In recent years, the application scenarios of Unmanned Aerial Vehicles (UAVs) have become increasingly widespread. As core components of UAVs, rotor blades’ health status is directly related to flight safety. Aiming at issues such as insufficient feature extraction, weak noise resistance, and low diagnostic accuracy in the crack fault diagnosis of UAV rotor blades, this study proposes a one-dimensional deep network integrating multi-scale convolution, a multi-path residual module, BiLSTM, and a self-attention mechanism, referred to as 1dMC-MPR-SABinet. Taking the triaxial (X, Y, Z) vibration signals of rotor blades as input, the method integrates a multi-scale convolution module and a multi-path residual module, models the bidirectional temporal dependencies of signals through Bi-LSTM, and is combined with a self-attention mechanism to enhance the capture of subtle fault features. Meanwhile, it adopts the Northern Goshawk Optimization algorithm to optimize hyperparameters, thereby improving stability in noisy environments. Experiments are validated based on a self-collected fault vibration dataset, with precision, recall, and F1-score as evaluation metrics. The results show that the proposed model achieves a diagnostic accuracy of 99.37% under noise-free conditions without NGO-based hyperparameter optimization, representing a maximum improvement of 6.50% over the comparative models. Under a strong noisy condition with SNR = 1, the base model achieves 91.95% accuracy, while after NGO-based hyperparameter optimization, the model performance is further improved, with the precision, recall, and F1-score reaching 97.64%, 97.78%, and 97.01%, respectively. Ablation experiments and generalization experiments further verify the rationality and effectiveness of the proposed architecture.

As a core component of rotating machinery, bearing health status is directly related to the operational stability and safety of the equipment. In the field of bearing fault diagnosis, although vibration signals are commonly used as monitoring data sources, their contact-based acquisition method is susceptible to constraints imposed by installation conditions and hardware parameters. To address this issue, this paper proposes a non-contact diagnostic method based on acoustic signals and constructs the 1dCMPR-BiSEnet model. In this study, six bearing operating conditions are defined, covering typical failure modes such as inner-race, outer-race, and cage faults. On this basis, a bearing acoustic dataset is constructed. Relying on the collected acoustic data, fault diagnosis experiments are conducted with the proposed method. The experimental results reveal that the diagnostic accuracy of this method reaches 99.97% under different rotational speeds, with an average AUC of 1.0 and an average AP of 0.9996. It delivers better overall performance than comparative algorithms and presents satisfactory robustness under high-noise environments. Furthermore, verified by the University of Ottawa Bearing Dataset, the method achieves a generalization accuracy of 98.06% in vibration signal scenarios. The high accuracy of the proposed method demonstrates that this study can provide valuable insights for relevant research in the field.

Thermomechanical coupling effects significantly influence the dynamic response of flexible multibody systems operating in thermal environments. Accurate simulation using conventional projection-based reduced-order models remains challenging due to strong nonlinearity and the time-varying nature of thermal fields. This work proposes a projection-free sparse-solving framework for thermomechanical coupling dynamics. The elastic and thermal fields are represented using sparse POD coefficients, and the governing equations are directly sampled online without Galerkin projection. The sparse coefficients are recovered via l₁ norm optimization at each time step. To ensure stable recovery under thermal-mechanical coupling, a unit-norm tight frame-based preconditioner is introduced to reduce the coherence of the underdetermined system matrix. The proposed method is validated through three numerical examples. Results show that the method maintains stable accuracy over long-time simulations, reduces computational time by over 40%, and exhibits improved robustness compared with the discrete empirical interpolation method in thermomechanical coupling problems. The adaptive basis selection capability and the necessity of unit norm tight frame preconditioning are confirmed. The method offers an efficient and reliable alternative for thermomechanical multibody dynamics simulation.