Real-time online unstart prediction of supersonic inlet based on pressure fluctuations

Abstract

Supersonic inlet unstart prediction is one of the most critical components in supersonic flight technology, because inlet unstart may cause unexpected damage to the engine. However, due to the nonlinear and nonstationary property of pressure signals, effective supersonic inlet unstart prediction based on pressure signals remains a challenging problem. In this paper, change-point detection (CD), wavelet packet transform (WPT), and deep learning (DL) are combined to realize real-time online unstart prediction for supersonic inlet. The combination of the water cycle algorithm (WCA) and penalized contrast change-point detection (PCCD) will accurately divide the signal into two different flow states based on global characteristics, providing a reliable dataset for training the subsequent convolutional neural network (CNN). Then, a novel network named WPT-CNN is applied and it will take pressure signals as input to implement time-frequency domain feature extraction. To improve the accuracy of the classification model, a multi-channel unstart prediction model is proposed, which can simultaneously receive real-time pressure from multiple sensors to obtain detailed information inside the supersonic inlet. Results indicate that WCA-PCCD and multi-channel model can achieve better real-time online unstart prediction in comparison with other change-point detection algorithms and single-channel model.