This study addressed the issues related to the difficulty of determining the operating status of machine tool spindle bearings due to the high rotational speeds and rapid temperature fluctuations. This paper presents an optimized model that combines Convolutional Neural Networks (CNNs) and Informer to dynamically predict the temperature rise process of bearings. Taking the H7006C angular contact ball bearing as the research object, a combination of experimental data and simulations was used to obtain the training dataset. Next, a model for predicting the temperature rise of the bearing was constructed using CNN + Informer and the structural parameters were optimized. Finally, the model’s generalization ability was then verified by predicting the bearing temperature rise process under various working conditions. The results show that the error of the simulation data source model was less than 1 °C at steady state; the temperature error of the bearing temperature rise prediction model was less than 0.5 °C at both the temperature rise and steady-state stages under variable rotational speeds and variable load conditions compared to Informer and Long Short Term Memory (LSTM) models; the maximum prediction error of the operating conditions outside the dataset was less than 0.5 °C, and the temperature rise prediction model has a high accuracy, robustness, and generalization capability.

In response to the challenge of timely fault identification in the spindle bearings of machine tools operating in complex environments, this study proposes a method based on a combination of infrared imaging with an Informer and a CNN + Swin Transformer. The aim is to achieve real-time monitoring of bearing faults, precise fault localization, and classification of fault severity. To accomplish this, an angular contact ball bearing was chosen as the research subject. Initially, an infrared image dataset was constructed, encompassing various fault positions and degrees, by simulating different forms of bearing faults. Subsequently, an Informer-based bearing temperature prediction model was established to select faulty bearing data. Lastly, the faulty data were input into the CNN + Swin Transformer model for bearing fault recognition and classification. The results demonstrate that the Informer model accurately identifies abnormal temperature rises during bearing operation, effectively screening out faulty bearings. Under steady-state conditions, the model achieves a classification accuracy of 97.8%. Furthermore, after employing the Informer screening process, the proposed model exhibits a recognition precision of 98.9%, surpassing other models such as CNN, SVM, and Swin Transformer, which are mentioned in this paper.