A New Time-Space Attention Mechanism Driven Multi-Feature Fusion Method for Tool Wear Monitoring
Abstract In order to accurately monitor the tool wear process, it is usually necessary to collect a variety of sensor signals during the cutting process. Different sensor signals in the feature space can provide complementary information. In addition, the monitoring signal is time series data, which also contains a wealth of tool degradation information in the time dimension. However, how to fuse multi-sensor information in time and space dimensions is a key issue that needs to be solved. This paper proposes a new time-space attention mechanism driven multi-feature fusion method to realize the tool wear monitoring. Firstly, lots of features are established from different sensor signals and selected preliminarily. Then, a new feature fusion model with time-space attention mechanism is constructed to fuse features in time and space dimensions. Finally, the tool degradation model is established according to the predicted wear, and the tool remaining useful life is predicted by particle filter. The effectiveness of this method is verified by a tool life cycle wear experiment. Through comparing with other feature fusion models, it is demonstrated that the proposed method realizes the tool wear monitoring more accurately and has better stability.
