The nickel–copper-based alloy K500 has been extensively utilized in aerospace and naval structures owing to its strength and corrosion resistance. In order to process this material through plastic deformation processes, the high temperature flow behavior is crucial to forming industries. In the present work, the change in the flow behavior of alloy K500 at different values of elevated temperatures and strain rates have been investigated through the compression test using a hydraulic-controlled universal testing machine. This is followed by its modeling through a commonly used quadratic statistical regression analysis (SRA), an image based-convolutional neural network (CNN) and a hybrid neuro-fuzzy-based adaptive neuro-fuzzy inference system (ANFIS) model. ANFIS has been reported to perform the best with mean absolute percent error of 14.24%, owing to the development of a proper input–output correlation using ANN and data clustering nature of the fuzzy sets. CNN on the other hand has failed to meet the desired expectations, which may be attributed to the availability of a very limited amount of data set. In fact, the current study has also shown the scope of CNN to perform reasonably better with larger data set.
DasDBalKSPratiharDK, et al.Correlating the weld-bead’s ‘macro-, micro-features’ with the weld-pool’s ‘fluid flow’ for electron beam welded SS 201 plates. Int J Mech Sci2021; 210: 106734.
2.
DasDPratiharDKRoyGG. Modeling of beam divergence. Optik (Stuttg)2022; 256: 168747.
3.
PratiharDK. Soft computing and AI: fundamentals and applications. New Delhi: Narosa Publishing House Pvt. Ltd., 2025.
4.
DasDDindaSKDasAK, et al.Study of micro-porosity in electron beam butt welding. Int J Adv Manuf Technol2022; 121: 4583–4600.
5.
DasDThakurNRoutM. Prediction of characteristic points of single-peak flow curve through statistical technique and artificial neural network. Int J Model Simul2025; 45: 629–637.
6.
YuRCaoYChenH, et al.Deep learning based real-time and in-situ monitoring of weld penetration: where we are and what are needed revolutionary solutions?J Manuf Process2023; 93: 15–46.
7.
FengSZhouHDongH. Using deep neural network with small dataset to predict material defects. Mater Des2019; 162: 300–310.
8.
UllahAElahiHSunZ, et al.Comparative analysis of AlexNet, ResNet18 and SqueezeNet with diverse modification and arduous implementation. Arab J Sci Eng2022; 47: 2397–2417.
9.
KrizhevskyASutskeverIHintonGE. Imagenet classification with deep convolutional neural networks. Commun ACM2017; 60: 84–90.
10.
SharmaSGuleriaK. Deep learning models for image classification: comparison and applications. In: 2022 2nd Int Conf Adv Comput Innov Technol Eng, 2022: 1733–1738. https://doi.org/10.1109/ICACITE53722.2022.9823516.
11.
WuSZhongSLiuY. Deep residual learning for image steganalysis. Multimed Tools Appl2018; 77: 10437–10453.
12.
DewanMWHuggettDJWarren LiaoT, et al.Prediction of tensile strength of friction stir weld joints with adaptive neuro-fuzzy inference system (ANFIS) and neural network. Mater Des2016; 92: 288–299.
13.
AyebMTurkiMFrijaM, et al.Artificial neural network and ANFIS approaches for mechanical properties prediction and optimization of a turbine blade treated by laser shock peening. Expert Syst Appl2024; 250: 123911.
14.
KhalafAHLinBAbdallaAN, et al.Enhanced prediction of corrosion rates of pipeline steels using simulated annealing-optimized ANFIS models. Results Eng2024; 24: 102853.
15.
ParuthiSRahmanIHusainA. Utilizing ANFIS for strength characteristics forecasting in variable heat-cured geopolymer composites. Mater Today Proc. 2024. https://doi.org/10.1016/j.matpr.2024.05.111.
16.
PazhamannilRVHadidiHMEdacherianA, et al.Prediction of the mechanical properties of heat-treated fused filament fabrication thermoplastics using adaptive neuro-fuzzy inference system. J Thermoplast Compos Mater2024; 37: 1385–1406.
17.
DilmaçHDemirF. Stress–strain modeling of high-strength concrete by the adaptive network-based fuzzy inference system (ANFIS) approach. Neural Comput Appl2013; 23: 385–390.
18.
MangirAOkumusVŞenZ. Moment–curvature relationship prediction of reinforced concrete beams by adaptive neuro-fuzzy inference system (ANFIS) modelling. Int J Fuzzy Syst2025. https://doi.org/10.1007/s40815-025-01981-7.
19.
NguyenTHTranNLNguyenDD. Prediction of axial compression capacity of cold-formed steel oval hollow section columns using ANN and ANFIS models. Int J Steel Struct2022; 22: 1–26.
20.
Bani Mostafa ArabNAyazMMirahmadi KhakiD. Statistical modeling of strain-hardening exponent and grain size of nb-microalloyed steels using a two-level factorial design of experiment. J Mater Eng Perform2013; 22: 3337–3347.
21.
LinYSuYZhaoQ, et al.A new regression model for the prediction of the stress–strain relations of different materials. Materials (Basel)2023; 16: 10–14.
22.
HeKZhangXRenS, et al.Deep residual learning for image recognition. In: Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit: 2016 December, 770–778. https://doi.org/10.1109/CVPR.2016.90.
23.
SimonyanKZissermanA. Very deep convolutional networks for large-scale image recognition. arXiv Prepress arXiv14091556v6. 2014.
24.
GoodfellowIWarde-FarleyDMirzaM, et al.Maxout networks. In: International conference on machine learning. Proceedings of Machine Learning Research (PMLR), 2013, pp 1319–1327.
ÖzdemSOrakİM. A novel method based on deep learning algorithms for material deformation rate detection. J Intell Manuf2025; 36: 3249–3270.
27.
MinhTNKhoaNTThuyNN, et al.Evaluating flexural strength of steel fiber reinforced geopolymer concrete using the ResNet approach and sensitivity analysis. Eng Technol Appl Sci Res2024; 14: 18099–18104.
28.
LiuZGuoBWuF, et al.An improved burr size prediction method based on the 1D-ResNet model and transfer learning. J Manuf Process2022; 84: 183–197.
29.
SongYQuZLiaoH, et al.Material twins generation of woven polymer composites based on ResL-U-net convolutional neural networks. Compos Struct2023; 307: 116672.
30.
KimSJMinHGParkJH, et al.Application of deep learning method for time reduction and precision improvement in displacement measurement during in-situ SEM tensile test. Meas J Int Meas Confed2024; 234: 114769.
31.
WanMLinYCLiSX, et al.MHAED-Net: a lightweight multiscale hybrid attention encoder-decoder network for the efficient segmentation of industrial forging images. J Supercomput2025; 81: 1001.
32.
WanMLinYCZengNF, et al.Perception and reconstruction of temperature field in forgings based on physical model and CNN model. Meas J Int Meas Confed2025; 242: 116210.
33.
ChenDDLinYCZhouY, et al.Dislocation substructures evolution and an adaptive-network-based fuzzy inference system model for constitutive behavior of a Ni-based superalloy during hot deformation. J Alloys Compd2017; 708: 938–946.
34.
KumarAKumarSKumarA, et al.Prediction of creep degradation in Fe–Cr–Ni single-crystal alloys for high-temperature applications: a molecular-dynamics and machine-learning approach. Mech Time-Dependent Mater2025; 29: 1–21.
35.
CroomBPBerksonMMuellerRK, et al.Deep learning prediction of stress fields in additively manufactured metals with intricate defect networks. Mech Mater2022; 165: 1–32.
36.
KostryzhevAGMarenychOOPanZ, et al.Strengthening mechanisms in Monel K500 alloyed with Al and Ti. J Mater Sci2023; 58: 4150–4164.
37.
TürkmenİKeddamM. Boronizing of Monel K500 alloy: microstructural characterization and modeling of boron diffusion. Mater Charact2024; 213: 113995.
38.
ChenJWangJYanF, et al.Effect of applied potential on the tribocorrosion behaviors of Monel K500 alloy in artificial seawater. Tribol Int2015; 81: 1–8.
39.
SamantarayDMandalSBhaduriAK. A critical comparison of various data processing methods in simple uni-axial compression testing. Mater Des2011; 32: 2797–2802.
40.
JainMPurushothamG (2018) Effect of almandine on microstructure and corrosion properties of nickel super alloy (K500) composite for aerospace gas turbine application. IOP Conf Ser Mater Sci Eng376:https://doi.org/10.1088/1757-899X/376/1/012051.
41.
DuchiJHazanESingerY. Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res2011; 12: 2121–2159.
42.
KingmaDPBaJL. Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980v9. 2014.
43.
BaydinAGRubioDMWoodF, et al. (2018) Online learning rate adaptation with hypergradient descent. 6th Int Conf Learn Represent ICLR 2018—Conf Track Proc1–11.
44.
SSMHaoXHouS, et al.Progressive data dropout: an embarrassingly simple approach to faster training. 1–17. 2025.
45.
ThanapolPLavangnanandaKBouvryP, et al. (2020) Reducing overfitting and improving generalization in training convolutional neural network (CNN) under limited sample sizes in image recognition. InCIT 2020—5th Int Conf Inf Technol300–305.https://doi.org/10.1109/InCIT50588.2020.9310787.
46.
SrivastavaNHintonGKrizhevskyA, et al.Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res2014; 15: 1929–1958.
47.
SoydanerD. A comparison of optimization algorithms for deep learning. Int J Pattern Recognit Artif Intell2020; 34: 2052013.
48.
WahabiMCabreraJMPradoJM. Hot working of two AISI 304 steels: a comparative study. Mater Sci Eng A2003; 343: 116–125.
49.
PratiharDK. Soft computing fundamentals and applications. New Delhi: Narosa Publishing House Pvt. Ltd, 2015.
