Neuro-fuzzy system based model for prediction of project performance in downstream sector of petroleum industry in Iran

Abstract

Purpose

Planning phase of a project results to series of crucial decisions which determine the path to objectives achievement. At the same time, in this phase, project encounters the highest level of uncertainty in comparison of all phases of project lifecycle. This paper aims to support early decisions of project based on the progress forecasting.

Design/methodology/approach

The scope of study is limited to downstream projects of petroleum industry in Iran, and the proposed model is trained and tested based on 75 Iranian completed petroleum projects. First, types of progress curve functions are investigated, and various types are studied and the most appropriate ones are selected through curve fitting. In the next step, using questionnaire, dependent and independent variables are recognized. Finally, using historical data and s-curve generator functions, a fuzzy inference system (ANFIS) based model have been developed to support early phases decision-making processes.

Findings

Based on the analysis of received questionnaires, six functional criteria in two groups as dependent variables and 25 independent variables, in two groups and four clusters are determined and categorized. Eventually, performance prediction model of a project has been developed by using Adaptive Nero Fuzzy Inference System.

Originality/value

The main contribution of this study to construction management knowledge is categorizing two groups of variables, which first one defines the project dynamic and the other calculates the key effects on previous one. Also, this investigation improves the current knowledge by analyzing the project system from the dynamic behavior perspective and modeling the defined variables using ANFIS tools.

Citation

Faraji, A. (2021), "Neuro-fuzzy system based model for prediction of project performance in downstream sector of petroleum industry in Iran", Journal of Engineering, Design and Technology, Vol. 19 No. 6, pp. 1268-1290. https://doi.org/10.1108/JEDT-06-2020-0241