In the carbon fiber-reinforced plastic milling process, the high abrasive property of carbon fiber will lead to the rapid growth of tool wear, resulting in poor surface quality of parts. However, due to the signal data distribution discrepancy under different working conditions, addressing the problem of local degradation and low prediction accuracy in tool wear monitoring model is a significant challenge. This paper proposes an entropy criterion deep conditional domain adaptation network, which effectively exploits domain invariant features of the signals and enhances the stability of model training. Furthermore, a novel unsupervised optimization method based on tool wear distribution is proposed, which refines the monitoring results of data-driven models. This approach reduces misclassification of tool wear conditions resulting from defects in data-driven models and interference from the manufacturing process, thereby enhancing the accuracy of the monitoring model. The experimental results show that the hybrid method provides assurance for the accurate construction of tool wear monitoring model under different working conditions.
Read full abstract