A knowledge graph attention network for the cold-start problem in intelligent manufacturing: Interpretability and accuracy improvement

In the rolling production of steel, predicting the performance of new products is challenging due to the low variety of data distributions resulting from standardized manufacturing processes and fixed product categories. This scenario poses a significant hurdle for machine learning models, leading t...

Descripción completa

Detalles Bibliográficos
Autores: Zhou, Ziye, Zhang, Yuqi, Wang, Zhuize, San-Martín, David, Liu, Yongqian, Liu, Yan, Wang, Chenchong, Xu, Wei
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:dnet:digitalcsic_::13d603569b1b93256546a031eca6cc78
Acceso en línea:http://hdl.handle.net/10261/426341
Access Level:acceso abierto
Palabra clave:Attention mechanisms
Cold-start problem
Graph neural network
Interpretable machine learning
Knowledge graph
Materials design
Mechanical performance
id ES_228c43fd88d7d75a2f1b4e5f1792bff7
oai_identifier_str oai:dnet:digitalcsic_::13d603569b1b93256546a031eca6cc78
network_acronym_str ES
network_name_str España
repository_id_str
spelling A knowledge graph attention network for the cold-start problem in intelligent manufacturing: Interpretability and accuracy improvementZhou, ZiyeZhang, YuqiWang, ZhuizeSan-Martín, DavidLiu, YongqianLiu, YanWang, ChenchongXu, WeiAttention mechanismsCold-start problemGraph neural networkInterpretable machine learningKnowledge graphMaterials designMechanical performanceIn the rolling production of steel, predicting the performance of new products is challenging due to the low variety of data distributions resulting from standardized manufacturing processes and fixed product categories. This scenario poses a significant hurdle for machine learning models, leading to what is commonly known as the “cold-start problem”. To address this issue, we propose a knowledge graph attention neural network for steel manufacturing (SteelKGAT). By leveraging expert knowledge and a multi-head attention mechanism, SteelKGAT aims to enhance prediction accuracy. Our experimental results demonstrate that the SteelKGAT model outperforms existing methods when generalizing to previously unseen products. Only the SteelKGAT model accurately captures the feature trend, thereby offering correct guidance in product tuning, which is of practical significance for new product development (NPD). Additionally, we employ the Integrated Gradients (IG) method to shed light on the model's predictions, revealing the relative importance of each feature within the knowledge graph. Notably, this work represents the first application of knowledge graph attention neural networks to address the cold-start problem in steel rolling production. By combining domain expertise and interpretable predictions, our knowledge-informed SteelKGAT model provides accurate insights into the mechanical properties of products even in cold-start scenarios.The research was financially supported by the National Key R&D Program (No. 2021YFB3702404) and National Natural Science Foundation of China (Nos. 52311530082 and U22A20106). The financial support provided by “Xingliao Talent Plan” project (Grant No. XLYC2203027) is gratefully acknowledged.Peer reviewedWiley-VCHNational Natural Science Foundation of ChinaNational Key Research and Development Program (China)San-Martin, David [0000-0001-6720-3599]Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]202620262025info:eu-repo/semantics/articlehttp://purl.org/coar/resource_type/c_6501http://hdl.handle.net/10261/426341reponame:DIGITAL.CSIC. Repositorio Institucional del CSICinstname:Consejo Superior de Investigaciones Científicas (CSIC)InglésSíinfo:eu-repo/semantics/openAccessoai:dnet:digitalcsic_::13d603569b1b93256546a031eca6cc782026-05-22T06:33:51Z
dc.title.none.fl_str_mv A knowledge graph attention network for the cold-start problem in intelligent manufacturing: Interpretability and accuracy improvement
title A knowledge graph attention network for the cold-start problem in intelligent manufacturing: Interpretability and accuracy improvement
spellingShingle A knowledge graph attention network for the cold-start problem in intelligent manufacturing: Interpretability and accuracy improvement
Zhou, Ziye
Attention mechanisms
Cold-start problem
Graph neural network
Interpretable machine learning
Knowledge graph
Materials design
Mechanical performance
title_short A knowledge graph attention network for the cold-start problem in intelligent manufacturing: Interpretability and accuracy improvement
title_full A knowledge graph attention network for the cold-start problem in intelligent manufacturing: Interpretability and accuracy improvement
title_fullStr A knowledge graph attention network for the cold-start problem in intelligent manufacturing: Interpretability and accuracy improvement
title_full_unstemmed A knowledge graph attention network for the cold-start problem in intelligent manufacturing: Interpretability and accuracy improvement
title_sort A knowledge graph attention network for the cold-start problem in intelligent manufacturing: Interpretability and accuracy improvement
dc.creator.none.fl_str_mv Zhou, Ziye
Zhang, Yuqi
Wang, Zhuize
San-Martín, David
Liu, Yongqian
Liu, Yan
Wang, Chenchong
Xu, Wei
author Zhou, Ziye
author_facet Zhou, Ziye
Zhang, Yuqi
Wang, Zhuize
San-Martín, David
Liu, Yongqian
Liu, Yan
Wang, Chenchong
Xu, Wei
author_role author
author2 Zhang, Yuqi
Wang, Zhuize
San-Martín, David
Liu, Yongqian
Liu, Yan
Wang, Chenchong
Xu, Wei
author2_role author
author
author
author
author
author
author
dc.contributor.none.fl_str_mv National Natural Science Foundation of China
National Key Research and Development Program (China)
San-Martin, David [0000-0001-6720-3599]
Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]
dc.subject.none.fl_str_mv Attention mechanisms
Cold-start problem
Graph neural network
Interpretable machine learning
Knowledge graph
Materials design
Mechanical performance
topic Attention mechanisms
Cold-start problem
Graph neural network
Interpretable machine learning
Knowledge graph
Materials design
Mechanical performance
description In the rolling production of steel, predicting the performance of new products is challenging due to the low variety of data distributions resulting from standardized manufacturing processes and fixed product categories. This scenario poses a significant hurdle for machine learning models, leading to what is commonly known as the “cold-start problem”. To address this issue, we propose a knowledge graph attention neural network for steel manufacturing (SteelKGAT). By leveraging expert knowledge and a multi-head attention mechanism, SteelKGAT aims to enhance prediction accuracy. Our experimental results demonstrate that the SteelKGAT model outperforms existing methods when generalizing to previously unseen products. Only the SteelKGAT model accurately captures the feature trend, thereby offering correct guidance in product tuning, which is of practical significance for new product development (NPD). Additionally, we employ the Integrated Gradients (IG) method to shed light on the model's predictions, revealing the relative importance of each feature within the knowledge graph. Notably, this work represents the first application of knowledge graph attention neural networks to address the cold-start problem in steel rolling production. By combining domain expertise and interpretable predictions, our knowledge-informed SteelKGAT model provides accurate insights into the mechanical properties of products even in cold-start scenarios.
publishDate 2025
dc.date.none.fl_str_mv 2025
2026
2026
dc.type.none.fl_str_mv info:eu-repo/semantics/article
http://purl.org/coar/resource_type/c_6501
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10261/426341
url http://hdl.handle.net/10261/426341
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Sí
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Wiley-VCH
publisher.none.fl_str_mv Wiley-VCH
dc.source.none.fl_str_mv reponame:DIGITAL.CSIC. Repositorio Institucional del CSIC
instname:Consejo Superior de Investigaciones Científicas (CSIC)
instname_str Consejo Superior de Investigaciones Científicas (CSIC)
reponame_str DIGITAL.CSIC. Repositorio Institucional del CSIC
collection DIGITAL.CSIC. Repositorio Institucional del CSIC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869404588225855488
score 15.812455

Similares en LA Referencia