Abstract
The mechanistic force model is one of the most common methods used to predict cutting forces in milling processes. In this model, the cutting forces are considered a function of cutting geometry and the material properties of the tool and workpiece, generally known as cutting coefficients. These coefficients are commonly identified by performing special calibration tests and are applied to predict cutting forces for other conditions. Although the mechanistic model is a powerful tool for predicting cutting forces, its accuracy decreases as the cutter-workpiece engagement geometry differs from the calibration tests. Thus, it is necessary to update the cutting coefficients to preserve the accuracy of the model. This paper proposes a real-time intelligent method, named “the mechanistic network,” for identifying and updating the cutting coefficients. To this end, an analogy between the mechanistic force model and artificial neural networks is identified, in which the weight coefficients of the artificial neural networks have been replaced with the cutting coefficients. To identify and update the cutting coefficients, an algorithm is proposed using stochastic gradient descent, which updates the coefficients in each iteration. In addition, some other important parameters in milling processes, such as the phase shift between the measured and predicted forces and run-out parameters, are calculated using stochastic gradient descent. The good performance of the proposed network is shown through case studies by utilizing reliable data existing in the literature and also by performing ball-end milling experimental tests. The results show that the proposed network can predict the cutting forces with an error of less than 10% and update the cutting coefficients with a calculation speed of 125k iterations per second. The robustness of the network against noise that may arise in real machining conditions is also shown. The proposed mechanistic network is a reliable and efficient tool that can be applied to real-time applications such as cyber-physical manufacturing systems and condition monitoring of machining processes.
Similar content being viewed by others
Abbreviations
- Subscript: r, t, a :
-
Representation of radial, tangential, and axial directions
- Subscript: i :
-
Representation of element number
- \({z}_{i}\) :
-
Value of z coordinate with respect to ball-end center (mm)
- \(d{S}_{i}\) :
-
Length of the cutting-edge element (mm)
- \({h}_{i}\) :
-
Undeformed chip thickness (mm)
- \(d{b}_{i}\) :
-
Chip width (mm)
- \({K}_{re}\), \({K}_{te}\), \({K}_{ae}\) :
-
Edge coefficients (N/mm)
- \({K}_{rc}\), \({K}_{tc}\), \({K}_{ac}\) :
-
Shear coefficients (N/mm2)
- \({dF}_{ri}\), \({dF}_{ti}\), \({dF}_{ai}\) :
-
Differential cutting forces (N)
- \({C}_{n}^{re}\), \({C}_{n}^{te}\), \({C}_{n}^{ae}\) :
-
Edge constants (N/mm(n+1))
- \({C}_{n}^{rc}\), \({C}_{n}^{tc}\), \({C}_{n}^{ac}\) :
-
Shear constants (N/mm(n+2))
- \(\overrightarrow{{F}_{p}}\) :
-
Predicted force vector (N)
- \(\overrightarrow{{F}_{s}}\) :
-
Measured force vector (N)
- \({F}_{px}\), \({F}_{py}\), \({F}_{pz}\) :
-
Predicted force components (N)
- \({F}_{sx}\), \({F}_{sy}\), \({F}_{sz}\) :
-
Measured force components (N)
- \({\widehat{n}}_{r}\),\({\widehat{n}}_{t}\), \({\widehat{n}}_{a}\) :
-
Unit vectors
- \({\phi }_{i}\) :
-
Element angular position (rad)
- \(\phi\) :
-
Total rotation of the tool (rad)
- \({\Omega }_{s}\) :
-
Spindle speed (rpm)
- \({\beta }_{0}\) :
-
Helix angle (rad)
- \({R}_{0}\) :
-
Radius of the ball-end tool (mm)
- \({N}_{f}\) :
-
Total number of flutes
- \({n}_{f}\) :
-
Flute number
- \(E\) :
-
Objective error function (N2)
- \(e\) :
-
Run-out value (mm)
- \({\overrightarrow{e}}_{ij}\) :
-
The relative position of the tool center with respect to the ideal position (mm)
- \({\phi }_{p}\) :
-
Run-out angle (rad)
- \({\phi }_{p0}\) :
-
Run-out angle at \(t=0 (s)\) (rad)
- \({h}_{ei}\) :
-
Effect of run-out on the undeformed chip thickness (mm)
- \({h}_{0i}\) :
-
Undeformed chip thickness without the effect of run-out (mm)
References
Marei M, El Zaatari S, Li W (2021) Transfer learning enabled convolutional neural networks for estimating health state of cutting tools. Robot Comput-Integr Manuf 71:102145. https://doi.org/10.1016/j.rcim.2021.102145
Ghorbani M, Movahhedy MR (2019) Extraction of surface curvatures from tool path data and prediction of cutting forces in the finish milling of sculptured surfaces. J Manuf Process 45:273–289. https://doi.org/10.1016/j.jmapro.2019.07.008
Moufki A et al (2000) Thermoviscoplastic modelling of oblique cutting: forces and chip flow predictions. Int J Mech Sci 42(6):1205–1232. https://doi.org/10.1016/S0020-7403(99)00036-3
Tsai C-L, Liao Y-S (2008) Prediction of cutting forces in ball-end milling by means of geometric analysis. J Mater Process Technol 205(1–3):24–33. https://doi.org/10.1016/j.jmatprotec.2007.11.083
Mahnama M, Movahhedy M (2012) Application of FEM simulation of chip formation to stability analysis in orthogonal cutting process. J Manuf Process 14(3):188–194. https://doi.org/10.1016/j.jmapro.2011.12.007
Yücesan G, Altintaş Y (1994) Improved modelling of cutting force coefficients in peripheral milling. Int J Mach Tools Manuf 34(4):473–487. https://doi.org/10.1016/0890-6955(94)90079-5
Lee P, Altintaş Y (1996) Prediction of ball-end milling forces from orthogonal cutting data. Int J Mach Tools Manuf 36(9):1059–1072. https://doi.org/10.1016/0890-6955(95)00081-X
Shin YC, Waters AJ (1997) A new procedure to determine instantaneous cutting force coefficients for machining force prediction. Int J Mach Tools Manuf 37(9):1337–1351. https://doi.org/10.1016/S0890-6955(96)00093-4
Jayaram S, Kapoor S, DeVor R (2001) Estimation of the specific cutting pressures for mechanistic cutting force models. Int J Mach Tools Manuf 41(2):265–281. https://doi.org/10.1016/S0890-6955(00)00076-6
Azeem A, Feng H-Y, Wang L (2004) Simplified and efficient calibration of a mechanistic cutting force model for ball-end milling. Int J Mach Tools Manuf 44(2–3):291–298. https://doi.org/10.1016/j.ijmachtools.2003.09.007
Grossi N et al (2015) Speed-varying cutting force coefficient identification in milling. Precis Eng 42:321–334. https://doi.org/10.1016/j.precisioneng.2015.04.006
Dikshit MK, Puri AB, Maity A (2017) Analysis of cutting force coefficients in high-speed ball end milling at varying rotational speeds. Mach Sci Technol 21(3):416–435. https://doi.org/10.1080/10910344.2017.1284562
Yu G, Wang L, Wu J (2018) Prediction of chatter considering the effect of axial cutting depth on cutting force coefficients in end milling. Int J Adv Manuf Technol 96(9):3345–3354. https://doi.org/10.1007/s00170-018-1745-z
Ghorbani M, Movahhedy MR (2019) An analytical model for cutter-workpiece engagement calculation in ball-end finish milling of doubly curved surfaces. Int J Adv Manuf Technol 102(5):1635–1657. https://doi.org/10.1007/s00170-018-3188-y
Lazoglu I (2003) Sculpture surface machining: a generalized model of ball-end milling force system. Int J Mach Tools Manuf 43(5):453–462. https://doi.org/10.1016/S0890-6955(02)00302-4
Lazoglu I, Boz Y, Erdim H (2011) Five-axis milling mechanics for complex free form surfaces. CIRP Ann 60(1):117–120. https://doi.org/10.1016/j.cirp.2011.03.090
Xu K et al (2021) ForceNet: An offline cutting force prediction model based on neuro-physical learning approach. J Manuf Syst 61:1–15. https://doi.org/10.1016/j.jmsy.2021.08.001
Guo M et al (2018) An identification model of cutting force coefficients for five-axis ball-end milling. Int J Adv Manuf Technol 99(1):937–949. https://doi.org/10.1007/s00170-018-2451-6
Yau H-T et al (2022) Direct computation of instantaneous cutting force in real-time multi-axis NC simulation. Int J Adv Manuf Technol 119(11):6967–6978. https://doi.org/10.1007/s00170-021-08545-7
Su S et al (2021) An image-based approach to predict instantaneous cutting forces using convolutional neural networks in end milling operation. Int J Adv Manuf Technol 115(5):1657–1669. https://doi.org/10.1007/s00170-021-07156-6
Tukora B, Szalay T (2011) Real-time determination of cutting force coefficients without cutting geometry restriction. Int J Mach Tools Manuf 51(12):871–879. https://doi.org/10.1016/j.ijmachtools.2011.08.003
Wan M et al (2007) Efficient calibration of instantaneous cutting force coefficients and runout parameters for general end mills. Int J Mach Tools Manuf 47(11):1767–1776. https://doi.org/10.1016/j.ijmachtools.2006.06.012
Yao Z-Q et al (2013) A chatter free calibration method for determining cutter runout and cutting force coefficients in ball-end milling. J Mater Process Technol 213(9):1575–1587. https://doi.org/10.1016/j.jmatprotec.2013.03.023
Wojciechowski S (2015) The estimation of cutting forces and specific force coefficients during finishing ball end milling of inclined surfaces. Int J Mach Tools Manuf 89:110–123. https://doi.org/10.1016/j.ijmachtools.2014.10.006
Zheng CM, Kang Y-H (2021) Locating the angular position of measured milling forces to determine dual-mechanism global cutting constants. Int J Adv Manuf Technol 115(5):1517–1528. https://doi.org/10.1007/s00170-021-07157-5
Leal-Muñoz E et al (2018) Identification of the actual process parameters for finishing operations in peripheral milling. J Manuf Sci Eng 140(8):084502. https://doi.org/10.1115/1.4039917
Leal-Muñoz E et al (2018) Accuracy of a new online method for measuring machining parameters in milling. Measurement 128:170–179. https://doi.org/10.1016/j.measurement.2018.06.018
Yao Q et al (2018) Identification of cutting force coefficients in machining process considering cutter vibration. Mech Syst Signal Process 103:39–59. https://doi.org/10.1016/j.ymssp.2017.09.038
Yao Q et al (2018) On-line cutting force coefficients identification for bull-end milling process with vibration. Measurement 125:243–253. https://doi.org/10.1016/j.measurement.2018.04.084
Goodall P, Pantazis D, West A (2020) A cyber physical system for tool condition monitoring using electrical power and a mechanistic model. Comput Ind 118:103223. https://doi.org/10.1016/j.compind.2020.103223
Dotcheva M, Millward H, Lewis A (2008) The evaluation of cutting-force coefficients using surface error measurements. J Mater Process Technol 196(1–3):42–51. https://doi.org/10.1016/j.jmatprotec.2007.04.136
Mostaghimi H et al (2021) Reconstruction of cutting forces through fusion of accelerometer and spindle current signals. J Manuf Process 68:990–1003. https://doi.org/10.1016/j.jmapro.2021.06.007
Bernini L, Albertelli P, Monno M (2023) Mill condition monitoring based on instantaneous identification of specific force coefficients under variable cutting conditions. Mech Syst Signal Process 185:109820. https://doi.org/10.1016/j.ymssp.2022.109820
Ning L, Veldhuis SC (2006) Mechanistic modeling of ball end milling including tool wear. J Manuf Process 8(1):21–28. https://doi.org/10.1016/S1526-6125(06)70098-6
Liu T, Zhu K, Wang G (2020) Micro-milling tool wear monitoring under variable cutting parameters and runout using fast cutting force coefficient identification method. Int J Adv Manuf Technol 111(11):3175–3188. https://doi.org/10.1007/s00170-020-06272-z
Xie Y et al (2021) Digital twin for cutting tool: Modeling, application and service strategy. J Manuf Syst 58:305–312. https://doi.org/10.1016/j.jmsy.2020.08.007
Luo W et al (2020) A hybrid predictive maintenance approach for CNC machine tool driven by digital twin. Robot Comput-Integr Manuf 65:101974. https://doi.org/10.1016/j.rcim.2020.101974
Zheng CM et al (2022) In-process identification of milling parameters based on digital twin driven intelligent algorithm. Int J Adv Manuf Technol 121(9):6021–6033. https://doi.org/10.1007/s00170-022-09685-0
Tong X et al (2020) Real-time machining data application and service based on IMT digital twin. J Intell Manuf 31(5):1113–1132. https://doi.org/10.1007/s10845-019-01500-0
Zuperl U et al (2006) A generalized neural network model of ball-end milling force system. J Mater Process Technol 175(1–3):98–108. https://doi.org/10.1016/j.jmatprotec.2005.04.036
Vaishnav S, Agarwal A, Desai KA (2020) Machine learning-based instantaneous cutting force model for end milling operation. J Intell Manuf 31(6):1353–1366. https://doi.org/10.1007/s10845-019-01514-8
Wang J et al (2021) Milling force prediction model based on transfer learning and neural network. J Intell Manuf 32(4):947–956. https://doi.org/10.1007/s10845-020-01595-w
Forootan M, Akbari J, Ghorbani M (2023) A new geometric approach for real-time cutting force simulation in 3-axis ball-end milling compatible with graphical game engines. Int J Adv Manuf Technol 1–20. https://doi.org/10.1007/s00170-023-12025-5
Sra S, Nowozin S, Wright SJ (2012) Optimization for machine learning. Mit Press. https://www.google.com/books/edition/Optimization_for_Machine_Learning/JPQx7s2L1A8C?hl=en
Fontaine M et al (2007) Modelling of cutting forces in ball-end milling with tool–surface inclination: part I: predictive force model and experimental validation. J Mater Process Technol 189(1–3):73–84. https://doi.org/10.1016/j.jmatprotec.2007.01.006
Author information
Authors and Affiliations
Contributions
Mahmoodreza Forootan: conceptualization, methodology, software, validation, writing—original draft, and writing—review and editing. Javad Akbari: supervision and writing—review and editing. Mohammad Ghorbani: supervision, validation, and writing—review and editing.
Corresponding author
Ethics declarations
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
Forootan, M., Akbari, J. & Ghorbani, M. A real-time intelligent method to identify mechanistic cutting force coefficients in 3-axis ball-end milling process using stochastic gradient decent: the mechanistic network. Int J Adv Manuf Technol 129, 2949–2968 (2023). https://doi.org/10.1007/s00170-023-12460-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-023-12460-4