Abstract The sensor selection for leak detection and diagnosis in a reusable liquid rocket engine was studied. Sufficient amounts of normal and leaked training data were generated by Monte Carlo simulations considering variations in system conditions based on past firing test results. A multivariate supervised analysis, in which measurements are linearly projected onto a vector that characterizes the difference between distributions of normal and leaked cases, successfully detected the simulated leaks that could not be detected by conventional univariate red-line judgment and unsupervised principal component analysis. Significant sensors for leak detection were selected using the greedy approach based on the detection performance score. It was found that only 11 of the 27 sensors were sufficient to maintain the detection performance.
Highlights Effective sensor set for propellant leak detection in rocket engines was identified. Training data with realistic system variation was generated by Monte Carlo simulation. Leak detection through supervised linear transformation was demonstrated. Greedy approach on the detection performance was employed for the optimization.
Model-based supervised sensor placement optimization to detect propellant leak in a liquid rocket engine
Acta Astronautica ; 195 ; 234-242
2022-02-15
9 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Advanced Performance, Liquid Propellant, Rocket Engine
AIAA | 2005
|Liquid-Propellant Rocket Engine Injector Dynamics
British Library Conference Proceedings | 1998
|Propellant Injector Influence on Liquid-Propellant Rocket Engine Instability
Online Contents | 2015
|Liquid-Propellant Rocket Engine Injector Dynamics
AIAA | 1998
|