Abstract
Artificial intelligence techniques are increasingly used for asset management. The abundance of data available in large electrical utility offers many application opportunities. The use of data-driven models can address some of the biases of physical models traditionally used in reliability engineering. However, in this context, as in many other fields of operation, the quality of data is often questioned by domain experts. Operational data are entered manually by maintenance technicians, and data entry errors are common. One of the errors that is observed is mislabeling of maintenance types, which can lead to poor statistical estimates of failure rate. This paper aims to improve the quality of historical maintenance data, to increase the accuracy of deployed models. To this end, the text fields available in the maintenance history is analyzed to predict the type of maintenance performed. Natural language processing (NLP) techniques are applied to solve this text classification problem. The models are applied to Hydro-Québec TransÉnergie’s power transmission assets. The application of such techniques allows the enrichment of databases and thus reduces uncertainty in decision-making for asset management.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amadi-Echendu, J.E., Brown, K., Willett, R., Mathew, J.: Definitions. London, Springer-Verlag, London, Concepts and Scope of Engineering Asset Management (2011)
Beysolow II, T.: Applied Natural Language Processing with Python: Implementing Machine Learning and Deep Learning Algorithms for Natural Language Processing, Apress, New York (2018)
Fahad, A., et al.: A survey of clustering algorithms for big data: taxonomy and empirical analysis. IEEE Trans. Emerg. Top. Comput. 2, 267–279 (2014)
Honnibal, M., Johnson, M.: An improved non-monotonic transition system for dependency parsing. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1373–1378 (2015)
Hurwitz, J., Kirsch, D.: Machine Learning for dummies. Wiley (2018)
International organisation for standardization. ISO 55000, 55001 and 55002 Asset Management Standards. BSI Standards (2015)
Islam, H.: Reliability-centered maintenance methodology and application: a case study. Engineering 2(11), 863–873 (2010)
Jimenez-cortadi, A., Irigoien, I., Boto, F., Sierra, B., Rodriguez, G.: Predictive maintenance on the machining process and machine tool. Appl. Sci. (2076–3417), 10, 224 (2020)
Lecun, Y., Misra, I.: Self-supervised learning: the dark matter of intelligence. Meta A I, 23 (2021)
Lewis, E.E.: Introduction to Reliability Engineering, Wiley, New York (1996)
Liang, Y.P., Blancke, O., Gaha, M., St-jean, G., Aïmeur, E.: Automatic Database Alignment Method to Improve Failure Data Quality. RAMS 2022 (In press) (2022)
Perrons, R.K., Jensen, J.W.: Data as an asset: what the oil and gas sector can learn from other industries about “Big Data.” Energy Policy 81, 117–121 (2015)
Russell, S. Norvig, P.: Artificial Intelligence: A Modern Approach (2002)
Thanaki, J.: Python Natural Language Processing, Packt Publishing Ltd., Birmingham (2017)
Vaswani, A., et al.: Attention is all you need. Adv. Neural inf. Proc. Syst. 30 (2017)
Yang, X., He, X., Liang, Y., Yang, Y., Zhang, S. Xie, P.: Transfer learning or self-supervised learning? A tale of two pretraining paradigms (2020). arXiv preprint arXiv:2007.04234
Acknowledgement
This research was supported by Hydro-Québec, the Natural Sciences and Engineering Research Council of Canada (NSERC) and the Université du Québec à Trois-Rivières through the Hydro-Québec Asset Management research Chair.
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 Switzerland AG
About this paper
Cite this paper
Payette, M., Abdul-Nour, G., Meango, T.JM., Côté, A. (2023). Improving Maintenance Data Quality: Application of Natural Language Processing to Asset Management. In: Crespo Márquez, A., Gómez Fernández, J.F., González-Prida Díaz, V., Amadi-Echendu, J. (eds) 16th WCEAM Proceedings. WCEAM 2022. Lecture Notes in Mechanical Engineering. Springer, Cham. https://doi.org/10.1007/978-3-031-25448-2_54
Download citation
DOI: https://doi.org/10.1007/978-3-031-25448-2_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25447-5
Online ISBN: 978-3-031-25448-2
eBook Packages: EngineeringEngineering (R0)