scholarly journals Recurrent Neural Network based Soft Sensor for flow estimation in Liquid Rocket Engine Injector calibration

Author(s):  
Gilbert Chandra D. ◽  
Vinoth B. ◽  
Srinivasulu Reddy U. ◽  
Uma G. ◽  
Umapathy M.
2015 ◽  
Vol 727-728 ◽  
pp. 880-883
Author(s):  
Min Chao Huang ◽  
Bao Yu Xing

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.


2020 ◽  
Vol 57 (2) ◽  
pp. 391-397
Author(s):  
S. B. Verma ◽  
Oskar Haidn

2013 ◽  
Vol 26 (1) ◽  
pp. 169-175 ◽  
Author(s):  
Seong Min Jeon ◽  
Hyun Duck Kwak ◽  
Suk Hwan Yoon ◽  
Jinhan Kim

2002 ◽  
Vol 124 (2) ◽  
pp. 363-368 ◽  
Author(s):  
F. Laurant ◽  
D. W. Childs

Test results are presented for the rotordynamic coefficients of a hybrid bearing that is representative of bearings for liquid-rocket-engine turbopump applications. The bearing is tested in the following two degraded conditions: (a) one of five orifices plugged, and (b) a locally enlarged clearance to simulate a worn condition. Test data are presented at 24,600 rpm, with supply pressures of 4.0, 5.5, and 7.0 MPa, and eccentricity ratios from 0.1 to 0.5 in 0.1 increments. Overall, the results suggest that neither a single plugged orifice nor significant wear on the bearing land will “disable” a well-designed hybrid bearing. These results do not speak to multiple plugged orifices and are not an endorsement for operations without filters to prevent plugging orifices.


Sign in / Sign up

Export Citation Format

Share Document