Excessive milling temperature during machining accelerates tool wear and damages the workpiece surface, which seriously affects tool life and workpiece quality. To address these issues, this study monitors the temperature changes during milling in real time. By collecting temperature data in the vicinity of the measuring tool, an Informer neural network was used to predict the temperature rise at the milling cutter measurement points, and the Pearson product-moment correlation coefficients were used to analyze the correlation between the machining parameters and multiple points on the backside of the milling cutter. The results of the study were also compared using GRU and LSTM models, which showed that the Informer model is more capable of real-time monitoring and prediction of tool temperatures during the milling process, which can help extend tool life and improve workpiece quality.