Residual stress prediction in hard machining: A comparative study of ANN, ANFIS, SVM and GPR models

Zaki Abdelfetah Abed; Kamel Haddouche; Sahraoui Aissat; Souâd Makhfi; Malek Habak

doi:10.18540/jcecvl10iss8pp21107

Authors

Zaki Abdelfetah Abed Research Laboratory of Industrial Technologies, Faculty of Applied Sciences, University of Tiaret, B. P. 78 Zaâroura 14000 Tiaret, Algeria https://orcid.org/0009-0004-4732-1335
Kamel Haddouche Research Laboratory of Industrial Technologies, Faculty of Applied Sciences, University of Tiaret, B. P. 78 Zaâroura 14000 Tiaret, Algeria https://orcid.org/0000-0002-7084-0246
Sahraoui Aissat Research Laboratory of Industrial Technologies, Faculty of Applied Sciences, University of Tiaret, B. P. 78 Zaâroura 14000 Tiaret, Algeria
Souâd Makhfi Research Laboratory of Industrial Technologies, Faculty of Applied Sciences, University of Tiaret, B. P. 78 Zaâroura 14000 Tiaret, Algeria
Malek Habak Laboratory of Innovate Technologies, Picardie Jules Verne University, Avenue des Facultés, Le Bailly 80025 Amiens Cedex 1, France

DOI:

https://doi.org/10.18540/jcecvl10iss8pp21107

Keywords:

Residual stresses. Hard machining. AISI 52100 steel. CBN cutting tool. Learning techniques. ANN. ANFIS. SVM. GPR.

Abstract

In the present investigation, techniques based on learning are applied to predict longitudinal and circumferential residual stresses during the hard turning of AISI 52100 steel by a CBN cutting tool. Residual stresses are one of the most commonly variables which evaluate the machined surface integrity. Predicting this last is a major objective related to the quality and life of manufactured products. In this context, we use four models to estimate residual stresses: Artificial Neural Network (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), Support Vector Machine (SVM), and Gaussian Process Regression (GPR). The analysis is based on experimental data structured in 34 combinations using work material J-C rheological properties (A, B and n) and cutting parameters (V_c, f and a_p). These rheological properties are related to the hardness and microstructure, which depend respectively on the heat treatment and carbide inclusion. For the developed models, ANFIS gives globally the best performances, achieving high value of R² and minimal MSE; it shows the most promise of prediction. This underscores the effectiveness of learning techniques in estimating residual stresses.

Downloads

References

Ajay, C., Vikas S. (2020). Surface Integrity of AISI 52100 Steel during Hard Turning in Different Near-Dry Environments. Advances in Materials Science and Engineering, 4256308. https://doi.org/10.1155/2020/4256308

Cristianini, N., Shawe-Taylor J. (2000). An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge University Press.

https://doi.org/10.1017/CBO9780511801389

Cortes, C., Vapnik, V. (1995). Support-vector networks. Mach Learn, 20, 273–297. https://doi.org/10.1007/BF00994018

Deng Z., Guo Z., Zhang X. (2017). Interval model updating using perturbation method and radial basis function neural networks. Mechanical Systems and Signal Processing, 84, 699-716.

https://doi.org/10.1016/j.ymssp.2016.09.001

Djellouli, K., Haddouche, K., Belarbi, M., & Aich, Z. (2023). Prediction of the cutting tool wear during dry hard turning of AISI D2 steel by using models based on Learning process and GA polyfit. The Journal of Engineering and Exact Sciences, 9(12). 18297.

https://doi.org/10.18540/jcecvl9iss12pp18297

Gholami, R., Fakhari, N. (2017). Support Vector Machine: Principles, Parameters, and Applications. In: Handbook of Neural Computation Elsevier, 515–535. https://doi.org/10.1016/B978-0-12-811318-9.00027-2

Gunn S. R. (1998). Support Vector Machines for classification and regression. Technical Report, University of Southampton.

https://meandmyheart.wordpress.com/wp-content/uploads/2009/02/svm_gunn1.pdf

Habak, M. (2006). Etude de l’influence de la microstructure et des paramètres de coupe sur le comportement en tournage dur de l’acier à roulement 100Cr6. Thèse de Doctorat, École Nationale Supérieure d'Arts et Métiers, France.

Hagan, M. T., Demuth, H. B., Beale, M. H., De Jesús, O. (2014). Neural Network Design. 2nd Edition eBook.

Hsu C-W., Chang C-C., Lin C-J. (2016). A practical guide to support vector classification. Technical report, National Taiwan University. http://www.csie.ntu.edu.tw/~cjlin.

Huang, X., Yansong, Z.., Daode, Z., Jing, X., Wen-qiong, Z., Shengnan, L., Zihang, Y. (2023). Effects of multi-pass turning on surface properties of AISI 52100 bearing steel. The International Journal of Advanced Manufacturing Technology, 127(3-4), 1823-1833. https://doi.org/10.1007/s00170-023-11677-7

Hüseyin Alp, Ç., Adem Ç., Necati U., Kubilay A. (2024). Performance of conventional and wiper CBN inserts under various cooling conditions in hard turning of AISI 52100 steel. Materials Testing, 66(2), 288-298. https://doi.org/10.1515/mt-2023-0263

Isabona, J., Imoize, A. L., Ojo, S., Do, D-T., Lee, C-C.. (2023). Machine Learning-Based GPR with LBFGS Kernel Parameters Selection for Optimal Throughput Mining in 5G Wireless Networks. Sustainability, 15, 1678. https://doi.org/10.3390/su15021678

Jang, J.-s. R. (1993). ANFIS: Adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, & Cybernetics, 23(3), 665–685. https://doi.org/10.1109/21.256541

Kara, F., Adem Çiçek A., and Halil Demir H. (2023). Effect of Deep Cryogenic Treatment on Microstructure, Mechanical Properties, and Residual Stress of AISI 52100 Bearing Steel. Engineered Science. 26. https://doi.org/10.30919/es960

Kokkirala, S., Holmberg, J., Klement, U. (2022). Effect of cutting parameters on the generated surface integrity of hard-turned martensitic AISI 52100 bearing steel. Procedia CIRP, 115: 154-159. http://dx.doi.org/10.1016/j.procir.2022.10.066.

Makhfi, S. (2018). Modélisation et simulation du comportement thermomécanique de l’usinage à grande vitesse. Thèse de Doctorat, Université de Tlemcen, Algérie.

Makhfi, S., Haddouche, K., Bourdim, A., Habak, M. (2018). Modeling of machining force in hard turning process. Mechanika, 24, 3, 367-375. http://dx.doi.org/10.5755/j01.mech.24.3.19146

Mimoun, C. H., Haddouche, K., Makhfi, S. (2022). A Comparative Study of Multiple Regression, ANN and Response Surface Method for Machining Force. Proc. of the Interdisciplinary Conference on Mechanics, Computers and Electrics (ICMECE 2022) 6-7 October 2022, Barcelona, Spain. http://www.icmece.org/2022/proceedings.pdf.

Outeiro, J. (2018). Residual stresses in machining operations. CIRP Encyclopedia of Production Engineering; Laperrière, L, Reinhart, G, Eds. Springer, Berlin, Heidelberg, 1-13. https://doi.org/10.1007/978-3-642-35950-7_16811-1

Paschoalinoto N. W. , Bordinassi E. C., Bortolussi R., Leonardi F., Delijaicov S. (2021). The effect of process parameters and cutting tool shape on residual stress of SAE 52100 hard turned steel by high speed machining. Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 235(1-2), 290-300.

http://dx.doi.org/10.1177/0954405420929788

Pawar S., Salve A., Chinchanikar S., Kulkarni A., Lamdhade G., (2017). Residual Stresses during Hard Turning of AISI 52100 Steel: Numerical Modelling with Experimental Validation. Materials Today: Proceedings, Part A 4(2), 2350-2359.

https://doi.org/10.1016/j.matpr.2017.02.084

Salcedo?Sanz, S., Rojo?Álvarez, J. L., Martínez?Ramón, M., Camps?Valls, G. (2014). Support vector machines in engineering: an overview. WIREs Data Min & Knowledge Discovery, 4, 234–267. https://doi.org/10.1002/widm.1125

Schulz, E., Speekenbrink, M., Krause, A. A. (2018). Tutorial on Gaussian process regression: Modelling, exploring, and exploiting functions. Journal of Mathematical Psychology, 1-16. https://doi.org/10.1101/095190

Sivaraman, V., Prakash, S. (2017). Recent developments in turning hardened steels – A review. Frontiers in Automobile and Mechanical Engineering. IOP Conf. Series: Materials Science and Engineering, 197. https://doi.org/10.1088/1757-899X/197/1/012009

Soori, M. Arezoo, B. (2022). A Review in Machining-Induced Residual Stress Journal of New Technology and Materials, 12(01), 64-83. https://hal.science/hal-03679993v1

Sutanto, H., Madl, J., (2018). Residual stress development in hard machining-a review. IOP Conference Series: Materials Science and Engineering. IOP Publishing.

https://doi.org/10.1088/1757-899X/420/1/012031

Vapnik V. N., (1998). Statistical Learning Theory. Wiley-Interscience.

Tabatabaeian, A., Ghasemi, A. R., Shokrieh, M. M., Marzbanrad, B., Baraheni, M., & Fotouhi, M. (2022). Residual stress in engineering materials: A review. Advanced Engineering Materials, 24(3), 2100786. https://doi.org/10.1002/adem.202100786