Rare events prediction in complex technical systems has been very interesting and critical issue for many industrial and commercial fields due to huge increase of sensors and rapid growth of Internet of Things (IoT). To detect anomalies and foresee machine failure during normal operation, various types of Predictive Maintenance (PdM) techniques have been studied. Among these techniques, unsupervised anomaly detection methods for multi-dimensional data set would be of more interest in many practical cases. So, in this demo, I have selected following three typical methods.
1. Htelling's T-square method
2. Gaussian mixture model
3. One-class SVM
To emulate a realistic situation, in this demo, I will use the dataset provided by C-MAPSST (Commercial Modular Aero-Propulsion SystemSimulation) [1, 2].
 A. Saxena, K. Goebel, D. Simon and N. Eklund, "Damage Propagation Modeling for Aircraft Engine Run-to-Failure Simulation," International Conference on Prognostics and Health Management, (2008).
 Turbofan Engine Degradation Simulation Data Set, https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/#turbofan
Akira Agata (2021). Demo Files for Predictive Maintenance (https://www.mathworks.com/matlabcentral/fileexchange/63012-demo-files-for-predictive-maintenance), MATLAB Central File Exchange. Retrieved .
MATLAB Release Compatibility
Platform CompatibilityWindows macOS Linux
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!Start Hunting!