A Machine Learning Approach for Big Data in Oil and Gas Pipelines

Mohamed, Abduljalil; Hamdi, Mohamed Salah; Tahar, Sofiène

doi:10.1109/ficloud.2015.54

Cited by 32 publications

(15 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experienced pipeline operators utilize Magnetic Flux Leakage (MFL) sensors to probe oil and gas pipelines for the purpose of localizing and sizing different defect types [4]. A large number of sensors is usually used to cover the targeted pipelines.…”

Section: Literature Reviewmentioning

confidence: 99%

“…A large number of sensors is usually used to cover the targeted pipelines. The sensors are equally distributed around the circumference of the pipeline; and every three millimeters the sensors measure MFL signals [4]. Thus, the collected raw data is so big that it makes the pipeline probing process difficult, exhausting and error-prone.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Thus, the collected raw data is so big that it makes the pipeline probing process difficult, exhausting and error-prone. Machine learning approaches such as neural networks have made it possible to effectively manage the complexity pertaining to big data and learn their intrinsic properties [4]. Discriminant features, which characterize different defect depth patterns, are first obtained from the raw data.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Neural networks are then trained using these features. The Levenberg-Marquardt back-propagation learning algorithm is adopted in the training process, during which the weight and bias parameters of the networks are tuned to optimize their performances [4].…”

Section: Literature Reviewmentioning

confidence: 99%

See 3 more Smart Citations

Big Data Approach Application for Steel Pipelines in the Conditions of Corrosion Fatigue

Skrynkovskyy¹,

Law²,

Yuzevych³

et al. 2018

JES

View full text Add to dashboard Cite

This paper presents results of the use of Big Data approach and neural network for the pipelines diagnosis problem. In this case the pipeline is in the conditions of crack growth of corrosion fatigue and exposed to hydrogen. It is proposed to use graphene protective coatings. The mathematical model for estimating the changes in the effective surface energy of WPL during plastic deformation, electrochemical overstrain, polarization potential and current density of the metal dissolution reaction at the top of the crack on the pipeline surface during its mechanical loading in an aqueous electrolyte solution is given. The dissolution of the metal is considered on the juvenile surface, taking into account the anode and cathode regions based on the approaches of surface physics and electrochemistry. An element of a mathematical model is a quality functional, taking into account information flows and a sensitivity coefficient. Functional quality is used to specify the feedback between the investment project methodology and risk estimates, as well as to optimize the information flows of enterprises and improve the system of protection of metallic underground pipelines that operate under conditions of corrosion fatigue. The purpose of this project is to improve the relevant regulatory and technical documents as well as software.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

See 2 more Smart Citations

Big Data Approach Application for Steel Pipelines in the Conditions of Corrosion Fatigue

Skrynkovskyy¹,

Law²,

Yuzevych³

et al. 2018

JES

View full text Add to dashboard Cite

show abstract

“…The sensors are placed at an equal distance along the bounds of the pipe and measure MFL signals at each 3 mm. As a result, the volume of collected data becomes extremely large [31,32].…”

Section: A Brief Review Of the Oil And Gas Industrymentioning

confidence: 99%

Big Data Strategy for the Oil and Gas Industry: General Directions

Alıguliyev¹,

İmamverdiyev²

2017

JPIT

View full text Add to dashboard Cite

Machine Learning an Intelligent Approach in Process Industries: A Perspective and Overview

Khan

Taqvi

2022

ChemBioEng Reviews

View full text Add to dashboard Cite

The field of machine learning has proven to be a powerful approach in smart manufacturing and processing in the chemical and process industries. This review provides a systematic overview of current state of artificial intelligence and machine learning and their applications in textile, nuclear power plant, fertilizer, water treatment, and oil and gas industries. Moreover, this study reveals the current dominant machine learning methods, pre and post processing of models, increased utilization of machine learning in terms of fault detection, prediction, optimization, quality control, and maintenance in these sectors. In addition, this review gives the insight into the actual benefits and impact of each method, and complications in their extensive deployment. Finally in the current impressive state, challenges, future development in terms of algorithm and infrastructure aspects are highlighted.

show abstract

A Machine Learning Approach for Big Data in Oil and Gas Pipelines

Cited by 32 publications

References 17 publications

Big Data Approach Application for Steel Pipelines in the Conditions of Corrosion Fatigue

Big Data Approach Application for Steel Pipelines in the Conditions of Corrosion Fatigue

Big Data Strategy for the Oil and Gas Industry: General Directions

Machine Learning an Intelligent Approach in Process Industries: A Perspective and Overview

Contact Info

Product

Resources

About