RECONSTRUCTING TEMPERATURE FIELD AND RADIATIVE PROPERTIES INSIDE BOILER FURNACE THROUGH DEEP LEARNING
11th International Symposium on Radiative Transfer, RAD25, Aydın, Türkiye, 16 - 20 Haziran 2025, cilt.1, ss.1-8, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Cilt numarası: 1
- Basıldığı Şehir: Aydın
- Basıldığı Ülke: Türkiye
- Sayfa Sayıları: ss.1-8
- Gazi Üniversitesi Adresli: Evet
Özet
Detecting the temperature field and radiative
properties inside a boiler furnace is crucial for studying the radiative heat
transfer process in the furnace. This study proposes a deep learning- based
method to reconstruct the temperature field and radiative properties
simultaneously. By specifying temperature fields and different combinations of
radiative properties, a data set with the direct problem of the radiative
imaging model is generated. The results show that the multi-task regression
model can accurately and quickly reconstruct both the temperature field and the
radiative properties and has good stability under different noise conditions.
This indicates that the proposed method has promising potential for the
construction of combustion medium of smart power plants.