CLASSIFICATION OF HYDROGEN CONCENTRATIONS BASED ON TIO2 GAS SENSOR RESPONSES USING ARTIFICIAL NEURAL NETWORK
DOI:
https://doi.org/10.11113/aej.v15.23553Keywords:
TiO2 gas sensor, principal component analysis, Artificial Neural Network, gas classificationAbstract
In this research endeavor, a TiO2 gas sensor was employed to discern the TiO2 gas sensor response to varying hydrogen gas concentrations across three distinct temperature settings: 150℃, 200℃, and 250℃. The concentration levels spanned from 100 to 1000 ppm. The primary objective of this investigation was twofold: firstly, to eliminate the noise from the captured response, thereby clustering the gas sensor response at various hydrogen concentrations using principal component analysis, and secondly, to classify the hydrogen concentration using an artificial neural network. Five distinct hydrogen concentration values were extracted from each set of samples, in the range of 100 to 1000 ppm. All the values were acquired at different operational temperatures. The ensuing analytical phase utilizes the Principal Component Analysis (PCA) method in conjunction with an Artificial Neural Network (ANN). Remarkably, classification accuracy achieved a median testing accuracy of 88.8% in 70% of the training data and 15% of the testing strategy
References
D. An, J. Dai, Z. Zhang, Y. Wang, N. Liu, and Y. Zou, 2024. “rGO/SnO2 nanocomposite based sensor for ethanol detection under low temperature,” Ceramics International, 50(9): 16272– 16283, DOI: 10.1016/j.ceramint.2024.02.107.
J. Y. Kim, S. P. Bharath, A. Mirzaei, S. S. Kim, and H. W. Kim, 2023, “Identification of gas mixtures using gold-decorated metal oxide based sensor arrays and neural networks,” Sensors Actuators B: Chemical, 386: 133767, DOI: 10.1016/j.snb.2023.133767.
J. Li et al., 2023, “Low-temperature and high-sensitivity Au-decorated thin walled SnO2 nanotubes sensor for ethanol detection,” Materials Today Communications, 37: 107217, doi: 10.1016/j.mtcomm.2023.107217.
V. S. Chandak, M. B. Kumbhar, and P. M. Kulal, 2024. “Highly sensitive and selective acetone gas sensor-based La-doped ZnO nanostructured thin film,” Materials Letters, 357: 135747, DOI: 10.1016/j.matlet.2023.135747.
X. Sun et al., 2024, “UV-activated AuAg/ZnO microspheres for highperformance methane sensor at room temperature,” Ceramics International, 50(17PB): 30552–30559, DOI: 10.1016/j.ceramint.2024.05.352.
[6] J. Chao, D. Meng, K. Zhang, J. Wang, L. Guo, and X. Yang, 2024. “Development of an innovative ethanol sensing sensor platform based on the construction of Au modified 3D porous ZnO hollow microspheres,” Materials Research Bulletin, 170: 112569, DOI: 10.1016/j.materresbull.2023.112569.
L. B. Tasyurek, E. Isik, I. Isik, and N. Kilinc, 2024, “Enhancing the performance of TiO2 nanotube-based hydrogen sensors through crystal structure and metal electrode,” International Journal of Hydrogen Energy. 54: 678–690, DOI: 10.1016/j.ijhydene.2023.08.202.
I. Nainggolan, W. T. Wadana, T. I. Nasution, and A. Sembiring, 2024, “The sensitivity of chitosan/TiO2 film on ammonia detection,” Materials Today: Proceedings, 0–7, DOI: 10.1016/j.matpr.2024.03.013.
S. Amaniah Mohd Chachuli, M. Nizar Hamidon, M. Ertugrul, M. S. Mamat, H. Jaafar, and N. H. Shamsudin, 2020, “TiO2/B2O3 thick film gas sensor for monitoring carbon monoxide at different operating temperatures,” Journal of Physics: Conference Series. 1432(1), DOI: 10.1088/1742-6596/1432/1/012040.
Y. Wang et al., 2023, “CuO/WO3 hollow microsphere P-N heterojunction sensor for continuous cycle detection of H2S gas,” Sensors Actuators B: Chemical, 374: 132823, DOI: 10.1016/j.snb.2022.132823.
L. Piliai et al. 2023. “NAP-XPS study of surface chemistry of CO and ethanol sensing with WO3 nanowires-based gas sensor,” Sensors Actuators B: Chemical, 397 DOI: 10.1016/j.snb.2023.134682.
D. L. Kong et al., 2023 “Ag-nanoparticles-anchored mesoporous In2O3 nanowires for ultrahigh sensitive formaldehyde gas sensors,” Materials Science and Engineering: B, 291. DOI: 10.1016/j.mseb.2023.116394.
M. B. Kgomo, K. Shingange, M. I. Nemufulwi, H. C. Swart, and G. H. Mhlongo, 2023. “Belt-like In2O3 based sensor for methane detection: Influence of morphological, surface defects and textural behavior,” Materials Research Bulletin, 158: 112076, DOI: 10.1016/j.materresbull.2022.112076.
S. Amaniah, M. Chachuli, M. Nizar, H. Mehmet, E. Shuhazlly, and M. Omer, “Comparative analysis of hydrogen sensing based on treated TiO2 in thick film gas sensor,” Applied Physics A: Materials Science and Processing, 128(7). DOI: 10.1007/s00339-022-05738-z.
S. A. Mohd Chachuli et al. 2024, “Effects of silver diffusement on TiO2-B2O3 nanocomposite sensor towards hydrogen sensing,” Materials Research Innovations. 1–14 DOI: 10.1080/14328917.2024.2304480.
K. Siwek and S. Osowski, 2018, “Deep neural networks and classical approach to face recognition – Comparative analysis,” Przegląd Elektrotechniczny, 94(4): 3–6. DOI: 10.15199/48.2018.04.01.
X. Yang, Z. Wang, H. Wu, L. Jiao, Y. Xu, and H. Chen, 2023, “Stable and compact face recognition via unlabeled data driven sparse representation-based classification,” Signal Processing: Image Communication, 11: 116889, DOI: 10.1016/j.image.2022.116889.
P. Kluge, 2021, “Methods for the classification and selection of extracted features of insulation defects from PD,” Przegląd Elektrotechniczny, 1(6): 79–82, DOI: 10.15199/48.2021.06.14.
T. Zhou, X. Zhu, H. Yang, X. Yan, X. Jin, and Q. Wan, 2023, “Identification of XLPE cable insulation defects based on deep learning,” Global Energy Interconnection, 6(1): 36–49, DOI: 10.1016/j.gloei.2023.02.004.
P. Narkhede, R. Walambe, S. Mandaokar, P. Chandel, K. Kotecha, and G. Ghinea, 2021. “Gas detection and identification using multimodal artificial intelligence based sensor fusion,” Applied System Innovation, 4(1): 1–14. DOI: 10.3390/asi4010003.
J. Oh et al. 2022., “Machine learning-based discrimination of indoor pollutants using an oxide gas sensor array: High endurance against ambient humidity and temperature,” Sensors Actuators B: Chemical, 364: 131894, DOI: 10.1016/j.snb.2022.131894.
J. Chu et al., 2021, “Identification of gas mixtures via sensor array combining with neural networks,” Sensors Actuators B: Chemical. 329: 129090, DOI: 10.1016/j.snb.2020.129090.
X. Chen, Q. Xing, X. Tang, Y. Cai, and M. Zhang, 2024, “Machine learning algorithm assisted cerium oxide based high selectivity acetone sensor,” Ceramics International, 50(21PA): 41770–41779, DOI: 10.1016/j.ceramint.2024.08.030.
N. Lim et al., 2024. “Enhancing mixed gas discrimination in e-nose system: Sparse recurrent neural networks using transient current fluctuation of SMO array sensor,” Journal of Industrial Information Integration, 42: 100715, DOI: 10.1016/j.jii.2024.100715.
B. Wang et al., 2023. “Artificial olfaction based on tafel curve for quantitative detection of acetone ethanol gas mixture,” Sensors Actuators B: Chemical, 377: 2–9, doi: 10.1016/j.snb.2022.133049.
I. Sohn et al., 2025, “Selective denoising autoencoder for classification of noisy gas mixtures using 2D transition metal dichalcogenides,” Talanta. 283: 127129, DOI: 10.1016/j.talanta.2024.127129.
Z. Wang et al., 2024. “Improved deep bidirectional recurrent neural network for learning the cross-sensitivity rules of gas sensor array,” Sensors Actuators B: Chemical, 401: 134996, DOI: 10.1016/j.snb.2023.134996.
