Title :
Study on Threshold Based on Cluster Mean
Author :
Xue, Yang ; Chunpeng, Jia ; Anyuan, Yang
Author_Institution :
Aviation Machine Eng. Dept., First Aeronaut. Coll. of Air Force, Xinyang, China
Abstract :
The threshold value of the monitoring system has a great influence on the reliability of the monitoring system. To determine the threshold value of the monitoring system for liquid rocket engine (LRE) operating condition, the cluster analysis method is used to analyze the test data of the LRE ground test, and put forth the method using the cluster mean to determine the threshold. The determined thresholds are verified off-line by the ground test data for LRE. The verify results show that: The monitoring system using the threshold based on cluster mean can monitor well and truly the LRE operating condition in time, and detect the abnormal parameters of the engine with high reliability and effectiveness for the ground test data. The threshold algorithm based on cluster mean is simple, reliable and can be easily repotted to other monitoring objects, and has good application prospects.
Keywords :
condition monitoring; reliability; rocket engines; LRE; application prospects; cluster analysis method; cluster mean threshold; liquid rocket engine; monitoring system; Automation; Computerized monitoring; Condition monitoring; Engines; Euclidean distance; Machine intelligence; Military computing; Pattern analysis; Rockets; System testing; cluster analysis; liquid rocket engine; the monitoring system; threshold;
Conference_Titel :
Intelligent Computation Technology and Automation (ICICTA), 2010 International Conference on
Conference_Location :
Changsha
Print_ISBN :
978-1-4244-7279-6
Electronic_ISBN :
978-1-4244-7280-2
DOI :
10.1109/ICICTA.2010.699
