the system, control signals are directly obtained by minimizing either the instant difference or the cumulative differences between a set point and the output of the neural model. Since the training algorithm guarantees that the output of the neural model approaches that of the actual system, it is shown that the control signals obtained can also make the real system output close to the set point. An application to a flow-rate control system is included to demonstrate the applicability of the proposed method and desired results are obtained.

An enhanced adaptive neural network control scheme for power systems

An enhanced adaptive neural network control scheme, based on the adaptive linear element (Adaline), is proposed and tested by applying it to a multimachine power system. Simulation results have shown that it is effective for different types of disturbances and over a wide range of operating conditions.

A nonlinear adaptive H/sup /spl infin// tracking control design in robotic systems via neural networks

An adaptive neural-network tracking control with a guaranteed H/sup /spl infin// performance is proposed for robotic systems with plant uncertainties and external disturbances. A neural-network system is introduced to learn these unknown (or uncertain) dynamics by an adaptive algorithm, Moreover, the effects on the tracking error due to the approximation error via the adaptive neural network must be attenuated to a prescribed level, i.e. an H/sup /spl infin// tracking performance is achieved. Hence, in this study, both the H/sup /spl infin// tracking theory and adaptive neural-network control scheme are combined together to achieve the nonlinear adaptive H/sup /spl infin// tracking control design for uncertain or unknown robotic systems. The developed control scheme is smooth and semiglobal as well as very simple and computationally efficient, since it does not require a knowledge of either the mathematical model or the parameterization of the robotic dynamics. Finally, extensive simulations are given to illustrate the tracking performance of a two-link robotic manipulator with the proposed adaptive neural H/sup /spl infin// control design.

Neural network modelling and control strategies for a pH process

The control of a pH process using neural networks is examined. The neural network as a universal approximator is used to good effect in this nonlinear problem, as is shown in the simulation results. In the modelling task, the dynamics of the process was carefully examined to determine a suitable structure for the net. In particular, a multilayer net consisting of two single hidden layers was constructed to reflect the Wiener model of the pH process. This led to much simpler training compared to similar modelling attempts by other researchers. For the control task, two schemes were simulated. In one approach, a net was used to deal with the static nonlinearity to achieve control over a wide working range. The dynamic controller used was the PID, with its parameters tuned on a relay auto-tuner. This control design was compared with the strong acid equivalent method. In the second approach, a direct model reference adaptive neural network control scheme was proposed. The training procedure uses the more efficient least squares algorithm developed by Loh and Fong.