Domain-Specific Knowledge Graph for Quality Engineering of Continuous Casting: Joint Extraction-Based Construction and Adversarial Training Enhanced Alignment

The intelligent development of continuous casting quality engineering is an essential step for the efficient production of high-quality billets. However, there are many quality defects that require strong expertise for handling. In order to reduce reliance on expert experience and improve the intell...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaojun Wu, Yue She, Xinyi Wang, Hao Lu, Qi Gao
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/10/5674
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849711095271391232
author Xiaojun Wu
Yue She
Xinyi Wang
Hao Lu
Qi Gao
author_facet Xiaojun Wu
Yue She
Xinyi Wang
Hao Lu
Qi Gao
author_sort Xiaojun Wu
collection DOAJ
description The intelligent development of continuous casting quality engineering is an essential step for the efficient production of high-quality billets. However, there are many quality defects that require strong expertise for handling. In order to reduce reliance on expert experience and improve the intelligent management level of billet quality knowledge, we focus on constructing a Domain-Specific Knowledge Graph (DSKG) for the quality engineering of continuous casting. To achieve joint extraction of billet quality defects entity and relation, we propose a Self-Attention Partition and Recombination Model (SAPRM). SAPRM divides domain-specific sentences into three parts: entity-related, relation-related, and shared features, which are specifically for Named Entity Recognition (NER) and Relation Extraction (RE) tasks. Furthermore, for issues of entity ambiguity and repetition in triples, we propose a semi-supervised incremental learning method for knowledge alignment, where we leverage adversarial training to enhance the performance of knowledge alignment. In the experiment, in the knowledge extraction part, the NER and RE precision of our model achieved 86.7% and 79.48%, respectively. RE precision improved by 20.83% compared to the baseline with sequence labeling method. Additionally, in the knowledge alignment part, the precision of our model reached 99.29%, representing a 1.42% improvement over baseline methods. Consequently, the proposed model with the partition mechanism can effectively extract domain knowledge, cand the semi-supervised method can take advantage of unlabeled triples. Our method can adapt the domain features and construct a high-quality knowledge graph for the quality engineering of continuous casting, providing an efficient solution for billet defect issues.
format Article
id doaj-art-fa23d4006c834e3fb0de3aa3dbf6d417
institution DOAJ
issn 2076-3417
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-fa23d4006c834e3fb0de3aa3dbf6d4172025-08-20T03:14:42ZengMDPI AGApplied Sciences2076-34172025-05-011510567410.3390/app15105674Domain-Specific Knowledge Graph for Quality Engineering of Continuous Casting: Joint Extraction-Based Construction and Adversarial Training Enhanced AlignmentXiaojun Wu0Yue She1Xinyi Wang2Hao Lu3Qi Gao4Shaanxi Joint Laboratory of Artificial Intelligence, School of Software Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaShaanxi Joint Laboratory of Artificial Intelligence, School of Software Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaShaanxi Joint Laboratory of Artificial Intelligence, School of Software Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaShaanxi Joint Laboratory of Artificial Intelligence, School of Software Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaChina National Heavy Machinery Research Institute Co., Ltd., Xi’an 710016, ChinaThe intelligent development of continuous casting quality engineering is an essential step for the efficient production of high-quality billets. However, there are many quality defects that require strong expertise for handling. In order to reduce reliance on expert experience and improve the intelligent management level of billet quality knowledge, we focus on constructing a Domain-Specific Knowledge Graph (DSKG) for the quality engineering of continuous casting. To achieve joint extraction of billet quality defects entity and relation, we propose a Self-Attention Partition and Recombination Model (SAPRM). SAPRM divides domain-specific sentences into three parts: entity-related, relation-related, and shared features, which are specifically for Named Entity Recognition (NER) and Relation Extraction (RE) tasks. Furthermore, for issues of entity ambiguity and repetition in triples, we propose a semi-supervised incremental learning method for knowledge alignment, where we leverage adversarial training to enhance the performance of knowledge alignment. In the experiment, in the knowledge extraction part, the NER and RE precision of our model achieved 86.7% and 79.48%, respectively. RE precision improved by 20.83% compared to the baseline with sequence labeling method. Additionally, in the knowledge alignment part, the precision of our model reached 99.29%, representing a 1.42% improvement over baseline methods. Consequently, the proposed model with the partition mechanism can effectively extract domain knowledge, cand the semi-supervised method can take advantage of unlabeled triples. Our method can adapt the domain features and construct a high-quality knowledge graph for the quality engineering of continuous casting, providing an efficient solution for billet defect issues.https://www.mdpi.com/2076-3417/15/10/5674quality engineering of continuous castingknowledge extractionknowledge alignmentdomain-specific knowledge graph
spellingShingle Xiaojun Wu
Yue She
Xinyi Wang
Hao Lu
Qi Gao
Domain-Specific Knowledge Graph for Quality Engineering of Continuous Casting: Joint Extraction-Based Construction and Adversarial Training Enhanced Alignment
Applied Sciences
quality engineering of continuous casting
knowledge extraction
knowledge alignment
domain-specific knowledge graph
title Domain-Specific Knowledge Graph for Quality Engineering of Continuous Casting: Joint Extraction-Based Construction and Adversarial Training Enhanced Alignment
title_full Domain-Specific Knowledge Graph for Quality Engineering of Continuous Casting: Joint Extraction-Based Construction and Adversarial Training Enhanced Alignment
title_fullStr Domain-Specific Knowledge Graph for Quality Engineering of Continuous Casting: Joint Extraction-Based Construction and Adversarial Training Enhanced Alignment
title_full_unstemmed Domain-Specific Knowledge Graph for Quality Engineering of Continuous Casting: Joint Extraction-Based Construction and Adversarial Training Enhanced Alignment
title_short Domain-Specific Knowledge Graph for Quality Engineering of Continuous Casting: Joint Extraction-Based Construction and Adversarial Training Enhanced Alignment
title_sort domain specific knowledge graph for quality engineering of continuous casting joint extraction based construction and adversarial training enhanced alignment
topic quality engineering of continuous casting
knowledge extraction
knowledge alignment
domain-specific knowledge graph
url https://www.mdpi.com/2076-3417/15/10/5674
work_keys_str_mv AT xiaojunwu domainspecificknowledgegraphforqualityengineeringofcontinuouscastingjointextractionbasedconstructionandadversarialtrainingenhancedalignment
AT yueshe domainspecificknowledgegraphforqualityengineeringofcontinuouscastingjointextractionbasedconstructionandadversarialtrainingenhancedalignment
AT xinyiwang domainspecificknowledgegraphforqualityengineeringofcontinuouscastingjointextractionbasedconstructionandadversarialtrainingenhancedalignment
AT haolu domainspecificknowledgegraphforqualityengineeringofcontinuouscastingjointextractionbasedconstructionandadversarialtrainingenhancedalignment
AT qigao domainspecificknowledgegraphforqualityengineeringofcontinuouscastingjointextractionbasedconstructionandadversarialtrainingenhancedalignment