An incremental learning framework for pipeline weld crack damage identification and leakage rate prediction

The weld crack leakage due to stress concentration and external load is a significant safety risk in pressure pipelines. Microstructural variations and dynamic propagation lead to unpredictable changes in leakage rate over time and conditions. To address the above problems, a novel framework called...

Full description

Saved in:
Bibliographic Details
Main Authors: Jing Huang, Zhifen Zhang, Yanlong Yu, Yongjie Li, Shuai Zhang, Rui Qin, Ji Xing, Wei Cheng, Guangrui Wen, Xuefeng Chen
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:Engineering Applications of Computational Fluid Mechanics
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/19942060.2024.2406256
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846136020048805888
author Jing Huang
Zhifen Zhang
Yanlong Yu
Yongjie Li
Shuai Zhang
Rui Qin
Ji Xing
Wei Cheng
Guangrui Wen
Xuefeng Chen
author_facet Jing Huang
Zhifen Zhang
Yanlong Yu
Yongjie Li
Shuai Zhang
Rui Qin
Ji Xing
Wei Cheng
Guangrui Wen
Xuefeng Chen
author_sort Jing Huang
collection DOAJ
description The weld crack leakage due to stress concentration and external load is a significant safety risk in pressure pipelines. Microstructural variations and dynamic propagation lead to unpredictable changes in leakage rate over time and conditions. To address the above problems, a novel framework called OILS-TCN for weld crack pattern recognition and leakage rate prediction is proposed. Firstly, the adaptive threshold optimization algorithm is introduced into the self-organizing incremental neural network to update and increase the crack leakage pattern. Secondly, the depth first search algorithm is combined with the radial basis function neural network to perform online increment labelling of the leakage state. Then, according to the attenuation characteristics of acoustic emission signals, a portable input-attention module is designed to add different weights to the input sequence. Finally, the accurate prediction of leakage rate under different conditions is realized based on the temporal convolutional network. Compared with other advanced methods, the proposed method has obvious advantages in the adaptability and accuracy of pipeline weld crack leakage rate prediction. In addition, the validity and necessity of each part of the framework proposed are discussed based on ablation experiments. The proposed method can predict the leakage rate in real time without modifying the hyperparameters of the model, and can provide a powerful guide for the online monitoring of the leakage AE technology of pressure pipeline in complex systems.
format Article
id doaj-art-5eb8d3a365d74b798d0d5a8655fbd23b
institution Kabale University
issn 1994-2060
1997-003X
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series Engineering Applications of Computational Fluid Mechanics
spelling doaj-art-5eb8d3a365d74b798d0d5a8655fbd23b2024-12-09T09:43:46ZengTaylor & Francis GroupEngineering Applications of Computational Fluid Mechanics1994-20601997-003X2024-12-0118110.1080/19942060.2024.2406256An incremental learning framework for pipeline weld crack damage identification and leakage rate predictionJing Huang0Zhifen Zhang1Yanlong Yu2Yongjie Li3Shuai Zhang4Rui Qin5Ji Xing6Wei Cheng7Guangrui Wen8Xuefeng Chen9The National Key Laboratory of Aerospace Power System and Plasma Technology, Xi’an Jiaotong University, Xi’an, People’s Republic of ChinaThe National Key Laboratory of Aerospace Power System and Plasma Technology, Xi’an Jiaotong University, Xi’an, People’s Republic of ChinaThe National Key Laboratory of Aerospace Power System and Plasma Technology, Xi’an Jiaotong University, Xi’an, People’s Republic of ChinaThe National Key Laboratory of Aerospace Power System and Plasma Technology, Xi’an Jiaotong University, Xi’an, People’s Republic of ChinaThe National Key Laboratory of Aerospace Power System and Plasma Technology, Xi’an Jiaotong University, Xi’an, People’s Republic of ChinaThe National Key Laboratory of Aerospace Power System and Plasma Technology, Xi’an Jiaotong University, Xi’an, People’s Republic of ChinaPeople’s Republic of China Nuclear Power Engineering Co., Ltd., Beijing, People’s Republic of ChinaThe National Key Laboratory of Aerospace Power System and Plasma Technology, Xi’an Jiaotong University, Xi’an, People’s Republic of ChinaThe National Key Laboratory of Aerospace Power System and Plasma Technology, Xi’an Jiaotong University, Xi’an, People’s Republic of ChinaThe National Key Laboratory of Aerospace Power System and Plasma Technology, Xi’an Jiaotong University, Xi’an, People’s Republic of ChinaThe weld crack leakage due to stress concentration and external load is a significant safety risk in pressure pipelines. Microstructural variations and dynamic propagation lead to unpredictable changes in leakage rate over time and conditions. To address the above problems, a novel framework called OILS-TCN for weld crack pattern recognition and leakage rate prediction is proposed. Firstly, the adaptive threshold optimization algorithm is introduced into the self-organizing incremental neural network to update and increase the crack leakage pattern. Secondly, the depth first search algorithm is combined with the radial basis function neural network to perform online increment labelling of the leakage state. Then, according to the attenuation characteristics of acoustic emission signals, a portable input-attention module is designed to add different weights to the input sequence. Finally, the accurate prediction of leakage rate under different conditions is realized based on the temporal convolutional network. Compared with other advanced methods, the proposed method has obvious advantages in the adaptability and accuracy of pipeline weld crack leakage rate prediction. In addition, the validity and necessity of each part of the framework proposed are discussed based on ablation experiments. The proposed method can predict the leakage rate in real time without modifying the hyperparameters of the model, and can provide a powerful guide for the online monitoring of the leakage AE technology of pressure pipeline in complex systems.https://www.tandfonline.com/doi/10.1080/19942060.2024.2406256Leakage ratepipeline weld crackacoustic emissionincremental learningtemporal convolution network
spellingShingle Jing Huang
Zhifen Zhang
Yanlong Yu
Yongjie Li
Shuai Zhang
Rui Qin
Ji Xing
Wei Cheng
Guangrui Wen
Xuefeng Chen
An incremental learning framework for pipeline weld crack damage identification and leakage rate prediction
Engineering Applications of Computational Fluid Mechanics
Leakage rate
pipeline weld crack
acoustic emission
incremental learning
temporal convolution network
title An incremental learning framework for pipeline weld crack damage identification and leakage rate prediction
title_full An incremental learning framework for pipeline weld crack damage identification and leakage rate prediction
title_fullStr An incremental learning framework for pipeline weld crack damage identification and leakage rate prediction
title_full_unstemmed An incremental learning framework for pipeline weld crack damage identification and leakage rate prediction
title_short An incremental learning framework for pipeline weld crack damage identification and leakage rate prediction
title_sort incremental learning framework for pipeline weld crack damage identification and leakage rate prediction
topic Leakage rate
pipeline weld crack
acoustic emission
incremental learning
temporal convolution network
url https://www.tandfonline.com/doi/10.1080/19942060.2024.2406256
work_keys_str_mv AT jinghuang anincrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction
AT zhifenzhang anincrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction
AT yanlongyu anincrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction
AT yongjieli anincrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction
AT shuaizhang anincrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction
AT ruiqin anincrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction
AT jixing anincrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction
AT weicheng anincrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction
AT guangruiwen anincrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction
AT xuefengchen anincrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction
AT jinghuang incrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction
AT zhifenzhang incrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction
AT yanlongyu incrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction
AT yongjieli incrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction
AT shuaizhang incrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction
AT ruiqin incrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction
AT jixing incrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction
AT weicheng incrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction
AT guangruiwen incrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction
AT xuefengchen incrementallearningframeworkforpipelineweldcrackdamageidentificationandleakagerateprediction