Chenchen Wang

Aero-engine safety and prognostics and health management (PHM) rely on robust vibration-based fault diagnosis. However, many deep learning studies on rotating machinery are evaluated under random train–test splits that mix hardware instances and may obscure the domain shift faced in deployment. This paper presents a protocol-driven end-to-end baseline for multi-sensor aero-engine-relevant vibration diagnosis on the HIT inter-shaft bearing benchmark. Six synchronous vibration channels are segmented into fixed-length windows, standardized using source-domain statistics, and classified by a compact 1D CNN backbone with and without squeeze-and-excitation (SE) channel attention. A deeper ResNet1D baseline is further introduced to examine whether increasing backbone capacity improves cross-bearing generalization under the same source-only training protocol. We compare random segment-level splits with bearing-level cross-splits that hold out entire bearings as unseen target domains, and we report deployment-oriented indicators including balanced accuracy, false-alarm rate (FAR), and miss rate over five random seeds. Under random splits, the compact CNN baseline reaches near-ceiling test accuracy, confirming that the benchmark is readily separable under in-domain interpolation. In contrast, cross-bearing evaluation reveals severe degradation: in the representative split, the baseline CNN accuracy collapses to approximately 15% with near-zero normal-class recall, while ResNet1D improves fault sensitivity but still retains a high FAR above 88%. Additional cross-bearing permutations further show that this degradation is not attributable to a single unfavorable source–target split. These findings indicate that, under the tested source-only backbones and protocols, distribution mismatch is a dominant bottleneck for deployment-ready cross-bearing diagnosis. The results establish a reproducible baseline for protocol-driven evaluation in aero-engine PHM and motivate future work on domain adaptation, domain generalization, calibration, and sequential decision logic.

For highly maneuverable aircraft, the afterburning engine serves as a core and critical component. Due to the complex structure of the afterburner and the strong coupling among parameters, mechanism-based modeling of afterburning engines remains extremely challenging. To address this problem, this paper proposes a data-driven hybrid algorithm modeling framework for a light-duty afterburning turbojet engine. Using test-bench data from the TWP220L light-duty afterburning turbojet, two hybrid algorithm models were developed: (i) PSO-DNN and (ii) NGO-LSSVM. Four models, DNN, PSO-DNN, LSSVM, and NGO-LSSVM, were compared by mapping engine input parameters (altitude, Mach number, rotor speed, and fuel flow rate) to two key performance outputs (thrust and turbine pressure ratio). Based on visual error analysis and regression evaluation metrics, it was found that the optimized algorithm significantly reduced the prediction error. The NGO-LSSVM model achieved the highest accuracy in both performance indicators, increasing R² by 5.3% for thrust, and increasing R² by 6.8% for turbine pressure ratio. This framework offers a practical and high-precision approach for light-duty afterburning engine performance prediction and lays a foundation for the development of model-based and data-driven onboard control strategies.

During high-altitude simulation tests, the accurate reproduction of environmental conditions directly affects the ability to reliably evaluate the engine’s performance under simulated high-altitude conditions. Traditional physical models, though interpretable, often fall short in handling nonlinear dynamics and time-delayed effects caused by disturbances such as abrupt flow rate fluctuations. For this problem, this work proposes a novel hybrid modeling framework that integrates physical principles with deep learning architectures. The proposed approach incorporates three key innovations. First, a physics-guided residual learning scheme is introduced, where the theoretical outlet temperature derived from energy conservation laws and assumptions of symmetric inlet mixing serves as a prior, and a data-driven model corrects residual deviations. Second, a multiscale feature extraction module is constructed by combining a Transformer with DWT, capturing both long-term regularities and short-term fluctuations that often exhibit quasi-symmetric patterns in structured systems. Third, a perturbation-aware memory structure is designed, fusing a Transformer branch for long-term dependency modeling with an extended LSTM (xLSTM) branch for short-term dynamic sensitivity. The experimental results on real-world test datasets demonstrate that the proposed hybrid model significantly outperforms traditional physical models. Specifically, it achieves an MAPE of 0.0156 and a R² of 0.9867, indicating high predictive accuracy. The model not only achieves superior prediction accuracy but also preserves physical interpretability, making it a promising solution for intelligent control in industrial mixing systems.