TY  - CHAP
A1  - Yamabe, Yuichiro
A1  - Kawamura, Hiroshi
A1  - Tani, Akinori
T1  - Optimal Design for Recurrent Architecture Network Harmonized with Circulation-type Societies by Applying Genetic Algorithms to Multiagent Model
N2  - In this paper, a circulation-type society is expressed by recurrent architecture network described with multi-agent model which consists of the following agents: user, builder, reuse maker, fabricator, waste disposer, material maker and earth bank (see Fig.1). Structural members, materials, resources and monies move among these agents. Each agent has its own rules and aims, regarding structural damages, lifetime, cost reduction, numbers of structural members and structural systems. Reasonable prices of members (fresh, reused, recycled and disposed) can be optimized by GAs in this system considering equal distribution of monies among agents.
KW  - Mehragentensystem
KW  - Lernendes System
KW  - Genetischer Algorithmus
Y1  - 2004
U6  - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20111215-1892
ER  - 
TY  - JOUR
A1  - Vogel, Manfred
A1  - Breit, Manfred
A1  - Märki, Fabian
T1  - Optimization of 4D Process Planning using Genetic Algorithms
N2  - The presented work focuses on the presentation of a discrete event simulator which can be used for automated sequencing and optimization of building processes. The sequencing is based on the commonly used component–activity–resource relations taking structural and process constraints into account. For the optimization a genetic algorithm approach was developed, implemented and successfully applied to several real life steel constructions. In this contribution we discuss the application of the discrete event simulator including its optimization capabilities on a 4D process model of a steel structure of an automobile recycling facility.
KW  - Produktmodell
KW  - Simulation
KW  - Bautechnik
KW  - Genetischer Algorithmus
Y1  - 2004
U6  - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20111215-2360
ER  - 
TY  - CHAP
A1  - Schoof, Jochen
T1  - Kommunizierende Genetische Algorithmen: Durch Evolution zur Kooperation
N2  - Die Kooperation zwischen Menschen und Computern gewinnt in zahlreichen Problemstellungen mehr und mehr an Bedeutung. Ein wesentlicher Grund hierfür ist die ständig wachsende Komplexität relevanter Problemstellungen. Dadurch bedingt sind weder der Mensch noch der Computer alleine in der Lage, zufriedenstellende Lösungen zu entwickeln. Die Kombination der individuellen Fähigkeiten hat sich in vielen Bereichen als gewinnbringend erwiesen. Genetische Algorithmen (GA) als Repräsentanten der >Evolutionary Computation< stellen einen Ansatz zur Lösung hochkomplexer Optimierungsaufgaben dar, der sich an den Vorgängen der Evolution orientiert. Im Gegensatz zu vielen anderen Optimierungsverfahren bringen sie einige Eigenarten mit, die kooperative Erweiterungen einfach und erfolg-versprechend machen. Der vorgestellte kommunizierende Genetische Algorithmus kombiniert die Vorteile der GA mit der Fähigkeit zur Kooperation. Es gelingt bei seiner Verwendung, gute externe Vorschläge aufzunehmen, während schlechte Vorschläge keinerlei negative Auswirkungen zeigen. Diese Robustheit gegen Irrtümer und Fehleingaben macht den KGA zu einer idealen Basis für Programme zur kooperativen Problemlösung.
KW  - Mensch-Maschine-Kommunikation
KW  - Genetischer Algorithmus
Y1  - 2000
U6  - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20111215-6123
ER  - 
TY  - CHAP
A1  - Bernstein, Swanhild
A1  - Richter, Matthias
T1  - The Use of Genetic Algorithms in Finite Element Model Identification
N2  - A realistic and reliable model is an important precondition for the simulation of revitalization tasks and the estimation of system properties of existing buildings. Thereby, the main focus lies on the parameter identification, the optimization strategies and the preparation of experiments. As usual structures are modeled by the finite element method. This as well as other techniques are based on idealizations and empiric material properties. Within one theory the parameters of the model should be approximated by gradually performed experiments and their analysis. This approximation method is performed by solving an optimization problem, which is usually non-convex, of high dimension and possesses a non-differentiable objective function. Therefore we use an optimization procedure based on genetic algorithms which was implemented by using the program package SLang...
KW  - Finite-Elemente-Methode
KW  - Genetischer Algorithmus
Y1  - 2003
U6  - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20111215-2769
ER  -