Evolvable hardware a new approach for control design

Authors:
Tatiane Jesus De Campos;José Raimundo De Oliveira;Mario Jungbeck
Affiliations:
School of Electrical and Computer Engineering, State University of Campinas, Campinas, SP, Brasil;School of Electrical and Computer Engineering, State University of Campinas, Campinas, SP, Brasil;School of Electrical and Computer Engineering, State University of Campinas, Campinas, SP, Brasil
Venue:
EC'06 Proceedings of the 7th WSEAS International Conference on Evolutionary Computing
Year:
2006

Citing 3
Cited 1

Control System Design

Control System Design
Unconstrained Evolution and Hard Consequences

Papers from an international workshop on Towards Evolvable Hardware, The Evolutionary Engineering Approach
On-Line Evolution of FPGA-Based Circuits: A Case Study on Hash Functions

EH '99 Proceedings of the 1st NASA/DOD workshop on Evolvable Hardware

Evolvable hardware applied to multi-objective optimization of controllers structure for robot manipulators

ACMOS'08 Proceedings of the 10th WSEAS International Conference on Automatic Control, Modelling & Simulation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Evolvable hardware (EHW) is a technique introduced to automatically design circuits where the circuit configuration is carried out by evolutionary algorithms. This paper shows that the evolutionary approach can discover the concept and learning behavior of the control systems. The system tested is a nonlinear pendulum. Experiments with different processes indicate that the gains obtained with evolvable hardware may provide better responses than those obtained by the classical PID controller whose gains are set by Genetic Algorithms. In this paper the Integral of the Square Error (ISE) criteria was used as performance index to be minimized through applying of Genetic Algorithms and Evolvable Hardware controllers. Analysis and simulation of nonlinear pendulum is provided to demonstrate that the proposed evolvable controller has excellent results.