Control of dynamic systems using fuzzy logic and neural networks

The use of artificial neural network is proposed for high-speed processing of rules in fuzzy logic controller (FLC). the logic element of an FLC is replaced by a single hidden layer feedforward network. the input and output fuzzy subsets are expressed it of numerical patterns. the network is trained using the back-propagation algori to establish fuzzy associations between the input and output fuzzy subsets. the inference mechanism of the network is compared with that of compositional law of inference. In the proposed implementation of FLC, all the rules are processed in paralle. This implementation has potential for high-speed processing of rules if the network is realized in hardware. the use of neural networks in fuzzy logic self-organizing is also ivestigated. © 1993 John Wiley & Sons, Inc.     

Implementations of artificial neural networks using current-modepulse width modulation technique

The use of a current-mode pulse width modulation (CM-PWM) technique to implement analog artificial neural networks (ANNs) is presented. This technique can be used to efficiently implement the weighted summation operation (WSO) that are required in the realization of a general ANN. The sigmoidal transformation is inherently performed by the nonlinear transconductance amplifier, which is a key component in the current integrator used in the realization of WSO. The CM-PWM implementation results in a minimum silicon area, and therefore is suitable for very large scale neural systems. Other pronounced features of the CM-PWM implementation are its easy programmability, electronically adjustable gains of neurons, and modular structures. In this paper, all the current-mode CMOS circuits (building blocks) required for the realization of CM-PWM ANNs are presented and simulated. Four modules for modular design of ANNs are introduced. Also, it is shown that the CM-PWM technique is an efficient method for implementing discrete-time cellular neural networks (DT-CNNs). Two application examples are given: a winner-take-all circuit and a connected component detector.     

高速公路动态交通流的BP神经网络建模

通过对高速公路宏观动态交通流模型的分析,针对高速公路交通系统的非线性时变特点,应用BP神经网络建立了高速公路宏观动态交通流模型。并利用一段高速公路的交通流数据对BP神经网络进行训练,得到网络参数。最后,为了验证BP网络模型的有效性,在MATLAB环境中对模型进行了仿真,并将仿真结果与原始模型的结果进行了比较。结果表明,该方法能较准确地描述高速公路交通流的真实行为,并且能够适应交通状况的变化。     

Nonlinear systems identification using dynamic multi-time scale neural networks

In this paper, two Neural Network (NN) identifiers are proposed for nonlinear systems identification via dynamic neural networks with different time scales including both fast and slow phenomena. The first NN identifier uses the output signals from the actual system for the system identification. The on-line update laws for dynamic neural networks have been developed using the Lyapunov function and singularly perturbed techniques. In the second NN identifier, all the output signals from nonlinear system are replaced with the state variables of the neuron networks. The on-line identification algorithm with dead-zone function is proposed to improve nonlinear system identification performance. Compared with other dynamic neural network identification methods, the proposed identification methods exhibit improved identification performance. Three examples are given to demonstrate the effectiveness of the theoretical results.     

Adaptive noise cancellation using enhanced dynamic fuzzy neural networks

In this paper, a novel adaptive noise cancellation algorithm using enhanced dynamic fuzzy neural networks (EDFNNs) is described. In the proposed algorithm, termed EDFNN learning algorithm, the number of radial basis function (RBF) neurons (fuzzy rules) and input-output space clustering is adaptively determined. Furthermore, the structure of the system and the parameters of the corresponding RBF units are trained online automatically and relatively rapid adaptation is attained. By virtue of the self-organizing mapping (SOM) and the recursive least square error (RLSE) estimator techniques, the proposed algorithm is suitable for real-time applications. Results of simulation studies using different noise sources and noise passage dynamics show that superior performance can be achieved.     

Classification of modulation signals using statistical signal characterization and artificial neural networks

Modulation recognition systems have to be able to correctly classify the incoming signal modulation scheme in the presence of noise. A new method for classification of analogue and digital modulated signals at low signal-to-noise ratio (SNR) is introduced in this paper. This method uses the statistical signal characterization (SSC) to extract parameters to classify the different modulation signals. The SSC technique produces a set of four numerical parameters for a specific modulated signal. Subsequent comparison of these parameters to those of other waveforms provides the basis for our classification system. The results of SSC technique are applied to an artificial neural network (ANN) to have a robust classification system in the presence of noise down to SNR of 3 dB. No a priori information is required by this technique about the set of input waveforms. The input to the classification system can be analogue or digital signals or a combination of both. The proposed technique shows a 100% efficiency of classification of analogue signals or digital signals at SNR of 7 dB. This classification efficiency reduces to 83% and 86% for analogue or digital signals at SNR of 3 dB. The SSC technique shows better classification results in comparison with other techniques with an important advantage over other methods, which is the simplicity of the neural network needed with this technique due to the small number of features used in the classification.     

Identification of linear and nonlinear dynamic systems using recurrent neural networks

This paper describes the use of Elman-type recurrent neural networks to identify dynamic systems. Networks as originally designed by Elman (Cognitive Sci., 1990, 14, 179–211) and also those in which self-connections are made to the context units were employed to identify a variety of linear and nonlinear systems. It was found that the latter networks were more versatile than the basic Elman nets in being able to model the dynamic behaviour of high order linear and nonlinear systems.     

Reinforcement learning of dynamic behavior by using recurrent neural networks

Reinforcement learning is a learning scheme for finding the optimal policy to control a system, based on a scalar signal representing a reward or a punishment. If the observation of the system by the controller is sufficiently rich to represent the internal state of the system, the controller can achieve the optimal policy simply by learning reactive behavior. However, if the state of the controlled system cannot be assessed completely using current sensory observations, the controller must learn a dynamic behavior to achieve the optimal policy. In this paper, we propose a dynamic controller scheme which utilizes memory to uncover hidden states by using information about past system outputs, and makes control decisions using memory. This scheme integrates Q-learning, as proposed by Watkins, and recurrent neural networks of several types. It performs favorably in simulations which involve a task with hidden states. This work was presented, in part, at the International Symposium on Artificial Life and Robotics, Oita, Japan, February 18–20, 1996     

Identification of nonlinear dynamic systems using functional linkartificial neural networks

We have presented an alternate ANN structure called functional link ANN (FLANN) for nonlinear dynamic system identification using the popular backpropagation algorithm. In contrast to a feedforward ANN structure, i.e., a multilayer perceptron (MLP), the FLANN is basically a single layer structure in which nonlinearity is introduced by enhancing the input pattern with nonlinear functional expansion. With proper choice of functional expansion in a FLANN, this network performs as good as and in some cases even better than the MLP structure for the problem of nonlinear system identification.     

不确定混沌系统的动态神经网络跟踪控制

针对不确定非线性混沌系统，提出了一种基于动态神经网络辨识器的自适应跟踪控制新方法，通过滑模控制技术在线调整动态神经网络辨识器权值，并在获取动态神经网络模型的基础上设计出优化控制器，实现混沌系统的轨道跟踪，对辨识误差和轨道跟踪误差进行分析并证明了它们的有界性，Lorenz混沌系统的仿真实验结果表明了控制策略的有效性。     

Nonlinear dynamic system identification using Chebyshev functionallink artificial neural networks

A computationally efficient artificial neural network (ANN) for the purpose of dynamic nonlinear system identification is proposed. The major drawback of feedforward neural networks, such as multilayer perceptrons (MLPs) trained with the backpropagation (BP) algorithm, is that they require a large amount of computation for learning. We propose a single-layer functional-link ANN (FLANN) in which the need for a hidden layer is eliminated by expanding the input pattern by Chebyshev polynomials. The novelty of this network is that it requires much less computation than that of a MLP. We have shown its effectiveness in the problem of nonlinear dynamic system identification. In the presence of additive Gaussian noise, the performance of the proposed network is found to be similar or superior to that of a MLP. A performance comparison in terms of computational complexity has also been carried out.     

Dispatching rule selection using artificial neural networks for dynamic planning and scheduling

To schedule a job shop, the first task is to select an appropriate scheduling algorithm or rule. Because of the complexity of scheduling problems, no general algorithm sufficient for solving all scheduling problems has yet been developed. Most job-shop scheduling systems offer alternative algorithms for different situations, and experienced human schedulers are needed to select the best dispatching rule in these systems. This paper proposes a new algorithm for job-shop scheduling problems. This algorithm consists of three stages. First, computer simulation techniques are used to evaluate the efficiency of heuristic rules in different scheduling situations. Second, the simulation results are used to train a neural network in order to capture the knowledge which can be used to select the most efficient heuristic rule for each scheduling situation. Finally, the trained neural network is used as a dispatching rule selector in the real-time scheduling process. Research results have shown great potential in using a neural network to replace human schedulers in selecting an appropriate approach for real-time scheduling. This research is part of an ongoing project of developing a real-time planning and scheduling system.     

Real time identification and control of dynamic systems using recurrent neural networks

Recently, several recurrent neural networks for solving constraint optimization problems were developed. In this paper, we propose a novel approach to the use of a projection neural network for solving real time identification and control of time varying systems. In addition to low complexity and simple structure, the proposed neural network can solve wider classes of time varying systems compare with other neural networks that are used for optimization such as Hopfield neural networks. Simulation results demonstrate the effectiveness and characteristics of the proposed neural network compared with a Hopfield neural network.     

Adaptive inverse control of linear and nonlinear systems using dynamic neural networks

In this paper, we see adaptive control as a three-part adaptive-filtering problem. First, the dynamical system we wish to control is modeled using adaptive system-identification techniques. Second, the dynamic response of the system is controlled using an adaptive feedforward controller. No direct feedback is used, except that the system output is monitored and used by an adaptive algorithm to adjust the parameters of the controller. Third, disturbance canceling is performed using an additional adaptive filter. The canceler does not affect system dynamics, but feeds back plant disturbance in a way that minimizes output disturbance power. The techniques work to control minimum-phase or nonminimum-phase, linear or nonlinear, single-input-single-output (SISO) or multiple-input-multiple-ouput (MIMO), stable or stabilized systems. Constraints may additionally be placed on control effort for a practical implementation. Simulation examples are presented to demonstrate that the proposed methods work very well.     

A fast approach for automatic generation of fuzzy rules bygeneralized dynamic fuzzy neural networks

A fast approach for automatically generating fuzzy rules from sample patterns using generalized dynamic fuzzy neural networks (GD-FNNs) is presented. The GD-FNN is built based on ellipsoidal basis functions and functionally is equivalent to a Takagi-Sugeno-Kang fuzzy system. The salient characteristics of the GD-FNN are: (1) structure identification and parameters estimation are performed automatically and simultaneously without partitioning input space and selecting initial parameters a priori; (2) fuzzy rules can be recruited or deleted dynamically; (3) fuzzy rules can be generated quickly without resorting to the backpropagation (BP) iteration learning, a common approach adopted by many existing methods. The GD-FNN is employed in a wide range of applications ranging from static function approximation and nonlinear system identification to time-varying drug delivery system and multilink robot control. Simulation results demonstrate that a compact and high-performance fuzzy rule-base can be constructed. Comprehensive comparisons with other latest approaches show that the proposed approach is superior in terms of learning efficiency and performance     

Input-to-state stabilization of dynamic neural networks

As a continuation of their previous published results, in this paper the authors propose a new methodology, for input-to-state stabilization of a dynamic neural network. This approach is developed on the basis of the recent introduced inverse optimal control technique for nonlinear control. An example illustrates the applicability of the proposed approach.     

Robot discrete adaptive control based on dynamic inversion using dynamical neural networks

A stable discrete time adaptive control approach using dynamic neural networks (DNNs) is developed in this paper for the trajectory tracking of a robotic manipulator with unknown nonlinear dynamics. By using dynamic inversion constructed by a DNN, the assumption under which the system state should be on a compact set can be removed. This assumption is usually required in neuro-adaptive control. The NN-based variable structure control is designed to guarantee the stability and improve the dynamic performance of the closed-loop system. The proposed control scheme ensures the global stability and desired tracking as well.     

Robust dynamic surface control of flexible joint robots using recurrent neural networks

A robust neuro-adaptive controller for uncertain flexible joint robots is presented. This control scheme integrates H-infinity disturbance attenuation design and recurrent neural network adaptive control technique into the dynamic surface control framework. Two recurrent neural networks are used to adaptively learn the uncertain functions in a flexible joint robot. Then, the effects of approximation error and filter error on the tracking performance are attenuated to a prescribed level by the embedded H-infinity controller, so that the desired H-infinity tracking performance can be achieved. Finally, simulation results verify the effectiveness of the proposed control scheme.     

On the modelling of nonlinear dynamic systems using support vector neural networks

Though neural networks have the ability to approximate nonlinear functions with arbitrary accuracy, good generalization results are obtained only if the structure of the network is suitably chosen. Therefore, selecting the ‘best’ structure of the neural networks is an important problem. Support vector neural networks (SVNN) are proposed in this paper, which can provide a solution to this problem. The structure of the SVNN is obtained by a constrained minimization for a given error bound similar to that in the support vector regression (SVR). After the structure is selected, its weights are computed by the linear least squares method, as it is a linear-in-weight network. Consequently, in contrast to the SVR, the output of the SVNN is unbiased. It is further shown here that the variance of the modelling error of the SVNN is bounded by the square of the given error bound in selecting its structure, and is smaller than that of the SVR. The performance of the SVNN is illustrated by a simulation example involving a benchmark nonlinear system.