This study investigates the use of machine learning (ML) to predict and analyse the thermal and geometric characteristics of molten pools formed during laser cladding of steels and superalloys onto C45 steel. Three ML models – random forest (RF), XGBoost, and support vector regression (SVR) – were trained using a comprehensive dataset and evaluated for predictive accuracy. XGBoost outperformed the others, achieving R2 values of .951 for maximum temperature, .932 for effective temperature gradient, .913 for dilution rate, and .945 for shape factor. However, this higher accuracy required longer training times due to the model's complexity. RF showed greater robustness to input feature variation, while XGBoost and SVR were more sensitive to feature selection, occasionally overlooking important parameters. Finally, case studies involving SS316 cladding on C45 steel validated the models' practical relevance and demonstrated the potential to optimize cladding parameters for improved control over molten pool behaviour and cladding quality
DingHYangTWangW, et al.Optimization and wear behaviors of 316L stainless steel laser cladding on rail material. Wear2023; 523: Article 204830.
2.
HeZZhanDYanX, et al.Effect of oscillating laser cladding on microstructure and properties of stainless steel cladding layers. Mater Today Commun2024; 41: Article 110254.
3.
GaoSFuQLiM, et al.Optimization of laser cladding parameters for high-entropy alloy-reinforced 316L stainless-steel via grey relational analysis. Coatings2024; 14. https://doi.org/10.3390/coatings14091103
4.
ZhuSNiuBChangZ, et al.Research on heat and mass transfer in the molten pool of laser cladding. Int J Adv Manuf Technol2024; 132: 983–1004.
5.
YangTZhangLWuN, et al.Analysis and prediction of geometrical shapes and dilution rate in laser cladding repair of Ti-6Al-4V alloy. Int J Adv Manuf Technol2024; 134: 4717–4728.
6.
WareeKWattanapornphanPWongpisanW, et al.Clad-geometric characteristics and melt-pool behavior on microstructure evolution of laser clad Stellite-6 on R260 grade rail steel. Prog Addit Manuf2024. https://doi.org/10.1007/s40964-024-00604-1
7.
SedighiAMNabaviSFFarshidianfarA. A review on effect of cooling rate on metallurgical, mechanical, geometrical characteristics and defects of laser cladding process. Lasers Manuf Mater Process2024; 11: 677–742.
8.
WangXWangBYuY, et al.Combining spark plasma sintering with laser cladding: a new strategy for fabricating microstructure of defect-free and highly wear-resistant AlCoCrFeNi high-entropy alloy. J Mater Res Technol2024; 32: 2101–2114.
9.
JianSLiuKLiJ, et al.A new test for evaluating the cracking susceptibility of laser cladding coatings and its validity on assessing the effect of laser power. Opt Laser Technol2025; 180: Article 111609.
10.
LiLCuiQZhouJ, et al.Study on the influence of laser power on the heat–flow multi-field coupling of laser cladding incoloy 926 on stainless steel surface. Materials (Basel)2024; 17. https://doi.org/10.3390/ma17194769
11.
LiGWangZYaoL, et al.Concentration mixing and melt pool solidification behavior during the magnetic field assisted laser cladding of Fe-Cr-based alloy on 45 steel surface. Surf Coatings Technol2022; 445: Article 128732.
12.
TianDLiCHuZ, et al.Modeling of temperature distribution and clad geometry of the molten pool during laser cladding of CoCrCuFeNi alloys. Int J Adv Manuf Technol2024; 132: 3683–3697.
13.
OuyangWXuZChaoY, et al.Effect of electrostatic field on microstructure and mechanical properties of the 316L stainless steel modified layer fabricated by laser cladding. Mater Charact2022; 191: Article 112123.
14.
YangMWuGLiX, et al.Influence of heat source model on the behavior of laser cladding pool. J Laser Appl2023; 35: 22006.
15.
LianGChuMFengM, et al.The inclined morphology and molten pool of laser cladding under different cladding methods. Opt Laser Technol2025; 180: Article 111445.
16.
FuYGuHQianL, et al.Laser cladding for pipeline components: understanding molten pool dynamics and track formation on outer/inner tube surfaces. Opt Laser Technol2024; 179: Article 111324.
17.
YeW-LSunA-DZhaiW-Z, et al.Finite element simulation analysis of flow heat transfer behavior and molten pool characteristics during 0Cr16Ni5Mo1 laser cladding. J Mater Res Technol2024; 30: 2186–2199.
18.
GeHDingSZhangP, et al.Influence of overlapping process on the distribution of Cr element in laser cladding 316L powder on 45# steel substrate. Surf Coatings Technol2024; 493: Article 131249.
19.
HuKWangYLiF, et al.Thermal-fluid modeling and physics-informed machine learning for predicting molten pool depth in single-layer multi-track fiber laser cladding. Int J Adv Manuf Technol2024; 135: 3591–3613.
20.
CaoXDuanCLuoX, et al.Physics-informed machine learning approach for molten pool morphology prediction and process evaluation in directed energy deposition of 12CrNi2 alloy steel. J Manuf Process2024; 119: 806–826.
21.
ZhuSChenWZhanX, et al.Optimization of dilution rate of laser cladding repair based on deep learning. Int J Adv Manuf Technol2020; 110: 1471–1484.
22.
ZhuSXiaWKamaliH, et al.Deep learning-driven precision control of dilution rate in multi-pass laser cladding: experiment and simulation. Int J Adv Manuf Technol2023; 127: 5353–5371.
23.
ChenXYaoMFuY, et al.Applying multi-sensor fusion strategy for enhanced predictions of clad hardness and dilution in laser hot-wire cladding process by an ensemble machine learning model. J Manuf Process2025; 133: 211–225.
24.
ChenXYaoMKongF, et al.In-situ quality monitoring of laser hot wire cladding process based on multi-sensing diagnosis and machine learning model. J Manuf Process2023; 87: 183–198.
25.
XuZ-YCuiP-FLiuX, et al.Research on rapid prediction method of laser cladding deposited layer state based on molten pool texture sequence. Opt Laser Technol2025; 181: Article 111857.
26.
DiwakarVSharmaAYusufzaiMZK, et al.Machine learning-based prediction of single clad characteristics and non-destructive characterization of multi-layer deposited FeCoNiCrMo HEA on EN24 via laser cladding. Mater Today Commun2024; 41: Article 110839.
27.
GanZYuGHeX, et al.Numerical simulation of thermal behavior and multicomponent mass transfer in direct laser deposition of CO-base alloy on steel. Int J Heat Mass Transf2017; 104: 28–38.
28.
DaoMHLouJ. Simulations of laser assisted additive manufacturing by smoothed particle hydrodynamics. Comput Methods Appl Mech Eng2021; 373: 113491.
29.
TamannaNCrouchRNaherS. Progress in numerical simulation of the laser cladding process. Opt Lasers Eng2019; 122: 151–163.
30.
HeXMazumderJ. Transport phenomena during direct metal deposition. J Appl Phys2007; 101.
31.
WeiJChuXSunX, et al.Machine learning in materials science. InfoMat2019; 1: 338–358.
32.
ProbstPWrightMNBoulesteixA. Hyperparameters and tuning strategies for random forest. Wiley Interdiscip Rev Data Min Knowl Discov2019; 9: Article e1301.
33.
LuW-CJiX-BLiM-J, et al.Using support vector machine for materials design. Adv Manuf2013; 1: 151–159.
34.
WangZHLiuYFWangT, et al.Intelligent prediction model of mechanical properties of ultrathin niobium strips based on XGBoost ensemble learning algorithm. Comput Mater Sci2024; 231: Article 112579.
35.
WongT-TYehP-Y. Reliable accuracy estimates from k-fold cross validation. IEEE Trans Knowl Data Eng2019; 32: 1586–1594.
36.
LiuYAlkhazalehHAKhanMA, et al.Local elasticity assessment of unidirectional fiber-reinforced polymer composites through impulse excitation and machine learning. J Reinf Plast Compos2024: Article 07316844241307083.
37.
ShenZSamavatianMSamavatianV. Integrating impulse excitation technique and machine learning to analyze elastic moduli in surface coatings. Eur J Mech - A/Solids2024; 105: Article 105250.
38.
UpretiKVermaMAgrawalM, et al.Prediction of mechanical strength by using an artificial neural network and random forest algorithm. J Nanomater2022; 2022: Article 7791582.
39.
ChenWYanBXuA, et al.An intelligent matching method for the equivalent circuit of electrochemical impedance spectroscopy based on random forest. J Mater Sci Technol2025; 209: 300–310.
40.
WangSCaiYSuJ, et al.XGBoost and genetic programming methods for analysing the vitreous transition of the epoxy adhesive. J Adhes Sci Technol2025: 1–26.
41.
XuPJiXLiM, et al.Small data machine learning in materials science. Npj Comput Mater2023; 9: 42.
42.
HuJSzymczakS. A review on longitudinal data analysis with random forest. Brief Bioinform2023; 24: Article bbad002.
