The application feedback on existing silicon nitride ceramic bearings and RCF experimental research all indicate that the primary failure mode of silicon nitride ceramic bearings is material spalling on the contact surface. Spalling failure occurs due to the initiation and propagation of cracks under rolling contact. However, silicon nitride ceramic bearings, owing to their unique manufacturing method, inevitably exhibit defects and cracks. Therefore, as silicon nitride ceramic bearings are increasingly prevalent, reducing the probability of spalling failure is crucial for extending their service life. This can only be achieved by gaining a clear understanding of the crack initiation and expansion mechanisms in silicon nitride ceramic bearings. This paper is based on silicon nitride rolling friction experiments. It involves the joint simulation of Franc3D-V8.4 and ABAQUS2020, wherein the crack front SIFs are calculated for each load contact position of the surface crack on the silicon nitride ceramic bearing ring during cyclic movement. The study also delves into the determination of the maximum effective stress intensity factors and explores the influence of the initial crack depth on the cycle life and direction of crack propagation. The research yields several valuable conclusions. The findings of this research offer theoretical guidance for formulating grinding technologies for silicon nitride rings and adjusting and controlling working parameters of silicon nitride ceramic ball bearings. These insights are crucial for enhancing the reliability and longevity of silicon nitride ceramic bearings in practical applications.

As the operating conditions of rolling bearings become increasingly demanding, traditional steel bearings can no longer fully meet the performance requirements of critical equipment. Silicon nitride full ceramic ball bearings, with intrinsic properties such as a low thermal expansion coefficient, low density, corrosion resistance, and wear resistance, offer significant advantages in extreme temperatures, high-speed operation, and harsh corrosive environments. As a result, they have become a key technical solution for the core transmission systems of high-end equipment. However, the dynamic evolution of their service performance under varying operating conditions—such as load and speed—remains insufficiently understood. This study systematically investigates the service performance evolution mechanism of silicon nitride full ceramic ball bearings under self-lubrication conditions. The key findings will provide a theoretical foundation for optimizing and regulating performance under extreme operating conditions.

Accurate classification of spindle rotational errors is critical for ensuring machining precision and operational reliability of CNC machine tools. However, existing methods face challenges in extracting discriminative feature information from vibration signals due to small inter-class differences and complex electromechanical interference. This paper proposes a novel deep learning model, MFAFENet, based on multi-sensor collaboration and multi-scale feature information adaptive fusion. Vibration signals from three mounting positions are transformed into time-frequency information representations via Short-time Fourier Transform. The proposed network adaptively fuses multi-scale feature information from parallel branches with different kernel sizes through a branch attention mechanism. An efficient channel attention module is then incorporated to recalibrate channel-wise feature responses. The cross-entropy loss function is employed to optimize the network parameters during training. Experiments on a spindle reliability test bench demonstrate that MFAFENet achieves 93.37% average test accuracy, outperforming other comparative methods. Ablation and comparative studies confirm the effectiveness of each module and the clear advantage of adaptive fusion over fixed-weight multi-scale methods. Multi-sensor fusion further improves accuracy by 7.23% over the best single-sensor setup. The proposed method establishes an effective end-to-end mapping between vibration signals and rotational errors, providing a promising solution for high-precision spindle condition monitoring.

The rapid expansion of the low-altitude economy places unprecedented demands on the safety and reliability of unmanned aerial vehicles (UAVs). To address the limitations of single-modal feature extraction in capturing heterogeneous complementary information, this paper proposes a temporal and time–frequency dual-modality weighted fusion network (TTF-DWFNet) for UAV fault diagnosis. The proposed framework employs a parallel dual-branch architecture: a temporal modality branch utilizes a one-dimensional Transformer with a broadcast self-attention mechanism to model global temporal dependencies from raw vibration data, while a time–frequency modality branch transforms the data into spectrograms and leverages a two-dimensional convolutional neural network (CNN) to extract local texture features. Furthermore, an adaptive weighted fusion module is designed to automatically learn the discriminative contribution weights of the heterogeneous features at the channel level, enabling effective feature integration. Extensive experiments on two public datasets show that TTF-DWFNet achieves state-of-the-art accuracy of 96.47% and 92.76%, outperforming existing CNN-based and Transformer-based methods. The proposed TTF-DWFNet architecture has great practical application potential.

The widespread application of drones in complex environments imposes higher demands on flight safety. However, traditional anomaly detection methods often rely on mathematical models or large amounts of labeled samples, which makes them ill suited to address practical challenges such as unmanned aerial vehicle systems, which exhibit strong nonlinear characteristics, a scarcity of fault samples, and highly variable operating conditions. To overcome the above difficulties, this work puts forward a one-dimensional selective kernel convolutional autoencoder (1-D SKCAE) based on Bayesian optimization for unsupervised drone anomaly detection. Relying solely on normal operation data, this model achieves accurate anomaly identification by leveraging the sudden changes in reconstruction error. For the model architecture, this paper designs a multi-scale selective kernel convolution module and combines an attention mechanism to achieve adaptive feature weighting for various receptive fields. This method effectively improves the model’s ability to represent complex operational conditions and subtle fault characteristics. Simultaneously, Bayesian optimization is embedded into the model training process as a hyperparameter search strategy, enabling the adaptive configuration of key hyperparameters to further enhance detection performance. Extensive experiments were conducted using the RflyMAD simulation dataset and the 3DR Solo real flight dataset. The results demonstrate that the 1-D SKCAE outperforms multiple comparative models, exhibiting superior robustness particularly in complex scenarios such as mixed multi-fault superposition. This method enables drone anomaly detection without fault labels, showcasing strong potential for engineering applications.