Abstract
Tool condition is the key factor affecting the quality and efficiency of precision cutting of parts. As tool wear is inevitable during machining, tool wear status during machining must be regularly monitored. This study proposes a combined convolutional neural network and support vector machine (SVM) approach for tool wear status monitoring. First, 1D cutting force data are wavelet-transformed and converted into 2D spectrogram. Second, the leaky-ReLU activation function is adopted to enhance network robustness. Third, an SVM classifier is used to replace the traditional Softmax function to improve the model generalization capability. Finally, the cutting force signal of the tool used for the machining of the aero-engine integral blisk is verified. The accuracy of the constructed network model can reach 98.28 %. Moreover, the proposed model has a simple structure, requires a small number of parameters, and has good robustness and reliability.
Similar content being viewed by others
Abbreviations
- FT :
-
Fourier transform
- WT :
-
Wavelet transform
- CNN :
-
Convolutional neural network
- ReLU :
-
Rectified linear unit
- SVM :
-
Support vector machine
References
T. Khan, M. Broderick, S. A. Sajid, J. Secker and C. M. Taylor, Development of an enhanced single point milling procedure to screen metalworking cutting fluid performance in terms of tool wear when machining aerospace alloys, Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 235 (10) (2021) 1164–1154.
Y. Cheng, J. Yang, D. Zuo, X. Song and X. Feng, Tool design and cutting parameters optimization for plunge milling blisk, International Journal of Manufacturing Research, 15 (3) (2020) 266–284.
R. A. Patil and S. L. Gombi, Experimental study of cutting force on a cutting tool during machining using inverse problem analysis, Journal of the Brazilian Society of Mechanical Sciences and Engineering, 40 (10) (2018) 494.
T. S. Liu, Y. Y. Liu and K. D. Zhang, An improved cutting force model in micro-milling considering the comprehensive effect of tool runout, size effect, and tool wear, The International Journal of Advanced Manufacturing Technology (2022) 659–668.
K. Gomathi and A. Balaji, Tool condition monitoring of PCB milling machine based on vibration analysis, Materials Today: Proceedings, 45 (P2) (2021) 3386–3397.
M. K. Liu, H. K. Tseng and M. Q. Tran, Tool wear monitoring and prediction based on sound signal, The International Journal of Advanced Manufacturing Technology, 103 (9–12) (2019) 3361–3373.
A. R. Khan, F. Doosti, M. Karimi, M. Harouni, U. Tariq, S. M. Fat and S. A. Bahaj, Authentication through gender classification from iris images using support vector machine, Microscopy Research and Technique, 84 (11) (2021) 2666–2676.
Y. H. Zhang and A. Jatowt, Estimating a one-class naive bayes text classifier, Intelligent Data Analysis, 24 (3) (2020) 567–579.
V. T. Nguyen, V. H. Nguyen and V. T. Pham, Deep stacked auto-encoder network based tool wear monitoring in the face milling process, Strojniski Vestnik-Journal of Mechanical Engineering, 66 (4) (2020) 227–234.
O. Geramifard, J.-X. Xu, J.-H. Zhou and X. Li, Multimodal hidden markov model-based approach for tool wear monitoring, IEEE Transactions on Industrial Electronics, 61 (6) (2014) 2900–2911.
Q. Wang, H. Wang, L. Hou and S. Yi, Overview of tool wear monitoring methods based on convolutional neural network, Applied Sciences, 11 (24) (2021) 12041–12041.
Z. Huang, J. Zhu, J. Lei, X. Li and F. Tian, Tool wear predicting based on multi-domain feature fusion by deep convolutional neural network in milling operations, Journal of Intelligent Manufacturing, 31 (2019) 953–966.
M. A. Giovanna, T. German and R. Svetan, Tool wear classification using time series imaging and deep learning, The International Journal of Advanced Manufacturing Technology, 104 (9–12) (2019) 3647–3662.
T. Bergs, C. Holst, P. Gupta and T. Augspurger, Digital image processing with deep learning for automated cutting tool wear detection, Procedia Manufacturing, 48 (C) (2020) 947–958.
P. K. Ambadekar and C. M. Choudhari, CNN based tool monitoring system to predict life of cutting tool, SN Applied Sciences, 2 (4) (2020) 616–630.
R. Bazi, T. Benkedjouh, H. Habbouche, S. Rechak and N. Zerhouni, A hybrid CNN-BiLSTM approach-based variational mode decomposition for tool wear monitoring, The International Journal of Advanced Manufacturing Technology, 19 (2022) 3803–3817.
C. Cooper, P. Wang, J. Zhang, R. X. Gao, T. Roney, I. Ragai and D. Shaffer, Convolutional neural network-based tool condition monitoring in vertical milling operations using acoustic signals, Procedia Manufacturing, 49 (2020) 105–111.
J. Duan, J. Duan, H. Zhou, X. Zhan, T. Li and T. Shi, Multi-frequency-band deep CNN model for tool wear prediction, Measurement Science and Technology, 32 (6) (2021) 065009.
D. A. Molitor, C. Kubik, M. Becker, R. H. Hetfleisch, F. Lyu and P. Groche, Towards high-performance deep learning models in tool wear classification with generative adversarial networks, Journal of Materials Processing Technology, 302 (2022) 117484.
N. Brili, M. Ficko and S. Klancnik, Automatic identification of tool wear based on thermography and a convolutional neural network during the turning process, Sensors, 21 (5) (2021) 1917–1917.
H. Y. Chen and C. H. Lee, Deep learning approach for vibration signals applications, Sensors, 21 (11) (2021) 3929.
A. H. Reza, M. Navideh and B. Mahmoud, A novel damage identification method based on short time Fourier transform and a new efficient index, Structures, 33 (2021) 3605–3614.
Z. Liu, X. Liu, S. Xie, J. Wang and X. Zhou, A novel fault diagnosis method for analog circuits based on multi-input deep residual networks with an improved empirical wavelet transform, Applied Sciences, 12 (3) (2020) 1675.
Z. Cui, Y. Gao, J. Hu, S. Tian and J. Cheng, LOS/NLOS identification for indoor UWB positioning based on morlet wavelet transform and convolutional neural networks, IEEE Communications Letters, 25 (8) (2021) 879–882.
K. Ramakrishnan, S. Scholte, V. Lamme, A. Smeulders and S. Ghebreab, Convolutional neural networks in the brain: an fMRI study, Journal of Vision, 15 (2015) 371.
Y. N. Han and B. W. Hong, Deep learning based on fourier convolutional neural network incorporating random kernels, Electronics, 10 (16) (2021) 2004.
C. T. Alexakos, Y. L. Karnavas, M. Drakaki and L. A. Tziafettas, A combined short time fourier transform and image classification transformer model for rolling element bearings fault diagnosis in electric motors, Machine Learning and Knowledge Extraction, 3 (1) (2021) 228–242.
L. K. Zhang, Y. Li, L. C. Dong, X. Q. Yang, X. X. Ding, Q. Zeng, L. M. Wang and Y. M. Shao, Gearbox fault diagnosis using multiscale sparse frequency-frequency distributions, IEEE Access (2019) 113089–113099.
S. M. Tayyab, S. Chatterton and P. Pennacchi, Intelligent defect diagnosis of rolling element bearings under variable operating conditions using convolutional neural network and order maps, Sensors, 22 (5) (2022) 2026.
D. Zhu, S. Lu, M. Wang, J. Lin and Z. Wang, Efficient precision-adjustable architecture for softmax function in deep learning, IEEE Transactions on Circuits and Systems II Express Briefs, 67 (12) (2020) 3382–3386.
Acknowledgments
This work was supported by the National Natural Science Foundation of China (51965051) and the Natural Science Foundation of Inner Mongolia (2019LH05029).
Author information
Authors and Affiliations
Corresponding author
Additional information
Nan Zhang is an Associate Professor of the School of Mechanical Engineering at Inner Mongolia University of Technology. She received a Ph.D. degree in Mechatronic Engineering from Northwestern Polytechnical University in 2021. Her research fields include machining mechanism, condition monitoring, residual life prediction and system reliability.
Rights and permissions
About this article
Cite this article
Zhao, JW., Guo, SJ., Ma, L. et al. Tool wear monitoring based on an improved convolutional neural network. J Mech Sci Technol 37, 1949–1958 (2023). https://doi.org/10.1007/s12206-023-0332-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12206-023-0332-x