Using Machine Learning and GA to Solve Time-Cost Trade-Off Problems
Publication: Journal of Construction Engineering and Management
Volume 125, Issue 5
Abstract
Existing genetic algorithms (GA) based systems for solving time-cost trade-off problems suffer from two limitations. First, these systems require the user to manually craft the time-cost curves for formulating the objective functions. Second, these systems only deal with linear time-cost relationships. To overcome these limitations, this paper presents a computer system called MLGAS (Machine Learning and Genetic Algorithms based System), which integrates a machine learning method with GA. A quadratic template is introduced to capture the nonlinearity of time-cost relationships. The machine learning method automatically generates the quadratic time-cost curves from historical data and also measures the credibility of each quadratic time-cost curve. The quadratic curves are then used to formulate the objective function that can be solved by the GA. Several improvements are made to enhance the capacity of GA to prevent premature convergence. Comparisons of MLGAS with an experienced project manager indicate that MLGAS generates better solutions to nonlinear time-cost trade-off problems.
Get full access to this article
View all available purchase options and get full access to this article.
References
1.
Ahlfred, D. P., and Mulvey, J. M. (1987). “Nonlinear programming on generalised networks.” ACM Trans. on Math. Software, 13, 350–367.
2.
Atkin, J. W. (1987). “The extraction of refined rules from knowledge-based neural networks.” Machine Learning, 13(1), 71–101.
3.
Berman, F. B. (1964). “Resource allocation in a PERT network under continuous activity time-cost functions.” Mgmt. Sci., 10, 724–735.
4.
Brooke, A., Kendrick, D., and Meeraus, L. (1988). GAMS: A user's guide. Scientific Press, Redwood City, Calif.
5.
Burns, S. A., Liu, L., and Feng, C. W. (1996). “The LP/IP hybrid method for construction time-cost trade-off analysis.” Constr. Mgmt. and Economics, 14(4), 265–276.
6.
Cusack, W. J. ( 1985). “Notes on epistemology of a rule-based expert system.” Artificial Intelligence, 59(Feb.), 197–204.
7.
Deckro R. F., Berbert, J. E., Verdini, W. A., Grimsrud, P. H., and Venkateshwar, S. (1995). “Nonlinear time/cost tradeoff models in project management.” Comp. in Industrial Engrg., 28(2), 219–229.
8.
De Jong, K. ( 1975). “An analysis of the behavior of a class of genetic adaptive systems,” PhD dissertation, University of Michigan, Ann Arbor, Mich.
9.
Eshelman, L. J., Caruana, R. A., and Schaffer, J. D. (1989). “Biases in the crossover landscape.” Proc., 3rd Int. Conf. on Genetic Algorithms, J. D. Schaffer, ed., Morgan Kaufmann Publishers, Inc., San Mateo, Calif., 10–19.
10.
Feng, C.-W., Liu, L., and Burns, S. (1997). “Using genetic algorithms to solve construction time-cost tradeoff problems.”J. Comp. in Civ. Engrg., ASCE, 11(3), 184–189.
11.
Fondahl, J. W. (1961). “A non-computer approach to the critical path method for the construction industry.” Tech. Rep. No 9, Constr. Inst., Standford University, Stanford, Calif.
12.
Fulkerson, D. (1961). “A network flow computation for project cost curves.” Mgmt. Sci., 7, 167–178.
13.
Goldberg, D. E. (1989). Genetic algorithms in search, optimization and machine learning. Addison-Wesley. Reading, Mass.
14.
Henderson, J. M., and Quandt, R. E. (1971). Microeconomic theory: A mathematical approach, 2nd Ed., McGraw-Hill, New York.
15.
HKHA. (1990). Annu. Rep., Hong Kong Housing Authority, Hong Kong.
16.
Holland, J. H. (1975). Adaptation in natural and artificial systems. MIT Press, Cambridge, Mass.
17.
Holt, B., and Fu, L. M. (1955). “Rule generation from neural networks.” IEEE Trans. on Sys., Man and Cybernetics, 8(3), 54–63.
18.
Kelly, J. E. (1961). “Critical-path planning and scheduling: Mathematical basis.” Operational Res., 9, 296–320.
19.
Khosrowshahi, F. (1997). “The optimum project duration and cost curve for Hong Kong public housing projects.” Engrg., Constr. and Arch. Mgmt., 4(4), 249–269.
20.
Langley, P., Simon, H. A., and Bradshaw, G. L. (1987). “Heuristics for empirical discovery.” Computational models of learning, B. Leonard, ed., Springer, Berlin, 271–279.
21.
Li, H. (1994). Machine learning of design concepts. Computational Mechanics Press. Southampton, U.K.
22.
Li, H., and Love, P. (1997). “Using improved genetic algorithms to facilitate time-cost optimization.”J. Constr. Engrg. and Mgmt., ASCE, 123(3), 233–237.
23.
Liebman, J., Lasdon, L., Schrage, L., and Waren, A. (1986). Modeling and optimization with GINO. Scientific Press, Palo Alto, Calif.
24.
Moselhi, O. (1991). “Neural networks as tools in construction.”J. Constr. Engrg. and Mgmt., 117(4), 606–625.
25.
Newton, R. S. (1991). “Research in machine learning: Recent progress, classification of methods, and future directions.” Machine learning: An artificial intelligence approach, Y. Kodratoff and R. S. Michalski, eds., Vol. 3, Morgan Kaufmann, Calif., 3–30.
26.
Prager, W. (1963). “A structural method of computing project cost polygons.” Mgmt. Sci., 9(3), 394–404.
27.
Reda, R., and Carr, R. I. (1989). “Time-cost tradeoff among related activities.”J. Constr. Engrg. and Mgmt., ASCE, 115(3), 475–486.
28.
Skibniewski, M., and Armijos, A. (1990). “Linear programming approach to construction equipment and labour assignments.” Struct. and Comp., 12, 44–50.
29.
Syswerda, G. (1989). “Uniform crossover in genetic algorithms.” Proc., 3rd Int. Conf. on Genetic Algorithms, J. D. Schaffer, ed., Morgan Kaufmann Publishers, Inc., San Mateo, Calif., 2–9.
Information & Authors
Information
Published In
Journal of Construction Engineering and Management
Volume 125 • Issue 5 • September 1999
Pages: 347 - 353
History
Received: Oct 14, 1998
Published online: Sep 1, 1999
Published in print: Sep 1999
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.