Abstract
Accurate prediction of the machining quality such as the surface roughness is one of the main objectives of the intelligent manufacturing research. In this study, we investigate the feasibility of combining milling stability analysis and a back propagation (BP) neural network model to predict the surface roughness of aerospace aluminum alloy 7075Al in high-speed precision milling. The difference between the critical depth of cut obtained from the milling stability lobe diagram (SLD) and the actual depth of cut (termed the “chatter stability feature”) was used as a critical input variable of the neural network model, thereby improving its prediction performance. It is demonstrated that the proposed chatter stability feature has a strong correlation with the surface roughness, making it an information-rich input feature of the prediction model. The experimental results show that the prediction accuracy can be improved by 7.8% compared with a neural network model that only uses the cutting parameters (i.e., spindle speed, feed rate, depth of cut, and feed rate per tooth) as predictors. In addition, univariate and multivariate sensitivity analysis results suggest that the performance of the proposed approach is robust to errors in the SLD measurements. Compared to conventional methods which only consider the cutting parameters, an improvement in prediction accuracy can be expected with up to 10% errors in modal parameters.
Similar content being viewed by others
References
Çolak O, Kurbanoğlu C, Kayacan MC (2007) Milling surface roughness prediction using evolutionary programming methods. Mater Des 28(2):657–66. https://doi.org/10.1016/j.matdes.2005.07.004
Muñoz-Escalona P, Maropoulos PG (2010) Artificial neural networks for surface roughness prediction when face milling Al 7075-T7351. J Mater Eng Perform 19(2):185–93. https://doi.org/10.1007/s11665-009-9452-4
Quintana G, Jd Ciurana, Ribatallada J (2010) Surface roughness generation and material removal rate in ball end milling operations. Mater Manu Processes 25(6):386–98. https://doi.org/10.1080/15394450902996601
Bachrathy D, Insperger T, Stépán G (2009) Surface properties of the machined workpiece for helical mills. Mach Sci Technol 13(2):227–45. https://doi.org/10.1080/10910340903012167
Karayel D (2009) Prediction and control of surface roughness in CNC lathe using artificial neural network. J Mater Process Technol 209:3125–3137. https://doi.org/10.1016/j.jmatprotec.2008.07.023
Asiltürk I, Çunkaş M (2011) Modeling and prediction of surface roughness in turning operations using artificial neural network and multiple regression method. Expert Syst Appl 38:5826–5832. https://doi.org/10.1016/j.eswa.2010.11.041
Bajić D, Lela B, Z̆ivković D (2008) Modeling of machined surface roughness and optimization of cutting parameters in face milling. Metalurgija 47:331–334
Groove M (1996) Fundamentals of modern manufacturing, Prentice Hall, Upper Saddle River
Lela B, Bajić D, Jozić S (2009) Regression analysis, support vector machines, and Bayesian neural network approaches to modeling surface roughness in face milling. Int J Adv Manufact Technol 42:1082–1088. https://doi.org/10.1007/s00170-008-1678-z
Abu-Mahfouz I, El Ariss O, Esfakur Rahman AHM, Banerjee A (2017) Surface roughness prediction as a classification problem using support vector machine. Int J Adv Manufact Technol 92:803–815. https://doi.org/10.1007/s00170-017-0165-9
Tangjitsitcharoen S, Thesniyom P, Ratanakuakangwan S (2017) Prediction of surface roughness in ball-end milling process by utilizing dynamic cutting force ratio. J Intell Manuf 28(1):13–21. https://doi.org/10.1007/s10845-014-0958-8
Lou SJ, Chen JC (1999) In-process surface roughness recognition (ISRR) system in end-milling operations. Int J Adv Manufact Technol 15:200–209. https://doi.org/10.1007/s001700050057
Pan Y, Wang Y, Zhou P, Yan Y, Guo D (2020) Activation functions selection for BP neural network model of ground surface roughness. J Intell Manuf 31(8):1825–36. https://doi.org/10.1007/s10845-020-01538-5
Markopoulos AP, Georgiopoulos S, Manolakos DE (2016) On the use of back propagation and radial basis function neural networks in surface roughness prediction. J Ind Eng Int 12(3):389–400. https://doi.org/10.1007/s40092-016-0146-x
Kao YC, Chen SJ, Vi TK, Feng GH, Tsai SY (2021) Study of milling machining roughness prediction based on cutting force. IOP Conf Ser: Mater Sci Eng 1009(1):012027. https://doi.org/10.1088/1757-899X/1009/1/012027
Quintana G, Ciurana J (2011) Chatter in machining processes: a review. Int J Mach Tools Manuf 51:363–376. https://doi.org/10.1016/j.ijmachtools.2011.01.001
Özşahin O, Budak E, Özgüven HN (2015) Identification of bearing dynamics under operational conditions for chatter stability prediction in high speed machining operations. Precis Eng 42:53–65. https://doi.org/10.1016/j.precisioneng.2015.03.010
Wang D, Löser M, Ihlenfeldt S, Wang X, Liu Z (2019) Milling stability analysis with considering process damping and mode shapes of in-process thin-walled workpiece. Int J Mech Sci 159:382–397. https://doi.org/10.1016/j.ijmecsci.2019.06.005
Altintaş Y, Budak E (1995) Analytical prediction of stability lobes in milling. CIRP Ann 44:357–362. https://doi.org/10.1016/S0007-8506(07)62342-7
Pour M, Torabizadeh MA (2016) Improved prediction of stability lobes in milling process using time series analysis. J Intell Manuf 27:665–677. https://doi.org/10.1007/s10845-014-0904-9
Nguyen V, Melkote S (2021) Hybrid statistical modelling of the frequency response function of industrial robots. Rob Comput Integr Manuf 70:102134. https://doi.org/10.1016/j.rcim.2021.102134
Wu Y, Feng J (2018) Development and application of artificial neural network. Wirel Pers Commun 102:1645–1656. https://doi.org/10.1007/s11277-017-5224-x
Srikant RR, Krishna PV, Rao ND (2011) Online tool wear prediction in wet machining using modified back propagation neural network. Proc Inst Mech Eng. Part B: J Eng Manuf 225(7):1009–18. https://doi.org/10.1177/0954405410395854
Guo T, Meng L, Cao J, Bai C (2020) An identification method of the weak link of stiffness for cantilever beam structure. Sci Prog 103(3):0036850420952671. https://doi.org/10.1177/0036850420952671
Totis G, Sortino M (2020) Polynomial Chaos-Kriging approaches for an efficient probabilistic chatter prediction in milling. Int J Mach Tool Manufact 157:103610. https://doi.org/10.1016/j.ijmachtools.2020.103610
Misaka T, Herwan J, Ryabov O, Kano S, Sawada H, Kasashima N et al (2020) Prediction of surface roughness in CNC turning by model-assisted response surface method. Precis Eng 62:196–203. https://doi.org/10.1016/j.precisioneng.2019.12.004
Funding
This work is supported by the National Key R&D Program of China (Grant No. 2020YFB1710400), the National Natural Science Foundation of China (Grant No. 52005205), and the National Science Fund for Distinguished Young Scholars (Grant No. 52225506).
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Material preparation, data collection, and analysis were performed by Long Bai, Xin Cheng, and Qizhong Yang. The first draft and revised version of the manuscript were written by Long Bai and Xin Cheng.
Corresponding author
Ethics declarations
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
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
Bai, L., Cheng, X., Yang, Q. et al. Predictive model of surface roughness in milling of 7075Al based on chatter stability analysis and back propagation neural network. Int J Adv Manuf Technol 126, 1347–1361 (2023). https://doi.org/10.1007/s00170-023-11133-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-023-11133-6