Machine Learning for Rocket Propulsion Health Monitoring
نویسنده
چکیده
This paper describes the initial results of applying two machine-learning-based unsupervised anomaly detection algorithms, Orca and GritBot, to data from two rocket propulsion testbeds. The first testbed uses historical data from the Space Shuttle Main Engine. The second testbed uses data from an experimental rocket engine test stand located at NASA Stennis Space Center. The paper describes four candidate anomalies detected by the two algorithms.
منابع مشابه
Unsupervised Anomaly Detection for Liquid-Fueled Rocket Propulsion Health Monitoring
This article describes the results of applying four unsupervised anomaly detection algorithms to data from two rocket propulsion testbeds. The first testbed uses historical data from the Space Shuttle Main Engine. The second testbed uses data from an experimental rocket engine test stand located at NASA Stennis Space Center. The article describes nine anomalies detected by the four algorithms. ...
متن کاملHealth Management Issues and Strategy for Air Force Missiles ( POSTPRINT )
As so-called “wooden rounds”, which are intended to sit stably in storage for extended periods and then function precisely as desired, at a moment’s notice, Air Force missiles would appear to be an ideal application for health monitoring. However, solid rocket motors that serve as the propulsion system for these missiles present a number of unique challenges for the development of integrated ve...
متن کاملTitle: Health Management Issues and Strategy for Air Force Missiles
As so-called “wooden rounds”, which are intended to sit stably in storage for extended periods and then function precisely as desired, at a moment’s notice, Air Force missiles would appear to be an ideal application for health monitoring. However, solid rocket motors that serve as the propulsion system for these missiles present a number of unique challenges for the development of integrated ve...
متن کاملRPA: Design Tool for Liquid Rocket Engine Analysis
RPA (Rocket Propulsion Analysis) is a design tool for the performance prediction of the liquidpropellant rocket engines. RPA is written in Java and can be used under any operating system that has installed Java Runtime Environment (e.g. Mac OS ® X, Sun SolarisTM, MS WindowsTM, any Linux etc). The tool can be used either as a standalone GUI application or as an object-oriented library. This docu...
متن کاملHybrid Rocket Propulsion Technology for Sounding Rocket Development
Hybrid combustion technology has recently been employed in the sounding rocket developments to support the science experiments of academic applications and the establishment of a viable flight test platform for space components development. Due to its safety nature in material handling and combustion processes, hybrid rockets are suitable for university and research institute environments for a...
متن کامل