Intelligent tool wear monitoring based on parallel residual and stacked bidirectional long short-term memory network

• Published in: Journal of manufacturing systems 2021-07, Vol.60, p.608-619
• Main Authors: Liu, Xianli, Liu, Shaoyang, Li, Xuebing, Zhang, Bowen, Yue, Caixu, Liang, Steven Y.
• Format: Article
• Language: English
• Subjects: Bidirectional long short-term memory network; Convolutional neural network; Deep learning; Parallel residual network; Tool wear; Tool wear monitoring
• ISSN: 0278-6125; 1878-6642
• DOI: 10.1016/j.jmsy.2021.06.006

•A novel integration model is proposed for tool wear monitoring.•The parallel residual network is utilized to realize multi-feature fusion and speed up the network learning process.•The stacked bidirectional long short-term memory network is designed to encode temporal information.•The smoothing method is used to improve the prediction accuracy. Effective tool wear monitoring (TWM) is essential for accurately assessing the degree of tool wear and for timely preventive maintenance. Existing data-driven monitoring methods mainly rely on complex feature engineering, which reduces the monitoring efficiency. This paper proposes a novel TWM model based on a parallel residual and stacked bidirectional long short-term memory (PRes–SBiLSTM) network. First, a parallel residual network (PResNet) is used to extract the multi-scale local features of sensor signals adaptively. Subsequently, a stacked bidirectional long short-term memory (SBiLSTM) network is used to obtain the time-series features related to the tool wear characteristics. Finally, the predicted tool wear value is outputted through a fully connected network. A smoothing correction method is applied to improve the prediction accuracy. The proposed model is experimentally verified to have a high prediction accuracy without sacrificing its generalization ability. A TWM system framework based on the PRes–SBiLSTM network is proposed, which has a certain reference value for TWM in actual industrial environments.