Machine Learning Algorithms for HUMS Improvement on Rotorcraft Components

The US Army Condition Based Maintenance program collects data from Health and Usage Monitoring Systems, Flight Data Recorders, Maintenance Records, and Reliability Databases. These data sources are not integrated, but decisions regarding the health of aircraft components are dependent upon the information stored within them. The Army has begun an effort to bring these data sources together using Machine Learning algorithms. Two prototypes will be built using decision-making machines: one for an engine output gearbox and another for a turbo-shaft engine. This paper will discuss the development of these prototypes and provide the path forward for implementation. The importance of determining applicable error penalty methods for machine learning algorithms for aerospace applications is explored. The foundations on which the applicable dataset is built are also explored, showing the importance of cleaning disparate datasets. The assumptions necessary to generate the dataset for learning are documented. The dataset is built and ready for unsupervised and supervised learning techniques to be applied.