MACHINE LEARNING BASED PREDICTIVE MODEL FOR SURFACE ROUGHNESS IN CYLINDRICAL GRINDING OF AL BASED METAL MATRIX COMPOSITE

Abstract

The Metal Matrix Composite (MMC) technology of today is a challenging topic with novel developments. MMC materials have a key role in space, automotive, naval, and aviation industries and supplies of the defense industry owing to their superior specifications. Hence, advancing the machining quality of these materials is an essential point. This work presents a machine learning-based prediction model for the surface roughness of LM25/SiC/4p composite. The related dataset is linked to an MMC, which is machined with a cylindrical grinder, so the input parameters of the model are depth of cut, wheel velocity, feed, and velocity of the workpiece. The proposed model is based on a state of the art machine-learning method called Gaussian Process Regression (GPR). Alongside its robust performance in the small datasets, GPR has the ability with its Bayesian approach basis in providing uncertainty evaluation on the predicted values. Parameter optimization is also applied to the proposed GPR model. For a better evaluation of the GPR, a support vector machine-based prediction model is also tested. In addition to the data split test method, models are tested with a 5-fold cross-validation algorithm. The experimental results present that the proposed GPR model reaches an adequate accuracy in terms of R-square, root mean squared error, and mean absolute error criteria.

Keywords

• metal matrix composite
• machine learning
• surface roughness
• GPR prediction model

References

1. [1] Devarasiddappa, D., et al. (2012). Artificial neural network modeling for predicting surface roughness in end milling of Al-SiCp metal matrix composites and its evaluation. Journal of Applied Sciences 12, 955–962.
2. [2] Laghari, R.A, et al. (2019). A review on application of soft computing techniques in machining of particle reinforcement metal matrix composites. Archives of Computational Methods in Engineering, 1–15.
3. [3] Chandrasekaran, M., Devarasiddappa, D. (2014). Artificial neural network modeling for surface roughness prediction in cylindrical grinding of Al-SiC p metal matrix composites and ANOVA analysis. Advances in Production Engineering & Management, 9, 59–70. [4] Yakut, R., Ürkmez Taşkın, N. (2019). Production of AA7075/B4C composite materials by semi-solid stirring method. European Journal of Technique, 9, 230–240.
4. [5] Ürkmez Taşkın, N., et al. (2020). The effects of welding pressure and reinforcement ratio on welding strength in diffusion-bonded AlMg3/SiCp Composites. European Journal of Technique, 10,75–85.
5. [6] Conduit, B.D., et al. (2017). Design of a nickel-base superalloy using a neural network. Materials and Design, 131, 358–365.
6. [7] Chen, C-T, Gu, G.X. (2019). Machine learning for composite materials. MRS Communications, 9, 556–566.
7. [8] Agrawal, A., Choudhary, A. (2018). An online tool for predicting fatigue strength of steel alloys based on ensemble data mining. International Journal of Fatigue, 113, 389–400.
8. [9] Bock, F.E., et al. (2019). A review of the application of machine learning and data mining approaches in continuum materials mechanics. Frontiers in Materials, 6, 110.

9. [10] Yang, C., et al. (2020). Prediction of composite microstructure stress-strain curves using convolutional neural networks. Materials and Design, 189, 108509.
10. [11] Sizemore, N.E., et al. (2020). Application of machine learning to the prediction of surface roughness in diamond machining. Procedia Manufacturing, 48, 1029–1040.
11. [12] Ajith Arul Daniel, S., et al. (2019). Multi objective prediction and optimization of control parameters in the milling of aluminium hybrid metal matrix composites using ANN and Taguchi -grey relational analysis. Defence Technology, 15, 545–556.
12. [13] Phate, M.R., Toney, S.B. (2019). Modeling and prediction of WEDM performance parameters for Al/SiCp MMC using dimensional analysis and artificial neural network. Engineering Science and Technology, an Internatıonal Journal, 22, 468–476.
13. [14] Babalola, P.O., et al. (2017). Artificial neural network prediction of aluminium metal matrix composite with silicon carbide particles developed using stir casting method. Internatıonal Journal of Mechanical & Mechatronics Engineering, 15 (6), 151–159.
14. [15] Amirjan, M., et al. (2013). Artificial neural network prediction of Cu–Al2O3 composite properties prepared bypowder metallurgy method. Journal of Materials Research and Technology, 2 (4), 351–355.
15. [16] Varol, T., Ozsahin, S. (2019). Artificial neural network analysis of the effect of matrix size and milling time on the properties of flake Al-Cu-Mg alloy particles synthesized by ball milling. Particule Science and Technology, 37, 381–390.
16. [17] Ugrasen, G., et al. (2018). Estimation of machining performances using MRA and GMDH in Wire EDM of Al2024 based Hybrid MMC. Materilas Today: Proceedings, 5, 3084–3092.
17. [18] Özyürek, D., et al. (2014). Experimental investigation and prediction of wear properties of Al/SiC metal matrix composites produced by thixomoulding method using Artificial Neural Networks. Materials and Design, 63, 270–277.
18. [19] Chuanmin, Z., et al. (2019). Surface roughness prediction model of SiCp/Al composite in grinding. Internatıonal Journal of Mechanical Sciences, 155, 98-109.
19. [20] Zain, A.M., et al. (2010). Prediction of surface roughness in the end milling machining using Artificial Neural Network. Expert Systems with Applications, 37, 1755–1768.
20. [21] Kumar, R., Chauhan, S. (2015). Study on surface roughness measurement for turning of Al 7075/10/SiCp and Al 7075 hybrid composites by using response surface methodology (RSM) and artificial neural networking (ANN). Measurement: Journal of the Internatıonal Measurement Confederation, 65, 166–180.
21. [22] Thankachan, T., et al. (2019). Prediction of surface roughness and material removal rate in wire electrical discharge machining on aluminum based alloys/composites using Taguchi coupled Grey Relational Analysis and Artificial Neural Networks. Applied Surface Science, 472, 22–35.
22. [23] Marani, M., et al. (2019). Neuro-fuzzy predictive model for surface roughness and cutting force of machined Al–20 Mg2Si–2Cu metal matrix composite using additives. Neural Computing and Applications, 1–12.
23. [24] Prakash Rao, C.R., et al. (2014). Effect of machining parameters on the surface roughness while turning particulate composites. Procedia Engineering, 97, 421–431.
24. [25] Şahin, İ. (2014). Prediction of surface roughness of Al/SiC composite material with artificial neural networks. Journal of Faculty of Engineering and Architecture of Gazi Univesity, 29, 209–216.
25. [26] Arthur, C.K., et al. (2020). Novel approach to predicting blast-induced ground vibration using Gaussian process regression. Engineering with Computers, 36, 29–42.
26. [27] Schmidt, J., et al. (2019). Recent advances and applications of machine learning in solid-state materials science. npj Computational Materials, 5, 83.
27. [28] Koçyiğit, F, et al. (2017). Prediction of thermal performance of designed different obstacles on absorber plates in solar air collectors by support vector machine. European Journal of Technique, 7, 186–194.
28. [29] Thiagarajan, C., et al. (2011). Cylindrical grinding of SiC particles reinforced aluminium metal matrix composites. ARPN Journal of Engineering and Applied Scieces, 6, 14–20.
29. [30] Gurgenc, T., et al. (2019). A study on the extreme learning machine based prediction of machining times of the cycloidal gears in CNC milling machines. Production Engineering, 13, 635–647.
30. [31] Ucar, F., Korkmaz, D. (2020). COVIDiagnosis-Net: Deep Bayes-Squeeze Net based diagnosis of the coronavirus disease 2019 (COVID-19) from X-ray images. Medical Hypotheses, 140,109761.
31. [32] Ekici, S., et al. (2020). Power quality event classification using optimized Bayesian convolutional neural networks. Electrical Engineering.
32. [33] Rasmussen, C.E., Williams, C.K.I. Gaussian processes for machine learning. MA:MIT Press, Cambridge, Massachusetts, 2006.