A Model Order and Time-delay Selection Method for Mimo Non-linear Systems and It’s Application to Neural Modelling
نویسندگان
چکیده
A new model order and time-delay selection method for neural network modelling of SISO non-linear systems has been recently proposed. The extension of this method to the MIMO case is developed in this paper. The MIMO form of the NARX model is considered and the order and time-delay for each input are selected by identifying linearised models of the system. Application of the method to a simulated continuously stirred tank reactor (CSTR) process is investigated to demonstrate the selection procedure. Neural models are subsequently developed for the process based on the order and time-delay selected using the proposed method and are compared to other neural models with different structures to demonstrate the effectiveness of the method.
منابع مشابه
Adaptive Consensus Control for a Class of Non-affine MIMO Strict-Feedback Multi-Agent Systems with Time Delay
In this paper, the design of a distributed adaptive controller for a class of unknown non-affine MIMO strict-feedback multi agent systems with time delay has been performed under a directed graph. The controller design is based on dynamic surface control method. In the design process, radial basis function neural networks (RBFNNs) were employed to approximate the unknown nonlinear functions. S...
متن کاملModelling and Compensation of uncertain time-delays in networked control systems with plant uncertainty using an Improved RMPC Method
Control systems with digital communication between sensors, controllers and actuators are called as Networked Control Systems (NCSs). In general, NCSs encounter with some problems such as packet dropouts and network induced delays. When plant uncertainty is added to the aforementioned problems, the design of the robust controller that is able to guarantee the stability, becomes more complex. In...
متن کاملMarkovian Delay Prediction-Based Control of Networked Systems
A new Markov-based method for real time prediction of network transmission time delays is introduced. The method considers a Multi-Layer Perceptron (MLP) neural model for the transmission network, where the number of neurons in the input layer is minimized so that the required calculations are reduced and the method can be implemented in the real-time. For this purpose, the Markov process order...
متن کاملRobust Adaptive Actuator Failure Compensation of MIMO Systems with Unknown State Delays
In this paper, a robust adaptive actuator failure compensation control scheme is proposed for a class of multi input multi output linear systems with unknown time-varying state delay and in the presence of unknown actuator failures and external disturbance. The adaptive controller structure is designed based on the SPR-Lyapunov approach to achieve the control objective under the specific assump...
متن کاملNovel Radial Basis Function Neural Networks based on Probabilistic Evolutionary and Gaussian Mixture Model for Satellites Optimum Selection
In this study, two novel learning algorithms have been applied on Radial Basis Function Neural Network (RBFNN) to approximate the functions with high non-linear order. The Probabilistic Evolutionary (PE) and Gaussian Mixture Model (GMM) techniques are proposed to significantly minimize the error functions. The main idea is concerning the various strategies to optimize the procedure of Gradient ...
متن کامل