A New Extensible Feature Matching Model for Corrosion Defects Based on Consecutive In-Line Inspections and Data Clustering

Corrosion is considered a leading cause of failure in pipeline systems. Therefore, frequent inspection and monitoring are essential to maintain structural integrity. Feature matching based on in-line inspections (ILIs) aligns corrosion data across inspections, facilitating the observation of corrosi...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohamad Shatnawi, Péter Földesi
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/6/2943
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850090033591091200
author Mohamad Shatnawi
Péter Földesi
author_facet Mohamad Shatnawi
Péter Földesi
author_sort Mohamad Shatnawi
collection DOAJ
description Corrosion is considered a leading cause of failure in pipeline systems. Therefore, frequent inspection and monitoring are essential to maintain structural integrity. Feature matching based on in-line inspections (ILIs) aligns corrosion data across inspections, facilitating the observation of corrosion progression. Nonetheless, the uncertainties of inspection tools and corrosion processes present in ILI data influence feature matching accuracy. This study proposes a new extensible feature matching model based on consecutive ILIs and data clustering. By dynamically segmenting the data into spatially localized clusters, this framework enables feature matching of isolated pairs and merging defects, as well as facilitating more precise localized transformations. Moreover, a new clustering technique—directional epsilon neighborhood clustering (DENC)—is proposed. DENC utilizes spatial graph structures and directional proximity thresholds to address the directional variability in ILI data while effectively identifying outliers. The model is evaluated on six pipeline segments with varying ILI data complexities, achieving high recall and precision of 91.5% and 98.0%, respectively. In comparison to exclusively point matching models, this work demonstrates significant improvements in terms of accuracy, stability, and managing the spatial variability and interactions of adjacent defects. These advancements establish a new framework for automated feature matching and contribute to enhanced pipeline integrity management.
format Article
id doaj-art-a535867701c847d2b3dfdc430056d36a
institution DOAJ
issn 2076-3417
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-a535867701c847d2b3dfdc430056d36a2025-08-20T02:42:38ZengMDPI AGApplied Sciences2076-34172025-03-01156294310.3390/app15062943A New Extensible Feature Matching Model for Corrosion Defects Based on Consecutive In-Line Inspections and Data ClusteringMohamad Shatnawi0Péter Földesi1Doctoral School of Multidisciplinary Engineering Sciences, Széchenyi István University, 9026 Győr, HungaryDepartment of Logistics, Széchenyi István University, 9026 Győr, HungaryCorrosion is considered a leading cause of failure in pipeline systems. Therefore, frequent inspection and monitoring are essential to maintain structural integrity. Feature matching based on in-line inspections (ILIs) aligns corrosion data across inspections, facilitating the observation of corrosion progression. Nonetheless, the uncertainties of inspection tools and corrosion processes present in ILI data influence feature matching accuracy. This study proposes a new extensible feature matching model based on consecutive ILIs and data clustering. By dynamically segmenting the data into spatially localized clusters, this framework enables feature matching of isolated pairs and merging defects, as well as facilitating more precise localized transformations. Moreover, a new clustering technique—directional epsilon neighborhood clustering (DENC)—is proposed. DENC utilizes spatial graph structures and directional proximity thresholds to address the directional variability in ILI data while effectively identifying outliers. The model is evaluated on six pipeline segments with varying ILI data complexities, achieving high recall and precision of 91.5% and 98.0%, respectively. In comparison to exclusively point matching models, this work demonstrates significant improvements in terms of accuracy, stability, and managing the spatial variability and interactions of adjacent defects. These advancements establish a new framework for automated feature matching and contribute to enhanced pipeline integrity management.https://www.mdpi.com/2076-3417/15/6/2943pipeline integritycorrosion managementdirectional epsilon neighborhood clustering (DENC)affine transformationlinear optimizationlinear programming
spellingShingle Mohamad Shatnawi
Péter Földesi
A New Extensible Feature Matching Model for Corrosion Defects Based on Consecutive In-Line Inspections and Data Clustering
Applied Sciences
pipeline integrity
corrosion management
directional epsilon neighborhood clustering (DENC)
affine transformation
linear optimization
linear programming
title A New Extensible Feature Matching Model for Corrosion Defects Based on Consecutive In-Line Inspections and Data Clustering
title_full A New Extensible Feature Matching Model for Corrosion Defects Based on Consecutive In-Line Inspections and Data Clustering
title_fullStr A New Extensible Feature Matching Model for Corrosion Defects Based on Consecutive In-Line Inspections and Data Clustering
title_full_unstemmed A New Extensible Feature Matching Model for Corrosion Defects Based on Consecutive In-Line Inspections and Data Clustering
title_short A New Extensible Feature Matching Model for Corrosion Defects Based on Consecutive In-Line Inspections and Data Clustering
title_sort new extensible feature matching model for corrosion defects based on consecutive in line inspections and data clustering
topic pipeline integrity
corrosion management
directional epsilon neighborhood clustering (DENC)
affine transformation
linear optimization
linear programming
url https://www.mdpi.com/2076-3417/15/6/2943
work_keys_str_mv AT mohamadshatnawi anewextensiblefeaturematchingmodelforcorrosiondefectsbasedonconsecutiveinlineinspectionsanddataclustering
AT peterfoldesi anewextensiblefeaturematchingmodelforcorrosiondefectsbasedonconsecutiveinlineinspectionsanddataclustering
AT mohamadshatnawi newextensiblefeaturematchingmodelforcorrosiondefectsbasedonconsecutiveinlineinspectionsanddataclustering
AT peterfoldesi newextensiblefeaturematchingmodelforcorrosiondefectsbasedonconsecutiveinlineinspectionsanddataclustering