A targeted one dimensional fully convolutional autoencoder network for intelligent compression of magnetic flux leakage data

Abstract In response to the issue of massive data volume generated by magnetic flux leakage (MFL) non-destructive testing in oil and gas pipelines, an intelligent data compression method based on a targeted one-dimensional fully convolutional autoencoder network is proposed. Firstly, a data preproce...

Full description

Saved in:
Bibliographic Details
Main Authors: Wenbo Xuan, Pengchao Chen, Rui Li, Fuxiang Wang, Kuan Fu, Zhitao Wen
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-96282-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850265489738039296
author Wenbo Xuan
Pengchao Chen
Rui Li
Fuxiang Wang
Kuan Fu
Zhitao Wen
author_facet Wenbo Xuan
Pengchao Chen
Rui Li
Fuxiang Wang
Kuan Fu
Zhitao Wen
author_sort Wenbo Xuan
collection DOAJ
description Abstract In response to the issue of massive data volume generated by magnetic flux leakage (MFL) non-destructive testing in oil and gas pipelines, an intelligent data compression method based on a targeted one-dimensional fully convolutional autoencoder network is proposed. Firstly, a data preprocessing module is designed to generate high-quality data required for subsequent processing, taking into account the characteristics of MFL data. Secondly, a data block classification algorithm is developed to calculate peak values for segmented differential data, and based on a predefined targeted threshold, distinguish different types of MFL data. Subsequently, based on the distinct data types, targeted one-dimensional fully convolutional autoencoder models are constructed to effectively achieve dimensionality reduction compression and reconstruction of the MFL data. Through practical experimental analysis, the reconstruction error such as MAE is reduced by about 27.7% and the compression ratio is improved by about 14% compared with traditional methods such as PCA. In addition, compared with ID-AE, the proposed 1D-FCAE reduces 206.8 k, 1.58G, and 80 s in parameters, memory usage, and training time, respectively, and reduces compression and decompression time by 60 ms and 69 ms, respectively, validating that it is easy to be applied in industrial environments with limited resources.
format Article
id doaj-art-843300ddd0b346febc0e8d2382397ead
institution OA Journals
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-843300ddd0b346febc0e8d2382397ead2025-08-20T01:54:25ZengNature PortfolioScientific Reports2045-23222025-04-0115111310.1038/s41598-025-96282-2A targeted one dimensional fully convolutional autoencoder network for intelligent compression of magnetic flux leakage dataWenbo Xuan0Pengchao Chen1Rui Li2Fuxiang Wang3Kuan Fu4Zhitao Wen5PipeChina Institute of Science and TechnologyPipeChina Institute of Science and TechnologyPipeChina Institute of Science and TechnologyPipeChina Institute of Science and TechnologyPipeChina Institute of Science and TechnologyNortheastern UniversityAbstract In response to the issue of massive data volume generated by magnetic flux leakage (MFL) non-destructive testing in oil and gas pipelines, an intelligent data compression method based on a targeted one-dimensional fully convolutional autoencoder network is proposed. Firstly, a data preprocessing module is designed to generate high-quality data required for subsequent processing, taking into account the characteristics of MFL data. Secondly, a data block classification algorithm is developed to calculate peak values for segmented differential data, and based on a predefined targeted threshold, distinguish different types of MFL data. Subsequently, based on the distinct data types, targeted one-dimensional fully convolutional autoencoder models are constructed to effectively achieve dimensionality reduction compression and reconstruction of the MFL data. Through practical experimental analysis, the reconstruction error such as MAE is reduced by about 27.7% and the compression ratio is improved by about 14% compared with traditional methods such as PCA. In addition, compared with ID-AE, the proposed 1D-FCAE reduces 206.8 k, 1.58G, and 80 s in parameters, memory usage, and training time, respectively, and reduces compression and decompression time by 60 ms and 69 ms, respectively, validating that it is easy to be applied in industrial environments with limited resources.https://doi.org/10.1038/s41598-025-96282-2
spellingShingle Wenbo Xuan
Pengchao Chen
Rui Li
Fuxiang Wang
Kuan Fu
Zhitao Wen
A targeted one dimensional fully convolutional autoencoder network for intelligent compression of magnetic flux leakage data
Scientific Reports
title A targeted one dimensional fully convolutional autoencoder network for intelligent compression of magnetic flux leakage data
title_full A targeted one dimensional fully convolutional autoencoder network for intelligent compression of magnetic flux leakage data
title_fullStr A targeted one dimensional fully convolutional autoencoder network for intelligent compression of magnetic flux leakage data
title_full_unstemmed A targeted one dimensional fully convolutional autoencoder network for intelligent compression of magnetic flux leakage data
title_short A targeted one dimensional fully convolutional autoencoder network for intelligent compression of magnetic flux leakage data
title_sort targeted one dimensional fully convolutional autoencoder network for intelligent compression of magnetic flux leakage data
url https://doi.org/10.1038/s41598-025-96282-2
work_keys_str_mv AT wenboxuan atargetedonedimensionalfullyconvolutionalautoencodernetworkforintelligentcompressionofmagneticfluxleakagedata
AT pengchaochen atargetedonedimensionalfullyconvolutionalautoencodernetworkforintelligentcompressionofmagneticfluxleakagedata
AT ruili atargetedonedimensionalfullyconvolutionalautoencodernetworkforintelligentcompressionofmagneticfluxleakagedata
AT fuxiangwang atargetedonedimensionalfullyconvolutionalautoencodernetworkforintelligentcompressionofmagneticfluxleakagedata
AT kuanfu atargetedonedimensionalfullyconvolutionalautoencodernetworkforintelligentcompressionofmagneticfluxleakagedata
AT zhitaowen atargetedonedimensionalfullyconvolutionalautoencodernetworkforintelligentcompressionofmagneticfluxleakagedata
AT wenboxuan targetedonedimensionalfullyconvolutionalautoencodernetworkforintelligentcompressionofmagneticfluxleakagedata
AT pengchaochen targetedonedimensionalfullyconvolutionalautoencodernetworkforintelligentcompressionofmagneticfluxleakagedata
AT ruili targetedonedimensionalfullyconvolutionalautoencodernetworkforintelligentcompressionofmagneticfluxleakagedata
AT fuxiangwang targetedonedimensionalfullyconvolutionalautoencodernetworkforintelligentcompressionofmagneticfluxleakagedata
AT kuanfu targetedonedimensionalfullyconvolutionalautoencodernetworkforintelligentcompressionofmagneticfluxleakagedata
AT zhitaowen targetedonedimensionalfullyconvolutionalautoencodernetworkforintelligentcompressionofmagneticfluxleakagedata