Real-Time Predictive Maintenance using Autoencoder Reconstruction and Anomaly Detection
This provides a real-time predictive maintenance solution for industrial engineers, though it is incremental as it applies existing autoencoder and anomaly detection methods to a specific domain.
The paper tackles the problem of reactive and costly rotary machine breakdown detection by proposing a machine learning approach that models normal operation and detects anomalies in real-time, demonstrating the ability to detect anomalies within an 'amber' warning range and raise alarms before machine failure.
Rotary machine breakdown detection systems are outdated and dependent upon routine testing to discover faults.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.