Computational & Technology Resources
an online resource for computational,
engineering & technology publications
Civil-Comp Proceedings
ISSN 1759-3433
CCP: 82
Edited by: B.H.V. Topping
Paper 31

Application of a Genetic Algorithm to Optimize the Layout of Temporary Construction Facilities

B. Soltani+, A.A. Ramezanianpour* and H.R. Ashrafi*

+Department of Civil Engineering, Construction Engineering and Management
*Department of Civil Engineering
Amir Kabir University of Technology, Tehran, Iran

Full Bibliographic Reference for this paper
B. Soltani, A.A. Ramezanianpour, H.R. Ashrafi, "Application of a Genetic Algorithm to Optimize the Layout of Temporary Construction Facilities", in B.H.V. Topping, (Editor), "Proceedings of the Eighth International Conference on the Application of Artificial Intelligence to Civil, Structural and Environmental Engineering", Civil-Comp Press, Stirlingshire, UK, Paper 31, 2005. doi:10.4203/ccp.82.31
Keywords: genetic algorithms, site layout, temporary facilities, operator, crossover, mutation.

An essential component of pre-tender planning, pre-contract planning and starting the project is site establishment. An efficient and effective site establishment provides the foundation for a successful project by configuring, structuring and organizing those temporary facilities needed to support the work on site.

Determination of position, availability and the period of presence of the temporary facilities for a construction site are important. The optimum layout of temporary facilities has a great effect in cost reduction of a project. In the present study, a Genetic Algorithm (GA) was used to optimize the layout of construction sites.

The optimization was conducted using both the crossover and the mutation operation; furthermore, using different rates of these operators and comparing the obtained results, the best rates of crossover and mutation operator were obtained. It was found that the optimum rates of cycle crossover and swap mutation were 80 and 0.2 respectively.

The objective of the site layout is to position temporary facilities at the correct time that the construction work can be served satisfactorily with minimal cost and reduced risk and working environment. While small construction projects might require little temporary site establishment, larger projects may require extensive site infrastructure. This paper starts with a general description of site layout and genetic algorithm and formulation for genetic algorithm solution is proposed. Following an introduction of site layout and genetic algorithm, numerical example of the problem is proposed for solution using genetic algorithm. Various crossover and mutation operators are considered for use in the solution. In this paper, genetic algorithm was used to solve construction temporary facilities in order to minimize cost of setup and removal.

Site layout problems have long been recognized as being of importance but while they have been written about, there has been no complete proposed solution. The nature of the problem means that no well-defined method can guarantee a solution [1].

The facility layout problem is concerned with finding the most efficient arrangement of several indivisible departments with unequal area requirements within a facility. The objective of the facility layout problem is to minimize the material handing cost or resource movement cost inside a facility.

In this paper the solution methods employed to solve the facility layout problem are heuristics methods. Heuristic methods are usually used for larger problems. The current trend in research for facility layout problems is concentrated in three areas: developing more suitable models, extending existing models to include a time element (dynamic layout), adding uncertainty (stochastic layout) or adding multiple criteria for evaluation. There are also special cases for specific types of problems.

The review of the facility layout problem can be found in Russell and Gau [2]. In this paper, the construction site layout problem is specified as the task to position a set of facilities on the site so that the layout objectives are optimized subject to layout constraints. The objective functions can be of any form that might be considered by a site manager or builder. In this paper an attempt was made to develop a model including the time element.

The behavior of any genetic algorithm on any problem depends on many factors with their random behavior which are not totally predictable. Different combinations of the possible values of the parameters were selected and genetic algorithm was implemented for 100 generations with a population of 100.

Twort, A.C., Rees, J.G., "Civil Engineering Supervision and Management" 3rd Edition. Arnold, London, 1995.
Russell, D.M., Gau, K.Y., "Trends and Perspectives: The Facility Layout Problem: Recent and Emerging Trends and Perspectives", Journal of Manufacturing Systems, 15(5), 1996, 351-366. doi:10.1016/0278-6125(96)84198-7

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £80 +P&P)