This study presents energy-saving performance analysis of a recirculating aquaculture system (RAS) that uses seawater-source heat pumps to control the seawater temperature in the breeding tank. The analysis is based on artificial neural network (ANN) and TRNSYS-based digital twin simulations. The complex thermal load of the RAS, which fluctuates in real time due to changing environmental conditions, is simulated using the dynamic simulation software, TRNSYS. A fuzzy logic controller (FLC) was designed based on the dynamic heat load calculated by TRNSYS and the water temperature data of the breeding tank enabling capacity control of the inverter manipulator of the heat pump. At this stage, energy is saved through the control of the variable speed compressor responding to the partial load via the inverter. Power consumption was predicted at appropriate time intervals using a custom-built ANN model. The prediction results are used to determine the optimal number of heat pumps to operate. Through the digital twin simulation, the proposed heat pump capacity control is compared with conventional operating number control in terms of temperature regulation performance and power consumption. The results demonstrated that the proposed method can be easily implemented in Matlab and significantly improves energy efficiency in RAS farms.

서 론
재료 및 방법
    연구 방법
    RAS 양식장 모델과 TRNSYS에 의한 동적 열부하 분석 모델
    FLC에 의한 용량제어 및 대수제어 로직
    TRNSYS 모델 기반 Digital Twin Simulation (DTS)
    전력 소비량 예측을 위한 ANN 모델
결과 및 고찰
    용량제어와 대수제어의 수온 제어 성능
결 론
사 사
References

• 남현서(국립부경대학교 대학원 냉동공조공학과 대학원생) | Hyun-Seo NAM (Student, Graduate School of Refrigeration and Air-conditioning Engineering, Pukyong National University, Busan 48513, Korea)
• 정석권(국립부경대학교 냉동공조공학과 교수) | Seok-Kwon JEONG (Professor, Department of Refrigeration and Air-conditioning Engineering, Pukyong National University, Busan 48513, Korea) Corresponding author