Abstract
Defects in main electrical equipment can potentially cause power grid collapses, leading to catastrophic risks and immense pressure on dispatch operations. We adopt a Knowledge Graph Completion (KGC) approach to diagnose defects in main electrical equipment. The conventional approach for knowledge graph completion involves randomly initializing the feature representation of nodes and edges. In the context of main electrical equipment, we propose an innovative method based on ChatGPT to generate a corpus for fine-tuning the pre-trained model. We then employ the pre-trained model as a feature extractor for nodes and edges, enhancing the relationships between nodes and improving the initial embedding quality of both nodes and edges. Our pre-trained model fine-tuning process can be efficiently executed on a CPU with less than 10% of the parameters required for fine-tuning the entire pre-trained model. Our experimental results show that our model effectively improves the performance of KGC in diagnosing defects in main electrical equipment.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bordes, A., Usunier, N., Garcia-Duran, A., et al.: Translating embeddings for modeling multi-relational data. In: Advances in Neural Information Processing Systems 26 (2013)
Gururangan, S., Marasović, A., Swayamdipta, S., et al.: Don’t stop pretraining: adapt language models to domains and tasks. arXiv preprint arXiv:2004.10964 (2020)
Houlsby, N., Giurgiu, A., Jastrzebski, S., et al.: Parameter-efficient transfer learning for NLP. In: International Conference on Machine Learning. PMLR, pp. 2790–2799 (2019)
Devlin, J., Chang, M.W., Lee, K., et al.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Yang, S., Wang, J., Meng, F., et al.: Text mining techniques for knowledge of defects in power equipment. In: 2021 10th IEEE International Conference on Communication Systems and Network Technologies (CSNT). IEEE, pp. 205–210 (2021)
Shcherbatov, I., Lisin, E., Rogalev, A., et al.: Power equipment defects prediction based on the joint solution of classification and regression problems using machine learning methods. Electronics 10(24), 3145 (2021)
Abid, A., Khan, M.T., Iqbal, J.: A review on fault detection and diagnosis techniques: basics and beyond. Artif. Intell. Rev. 54, 3639–3664 (2021)
Meng, F., Yang, S., Wang, J., et al.: Creating knowledge graph of electric power equipment faults based on BERT–BiLSTM–CRF model. J. Electr. Eng. Technol. 17, 2507–2516 (2022)
Graves, A.: Long short-term memory. In: Supervised Sequence Labelling with Recurrent Neural Networks. Studies in Computational Intelligence, vol. 385, pp. 37–45. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-24797-2_4
Lafferty, J., McCallum, A., Pereira, F.C.N.: Conditional random fields: probabilistic models for segmenting and labeling sequence data (2001)
Chen, Q., Li, Q., Wu, J., et al.: Application of knowledge graph in power system fault diagnosis and disposal: a critical review and perspectives. Front. Energy Res. 10, 1307 (2022)
Zhang, T., Ding, J., Guo, Z.: Multimodal knowledge graph for power equipment defect data. In: Proceedings of the 7th International Conference on Cyber Security and Information Engineering, pp. 666–668 (2022)
Qiu, X., Sun, T., Xu, Y., et al.: Pre-trained models for natural language processing: a survey. Sci. China Technol. Sci. 63(10), 1872–1897 (2020)
Hai, H.N.: ChatGPT: The Evolution of Natural Language Processing. Authorea Preprints (2023)
Ouyang, L., Wu, J., Jiang, X, et al.: Training language models to follow instructions with human feedback. In: Advances in Neural Information Processing Systems 35, pp. 27730–27744 (2022)
Ali, M., Berrendorf, M., Hoyt, C.T., et al.: PyKEEN 1.0: a python library for training and evaluating knowledge graph embeddings. J. Mach. Learn. Res. 22(1), 3723–3728 (2021)
Yang, B., Yih, W., He, X., et al.: Embedding entities and relations for learning and inference in knowledge bases. arXiv preprint arXiv:1412.6575 (2014)
He, S., Liu, K., Ji, G., et al.: Learning to represent knowledge graphs with Gaussian embedding. In: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, pp. 623–632 (2015)
Galkin, M., Denis, E., Wu, J., et al.: Nodepiece: compositional and parameter-efficient representations of large knowledge graphs. arXiv preprint arXiv:2106.12144 (2021)
Wang, A., Singh, A., Michael, J., et al.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461, (2018)
Opitz, J., Parcalabescu, L., Frank, A.: AMR similarity metrics from principles. Trans. Assoc. Comput. Linguist. 8, 522–538 (2020)
Acknowledgements
This work is supported by the Research Funds from State Grid Fujian (SGFJDK00SZJS2200162).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Huang, J. et al. (2023). Improve Knowledge Graph Completion for Diagnosing Defects in Main Electrical Equipment. In: Huang, DS., Premaratne, P., Jin, B., Qu, B., Jo, KH., Hussain, A. (eds) Advanced Intelligent Computing Technology and Applications. ICIC 2023. Lecture Notes in Computer Science(), vol 14090. Springer, Singapore. https://doi.org/10.1007/978-981-99-4761-4_62
Download citation
DOI: https://doi.org/10.1007/978-981-99-4761-4_62
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-4760-7
Online ISBN: 978-981-99-4761-4
eBook Packages: Computer ScienceComputer Science (R0)