Differential Neural Networks for Robust Nonlinear Control (original) (raw)
Related papers
IETE Journal of Research, 2007
This paper addresses the identification and control of nonlinear systems by means of Fuzzy Hammerstein (FH) models, which consist of a static fuzzy model connected in series with a linear dynamic model. For the identification of nonlinear dynamic systems with the proposed FH models, two methods are proposed. The first one is an alternating optimization algorithm that iteratively refines the estimate of the linear dynamics and the parameters of the static fuzzy model. The second method estimates the parameters of the nonlinear static model and of the linear dynamic model simultaneously by using a constrained recursive least-squares algorithm. The obtained FH model is incorporated in a model-based predictive control scheme and a new constraint-handling method is presented. A simulated water-heater process is used as an illustrative example. A comparison with an affine neural network and a linear model is given. Simulation results show that the proposed FH modeling approach is useful for modular parsimonious modeling and model-based control of nonlinear systems.
Model-based identification and control of nonlinear dynamic systems using neural networks
1996
The difficulties in identification and control of engineering systems are due to several factors including the presence of several types of nonlinearities, and significant and unknown sources of variations in the operating conditions of the system. In many of these problems, the underlying physics that contributes to the nonlinear system characteristics can be modeled using physical laws. However, due to analytical tractability, the traditional approach has not always made effective use of available physically based models. In this thesis, new parameter estimation and control techniques, which take advantage of prior physical knowledge of dynamic systems, are presented. The tools used are artificial neural networks (ANN). For parameter estimation problems, the scheme denoted as theta\thetatheta-adaptive neural networks (TANN) is developed. TANN is useful for systems where the unknown parameters occur nonlinearly. For control problems, we consider two classes of nonlinear stabilization probl...
Using Neural Networks for Identification and Control of Systems
2015
The present work addresses the utilization of Artificial Neural Networks (NN) for the identification and control of systems, in special to control nonlinear dynamic systems or systems with some degree of uncertainty. Because NNs have an inherent ability to approximate functions and to adapt to changes in input and parameters, they can be used to control systems too complex for linear controllers, such as PID controllers. In the present work a mathematical basis for NN is presented, the mathematical representation of a process unit, or neuron, and how they can be put together in order to form nets that can learn from external data. In sequence, it is presented structures of inputs that can be used along with NN to model nonlinear systems. The most common configurations of input vectors for the training of NN are highlighted. Following, a method of control is presented that take advantage of NN, where a NN is used to build a predictive nonlinear controller using a model predictive con...
Modelling and Control of Dynamical Systems Using Neural Network – A Review
2020
This paper presents a brief review on how artificial neural networks can be used in modelling and control of dynamical systems. The paper is broadly categorized into two; the first part is a short overview on artificial neural networks, particularly its generalization property, as applied to systems identification. The subsequent part contains a review onsome of the typical approaches used in the control of dynamical systems using neural networks which includes model predictive control, NARMA-L2 Control and model reference control. Finally, a comparative conclusion was made to distinguish the performances of the different control methods presented in this paper.
Review of identification techniques for nonlinear systems using neural networks
Control Engineering Practice, 1993
Most practical systems exhibit nonlinear characteristics of varying extent e.g from a simple valve to that of pH-processes in a chemical industry. In this paper we briefly review some of the Neural Network methods with a view to identify such systems. This is due to the fact that identification of the unknown system parameters form the backbone of most adaptive control strategies. In this paper the neural net techniques are reviewed from the point of view of approximating the hypersurface which maps the Input-Output space.
Neural Networks based Identification for Control
This paper raises the issue of finding reduced/minimal state-space form for MIMO systems based on neural networks. Two cases are studied: when system is given as a "black-box" model and when order of the controlled system is known a priori. Modified structure of the standard NN-ANARX (Additive Nonlinear AutoRegressive with eXogenous inputs based on Neural Networks) allows to eliminate all reduced interconnections between neurons and thus to get the minimal state-space representation in second case. If we deal with unknown dynamical system then one can reduce model and find optimal structure of the neural network automatically using genetic algorithm (GA). After the model was found, parameters of the NN can be used to design a state controller for the control of nonlinear MIMO systems using the feedback linearization.
System identification using dynamic neural networks: Training and initialization aspects
2002
This paper explores training and initialization aspects of dynamic neural networks when applied to the nonlinear system identification problem. A well known dynamic neural network structure contains both output states and hidden states. Output states are related to the outputs of the system represented by the network. Hidden states are particularly important in allowing dynamic neural networks to approximate complex nonlinear dynamics. An optimisation based method is proposed in this paper for properly initialising the hidden states of a dynamic neural network, so as to avoid the introduction of bias in the network parameters as a result of incorrect hidden state initialisation. Furthermore, a simple optimisation based method is proposed to initialise the hidden states once the network has been trained. The methods are illustrated with experimental data taken from a laboratory scale pressure plant. Copyright c ¢ 2002 IFAC.
Stability Analysis of Neural Networks-Based System Identification
Modelling and Simulation in Engineering, 2008
This paper treats some problems related to nonlinear systems identification. A stability analysis neural network model for identifying nonlinear dynamic systems is presented. A constrained adaptive stable backpropagation updating law is presented and used in the proposed identification approach. The proposed backpropagation training algorithm is modified to obtain an adaptive learning rate guarantying convergence stability. The proposed learning rule is the backpropagation algorithm under the condition that the learning rate belongs to a specified range defining the stability domain. Satisfying such condition, unstable phenomena during the learning process are avoided. A Lyapunov analysis leads to the computation of the expression of a convenient adaptive learning rate verifying the convergence stability criteria. Finally, the elaborated training algorithm is applied in several simulations. The results confirm the effectiveness of the CSBP algorithm.