A Modified Approximate Internal Model-based Neural Control for the Typical Industrial Processes

Journal Title: Elektronika - Year 2014, Vol 18, Issue 1

Abstract

A modification of the Approximate Internal Modelbased Neural Control (AIMNC), using Multi Layer Neural Network (MLNN) is introduced. A necessary condition that the system provides zero steady-state error in case of the constant reference and constant disturbances is derived. In the considered control strategy only one neural network (NN), which is the neural model of the plant, should be trained off-line. An inverse neural controller can be directly obtained from the neural model without need for a further training. Simulations demonstrate performance improvement of the modified AIMNC strategy. An extension of the modified AIMNC controller for the typical industrial processes is proposed.

Authors and Affiliations

Jasmin Igic, Milorad Bozic

Keywords

Related Articles

Design and Implementation of a Novel Directional Coupler for UHF RFID Reader

The directional coupler is applied to isolating RX from TX because of low cost and simplicity compared to the circulator in the radio-frequency identification (RFID) reader. Because of unequal phase velocity between odd...

Research Issues in DFIG Based Wind Energy System

Among different renewable energy sources, Wind energy is the most imperative energy source in power system. The development of grid connected wind energy conversion system expands, its grid connectivity issues has additi...

An Intelligent Hybrid Protocol for Effective Load Balancing and Energy Efficient Routing for MANETs

MANET (Mobile ad hoc network) is an autonomous decentralised network. And it is a collection of wireless mobile nodes that dynamically form a temporary network without the reliance of any infrastructure or central admini...

Some examples of photorefractive oscillators

The photorefractive effect presents a periodical change of the refractive index of an optical environment under the influence of a coherent light. An interesting phenomenon which occurs at this effect is optical phase co...

CFOA-Based Fractional Order PIλDδ Controller

Conventional Current Feedback Operational Amplifier (CFOA) is not current controllable or not electronically controllable. It is thus of interest to add a current mirror into the CFOA in order to make it current controll...

Download PDF file
  • EP ID EP110556
  • DOI 10.7251/ELS1418046I
  • Views 85
  • Downloads 0

How To Cite

Jasmin Igic, Milorad Bozic (2014). A Modified Approximate Internal Model-based Neural Control for the Typical Industrial Processes. Elektronika, 18(1), 46-53. https://europub.co.uk/articles/-A-110556