Fractional-Order-Enhanced Dual-View Representation and VibrMamba–VMamba Collaborative Modeling for Gearbox Fault Diagnosis

Gearbox fault diagnosis under controlled bench-test conditions with known speed variations and noise interference remains challenging because nonstationarity, background noise, and operating-condition fluctuations can easily submerge weak localized fault features. To address this issue, this study proposes a fault diagnosis method based on a fractional-order-enhanced dual-view representation and VibrMamba–VMamba collaborative modeling. First, this study introduces a Grünwald–Letnikov fractional-order differential enhancement module with a fractional order of α = 0.6 to strengthen fault-sensitive impulsive components and improve the representation of nonstationary vibration signals. The framework then uses the enhanced signal to construct dual-view inputs: a fractional-order-enhanced one-dimensional vibration sequence and a fractional-order-enhanced synchrosqueezing transform (SST) time–frequency image. Subsequently, the framework constructs a VibrMamba temporal branch and a VMamba visual branch to extract dynamic temporal features and global structural features, respectively. Instead of using simple feature concatenation, this study designs a sample-adaptive collaborative fusion mechanism with gated weighting and cross-branch residual enhancement to integrate complementary temporal–visual representations. Bench-level experiments show that the proposed method achieves 98.90% diagnostic accuracy under clean test conditions and maintains 91.52% accuracy at −5 dB signal-to-noise ratio (SNR). These results should be interpreted as bench-level validation under controlled laboratory conditions rather than as direct evidence of field-level generalization. This framework provides a methodological solution that integrates fractional-order signal enhancement, dual-view representation, and Mamba-style collaborative state-space modeling for gearbox fault classification under controlled laboratory conditions with known speed variations and noise disturbances.