Abstract
A new concept on 'heredity and evolution of designs' was developed by the author and a general algorithm to simulate the heredity and evolution of designs is presented in this study with reference to engineering analysis. The ordinary design process is considered here to have a distributed hierarchical structure and is modeled. The design in each level is optimized by the genetic algorithm to maximize the fitness function under some constraints. In some of the levels, engineering analysis can be involved. The fitness function and constraints to be used for the genetic algorithm in each level are modified by the resulting designs in the lower or upper level. The proposed method is applied to simple examples of car designs and demonstrated. Further studies will follow to examine and evaluate the proposed method from many points of view.
| Original language | English |
|---|---|
| Pages (from-to) | 4646-4652 |
| Number of pages | 7 |
| Journal | Nippon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C |
| Volume | 61 |
| Issue number | 592 |
| Publication status | Published - 1995 Dec |
| Externally published | Yes |
Fingerprint
ASJC Scopus subject areas
- Mechanical Engineering
Cite this
Study on heredity and evolution of designs by using genetic algorithms. / Yamakawa, Hiroshi.
In: Nippon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C, Vol. 61, No. 592, 12.1995, p. 4646-4652.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Study on heredity and evolution of designs by using genetic algorithms
AU - Yamakawa, Hiroshi
PY - 1995/12
Y1 - 1995/12
N2 - A new concept on 'heredity and evolution of designs' was developed by the author and a general algorithm to simulate the heredity and evolution of designs is presented in this study with reference to engineering analysis. The ordinary design process is considered here to have a distributed hierarchical structure and is modeled. The design in each level is optimized by the genetic algorithm to maximize the fitness function under some constraints. In some of the levels, engineering analysis can be involved. The fitness function and constraints to be used for the genetic algorithm in each level are modified by the resulting designs in the lower or upper level. The proposed method is applied to simple examples of car designs and demonstrated. Further studies will follow to examine and evaluate the proposed method from many points of view.
AB - A new concept on 'heredity and evolution of designs' was developed by the author and a general algorithm to simulate the heredity and evolution of designs is presented in this study with reference to engineering analysis. The ordinary design process is considered here to have a distributed hierarchical structure and is modeled. The design in each level is optimized by the genetic algorithm to maximize the fitness function under some constraints. In some of the levels, engineering analysis can be involved. The fitness function and constraints to be used for the genetic algorithm in each level are modified by the resulting designs in the lower or upper level. The proposed method is applied to simple examples of car designs and demonstrated. Further studies will follow to examine and evaluate the proposed method from many points of view.
UR - http://www.scopus.com/inward/record.url?scp=0029487931&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0029487931&partnerID=8YFLogxK
M3 - Article
AN - SCOPUS:0029487931
VL - 61
SP - 4646
EP - 4652
JO - Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C
JF - Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C
SN - 0387-5024
IS - 592
ER -