Prediction of product roughness, profile, and roundness using machine learning techniques for a hard turning process

Abstract

High product quality is one of key demands of customers in the field of manufacturing such as computer numerical control (CNC) machining. Quality monitoring and prediction is of great importance to assure high-quality or zero defect production. In this work, we consider roughness parameter R _a, profile deviation P _t and roundness deviation R _ONt of the machined products by a lathe. Intrinsically, these three parameters are much related to the machine spindle parameters of preload, temperature, and rotations per minute (RPMs), while in this paper, spindle vibration and cutting force are taken as inputs and used to predict the three quality parameters. Power spectral density (PSD) based feature extraction, the method to generate compact and well-correlated features, is proposed in details in this paper. Using the efficient features, neural network based machine learning technique turns out to be able to result in high prediction accuracy with R ² score of 0.92 for roughness, 0.86 for profile, and 0.95 for roundness.

Keywords

Computer numerical control (CNC) machining / Quality prediction / Roughness parameter / Profile deviation / Roundness deviation / Machine learning

References

[1] Saravanan S, Yadava GS, Rao PV. Condition monitoring studies on spindle bearing of a lathe. Int J Adv Manuf Technol, 2006, 28: 993-1005.

[2] Kumar NS, Shetty A, Shetty A, et al. Effect of spindle speed and feed rate on surface roughness of carbon steels in CNC turning. Procedia Eng, 2012, 38: 691-697.

[3] Thakkar J, Patel MI. A review on optimization of process parameters for surface roughness and material removal rate for SS 410 material during turning operation. Int J Eng Res Appl, 2014, 4(2): 235-242.

[4] Singh M, Gangopadhyay S (2017) Effect of cutting parameter and cutting environment on surface integrity during machining of Nimonic C-263a Ni based superalloy. In: International conference on advances in mechanical, industrial, automation and management systems, Motilal Nehru national institute of technology Allahabad, India, 3–5 February, pp 231–238

[5] Janahiraman TV, Ahmad N (2014) An optimal-pruned extreme learning machine based modeling of surface roughness. In: International conference on information technology and multimedia (ICIMU), Pultrajaya, Malaysia, 18–20 November

[6] Al Hazza MH, Adesta EY, Seder AM (2015) Using soft computing methods as an effective tool in predicting surface roughness. In: 4th international conference on advanced computer science applications and technologies, pp 9–13

[7] Dahbi S, Ezzine L, El Moussami H (2016) Modeling of surface roughness in turning process by using artificial neural networks. In: 3rd international conference on logistics operations management (GOL), 23–25 May

[8] Lu C. Study on prediction of surface quality in machining process. J Mater Process Technol, 2008, 205: 439-450.

[9] Fang N, Pai PS, Edwards N (2016) Multidimensional signal processing and modeling with neural networks in metal machining: cutting forces, vibrations, and surface roughness. In: 8th IEEE international conference on communication software and networks, pp 77–80

[10] Zmarzly P. Technological heredity of the turning process. Tech Gaz, 2020, 27(4): 1194-1203.

[11] Suneel TS. Intelligent tool path correction for improving accuracy in CNC turning. Int J Prod Res, 2010, 38(14): 3181-3202.

[12] Şahinoğlu A, Karabulut Ş, Güllü A. Study on spindle vibration and surface finish in turning of Al 7075. Solid State Phenom, 2017, 261: 321-327.

[13] Kamble PD, Waghmare AC, Askhedkar RD, et al. Multi objective optimization of turning parameters considering spindle vibration by hybrid Taguchi principle component analysis (HTPCA). Mater Today, 2017, 4: 2077-2084.

[14] Shetty VM, Pallapothu M, Pothuganti VR. Experimental analysis on the influence of spindle vibrations of CNC lathe on surface roughness using Taguchi method. Int J Curr Eng Technol, 2015, 5(2): 1273-1276.

[15] Chang HK, Kim JH, Kim IH, et al. In-process surface roughness prediction using displacement signals from spindle motion. Int J Mach Tools Manuf, 2007, 47(6): 1021-1026.

[16] Lee J, Gao W, Shimizu Y, et al. Spindle error motion measurement of a large precision roll lathe. Int J Precis Eng Manuf, 2012, 13(6): 861-867.

[17] Maračeková M, Zvončan M, Görög A. Effect of clamping pressure on parts inaccuracy in turning. Technicki Vjesnik, 2012, 19(3): 509-512.

[18] Alfares MA, Elsharkawy AA. Effects of axial preloading of angular contact ball bearings on the dynamics of a grinding machine spindle system. J Mater Process Technol, 2003, 136: 48-59.

[19] Li Y, Zhao W, Lan S, et al. A review on spindle thermal error compensation in machine tools. Int J Mach Tools Manuf, 2015, 95: 20-38.

[20] Yang H, Ni J. Dynamic neural network modeling for nonlinear, nonstationary machine tool thermally induced error. Int J Mach Tools Manuf, 2005, 45(4): 455-465.

[21] Tseng PC, Ho JL. A study of high-precision CNC lathe thermal errors and compensation. Int J Adv Manuf Technol, 2002, 19: 850-858.

[22] Stępień K. Research on a surface texture analysis by digital signal processing methods. Teh Vjesn-Tech Gaz, 2014, 21(3): 485-493.

[23] Quick guide to surface roughness measurement. Reference guide for laboratory and workshop. https://www.mitutoyo.com/wp-content/uploads/2012/11/1984_Surf_Roughness_PG.pdf.

[24] Scikit-learn user guide, https://scikit-learn.org/stable/_downloads/scikit-learn-docs.pdf.

[25] Yan W, Zhou JH (2018) Early fault detection of aircraft components using flight sensor data. In: IEEE 23rd international conference on emerging technologies and factory automation, Turin, Italy, 4–7 September

[26] Tyagi S, Panigrahi SK. A comparative study of SVM classifiers and artificial neural networks application for rolling element bearing fault diagnosis using wavelet transform preprocessing. J Appl Comput Mech, 2017, 3(1): 80-91.