PREDICTION OF SKIN TEMPERATURE IN DIFFERENT THERMAL CONDITIONS USING ARTIFICIAL NEURAL NETWORK


Yuce B. E.

HEAT TRANSFER RESEARCH, cilt.54, sa.10, ss.1-17, 2023 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 54 Sayı: 10
  • Basım Tarihi: 2023
  • Doi Numarası: 10.1615/heattransres.2023046395
  • Dergi Adı: HEAT TRANSFER RESEARCH
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Aerospace Database, Communication Abstracts, Compendex, INSPEC, Metadex, Civil Engineering Abstracts
  • Sayfa Sayıları: ss.1-17
  • Bursa Uludağ Üniversitesi Adresli: Hayır

Özet

Ensuring the thermal satisfaction of people with their environment increases both the quality of life and productivity. In addition, providing the thermal conditions is important to keep energy consumption at an optimum level. Skin temperature is one of the most appropriate parameters to understand the thermal relationship of the human body with the environment. In this study, the transient temperatures of 16 body segments under different thermal conditions were predicted by the artificial neural networks (ANN) method. In the thermal sensitivity model, the temperatures of body parts at different ambient temperatures, relative humidity (RH), and metabolic rates were determined and used as a database in the teaching process in the artificial neural network model. The results obtained from the ANN model were compared with the results of the thermal sensitivity model, and then the results were found to be quite compatible with each other. Following the validation study, the body temperature was calculated at 20 degrees C, 25 degrees C, and 30 degrees C ambient temperature. The effect of metabolic rates under reclining, relaxed, sedentary, and light activity conditions on skin temperature was also investigated. Relative humidity was examined at 50%, 40%, 30%, and 20% values together with other thermal parameters. It is observed that there is a good agreement between the ANN model predictions and the complex simulation model.