To address the insufficient representation of fault characteristics in rotating machinery vibration signals, the sensitivity of conventional Transformers to variations in input response amplitudes, and the limited ability of fixed sequence embedding to preserve continuous temporal information, a rotating machinery fault diagnosis method based on Amplitude-Calibrated Sequence Embedding (ACSE) and a Response-Normalized Transformer (RNformer) is proposed. First, ACSE is designed to construct local temporal feature representations through continuous convolutional mapping, while an amplitude response estimation and adaptive amplitude calibration mechanism is employed to dynamically recalibrate the response intensity at different temporal positions. Rather than simply rescaling the signal amplitude range, amplitude calibration adaptively strengthens the feature contribution of regions associated with fault-induced impacts according to the vibration response intensity, thereby highlighting fault-sensitive information while suppressing the influence of noncritical amplitude fluctuations. In this way, continuous temporal characteristics are preserved while fault-relevant information is enhanced. Second, RNformer is constructed by incorporating a response normalization mechanism into the Transformer encoder to mitigate the interference of abnormal amplitude responses with global feature modeling, thereby improving the stability and robustness of feature representations under complex operating conditions. Finally, a lightweight channel attention mechanism is introduced to further enhance critical fault features and perform fault classification. Experiments were conducted on the Paderborn University bearing dataset and the University of Connecticut gear dataset. The proposed method achieved average diagnostic accuracies of 99.36% and 99.28%, respectively, outperforming the best-performing baseline methods by 1.82 and 1.56 percentage points. These results demonstrated the effectiveness of the proposed method for fault diagnosis.

To address the limited extraction of local fault features, ineffective fusion of multi-scale fault information and interference from redundant noise in vibration-based fault diagnosis of rolling bearings and gears under complex operating conditions, a multi-scale gated feature refinement Vision Transformer (MGFR-ViT), is proposed. First, one-dimensional vibration signals are reconstructed as two-dimensional vibration matrices, making them compatible with patch embedding and Vision Transformer-based feature modeling. A locally enhanced Vision Transformer module is then developed by incorporating a local enhancement mechanism into the standard Vision Transformer architecture, thereby improving the extraction of locally fault-sensitive features while preserving global dependency modeling. Furthermore, a multi-scale gated feature refinement module is introduced to adaptively enhance fault-relevant information and suppress redundant features and noise through parallel multi-scale convolutions with different receptive fields, channel interaction, and gated weighting. Finally, global average pooling and a fully connected classifier are employed for fault classification. Experiments conducted on bearing and gear datasets demonstrated that MGFR-ViT achieved superior diagnostic performance and feature separability compared with several representative fault diagnosis models. Ablation studies further validated the effectiveness and complementarity of the proposed modules. These results indicate that MGFR-ViT provides an effective feature-learning framework for vibration-based fault diagnosis of rotating machinery.