Document Open Access Logo

Towards Predictive Maintenance in an Aluminum Die-Casting Process Using Deep Learning Clustering and Dimensionality Reduction

Authors Miguel Cubero , Luis Ignacio Jiménez , Daniel López , Belarmino Pulido , Carlos Alonso-González

PDF

File

Thumbnail PDF
PDF
OASIcs.DX.2025.6.pdf
  • Filesize: 10.57 MB
  • 16 pages

Document Identifiers

Subject Classification

ACM Subject Classification
  • Computing methodologies → Cluster analysis
  • Computing methodologies → Dimensionality reduction and manifold learning
Keywords
  • Prognostics
  • Deep Learning
  • Clustering
  • UMAP
  • LOWESS regression

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
    0
    Metadata Views

Abstract

In the manufacturing industry, predictive maintenance requires the estimation of the health status of key subsystems or components. In this study, we will look for degradation patterns in the piston of an injection machine used in an aluminum die casting process operating in an automobile factory in Valladolid (Spain). The injection machine produces a new engine block every 90 seconds and each injection device provides 2000 measurements of various physical variables. This study faced the challenge of finding piston head degradation patterns for an injection machine in the factory, using time series data obtained from the controller, as a preliminary step to estimate the remaining useful life (RUL) of the piston head. The proposed solution used advanced deep learning clustering techniques to generate an index related with the progression of the degradation of the components. The results indicated that degradation patterns can be identified. Later on, using an exponential function an approximation of the RUL can be provided to the plant operator to achieve an ordered piston replacement.

Cite As Get BibTex

Miguel Cubero, Luis Ignacio Jiménez, Daniel López, Belarmino Pulido, and Carlos Alonso-González. Towards Predictive Maintenance in an Aluminum Die-Casting Process Using Deep Learning Clustering and Dimensionality Reduction. In 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 6:1-6:16, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025) https://doi.org/10.4230/OASIcs.DX.2025.6

Author Details

Miguel Cubero
  • University of Valladolid, Spain
Luis Ignacio Jiménez
  • University of Valladolid, Spain
Daniel López
  • HORSE Powertrain, Valladolid, Spain
Belarmino Pulido
  • University of Valladolid, Spain
Carlos Alonso-González
  • University of Valladolid, Spain

Funding

This work has been partially supported by Spanish Ministerio de Ciencia e Innovación under Grant PID2021-126659OB-I00.
  • Cubero, Miguel: M. Cubero’s work has been supported by the 2024 Investigo Programme from the Spanish Ministerio de Trabajo y Economia social using EU Next Generation Funds.

Acknowledgements

Authors want to thank our former students David Garcia de Vicuña López de Ciordia and Daniel Veganzones for their help in early stages of this work; also, authors want to acknowledge the people from the Informatics and Injection Sections of the factory for granting access to the time series dataset, and for the help and support provided in understanding the injection process.

References

  1. Gerardo Acosta, Carlos Alonso González, and Belarmino Pulido. Basic tasks for knowledge-based supervision in process control. Engineering Applications of Artificial Intelligence, 14(4):441-455, 2001. Google Scholar
  2. Nagdev Amruthnath and Tarun Gupta. A research study on unsupervised machine learning algorithms for early fault detection in predictive maintenance. In 2018 5th International Conference on Industrial Engineering and Applications (ICIEA), pages 355-361, 2018. URL: https://doi.org/10.1109/IEA.2018.8387124.
  3. Vepa Atamuradov, Kamal Medjaher, Pierre Dersin, Benjamin Lamoureux, and Noureddine Zerhouni. Prognostics and health management for maintenance practitioners-review, implementation and tools evaluation. International Journal of Prognostics and Health Management, 8(3):1-31, 2017. Google Scholar
  4. Piero Baraldi, Francesco Cadini, Francesca Mangili, and Enrico Zio. Model-based and data-driven prognostics under different available information. Probabilistic Engineering Mechanics, 32:66-79, 2013. Google Scholar
  5. James C Bezdek. Pattern recognition with fuzzy objective function algorithms. Springer Science & Business Media, 2013. Google Scholar
  6. William S. Cleveland. Robust locally weighted regression and smoothing scatterplots. Journal of the American Statistical Association, 74(368):829-836, 1979. URL: https://doi.org/10.1080/01621459.1979.10481038.
  7. Miguel Cubero, Diego Garcia-Alvarez, Luis Ignacio Jiménez, Daniel López Gómez, Belarmino Pulido, and Carlos Alonso González. Deep-learning clustering to assess the health state in a die-casting process in the automotive industry. In 6th "International Conference on Control and Fault-Tolerant Systems (SYSTOL)", 2025. Google Scholar
  8. Matthew J Daigle and Kai Goebel. A model-based prognostics approach applied to pneumatic valves. International Journal of Prognostics and Health Management Volume 2 (color), 84, 2011. Google Scholar
  9. David Garcia de Vicuña Lopez de Ciordia. Application of time-series clustering for Factory 4.0 (in Spanish). Master’s thesis, Escuela de Ingenieria Informatica de Valladolid, Universidad de Valladolid, July 2024. Supervisors: B. Pulido, C. Alonso-Gonzalez. Google Scholar
  10. Alberto Diez-Olivan, Javier Del Ser, Diego Galar, and Basilio Sierra. Data fusion and machine learning for industrial prognosis: Trends and perspectives towards industry 4.0. Information Fusion, 50:92-111, 2019. URL: https://doi.org/10.1016/J.INFFUS.2018.10.005.
  11. J. Y. Franceschi, A. Dieuleveut, and M. Jaggi. Unsupervised scalable representation learning for multivariate time series. Advances in Neural Information Processing Systems, 32, 2019. Google Scholar
  12. B. Lafabregue, J. Weber, P. Gançarski, and G. Forestier. End-to-end deep representation learning for time series clustering: a comparative study. Data Mining and Knowledge Discovery, 36(1):29-81, 2022. URL: https://doi.org/10.1007/S10618-021-00796-Y.
  13. Han Li, Wei Zhao, Yuxi Zhang, and Enrico Zio. Remaining useful life prediction using multi-scale deep convolutional neural network. Applied Soft Computing, 89:106113, 2020. URL: https://doi.org/10.1016/J.ASOC.2020.106113.
  14. Elizabeth Ann Maharaj, Pierpaolo D'Urso, and Jorge Caiado. Time series clustering and classification. Chapman and Hall/CRC, 2019. Google Scholar
  15. Leland McInnes, John Healy, Nathaniel Saul, and Lucas Großberger. UMAP: uniform manifold approximation and projection. Journal of Open Source Software, 3(29):861, 2018. URL: https://doi.org/10.21105/JOSS.00861.
  16. Bojana Nikolic, Jelena Ignjatic, Suzic Nikola, Branislav Stevanov, Aleksandar Rikalovic, et al. Predictive manufacturing systems in industry 4.0: Trends, benefits and challenges. In Proceedings of 28th DAAAM International Symposium on Intelligent Manufacturing and Automation, pages 796-802. DAAAM International, Vienna, Austria, 2017. Google Scholar
  17. Anibal Hernando Novo. Health state estimation for an injection machine using deep-learning (in Spanish). BSc thesis, Escuela de Ingenieria Informatica de Valladolid, Universidad de Valladolid, July 2025. Supervisors: D. Garcia, B. Pulido. Google Scholar
  18. Enrique H Ruspini. Numerical methods for fuzzy clustering. Information Sciences, 2(3):319-350, 1970. URL: https://doi.org/10.1016/S0020-0255(70)80056-1.
  19. Girish Kumar Singh et al. Induction machine drive condition monitoring and diagnostic research - A survey. Electric Power Systems Research, 64(2):145-158, 2003. Google Scholar
  20. George J Vachtsevanos, Frank Lewis, Michael Roemer, Andrew Hess, and Biqing Wu. Intelligent fault diagnosis and prognosis for engineering systems, volume 456. Wiley Online Library, 2006. Google Scholar
  21. Laurens van der Maaten and Geoffrey Hinton. Visualizing data using t-SNE. Journal of Machine Learning Research, 9(11):2579-2605, 2008. Google Scholar
  22. Z. Wang, W. Yan, and T. Oates. Time series classification from scratch with deep neural networks: A strong baseline. In 2017 International Joint Conference on Neural Networks (IJCNN), pages 1578-1585. IEEE, 2017. Google Scholar
  23. Shu-Xin Zhou. The practical applications of industry 4.0 technology to a new plant for both manufacturing technique and manufacturing process in new product introduction. IEEE Access, 9:149218-149226, 2021. URL: https://doi.org/10.1109/ACCESS.2021.3124373.
  24. Enrico Zio. Prognostics and health management of industrial equipment. Diagnostics and prognostics of engineering systems: methods and techniques, pages 333-356, 2013. Google Scholar
  25. Enrico Zio. Chapter 8 - Data-driven prognostics and health management (PHM) for predictive maintenance of industrial components and systems. In Curtis Lee Smith, Katya Le Blanc, and Diego Mandelli, editors, Risk-Informed Methods and Applications in Nuclear and Energy Engineering, pages 113-137. Academic Press, 2024. Google Scholar
Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2025 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact