Journal of Scientific and Industrial Research

Open Access Open Access  Restricted Access Subscription Access

Deep Neural Network Based Modelling of Chemisorption Process on Surface of Oxide Based Gas Sensors


Affiliations
1 J. C. Bose University of Science and Technology, YMCA, Faridabad 121 006, Haryana, India
2 Department of Electronic Science, Kurukshetra University, Kurukshetra 136 119, Haryana, India
 

The sensor response of the metal oxide based gas sensor has been simulated using Deep Neural Network (DNN) model. The neural network designed for the modelling of the sensor has single input layer, three hidden layers and single output layer. The linear regression algorithm has been used to compute the electrical conductance of the sensor at given temperature and pressure. The data generated through modified Wolkenstein method has been used for training, validation and testing of the developed network. The data for materials Tin (IV) oxide (SnO2), Tin (II) oxide (SnO) and Copper (I) oxide (Cu2O) with different Eg values has been utilized. The other input parameters like Temperature, ND, NC, NV, EF−ESSand ECS−EF are varied for the specific range to collect a variety of data for calculation of electrical conductance of the sensor. The total data used for training, validation and testing was 1,90,512 data points. The plots for training, validation and testing phase have been plotted. The sensor response computed through the proposed model is validated with the results of already published mathematical model. The sensor response shows steep change when the gas concentration of the target gas reaches above 10-8 atm. The proposed model can be retrained or transfer learning can be applied for using the same model for other types of materials for gas sensing applications.

Keywords

Chemisorption, Deep neural network, Gas sensor, Numerical modelling.
User
Notifications
Font Size

  • Shankar P & Rayappan J B B, Gas sensing mechanism of metal oxides: The role of ambient atmosphere, type of semiconductor and gases - A review, Sci Lett, 126(4) (2015).

  • Barsan N, Koziej D & Weimar U, Metal oxide-based gas sensor research: How to?, Sens Actuators B: Chem, 121(1) (2007) 18–35, https://doi.org/10.1016/j.snb.2006.09.047.

  • Korotcenkov G, Metal oxides for solid-state gas sensors: What determines our choice?, Mater Sci Eng B, 139(1) (2007) 1–23, https://doi.org/10.1016/j.mseb. 2007.01.044.

  • Li Z, Yu J, Dong D, Yao G, Wei G, He A, Wu H, Zhu H, Huang Z & Tang Z, E-nose based on a high-integrated and low-power metal oxide gas sensor array, Sens Actuators B: Chem, 380(1) (2023) 133289, https://doi.org/10.1016/ J.SNB.2023.133289.

  • Nurputra D, Kusumaatmaja A, Hakim M, Hidayat S, Julian T, Sumanto B, Mahendradhata Y, Saktiawati A, Wasisto H & Triyana K, Fast and noninvasive electronic nose for sning out COVID-19 based on exhaled breath-print recognition, NPJ Digit Med, 5(1) (2021) 115, https://doi.org/ 10.21203/rs.3.rs-750988/v1.

  • Sharma N & Liu Y A, A hybrid science-guided machine learning approach for modeling chemical processes: A review, AIChE J, 68(5) (2022) 17609, https://doi.org/10.1002/ aic.17609.

  • Aliyana A K, Kumar S K N, Marimuthu P, Baburaj A, Adetunji M, Frederick T, Sekhar P & Fernandez R E, Machine learning-assisted ammonium detection using zinc oxide/multi-walled carbon nanotube composite based impedance sensors, Sci Rep, 11(1) (2021) 24321, https://doi.org/10.1038/s41598-021-03674-1.

  • Oh J, Kim S H, Lee M-J, Hwang H, Ku W, Lim J, Hwang I-S, Lee J-H & Hwang J-H, Machine learning-based discrimination of indoor pollutants using an oxide gas sensor array: High endurance against ambient humidity and temperature, Sens Actuators B: Chem, 364(1) (2022) 131894, https://doi.org/10.1016/J.SNB.2022.131894.

  • Zhang Y & Xu X, Predictions of adsorption energies of methane-related species on Cu-based alloys through machine learning, Mach Learn, 3(1) (2021) 100010, https://doi.org/10.1016/j.mlwa.2020.100010.

  • Esterhuizen J A, Goldsmith B R & Linic S, Theory-guided machine learning finds geometric structure-property relationships for chemisorption on subsurface alloys, Chem, 6(11) (2020) 3100–3117, https://doi.org/10.1016/ j.chempr. 2020.09.001.

  • Toyao T, Suzuki K, Kikuchi S, Takakusagi S, Shimizu K & Takigawa I, Toward effective utilization of methane: Machine learning prediction of adsorption energies on metal alloys, J Phys Chem C, 122(15) (2018) 8315–8326, https://doi.org/10.1021/acs.jpcc.7b12670.

  • Xiao J, Fu Z, Wang G, Ye X & Xu G, Atomicallythin 2D TiO2 nanosheets with ligand modified surface for ultrasensitive humidity sensor, Jiegou Huaxue, 41(4) (2022) 2204054–2204060, https://doi.org/10.14102/j.cnki.0254- 5861.2022-0046.

  • Gomri S, Seguin J-L, Guerin J & Aguir K, Adsorption– desorption noise in gas sensors: Modelling using Langmuir and Wolkenstein models for adsorption, Sens Actuators B: Chem, 114(1) (2006) 451–459, https://doi.org/10.1016/ j.snb.2005.05.033.

  • Bejaoui A, Guerin J & Aguir K, Modeling of a p-type resistive gas sensor in the presence of a reducing gas, Sens Actuators B: Chem, 181(1) (2013) 340–347, https://doi.org/10.1016/j.snb.2013.01.018S.

  • Brinzari V, Korotcenkov G & Boris Y, Chemisorptional approach to kinetic analysis of SnO2: Pd-based thin film gas sensors, J Optoelectron Adv Mater, 4(1), 2002 147–150.

  • Bârsan N, Hübner M & Weimar U, Conduction mechanisms in SnO2 based polycrystalline thick film gas sensors exposed to CO and H2 in different oxygen backgrounds, Sens Actuators B: Chem, 157(2) (2011) 510–517, https://doi.org/ 10.1016/j.snb.2011.05.011.

  • Gomri S, Seguin J-L & Aguir K, Modeling on oxygen chemisorption-induced noise in metallic oxide gas sensors, Sens Actuators B: Chem, 107(2) (2005) 722–729, https://doi.org/10.1016/j.snb.2004.12.003.

  • Wolkenstein T, The electron theory of catalysis on semiconductors, Adv Catal, 12(1) (1960) 189–264. https://doi.org/10.1016/S0360-0564(08)60603-3.

  • Bârsan N, Transduction in semiconducting metal oxide basedgas sensors - Implications of the conduction mechanism, Procedia Eng, 25(1) (2011) 100–103, https://doi.org/10.1016/ j.proeng.2011.12.025.

  • Gupta R, Kumar A, Rohilla V, Kumar P, Kumar M & Kumar D, Noise spectroscopy based numerical modelling of chemisorption on SnO2 surface for CO gas sensing applications, Micro Nanostructures, 171(1) (2022) 207423, https://doi.org/10.1016/j.micrna. 2022.207423.

  • Kumar A, Kumar M, Kumar R, Singh R, Prasad B & Kumar D, Numerical model for the chemical adsorption of oxygen and reducing gas molecules in presence of humidity on the surface of semiconductor metal oxide for gas sensors applications, Mater Sci Semicond, 90(1) (2019) 236–244, https://doi.org/10.1016/j.mssp.2018.10.020.

  • Pareek V & Chaudhury S, Deep learning-based gas identification and quantification with auto-tuning of hyperparameters, Soft Comput, 25(22) (2021) 14155–14170, https://doi.org/10.1007/s00500-021-06222-1.

  • Kwon Y M, Oh B, Purbia R, Chae H Y, Han G H, Kim S-W, Choi K-J, Lee Y, Kim J J & Baik J M, High-performance and self-calibrating multi-gas sensor interface to trace multiple gas species with sub-ppm level, Sens Actuators B: Chem, 375(1) (2023)132939, https://doi.org/10.1016/ J.SNB.2022.132939.

  • Zhai S, Han M, Li Z, Yang S, Duan S & Yan J, M2FL-CCC: Multibranch multilayer feature leaning and comprehensive classification criterion for gas sensor drift compensation, IEEE Trans Instrum, 72(1) (2023) 1–12, https://doi.org/ 10.1109/TIM.2023.3296820.

  • Juffry Z H M, Kamarudin K, Adom A H, Miskon M F, Kamarudin L M, Zakaria A, Zakaria S M M S & Abdullah A N, Application of deep neural network for gas source localization in an indoor environment, Int J Comput Commun, 18(3) (2023) 5084, https://doi.org/10.15837/ ijccc.2023.3.5084.

  • Rajshekar K & Kannadassan D, A comprehensive density-ofstates model for oxide semiconductor thin film transistors, J Comput Electron, 20(6) (2021) 2331–2341, https://doi.org/ 10.1007/s10825-021-01783-8.


Abstract Views: 106

PDF Views: 55




  • Deep Neural Network Based Modelling of Chemisorption Process on Surface of Oxide Based Gas Sensors

Abstract Views: 106  |  PDF Views: 55

Authors

Rahul Gupta
J. C. Bose University of Science and Technology, YMCA, Faridabad 121 006, Haryana, India
Pradeep Kumar
J. C. Bose University of Science and Technology, YMCA, Faridabad 121 006, Haryana, India
Dinesh Kumar
Department of Electronic Science, Kurukshetra University, Kurukshetra 136 119, Haryana, India

Abstract


The sensor response of the metal oxide based gas sensor has been simulated using Deep Neural Network (DNN) model. The neural network designed for the modelling of the sensor has single input layer, three hidden layers and single output layer. The linear regression algorithm has been used to compute the electrical conductance of the sensor at given temperature and pressure. The data generated through modified Wolkenstein method has been used for training, validation and testing of the developed network. The data for materials Tin (IV) oxide (SnO2), Tin (II) oxide (SnO) and Copper (I) oxide (Cu2O) with different Eg values has been utilized. The other input parameters like Temperature, ND, NC, NV, EF−ESSand ECS−EF are varied for the specific range to collect a variety of data for calculation of electrical conductance of the sensor. The total data used for training, validation and testing was 1,90,512 data points. The plots for training, validation and testing phase have been plotted. The sensor response computed through the proposed model is validated with the results of already published mathematical model. The sensor response shows steep change when the gas concentration of the target gas reaches above 10-8 atm. The proposed model can be retrained or transfer learning can be applied for using the same model for other types of materials for gas sensing applications.

Keywords


Chemisorption, Deep neural network, Gas sensor, Numerical modelling.

References