مهندسی منابع آب (Jul 2024)

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

  • Reza Bakhshi,
  • sina fard moradi nia,
  • Rasool Jani,
  • Ramin Vafaei Poor

DOI
https://doi.org/10.30495/wej.2024.31317.2374
Journal volume & issue
Vol. 17, no. 61
pp. 65 – 85

Abstract

Read online

AbstractIntroduction: 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.

Keywords