Gated Recurrent Units Based Neural Network For Tool Condition Monitoring

Tool condition monitoring (TCM) is a prerequisite to ensure high finishing quality of workpiece in manufacturing automation. One of the most important components in TCM system is tool wear estimation. How to achieve estimation with high accuracy is still an open question. In the past few decades, recurrent neural network (RNN) has shown a great success in learning long-term dependence of the sequential data. However, traditional RNNs (e.g., vanilla RNN, etc.) suffer gradient vanishing or exploding problem as well as long computational training time when the model is trained through back propagation through time (BPTT). To address these issues, we propose a gated recurrent units (GRU) based neural network to estimate the tool wear for tool condition monitoring. The GRU neural network can analyze time-series data on multiple time scales and can avoid gradient vanishing during training. A real-world gun drilling experimental dataset is used as a case study for tool condition monitoring in this paper. The performance of the proposed GRU based TCM approach is compared with other well-known models including support vector regression (SVR) and multi-layer perceptron (MLP). The experimental results show that the proposed GRU based TCM approach outperforms other competing models on this real-world gun drilling dataset.

[1]  Vishal Wayal,et al.  Tool Condition Monitoring System: A Review , 2015 .

[2]  M. F. DeVries,et al.  Neural Network Sensor Fusion for Tool Condition Monitoring , 1990 .

[3]  Gary D. Bernard,et al.  Multirate Coupled Hidden Markov Models and Their Application to Machining Tool-Wear Classification , 2007, IEEE Transactions on Signal Processing.

[4]  Shih-Chieh Lin,et al.  Drill wear monitoring using neural networks , 1996 .

[5]  Gary D. Bernard,et al.  Multilevel Classification of Milling Tool Wear with Confidence Estimation , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Frank L. Lewis,et al.  Intelligent Diagnosis and Prognosis of Tool Wear Using Dominant Feature Identification , 2009, IEEE Transactions on Industrial Informatics.

[7]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[8]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[9]  Haizhou Li,et al.  A Cost-Sensitive Deep Belief Network for Imbalanced Classification , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[10]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[11]  T. I. El-Wardany,et al.  Tool condition monitoring in drilling using vibration signature analysis , 1996 .

[12]  Jason Weston,et al.  Gene Selection for Cancer Classification using Support Vector Machines , 2002, Machine Learning.

[13]  Krzysztof Jemielniak,et al.  Tool failure detection based on analysis of acoustic emission signals , 1998 .

[14]  Yoshua Bengio,et al.  Gated Feedback Recurrent Neural Networks , 2015, ICML.

[15]  W. König,et al.  Tool monitoring of small drills with acoustic emission , 1992 .

[16]  Paul K. Wright,et al.  Computer-assisted Prediction of Drill-failure Using In-process Measurements of Thrust Force , 1988 .

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

[18]  Kay Chen Tan,et al.  Training cost-sensitive Deep Belief Networks on imbalance data problems , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[19]  Issam Abu-Mahfouz,et al.  Drilling wear detection and classification using vibration signals and artificial neural network , 2003 .

[20]  Yoke San Wong,et al.  Multiclassification of tool wear with support vector machine by manufacturing loss consideration , 2004 .

[21]  Kay Chen Tan,et al.  Multiobjective Deep Belief Networks Ensemble for Remaining Useful Life Estimation in Prognostics , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[22]  Haizhou Li,et al.  A Multi-State Diagnosis and Prognosis Framework with Feature Learning for Tool Condition Monitoring , 2018, ArXiv.

[23]  Xiang Li,et al.  Multimodal Hidden Markov Model-Based Approach for Tool Wear Monitoring , 2014, IEEE Transactions on Industrial Electronics.

[24]  Haizhou Li,et al.  A data-driven prognostics framework for tool remaining useful life estimation in tool condition monitoring , 2017, 2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA).

[25]  Geok Soon Hong,et al.  Tool condition monitoring in deep hole gun drilling: A data-driven approach , 2017, 2017 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM).

[26]  Geok Soon Hong,et al.  Multi-category micro-milling tool wear monitoring with continuous hidden Markov models , 2009 .

[27]  T. I. Liu,et al.  Intelligent Classification and Measurement of Drill Wear , 1994 .

[28]  Wojciech Zaremba,et al.  An Empirical Exploration of Recurrent Network Architectures , 2015, ICML.

[29]  Tianyou Zhang,et al.  Health Index-Based Prognostics for Remaining Useful Life Predictions in Electrical Machines , 2016, IEEE Transactions on Industrial Electronics.

[30]  Xiaoli Li,et al.  Current-sensor-based feed cutting force intelligent estimation and tool wear condition monitoring , 2000, IEEE Trans. Ind. Electron..

[31]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[32]  Kay Chen Tan,et al.  Deep Belief Networks Ensemble with Multi-objective Optimization for Failure Diagnosis , 2015, 2015 IEEE International Conference on Systems, Man, and Cybernetics.

[33]  Cuneyt Oysu,et al.  Drill wear monitoring using cutting force signals , 2004 .