Paper Titles
Multi–Objective Optimization of Flame Scarfing Parameters in Low-Carbon Steel Slabs for Enhanced Process Performance
p.3
Novel Non-Destructive Approach for Heat-Affected Zone (HAZ) Boundary Identification in Cold-Formed A 240 TP 304L Stainless Steel Using Magnetic Measurements
p.13
Mechanical Properties and Microstructural Analysis of AISI 304 and Duplex 2550 Welded by GTAW and SMAW Techniques
p.23
Effect of ERNiCr-3 and ER70S-G Filler Metals on Mechanical and Microstructural Properties of TIG-Welded SS 409–Cu C11000 Joints
p.33
Generalized Regression Neural Network-Based Analysis of the Effectiveness of Cryogenic Machining on SS316
p.41
Experimental Study of Pin Profile Effects on Microstructure, Mechanical and Fatigue Properties of Friction Stir Welded AZ31B-H24 Magnesium Alloy Joints
p.51
Effect of Zn Addition on the Physical and Mechanical Properties of Sn 0.7Cu1.5Ag Lead-Free Solder Alloy
p.61
Solvent-Driven Flux Deposition Behavior and Weld Pool Response in A-TIG Welding of Aluminum 5083-H116
p.69
The Effect of the Combination of Vibration and Mold Temperature on the Characteristics of Remelted Aluminum
p.77

Generalized Regression Neural Network-Based Analysis of the Effectiveness of Cryogenic Machining on SS316

Article Preview

Abstract:

This study develops a generalized regression neural network (GRNN) model to analyze the effectiveness of cryogenic machining compared to dry and wet machining. The model was trained using datasets derived from face milling experiments on SS316 stainless steel, involving variations in spindle speed, feed rate, and depth of cut, with surface roughness (Ra) as the measured output. Cryogenic machining consistently produced lower Ra values, as confirmed by Interval Plot analysis. The GRNN model accurately predicted Ra, achieving low Mean Absolute Percentage Error values (2.31% for training and 2.05% for testing), along with high coefficients of determination (R² = 0.9957 for training and 0.9956 for testing). The GRNN model was then utilized for sensitivity analysis and response surface analysis. Perturbation-based sensitivity analysis identified the machining technique as the most influential parameter. Response surface analysis further confirmed the superiority of cryogenic machining across all parameter settings.

You might also be interested in these eBooks
Composite Materials, Properties and Processing of Steel and Alloys View Preview

Info:

Periodical:

Materials Science Forum (Volume 1195)

Pages:

41-48

DOI:

https://doi.org/10.4028/p-l5OvJ6

Citation:

Cite this paper

Online since:

June 2026

Authors:

Muhamad Nur Rohman*, Dony Perdana, Wiji Lestariningsih, Luki Trihardani

Keywords:

Cryogenic Machining, Face Milling, GRNN, Sensitivity Analysis, Surface Roughness

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

© 2026 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

References

[1] J. V Abellán-Nebot, C.V. Pastor, H.R. Siller, A review of the factors influencing surface roughness in machining and their impact on sustainability, Sustain. 16 (2024) 1917.

DOI: 10.3390/su16051917

Google Scholar

[2] T.T. Opoz, A. Burgess, J.I. Ahuir-Torres, H.R. Kotadia, S. Tammas-Williams, The effect of surface finish and post-processing on mechanical properties of 17-4 PH stainless steel produced by the atomic diffusion additive manufacturing process (ADAM), Int. J. Adv. Manuf. Technol. 130 (2024) 4043–4066.

DOI: 10.1007/s00170-024-12949-6

Google Scholar

[3] L. Trihardani, C.-T. Wang, Y.-J. Hsieh, Making optimal location-sizing decisions for deploying hybrid renewable energy at B&Bs, Appl. Sci. 12 (2022) 6087.

DOI: 10.3390/app12126087

Google Scholar

[4] S. Pawanr, K. Gupta, Analysis of surface roughness and machine learning-based modeling in dry turning of super duplex stainless steel using textured tools, Technologies. 13 (2025) 243.

DOI: 10.3390/technologies13060243

Google Scholar

[5] M.E. Korkmaz, M.K. Gupta, A state of the art on cryogenic cooling and its applications in the machining of difficult-to-machine alloys, Materials (Basel). 17 (2024) 2057.

DOI: 10.3390/ma17092057

Google Scholar

[6] M. Vinay, B. Navin Kumar, C.H.C. Alexander, Experimental evaluation of cryogenic cooling's influence on surface roughness in monel milling, in: 5th Int. Conf. Sustain. Innov. Eng. Technol. 2023, Kuala Lumpur, Malaysia, 2023: p.1–9.

DOI: 10.1063/5.0229666

Google Scholar

[7] G. Sourish, R. Knoblauch, M. El Mansori, C. Corleto, Towards AI driven surface roughness evaluation in manufacturing: a prospective study, J. Intell. Manuf. (2024).

DOI: 10.1007/s10845-024-02493-1

Google Scholar

[8] J.H. Ko, C. Yin, A review of artificial intelligence application for machining surface quality prediction: from key factors to model development, J. Intell. Manuf. (2025).

DOI: 10.1007/s10845-025-02571-y

Google Scholar

[9] K. Antosz, E. Kozłowski, J. Sep, S. Prucnal, Application of machine learning to the prediction of surface roughness in the milling process on the basis of sensor signals, Materials (Basel). 18 (2025) 148.

DOI: 10.3390/ma18010148

Google Scholar

[10] V.S. Nair, K. Rameshkumar, S. Saravanamurugan, Roughness prediction in end milling of Ti1023 alloy using machine learning-based gaussian process regression, Procedia Comput. Sci. 253 (2025) 455–464.

DOI: 10.1016/j.procs.2025.01.107

Google Scholar

[11] G. Basar, O. Der, M.A. Guvenc, AI-powered hybrid metaheuristic optimization for predicting surface roughness and kerf width in CO2 laser cutting of 3D-printed PLA-CF composites, J. Thermoplast. Compos. Mater. 38 (2025) 2688–2717. https://doi.org/10.1177/08927057251344183%0A.

DOI: 10.1177/08927057251344183

Google Scholar

[12] M.N. Rohman, J.-R. Ho, C.-T. Lin, P.-C. Tung, C.-K. Lin, Predicting and enhancing the multiple output qualities in curved laser cutting of thin electrical steel sheets using an artificial intelligence approach, Mathematics. 12 (2024) 937.

DOI: 10.3390/math12070937

Google Scholar

[13] M.N. Rohman, J.-R. Ho, P.-C. Tung, H.-P. Tsui, C.-K. Lin, Prediction and optimization of geometrical quality for pulsed laser cutting of non-oriented electrical steel sheet, Opt. Laser Technol. 149 (2022) 107847.

DOI: 10.1016/j.optlastec.2022.107847

Google Scholar

[14] M.N. Rohman, J.-R. Ho, P.-C. Tung, C.-T. Lin, C.-K. Lin, Prediction and optimization of dross formation in laser cutting of electrical steel sheet in different environments, J. Mater. Res. Technol. 18 (2022) 1977–1990.

DOI: 10.1016/j.jmrt.2022.03.106

Google Scholar

[15] S.K. Singh, H.S. Mali, D.R. Unune, S. Wojciechowski, D. Wilczyński, Application of generalized regression neural network and gaussian process regression for modelling hybrid micro-electric discharge machining: A comparative study, Processes. 10 (2022) 755.

DOI: 10.3390/pr10040755

Google Scholar

[16] N. Liu, J. Han, X. Tian, L. Xia, M. Li, R. Xue, Research on grinding force prediction of spiral bevel gear based on generalized regression neural network and undeformed grinding chips, Eng. Appl. Artif. Intell. 156 (2025) 111301.

DOI: 10.1016/j.engappai.2025.111301

Google Scholar

[17] M.C.K. Rao, R.L. Malghan, A.K. Shettigar, M.A. Herbert, S.S. Rao, Advantages of cryogenic machining technique over without-coolant and with-coolant machining on SS316, Eng. Res. Express. 3 (2021) 015040.

DOI: 10.1088/2631-8695/abecd6

Google Scholar

[18] S.-J. Kang, J.-H. Fan, W. Mao, Q. Wu, J. Feng, Y. Yin, Evaluating the optical classification of fermi BCUs using machine learning, Astrophys. J. 872 (2019) 189.

DOI: 10.3847/1538-4357/ab0383

Google Scholar

[19] R. Eberhart, J. Kennedy, New optimizer using particle swarm theory, Proc. Int. Symp. Micro Mach. Hum. Sci. (1995) 39–43.

DOI: 10.1109/mhs.1995.494215

Google Scholar

[20] H. Ding, Z. Wang, Y. Guo, Multi-objective optimization of fiber laser cutting based on generalized regression neural network and non-dominated sorting genetic algorithm, Infrared Phys. Technol. 108 (2020) 103337.

DOI: 10.1016/j.infrared.2020.103337

Google Scholar