Neural network fusion and inversion model for NDIR sensor measurement
Fragment książki (Materiały konferencyjne)
MNiSW
15
WOS
| Status: | |
| Autorzy: | Cięszczyk Sławomir, Komada Paweł |
| Wersja dokumentu: | Drukowana | Elektroniczna |
| Arkusze wydawnicze: | 0,5 |
| Język: | angielski |
| Strony: | 173 - 179 |
| Web of Science® Times Cited: | 1 |
| Scopus® Cytowania: | 4 |
| Bazy: | Web of Science | Scopus |
| Efekt badań statutowych | NIE |
| Materiał konferencyjny: | TAK |
| Nazwa konferencji: | 16th Conference on Optical Fibers and their Applications |
| Skrócona nazwa konferencji: | 16th SPIE-IEEE-OFTA 2015 |
| URL serii konferencji: | LINK |
| Termin konferencji: | 22 września 2015 do 25 września 2015 |
| Miasto konferencji: | Nałęczów |
| Państwo konferencji: | POLSKA |
| Publikacja OA: | NIE |
| Abstrakty: | angielski |
| This article presents the problem of the impact of environmental disturbances on the determination of information from measurements. As an example, NDIR sensor is studied, which can measure industrial or environmental gases of varying temperature. The issue of changes of influence quantities value appears in many industrial measurements. Developing of appropriate algorithms resistant to conditions changes is key problem. In the resulting mathematical model of inverse problem additional input variables appears. Due to the difficulties in the mathematical description of inverse model neural networks have been applied. They do not require initial assumptions about the structure of the created model. They provide correction of sensor non-linearity as well as correction of influence of interfering quantity. The analyzed issue requires additional measurement of disturbing quantity and its connection with measurement of primary quantity. Combining this information with the use of neural networks belongs to the class of sensor fusion algorithm. |
