Data-Driven Research on Health Monitoring Algorithms for the Liquid Rocket Engine

被引：0

作者：

Liu Z. ^{[1
]}

Wu Y. ^{[2
]}

Wang G. ^{[1
]}

Li C. ^{[1
]}

Wang S. ^{[2
]}

Chen H. ^{[2
]}

机构：

[1] Beijing Institute of Astronautical Systems Engineering, Beijing

[2] School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai

来源：

Hsi-An Chiao Tung Ta Hsueh/Journal of Xi'an Jiaotong University | 2024年 / 58卷 / 04期

关键词：

data-driven; fault detection; health monitoring; liquid rocket engine;

D O I：

10.7652/xjtuxb202404017

中图分类号：

学科分类号：

摘要：

Regarding the difficulty in identifying and locating faults such as the root fracture of the oxygen rotor of the rocket engine and cracks at the joint of the shaft disk, fault detection and mode discrimination at the data level are conducted based on the test data of a certain liquid rocket engine through machine learning, data analysis, and other methods while bypassing the internal complex physical mechanism. For fault detection, two fault detection algorithms respectively applicable to fast-variable data and slow-variable data are proposed, which can process rocket engine data under various working conditions and achieve high accuracy rates of 84. 2% and 94. 9% respectively after testing. For fault mode discrimination, a clustering algorithm based on the sliding window is presented, which can realize the distinction of different fault modes, and the recognition accuracy of the two fault modes can reach 86. 2% and 95. 5% respectively. The abnormal frequency interval of vibration data corresponding to the two fault modes is given, thus providing related clues for relevant researchers. © 2024 Xi'an Jiaotong University. All rights reserved.

引用

页码：182 / 191

页数：9

共 25 条

[1]

ZENG Ruilin, WANG Guan, WANG Xiaoyu, Research on rocket nozzle polarity automatic identification system improvement, Astronautical Systems Engineering Technology, 6, 6, pp. 52-61, (2022)

[2]

MA Juntian, ZHANG Suming, YAN Xiaotao, Research on feature extraction and remaining useful life prediction for mechanical vibration signal based on image recognition, Astronautical Systems Engineering Technology, 5, 4, pp. 33-42, (2021)

[3]

CHEN Xi, LIAO Mingfu, WANG Yankai, Investigation of aeroengine fault fusion diagnosis, Aeroengine, 39, 4, pp. 78-84, (2013)

[4]

KONAR P, CHATTOPADHYAY P., Bearing fault detection of induction motor using wavelet and support vector machines, Applied Soft Computing, 6, pp. 4203-4211

[5]

SHARMA R K, SUGUMARAN V, KUMAR H, ct al, A comparative study of naive Baycs classifier and Baycs net classifier for fault diagnosis of roller bearing using sound signal, International Journal of Decision Support Systems, 1, 1, pp. 115-129, (2015)

[6]

MBO'OCP, HAMEYER K., Fault diagnosis of bearing damage by means of the linear discriminant analysis of stator current features from the frequency selection [J], IEEE Transactions on Industry Applications, 52, 5, pp. 3861-3868, (2016)

[7]

ZHAO Yongping, SONG Fangquan, PAN Yingting, Retargeting extreme learning machines for classification and their applications to fault diagnosis of aircraft engine, Aerospace Science and Technology, 71, pp. 603-618, (2017)

[8]

LI Bing, ZHAO Yongping, Group reduced kernel extreme learning machine for fault diagnosis of aircraft engine, Engineering Applications of Artificial Intelligence, 96, (2020)

[9]

PANDYA D H, UPADHYAY S H, HARSHA S P., Fault diagnosis of rolling clement bearing with intrinsic mode function of acoustic emission data using APF-KNN, Expert Systems with Applications, 40, 10, pp. 4137-4145, (2013)

[10]

PAN Haiyang, YANG Yu, ZHENG Jindc, ct al, A fault diagnosis approach for roller bearing based on symplcctic geometry matrix machine, Mechanism and Machine Theory, 140, pp. 31-43, (2019)

← 1 2 3 →