LSTM VS. Feed-Forward Autoencoders for Unsupervised Fault Detection in Hydraulic Pumps
By: P. Sánchez , K. Reyes , B. Radu and more
Potential Business Impact:
Finds broken machines before they stop working.
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.
Similar Papers
Early Fault Detection on CMAPSS with Unsupervised LSTM Autoencoders
Machine Learning (CS)
Finds engine problems before they happen.
Assesing the Viability of Unsupervised Learning with Autoencoders for Predictive Maintenance in Helicopter Engines
Machine Learning (CS)
Finds engine problems before they happen.
A Physics-Aware Attention LSTM Autoencoder for Early Fault Diagnosis of Battery Systems
Systems and Control
Finds battery problems early, before they cause trouble.