Computational performance comparison of multiple regression analysis, artificial neural network and machine learning models in turning of GFRP composites with brazed tungsten carbide tipped tool

Gadagi, A. Amith; Adake, B. Chandrashekar

doi:10.22061/jcarme.2022.8684.2164

تعداد نشریات	11
تعداد شماره‌ها	237
تعداد مقالات	2,398
تعداد مشاهده مقاله	3,831,355
تعداد دریافت فایل اصل مقاله	2,775,952

	Computational performance comparison of multiple regression analysis, artificial neural network and machine learning models in turning of GFRP composites with brazed tungsten carbide tipped tool
Journal of Computational & Applied Research in Mechanical Engineering (JCARME)
مقاله 1، دوره 12، شماره 2 - شماره پیاپی 24، فروردین 2023، صفحه 133-143 اصل مقاله (657.52 K)
نوع مقاله: Research Paper
شناسه دیجیتال (DOI): 10.22061/jcarme.2022.8684.2164
نویسندگان
A. Amith Gadagi^* ؛ B. Chandrashekar Adake
Department of Mechanical Engineering, KLE Dr. M. S. Sheshgiri College of Engineering & Technology, Belagavi, Karnataka, 590008, India
تاریخ دریافت: 21 آذر 1400، تاریخ بازنگری: 22 شهریور 1401، تاریخ پذیرش: 02 مهر 1401
چکیده
In a turning process, it is essential to predict and choose appropriate process parameters to get a component’s proper surface roughness (R_a). In this paper, the prediction of R_a through the artificial neural network (ANN), multiple regression analysis (MRA), and random forest method (machine learning) are made and compared. Using the process variables such as feed rate, spindle speed, and depth of cut, the turning process of glass fiber-reinforced plastic (GFRP) composite specimens is conducted on a conventional lathe with the help of a single-point HSS turning tool brazed with a carbide tip. The surface roughness of turned GFRP components is measured experimentally using the Talysurf method. By utilizing Taguchi's L27 array, the experiments are carried out and the experimental results are utilized in the development of MRA, ANN, and random forest method models for predicting the R_a. It is observed that the mean absolute error (MAE) of MRA, ANN and random forest for the training cases are found to be 39.33%, 0.56%, and 24.88%, respectively whereas for the test cases MAE is 54.34%, 2.59%, and 24.88% for MRA, ANN, and random forest, respectively.
کلیدواژه‌ها
Machining؛ Neural networks؛ Machine learning؛ Regression analysis

مراجع
[1] D.T. Hull and W. Clyne,“An introduction to composite materials,” 2^nd ed., Cambridge univ. press, (1996). [2] T. Rajasekaran, K. Palanikumar and B.K. Vinayagam, “Turning CFRP composites with Ceramic tool for Surface Roughness Analysis,” Procedia Eng., Vol. 38,No.1pp.2922–2929, (2012). [3] P.M.M.S. Sarma, L. Karunamoorthy and K. Palanikumar, “Surface Roughness Parameters Evaluation in Machining GFRP Composites by PCD Tool using Digital Image Processing,” J. Reinf. Plast.Compos., Vol. 28, No.13,pp.1567-1585, (2009). [4] K. Palanikumar, B. Latha, V. S. Senthilkumar and J. P. Davim, “Analysis on Drilling of Glass Fiber–Reinforced Polymer (GFRP) Composites Using Grey Relational Analysis,” Mater. Manuf. Processes, Vol. 27, No.3,pp. 297-305,(2012). [5] I.S.N.V.R. Prashanth and B. Chandra Mouli, “Critical Analysis in Milling of GFRP Composites by Various End Mill Tools,” Mater. Today:. Proc., Vol. 5, No.6, pp.14607-14617, (2018). [6] A. I. Azmi, R.J.T. Lin and D. Bhattacharyya, “Experimental Study of Machinability of GFRP Composites by End Milling,” Mater. Manuf. Processes, Vol. 27,No.10,pp. 1045-1050, (2012). [7] I.Shivakoti, G.Kibria, P. M.Pradhan, B. B. Pradhan and A.Sharma, “ANFIS based prediction and parametric analysis during turning operation of Stainless Steel 202,” Mater. Manuf. Processes, Vol.34, No.1, pp.112-121, (2019). [8] N. Manikandan, K. Balasubramanian, D. Palanisamy, P.M. Gopal, D. Arul Kirubakaran and J.S.Bihoj, “Machinability analysis and ANFIS modelling on Advanced Machining of Hybrid Metal Matrix composite for Aerospace applications,”Mater. Manuf. Processes, Vol.34, No.16, pp. 1866-1881, (2019). [9] K.Balasubramanian, M. Nataraj and P. Duraisamy, “Machinability analysis and application of response surface approach on CNC turning of Lm6/sicp composites,”Mater. Manuf. Processes, Vol.34, No.12, pp.1389-1400, (2019). [10] V. Varghese, M.K. Ramesh and D. Chakradhar, “Experimental Investigation and optimization of machining parameters for sustainable machining,”Mater. Manuf. Processes, Vol. 33, No.16, pp.1782-1792, (2018). [11] D.Priyadarshi and R.Kumarsharma, “Optimization for turning of Al6061-Sic-Gr Hybrid Nanocomposites using Response Surface Methodology”,Mater. Manuf. Processes, Vol.31, No.10, pp.1342-1350, (2016). [12] V. Mukkoti, G. Sankaraiah and M. Yohan, “Effect of cryogenic treatment of Tungsten carbide tools on Cutting force and power consumption in CNC milling process,”Mater. Manuf. Processes, Vol.6, No.1, pp.149-170, (2018). [13]K. Palanikumar, L. Karunamoorthy, R. Karthikeyan and B. Latha,“Optimization of machining parameters in turning GFRP composites using a carbide (K10) tool based on the taguchi method with fuzzy logics,” Met. Mater., Vol.12, No.6, pp.483-491, (2006). [14] K. Palanikumar, L. Karunamoorthy and R.Karthikeyan, “Multiple Performance Optimization of Machining Parameters on the Machining of GFRP Composites Using Carbide (K10) Tool,” Mater. Manuf. Processes, Vol.21, No.8, pp.846-852, (2006). [15] H.Charukar and T. L. Schmitz, “A neural network approach for chatter prediction in turning,”Procedia Manufacturing, Vol.34, No. 1, pp. 885-892, (2019). [16] B.Goel, S. Singh andR. V.Sarepaka, “Optimizing single point diamond turning for mono crystalline Germanium using Grey regression Analysis,”Mater. Manuf. Processes, Vol.30, No.8, pp.1018-1025, (2015). [17]R. Ferreria, D. Carou, C.H.Lauro and J.P.Davim, “Surface roughness investigation in the hard turning of steel using Ceramic tools,” Mater. Manuf. Processes, Vol.31, No.5, pp. 648-652, (2016). [18] P. M. M. S. Sarma, L. Karunamoorthy and K. Palanikumar,, “Modeling and Analysis of Cutting Force in Turning of GFRP Composites by CBN Tools,” J. Reinf. Plast. Compos., Vol. 27, No.7, pp. 711-723, (2008). [19] P. Mistry, D. Neagu, P. R. Trundle and J. D. Vessey, “Using random forest and decision tree models for a new vehicle prediction approach in computational toxicology,” Soft Computing, Vol.20, No. 8, pp. 2967–2979, (2016). [20] P. Zhou, Z. Li, S. Snowling, B. W. Baetz, D. Na and G. Boyd, “A random forest model for inflow prediction at wastewater treatment plants,” Stoch Environ Res Risk Assess, Vol.33, No. 10, pp. 1781–1792, (2019). [21] J. Zhang, M. Li, Y. Feng and C. Yang, “Robotic grasp detection based on image processing and random forest,” Multimed Tools Appl, Vol.79, No.3, pp. 2427–2446, (2020). [22] S. Kwak, J. Kim, H. Ding, X. Xu, R. Chen, J. Guo and H. Fu, “Machine learning prediction of the mechanical properties of γ-TiAl alloys produced using random forest regression model,” Journal of Materials Research and Technology, Vol. 18, No.1, pp. 520-530, (2022). [23] J. Wang, Z. Song, L. Chen, T. Xu, L. Deng and Z. Qi, “Prediction of CO2 solubility in deep eutectic solvents using random forest model based on COSMO-RS-derived descriptors,” Green Chemical Engineering, Vol. 2, No.4, pp. 431-440, (2021). [24] Y. Liu, S. Chen, J. Ye, Y. Xian, X. Wang, J. Xuan, N. Tan, Q. Li, J. Chen and Z. Ni,“ Random forest for prediction of contrast-induced nephropathy following coronary angiography,” Int J Cardiovasc Imaging, Vol. 36, No.6, pp. 983–991, (2020). [25] F. J. Pontes, A. P. de Paiva, P. P.Balestrassi, J. R. Ferreira and M. B. da Silva, “Optimization of Radial Basis Function neural network employed for prediction of surface roughness in hard turning process using Taguchi's orthogonal arrays,” Expert Systems with Applications, Vol.39, No.9, pp. 7776-7787, (2012).
آمار تعداد مشاهده مقاله: 1,075 تعداد دریافت فایل اصل مقاله: 953

سامانه مدیریت نشریات علمی. طراحی و پیاده سازی از سیناوب

پیوندهای مفید

آمار

Computational performance comparison of multiple regression analysis, artificial neural network and machine learning models in turning of GFRP composites with brazed tungsten carbide tipped tool