Defect Severity Identification for a Catenary System Based on Deep Semantic Learning
A variety of Chinese textual operational text data has been recorded during the operation and maintenance of the high-speed railway catenary system. Such defect text records can facilitate defect detection and defect severity analysis if mined efficiently and accurately. Therefore, in this context,...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-12-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/24/9922 |
_version_ | 1797455317108260864 |
---|---|
author | Jian Wang Shibin Gao Long Yu Dongkai Zhang Lei Kou |
author_facet | Jian Wang Shibin Gao Long Yu Dongkai Zhang Lei Kou |
author_sort | Jian Wang |
collection | DOAJ |
description | A variety of Chinese textual operational text data has been recorded during the operation and maintenance of the high-speed railway catenary system. Such defect text records can facilitate defect detection and defect severity analysis if mined efficiently and accurately. Therefore, in this context, this paper focuses on a specific problem in defect text mining, which is to efficiently extract defect-relevant information from catenary defect text records and automatically identify catenary defect severity. The specific task is transformed into a machine learning problem for defect text classification. First, we summarize the characteristics of catenary defect texts and construct a text dataset. Second, we use BERT to learn defect texts and generate word embedding vectors with contextual features, fed into the classification model. Third, we developed a deep text categorization network (DTCN) to distinguish the catenary defect level, considering the contextualized semantic features. Finally, the effectiveness of our proposed method (BERT-DTCN) is validated using a catenary defect textual dataset collected from 2016 to 2018 in the China Railway Administration in Chengdu, Lanzhou, and Hengshui. Moreover, BERT-DTCN outperforms several competitive methods in terms of accuracy, precision, recall, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>F</mi><mn>1</mn></msub></semantics></math></inline-formula>-score value. |
first_indexed | 2024-03-09T15:52:41Z |
format | Article |
id | doaj.art-88a024a628184bbf83848aee5e825b2c |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T15:52:41Z |
publishDate | 2022-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-88a024a628184bbf83848aee5e825b2c2023-11-24T17:57:32ZengMDPI AGSensors1424-82202022-12-012224992210.3390/s22249922Defect Severity Identification for a Catenary System Based on Deep Semantic LearningJian Wang0Shibin Gao1Long Yu2Dongkai Zhang3Lei Kou4School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, ChinaSchool of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, ChinaSchool of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, ChinaCollege of Information Engineering, Henan University of Science and Technology, Luoyang 471023, ChinaInstitute of Oceanographic Instrumentation, Qilu University of Technology (Shandong Academy of Sciences), Qingdao 266075, ChinaA variety of Chinese textual operational text data has been recorded during the operation and maintenance of the high-speed railway catenary system. Such defect text records can facilitate defect detection and defect severity analysis if mined efficiently and accurately. Therefore, in this context, this paper focuses on a specific problem in defect text mining, which is to efficiently extract defect-relevant information from catenary defect text records and automatically identify catenary defect severity. The specific task is transformed into a machine learning problem for defect text classification. First, we summarize the characteristics of catenary defect texts and construct a text dataset. Second, we use BERT to learn defect texts and generate word embedding vectors with contextual features, fed into the classification model. Third, we developed a deep text categorization network (DTCN) to distinguish the catenary defect level, considering the contextualized semantic features. Finally, the effectiveness of our proposed method (BERT-DTCN) is validated using a catenary defect textual dataset collected from 2016 to 2018 in the China Railway Administration in Chengdu, Lanzhou, and Hengshui. Moreover, BERT-DTCN outperforms several competitive methods in terms of accuracy, precision, recall, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>F</mi><mn>1</mn></msub></semantics></math></inline-formula>-score value.https://www.mdpi.com/1424-8220/22/24/9922catenary systemdeep learningtext miningpre-trained language modeldefect severity classification |
spellingShingle | Jian Wang Shibin Gao Long Yu Dongkai Zhang Lei Kou Defect Severity Identification for a Catenary System Based on Deep Semantic Learning Sensors catenary system deep learning text mining pre-trained language model defect severity classification |
title | Defect Severity Identification for a Catenary System Based on Deep Semantic Learning |
title_full | Defect Severity Identification for a Catenary System Based on Deep Semantic Learning |
title_fullStr | Defect Severity Identification for a Catenary System Based on Deep Semantic Learning |
title_full_unstemmed | Defect Severity Identification for a Catenary System Based on Deep Semantic Learning |
title_short | Defect Severity Identification for a Catenary System Based on Deep Semantic Learning |
title_sort | defect severity identification for a catenary system based on deep semantic learning |
topic | catenary system deep learning text mining pre-trained language model defect severity classification |
url | https://www.mdpi.com/1424-8220/22/24/9922 |
work_keys_str_mv | AT jianwang defectseverityidentificationforacatenarysystembasedondeepsemanticlearning AT shibingao defectseverityidentificationforacatenarysystembasedondeepsemanticlearning AT longyu defectseverityidentificationforacatenarysystembasedondeepsemanticlearning AT dongkaizhang defectseverityidentificationforacatenarysystembasedondeepsemanticlearning AT leikou defectseverityidentificationforacatenarysystembasedondeepsemanticlearning |