The development of health monitoring technology for liquid rocket engines (LREs) can effectively improve the safety and reliability of launch vehicles, which has important theoretical and engineering significance. Therefore, we propose a fault detection and diagnosis (FDD) method for a large LOX/kerosene rocket engine based on long short-term memory (LSTM) and generative adversarial networks (GANs). Specifically, we first modeled a large LOX/kerosene rocket engine using MATLAB/Simulink and simulated the engine’s normal and fault operation states involving various startup and steady-state stages utilizing fault injection. Second, we created an LSTM-GAN model trained with normal operating data using LSTM as the generator and a multilayer perceptron (MLP) as the discriminator. Third, the test data were input into the discriminator to obtain the discrimination results and realize fault detection. Finally, the test data were input into the generator to obtain the predicted samples and calculate the absolute error between the predicted and the real value of each parameter. Then the fault diagnosis index, standardized absolute error (SAE), was constructed. SAE was analyzed to realize fault diagnosis. The simulated results highlight that the proposed method effectively detects faults in the startup and steady-state processes, and diagnoses the faults in the steady-state process without missing an alarm or being affected by false alarms. Compared with the conventional redline cut-off system (RCS), adaptive threshold algorithm (ATA), and support vector machine (SVM), the fault detection process of LSTM-GAN is more concise and more timely.
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.