Multicomponent SF6 decomposition product sensing with a gas-sensing microchip
Autor: | Dawei Wang, Huan Yuan, Aijun Yang, Xu Yang, Qiongyuan Wang, Jifeng Chu, Mingzhe Rong, Xiaohua Wang |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2021 |
Předmět: |
Generalization
Computer science Materials Science (miscellaneous) Reliability (computer networking) 02 engineering and technology 01 natural sciences lcsh:Technology Industrial and Manufacturing Engineering chemistry.chemical_compound Decomposition (computer science) Electrical and Electronic Engineering Statistical hypothesis testing business.industry Noise (signal processing) lcsh:T 010401 analytical chemistry Pattern recognition 021001 nanoscience & nanotechnology Condensed Matter Physics Chip Atomic and Molecular Physics and Optics 0104 chemical sciences Sulfur hexafluoride Surface micromachining chemistry lcsh:TA1-2040 Artificial intelligence 0210 nano-technology business lcsh:Engineering (General). Civil engineering (General) |
Zdroj: | Microsystems & Nanoengineering, Vol 7, Iss 1, Pp 1-16 (2021) |
ISSN: | 2055-7434 |
Popis: | A difficult issue restricting the development of gas sensors is multicomponent recognition. Herein, a gas-sensing (GS) microchip loaded with three gas-sensitive materials was fabricated via a micromachining technique. Then, a portable gas detection system was built to collect the signals of the chip under various decomposition products of sulfur hexafluoride (SF6). Through a stacked denoising autoencoder (SDAE), a total of five high-level features could be extracted from the original signals. Combined with machine learning algorithms, the accurate classification of 47 simulants was realized, and 5-fold cross-validation proved the reliability. To investigate the generalization ability, 30 sets of examinations for testing unknown gases were performed. The results indicated that SDAE-based models exhibit better generalization performance than PCA-based models, regardless of the magnitude of noise. In addition, hypothesis testing was introduced to check the significant differences of various models, and the bagging-based back propagation neural network with SDAE exhibits superior performance at 95% confidence. |
Databáze: | OpenAIRE |
Externí odkaz: |