Abstract
Atmospheric Ar:H2 plasma is an eco-friendly option for the reduction of metal oxides. For better reduction performance and safety concern, the hydrogen gas injected into the reactor should be monitored. A hydrogen flow rate estimation system is presented in this paper by using an artificial neural network (ANN) model fed with features of optical emission spectra of the plasma. ANN models are studied with two different sets of input, i.e. for the first case the inputs to the model are the three features of Hα line such as the peak intensity count, full-width half maximum and area under Hα line, while for the second case, the peak intensity count of a group of emission lines like Hα, Ar I, O I, K I, Na D lines are considered as the inputs. ANN model is developed for estimating four different sets of hydrogen flow rates 5, 8, 10 and 12 litres per minute (lpm) when the argon flow rate is constant at 10 lpm. For both the input features, the model performances are compared, and it is shown that improved estimation accuracy is observed from the second case, i.e. from peak intensity count of a group of emission lines instead of only hydrogen emission line.
Similar content being viewed by others
References
Guessasma S, Montavon G, Coddet C (2004) Modeling of the APS plasma spray process using artificial neural networks: basis, requirements and an example. Comput Mater Sci 29:315–333
Leparoux M, Loher M, Schreuders C, Siegmann S (2008) Neural network modelling of the inductively coupled RF plasma synthesis of silicon nanoparticles. Powder Technol 185:109–115
Srinivas K, Vundavilli PR, Hussain MM, Saiteja M (2016) Prediction of welded joint strength in plasma arc welding: a comparative study using back-propagation and radial basis neural networks. IOP Conf Ser Mater Sci Eng 149(1-8):012033
Hong SJ, May GS, Park DC (2003) Neural network modeling of reactive ion etching using optical emission spectroscopy data. IEEE Trans Semicond Manuf 16(4):598–608
Lee SF, Spanos CJ (1995) Prediction of wafer state after plasma processing using real-time tool data. IEEE Trans Semicond Manuf 8:252–261
Pal S, Pal SK, Samantaray AK (2008) Artificial neural network modeling of weld joint strength prediction of a pulsed metal inert gas welding process using arc signals. J Mater Process Technol 202:464–474
Kim B, Lee H, Kim D (2009) Modeling of thin film process data using a genetic algorithm-optimized initial weight of back propagation neural network. Appl Artif Intell 23:168–178
Kim B, Kim D (2012) Use of neural network to in situ conditioning of semiconductor plasma processing equipment. Appl Soft Comput 12:826–831
Kim B, Kwon M (2009) Prediction of plasma etch process by using actinometry-based optical emission spectroscopy data and neural network. J Mater Process Technol 209:2620–2626
Barana O, Manduchi G (2002) Application of neural networks for the measurement of electronic temperature in nuclear fusion experiments. Neural Comput Appl 10:351–356
Jelil RA, Zeng X, Koehl L, Perwuelz A (2013) Modeling plasma surface modification of textile fabrics using artificial neural networks. Eng Appl Artif Intell 26:1854–1864
Rastovic D (2012) Targeting and synchronization at tokamak with recurrent artificial neural networks. Neural Comput Appl 21(5):1065–1069
Liu T, Planche MP, Kanta AF, Deng S, Montavon G, Deng K, Ren ZM (2013) Plasma spray process operating parameters optimization based on artificial intelligence. Plasma Chem Plasma Process 33:1025–1041
Choudhury TA, Berndt CC, Man Z (2015) Modular implementation of artificial neural network in predicting in-flight particle characteristics of an atmospheric plasma spray process. Eng Appl Artif Intell 45:57–70
Yadav N, Yadav A, Kumar M, Kim JH (2017) An efficient algorithm based on artificial neural networks and particle swarm optimization for solution of nonlinear Troesch’s problem. Neural Comput Appl 28:171–178
Raja MAZ, Shah FH, Tariq M, Ahmad I, Ahmad SI (2017) Design of artificial neural network models optimized with sequential quadratic programming to study the dynamics of nonlinear Troesch’s problem arising in plasma physics. Neural Comput Appl. https://doi.org/10.1007/s00521-016-2530-2
Yadav N, McFall KS, Kumar M, Kim JH (2016) A length factor artificial neural network method for the numerical solution of the advection dispersion equation characterizing the mass balance of fluid flow in a chemical reactor. Neural Comput Appl. https://doi.org/10.1007/s00521-016-2722-9
Khandelwal M, Marto A, Fatemi SA, Ghoroqi M, Armaghani DJ, Singh TN, Tabrizi O (2018) Implementing an ANN model optimized by genetic algorithm for estimating cohesion of limestone samples. Eng Comput 34:307–317
Abad SV, Yilmaz M, Armaghani DJ, Tugrul A (2018) Prediction of the durability of limestone aggregates using computational techniques. Neural Comput Appl 29(2):423–433
Dalvand S, Ebrahimi M, Pouryoussefi SG (2018) Experimental investigation, modeling and prediction of transition from uniform discharge to filamentary discharge in DBD plasma actuators using artificial neural network. Appl Therm Eng 29:50–61
Chaki S, Bathe RN, Ghosal S, Padmanabham G (2018) Multi-objective optimisation of pulsed Nd:YAG laser cutting process using integrated ANN–NSGAII model. J Intell Manuf 29(1):175–190
Chen J, Feng J, Lu S, Shen Z, Du Y, Peng L, Nian P, Yuan S, Zhang A (2018) Non-thermal plasma and Fe2+ activated persulfate ignited degradation of aqueous crystal violet: degradation mechanism and artificial neural network modeling. Sep Purif Technol 191:75–85
Davoudi M, Davoudi M (2018) Estimation of ECH power deposition based on neural networks and fuzzy logic in plasma fusion Tokamaks. Fusion Eng Des 129:58–67
Palmer RA, Doan TM, Lloyd PG, Jarvis BL, Ahmed NU (2002) Reduction of TiO2 with hydrogen plasma. Plasma Chem Plasma Process 22:335–350
Fauchais P, Rat V, Delbos C, Coudert JF, Chartier T, Bianchi L (2005) Understanding of suspension DC plasma spraying of finely structured coatings for SOFC. IEEE Trans Plasma Sci 33:920–930
Crowl DA, Jo YD (2007) The hazards and risks of hydrogen. J Loss Prev Process Ind 20:158–164
Hiebler H, Plaul JF (2004) Hydrogen plasma smelting reduction—an option for steelmaking in the future. Metalurgija 43:155–162
Plaul JF, Krieger W, Back E (2005) Reduction of fine ores in argon–hydrogen plasma. Steel Res Int 76:548–554
Lemperle M, Weigel A (1985) On the smelting reduction of iron ores with hydrogen-argon plasma. Steel Res Int 56:465–469
Kamiya K, Kitahara N, Morinaka I, Sakuraya K, Ozawa M, Tanaka M (1984) Reduction of molten iron oxide and FeO bearing slags by H2–Ar plasma. Trans Iron Steel Inst Jpn 24:7–16
Sabat KC, Rajput P, Paramguru R, Bhoi B, Mishra BK (2014) Reduction of oxide minerals by hydrogen plasma: an overview. Plasma Chem Plasma Process 34(1):1–23
Das S, Das DP, Rajput P, Ghosh J, Bhoi B, Mishra BK (2016) Monitoring hydrogen plasma reduction of oxides by Na D lines. Plasma Chem Plasma Process 36(4):1125–1139
Rajput P, Bhoi B, Sahoo S, Paramguru RK, Mishra BK (2013) Preliminary investigation into direct reduction of iron in low temperature hydrogen plasma. Ironmak Steelmak 40:61–68
Hassoun MH (1995) Fundamentals of artificial neural networks. MIT Press, Cambridge
NIST Database, http://physics.nist.gov/PhysRefData/ASD/lines_form.html. Accessed 14 Aug 2018
Acknowledgements
The authors would like to acknowledge the Ministry of Steel, Govt. of India and CSIR for financial support under GAP-208 and FAC-11, OLP-50 Projects, respectively. Sarita Das would like to thank CSIR for financial assistance through CSIR-SRF fellowship.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
All authors declare that they have no conflict of interest.
Rights and permissions
About this article
Cite this article
Das, S., Das, D.P., Sarangi, C.K. et al. Estimation of hydrogen flow rate in atmospheric Ar:H2 plasma by using artificial neural network. Neural Comput & Applic 32, 1357–1365 (2020). https://doi.org/10.1007/s00521-018-3674-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-018-3674-z