In-process tool condition forecasting based on a deep learning method

Abstract It is widely acknowledged that machining precision and surface integrity are greatly affected by cutting tool conditions. In order to enable early cutting tool replacement and proactive actions, tool wear conditions should be estimated in advance and updated in real-time. In this work, an approach to in-process tool condition forecasting is proposed based on a deep learning method. A long short-term memory network is designed to forecast multiple flank wear values based on historical data. A residual convolutional neural network is built to enable in-process tool condition monitoring, using raw signals acquired during the machining process. The integration of them enables in-process tool condition forecasting. Median-based correction and mean-based correction are adopted to improve the accuracy. IEEE PHM 2010 challenge data has been used to illustrate and validate this approach. Experimental study and quantitative comparisons showed that future flank wear values could be precisely forecasted during the machining process. The proposed approach contributes to prompt and reliable cutting tool condition forecasting, which will support the decision-making about cutting tool replacement in data-driven smart manufacturing.

[1]  Romulo Gonçalves Lins,et al.  In-process machine vision monitoring of tool wear for Cyber-Physical Production Systems , 2020, Robotics Comput. Integr. Manuf..

[2]  Jürgen Schmidhuber,et al.  A local learning algorithm for dynamic feedforward and recurrent networks , 1990, Forschungsberichte, TU Munich.

[3]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[4]  Dazhong Wu,et al.  Deep learning for smart manufacturing: Methods and applications , 2018, Journal of Manufacturing Systems.

[5]  Elijah Kannatey-Asibu,et al.  Monitoring tool wear using classifier fusion , 2017 .

[6]  Yancheng Liu,et al.  Mechanical state prediction based on LSTM neural netwok , 2017, 2017 36th Chinese Control Conference (CCC).

[7]  Wei Xue,et al.  Review of tool condition monitoring methods in milling processes , 2018 .

[8]  Robert X. Gao,et al.  Cloud-enabled prognosis for manufacturing , 2015 .

[9]  Robert X. Gao,et al.  Deep heterogeneous GRU model for predictive analytics in smart manufacturing: Application to tool wear prediction , 2019, Comput. Ind..

[10]  Xing Fang,et al.  Performance enhancing techniques for deep learning models in time series forecasting , 2019, Eng. Appl. Artif. Intell..

[11]  Chen Zhang,et al.  Tool wear model based on least squares support vector machines and Kalman filter , 2014, Prod. Eng..

[12]  Xiaoli Li,et al.  Deep Convolutional Neural Network Based Regression Approach for Estimation of Remaining Useful Life , 2016, DASFAA.

[13]  Robert X. Gao,et al.  Heterogeneous data-driven hybrid machine learning for tool condition prognosis , 2019, CIRP Annals.

[14]  Anton S. Grigoryev,et al.  Real-Time Diagnosis and Forecasting Algorithms of the Tool Wear in the CNC Systems , 2015, ICSI.

[15]  Yingfeng Zhang,et al.  A comprehensive review of big data analytics throughout product lifecycle to support sustainable smart manufacturing: A framework, challenges and future research directions , 2019, Journal of Cleaner Production.

[16]  Yong Lu,et al.  Multi-scale hybrid HMM for tool wear condition monitoring , 2016 .

[17]  Fei Tao,et al.  Make more digital twins , 2019, Nature.

[18]  Xionghui Zhou,et al.  A method of NC machine tools intelligent monitoring system in smart factories , 2020, Robotics Comput. Integr. Manuf..

[19]  Ray Y. Zhong,et al.  A proactive material handling method for CPS enabled shop-floor , 2020, Robotics Comput. Integr. Manuf..

[20]  Lei Ren,et al.  Bearing remaining useful life prediction based on deep autoencoder and deep neural networks , 2018, Journal of Manufacturing Systems.

[21]  David He,et al.  Using Deep Learning-Based Approach to Predict Remaining Useful Life of Rotating Components , 2018, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[22]  Suet To,et al.  Novel tool wear monitoring method in ultra-precision raster milling using cutting chips , 2014 .

[23]  Frank L. Lewis,et al.  Tool wear forecast using Dominant Feature Identification of acoustic emissions , 2010, 2010 IEEE International Conference on Control Applications.

[24]  Paul Maropoulos,et al.  A novel method for accurately monitoring and predicting tool wear under varying cutting conditions based on meta-learning , 2019, CIRP Annals.

[25]  Andrew Kusiak,et al.  Data-driven smart manufacturing , 2018, Journal of Manufacturing Systems.

[26]  Robert X. Gao,et al.  Digital Twin for Machining Tool Condition Prediction , 2019, Procedia CIRP.

[27]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Peng Wang,et al.  Long short-term memory for machine remaining life prediction , 2018, Journal of Manufacturing Systems.

[29]  Xiang Li,et al.  Remaining useful life estimation in prognostics using deep convolution neural networks , 2018, Reliab. Eng. Syst. Saf..

[30]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[31]  Zhiwei Guo,et al.  Tool wear prediction considering uncovered data based on partial least square regression , 2014 .

[32]  Roberto Teti,et al.  Image data processing via neural networks for tool wear prediction , 2013 .

[33]  Dong-Won Kim,et al.  Fuzzy logic based tool condition monitoring for end-milling , 2017 .

[34]  Andrew Kusiak,et al.  Smart manufacturing must embrace big data , 2017, Nature.

[35]  Robert X. Gao,et al.  Deep learning and its applications to machine health monitoring , 2019, Mechanical Systems and Signal Processing.