# Real-Time Predictive Maintenance using Autoencoder Reconstruction and Anomaly Detection

arXiv: https://arxiv.org/abs/2110.01447 · HTML: https://mlsanity.com/paper/2110.01447/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 23 references that are in the map.
- First posted on arXiv 1 Oct 2021.

## Builds on (most cited first, 4 of 4)

- [Anomaly Detection using Autoencoders in High Performance Computing Systems](https://mlsanity.com/paper/1811.05269/) (2018)
- [A Survey of Predictive Maintenance: Systems, Purposes and Approaches](https://mlsanity.com/paper/1912.07383/) (2019)
- [Deep Learning and Its Applications to Machine Health Monitoring: A Survey](https://mlsanity.com/paper/1612.07640/) (2016)
- [A Stacked Autoencoder Neural Network based Automated Feature Extraction Method for Anomaly detection in On-line Condition Monitoring](https://mlsanity.com/paper/1810.08609/) (2018)

## Abstract (arXiv)

Rotary machine breakdown detection systems are outdated and dependent upon routine testing to discover faults. This is costly and often reactive in nature. Real-time monitoring offers a solution for detecting faults without the need for manual observation. However, manual interpretation for threshold anomaly detection is often subjective and varies between industrial experts. This approach is ridged and prone to a large number of false positives. To address this issue, we propose a Machine Learning (ML) approach to model normal working operation and detect anomalies. The approach extracts key features from signals representing known normal operation to model machine behaviour and automatically identify anomalies. The ML learns generalisations and generates thresholds based on fault severity. This provides engineers with a traffic light system were green is normal behaviour, amber is worrying and red signifies a machine fault. This scale allows engineers to undertake early intervention measures at the appropriate time. The approach is evaluated on windowed real machine sensor data to observe normal and abnormal behaviour. The results demonstrate that it is possible to detect anomalies within the amber range and raise alarms before machine failure.