Multi-frequency-band deep CNN model for tool wear prediction

Jian Duan; JIE DUAN; Hongdi Zhou; Xiaobin Zhan; Tianxiang Li; Tielin Shi

doi:10.1088/1361-6501/abb7a0

journal article Apr 06, 2021

Multi-frequency-band deep CNN model for tool wear prediction

Jian Duan

JIE DUAN

Hongdi Zhou Xiaobin Zhan Tianxiang Li

Tielin Shi

Measurement Science and Technology Vol. 32 No. 6 pp. 065009 · IOP Publishing

View at Publisher Save 10.1088/1361-6501/abb7a0

Abstract

Abstract
A reliable data-driven tool condition monitoring system is more and more promising for cutting down on machine downtime and economic losses. However, traditional methods are not able to address machining big data because of low model generalizability and laborious feature extraction by hand. In this paper, a novel deep learning model, named multi-frequency-band deep convolution neural network (MFB-DCNN), is proposed to handle machining big data and to monitor tool condition. First, samples are enlarged and a three-layer wavelet package decomposition is applied to obtain wavelet coefficients in different frequency bands. Then, the multi-frequency-band feature extraction structure based on a deep convolution neural network structure is introduced and utilized for sensitive feature extraction from these coefficients. The extracted features are fed into full connection layers to predict tool wear conditions. After this, milling experiments are conducted for signal acquisition and model construction. A series of hyperparameter selection experiments is designed for optimization of the proposed MFB-DCNN model. Finally, the prediction performance of typical models is evaluated and compared with that of the proposed model. The results show that the proposed model has outstanding generalizability and higher prediction performance, and a well designed structure can remedy the absence of complicated feature engineering.

Topics

No keywords indexed for this article. Browse by subject →

References

48

[1]

Zhou "Review of tool condition monitoring methods in milling processes" Int. J. Adv. Manuf. Technol. (2018) 10.1007/s00170-018-1768-5

[2]

Wu "Automatic identification of tool wear based on convolutional neural network in face milling process" Sensors (2019) 10.3390/s19183817

[3]

In situ measurement of cutting edge temperature in turning using a near-infrared fiber-optic two-color pyrometer

Jinghui Han, Kaiwei Cao, Lian Xiao et al.

Measurement 2020 10.1016/j.measurement.2020.107595

[4]

Li "Data-driven smart manufacturing: tool wear monitoring with audio signals and machine learning" J. Manuf. Processes (2019) 10.1016/j.jmapro.2019.10.020

[5]

Detection process approach of tool wear in high speed milling

M. Kious, A. Ouahabi, M. Boudraa et al.

Measurement 2010 10.1016/j.measurement.2010.08.014

[6]

Kurada "A review of machine vision sensors for tool condition monitoring" Comput. Ind. (1997) 10.1016/s0166-3615(96)00075-9

[7]

Li "A review of tool wear estimation using theoretical analysis and numerical simulation technologies" Int. J. Refract. Met. Hard Mater. (2012) 10.1016/j.ijrmhm.2012.05.006

[8]

Leem "A customized neural network for sensor fusion in on-line monitoring of cutting tool wear" J. Eng. Ind. (1995) 10.1115/1.2803289

[9]

Zhu "Online tool wear monitoring via hidden semi-Markov model with dependent durations" IEEE Trans. Ind. Inform. (2018) 10.1109/tii.2017.2723943

[10]

Wang "Enhanced particle filter for tool wear prediction" J. Manuf. Syst. (2015) 10.1016/j.jmsy.2015.03.005

[11]

Cao "The concept and progress of intelligent spindles: a review" Int. J. Mach. Tools Manuf. (2017) 10.1016/j.ijmachtools.2016.10.005

[12]

Deep learning and its applications to machine health monitoring

Rui Zhao, Ruqiang Yan, Zhenghua Chen et al.

Mechanical Systems and Signal Processing 2019 10.1016/j.ymssp.2018.05.050

[13]

Wang "Deep heterogeneous GRU model for predictive analytics in smart manufacturing: application to tool wear prediction" Comput. Ind. (2019) 10.1016/j.compind.2019.06.001

[14]

Duan "A novel ResNet-based model structure and its applications in machine health monitoring" J. Vib. Control (2020) 10.1177/1077546320936506

[15]

An "A data-driven model for milling tool remaining useful life prediction with convolutional and stacked LSTM network" Measurement (2020) 10.1016/j.measurement.2019.107461

[16]

Cao "An intelligent milling toolwear monitoring methodology based on convolutional neural network with derived wavelet frames coefficient" Appl. Sci. (2019) 10.3390/app9183912

[17]

Mohanraj "Tool condition monitoring techniques in milling process—a review" J. Mater. Res. Technol. (2020) 10.1016/j.jmrt.2019.10.031

[18]

Rehorn "State-of-the-art methods and results in tool condition monitoring: a review" Int. J. Adv. Manuf. Technol. (2005) 10.1007/s00170-004-2038-2

[19]

Yen "Applying the self-organization feature map (SOM) algorithm to AE-based tool wear monitoring in micro-cutting" Mech. Syst. Signal Process. (2013) 10.1016/j.ymssp.2012.05.001

[20]

Zhu "Wavelet analysis of sensor signals for tool condition monitoring: a review and some new results" Int. J. Mach. Tools Manuf. (2009) 10.1016/j.ijmachtools.2009.02.003

[21]

Torabi "Application of clustering methods for online tool condition monitoring and fault diagnosis in high-speed milling processes" IEEE Syst. J. (2016) 10.1109/jsyst.2015.2425793

[22]

Javed "Tool wear monitoring and prognostics challenges: a comparison of connectionist methods toward an adaptive ensemble model" J. Intell. Manuf. (2018) 10.1007/s10845-016-1221-2

[23]

Bhat "Tool condition classification in turning process using hidden Markov model based on texture analysis of machined surface images" Measurement (2016) 10.1016/j.measurement.2016.05.022

[24]

Wang "A new tool wear monitoring method based on multi-scale PCA" J. Intell. Manuf. (2019) 10.1007/s10845-016-1235-9

[25]

Liao "Tool wear state recognition based on GWO–SVM with feature selection of genetic algorithm" Int. J. Adv. Manuf. Technol. (2019) 10.1007/s00170-019-03906-9

[26]

Liu "An integrated condition-monitoring method for a milling process using reduced decomposition features" Meas. Sci. Technol. (2017) 10.1088/1361-6501/aa6bcc

[27]

Chen "Predicting tool wear with multi-sensor data using deep belief networks" Int. J. Adv. Manuf. Technol. (2018) 10.1007/s00170-018-2571-z

[28]

Li "Research on a tool wear monitoring algorithm based on residual dense network" Symmetry (2019) 10.3390/sym11060809

[29]

Cao "Combining translation-invariant wavelet frames and convolutional neural network for intelligent tool wear state identification" Comput. Ind. (2019) 10.1016/j.compind.2018.12.018

[30]

Duan "A novel bearing health prognostic method based on time-frequency analysis and LSTM" (2019)

[31]

Cui "Manufacturing big data ecosystem: a systematic literature review" Robot. Comput.-Integr. Manuf. (2020) 10.1016/j.rcim.2019.101861

[32]

Tao "Data-driven smart manufacturing" J. Manuf. Syst. (2018) 10.1016/j.jmsy.2018.01.006

[33]

Xu "A novel convolutional transfer feature discrimination network for unbalanced fault diagnosis under variable rotational speeds" Meas. Sci. Technol. (2019) 10.1088/1361-6501/ab230b

[34]

Liu "A novel transformer-based neural network model for tool wear estimation" Meas. Sci. Technol. (2020) 10.1088/1361-6501/ab7282

[35]

Deep learning

Yann LeCun, Yoshua Bengio, Geoffrey Hinton

Nature 2015 10.1038/nature14539

[36]

Deep learning in neural networks: An overview

Jürgen Schmidhuber

Neural Networks 2015 10.1016/j.neunet.2014.09.003

[37]

Yaqoob "Autonomous driving cars in smart cities: recent advances, requirements and challenges" IEEE Netw. (2019) 10.1109/mnet.2019.1900120

[38]

Kroemer "A review of robot learning for manipulation: Challenges, representations, and algorithms" (2019)

[39]

Chen "Basic research on machinery fault diagnostics: Past, present and future trends" Front. Mech. Eng. (2018) 10.1007/s11465-018-0472-3

[40]

Khan "A review on the application of deep learning in system health management" Mech. Syst. Signal Process. (2018) 10.1016/j.ymssp.2017.11.024

[41]

Hu "Data-driven fault diagnosis method based on compressed sensing and improved multiscale network" IEEE Trans. Ind. Electron. (2019) 10.1109/tie.2019.2912763

[42]

Aghazadeh "Tool condition monitoring using spectral subtraction and convolutional neural networks in milling process" Int. J. Adv. Manuf. Technol. (2018) 10.1007/s00170-018-2420-0

[43]

Huang "Tool wear predicting based on multi-domain feature fusion by deep convolutional neural network in milling operations" J. Intell. Manuf. (2019) 10.1007/s10845-019-01488-7

[44]

Gao (2011)

[45]

Deep learning for smart manufacturing: Methods and applications

Jinjiang Wang, Yulin Ma, Laibin Zhang et al.

Journal of Manufacturing Systems 2018 10.1016/j.jmsy.2018.01.003

[46]

Xu "Empirical evaluation of rectified activations in convolutional network" (2015)

[47]

He "Delving deep into rectifiers: surpassing human-level performance on ImageNet classification" (2015)

[48]

Kingma "Adam: a method for stochastic optimization" (2014)

Cited By

41

Wear monitoring of micro-milling tools based on Improved Siamese Neural Network

Gang Zheng, Xinfeng Lv · 2024

Proceedings of the Institution of M...

A Review of Physics-Based, Data-Driven, and Hybrid Models for Tool Wear Monitoring

Haoyuan Zhang, Shanglei Jiang · 2024

Machines

Metrics

41

Citations

48

References

Details

Published: Apr 06, 2021
Vol/Issue: 32(6)
Pages: 065009
License: View

Authors

College of Civil Engineering and Architecture Zhejiang University Hangzhou China

T

Tielin Shi

Funding

National Natural Science Foundation of China Award: 51675204

National Science and Technology Major Project of China Award: 2018ZX04035002-002

Natural Science Foundation of Hubei Province Award: 2019CFB326

Key-Area Research and Development Program of Guangdong Province Award: Grant No. 2020B090927002

Scientific Research Foundation for Doctoral Program of Hubei University of Technology Award: BSQD2017003

Cite This Article

Jian Duan, JIE DUAN, Hongdi Zhou, et al. (2021). Multi-frequency-band deep CNN model for tool wear prediction. Measurement Science and Technology, 32(6), 065009. https://doi.org/10.1088/1361-6501/abb7a0

Multi-frequency-band deep CNN model for tool wear prediction

You May Also Like