A manufacturing knowledge graph completion method based on a lightweight dual encoding model (original) (raw)
Abstract
Ensuring stable equipment operation is crucial for manufacturing. Intelligent maintenance decisions powered by manufacturing knowledge graphs can reduce reliance on manual maintenance and enhance efficiency. However, existing knowledge graphs face challenges such as sparse information and complex relationship modeling. Knowledge graph completion can predict missing relationships and entities to enrich the graph. Current completion methods neglect semantic information in entity descriptions, leading to incomplete data, while encoding triples and descriptions increases computational costs. Therefore, this paper proposes a Lightweight Dual Encoding Model (LDEM) for manufacturing knowledge graph completion. LDEM uses ALBERT to encode entity descriptions and captures rich semantics through precomputed embeddings. The graph attention module aggregates neighborhood information, and ConvKB decodes embeddings into predictions. The dataset used in this study comes from a vehicle welding workshop in Chongqing, China. Experiments show that LDEM outperforms state-of-the-art models in all metrics, achieving 80.1 points in Hits@10 and demonstrating superior ability to capture entity relationships and semantic information, thereby enhancing the completion of the manufacturing knowledge graph.
Access this article
Subscribe and save
- Starting from 10 chapters or articles per month
- Access and download chapters and articles from more than 300k books and 2,500 journals
- Cancel anytime View plans
Buy Now
Price excludes VAT (USA)
Tax calculation will be finalised during checkout.
Instant access to the full article PDF.
Similar content being viewed by others
References
- Carvalho TP, Soares FAAMN, Vita R (2019) A systematic literature review of machine learning methods applied to predictive maintenance. Computers Ind Eng 137:106024
Article Google Scholar - Xu H, Li P, Cong Z et al (2021) Research on fault diagnosis method of electric energy metering equipment based on expert system. IOP Conf Ser Earth Environ Sci 632:042072
Article Google Scholar - Ding Y, Li H, Zhu F et al (2023) A Semi-Supervised failure knowledge graph construction method for decision support in operations and maintenance. IEEE Trans Industr Inf 20(3):3104–3114
Article Google Scholar - Teng H, Deng Z, Lu L et al (2022) Research on machining process state monitoring based on multi-sensor information fusion. J Mech Eng 58(6):26–41
Article Google Scholar - Han T, Li Y, Lei Y et al (2022) Semi-supervised fault diagnosis method for key components of industrial robots based on fusion graph label propagation and discriminant feature enhancement. J Mech Eng 58(17):116–124
Article Google Scholar - Du K, Yang B, Xie K et al (2025) Llm-manuf: an integrated framework of fine-tuning large language models for intelligent decision-making in manufacturing. Adv Eng Inform 65:103263
Article Google Scholar - Yang X, Ma G, Jin X et al (2023) Knowledge graph embedding and completion based on entity community and local importance. Appl Intell 53:22132–22142
Article Google Scholar - Bordes A, Usunier N, Garcia-Duran A et al (2013) Translating embeddings for modeling multi-relational data. Adv Neural Inf Process Syst. 26(2):2787–2795
Google Scholar - Wang Z, Zhang J, Feng J (2014) Knowledge graph embedding by translating on hyperplanes. Proceedings of the AAAI Conference on Artificial Intelligence 28:1112–1119
Article Google Scholar - Lin Y, Liu Z, Luan H et al (2015) Modeling relation paths for representation learning of knowledge bases. Proceedings of the. Conference on Empirical Methods in Natural Language Processing. 2015,705–714
- Li X, Tian Y, Ji S (2024) Semantic- and relation-based graph neural network for knowledge graph completion. Appl Intell 54:6085–6107
Article Google Scholar - Wang J, Li W, Liu W et al (2023) Enabling inductive knowledge graph completion via structure-aware attention network. Appl Intell 53:25003–25027
Article Google Scholar - Zhang J, Shen B (2024) A lightweight hierarchical graph convolutional model for knowledge graph representation learning. Appl Intell 54:10695–10708
Article Google Scholar - Xu G, Rao G, Zhang L et al (2025) Entity-relation aggregation mechanism graph neural network for knowledge graph embedding. Appl Intell 55:43
Article Google Scholar - Zan S, Ji W, Zhou G (2025) Knowledge graph embeddings based on 2d convolution and self-attention mechanisms for link prediction. Appl Intell 55:104
Article Google Scholar - Zhang J, Shen B, Wang T et al (2023) Converting hyperparameter gamma in distance-based loss functions to normal parameter for knowledge graph completion. Appl Intell 53:23369–23382
Article Google Scholar - Liu S, Li W, Song X et al (2025) NP-FedKGC: a neighbor prediction-enhanced federated knowledge graph completion model. Appl Intell 55:235
Article Google Scholar - Yang X, Li Q, Wei D et al (2024) Implicit relational attention network for few-shot knowledge graph completion. Appl Intell 54:6433–6443
Article Google Scholar - Tao Y, Tao H, Zhuang Z et al (2024) Quantized iterative learning control of communication-constrained systems with encoding and decoding mechanism. Trans Inst Meas Control 46(10):1943–1954
Article Google Scholar - Tao H, Zheng J, Wei J et al (2023) Repetitive process based indirect-type iterative learning control for batch processes with model uncertainty and input delay. J Process Control 132:103112
Article Google Scholar - Guan S, Zhuang Z, Tao H et al (2023) Feedback-aided PD-type iterative learning control for time-varying systems with non-uniform trial lengths. Trans Inst Meas Control 45(11):2015–2026
Article Google Scholar - Zhang D, Liu Z, Tan J et al (2021) A review on knowledge graph and its application prospects to intelligent manufacturing. J Mech Eng 57(5):90–113
Article Google Scholar - CHHIM P, CHINNAM R B, SADAWI N (2019) Product design and manufacturing process based ontology for manufacturing knowledge reuse. J Intell Manuf 30(2):905–916
Article Google Scholar - Tago FP, Francisco M (2023) The adoption of 4Step-Rule-Set method for ontological design: application in a real industrial project. Procedia Comput Sci 219:405–415
Article Google Scholar - GUREVYCH SOROKIND (2017) I. Context-aware representations for knowledge base relation extraction. Proceedings of the Conference on Empirical Methods in Natural Language Processing. 2017:1784–1789
- Sun Z, Hu W, Zhang Q et al (2018) Bootstrapping entity alignment with knowledge graph embedding. Proceedings of the 27th International Joint Conference on Artificial Intelligence. : 4396–4402
- Chen J, Yang H, Dong M et al (2014) Design knowledge updating method based on similarity matching of ontology semantic block. J Mech Eng 50(7):161–167
Article MathSciNet Google Scholar - Schlichtkrull M, Kipf TN, Bloem P et al (2018) Modeling relational data with graph convolutional networks. Proceedings 15. Springer International Publishing. : 593–607
- Wang T, Shen B, Zhong Y (2023) SSKGE: a time-saving knowledge graph embedding framework based on structure enhancement and semantic guidance. Appl Intell 53:25171–25183
Article Google Scholar - Trouillon T, Welbl J, Riedel S et al (2016) Complex embeddings for simple link prediction. International conference on machine learning. : 2071–2080
- Dettmers T, Minervini P, Stenetorp P et al (2018) Convolutional 2d knowledge graph embeddings. Proceedings of the AAAI conference on artificial intelligence. 32(1)
- Yu M, Jiang T, Yu J et al (2023) Sepake: a structure-enhanced and position-aware knowledge embedding framework for knowledge graph completion. Appl Intell 53:23113–23123
Article Google Scholar - VASHISHTH S, SANYAL S et al (2019) NITIN V,. Composition-based multi-relational graph convolutional networks. International Conference on Learning Representations
- Jiang T, Liu T, Ge T et al (2016) Encoding temporal information for time-aware link prediction. Proceedings of the. Conference on Empirical Methods in Natural Language Processing. 2016: 2350–2354
- GARCIA-DURAN A, DUMANCIC S (2018) NIEPERT M. Learning sequence encoders for temporal knowledge graph completion. Proceedings of the Conference on Empirical Methods in Natural Language Processing. 2018:4816–4821
- Lu X, Wang L, Jiang Z et al (2022) MMKRL: a robust embedding approach for multi-modal knowledge graph representation learning. Appl Intell 52:7480–7497
Article Google Scholar - Devlin J, Chang MW, Lee K et al (2019) Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies. 1: 4171–4186
- Nguyen DQ, Nguyen TD, Nguyen DQ et al (2017) A novel embedding model for knowledge base completion based on convolutional neural networt. ArXiv Preprint arXiv:1712.02121
- Sun Z, Deng ZH, Nie JY et al (2019) Rotate: Knowledge graph embedding by relational rotation in complex space. arXiv preprint arXiv:1902.10197
- Zhang Z, Cai J, Zhang Y et al (2020) Learning hierarchy-aware knowledge graph embeddings for link prediction. Proceedings of the AAAI conference on artificial intelligence 34(03):3065–3072
Article Google Scholar - Yao L, Mao C, Luo Y (2019) KG-BERT: BERT for knowledge graph completion. arXiv preprint arXiv:1909.03193
- Wang L, Zhao W, Wei Z et al (2022) SimKGC: Simple contrastive knowledge graph completion with pre-trained language models. arXiv preprint arXiv:2203.02167
Acknowledgements
This work was supported by the National Key Research and Development Program of China (no. 2023YFB3306800), the New Chongqing Young Innovative Talent Program (no. CSTB2024NSCQ-QCXMX0028), the Key Laboratory of Industrial Software Engineering and Application Technology of Ministry of Industry and Information Technology (HK202303540), and the Fundamental Research Funds for the Central Universities (2023CDJKYJH033).
Author information
Authors and Affiliations
- State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University, Chongqing, 400044, China
Xing Qi, Xiaoyu Shen, Yucheng Zhang & Bo Yang - School of Mechanical Science & Engineering, Huazhong University of Science and Technology, Wuhan, 430074, China
Keqiang Xie - The Fifth Electronics Research Institute of the Ministry Industry and Information Technology, Guangzhou, 510000, China
Keqiang Xie & Nan Dong - Seres Automobile Co., Ltd., Chongqing, 400020, China
Yucheng Zhang
Authors
- Xing Qi
- Xiaoyu Shen
- Yucheng Zhang
- Bo Yang
- Keqiang Xie
- Nan Dong
Corresponding authors
Correspondence toYucheng Zhang or Keqiang Xie.
Ethics declarations
Conflict of interest
We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work, there is no professional or other personal interest of any nature or kind in any product, service or company that could be construed as influencing the position presented in the manuscript entitled.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Qi, X., Shen, X., Zhang, Y. et al. A manufacturing knowledge graph completion method based on a lightweight dual encoding model.Appl Intell 55, 1009 (2025). https://doi.org/10.1007/s10489-025-06909-0
- Received: 28 November 2024
- Accepted: 09 September 2025
- Published: 07 October 2025
- Version of record: 07 October 2025
- DOI: https://doi.org/10.1007/s10489-025-06909-0