Fault detection and diagnosis for liquid rocket engines with sample imbalance based on Wasserstein generative adversarial nets and multilayer perceptron

Abstract

The reliability of liquid rocket engines (LREs), which are the main propulsion device of launch vehicles, cannot be overemphasised. The development of fault detection and diagnosis (FDD) technology for LREs can effectively improve the safety and reliability of launch vehicles, which has important theoretical and engineering significance. With the rapid development of artificial intelligence technologies such as machine learning and artificial neural network, data-driven FDD methods have gained increasing attention. However, the scarcity of engine fault samples limits the application of this methods. We proposed a method combining Wasserstein generative adversarial nets (WGANs) and multilayer perceptron (MLP) to perform FDD for LREs with sample imbalance. Wasserstein generative adversarial nets were trained using the fault data from the actual hot-firing ground test of a large LRE. Considerable fault data were generated to expand the data set to balance the ratio of positive and negative samples. Subsequently, the expanded data set was used to train the MLP for FDD of a large LRE. The results showed that the samples generated by the WGAN were authentic, confirming the application of the proposed method as a novel and effective tool for establishing a complete LRE fault database. Furthermore, the diagnosis times of the proposed method on five fault tests were advanced by 0.66, 15.82, 0.24, 0.14 and 1.08 s in relation to those of the conventional red-line cut-off system. Compared with support vector machine and adaptive threshold algorithm, the proposed method also performed better.

Keywords

liquid rocket engine sample imbalance fault detection and diagnosis Wasserstein generative adversarial nets multilayer perceptron

Get full access to this article

View all access options for this article.

References

Donati . Infusion of innovative technologies for mission operations. Acta Astronautica 2010; 67: 1132–1137.

. Liquid-propellant rocket engines health-monitoring—a survey. Acta Astronautica 2005; 56: 347–356.

Xie

Liu

Ding

, et al. Implementation of fault detection and alarm system based on ATA algorithm in liquid rocket engine. J Rocket Propulsion 2005; 31(6): 19–22.

Tejwani

Dyke

Bircher

. Approach to SSME Health Monitoring III. Exhaust Plume Emission Spectroscopy: Recent Results and Detailed Analysis. AIAA; 1993.

Hawman

. Health Monitoring System for the SSME – Program Overview. AIAA; 1990.

Cha

Park

, et al. Fault detection and diagnosis algorithms for transient state of an open-cycle liquid rocket engine using nonlinear Kalman filter methods, Acta Astronautica 2019; 163: 147–156.

Wheeler

Dhawan

Meyer

. SSME Sensor Modeling Using Radial Basis Function Neural Networks. AIAA; 1994.

Park

Ahn

. Deep neural network approach for fault detection and diagnosis during startup transient of liquid-propellant rocket engine. Acta Astronautica 2020; 177: 714-730.

Zhu

Cheng

, et al. Steady-state process fault detection for liquid rocket engines based on convolutional auto-encoder and one-class SVM. IEEE Access 2020; 8: 3144–3158.

10.

Goodfellow

Pouget

Mirza

, et al. Generative adversarial nets. Adv Neural Inf Process Syst 2014; 27.

11.

Zhang

Tang

Xie

, et al. Generative adversarial network-based image-level optimal setpoint calculation for flotation reagents control. Expert Syst Appl 2022; 197: 116790.

12.

Shi

. Imputing missing indoor air quality data with inverse mapping generative adversarial network. Building Environ 2022; 215: 108896.

13.

Wang

, et al. Framework of nacelle inverse design method based on improved generative adversarial networks. Aerospace Sci Technol 2022; 121: 107365.

14.

Liu

Al-Shehari

Zhang

. Attention mechanism enhancement algorithm based on cycle consistent generative adversarial networks for single image dehazing. J Vis Commun Image R 2022; 83: 103434.

15.

Wang

. An intelligent diagnosis scheme based on generative adversarial learning deep neural networks and its application to planetary gearbox fault pattern recognition. Neurocomputing 2018; 310: 213–222.

16.

Han

Liu

Yang

, et al. A novel adversarial learning framework in deep convolutional neural network for intelligent diagnosis of mechanical faults. Knowledge-Based Syst 2019; 165: 474–487.

17.

Shao

Wang

Yan

. Generative adversarial networks for data augmentation in machine fault diagnosis. Comput Industry 2019; 106: 85–93.

18.

Zhang

. Predicting pipeline leakage in petrochemical system through GAN and LSTM. Knowledge-Based Syst 2019; 175: 50–61.

19.

Liu

Jiang

et al. Data synthesis using deep feature enhanced generative adversarial networks for rolling bearing imbalanced fault diagnosis. Mech Syst Signal Process 2022; 163: 108139.

20.

Wang

Zhang

, et al. Diagnosis of inter-turn short circuit of permanent magnet synchronous motor based on deep learning and small fault samples. Neurocomputing 2021; 442: 348–358.

21.

Kingma

. Adam: A method for Stochastic Optimization. 2015.

22.

Wang

Zhang

, et al. Deep learning for smart manufacturing: methods and applications. J Manuf Syst 2018.

23.

Goodfellow

Bengio

Courville

. Deep Learning. Cambridge, MA: The MIT Press; 2016.

24.

Hinton

Srivastava

Krizhevsky

, et al. Improving neural networks by preventing co-adaptation of feature detectors. Computer Sci 2012; 3(4): 212–223.

25.

Arjovsky

Chintala

Bottou

, et al. International Conference on Machine Learning; 2017.

26.

Rubner

Tomasi

Guibas

. The earth mover’s distance as a metric for image retrieval. Int J Comp Vis 2000; 40(2): 99–121.

27.

Gretton

Borgwardt

Rasch

, et al. A kernel two-sample test. J Machine Learn Res 2012; 13: 723–773.

28.

Liang

. Data Mining Algorithm and Application. Peking University Press; 2006.

29.

Aksoy

Haralick

. Feature normalization and likelihood-based similarity measures for image retrieval. Pattern Recognit Lett 2001; 22(5): 563–582.

30.

Deng

Cheng

Shi

. Fault detection and diagnosis for liquid rocket engines based on long short-term memory and generative adversarial networks. Aerospace 2022; 9: 399.