This study deals with the application of an artificial neural network (ANN) model to predict power consumption for utilizing seawater source heat pumps of recirculating aquaculture system. An integrated dynamic simulation model was constructed using the TRNSYS program to obtain input and output data for the ANN model to predict the power consumption of the recirculating aquaculture system with a heat pump system. Data obtained from the TRNSYS program were analyzed using linear regression, and converted into optimal data necessary for the ANN model through normalization. To optimize the ANN-based power consumption prediction model, the hyper parameters of ANN were determined using the Bayesian optimization. ANN simulation results showed that ANN models with optimized hyper parameters exhibited acceptably high predictive accuracy conforming to ASHRAE standards.

We analyzed the performance of hubless rim propellers based on the number of blades, maintaining a fixed pitch ratio and expanded area ratio, using computational fluid dynamics (CFD). Thrust coefficient, torque coefficient and efficiency according to the number of blades were analyzed. In addition, the pressure distribution on the discharge and suction sides of the blade was analyzed. As the advance ratio increases, the thrust coefficient decreases. The highest thrust was shown when the advance ratio was lowest. For the three, four, five and six-blades, the torque coefficient tended to decrease as the advance ratio increased. In the case of seven and eight-blades, the torque coefficient tended to increase as the advance ratio increased. The maximum efficiency was found when the advance ratio was 0.8. When the three-blade, it showed high efficiency at all advance ratios. A high pressure distribution was observed at the leading edge of the discharge blade, and a low pressure distribution was observed at the trailing edge. Applying a hubless rim-driven thruster with the three-blade can generate higher thrust and increase work efficiency.