Abstract
Cutting force detection can contribute to predicting the productivity and quality of end milling operations. Instantaneous cutting force prediction of digital twins in end milling operations should be near real-time and accurate. This paper proposes an image-based approach that can contain more useful information due to a higher dimension and simplify the complexity of computing geometric data. The cutter frame image (CFI) is utilized as one of the inputs of a convolutional neural network (CNN) to predict instantaneous cutting forces. Considering the convenience of capturing massive data, the approach uses cutting forces generated from a mechanistic force model instead of experimental cutting forces to train the CNN. The correlation coefficient R2 value between predicted results and simulated results is 0.9999 and the average time cost per image is 0.057 s in a cutting condition, which validates the possibility to use the image-based method to predict instantaneous cutting forces accurately and efficiently in the digital twin.
Similar content being viewed by others
Abbreviations
- NN :
-
Neural network
- ANN :
-
Artificial neural network
- CNN :
-
Convolutional neural network
- CWEs :
-
Cutter-workpiece engagements
- CFI :
-
Cutter frame image
- FEM :
-
Finite element method
- AABB :
-
Axis-aligned bounding box
- ADOC :
-
Axial depth of cutting
- RDOC :
-
Radial depth of cutting
- MSE :
-
Mean squared error
- RMSE :
-
Root mean squared error
- R 2 :
-
Correlation coefficient
- SGD :
-
Stochastic gradient descent
- Adam :
-
Adaptive moment estimation
- φ(i,j,k):
-
Immersion angle
- φ st :
-
Reference immersion angle
- Ω :
-
Spindle speed
- φ p :
-
Pitch angle between each tooth
- ψ p :
-
Lag angle
- dF t :
-
Differential tangential cutting force
- dF r :
-
Differential radial cutting force
- dF a :
-
Differential axial cutting force
- K tc :
-
Tangential shear force coefficient
- K rc :
-
Radial shear force coefficient
- K ac :
-
Axial shear force coefficient
- K te :
-
Tangential edge force coefficient
- K re :
-
Radial edge force coefficient
- K ae :
-
Axial edge force coefficient
- h :
-
Instantaneous cutting thickness
- dz :
-
Depth of the infinitesimal flute segment
- ds :
-
Length of the infinitesimal flute segment
- S :
-
Initial width of the CFI
- T :
-
Initial height of the CFI
- W :
-
Final width and height of the CFI
- λ :
-
Resolution of the CFI
- β 0 :
-
Helix angle
- c :
-
Feed rate
- ρ j :
-
jth cutting tool position
- ρ j+ 1 :
-
j + 1th cutting tool position
References
Aghazadeh F, Tahan A, Thomas M (2018) Tool condition monitoring using spectral subtraction and convolutional neural networks in milling process. Int J Adv Manuf Technol 98:3217–3227
Akıncıoğlu S, Mendi F, Çiçek A, Akıncıoğlu G (2013) Ann-based prediction of surface and hole quality in drilling of aisi d2 cold work tool steel. Int J Adv Manuf Technol 68(1):197– 207
AltintaĹs Y, Lee P (1996) A general mechanics and dynamics model for helical end mills. CIRP Ann 45(1):59–64
Benouamer MO, Michelucci D (1997) Bridging the gap between csg and brep via a triple ray representation. In: Proceedings of the fourth ACM symposium on solid modeling and applications, p 68–79. Association for Computing Machinery
Budak E, Altinta Y, Armarego EJA (1996) Prediction of milling force coefficients from orthogonal cutting data. J Manufac Sci Eng 118(2):216–224
Engin S, Altintas Y (2001) Mechanics and dynamics of general milling cutters: Part i: helical end mills. Int J Mach Tools Manuf 41(15):2195–2212
Ferry WB, Altintas Y (2008) Virtual five-axis flank milling of jet engine impellers part i: Mechanics of five-axis flank milling. J Manufac Sci Eng 130(1):011005
Fu Y, Zhang Y, Gao Y, Gao H, Mao T, Zhou H, Li D (2017) Machining vibration states monitoring based on image representation using convolutional neural networks. Eng Appl Artif Intel 65:240–251
Fussell B, Jerard R, Hemmett J (2000) Robust Feedrate Selection for 3-Axis NC Machining Using Discrete Models. J Manuf Sci Eng 123(2):214–224
Fussell B, Jerard R, Hemmett J (2003) Modeling of cutting geometry and forces for 5-axis sculptured surface machining. Comput Aided Des 35(4):333–346
Huang Z, Zhu J, Lei J, Li X, Tian F (2020) Tool wear predicting based on multi-domain feature fusion by deep convolutional neural network in milling operations. J Intell Manuf 31:953–266
Koenigsberger F, Tlusty J (1970) Chapter 2 - static and dynamic stiffness. In: Machine tool structures, pp 1–100
Li ZL, Zhu LM (2016) Mechanistic modeling of five-axis machining with a flat end mill considering bottom edge cutting effect. J Manuf Sci Eng 138(11):111012
Merchant EM (1945) Mechanics of the metal cutting process. ii. plasticity conditions in orthogonal cutting. J Appl Phys 16(6):318–324
Perez H, Diez E, Marquez JJ, Vizan A (2013) An enhanced method for cutting force estimation in peripheral milling. Int J Adv Manuf Technol 69(5):1731–1741
Szecsi T (1999) Cutting force modeling using artificial neural networks. J Mater Process Technol 92-93:344–349
Vaishnav S, Agarwal A, Desai KA (2020) Machine learning-based instantaneous cutting force model for end milling operation. J Intell Manuf 31:1353–1366
Van Hook T (1986) Real-time shaded nc milling display. SIGGRAPH Comput Graph 20(4):15–20
Yoon M, Kim Y (2004) Cutting dynamic force modelling of endmilling operation. J Mater Process Technol 155-156:1383–1389
Yun WS, Cho DW (2001) Accurate 3-d cutting force prediction using cutting condition independent coefficients in end milling. Int J Mach Tools Manuf 41(4):463–478
Zuperl U, Cus F (2004) Tool cutting force modeling in ball-end milling using multilevel perceptron. J Mater Process Technol 153-154:268–275
Funding
This work was supported by the Ministry of Industry and Information Technology of the People’s Republic of China.
Author information
Authors and Affiliations
Corresponding author
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
Su, S., Zhao, G., Xiao, W. et al. An image-based approach to predict instantaneous cutting forces using convolutional neural networks in end milling operation. Int J Adv Manuf Technol 115, 1657–1669 (2021). https://doi.org/10.1007/s00170-021-07156-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-021-07156-6