计算机科学
变压器
人工智能
编码器
参数化复杂度
频道(广播)
模式识别(心理学)
特征(语言学)
计算机视觉
线性可变差动变压器
特征向量
标识符
特征提取
方位(导航)
钞票
工程类
电子工程
噪音(视频)
断层(地质)
故障检测与隔离
语音识别
状态监测
稳健性(进化)
背景噪声
机器学习
作者
Qian Gu,Chaoyang Weng,Wenbo Huang,Baochun Lu
出处
期刊:Journal of Computational Design and Engineering
[Oxford University Press]
日期:2026-09-16
卷期号:13 (10): 21-44
摘要
Reliable bearing fault diagnosis under variable operating conditions and severe noise remains challenging because empirically selected time-frequency front ends may produce degraded representations, while generic attention mechanisms lack explicit sensitivity to fault-related spectral structures. To address these limitations, this study proposes a robust cascaded framework termed window-transform synergistic spectro-temporal channel attention Vision Transformer (WT-STCA-ViT), which integrates a window-enhanced Fourier-based synchrosqueezing transform with an STCA-ViT. Specifically, a parameterized $\alpha {\rm{\text {-} exponential\, Kaiser {\!-\!} Blackman}}$ $(\alpha {\rm{ {\text{-}} EKB}})$ window family and a task-constrained parameter screening strategy are established to optimize spectral concentration and transient localization, mitigating energy spreading across noisy scenarios. The resulting high-resolution time-frequency maps are encoded using a pretrained ViT backbone and refined via the proposed frequency-axis-structure-aware STCA mechanism, which generates frequency-dependent channel weights to calibrate band-level features while suppressing noise-dominated and irrelevant feature responses. Furthermore, a lightweight post-Transformer encoder and low-rank adaptation adapters are coupled to achieve global token-level refinement and parameter-efficient optimization. Extensive benchmarks on the public Case Western Reserve University (CWRU) dataset and a self-built cylindrical roller bearing dataset demonstrate competitive diagnostic accuracy, improved weak-fault recognition, and stable feature separability, with computational cost analysis further confirming a favorable trade-off among diagnostic robustness, trainable-parameter efficiency, and potential for low-latency online deployment.
科研通智能强力驱动
Strongly Powered by AbleSci AI