Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

A simple genetic algorithm for the design of reinforced concrete beams

A simple genetic algorithm for the design of reinforced concrete beams We present an optimization model for the design of rectangular reinforced concrete beams subject to a specified set of constraints. Our model is more realistic than previously published models because it minimizes the cost of the beam on strength design procedures, while also considering the costs of concrete, steel and shuttering. Thus our method leads to very practical designs. As there is an infinite number of possible beam dimensions and reinforcement ratios that yield the same moment of resistance, an efficient search technique is preferred over the more traditional iterative methods. We employ a simple genetic algorithm as the search engine, and we compare our results with those obtained via geometric programming. Since the adjustment of parameters in a genetic algorithm (e.g., population size, crossover and mutation rates, and maximum number of generations) is a significant problem for any application, we present our own methodology to deal with this problem. A prototype of this system is currently being tested in México, in order to evaluate its potential as a reliable design tool for real world applications. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Engineering with Computers Springer Journals

A simple genetic algorithm for the design of reinforced concrete beams

Loading next page...
 
/lp/springer-journals/a-simple-genetic-algorithm-for-the-design-of-reinforced-concrete-beams-aefYRtqkER

References (30)

Publisher
Springer Journals
Copyright
Copyright © 1997 by Springer-Verlag London Limited
Subject
Computer Science; Computer-Aided Engineering (CAD, CAE) and Design; Math. Applications in Chemistry; Systems Theory, Control; Calculus of Variations and Optimal Control; Optimization; Classical Mechanics; Appl.Mathematics/Computational Methods of Engineering
ISSN
0177-0667
eISSN
1435-5663
DOI
10.1007/BF01200046
Publisher site
See Article on Publisher Site

Abstract

We present an optimization model for the design of rectangular reinforced concrete beams subject to a specified set of constraints. Our model is more realistic than previously published models because it minimizes the cost of the beam on strength design procedures, while also considering the costs of concrete, steel and shuttering. Thus our method leads to very practical designs. As there is an infinite number of possible beam dimensions and reinforcement ratios that yield the same moment of resistance, an efficient search technique is preferred over the more traditional iterative methods. We employ a simple genetic algorithm as the search engine, and we compare our results with those obtained via geometric programming. Since the adjustment of parameters in a genetic algorithm (e.g., population size, crossover and mutation rates, and maximum number of generations) is a significant problem for any application, we present our own methodology to deal with this problem. A prototype of this system is currently being tested in México, in order to evaluate its potential as a reliable design tool for real world applications.

Journal

Engineering with ComputersSpringer Journals

Published: Feb 4, 2005

There are no references for this article.