Artificial neural network models for predicting condition of offshore oil and gas pipelines

El-Abbasy, Mohammed S.; Senouci, Ahmed; Zayed, Tarek; Mirahadi, Farid; Parvizsedghy, Laya

doi:10.1016/j.autcon.2014.05.003

Cited by 163 publications

(47 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With each HL are PEs or neurons which determines how well a problem can be learned. Too many PEs can lead to the NN memorizing the problem and not generalize well while too few PEs can lead to the NN learning well but lacking the power to learn the pattern well (El-Abbasy et al, 2014). Iteration is needed to generate the optimum numbers of PEs.…”

Section: Electric Light and Power Elementsmentioning

confidence: 99%

Cost estimation for electric light and power elements during building design

Aibinu

Dassanayake

Chan

et al. 2015

Engineering, Construction and Architectural Management

View full text Add to dashboard Cite

Purpose – The study reported in this paper proposed the use of artificial neural networks (ANN) as viable alternative to regression for predicting the cost of building services elements at the early stage of design. The purpose of this paper is to develop, test and validate ANN models for predicting the costs of electrical services components. Design/Methodology/Approach – The research is based on data mining of over 200 building projects in the office of a medium size electrical contractor. Of the over 200 projects examined, 71 usable data were found and used for the ANN modeling. Regression models were also explored using IBM Statistical Package for Social Sciences Statistics Software 21, for the purpose of comparison with the ANN models. Findings – The findings show that the cost forecasting models based on ANN algorithm are more viable alternative to regression models for predicting the costs of light wiring, power wiring and cable pathways. The ANN prediction errors achieved are 6.4, 4.5 and 4.5 per cent for the three models developed whereas the regression models were insignificant. They did not fit any of the known regression distributions. Practical implications – The validated ANN models were converted to a desktop application (user interface) package – “Intelligent Estimator.” The application is important because it can be used by construction professionals to reliably and quickly forecast the costs of power wiring, light wiring and cable pathways using building variables that are readily available or measurable during design stage, i.e. fully enclosed covered area, unenclosed covered area, internal perimeter length and number of floors. Originality/value – Previous studies have concluded that the methods of estimating the budget for building structure and fabric work are inappropriate for use with mechanical and electrical services. Thus, this study is unique because it applied the ANN modeling technique, for the first time, to cost modeling of electrical services components for building using real world data. The analysis shows that ANN is a better alternative to regression models for predicting cost of services elements because the relationship between cost and the cost drivers are non-linear and distribution types are unknown.

show abstract

Section: Electric Light and Power Elementsmentioning

confidence: 99%

Cost estimation for electric light and power elements during building design

Aibinu

Dassanayake

Chan

et al. 2015

Engineering, Construction and Architectural Management

View full text Add to dashboard Cite

show abstract

“…Now, there are more than 60 countries with pipeline networks, with a length of more than 2000 km. The United States has the longest pipeline network in the world followed by Russia [13]. Many researchers had discussed the improvement of oil and gas pipeline networks, specifically in the 1970s.…”

Section: A Oil-gas Pipeline Networkmentioning

confidence: 99%

“…Models for the forecasting and evaluation of the state of oil and gas pipelines were developed using artificial neural network technology (ANN) based on the data provided for three oil and gas pipelines in Qatar. These models were able to predict the state of pipelines by a success rate of 97% [13].…”

Section: A Oil-gas Pipeline Networkmentioning

confidence: 99%

Performance Evaluation of Different Short Path Algorithms to Improve Oil-Gas Pipelines

Almaalei¹,

Razali²

2019

IJACSA

View full text Add to dashboard Cite

The oil-gas pipeline is a complicated and expensive system in terms of construction, control, materials, monitoring, and maintenance which includes economic, social and environmental hazards. As a case study of Iraq, the system of pipelines is above the ground and is liable to disasters that may produce an environmental tragedy as well as the loss of life and money. Hence, this article presents a performance evaluation of different short path algorithms to improve oil-gas pipelines. The chosen algorithms in this paper were Parallel Short Path Algorithm (PSPA), Ant Colony Optimization (ACO) algorithm and Genetic Algorithm (GA). The main performance metric is the cost of the pipelines. Simulation trials were performed using the MATLAB program for the chosen algorithms. The performance comparison showed that the lowest cost of laying oil and gas pipelines was by applying the GA algorithm when the number of wells was set to 50-600. Conversely, the PSPA algorithm showed the best performance in terms of required implementation time for all scenarios. Besides, PSPA appeared to have acceptable performance in terms of the cost of the pipeline when the number of wells was arranged between50-600. Furthermore, PSPA showed the best performance for 700 and 840 wells in terms of the cost of laying the oil and gas pipelines compared to ACO and GA. It should be noted that the ACO algorithm showed medium performance in terms of the cost of laying oil and gas pipelines compared to PSPA and GA.

show abstract

“…Therefore, prediction of their performance due to environmental conditions is of importance. El-Abbasy et al [5] employed ANNs to predict the condition of offshore oil and gas pipelines based on several factors besides corrosion based on historical inspection data collected from three existing offshore oil and gas pipelines in Qatar. They achieved accuracy more than 97% in validating datasets which can be considered as a reasonable performance criterion for their proposed model.…”

Section: Introductionmentioning

confidence: 99%