2026-07-24T05:17:04Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:24795 2026-02-09T07:47:26Z ddc:004 open_access

Towards Predictive Maintenance in an Aluminum Die-Casting Process Using Deep Learning Clustering and Dimensionality Reduction Cubero, Miguel Jiménez, Luis Ignacio López, Daniel Pulido, Belarmino Alonso-González, Carlos Prognostics Deep Learning Clustering UMAP LOWESS regression 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. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Miguel Cubero and Luis Ignacio Jiménez and Daniel López and Belarmino Pulido and Carlos Alonso-González 2025 Is Part Of OASIcs, Volume 136, 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/OASIcs.DX.2025.6 urn:nbn:de:0030-drops-247951 https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2025.6 eng https://creativecommons.org/licenses/by/4.0/legalcode