Premium
Application of genetic algorithm to speed servo system and positioning system
Author(s) -
Yoshida Susumu,
Kamano Takuya,
Suzuki Takayuki,
Harada Hironobu
Publication year - 1996
Publication title -
electrical engineering in japan
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.136
H-Index - 28
eISSN - 1520-6416
pISSN - 0424-7760
DOI - 10.1002/eej.4391170307
Subject(s) - feed forward , control theory (sociology) , controller (irrigation) , fitness function , genetic algorithm , tracking error , convergence (economics) , computer science , servomechanism , tracking (education) , engineering , control engineering , control (management) , artificial intelligence , machine learning , psychology , agronomy , pedagogy , economics , biology , economic growth
This paper considers a genetic algorithm application to feedforward controllers of speed servo and positioning systems. The system consists of a conventional feedback controller and a feedforward controller. The parameters of the feedforward controller are regarded as the chromosome on a gene. The genetic algorithm is used to tune the parameters of the feedforward controller, the objective of which is to make the feedforward controller a dynamic inverse of the plant. The tracking error between the desired output and the actual output at every sampling period is used to calculate the fitness of one gene. The range of mutation is dependent on the magnitude of the tracking error, which ensures parameter convergence. The effect of fitness function and the width of mutation on tracking performances is investigated. The experimental results demonstrate the effectiveness of the proposed genetic algorithm in improving tracking performances.