Machine Learning for Enhanced CBM+
Abstract
The proposed program focuses first on developing autoencoders using normaloperating data for anomaly detection, while also recognizing the need for signal fault detection. Special attention will be given to exploring the effectiveness of the approach when applied to individual assets and to fleets. Next, transfer learning will be employed to extend the trained autoencoder models and their components to diagnostic capabilities. The diagnostics developed using autoencoders will be compared to the results of other traditional methods, such as physics based diagnostic classifiers. Furthermore, detection and isolation metrics will be utilized to determine the effectiveness of the autoencoder based diagnostic approach.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Aug 20, 2019
- Source ID
- N000141912600
Entities
People
- Michael Thurston
Organizations
- Office of Naval Research
- Rochester Institute of Technology
- United States Navy