Abstract
Online monitoring of depths of cut (DOC) is an essential way to avoid machining defects, such as over-cutting and machining chatter. Data-driven machine learning method has been widely used to build the monitoring algorithms. However, deficient training data and un-interpretable algorithm make it difficult for application. Therefore, a physics-informed interpretable machine learning algorithm was proposed. Firstly, a physical simulation model incorporated with DOC was established with the rotation speed and feed speed as its inputs and time-domain signals of milling force as its outputs. The output force signals were quantitatively presented by time domain and frequency domain features. Secondly, six dimensionless features, namely the kurtosis, skewness, waveform factor, peak factor, pulse factor, and margin factor of the resultant milling force, were explored through sensitivity analysis method. They were sensitive to DOC but insensitive to milling force coefficient, speed, and feed speed. Then, a quantitative relationship model between features and DOC was established using the least squares linear regression algorithm, which has an intrinsic interpretability. Finally, the model was trained by a labeled 100-group experimental data. The results show that the accuracy of the proposed model for DOC monitoring is higher than 90%.
Similar content being viewed by others
Data availability
All data generated or analyzed during this study were available by emailing to author (sunl@just.edu.cn).
References
Liu Y, Kilic ZM, Altintas Y (2022) Monitoring of in-process force coefficients and tool wear. Cirp J Manuf Sci Technol 38:105–119. https://doi.org/10.1016/j.cirpj.2022.04.009
Sun W, Zhang D, Luo M (2021) Machining process monitoring and application: a review. Journal of Advanced Manufacturing. Sci Technol 1(2):2021001. https://doi.org/10.51393/j.jamst.2021001
Altintas Y, Yellowley I (1987) The identification of radial width and axial depth of cut in peripheral milling. Int J Machine Tools Manuf 27:367–381. https://doi.org/10.1016/S0890-6955(87)80010-X
Yang L, DeVor RE, Kapoor SG (2005) Analysis of force shape characteristics and detection of depth-of-cut variations in end milling. J Manuf Sci Eng 127:454–462. https://doi.org/10.1115/1.1947207
Jiang Z, Qi X, Sun Y et al (2020) Cutting depth monitoring based on milling force for robot-assisted laminectomy. IEEE Trans Autom Sci Eng 17:2–14. https://doi.org/10.1109/TASE.2019.2920133
Grossi N, Morelli L, Scippa A et al (2022) A frequency-based analysis of cutting force for depths of cut identification in peripheral end-milling. Mech Syst Signal Process 171:108943. https://doi.org/10.1016/j.ymssp.2022.108943
Choi J, Yang M (1999) In-process prediction of cutting depths in end milling. Int J Machine Tools Manuf 39:705–721. https://doi.org/10.1016/S0890-6955(98)00067-4
Leal-Munoz E, Diez E, Perez H et al (2018) Identification of the actual process parameters for finishing operations in peripheral milling. J Manuf Sci Eng Trans Asme 140. https://doi.org/10.1115/1.4039917
Leal-Munoz E, Diez E, Perez H et al (2018) Accuracy of a new online method for measuring machining parameters in milling. Measurement: J Int Meas Confed 128:170–179. https://doi.org/10.1016/j.measurement.2018.06.018
Prickett PW, Siddiqui RA, Grosvenor RI (2011) The development of an end-milling process depth of cut monitoring system. Int J Adv Manuf Technol 52:89–100. https://doi.org/10.1007/s00170-010-2711-6
Gaja H, Liou F (2016) Automatic detection of depth of cut during end milling operation using acoustic emission sensor. Int J Adv Manuf Technol 86:2913–2925. https://doi.org/10.1007/s00170-016-8395-9
Li X, Liu X, Yue C et al (2022) Systematic review on tool breakage monitoring techniques in machining operations. Int J Machine Tools Manuf 176:103882. https://doi.org/10.1016/j.ijmachtools.2022.103882
Nasir V, Sassani F (2021) A review on deep learning in machining and tool monitoring: methods, opportunities, and challenges. Int J Adv Manuf Technol 115:2683–2709. https://doi.org/10.1007/s00170-021-07325-7
Wang J, Xu C, Zhang J et al (2021) Big data analytics for intelligent manufacturing systems: a review. J Manuf Syst. https://doi.org/10.1016/j.jmsy.2021.03.005
Mozaffar M, Liao S, Xie X et al (2022) Mechanistic artificial intelligence (mechanistic-ai) for modeling, design, and control of advanced manufacturing processes: current state and perspectives. J Mater Process Technol 302:117485. https://doi.org/10.1016/j.jmatprotec.2021.117485
Wang J, Li Y, Zhao R et al (2020) (2020) Physics guided neural network for machining tool wear prediction. J Manuf Syst 57:298–310. https://doi.org/10.1016/j.jmsy.2020.09.005
Chen G, Li Y, Liu X et al (2021) Physics-informed Bayesian inference for milling stability analysis. Int J Machine Tools Manuf 167:103767. https://doi.org/10.1016/j.ijmachtools.2021.103767
Vogl GW, Regli DA et al (2022) Real-time estimation of cutting forces via physics-inspired data-driven model. CIRP Annals 71(1):317–320. https://doi.org/10.1016/j.cirp.2022.04.071
Guo H, Zhang Y, Zhu K (2022) Interpretable deep learning approach for tool wear monitoring in high-speed milling. Comput Ind 138:103638. https://doi.org/10.1016/j.compind.2022.103638
Xie J, Hu P, Chen J et al (2023) Deep learning-based instantaneous cutting force modeling of three-axis cnc milling. Int J Mech Sci 246:108153. https://doi.org/10.1016/j.ijmecsci.2023.108153
Li Y, Wang J, Huang Z et al (2022) Physics-informed meta learning for machining tool wear prediction. J Manuf Syst 62:17–27. https://doi.org/10.1016/j.jmsy.2021.10.013
Kline WA, DeVor RE, Lindberg JR (1982) The prediction of cutting forces in end milling with application to cornering cuts. Int J Machine Tool Design Res 22:7–22. https://doi.org/10.1016/0020-7357(82)90016-6
Cai S, Cai Z, Yao B et al (2021) Identifying the transient milling force coefficient of a slender end-milling cutter with vibrations. J Manuf Process 67:262–274. https://doi.org/10.1016/j.jmapro.2021.04.068
Duan Z, Li C, Ding W et al (2021) Milling force model for aviation aluminum alloy: academic insight and perspective analysis. Chin J Mech Eng 34:1–35. https://doi.org/10.1186/s10033-021-00536-9
Funding
This work was supported by the National Natural Science Foundation of China (62203193), the National Natural Science Foundation of China (51605207), and the General Project of Natural Science Research for Institutions of Higher Education of Jiangsu Province of China (21KJB510016)
Author information
Authors and Affiliations
Contributions
Guochao Li proposed the main analysis ideas, established the analysis framework, developed the physics simulation model, and helped to read and approve the final manuscript. Ru Jiang and Hao Zheng explored six dimensionless characteristics and established a quantitative relationship model between features and DOC. Shixian Xu and Li Sun provided analytical and linguistic guidance.
Corresponding author
Ethics declarations
Ethics approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
Not applicable.
Competing interests
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
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Li, G., Zheng, H., Jiang, R. et al. Physics-informed interpretable machine learning method for DOC monitoring in peripheral milling. Int J Adv Manuf Technol 132, 179–191 (2024). https://doi.org/10.1007/s00170-024-13364-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-024-13364-7