Artificial neural networks models for predicting performance measurement of oil projects

被引：0
作者：
Jasim N.A. [1 ]
Ibrahim A.A. [2 ]
Hatem W.A. [3 ]
机构：
[1] College of Engineering, Department of Civil Engineering, University of Diyala, Baqubah
[2] College of Engineering Department of Civil Engineering, University of Tikrit, Tikrit
[3] Middle Technical University, Baghdad
来源：
Asian Journal of Civil Engineering | 2023年 / 24卷 / 8期
关键词：
Artificial neural network (ANN); Cost Performance Index (CPI); Earned value (EV); Oil Projects; Predicting; Schedule Performance Index (SPI); To-Complete Cost Performance Indicator (TCPI);
D O I：
10.1007/s42107-023-00737-8
中图分类号：
学科分类号：
摘要：
Currently, the oil and gas industry is one of the most significant world sectors, especially in the middle east region. However, sometimes the success of projects in the industry is at stake due to various factors. Poor ways of measuring performance in oil projects can lead to cost overruns, schedule delays, and changes in the scope of the project. As a result, this paper aims to create Artificial Neural Networks (ANN) Models for Predicting Performance Measurement of Iraqi oil projects to reduce estimation error for cost and time. ANN is utilized to develop three mathematical models for estimating Earned Value (EV) Indexes which are the Schedule Performance Index (SPI), Cost Performance Index (CPI), and To-Complete Cost Performance Indicator (TCPI). The data are based on (83) monthly reports starting on a date (26 Jun 2015) up to (25 August 2022) collected from the Karbala Refinery Project which is one of the huge and modern projects of the Oil Projects Company (SCOP), the Iraqi Ministry of Oil. The results show many important points such as average accuracy (AA%) for the CPI, SPI, and TCPI was 95.194%, 92.195%, and 83.706%, respectively, while the correlation coefficients (R) were 92.4%, 98.4%, and 93.7%. It has been shown that there are relatively few differences between the theoretical and actual results. Therefore, the ANN technique is used in this paper to emanate the prediction models for its more correct earned value indexes. © 2023, The Author(s), under exclusive licence to Springer Nature Switzerland AG.
引用
收藏
页码：3597 / 3612
页数：15
相关论文
共 16 条
[1]  
Alcineide P., Gean S., Luiz M.F.M., Felipe C.A., de Debora G.S., Cost forecasting of public construction projects using multilayer perceptron artificial neural networks: a case study, Ingenieria e Investigacion, 41, 3, pp. 1-11, (2021)
[2]  
AlNoaimi F.A., Mazzuchi T.A., Risk management application in an oil and gas company for projects, International Journal of Business Ethics and Governance, (2021)
[3]  
Fanaei S.-S., Performance Measurement, Forecasting and Optimization Models for Construction Projects, (2019)
[4]  
Hammoody O., Al-Somaydaii J., Al-Zwainy F., Hayder G., Forecasting and determining of cost performance index of tunnels projects using artificial neural networks, International Journal for Computational Civil and Structural Engineering, 18, 1, pp. 51-60, (2022)
[5]  
Jaber F.K., Jasim N.A., Al-Zwainy F.M.S., Forecasting techniques in construction industry: Earned value indicators and performance models, Scientific Review Engineering and Environmental Sciences, 29, 2, pp. 234-243, (2020)
[6]  
Jasim N.A., Maruf S.M., Aljumaily H.S.M.M.F., Al-Zwain S., Predicting index to complete schedule performance indicator in highway projects using artificial neural network model, Archives of Civil Engineering, (2020)
[7]  
Kassem M.A., Risk management assessment in oil and gas construction projects using structural equation modeling (PLS-SEM), Gases, 2, 2, pp. 33-60, (2022)
[8]  
Kaveh A., Iranmanesh A., Comparative study of backpropagation and improved counterpropagation neural nets in structural analysis and optimization, International Journal of Space Structures, 13, 4, pp. 177-185, (1998)
[9]  
Kaveh A., Khalegi A., Prediction of strength for concrete specimens using Artificial neural networks, pp. 165-171, (1998)
[10]  
Kaveh A., Khavaninzadeh N., Efficient training of two ANNs using four meta-heuristic algorithms for predicting the FRP strength, Structures, 52, 256, (2023)
12