PHM

VAE for interval-values data.

This work proposes a compression-based approach for problems with limited labeled data.

This work proposes a novel Deep Learning model based on a Transformer encoder to accurately estimate degradation modes and early detect knee points.

This work proposes a method for developing equipment lifespan estimators that combine incomplete physical and numerical information.

This work proposes a methodology for developing deterioration models to estimate the remaining lifetime of a system using physics-informed learning (PIL).

This work proposes a method for designing simple models of the remaining lifetime of a system.

This work presents a novel approach for unsupervised anomaly detection based on word embeddings using time series data represented as text.

This work proposes a new methodology for opportunistic diagnosis using machine learning algorithms trained directly on photovoltaic battery charging data.

This work proposes a new methodology for opportunistic diagnosis using machine learning algorithms trained directly on photovoltaic battery charging data.

This work proposes a new representation of battery data as images, in order to leverage the use of well-established Convolutional Neural Networks for battery degradation diagnosis.

This work presents a model of the running resistance of a locomotive powered by liquefied natural gas.

This work presents an informed weak supervision methodology for learning the deterioration of a battery from charge and discharge data.

This work proposes a novel approach based on variational encoding to evaluate aircraft engine monitoring data.

This work presents RUL-RVE, a Python tool for the assessment of Remaining Useful Life (RUL) that can achieve remarkable forecast accuracy while providing an interpretable assessment.

This work presents a novel recurrent VAE-based framework for the assessment of Engine Health Monitoring (EHM) data in aircraft.