Performance evaluation and multi-objective optimization of a low-temperature CO2 heat pump water heater based on artificial neural network and new economic analysis

Abstract

For the advantages of high efficiency and low impact to the environment, CO2 air source heat pump water heater (ASHPWH) is applied to produce domestic water, which also reveals good potential in cold regions. In order to boost the system performance and practicability under low ambient temperature, optimization for CO2 ASHPWH is conducted using non-dominated sorting genetic algorithm (NSGA-II). A validated artificial neural network (ANN) predicts energy parameters for the optimization. And an economic model provides economic and environmental parameters, which considers the influence of housing price, tank volume, and on/off-peak electricity price, rarely taken into account in published studies. Then the optimizing progress is conducted under −20 °C ambient temperature and 9–65 °C water temperature, in which four optimized variables are selected: gas cooler outlet temperature (Tgc), heat rejection pressure (Pgc), compressor displacement (qvh) and water tank volume (Vwt). The final solution of Tgc = 15 °C, Pgc = 8294.1 kPa, Vwt = 0.3647 m3, qvh = 401.33 mL/s results in two objectives (CO2 emission and total annual cost) of 8599.4 kg and 1626.9 $/year, revealing advantages both in energy and economy. It is noteworthy that the cost of the space occupied by system is the fourth important factor in capital cost. These results lay solid foundation for further studies and system application.