08. Sustainable & Renewable Energy

We have developed an air-cooled regenerative Organic Rankin Cycle (ORC) with the output of 1 kW. Air-cooled regenerative ORC has few restrictions on installation conditions and also consume low power. However, no previous research has discussed the performance of regenerative ORC that use air-cooled condensers based on machine learning. In this study, we developed a machine learning prediction model using actual measured values from a demonstration test of the ORC using hot spring as heat source in Obama Town, Unzen City as training data, and considered the effect of air temperature on the output characteristics of the ORC. The machine learning model was able to predict the output of the actual measured values and indicated that the output was affected by the mass flow rate. Moreover, we demonstrated that it is possible to predict the output of the ORC based on the measured air temperature data observed in the Obama Hot Spring.

5

Ms.

Corresponding author, Presenting author