Early Fault Detection on CMAPSS with Unsupervised LSTM Autoencoders

TL;DR

This paper presents an unsupervised LSTM autoencoder approach for early fault detection in turbofan engines using CMAPSS data, enabling real-time alerts without labeled failure data.

Contribution

It introduces a novel unsupervised framework that normalizes sensor data and detects faults via reconstruction error, eliminating the need for run-to-failure labels.

Findings

High recall in fault detection across regimes

Low false-alarm rates demonstrated

Scalable and deployable in real-time systems

Abstract

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.