LRE Fault Detection and Isolation Based on Fuzzy Direction Neural Network

2015 ◽  
Vol 727-728 ◽  
pp. 880-883
Author(s):  
Min Chao Huang ◽  
Bao Yu Xing
Keyword(s):  
Neural Network ◽  
Fault Detection ◽  
Fuzzy Sets ◽  
Fuzzy Set ◽  
Rocket Engine ◽  
Fault Detection And Isolation ◽  
Liquid Rocket Engine ◽  
Direction Vector ◽  
Liquid Rocket ◽  
Turbo Pump

A fuzzy directions neural network used for fault detection and isolation (FDI) of a liquid rocket engine (LRE) is presented in this paper. Neural network utilizes fuzzy sets as engine fault classes. Each fuzzy set is an aggregate of fuzzy direction bodies. A fuzzy direction body is described by a direction vector, an included angle and two radii. FDI simulation of the turbo-pump fed liquid rocket engine demonstrates the strong qualities of the fuzzy direction neural network.

Failure Analysis of Ball-Bearing of Turbo-Pump Used in Liquid Rocket Engine

2015 ◽  
Vol 830-831 ◽  
pp. 709-712 ◽  
Author(s):  
Venkateswarlu Vartha ◽  
M.S. Arun Kumar ◽  
Saxon Mathew ◽  
Rajan Aneesh ◽  
John Bejoy ◽  
...  
Keyword(s):  
Failure Analysis ◽  
Ball Bearing ◽  
Rocket Engine ◽  
Operating Conditions ◽  
Rolling Contact ◽  
Liquid Rocket Engine ◽  
Bearing Failure ◽  
Deep Groove ◽  
Liquid Rocket ◽  
Turbo Pump

Rolling contact bearings often referred as antifriction bearings are found in many applications where rotating components are involved. Extreme operating conditions, counterfeit or inferior quality bearings, inadequate lubrication, etc often lead to bearing failures. Each rolling contact bearing failure leaves traces of evidences on what caused its failure. Failure analysis of one such bearing is the subject of this paper.One of the engine ground tests was aborted due to the failure of a self-aligning deep groove ball bearing used in turbo-pump of a liquid rocket engine. Series of engine ground tests are conducted as a part of injector acceptance for a liquid rocket engine. The bearing failure occurred in the seventh engine test of one of such series of ground tests. The bearing mentioned here is made of SAE 52100 steel. Post-test hardware inspection revealed that the bearing and the dynamic seals on either side of the bearing are in failed condition. Inner race of bearing was found blackish in appearance with indentation and corrosion marks. Localized black spots were observed in outer race. Bearing balls were found in deformed condition. The paper highlights the failure analysis of the bearing, root cause of the bearing failure and recommendations to avoid such failures.

scholarly journals Oxygen-hidrogen liquid rocket engine using turbo-pump developed for aviation hidrogen liquid two-spool turbo-jet

2014 ◽  
pp. 302-306
Author(s):  
A. I. Ivanov ◽  
V. A. Borisov
Keyword(s):  
Gas Turbine ◽  
Rocket Engine ◽  
Gas Turbine Engine ◽  
Liquid Rocket Engine ◽  
Rocket Engines ◽  
Turbine Engine ◽  
Aircraft Gas Turbine Engine ◽  
Liquid Rocket ◽  
Turbo Pump

The possibility of using in small trust rocket engines hydrogen turbopump unit developed for aircraft gas turbine engine is considered.

scholarly journals A Method for Real-Time Fault Detection of Liquid Rocket Engine Based on Adaptive Genetic Algorithm Optimizing Back Propagation Neural Network

Sensors ◽  
2021 ◽  
Vol 21 (15) ◽  
pp. 5026
Author(s):  
Huahuang Yu ◽  
Tao Wang
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Fault Detection ◽  
Real Time ◽  
Bp Neural Network ◽  
Rocket Engine ◽  
Back Propagation ◽  
Liquid Oxygen ◽  
Adaptive Genetic Algorithm ◽  
Liquid Rocket

A real-time fault diagnosis method utilizing an adaptive genetic algorithm to optimize a back propagation (BP) neural network is intended to achieve real-time fault detection of a liquid rocket engine (LRE). In this paper, the authors employ an adaptive genetic algorithm to optimize a BP neural network, produce real-time predictions regarding sensor data, compare the projected value to the actual data collected, and determine whether the engine is malfunctioning using a threshold judgment mechanism. The proposed fault detection method is simulated and verified using data from a certain type of liquid hydrogen and liquid oxygen rocket engine. The experiment results show that this method can effectively diagnose this liquid hydrogen and liquid oxygen rocket engine in real-time. The proposed method has higher system sensitivity and robustness compared with the results obtained from a single BP neural network model and a BP neural network model optimized by a traditional genetic algorithm (GA), and the method has engineering application value.

Sign in / Sign up

Export Citation Format

Share Document