Impact Analysis of Inline Inspection Accuracy on Pipeline Integrity Planning

Xie, Mingjiang; Sutherland, Jeff; Fang, Bin; Gu, Bill; Tian, Zhigang

doi:10.1115/1.4047270

Cited by 3 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, the risk execution based on the recorded data may not be sufficient to assess the risk without conducting a direct inspection such as ILI is also critical. The author of [23] describes the benefit of ILI in significantly impacting the assessment of the pipeline integrity management program. The works model that ILI is a promising tool to study the severity level of pipelines and detect possible threats corresponding to unresolved pipeline issues.…”

Section: Literature Review and Problem Statementmentioning

confidence: 99%

Risk analysis of Ex-spool 16” mol: an insight of machine learning and experimental result

Aditiyawarman

Soedarsono

Kaban

et al. 2022

EEJET

View full text Add to dashboard Cite

The paper reports the development of a Risk-Based Inspection (RBI)-Machine Learning perspective. The Optical Emission Spectrometry (OES), Tensile and Hardness Test, Scanning Electron Microscope (SEM), Energy Dispersive X-Ray Spectroscopy (EDS), Sulfate Reducing Bacteria Check, and X-Ray Diffraction (XRD) was used to analyze the root cause of the pipeline’s failure. Corrosion attack shows at the cross-section microstructure based on SEM results. Carbon, Manganese, Phosphorous, and sulfur’s chemical composition is dramatically lower than the standard API 5L Grade X42. Siderite and hematite dominate the composition of the corroded area as a result of CO2 dissolving in water. In contrast, hematite is generated due to the pipe and outdoor atmosphere reaction. Severe local wall thinning of the sand abrasion causes the degradation of the material’s mechanical properties and increases the corrosion rate. This result amplifies by the development of Machine Learning (ML) of Pearson Multicollinear Matrix and Supervised ML (Random Forest, Support Vector Machine, and Linear Regression) to estimate the corrosion degradation of the material. The source of datasets provided by ILI inspection includes the calculated PoF Remaining Useful Life (RuL) as input data, while Probability of Failure (PoF) prediction serves as output data. The Random Forest shows superior predictions of 92.18 %, with the lowest validation loss of 0.0316. The modeling result confirms the experimental outcome. This work demonstrates the implementation strategy to reduce the analysis time, minimize human bias, and serve as a reliable reference tool and guideline to maintain the integrity of the subsea pipelines.

show abstract

Section: Literature Review and Problem Statementmentioning

confidence: 99%

Risk analysis of Ex-spool 16” mol: an insight of machine learning and experimental result

Aditiyawarman

Soedarsono

Kaban

et al. 2022

EEJET

View full text Add to dashboard Cite

show abstract

“…Inline inspection (ILI) tools are widely used to detect and inspect the location and size of pipeline corrosion defects [7][8][9][10]. The accuracy of the ILI tool has a great impact on the prediction results.…”

Section: Introductionmentioning

confidence: 99%

A Prognostics Method Based on Back Propagation Neural Network for Corroded Pipelines

Xie

Zhao

et al. 2021

Micromachines

Self Cite

View full text Add to dashboard Cite

A method that employs the back propagation (BP) neural network is used to predict the growth of corrosion defect in pipelines. This method considers more diversified parameters that affect the pipeline’s corrosion rate, including pipe parameters, service life, corrosion type, corrosion location, corrosion direction, and corrosion amount in a three-dimensional direction. The initial corrosion time is also considered, and, on this basis, the uncertainties of the initial corrosion time and the corrosion size are added to the BP neural network model. In this paper, three kinds of pipeline corrosion growth models are constructed: the traditional corrosion model, the corrosion model considering the uncertainties of initial corrosion time and corrosion depth, and corrosion model also considering the uncertainties of corrosion size (length, width, depth). The rationality and effectiveness of the proposed prediction models are verified by three case studies: the uniform model, the exponential model, and the gamma process model. The proposed models can be widely used in the prediction and management of pipeline corrosion.

show abstract

Maintenance strategy optimization of pipeline system with multi-stage corrosion defects based on heuristically genetic algorithm

Xie

Zhao

Pei

2023

Process Safety and Environmental Protection

View full text Add to dashboard Cite

Impact Analysis of Inline Inspection Accuracy on Pipeline Integrity Planning

Cited by 3 publications

References 9 publications

Risk analysis of Ex-spool 16” mol: an insight of machine learning and experimental result

Risk analysis of Ex-spool 16” mol: an insight of machine learning and experimental result

A Prognostics Method Based on Back Propagation Neural Network for Corroded Pipelines

Maintenance strategy optimization of pipeline system with multi-stage corrosion defects based on heuristically genetic algorithm

Contact Info

Product

Resources

About