Adaptive robot control using neural networks

This paper studies the trajectory tracking problem to control the nonlinear dynamic model of a robot using neural networks. These controllers are based on learning from input-output measurements and not on parametric-model-based dynamics. Multilayer recurrent networks are used to estimate the dynamics of the system and the inverse dynamic model. The training is achieved using the backpropagation method. The minimization of the quadratic error is computed by a variable step gradient method. Another multilayer recurrent neural network is added to estimate the joint accelerations. The control process is applied to a two degree-of-freedom (DOF) SCARA robot using a DSP-based controller. Experimental results show the effectiveness of this approach. The tracking trajectory errors are very small and torques expected at manipulator joints are free of chattering.<>     

Variable neural networks for adaptive control of nonlinear systems

This paper is concerned with the adaptive control of continuous-time nonlinear dynamical systems using neural networks. A novel neural network architecture, referred to as a variable neural network, is proposed and shown to be useful in approximating the unknown nonlinearities of dynamical systems. In the variable neural networks, the number of basis functions can be either increased or decreased with time, according to specified design strategies, so that the network will not overfit or underfit the data set. Based on the Gaussian radial basis function (GRBF) variable neural network, an adaptive control scheme is presented. The location of the centers and the determination of the widths of the GRBFs in the variable neural network are analyzed to make a compromise between orthogonality and smoothness. The weight-adaptive laws developed using the Lyapunov synthesis approach guarantee the stability of the overall control scheme, even in the presence of modeling error(s). The tracking errors converge to the required accuracy through the adaptive control algorithm derived by combining the variable neural network and Lyapunov synthesis techniques. The operation of an adaptive control scheme using the variable neural network is demonstrated using two simulated examples     

ECG analysis using nonlinear PCA neural networks for ischemiadetection

The detection of ischemic cardiac beats from a patient's electrocardiogram (EGG) signal is based on the characteristics of a specific part of the beat called the ST segment. The correct classification of the beats relies heavily on the efficient and accurate extraction of the ST segment features. An algorithm is developed for this feature extraction based on nonlinear principal component analysis (NLPCA). NLPCA is a method for nonlinear feature extraction that is usually implemented by a multilayer neural network. It has been observed to have better performance, compared with linear principal component analysis (PCA), in complex problems where the relationships between the variables are not linear. In this paper, the NLPCA techniques are used to classify each segment into one of two classes: normal and abnormal (ST+, ST-, or artifact). During the algorithm training phase, only normal patterns are used, and for classification purposes, we use only two nonlinear features for each ST segment. The distribution of these features is modeled using a radial basis function network (RBFN). Test results using the European ST-T database show that using only two nonlinear components and a training set of 1000 normal samples from each file produce a correct classification rate of approximately 80% for the normal beats and higher than 90% for the ischemic beats     

An approach for sensorless position estimation for switchedreluctance motors using artifical neural networks

This paper presents a new approach to the sensorless control of the switched-reluctance motor (SRM). The basic premise of the method is that an artificial neural network (ANN) forms a very efficient mapping structure for the nonlinear SRM. Through measurement of the phase flux linkages and phase currents the neural network is able to estimate the rotor position, thereby facilitating elimination of the rotor position sensor. The ANN training data set is comprised of magnetization data for the SRM with flux linkage (λ) and current (i) as inputs and the corresponding position (&thetas;) as output in this set. Given a sufficiently large training data set, the ANN can build up a correlation among λ, i and &thetas; for an appropriate network architecture. This paper presents the development, implementation, and operation of an ANN-based position estimator for a three-phase SRM     

Mobile robot control by neural networks using self-supervisedlearning

A reinforcement learning algorithm based on supervised learning is described. It uses associative search to discover and learn actions that make the system perform a desired task. One problem with associative search is that the system's actions are often inconsistent. In the searching process, the system's actions are always decided stochastically, so the system cannot perform learned actions more than once, even if they have been determined to be suitable actions for the desired task. To solve this problem, a neural network that can predict an evaluation of an action and control the influence of the stochastic element is used. Results from computer simulations using the algorithms to control a mobile robot are described     

Trajectory control of robotic manipulators using neural networks

The authors present a nonlinear compensator using neural networks for trajectory control of robotic manipulators. The neural networks are not used to learn inverse-dynamics but to compensate nonlinearities of robotic manipulators. The performance of the proposed neural network controller is compared with that of the adaptive controller proposed by J.J. Craig (1988), and the effectiveness of the proposed neural network controller in compensating the unstructured uncertainties is clarified. A learning scheme using a model of known dynamics of manipulators is also proposed. The model learning can be done offline and needs no data recording of actual manipulator operation     

Longitudinal wheel slip control using dynamic neural networks

The control of automotive braking systems performance and a wheel slip is a challenging problem due to nonlinear dynamics of a braking process and a tire–road interaction. When the wheel slip is not between the optimal limits during braking, the desired tire–road friction force cannot be achieved, which influences braking distance, the loss in steerability and maneuverability of the vehicle. In this paper, the new approach, based on dynamic neural networks, has been employed for improving of the longitudinal wheel slip control. This approach is based on dynamic adaptation of the brake actuation pressure, during a braking cycle, according to the identified maximum adhesion coefficient between the wheel and road. The brake actuated pressure was adjusted on the level which provides the optimal longitudinal wheel slip versus the brake actuated pressure selected by a driver, the current vehicle speed, load conditions, the brake interface temperature and the current value of the wheel slip. The dynamic neural network has been used for modeling of a nonlinear functional relationship between the brake actuation pressure and the longitudinal wheel slip during a braking cycle. It provided preconditions for control of the brake actuation pressure based on the wheel slip change.     

Optimised PWM inverter control using artificial neural networks

A novel method of producing optimum switching functions for the voltage and harmonic control of DC-to-AC bridge inverters using neural networks is presented. Results obtained from an experimental implementation of a neural network-based inverter system are included. The implementation does not depend on any hardware configuration and can be modified without affecting the performance     

Identification and control of continuous-time nonlinear systems via dynamic neural networks

In this paper, we present an algorithm for the online identification and adaptive control of a class of continuous-time nonlinear systems via dynamic neural networks. The plant considered is an unknown multi-input/multi-output continuous-time higher order nonlinear system. The control scheme includes two parts: a dynamic neural network is employed to perform system identification and a controller based on the proposed dynamic neural network is developed to track a reference trajectory. Stability analysis for the identification and the tracking errors is performed by means of Lyapunov stability criterion. Finally, we illustrate the effectiveness of these methods by computer simulations of the Duffing chaotic system and one-link rigid robot manipulator. The simulation results demonstrate that the model-based dynamic neural network control scheme is appropriate for control of unknown continuous-time nonlinear systems with output disturbance noise.     

A new macromodeling approach for nonlinear microwave circuits basedon recurrent neural networks

A new macromodeling approach is developed in which a recurrent neural network (RNN) is trained to learn the dynamic responses of nonlinear microwave circuits. Input and output waveforms of the original circuit are used as training data. A training algorithm based on backpropagation through time is developed. Once trained, the RNN macromodel provides fast prediction of the full analog behavior of the original circuit, which can be useful for high-level simulation and optimization. Three practical examples of macromodeling a power amplifier, mixer, and MOSFET are used to demonstrate the validity of the proposed macromodeling approach     

A neural network approach to the traffic control problem in reverse baseline networks

A neural network for the traffic control problem applied to reverse baseline networks has been proposed in this paper. This problem has been first represented by an energy function. A neural network is applied for maximizing the energy of the function under the constraints of the reverse baseline network. The number of iteration steps in our neural network is limited by a performed upper bound O(n), wheren is the size of ann ×n network. The throughputs of our neural network have been shown by the empirical results to be better than the conventional algorithm (modified Bipartite Matching Algorithm) when the packet densities rise higher than 50%.     

An improved scheme for direct adaptive control of dynamical systems using backpropagation neural networks

This paper presents an improved direct control architecture for the on-line learning control of dynamical systems using backpropagation neural networks. The proposed architecture is compared with the other direct control schemes. In this scheme the neural network interconnection strengths are updated based on the output error of the dynamical system directly, rather than using a transformed version of the error employed in other schemes. The ill effects of the controlled dynamics on the on-line updating of the network weights are moderated by including a compensating gain layer. An error feedback is introduced to improve the dynamic response of the control system. Simulation studies are performed using the nonlinear dynamics of an underwater vehicle and the promising results support the effectiveness of the proposed scheme.     

Real-time control of reactive ion etching using neural networks

This paper explores the use of neural networks for real-time, model-based feedback control of reactive ion etching (RIE). This objective is accomplished in part by constructing a predictive model for the system that can be approximately inverted to achieve the desired control. An indirect adaptive control (IAC) strategy is pursued. The IAC structure includes a controller and plant emulator, which are implemented as two separate back-propagation neural networks. These components facilitate nonlinear system identification and control, respectively. The neural network controller is applied to controlling the etch rate of a GaAs/AlGaAs metal-semiconductor-metal (MSM) structure in a BCl₃/Cl₂ plasma using a Plasma Therm 700 SLR series RIE system. Results indicate that in the presence of disturbances and shifts in RIE performance, the IAC neural controller is able to adjust the recipe to match the etch rate to that of the target value in less than 5 s. These results are shown to be superior to those of a more conventional control scheme using the linear quadratic Gaussian method with loop-transfer recovery, which is based on a linearized transfer function model of the RIE system     

Stability in contractive nonlinear neural networks

We consider models of the form mu chi = -x + p + WF(x) where x = x(t) is a vector whose entries represent the electrical activities in the units of a neural network. W is a matrix of synaptic weights, F is a nonlinear function, and p is a vector (constant or slowly varying over time) of inputs to the units. If the map WF(x) is a contraction, then the system has a unique equilibrium which is globally asymptotically stable; consequently the network acts as a stable encoder in that its steady-state response to an input is independent of the initial state of the network. We consider some relatively mild restrictions on W and F(x), involving the eigenvalues of W and the derivative of F, that are sufficient to ensure that WF(x) is a contraction. We show that in the linear case with spatially-homogeneous synaptic weight, the eigenvalues of W are simply related to the Fourier transform of the connection pattern. This relation makes it possible, given cortical activity patterns as measured by autoradiographic labeling, to construct a pattern of synaptic weights which produces steady state patterns showing similar frequency characteristics. Finally, we consider the relationships, in the spatial and frequency domains, between the equilibrium of the model and that of the linear approximation mu chi = -x + p + Wx; this latter equilibrium can be computed easily from p in the homogeneous case using discrete Fourier transforms.     

Stable identification of nonlinear systems using neural networks: theory and experiments

This paper presents an approach for stable identification of multivariable nonlinear system dynamics using a multilayer feedforward neural network. Unlike most of the previous neural network identifiers, the proposed identifier is based on a nonlinear-in-parameters neural network (NLPNN). Therefore, it is applicable to systems with higher degrees of nonlinearities. Both parallel and series-parallel models are used with no a priori knowledge about the system dynamics. The method can be considered both as an online identifier that can be used as a basis for designing a neural network controller as well as an offline learning scheme for monitoring the system states. A novel approach is proposed for the weight updating mechanism based on the modification of the backpropagation (BP) algorithm. The stability of the overall system is shown using Lyapunov's direct method. To demonstrate the performance of the proposed algorithm, an experimental setup consisting of a three-link macro-micro manipulator (M/sup 3/) is considered. The proposed approach is applied to identify the dynamics of the experimental robot. Experimental and simulation results are given to show the effectiveness of the proposed learning scheme.     

Real-time parallel adaptive neural network control for nonlinear servomechanisms—an approach using direct adaptive techniques

In this paper, a parallel adaptive neural network control system applicable to nonlinear dynamical systems of the type commonly encountered in many practical position control servomechanisms is developed. The controller is based on the use of direct adaptive techniques and an approach of using an additional parallel neural network to provide adaptive enhancements to a basic fixed neural network-based nonlinear controller. Properties of the proposed new controller are discussed in the paper and it is shown that if Gaussian radial basis function networks are used for the additional parallel neural network, uniformly stable adaptation is assured and asymptotic tracking of the position reference signal is achieved. The effectiveness of the proposed adaptive neural network control system is demonstrated in real-time implementation experiments for position control in a servomechanism with asymmetrical loading and changes in the load.     

基于T-S模糊神经网络的ATM网络拥塞控制

本文充分考虑了模糊神经网络的学习功能，提出了利用T－S模糊神经网络算法对ATM网络进行拥塞控制的方案。仿真结果表明，该方法改善了网络对拥塞的实时处理能力，又增加了网络资源的利用率。     

基于神经网络的一类非线性系统自适应反步控制

针对传统自适应控制需要满足匹配条件、激发信号存在以及逼近误差有界等条件,提出一种新的基于神经网络的一类非线性系统自适应反步控制器设计方案.使用三层神经网络逼近系统的非线性特性,通过网络权系数自适应调整来不断的在线估计未知的逼近误差上界,采用有σ修正项的自适应律以放松持续激励条件.给出了基于Lyapunov意义上的闭环系统稳定性分析,证明跟踪误差收敛于原点的一个ε领域内.仿真结果表明了所提反步控制器的正确性.     

Optimal nonlinear adaptive prediction and modeling of MPEG video inATM networks using pipelined recurrent neural networks

This paper investigates the application of a pipelined recurrent neural network (PRNN) to the adaptive traffic prediction of MPEG video signal via dynamic ATM networks. The traffic signal of each picture type (I, P, and B) of MPEG video is characterized by a general nonlinear autoregressive moving average (NARMA) process. Moreover, a minimum mean-squared error predictor based on the NARMA model is developed to provide the best prediction for the video traffic signal. However, the explicit functional expression of the best mean-squared error predictor is actually unknown. To tackle this difficulty, a PRNN that consists of a number of simpler small-scale recurrent neural network (RNN) modules with less computational complexity is conducted to introduce the best nonlinear approximation capability into the minimum mean-squared error predictor model in order to accurately predict the future behavior of MPEG video traffic in a relatively short time period based on adaptive learning for each module from previous measurement data, in order to provide faster and more accurate control action to avoid the effects of excessive load situation. Since those modules of PRNN can be performed simultaneously in a pipelined parallelism fashion, this would lead to a significant improvement in the total computational efficiency of PRNN. In order to further improve the convergence performance of the adaptive algorithm for PRNN, a learning-rate annealing schedule is proposed to accelerate the adaptive learning process. Another advantage of the PRNN-based predictor is its generalization from learning that is useful for learning a dynamic environment for MPEG video traffic prediction in ATM networks where observations may be incomplete, delayed, or partially available. The PRNN-based predictor presented in this paper is shown to be promising and practically feasible in obtaining the best adaptive prediction of real-time MPEG video traffic     

Precise friction control for the nonlinear friction system using the friction state observer and sliding mode control with recurrent fuzzy neural networks

This paper deals with a tracking control problem of a mechanical servo system with nonlinear dynamic friction which contains a directly immeasurable friction state variable and an uncertainty caused by incomplete parameter modeling and its variations. In order to provide an efficient solution to these control problems, we propose a composite control scheme, which consists of a friction state observer, a RFNN approximator and an approximation error compensator with sliding mode control. In first, a sliding mode controller and friction state observer are designed to estimate the unknown internal state of the LuGre friction model. Next, a RFNN is developed to approximate an unknown lumped friction uncertainty. Finally, an adaptive error compensator is designed to compensate an approximation error of RFNN. Some simulations and experiments on the mechanical servo system composed of ball-screw and DC servo motor are executed. Their results give a satisfactory performance of the proposed control scheme.