Abstract
Accurate prediction of tool flank wear during turning is important so that the cutting tool can be replaced before excessive damage occurs to the workpiece surface. Existing online methods of tool wear prediction using sensor signals can be affected by noise, thus resulting in false alarms. The aim of this work is to develop deep learning regression models to predict tool wear state using features extracted from 2-D images of surface profile of the workpiece. Two models, namely convolutional neural network (CNN) and deep neural network (DNN), were compared in terms of prediction accuracy. Images of the workpiece surface profile were captured using high-resolution camera with the aid of backlighting after each machining pass. Workpiece surface profile images along a distance of two wavelengths were cropped and fed into the CNN network for wear prediction. For the DNN model, the surface height data were extracted to subpixel accuracy from each cropped image and used to train the model. Based on the results, the CNN model was able to predict the wear state with an accuracy of 98.9%, with an average testing RMSE of 2.0969, while the DNN model can predict wear state at an accuracy of 89.1%, with average testing RMSE of 2.5881. The study shows that cropped images of the machined surface profile can be more reliably used to predict the amount of tool flank wear during turning by using the CNN model compared to the height data used in the DNN model.
Similar content being viewed by others
Availability of data and material
The data will be made available upon request.
Code availability
The computer codes will be made available upon request.
References
Kurada S, Bradley C (1997) A review of machine vision sensors for tool condition monitoring. Comput Ind 34(1):55–72. https://doi.org/10.1016/s0166-3615(96)00075-9
Deng B, Peng F, Zhou L, Wang H, Yang M, Yan R (2020) A comprehensive study on flank wear progression of polycrystalline diamond micro-tool during micro end-milling of SiCp/Al composites. Wear 456–457:203291. https://doi.org/10.1016/j.wear.2020.203291
Rao KV, Kumar YP, Singh VK, Raju LS, Ranganayakulu K (2021) Vibration-based tool condition monitoring in milling of Ti-6Al-4V using an optimization model of GM(1, N) and SVM. Int J Adv Manuf Technol 115:1931–1941. https://doi.org/10.1007/s00170-021-07280-3
Zhou C, Guo K, Sun J (2021) An integrated wireless vibration sensing tool holder for milling tool condition monitoring with singularity analysis. Measurement 174:109038. https://doi.org/10.1016/j.measurement.2021.109038
Hassan M, Sadek A, Attia MH (2021) Novel sensor-based tool wear monitoring approach for seamless implementation in high-speed milling applications. CIRP Ann 70(1):87–90. https://doi.org/10.1016/j.cirp.2021.03.024
Yuan J, Liu L, Yang Z, Bo J, Zhang Y (2021) Tool wear condition monitoring by combining spindle motor current signal analysis and machined surface image processing. Int J Adv Manuf Technol 116:2697–2709. https://doi.org/10.1007/s00170-021-07366-y
Li Y, Liu C, Hua J, Gao J, Maropoulos P (2019) A novel method for accurately monitoring and predicting tool wear under varying cutting conditions based on meta-learning. CIRP Ann 68(1):487–490. https://doi.org/10.1016/j.cirp.2019.03.010
Xu X, Wang J, Zhong B, Ming W, Chen M (2021) Deep learning-based tool wear prediction and its application for machining process using multi-scale feature fusion and channel attention mechanism. Measurement 177:109254. https://doi.org/10.1016/j.measurement.2021.109254
Sun H, Zhang J, Mo R, Zhang X (2020) In-process tool condition forecasting based on a deep learning method. Robot Comput Integr Manuf 64:101924. https://doi.org/10.1016/j.rcim.2019.101924
He Z, Shi T, Xuan J, Li T (2021) Research on tool wear prediction based on temperature signals and deep learning. Wear 478–479:203902. https://doi.org/10.1016/j.wear.2021.203902
Wang D, Hong R, Lin X (2021) A method for predicting hobbing tool wear based on CNC real-time monitoring data and deep learning. Precis Eng 72:847–857. https://doi.org/10.1016/j.precisioneng.2021.08.010
Ma J, Luo D, Liao X, Zhang Z, Huang Y, Lu J (2021) Tool wear mechanism and prediction in milling TC18 titanium alloy using deep learning. Measurement 173:108554. https://doi.org/10.1016/j.measurement.2020.108554
Ou J, Li H, Huang G, Yang G (2020) Intelligent analysis of tool wear state using stacked denoising autoencoder with online sequential-extreme learning machine. Measurement 167:108153. https://doi.org/10.1016/j.measurement.2020.108153
Liu X, Liu S, Li X, Zhang B, Yue C, Liang SY (2021) Intelligent tool wear monitoring based on parallel residual and stacked bidirectional long short-term memory network. J Manuf Syst 60:608–619. https://doi.org/10.1016/j.jmsy.2021.06.006
Bombiński S, Kossakowska J, Jemielniak K (2022) Detection of accelerated tool wear in turning. Mech Syst Signal Process 162:108021. https://doi.org/10.1016/j.ymssp.2021.108021
Lee WK, Ratnam MM, Ahmad ZA (2017) Detection of chipping in ceramic cutting inserts from workpiece profile during turning using fast Fourier transform (FFT) and continuous wavelet transform (CWT). Precis Eng 47:406–423. https://doi.org/10.1016/j.precisioneng.2016.09.014
Wang P, Liu Z, Gao RX, Guo Y (2019) Heterogeneous data-driven hybrid machine learning for tool condition prognosis. CIRP Ann 68(1):455–458. https://doi.org/10.1016/j.cirp.2019.03.007
Shahabi HH, Ratnam MM (2009) Assessment of flank wear and nose radius wear from workpiece roughness profile in turning operation using machine vision. Int J Adv Manuf Technol 43(1–2):11–21. https://doi.org/10.1007/s00170-008-1688-x
Derani MN, Ratnam MM, Nasir RM (2021) Improved measure of workpiece surface deterioration during turning using non-contact vision method. Precis Eng 68:273–284. https://doi.org/10.1016/j.precisioneng.2020.12.016
Bergs T, Holst C, Gupta P, Augspurger T (2020) Digital image processing with deep learning for automated cutting tool wear detection. Procedia Manuf 48:947–958. https://doi.org/10.1016/j.promfg.2020.05.134
Li X, Yang Y, Ye Y, Ma S, Hu T (2021) An online visual measurement method for workpiece dimension based on deep learning. Measurement 185:110032. https://doi.org/10.1016/j.measurement.2021.110032
Lutz B, Reisch R, Kisskalt D, Avci B, Regulin D, Knoll A, Franke J (2020) Benchmark of automated machine learning with state-of-the-art image segmentation algorithms for tool condition monitoring. Procedia Manuf 51:215–221. https://doi.org/10.1016/j.promfg.2020.10.031
Liu Y, Guo L, Gao H, You Z, Ye Y, Zhang B (2022) Machine vision-based condition monitoring and fault diagnosis of machine tools using information from machined surface texture: a review. Mech Syst Signal Process 164:108068. https://doi.org/10.1016/j.ymssp.2021.108068
Tabatabai AJ, Mitchell OR (1984) Edge location to sub-pixel values in digital imagery. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI- 6(2):188–201
Kingma D, Ba J (2015) ADAM: a method for stochastic optimization. Computer Science, Mathematics (CoRR), 1412.6980 International Conference on Learning Representations. May 7–9, San Diego, CA
Funding
This work was supported by the Fundamental Research Grant (FRGS) offered by the Ministry of Education, Malaysia (Project code: FRGS/1/2019/TK03/USM/01/1).
Author information
Authors and Affiliations
Contributions
Meng Lip Lim carried out the deep learning analysis and wrote the first draft (50%). Mohd Naqib Derani carried out the experimental work (15%). Mani Maran Ratnam guided the work and corrected the draft (30%). Ahmad Razlan Yusoff checked the final draft and recommended revision (5%).
Corresponding author
Ethics declarations
Ethics approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
The authors give their consent for publication.
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Lim, M.L., Derani, M.N., Ratnam, M.M. et al. Tool wear prediction in turning using workpiece surface profile images and deep learning neural networks. Int J Adv Manuf Technol 120, 8045–8062 (2022). https://doi.org/10.1007/s00170-022-09257-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-022-09257-2