Restricted accessResearch articleFirst published online 2025
Artificial neural network- multi-criteria decision making approaches to predict and validate the role of roughness parameters of D2 tool steel generated by various machining processes on friction and wear under dry and lubricated conditions
Dies made of D2 tool steel commonly fail in heavy-duty cutting due to excessive wear from contact with sheet metal. Their wear resistance depends on steel composition, heat and surface treatment, and machining quality. Surface roughness from machining is a key factor in die failure. This study examines the impact of surfaces produced by various machining processes on the tribological properties of tool steel under lubricated and dry sliding conditions. Heat-treated D2 tool steel was machined using four processes—wire-cut electric discharge machining (WEDM), electric discharge machining (EDM), computer numerical control milling (CNC), and surface grinding (SG)—to generate surfaces with varying roughness. Surface roughness measurements revealed that CNC-milled surfaces had the highest roughness parameters, followed by SG, EDM, and WEDM. Based on the tribological results, artificial neural models (ANN) were used to predict the effect of roughness parameters on the coefficient of friction (COF) and specific wear rates (SWR). The ANN predictions were further validated using the novel MCDM approach. These approaches concluded that Ra, Rq, and Rv significantly influenced COF and SWR under lubricated conditions, whereas Ra, Rp, and Rv influenced the same under dry sliding conditions. Three-body abrasive wear was the dominant wear mechanism under both conditions. Additionally, micro-grooves were generated due to this wear mechanism under dry sliding conditions compared to lubricated ones.
ŁępickaMGrądzka-DahlkeMPieniakD, et al.Effect of mechanical properties of substrate and coating on wear performance of TiN-or DLC-coated 316LVM stainless steel. Wear2017; 382: 62–70.
2.
SaravananIPerumalAEIssacRF, et al.Optimization of wear parameters and their relative effects on TiN coated surface against Ti6Al4V alloy. Mater Des2016; 92: 23–35.
3.
SedlačekMPodgornikBVižintinJ. Influence of surface preparation on roughness parameters, friction and wear. Wear2009; 266: 482–487.
4.
Abellán-NebotJVVila PastorCSillerHR. A review of the factors influencing surface roughness in machining and their impact on sustainability. Sustainability2024; 16: 1917.
5.
LuELiuJXiongY, et al.The influences of light source and roughness ranges on colour image-based visual roughness measurement performance. Measurement (Mahwah N J)2019; 147: 106855.
6.
YangHZhengHZhangT. A review of artificial intelligent methods for machined surface roughness prediction. Tribol Int2024; 199: 109935.
7.
GoodhandMNWaltonKBluntL, et al.The limitations of using “ra” to describe surface roughness. J Turbomach2016; 138: 101003.
8.
SzalaMSzafranMMatijošiusJ, et al.Abrasive wear mechanisms of S235JR, S355J2, C45, AISI 304, and Hardox 500 steels tested using garnet, corundum and carborundum abrasives. Adv Sci Technol Res J2023; 17: 147–160.
9.
DuoYTangJZhaoZ, et al.Discrimination of wear performance based on surface roughness parameters arithmetic mean height (Sa) and skewness (Ssk). Wear2024; 548–549: 205397.
10.
WeiTZhouZLingX, et al.A study of the effect of roughness on the three-body wear mechanism from a microscopic point of view: asperity peak removal. Metals (Basel)2024; 14: 1385.
11.
ElbahMYalleseMAAouiciH, et al.Comparative assessment of wiper and conventional ceramic tools on surface roughness in hard turning AISI 4140 steel. Measurement (Mahwah N J)2013; 46: 3041–3056.
12.
ÖzbekOSaruhanH. The effect of vibration and cutting zone temperature on surface roughness and tool wear in eco-friendly MQL turning of AISI D2. J Mater Res Technol2020; 9: 2762–2772.
13.
OzkavakHVSofuMMDumanB, et al.Estimating surface roughness for different EDM processing parameters on Inconel 718 using GEP and ANN. CIRP J Manuf Sci Technol2021; 33: 306–314.
14.
HadadMBuiLQNguyenCT. Experimental investigation of the effects of tool initial surface roughness on the electrical discharge machining (EDM) performance. Int J Adv Manuf Technol2018; 95: 2093–2104.
15.
JiangJArnellRD. The effect of substrate surface roughness on the wear of DLC coatings. Wear2000; 239: 1–9.
16.
LiangGSchmauderSLyuM, et al.An investigation of the influence of initial roughness on the friction and wear behavior of ground surfaces. Materials (Basel)2018; 11: 237.
17.
FedericiMMenapaceCMoscatelliA, et al.Effect of roughness on the wear behavior of HVOF coatings dry sliding against a friction material. Wear2016; 368: 326–334.
18.
StevićŽPamučarDPuškaA, et al.Sustainable supplier selection in healthcare industries using a new MCDM method: measurement of alternatives and ranking according to compromise solution (MARCOS). Comput Ind Eng2020; 140: 106231.
19.
DemirGChatterjeePKadryS, et al.Measurement of alternatives and ranking according to compromise solution (MARCOS) method: a comprehensive bibliometric analysis. Decis Mak Appl Manag Eng2024; 7: 313–336.
20.
MitraA. Cotton fibre selection based on quality value using measurement of alternatives and ranking according to compromise solution (MARCOS) method. Res J Text Apparel2024; 28: 299–316.
21.
Ahijith KumarPVPatnaikLBharatiK, et al.Investigating tool wear rate and surface quality of hardened tool steel: a fuzzy-MARCOS analysis and response surface methodology study. Int J Interact Des Manuf2024; 18: 4137–4158.
22.
KaraaslanAAdarTDeliceEK. Regional evaluation of renewable energy sources in Turkey by new integrated AHP-MARCOS methodology: a real application. Int J Sustain Energy2022; 41: 103–125.
23.
Hashemkhani ZolfaniSBazrafshanREcerF, et al.The suitability-feasibility-acceptability strategy integrated with Bayesian BWM-MARCOS methods to determine the optimal lithium battery plant located in South America. Mathematics2022; 10: 2401.
24.
Jafarzadeh GhoushchiSShaffiee HaghshenasSMemarpour GhiaciA, et al.Road safety assessment and risks prioritization using an integrated SWARA and MARCOS approach under spherical fuzzy environment. Neural Comput Appl2023; 35: 4549–4567.
25.
HaqRSUSaeedMMateenN, et al.Sustainable material selection with crisp and ambiguous data using single-valued neutrosophic-MEREC-MARCOS framework. Appl Soft Comput2022; 128: 109546.
26.
KumarSBhaumikSPatnaikL, et al.Application of integrated BWM fuzzy-MARCOS approach for coating material selection in tooling industries. Materials (Basel)2022; 15: 9002.
27.
ChakrabortySChakrabortyS. A scoping review on the applications of MCDM techniques for parametric optimization of machining processes. Arch Comput Method Eng2022; 29: 4165–4186.
28.
Keshavarz-GhorabaeeMAmiriMZavadskasEK, et al.Determination of objective weights using a new method based on the removal effects of criteria (MEREC). Symmetry (Basel)2021; 13: 525.
29.
DasPPChakrabortyS. A comparative assessment of multicriteria parametric optimization methods for plasma arc cutting processes. Decis Anal J2023; 6: 100190.
30.
NguyenHQNguyenVTPhanDP, et al.Multi-criteria decision making in the PMEDM process by using MARCOS, TOPSIS, and MAIRCA methods. Appl Sci2022; 12: 3720.
31.
ChatterjeeSChakrabortyS. 3D Printing machine selection using novel integrated MEREC-MCRAT MCDM method. AIP Conf Proc2023; 2786: 0145447.
32.
KeleşN. A multi-criteria decision-making framework based on the MEREC method for the comprehensive solution of forklift selection problem. Eskisehir Osmangazi Univ J Econ Admin Sci2023; 18: 573–590.
33.
SimicVGokasarIDeveciM, et al.Mitigating climate change effects of urban transportation using a type-2 neutrosophic MEREC-MARCOS model. IEEE Trans Eng Manag2024; 71: 3233–3249.
34.
SaadMSMohd NorAAbd RahimI, et al.Optimization of FDM process parameters to minimize surface roughness with integrated artificial neural network model and symbiotic organism search. Neural Comput Appl2022; 34: 17423–17439.
35.
SolerDTelleriaMGarcía-BlancoMB, et al.Prediction of surface roughness of SLM built parts after finishing processes using an artificial neural network. J Manuf Mater Process2022; 6: 82.
36.
UlkirOAkgunG. Predicting and optimising the surface roughness of additive manufactured parts using an artificial neural network model and genetic algorithm. Sci Technol Weld Join2023; 28: 548–557.
37.
SoMSSeoGJKimDB, et al.Prediction of metal additively manufactured surface roughness using deep neural network. Sensors2022; 22: 7955.
38.
BhaumikSKamarajM. Artificial neural network and multi-criterion decision making approach of designing a blend of biodegradable lubricants and investigating its tribological properties. Proc Inst Mech Eng J Eng Tribol2021; 235: 1575–1589.
39.
BagciMBhaumikS. Investigating the solid particle erosion behavior of H3BO3 / B2O3 / SiO2 / Al2O3 reinforced glass fibre/epoxy composites and parametric evaluation using artificial intelligence. Tribol Mater Surf Interfaces2024; 18: 171–182.
40.
OldenJDJoyMKDeathRG. An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data. Ecol Modell2004; 178: 389–397.
41.
YusopZBAhmedKShiraziSM, et al.Weighting methods and their effects on multi-criteria decision-making model outcomes in water resources management. Switzerland: Springer Cham, 2015.
42.
MenezesPLKishoreKailasSV. Influence of roughness parameters on COF under lubricated conditions. Sadhana2008; 33: 181–190.
43.
WenQLiuMZhangZ, et al.Experimental investigation into the friction coefficient of ball-on-disc in dry sliding contact considering the effects of surface roughness, low rotation speed, and light normal load. Lubricants2022; 10: 256.
44.
ZhangXGZhangYLWangJM, et al.Prediction of sliding friction coefficient based on a novel hybrid molecular-mechanical model. J Nanosci Nanotechnol2018; 18: 5551–5557.
45.
YamaguchiKSasakiCTsuboiR, et al.Effect of surface roughness on friction behaviour of steel under boundary lubrication. Proc Inst Mech Eng Part J Eng Tribol2014; 228: 1015–1019.
46.
HuEZXuYHuKH, et al.Tribological properties of 3 types of MoS₂ additives in different base greases. Lubr Sci2017; 29: 541–555.
47.
EverittCMAlfredssonB. The influence of gear surface roughness on rolling contact fatigue under thermal elastohydrodynamic lubrication with slip. Tribol Int2020; 151: 106394.
48.
HuangLDengXLiC, et al.Effect of TiC particles on three-body abrasive wear behavior of low alloy abrasion-resistant steel. Wear2019; 434: 202971.
49.
GheisariRPolycarpouAA. Tribological performance of graphite-filled polyimide and PTFE composites in oil-lubricated three-body abrasive conditions. Wear2019; 436: 203044.
DengXHuangLWangQ, et al.Three-body abrasion wear resistance of TiC-reinforced low-alloy abrasion-resistant martensitic steel under dry and wet sand conditions. Wear2020; 452: 203310.
52.
StelmakhAUPilgunYVKolenovSO, et al.Reduction of friction and wear by grooves applied on the nanoscale polished surface in boundary lubrication conditions. Nanoscale Res Lett2014; 9: 226.
53.
ZhouYZhuHZhangW, et al.Influence of surface roughness on the friction property of textured surface. Adv Mech Eng2015; 7: 1–9.
