Multi-Scale Convolutional Gated Recurrent Unit Networks for Tool Wear Prediction in Smart Manufacturing

As an integrated application of modern information technologies and artificial intelligence, Prognostic and Health Management (PHM) is important for machine health monitoring. Prediction of tool wear is one of the symbolic applications of PHM technology in modern manufacturing systems and industry. In this paper, a multi-scale Convolutional Gated Recurrent Unit network (MCGRU) is proposed to address raw sensory data for tool wear prediction. At the bottom of MCGRU, six parallel and independent branches with different kernel sizes are designed to form a multi-scale convolutional neural network, which augments the adaptability to features of different time scales. These features of different scales extracted from raw data are then fed into a Deep Gated Recurrent Unit network to capture long-term dependencies and learn significant representations. At the top of the MCGRU, a fully connected layer and a regression layer are built for cutting tool wear prediction. Two case studies are performed to verify the capability and effectiveness of the proposed MCGRU network and results show that MCGRU outperforms several state-of-the-art baseline models.

Automated summary

The paper proposes a multi-scale Convolutional Gated Recurrent Unit network (MCGRU) for tool wear prediction, which enhances adaptability to features of different time scales through multiple parallel branches. Different scales of features extracted from raw data are then used to learn significant representations using a Deep Gated Recurrent Unit network, and ultimately cutting tool wear prediction is carried out through a fully connected layer and a regression layer.