Accurate diagnosis of bearing faults is crucial for ensuring the safe and reliable operation of rotating machinery. To enhance the recognition accuracy of rolling bearings under nonlinear and non-stationary vibration conditions, this study proposes an integrated approach combining a multi-stage signal preprocessing strategy, termed EMDWS (Empirical Mode Decomposition with Wavelet denoising and SMOTE), with a hybrid deep learning architecture that integrates a Convolutional Neural Network (CNN) and a Transformer model, hereinafter referred to as CNT (CNN-Transformer). The method first applies empirical mode decomposition (EMD) in conjunction with wavelet denoising to enhance the representation of non-stationary fault features. Subsequently, the synthetic minority oversampling technique (SMOTE) is employed to address the issue of class imbalance in the dataset. A hybrid CNN-Transformer model is constructed by integrating convolutional neural networks and Transformer modules, enabling the extraction of both local and global signal characteristics. Furthermore, Bayesian optimization is applied to fine-tune the model’s hyperparameters, thereby enhancing both the efficiency and robustness of the model. Experimental results demonstrate that the proposed method achieves a high identification accuracy of 99.83%, indicating its effectiveness in distinguishing various bearing fault types.