Yafeng Shen

Online monitoring of rub-impact faults is essential for aero-engine safety, yet existing methods struggle with asynchronous multi-modal data, diverse sensor configurations, and the scarcity of reliable fault annotations. To address these challenges, this paper proposes RubNet, a domain generalization framework that first employs a physics-guided temporal alignment strategy to precisely align high-frequency vibration signals with low-frequency state parameters based on spectral centroid correlations. A multi-scale channel attention convolutional neural network is subsequently utilized to extract robust features, leveraging adversarial domain generalization to learn representations that remain invariant to shifts in sensor position and orientation. Furthermore, to mitigate label noise during temporal fine-tuning, the framework integrates an uncertainty-aware soft label aggregation mechanism that fuses conflicting annotations from human experts, vision language models, and pre-trained model predictions using the Dawid-Skene algorithm. Experimental validation on real-world ground test data demonstrates that RubNet achieves state-of-the-art performance with an F1-score of 93.26% and superior generalization capabilities across unseen sensor domains, while maintaining low computational complexity suitable for real-time deployment.

Aero engine surge diagnosis is a key technology in engine health management, and its diagnostic accuracy is of great significance for ensuring operational safety. Traditional threshold-based diagnostic methods are significantly affected by working conditions, which makes it difficult to achieve full working condition coverage. Moreover, due to issues such as varying feature thresholds across conditions, weak signal characteristics, and low identifiability, the diagnostic accuracy remains limited. To address these challenges, this paper proposes an STFF-CANet (Spatio-Temporal Feature Fusion Cross-Attentional Network) diagnosis model of aero engine surge based on spatio-temporal feature fusion. The model first employs a Convolutional Neural Network (CNN) to extract spatial features from the frequency domain of dynamic signals via Fast Fourier Transform (FFT). Simultaneously, a Bidirectional Long Short-Term Memory (BiLSTM) network is used to capture temporal features from signals optimized by Variational Mode Decomposition (VMD). A cross-attention mechanism is further introduced to achieve deep fusion of spatiotemporal features, thereby enhancing the capability to identify weak fault characteristics. In addition, the sliding window slice method is used to expand the sample size for the small sample fault data of the engine surge of an aero engine. This ensures both informational continuity between slices and statistical stability of features, effectively mitigating the difficulty of diagnosing early and weak surge characteristics under small-sample conditions. Experimental results demonstrate that the model achieves an F1-score, Recall, Precision, and Accuracy of 97.96%, 97.52%, 98.43%, and 99.01%, respectively, in surge fault classification. These outcomes meet the practical requirements for aero engine surge diagnosis and provide an effective solution for early fault warning in complex industrial equipment.

Sapphire Fabry-Perot interferometers are useful sensors for realizing high-precision strain measurement under ultrahigh temperature. The low fineness of sapphire Fabry-Perot cavities, due to the relatively low endface reflectivity, limits the accuracy of the cavity length demodulation and hence the strain measurement. Here we propose a multi-order optimal cavity length estimation algorithm to increase the demodulation accuracy of sapphire Fabry-Perot cavities especially under high temperature. The algorithm is designed to evaluate the optimal cavity length by exploiting all valleys in the reflection spectrum and to determine possible cavity lengths of each interference order, then obtaining the optimal cavity length with the minimum deviation between the valleys. Using the algorithm, the repeatability of the cavity length demodulation can reach 1 nm, corresponding to a strain measurement repeatability of 0.1 με. The zero-drift and the repeatability precision of the cavity demodulation is measured as 0.1% (FS) and higher than 0.5% (FS) respectively. As an application, the method is exploited on the thermal wind tunnel testing experiment. Results show that the strain measurement error is less than 5% (FS) at 1000 °C, fulfilling the requirements for strain monitoring of wind tunnel balances.

The health monitoring system has been the main technological approach to extending the life of gas turbine engines and reducing maintenance costs resulting from performance degradation caused by asymmetric factors like carbon deposition, damage, or deformation. One of the most critical techniques within the health monitoring system is performance degradation prediction. At present, most research on degradation prediction is carried out using NASA’s open dataset, C-MAPSS, without considering that monitoring measurements are not always available, as in the ideal dataset. This limitation makes fault diagnosis algorithms and remaining useful life prediction methods difficult to apply to real gas turbine engines. Therefore, to solve the problem of performance degradation prediction in light-duty gas turbine engines, a prediction diagram is proposed based on Long Short-Term Memory (LSTM). Various types of onboard signals are taken into consideration among the experimental data. Only accumulated usage time, total temperature and total pressure before the inlet, low-pressure rotor speed, high-pressure rotor speed, fuel flow rate, exhaust temperature, and thrust are used in the training process, which is indispensable for an aero-engine. A genetic algorithm (GA) is introduced into the training process to optimize the hyperparameters of LSTM. The performance degradation prediction modeled with the GA-LSTM method is validated using experimental data. The maximum prediction error of thrust is 70 daN, and the mean absolute percentage error (MAPE) is less than 0.04. This study provides a practical approach to implementing performance degradation prediction in health monitoring systems to improve gas turbine engine reliability, economy, and environmental performance.

Thermoacoustic oscillation is indeed a phenomenon characterized by the symmetric coupling of thermal and acoustic waves. This paper introduces a novel approach for monitoring and predicting thermoacoustic combustion instability using a combination of recurrence quantification analysis (RQA) and an optimized deep belief network (DBN). Six samples of combustion state data were collected using two distinct types of burners to facilitate the training and validation of GA-DBN. The proposed methodology leverages RQA to extract intricate patterns and dynamic features from time series data representing combustion behavior. By quantifying the recurrence plot of specific patterns, the analysis provides valuable insights into the underlying thermoacoustic dynamics. Among three different feature extraction methods, RQA stands out remarkably in performance. These RQA-derived features serve as input to a carefully tuned DBN, which is trained to learn the complex relationships within the combustion process. The classification accuracy of deep belief network optimized by genetic algorithm (GA-DBN) reached an impressive 99.8%. Subsequent multiple comparisons were conducted between GA-DBN, DBN, and support vector machine (SVM), revealing that GA-DBN consistently demonstrated satisfactory classification results. This method holds significant importance in monitoring intricate combustion states.

Lipid droplets (LDs) are dynamic lipid storage organelles that can sense and respond to changes in systemic energy balance. The size and number of LDs are controlled by complex and delicate mechanisms, among which, whether and which SNARE proteins mediate LD fusion, and the mechanisms governing this process remain poorly understood. Here we identified a SNARE complex, syntaxin 18 (STX18)–SNAP23–SEC22B, that is recruited to LDs to mediate LD fusion. STX18 targets LDs with its transmembrane domain spanning the phospholipid monolayer twice. STX18–SNAP23–SEC22B complex drives LD fusion in adiposome lipid mixing and content mixing in vitro assays. CIDEC/FSP27 directly binds STX18, SEC22B, and SNAP23, and promotes the lipid mixing of SNAREs-reconstituted adiposomes by promoting LD clustering. Knockdown of STX18 in mouse liver via AAV resulted in smaller liver and reduced LD size under high-fat diet conditions. All these results demonstrate a critical role of the SNARE complex STX18–SNAP23–SEC22B in LD fusion.