Design, development and performance optimization of a new artificial intelligent controlled multiple-beam optical scanning module

Johnny Siaw Paw Koh, I. B. Aris, Vigna Kumaran Ramachandaramurthy, S. M. Bashi, M. H. Marhaban

Research output: Contribution to journalArticle

Abstract

This research presents a new approach to optimise the performance of a multiple-beam optical scanning system in terms of its marking combinations and speed, using Genetic Algorithm (GA). The problem has been decomposed into two sub problems; task segregation, where the marking tasks need to be segregated and assigned for each scanner head and path planning where the best combinatorial paths for each scanner are determined in order to minimise the total motion of marking time. The knowledge acquired by the process is interpreted and mapped into vectors, which are kept in the database and used by the system to guide its reasoning process. The main motivation for this study is to introduce and evaluate an advance new customized GA. Comparison results of different combinatorial operators and tests with different probability factors are shown. Also, proposed are the new modifications to existing crossover operator called DPPC (Dynamic Pre-Populated Crossover) together with modification of a simple crossover selection method, called BCS (Bi-Cycle Selection Method). The performance of the new operator called GA_INSP (GA Inspection Module) for a better evolutionary approach to the time-based problem has been discussed in the study. The representation approach has been implemented via a computer program in order to achieve optimized marking performance. This algorithm has been tested and implemented successfully via a dual-beam optical scanning module.

Original languageEnglish
Pages (from-to)2201-2208
Number of pages8
JournalJournal of Applied Sciences
Volume6
Issue number10
DOIs
Publication statusPublished - 30 Aug 2006

Fingerprint

Genetic algorithms
Scanning
Mathematical operators
Motion planning
Computer program listings
Inspection

All Science Journal Classification (ASJC) codes

  • General

Cite this

@article{f8752fffa9c64d30842d1814100a94f6,
title = "Design, development and performance optimization of a new artificial intelligent controlled multiple-beam optical scanning module",
abstract = "This research presents a new approach to optimise the performance of a multiple-beam optical scanning system in terms of its marking combinations and speed, using Genetic Algorithm (GA). The problem has been decomposed into two sub problems; task segregation, where the marking tasks need to be segregated and assigned for each scanner head and path planning where the best combinatorial paths for each scanner are determined in order to minimise the total motion of marking time. The knowledge acquired by the process is interpreted and mapped into vectors, which are kept in the database and used by the system to guide its reasoning process. The main motivation for this study is to introduce and evaluate an advance new customized GA. Comparison results of different combinatorial operators and tests with different probability factors are shown. Also, proposed are the new modifications to existing crossover operator called DPPC (Dynamic Pre-Populated Crossover) together with modification of a simple crossover selection method, called BCS (Bi-Cycle Selection Method). The performance of the new operator called GA_INSP (GA Inspection Module) for a better evolutionary approach to the time-based problem has been discussed in the study. The representation approach has been implemented via a computer program in order to achieve optimized marking performance. This algorithm has been tested and implemented successfully via a dual-beam optical scanning module.",
author = "Koh, {Johnny Siaw Paw} and Aris, {I. B.} and Ramachandaramurthy, {Vigna Kumaran} and Bashi, {S. M.} and Marhaban, {M. H.}",
year = "2006",
month = "8",
day = "30",
doi = "10.3923/jas.2006.2201.2208",
language = "English",
volume = "6",
pages = "2201--2208",
journal = "Journal of Applied Sciences",
issn = "1812-5654",
publisher = "Asian Network for Scientific Information",
number = "10",

}

Design, development and performance optimization of a new artificial intelligent controlled multiple-beam optical scanning module. / Koh, Johnny Siaw Paw; Aris, I. B.; Ramachandaramurthy, Vigna Kumaran; Bashi, S. M.; Marhaban, M. H.

In: Journal of Applied Sciences, Vol. 6, No. 10, 30.08.2006, p. 2201-2208.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Design, development and performance optimization of a new artificial intelligent controlled multiple-beam optical scanning module

AU - Koh, Johnny Siaw Paw

AU - Aris, I. B.

AU - Ramachandaramurthy, Vigna Kumaran

AU - Bashi, S. M.

AU - Marhaban, M. H.

PY - 2006/8/30

Y1 - 2006/8/30

N2 - This research presents a new approach to optimise the performance of a multiple-beam optical scanning system in terms of its marking combinations and speed, using Genetic Algorithm (GA). The problem has been decomposed into two sub problems; task segregation, where the marking tasks need to be segregated and assigned for each scanner head and path planning where the best combinatorial paths for each scanner are determined in order to minimise the total motion of marking time. The knowledge acquired by the process is interpreted and mapped into vectors, which are kept in the database and used by the system to guide its reasoning process. The main motivation for this study is to introduce and evaluate an advance new customized GA. Comparison results of different combinatorial operators and tests with different probability factors are shown. Also, proposed are the new modifications to existing crossover operator called DPPC (Dynamic Pre-Populated Crossover) together with modification of a simple crossover selection method, called BCS (Bi-Cycle Selection Method). The performance of the new operator called GA_INSP (GA Inspection Module) for a better evolutionary approach to the time-based problem has been discussed in the study. The representation approach has been implemented via a computer program in order to achieve optimized marking performance. This algorithm has been tested and implemented successfully via a dual-beam optical scanning module.

AB - This research presents a new approach to optimise the performance of a multiple-beam optical scanning system in terms of its marking combinations and speed, using Genetic Algorithm (GA). The problem has been decomposed into two sub problems; task segregation, where the marking tasks need to be segregated and assigned for each scanner head and path planning where the best combinatorial paths for each scanner are determined in order to minimise the total motion of marking time. The knowledge acquired by the process is interpreted and mapped into vectors, which are kept in the database and used by the system to guide its reasoning process. The main motivation for this study is to introduce and evaluate an advance new customized GA. Comparison results of different combinatorial operators and tests with different probability factors are shown. Also, proposed are the new modifications to existing crossover operator called DPPC (Dynamic Pre-Populated Crossover) together with modification of a simple crossover selection method, called BCS (Bi-Cycle Selection Method). The performance of the new operator called GA_INSP (GA Inspection Module) for a better evolutionary approach to the time-based problem has been discussed in the study. The representation approach has been implemented via a computer program in order to achieve optimized marking performance. This algorithm has been tested and implemented successfully via a dual-beam optical scanning module.

UR - http://www.scopus.com/inward/record.url?scp=33749128068&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33749128068&partnerID=8YFLogxK

U2 - 10.3923/jas.2006.2201.2208

DO - 10.3923/jas.2006.2201.2208

M3 - Article

VL - 6

SP - 2201

EP - 2208

JO - Journal of Applied Sciences

JF - Journal of Applied Sciences

SN - 1812-5654

IS - 10

ER -