Applying project management knowledge and hybrid algorithm in predicting the time and cost of completing dam projects

Subject Areas : Research Paper

Reza Bakhshi ¹ , Sina Fard Moradinia ² , Rasool Jani ³ , Ramin Vafaei Poor Sorkhabi ⁴

1 - Department of Civil Engineering, Tabriz Branch, Islamic Azad University, Tabriz, Iran
2 - Department of Civil Engineering, Tabriz Branch, Islamic Azad University, Tabriz, Iran
3 - Department of Civil Engineering, Tabriz Branch, Islamic Azad University, Tabriz, Iran
4 - Department of Civil Engineering, Tabriz Branch, Islamic Azad University, Tabriz, Iran

Received: 2022-12-10 Published : 2024-10-02

Keywords: Hybrid algorithm, EDAC, Kalman filter, Cost prediction, Dam construction,

Abstract :

Introduction: Precisely predicting the time and cost of completing projects is vital because the lack of a proper estimation will be accompanied by an irrational upsurge in the exact execution costs compared to the set budget. Using the earned value method (EVM) to predict the time and cost of projects is prevalent. However, using this method alone highlights good accuracy in predicting time and cost of projects. Consequently, models based on EVM were developed.

Methods: The present article was developed using the EVM method and hybrid algorithms to predict the time and cost of completing projects. To attain this goal, the data from four dams, A, B, C, and D, were used to build models, and the data of the under-construction dam E were used to validate the models resulting from the modeling stage. To this end, the parameters earned schedule (Month), earned value ($), actual progress (%), and actual cost (%) are used as inputs for predicting time and for predicting cost, as well as these parameters, time is also defined as input of hybrid algorithms.

Findings: Comparing the consequences of the hybrid algorithms in the training and test stage designates the high accuracy of the LSSVM-PSO model compared to the LSSVM-GA. The low variance in the error values of these two stages for this model suggests its high generalization ability on unseen data. The use of these hybrid models in forecasting the time for the E dam gave a prior warning for the delay in the completion of the project in the first month. Likewise, in cost predicting, the LSSVM-PSO and LSSVM-GA models issued an early warning in the seventh and ninth months, respectively, for the non-conformity of the project cost with the planned cost. This is while the Kalman filter stated the primary warning to predict the project's completion time in the seventh month, and this model gave no warning regarding the planned cost. Comparing these results with the periodical reports of the E dam construction project designates the excellent performance of hybrid models, particularly the LSSVM-PSO model.

 

References:

1. Gowan, J. A., Mathieu, R. G., & Hey, M. B. 2006. Earned value management in a data warehouse project. Information management & computer security, 14(1), 37-50.
2. Attalla, M., & Hegazy, T. (2003). Predicting cost deviation in reconstruction projects: Artificial neural networks versus regression. Journal of construction engineering and management, 129(4), 405-411.
3. Kim, G. H., An, S. H., & Kang, K. I. 2004. Comparison of construction cost estimating models based on regression analysis, neural networks, and case-based reasoning. Building and environment, 39(10), 1235-1242.
4. Wilmot, C. G., & Mei, B. 2005. Neural network modeling of highway construction costs. Journal of construction engineering and management, 131(7), 765-771.
5. Kim, B. C., & Reinschmidt, K. F. 2010. Probabilistic forecasting of project duration using Kalman filter and the earned value method. Journal of Construction Engineering and Management, 136(8), 834-843.
6. Sonmez R. 2011. Range estimation of construction costs using neural networks with bootstrap prediction intervals. Expert Syst Appl.; 38(8):9913–7.
7. Wang Y-R, Yu C-Y, Chan H-H. 2012. Predicting construction cost and schedule success using artificial neural networks ensemble and support vector machines classification models. Int J Proj Manag.30(4):470–8.
8. Cheng M-Y, Hoang N-D, Roy AF V, Wu Y-W. 2012. A novel time-depended evolutionary fuzzy SVM inference model for estimating construction project at completion. Eng Appl Artif Intell. 25(4):744–52.
9. Wauters M, Vanhoucke M. 2014. Support vector machine regression for project control forecasting. Autom Constr.47:92–106.
10. Kim B-C. 2015. Integrating risk assessment and actual performance for probabilistic project cost forecasting: a second moment Bayesian model.IEEE Trans Eng Manag. 62(2):158–70.
11. Mortaji STH, Noorossana R, Bagherpour M. 2015. Project completion time and cost prediction using change point analysis. J Manag Eng. 31(5):4014086.
12. Akhbari M. 2018. Project time and cost forecasting using monte carlo simulation and artificial neural networks. Int J Ind Eng Prod Res. 29(2):231–9.
13. Jiang Q. 2019. Estimation of construction project building cost by back-propagation neural network. J Eng Des Technol.
14. Najafi S, Moosavirad SH, Ariafar S. 2019. Predicting the project time and costs using EVM based on gray numbers. Eng Constr Archit Manag.
15. Soltan S, Ashrafi M. 2020. Predicting project duration and cost, and selecting the best action plan using statistical methods for earned value management. J Proj Manag. 5(3):157–66.
16. Khalaf TZ, Çağlar H, Çağlar A, Hanoon AN. 2020. Particle swarm optimization based approach for estimation of costs and duration of construction projects. Civ Eng J.6(2):384–401.
17. Asadabadi MR, Zwikael O. 2021. Integrating risk into estimations of project activities’ time and cost: A stratified approach. Eur J Oper Res. 291(2):482–90.
18. Bakhshi R, Moradinia SF, Jani R, Poor RV. 2022. Presenting a Hybrid Scheme of Machine Learning Combined with Metaheuristic Optimizers for Predicting Final Cost and Time of Project. KSCE J Civ Eng.1–16.
19. Anemangely M, Ramezanzadeh A, Tokhmechi B, Molaghab A, Mohammadian A. 2018. Drilling rate prediction from petrophysical logs and mud logging data using an optimized multilayer perceptron neural network. J Geophys Eng.15(4):1146–59.
20. Mehrad M, Bajolvand M, Ramezanzadeh A, Neycharan JG. 2020. Developing a new rigorous drilling rate prediction model using a machine learning technique. J Pet Sci Eng.192:107338.
21. Sabah M, Mehrad M, Ashrafi SB, Wood DA, Fathi S. 2021. Hybrid machine learning algorithms to enhance lost-circulation prediction and management in the Marun oil field. J Pet Sci Eng.198:108125.
22. Kennedy J, Eberhart R. 1995. Particle swarm optimization. In: Proceedings of ICNN’95-international conference on neural networks. IEEE. p. 1942–8.
23. Czarnigowska A. 2008. Earned value method as a tool for project control. Bud i Archit.3(2):15–32.
24. Lipke W. 2014. Introduction to earned schedule. PM World J.3(11):8–9.
25. Kim B-C, Reinschmidt KF. 2011. Combination of project cost forecasts in earned value management. J Constr Eng Manag. 137(11):958–66.
26. Wang, H. and Hu, D., 2005. October. Comparison of SVM and LS-SVM for regression. In 2005 International conference on neural networks and brain (Vol. 1, pp. 279-283). IEEE.
27. Welch G, Bishop G. 1995. An introduction to the Kalman filter.
28. Suykens JAK, Vandewalle J. 1999. Least squares support vector machine classifiers. Neural Process Lett. 9(3):293–300.
29. Vapnik V. 2013. The nature of statistical learning theory. Springer science & business media.
30. Duan K, Keerthi SS, Poo AN. 2003. Evaluation of simple performance measures for tuning SVM hyperparameters. Neurocomputing. 51: 41–59.
31. Couceiro, M., Ghamisi, P., Couceiro, M. and Ghamisi, P., 2016. Particle swarm optimization. Fractional order darwinian particle swarm optimization: Applications and evaluation of an evolutionary algorithm, pp.1-10.
32. Coello CAC, Lamont GB, Van Veldhuizen DA. 2007. Evolutionary algorithms for solving multi-objective problems. Vol. 5. Springer.
33. Clerc M. 2010. Particle swarm optimization. Vol. 93. John Wiley & Sons.