Most existing fault diagnosis methods, although capable of extracting interpretable features such as attention-weighted fault-related frequencies, remain essentially black-box models that provide only classification results without transparent reasoning or diagnostic justification, limiting users’ ability to understand and trust diagnostic outcomes. In this work, we present a novel, interpretable fault diagnosis framework that integrates spectral feature extraction with large language models (LLMs). Vibration signals are first transformed into spectral representations using Hilbert- and Fourier-based encoders to highlight key frequencies and amplitudes. A channel attention-augmented convolutional neural network provides an initial fault type prediction. Subsequently, structured information—including operating conditions, spectral features, and CNN outputs—is fed into a fine-tuned enhanced LLM, which delivers both an accurate diagnosis and a transparent reasoning process. Experiments demonstrate that our framework achieves high diagnostic performance while substantially improving interpretability, making advanced fault diagnosis accessible to non-expert users in industrial settings.

Accurate fault diagnosis in aerospace transmission systems is essential for ensuring equipment reliability and operational safety, especially for aero-engine bearings. However, current approaches relying on Convolutional Neural Networks (CNNs) for Euclidean data and Graph Convolutional Networks (GCNs) for non-Euclidean structures struggle to simultaneously capture heterogeneous data properties and complex spatio-temporal dependencies. To address these limitations, we propose a novel Spatial–Temporal Hypergraph Fault Diagnosis framework (STHFD). Unlike conventional graphs that model pairwise relations, STHFD employs hypergraphs to represent high-order spatial–temporal correlations more effectively. Specifically, it constructs distinct spatial and temporal hyperedges to capture multi-scale relationships among fault signals. A type-aware hypergraph learning strategy is then applied to encode these correlations into discriminative embeddings. Extensive experiments on aerospace fault datasets demonstrate that STHFD achieves superior classification performance compared to state-of-the-art diagnostic models, highlighting its potential for enhancing intelligent fault detection in complex aerospace systems.

In this paper, a miniaturized cavity filter with wide-stopband and wide-passband is proposed. Because of the bended stub-loaded resonator (BSLR), the proposed cavity filter successfully excites three TEM modes, namely TEM-I, TEM-II and TEM-III. The low-frequency transmission zero (LFTZ) is generated by the lateral probe, and the high-frequency transmission zero (HFTZ) is generated by the lateral stub. The lateral metal cylinder can concentrate the electric field of the stray mode, leading to a high suppression level. The asymmetric vertical arrangement of the probes can suppress the fundamental TE101 mode and several high-order modes. Therefore, a stopband with a bandwidth of 2.02 times the center frequency is formed. The proposed cavity filter has a bandwidth of 42% and an electrical size of 0.26λg×0.25λg×0.22λg. It has several advantages applied to the 5G communication system.

Fault diagnosis across sensor locations becomes difficult when vibration measurements contain strong noise and only a few labeled target samples are available. This study develops an Attention Mask-guided Optimal Transport (AM-OT) framework for this setting. A wide-kernel multi-scale network with channel attention extracts vibration representations, while supervised noise-contrastive pretraining encourages class discrimination across noise perturbations. During target adaptation, a joint source–target attention mask reweights feature differences in the optimal transport cost, reducing the influence of low-weight channels on alignment. In experiments using measured CWRU bearing signals from three sensor locations with controlled Gaussian noise, the reported five-shot comparison achieves an average accuracy of 71.40% across six spatial transfer tasks using 20 labeled target windows, or 0.5% of the target domain. These results demonstrate the effectiveness of AM-OT for few-shot cross-sensor diagnosis on the noisy CWRU benchmark.