Open AccessMethod for Predicting Cutter Remaining Life Based on Multi-scale Cyclic Convolutional Network (MSRCNN)
Author(s) -
Tao Li,
Yinquan Yu,
Jie Yang,
Zhang Long,
WenBin Tu,
Yong Hao
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1754/1/012218
Subject(s) - convolutional neural network , convolution (computer science) , computer science , scale (ratio) , convergence (economics) , artificial intelligence , process (computing) , pattern recognition (psychology) , layer (electronics) , artificial neural network , recurrent neural network , deep learning , data mining , algorithm , materials science , physics , quantum mechanics , economics , composite material , economic growth , operating system
In the process of predicting the remaining cutter life (RUL), the deep learning method such as convolutional neural network (CNN) does not consider the time correlation of different degradation states, which directly affects the accuracy of the remaining cutter life prediction. To extract the features with time series information to predict the RUL more effectively, this paper proposes a new deep neural network, which is named the multi-scale cyclic convolutional neural network (MSRCNN). In the MSRCNN, a cyclic convolutional layer is constructed to simulate the time correlation of different degradation states for mining the timing characteristics of the data. Multi-scale features are extracted through multi-scale convolution, and the convergence of parameters is improved by layer-by-layer training and fine-tuning. Finally, the RUL is predicted based on the features. The comparison with the published prediction methods of CNN and recurrent neural network (RNN) models proves that our proposed method (MSRCNN) is effective and superior in improving the accuracy of RUL prediction.