Tool wear prediction method based on dual-attention mechanism network

Effective tool wear monitoring (TWM) methods are helpful in accurately estimating tool wear status, and rationally using and replacing tools, thereby improving machining quality and production efficiency. In this paper, a dual-attention mechanism network is designed, which not only overcomes the information loss problem, but also enhances the interpretability of deep learning model. Firstly, Z-Score standardization is applied to the cutting force signals, CNN-GRU is built as the basic framework, improving the traditional SE attention mechanism, and integrating it into the model input for adaptive weight allocation. Furthermore, embedding the multi-head attention mechanism into the connection layer between CNN and GRU, and the weighted features are input into GRU for sequence modeling. Ultimately, a fully connected layer is used to establish a mapping from high-dimensional features to the dimension of tool wear, and a linear regression layer is used to output wear prediction values. Compared with several common deep learning models, the dual-attention mechanism model is more reliable and superior. The enhancement of model performance through the dual-attention mechanism was further quantified through the ablation experiment, specifically, the MAE was reduced by 62.33%, 46.03%, and 33.58%, and the RMSE was reduced by 63.05%, 48.62%, and 35.70%, respectively.