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

Abstract

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.

Slippage Sensory Feedback and Nonlinear Force Control System for a Low-Cost Prosthetic Hand

“…At this moment, the finger is been controlled in a predictive fashion, based on a static model. However, it is important to make the model to approach asymptotically to the real system in order to better represent the system dynamics [14]. This added precision will result in better performance of the control system.…”

“…The minimization of the objective function was implemented based on the methodology explained in [11,14]. It is performed by using gradient descendent technique where the future set of control inputs is determined by:…”

“…(16), a recursive method is employed (for more details about this methodology please consult [14]). Furthermore, we designed the feedback control algorithm such that every time the system reaches a force within % 1  of the reference force, the motor is turned off.…”

Operation of Compressor and Electronic Expansion Valve via Different Controllers

“…Since ANNs define, in general, a nonlinear algebraic function, they can cope with nonlinearities inherent in control systems possessing complex dynamics. As in the general ANN literature, the mostly widely used ANN model in identification and control is the Multi Layer Perceptron (MLP) due to its function approximation capability and the existence of an efficient learning algorithm (Ahmed, 2000;Lightbody & Irwin, 1995;Meireles et al, 2003;Noriega & Wang, 1998;Omidvar & Elliott, 1997). MLP is a multilayer, algebraic neural network of neurons, called as perceptrons, which are multi-input, single-output functional units taking firstly a weighted sum of their inputs and then pass it through a sigmoidal nonlinearity to produce its output shown in Fig.…”

PNNARMA model: an alternative to phenomenological models in chemical reactors

“…Thus, they can be used to generate NARMA models which are referred in this work as series-parallel models. This approach has been used in numerous applications (Narendra and Parthasarathy, 1990;Bhat and McAvoy, 1990;Chen and Billings, 1992;Levin and Narendra, 1995;Choi et al, 1996;Suykens and Bersini, 1996;Levin and Narendra, 1996;Narendra and Mukhopadhyay, 1997;Lu and Basan, 1998;Noriega and Wang, 1998). However, these models cannot act as process simulators because a discrete sequence of delayed measured output of the process is required.…”