In this work, the forward and reverse mapping of the E-jet-based micro-additive manufacturing process is carried out. A conductive polymer named PEDOT:PSS (poly (3, 4-ethylenedioxythiophene): polystyrene sulfonate) is used to generate patterns on a flexible substrate that can be employed for printed electronics applications. The aim of the study is to demonstrate the use of machine learning techniques for better regulation of E-jet. Artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) are used to model the manufacturing capability of E-jet. Experiments are conducted on the developed experimental setup. The investigated data are used to train and test the machine learning models. Different activation functions and membership functions are used in developing the models. The results are compared to measure the efficacy of the adopted approaches. The comparative study highlighted that the ANFIS model performed better in forward mapping. The model deviation is less than 5%. Furthermore, the bipolar sigmoid ANN-based approach is more suitable for reverse mapping of E-jet. The estimated error for the bipolar sigmoid model is <10%. The present work demonstrated the successful implementation of a machine learning approach for effective offline control of the micro-additive manufacturing process. Practitioners may employ the conducted research work as a template for improving the fabrication performance of E-jet across a wide range of operating scenarios.
MiskovicGKaufholdR. Additive manufacturing for nano-feature applications: electrohydrodynamic printing as a next-generation enabling technology. IEEE Open J Nanotechnol2022; 3: 191–198.
2.
MkhizeNBhaskaranH. Electrohydrodynamic jet printing: introductory concepts and considerations. Small Sci2022; 2: 2100073.
3.
CaiLZhangSZhangY, et al.Direct printing for additive patterning of silver nanowires for stretchable sensor and display applications. Adv Mater Technol2018; 3: 1700232.
4.
SeongBYooHNguyenVD, et al.Metal-mesh based transparent electrode on a 3-D curved surface by electrohydrodynamic jet printing. J Micromechanics Microengineering2014; 24: 97002.
5.
OnsesMSSutantoEFerreiraPM, et al.Mechanisms, capabilities, and applications of high-resolution electrohydrodynamic jet printing. Small2015; 11: 4237–4266.
6.
YangYJKimHCSajidM, et al.Drop-on-demand electrohydrodynamic printing of high resolution conductive micro patterns for MEMS repairing. Int J Precis Eng Manuf2018; 19: 811–819.
7.
WangDZhaoXLinY, et al.Fabrication of micro/nano-structures by electrohydrodynamic jet technique. Front Mech Eng2017; 12: 477–489.
8.
WillsonCGRomanBJ. The future of lithography: SEMATECH litho forum 2008. ACS Nano2008; 2: 1323–1328.
9.
CalvertP. Inkjet printing for materials and devices. Chem Mater2001; 13: 3299–3305.
10.
DasRMahapatraABallAK, et al.Study of thermo-fluidic behavior of micro-droplet in inkjet-based micro manufacturing processes. In: AIP Conference Proceedings, p. 020069.
11.
DasRKumar BallAShekhar RoyS. Optimization of E-jet based micro manufacturing process using grey relation analysis. Mater Today Proc2018; 5: 200–206.
12.
DasRBallAKRoySS. Parametric optimization of E-jet based micro manufacturing system through hybrid Taguchi methodology. Mater Today Proc2018; 5: 6981–6989.
13.
DerbyB. Inkjet printing of functional and structural materials: fluid property requirements, feature stability, and resolution. Annu Rev Mater Res2010; 40: 395–414.
14.
LuSJiangHLiM, et al.Nozzle and needle during high viscosity adhesive jetting based on piezoelectric jet dispensing. Smart Mater Struct2015; 24: 105023.
15.
LiYDahhanOFilipeCDM, et al.Deposited nanoparticles can promote air clogging of piezoelectric inkjet printhead nozzles. Langmuir2019; 35: 5517–5524.
16.
ElsersawyRRahmanASakib-Uz-ZamanC, et al.Multifunctional inks in aerosol jet printing: performance, challenges, and applications. Front Manuf Technol2025; 5: 1–19.
17.
LiGWangSZhangZ, et al.Precision control of aerosol jet printing for conformal electronics fabrication with ultra-fine and wide-range resolution. Adv Mater Technol2025; 10: 2402114.
18.
HuangXLiMYinQ, et al.A review on laser-induced forward transfer in digital additive manufacturing. Opt Laser Technol2025; 192: 113914.
19.
AzizMAAwasthiSKangS. Investigation of fabrication of Li-ion battery electrodes using femtosecond laser induced forward transfer: parameter optimization and material transfer strategies. In: AIP Conference Proceedings, p. 020012.
20.
LipovkaARodriguezRDGarciaA, et al.Overcoming stability and substrate adhesion challenges by laser-induced transfer of MXenes. ACS Appl Mater Interfaces2025; 17: 68684–68694.
21.
ZelenyJ. Instability of electrified liquid surfaces. Phys Rev1917; 10: 1–6.
22.
ChoiHKParkJ-UParkOO, et al.Scaling laws for jet pulsations associated with high-resolution electrohydrodynamic printing. Appl Phys Lett2008; 92: 123109.
23.
LeeMWKangDKKimNY, et al.A study of ejection modes for pulsed-DC electrohydrodynamic inkjet printing. J Aerosol Sci2012; 46: 1–6.
24.
LeeMWAnSKimNY, et al.Effects of pulsing frequency on characteristics of electrohydrodynamic inkjet using micro-Al and nano-Ag particles. Exp Therm Fluid Sci2013; 46: 103–110.
25.
XuLWangXLeiT, et al.Electrohydrodynamic deposition of polymeric droplets under low-frequency pulsation. Langmuir2011; 27: 6541–6548.
26.
RahmanKAliKMuhammadNM, et al.Fine resolution drop-on-demand electrohydrodynamic patterning of conductive silver tracks on glass substrate. Appl Phys A2013; 111: 593–600.
27.
BartonKMishraSAlleyneA, et al.Control of high-resolution electrohydrodynamic jet printing. Control Eng Pract2011; 19: 1266–1273.
28.
AnSLeeMWKimNY, et al.Effect of viscosity, electrical conductivity, and surface tension on direct-current-pulsed drop-on-demand electrohydrodynamic printing frequency. Appl Phys Lett2014; 105: 214102.
29.
ParkJ-UHardyMKangSJ, et al.High-resolution electrohydrodynamic jet printing. Nat Mater2007; 6: 782–789.
30.
LeeSKimJChoiJ, et al.Patterned oxide semiconductor by electrohydrodynamic jet printing for transparent thin film transistors. Appl Phys Lett2012; 100: 102108.
31.
NothnagleCBaptistJRSanfordJ, et al.EHD printing of PEDOT: PSS inks for fabricating pressure and strain sensor arrays on flexible substrates. In: PopaDWijesundaraMBJBlowersM (eds) Next-generation robotics II; and machine intelligence and bio-inspired computation: theory and applications IX. 9494. Bellingham, WA, USA: SPIE Proceedings, 2015, pp.949403.
32.
KimBHOnsesMSLimJB, et al.High-resolution patterns of quantum dots formed by electrohydrodynamic jet printing for light-emitting diodes. Nano Lett2015; 15: 969–973.
33.
LeeJChoiHKYangL, et al.Nondestructive real-time monitoring of enhanced stem cell differentiation using a graphene-Au hybrid nanoelectrode array. Adv Mater2018; 30: 1802762.
34.
OhSYHongSYJeongYR, et al.Skin-attachable, stretchable electrochemical sweat sensor for glucose and pH detection. ACS Appl Mater Interfaces2018; 10: 13729–13740.
35.
ReiserALindénMRohnerP, et al.Multi-metal electrohydrodynamic redox 3D printing at the submicron scale. Nat Commun2019; 10: 1853.
36.
GaoDZhouJG. Designs and applications of electrohydrodynamic 3D printing. Int J Bioprinting2018; 5: 172.
37.
ZhangZWangLYinT, et al.Electrohydrodynamic jet printing of micro-structured electrode featuring 3D gold micropillar array for non-enzymatic detection of glucose. Addit Manuf2025; 106: 104806.
38.
WangKStarkJPW. Direct fabrication of electrically functional microstructures by fully voltage-controlled electrohydrodynamic jet printing of silver nano-ink. Appl Phys A2010; 99: 763–766.
39.
AhmadZRasekhMEdirisingheM. Electrohydrodynamic direct writing of biomedical polymers and composites. Macromol Mater Eng2010; 295: 315–319.
40.
RautRBallAKBasakA. Scalable and transferable graph neural networks for predicting temperature evolution in laser powder bed fusion. Eng Appl Artif Intell2025; 153: 110898.
41.
BallAKBasakA. AI modeling for high-fidelity heat transfer and thermal distortion forecast in metal additive manufacturing. Int J Adv Manuf Technol2023; 128: 2995–3010.
42.
ElaminNYElaminMRSalihM, et al.Machine learning-enabled discrete transfer function modeling and optimization of mechanical properties in ARB-fabricated Al/Ni/SiC nanocomposites. Mater Today Commun2025; 49: 113777.
43.
AhmadianHZhouTAbd ElazizM, et al.Predicting crystallite size of Mg-Ti-SiC nanocomposites using an adaptive neuro-fuzzy inference system model modified by termite life cycle optimizer. Alexandria Eng J2023; 84: 285–300.
44.
AlbahkaliTAbdoHSSalahO, et al.Adaptive neuro-fuzzy-based models for predicting the tribological properties of 3D-printed PLA green composites used for biomedical applications. Polymers (Basel)2023; 15: 3053.
45.
SavkovicBKovacPDudicB, et al.Application of an adaptive “neuro-fuzzy” inference system in modeling cutting temperature during hard turning. Appl Sci2019; 9: 3739.
46.
DambattaYSSayutiMSarhanAAD, et al.Prediction of specific grinding forces and surface roughness in machining of AL6061-T6 alloy using ANFIS technique. Ind Lubr Tribol2019; 71: 309–317.
47.
BallAKDasRRoySS, et al.Modeling of EHD inkjet printing performance using soft computing-based approaches. Soft Comput2020; 24: 571–589.
48.
DattaSDasAKRazaMS, et al.Study on laser beam butt-welding of NiTinol sheet and input-output modelling using neural networks trained by metaheuristic algorithms. Mater Today Commun2022; 32: 104089.
49.
MajiKPratiharDKNathAK. Forward and inverse predictions of deformations in laser forming of shaped surfaces under coupling mechanism. J Laser Appl2018; 30: 32011.
50.
PratiharDK. Expert systems in manufacturing processes using soft computing. Int J Adv Manuf Technol2015; 81: 887–896.
51.
ChangJHeJLeiQ, et al.Electrohydrodynamic printing of microscale PEDOT:PSS-PEO features with tunable conductive/thermal properties. ACS Appl Mater Interfaces2018; 10: 19116–19122.
52.
KimYGenslerMKimJ, et al.High-resolution patterning via electrohydrodynamic (EHD)-jet printing for quantum dot light-emitting diodes. J Soc Inf Disp2025; 33: 1092–1102.
53.
YangMYuC. Microfabricated conductive PEDOT:PSS hydrogels for soft electronics. Korean J Chem Eng2025; 42: 935–952.
54.
PrabhuSVNagarajanNThakurY, et al.Processing and carbon nanotube actions on functional behavior of poly(3,4-ethylenedioxythiophene): poly (styrene sulfonate) conductive polymer. J Appl Polym Sci2025; n/a: e70087.
55.
ShettySSaquibMSelvakumarM, et al.Screen-printable water-based poly(3,4-ethylenedioxythiophene): poly(styrenesulfonate)/ polypyrrole/ reduced graphene oxide ink for micro-supercapacitor and humidity sensor. J Power Sources2025; 660: 238492.
56.
MontgomeryD. Design and analysis of experiments: International student version. 8th ed. New Delhi: Wiley India Pvt. Ltd, 2013.
57.
DasRBallAKRoySS. Application of PCA-based hybrid methodologies for parameter optimization of E-jet based micro-fabrication process: a comparative study. J Brazilian Soc Mech Sci Eng2018; 40: 454.
58.
BallAKDasRRoySS, et al.Experimentation modelling and optimization of electrohydrodynamic inkjet microfabrication approach: a Taguchi regression analysis. Sadhana - Acad Proc Eng Sci2019; 44: 167–183.
59.
Kumar BallADasRDasD, et al.Design, development and experimental investigation of E-jet based additive manufacturing process. Mater Today Proc2018; 5: 7355–7362.
60.
DasRBallAKShekhar RoyS. Application of MCDM methodology for performance evaluation of inkjet based micro-fabrication process. IOP Conf Ser Mater Sci Eng2018; 377: 012034.
61.
ShucaiYChunshengHMinliZ. A prediction model for titanium alloy surface roughness when milling with micro-textured ball-end cutters at different workpiece inclination angles. Int J Adv Manuf Technol2019; 100: 2115–2122.
62.
MalghanRLKRMCShettigarAK, et al.Forward and reverse mapping for milling process using artificial neural networks. Data Br2018; 16: 114–121.
63.
SunXYueLYuL, et al.Machine learning-enabled forward prediction and inverse design of 4D-printed active plates. Nat Commun2024; 15: 5509.
64.
ReddyDYAPratiharDK. Neural network-based expert systems for predictions of temperature distributions in electron beam welding process. Int J Adv Manuf Technol2011; 55: 535–548.
65.
RoySS. Modelling and predicting surface finish in turning using an adaptive neuro-fuzzy inference system. Int J Intell Eng Informatics2013; 2: 1.
PratiharDK. Soft computing: Fundamentals and applications. New Delhi, India: Alpha Science International, Limited, 2015.
70.
BengioYSimardPFrasconiP. Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Networks1994; 5: 157–166.
71.
KosaracAMladjenovicCZeljkovicM, et al.Neural-network-based approaches for optimization of machining parameters using small dataset. Materials (Basel)2022; 15: 700.
72.
SzandałaT, et al.Review and comparison of commonly used activation functions for deep neural networks. In: BhoiAKMallickPKLiuC-M (eds) Singapore: Springer Singapore, 2021, pp.203–224.
73.
SondagarHBhadauriaSSSharmaVS. Artificial neural network (ANN) based prediction of process parameters in additive manufacturing. IOP Conf Ser Mater Sci Eng2021; 1136: 012026.
74.
LucignanoCMontanariRTagliaferriV, et al.Artificial neural networks to optimize the extrusion of an aluminium alloy. J Intell Manuf2010; 21: 569–574.
75.
SudhaLDillibabuRSrivatsa SrinivasS, et al.Optimization of process parameters in feed manufacturing using artificial neural network. Comput Electron Agric2016; 120: 1–6.
76.
KhoshvaghtHPermalaRRRazmjouA, et al.A critical review on selecting performance evaluation metrics for supervised machine learning models in wastewater quality prediction. J Environ Chem Eng2025; 13: 119675.
77.
AlaliYHarrouFSunY. Unlocking the potential of wastewater treatment: machine learning based energy consumption prediction. Water (Basel)2023; 15: 2349.
78.
HamadaMSZaqootHASetharWA. Using a supervised machine learning approach to predict water quality at the Gaza wastewater treatment plant. Environ Sci Adv2024; 3: 132–144.
79.
WarrenWG. Correlation or regression: bias or precision. Appl Stat1971; 20: 148.
80.
SpiessA-NNeumeyerN. An evaluation of R2 as an inadequate measure for nonlinear models in pharmacological and biochemical research: a Monte Carlo approach. BMC Pharmacol2010; 10: 6.
81.
ChiccoDWarrensMJJurmanG. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Comput Sci2021; 7: e623.
82.
WillmottCJ. Some comments on the evaluation of model performance. Bull Am Meteorol Soc1982; 63: 1309–1313.
83.
AsueroAGSayagoAGonzálezAG. The correlation coefficient: an overview. Crit Rev Anal Chem2006; 36: 41–59.
84.
RobesonSMWillmottCJ. Decomposition of the mean absolute error (MAE) into systematic and unsystematic components. PLoS ONE2023; 18: e0279774.
85.
ZaghloulMSHamzaRAIorhemenOT, et al.Comparison of adaptive neuro-fuzzy inference systems (ANFIS) and support vector regression (SVR) for data-driven modelling of aerobic granular sludge reactors. J Environ Chem Eng2020; 8: 103742.
86.
MakridakisS. Accuracy measures: theoretical and practical concerns. Int J Forecast1993; 9: 527–529.
87.
KimSKimH. A new metric of absolute percentage error for intermittent demand forecasts. Int J Forecast2016; 32: 669–679.
88.
WillmottCJRobesonSMMatsuuraK. A refined index of model performance. Int J Climatol2012; 32: 2088–2094.
89.
WillmottCJMatsuuraK. On the use of dimensioned measures of error to evaluate the performance of spatial interpolators. Int J Geogr Inf Sci2006; 20: 89–102.
90.
GoodwinPLawtonR. On the asymmetry of the symmetric MAPE. Int J Forecast1999; 15: 405–408.
91.
MathewsBPDiamantopoulosA. Towards a taxonomy of forecast error measures a factor-comparative investigation of forecast error dimensions. J Forecast1994; 13: 409–416.
92.
PalaniSNatarajanUChellamalaiM. On-line prediction of micro-turning multi-response variables by machine vision system using adaptive neuro-fuzzy inference system (ANFIS). Mach Vis Appl2013; 24: 19–32.
93.
ShastriASNargundkarAKulkarniAJ, et al.Multi-cohort intelligence algorithm for solving advanced manufacturing process problems. Neural Comput Appl2020; 32: 15055–15075.
94.
SuganthiXHNatarajanUSathiyamurthyS, et al.Prediction of quality responses in micro-EDM process using an adaptive neuro-fuzzy inference system (ANFIS) model. Int J Adv Manuf Technol2013; 68: 339–347.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
