arXiv subjects

K. Reyes

Publications and source records attributed to K. Reyes.

5 recordsLinked to original sources

arXiv2026

Assesing the Viability of Unsupervised Learning with Autoencoders for Predictive Maintenance in Helicopter Engines

Unplanned engine failures in helicopters can lead to severe operational disruptions, safety hazards, and costly repairs. To mitigate these risks, this study compares two predictive maintenance strategies for helicopter engines: a supervised classification pipeline and an unsupervised anomaly detection approach based on autoencoders (AEs). The supervised method relies on labelled examples of both normal and faulty behaviour, while the unsupervised approach learns a model of normal operation using only healthy engine data, flagging deviations as potential faults. Both methods are evaluated on a real-world dataset comprising labelled snapshots of helicopter engine telemetry. While supervised models demonstrate strong performance when annotated failures are available, the AE achieves effective detection without requiring fault labels, making it particularly well suited for settings where failure data are scarce or incomplete. The comparison highlights the practical trade-offs between accuracy, data availability, and deployment feasibility, and underscores the potential of unsupervised learning as a viable solution for early fault detection in aerospace applications.

cs.LG↗

arXiv2026

LSTM VS. Feed-Forward Autoencoders for Unsupervised Fault Detection in Hydraulic Pumps

Unplanned failures in industrial hydraulic pumps can halt production and incur substantial costs. We explore two unsupervised autoencoder (AE) schemes for early fault detection: a feed-forward model that analyses individual sensor snapshots and a Long Short-Term Memory (LSTM) model that captures short temporal windows. Both networks are trained only on healthy data drawn from a minute-level log of 52 sensor channels; evaluation uses a separate set that contains seven annotated fault intervals. Despite the absence of fault samples during training, the models achieve high reliability.

cs.LG↗

arXiv2026

Early Fault Detection on CMAPSS with Unsupervised LSTM Autoencoders

This paper introduces an unsupervised health-monitoring framework for turbofan engines that does not require run-to-failure labels. First, operating-condition effects in NASA CMAPSS sensor streams are removed via regression-based normalisation; then a Long Short-Term Memory (LSTM) autoencoder is trained only on the healthy portion of each trajectory. Persistent reconstruction error, estimated using an adaptive data-driven threshold, triggers real-time alerts without hand-tuned rules. Benchmark results show high recall and low false-alarm rates across multiple operating regimes, demonstrating that the method can be deployed quickly, scale to diverse fleets, and serve as a complementary early-warning layer to Remaining Useful Life models.

cs.LG↗

arXiv2021

Machine-Learning Enabled Search for The Next-Generation Catalyst for Hydrogen Evolution Reaction

The development of active catalysts for hydrogen evolution reaction (HER) made from low-cost materials constitutes a crucial challenge in the utilization of hydrogen energy. Earth-abundant molybdenum disulfide (MoS$_2$) has been discovered recently with good activity and stability for HER. In this report, we employed the hydrothermal technique for MoS$_2$ synthesis which is a cost-effective and environmentally friendly approach and has the potential for future mass production. To investigate the structure-property relationship, scanning electron microscope (SEM), transmission electron microscope (TEM), X-ray diffraction (XRD), Raman spectroscopy, X-ray photoelectron spectroscopy (XPS), and various electrochemical characterizations have been conducted. A strong correlation between the material structure and the HER performance has been observed. Moreover, machine-learning (ML) techniques were built and subsequently used within a Bayesian Optimization framework to validate the optimal parameter combinations for synthesizing high-quality MoS$_2$ catalyst within the limited parameter space. The model will be able to guide the wet chemical synthesis of MoS$_2$ and produce the most effective HER catalyst eventually.

cond-mat.mtrl-sci↗

arXiv2016

The Latin American Giant Observatory: Contributions to the 34th International Cosmic Ray Conference (ICRC 2015)

The Latin American Giant Observatory (LAGO) is an extended cosmic ray observatory composed by a network of water-Cherenkov detectors spanning over different sites located at significantly different altitudes (from sea level up to more than $5000$\,m a.s.l.) and latitudes across Latin America, covering a huge range of geomagnetic rigidity cut-offs and atmospheric absorption/reaction levels. This detection network is designed to measure the temporal evolution of the radiation flux at ground level with extreme detail. The LAGO project is mainly oriented to perform basic research in three branches: high energy phenomena, space weather and atmospheric radiation at ground level. LAGO is built and operated by the LAGO Collaboration, a non-centralized collaborative union of more than 30 institutions from ten countries. These are the contributions of the LAGO Collaboration to the 34th International Cosmic Ray Conference, 30 July - 6 August 2015, The Hague, The Netherlands

astro-ph.IM↗