Interpretable convolutional neural network for milling cutter wear state recognition

Convolutional neural networks (CNNs) are essential tools for identifying the wear state of a milling cutter. However, the decision mechanism and classification basis of CNNs is unclear, which reduces the credibility of the recognition results and limits their application in industrial recognition. Tackling the challenge of poor interpretability in traditional CNNs, this paper introduces an interpretable convolutional neural network (STA-CNN) designed specifically for identifying the wear state of milling cutters. Firstly, an attention layer is embedded in the CNN to prioritize important milling cutter wear information. Secondly, the Stockwell transform (S-Transform) is embedded into the spatial attention convolution layer to form an interpretable Stockwell attention convolution layer. Finally, a physically meaningful loss function is designed for the tool wear state to guide the STA-CNN model in learning and updating the parameters. The STA-CNN model achieves 98% accuracy in recognizing tool wear states and demonstrates good interpretability.