Transcritical CO2 Heat Pump Research Articles

Characteristic analysis and performance optimization of a transcritical CO2 heat pump for high-temperature heating: An experimental study

Based on the improved experiment, a study on the characterization and optimization of transcritical CO2 heat pumps for high-temperature heating is conducted through the combined analysis perspective of thermal quality and heat capacity, as well as the proposed indicator. The result shows that: In the heat transfer process of the gas cooler, the thermal quality of CO2 is closely related to the variation of discharge pressure and compression ratio, and the temperature rise of water shows a corresponding three stages; An increase in the heating temperature (th) requires a higher level of thermal quality on the CO2 side, which exacerbates the heat capacity mismatch in the gas cooler; The elevated compressor speed (ncom) can effectively alleviate this mismatch, but an excessive ncom can instead cause a reduction in system COP; In the study, the COP of the system is improved by up to 26.12 % by optimizing the throttle opening benchmark, and it is further enhanced by up to 19.91 % through the synergistic control strategy optimization; Consequently, the optimized COP can be obtained 2.204 when the required th is 100 °C; Furthermore, the introduction of IHX significantly benefits the high-temperature heating performance of the system and the COP lifting studied ranges 3.70%–14.12 %.

Numerical investigation of high temperature heat pump integrated hybrid cooling system

Over 67 % of the energy demand within the pharmaceutical and semiconductor industries is for their cleanrooms, driven by stringent temperature and humidity control requirements. Despite high energy usage, heating, ventilation, and air-conditioning (HVAC) units consisting of conventional vapor compression systems (CVCS) are favoured for their simplicity. Hybrid cooling systems (HCS) offer potential efficiency gains by separating latent and sensible loads. Still, reliance on fossil-fuel-fired or electric heaters to regenerate the desiccant makes it energy intensive and reduces CO2 mitigation benefits. This study explores high-temperature heat pumps to simultaneously cool process air and heat regeneration air, thereby using multiple benefits. Heat pumps with condensing temperatures of 80 °C, 90 °C, and 120 °C and an ejector-enhanced trans-critical CO2 heat pump were compared with CVCS and HCS. The 120-bu and CO2HP configurations demonstrated a system COP of 2.94 and 3.22, respectively, surpassing CVCS, which has a system COP of 1.44. These setups achieved CO2 emission reduction of 51 % and 55.2 %, compared to CVCS, respectively.

A quasi-two-stage trans-critical CO2 heat pump with in-cycle thermal storage for performance enhancement

To decarbonise the heating sector, there is a strong demand for environmentally friendly and cost-effective heating technologies. Trans-critical CO2 heat pumps offer a sustainable alternative to traditional vapor compression cycles that rely on environmentally harmful synthetic refrigerants. However, a significant challenge within trans-critical CO2 heat pumps is their high throttling loss during expansion, leading to substantial flash gas production and subsequently higher recompression power consumption. In this paper, we apply our Flexible Heat Pump cycle concept to trans-critical CO2 heat pumps to address this issue. A thermal storage unit is introduced into a traditional trans-critical CO2 heat pump cycle to recover heat from the hot super-critical CO2 leaving the gas cooler during charging mode. Once it is fully charged, the stored heat is then used as a temporary heat source for the heat pump’s operation during the discharging mode. Since the recovered heat has a higher temperature than ambient. The resultant flexible trans-critical CO2 heat pump (FlexiCO2-HP) reduces throttling losses and the compressor’s power consumption, leading to a higher average COP (Coefficient of Performance). The obtained results of the FlexiCO2-HP are compared against a single-stage trans-critical CO2 heat pump. For gas cooler temperatures ranging from 35 °C to 60 °C and across various discharge pressures, its COP is potentially 10 % to 40 % higher than the standard cycle under ideal conditions. In addition, the proposed system demonstrates a lower optimal gas cooler pressure across different gas cooler temperatures. Furthermore, this study compares the FlexiCO2-HP with other trans-critical CO2 systems, including those with expansion work recovery and two-stage configurations. The results demonstrate that the FlexiCO2-HP offers improvements in COP for most conditions, though not all. It has the potential to achieve a comparable COP when compared with ejector-based and expander-based heat pumps or two-stage systems, but it is much simpler in design without introducing an extra expander or compressor.

Refrigerant charge estimation method based on data-physic hybrid-driven model for the fault diagnosis of transcritical CO2 heat pump system

The transcritical CO2 heat pump system is a promising and excellent heating scheme. However, the operating pressure of the transcritical CO2 heat pump system is high, and refrigerant leakage is a frequent problem. It is worth noting that the operating principle of CO2 heat pump systems is unique. Thus, conventional refrigerant charge estimation methods for subcritical systems cannot be directly applied to transcritical systems. In this study, a novel refrigerant charge estimation method for the transcritical CO2 heat pump system is proposed. Based on the heat and mass transfer characteristics of the transcritical system, the grey box model constrained by physical laws is constructed. Based on the machine learning algorithm, the correction model of the grey box model is built. The hybrid model combines the advantages of the high generalization ability of the physic-driven model and the nonlinear fitting ability of the data-driven model. The results show that the novel estimation method can accurately predict the refrigerant charge, enabling fault diagnosis of refrigerant leakage. The data-driven correction model can improve the prediction accuracy of the grey box model. The Mean Relative Error of the hybrid-driven model can be controlled within 5 %.

Structural analysis and optimization of flattened tube gas cooler for transcritical CO2 heat pump systems

The performance of gas cooler is acknowledged as a vital factor in CO2 heat pump systems. Consequently, its optimal design can significantly impact the overall efficiency, attributed to the pronounced changes in thermophysical properties of CO2 during pseudo-critical operating conditions. This research examines, for the first time, various configurations of flattened tubes (FTs) utilized as the conduit for CO2 flow within the gas cooler. It is established that changing the cross-sectional configuration represents an effective approach for enhancing the thermal performance of the gas cooler, resulting in a significant increase of up to 60 % in heat transfer coefficient. All FTs exhibit superior overall performance across most CO2 cooling conditions compared to circular tubes. Regarding the performance index, the overall improvement can be reached up to 31.8 % and 18.6 % under near-critical and trans-critical conditions, respectively. Furthermore, an optimization is conducted using BBD-RSM for a specific alternating FT due to its potential to enhance the thermal performance not only on the CO2 side but also on the cold side of the gas cooler. The analysis highlights the significant positive influence of the minimum axis on the thermal and hydraulic specifications of gas cooler, followed by the transition length.

Multi-factor coupling optimization of heat recovery effectiveness in a transcritical CO2 heat pump

In the background of energy shortage and climate change, transcritical CO2 heat pump(HTP) technology has attracted lots of attention because of its energy-saving and environmentally friendly advantages. In this research, an experimentally verified simulation model of transcritical CO2 HTP is established to investigate multi-factor coupling optimization of heat recovery effectiveness(ηIHX). First, the coupling optimization mechanism of ηIHX and discharge pressure(pdis) is analyzed. Moreover, this research explores the influence of ηIHX on heating capacity, power consumption, discharge temperature(tdis), and internal heat exchanger(IHX) cost, and further proposes a comprehensive heat recovery index to optimize the above factors. Based on this index the optimal heat recovery effectiveness(ηIHX,opt) for each operating condition is obtained. Also, a failure boundary for the coupling optimization of the ηIHX is also indicated. In addition, the optimal discharge pressure(pdis,opt) prediction correlation for different ηIHXs is proposed, which can be used for heat recovery effectiveness collaborative optimization control. Finally, a general method for evaluating IHX is provided. Taking Xi'an as an example, the optimal heat recovery area(AIHX,opt) of this HTP system is 0.42m2, with which the optimized HTP system operates safely at extreme operating conditions, resulting in an annual lucre of 1,211 CNY.

Experimental study on performance and compressor characteristics of transcritical CO2 heat pump system

The accelerated advancement of the economy has led to a heightened focus on the issue of energy conservation and reduced consumption within heat pump systems. An experimental investigation was conducted to analyze the impact of discharge pressure and outlet water temperature on the performance of the transcritical CO2 single-stage heat pump system and vapor injection heat pump system. The experimental results show that the heating capacity first increases and then tends to be constant or even slightly decreases with the increase of discharge pressure in single-stage heat pump system. When subjected to the same operating conditions, the coefficient of performance of vapor injection heat pump system exceeds that of single-stage heat pump system. Compared with single-stage heat pump system, the performance coefficient of vapor injection heat pump system has increased by an average of 6.21% and the heating capacity has increased by an average of 9.54%. Additionally, the volumetric efficiency of the compressor substantially decreases when producing high-temperature hot water. Semi-empirical models for evaluating the compressor performance in both single-stage heat pump system and vapor injection pump system are established through the parameterization of the volumetric efficiency with respect to the pressure ratio and compressor speed. These models effectively forecast compressor performance.

Performance analysis of transcritical CO2 and common medium low-temperature air energy heat pump

To comply with the development of the “dual-carbon” goal, a new refrigerant for heat pump products is necessary. Firstly, mathematical models of enhanced vapor injection air energy heat pump and transcritical CO2 heat pump systems were established, and they were calculated using thermodynamic methods. The results show that when CO2 is used as the refrigerant, the discharge temperature is 30% and 22.7%, which is higher than that of R410A and R134a, and 4.9% lower than that of R32. At the compressor outlet, the volume flow rate of CO2 is 59.0%, 60.8%, and 64.2% less than R410A, R32, and R134a, respectively. In terms of power consumption, the difference between CO2 and R410 A is within 6%. The power consumption of the CO2 system is 0% ∼ 6.4% higher than that of the R32 system and 29.2% ∼ 46.5% lower than that of the R134a system. The COP of the CO2 system is within 6% of that of the R410A and R32 systems, which is 41% ∼ 87% higher than that of the R134a system. When the ratio of CO2 / R32 is 0 ∼ 0.2 and 0.9, the COP of the mixed refrigerant is better than that of the single refrigerant CO2.

The comprehensive research on the transcritical CO2 thermal management system used in thermostatic transport vehicles

Natural fluid CO2 has become the preferred target of refrigerant alternative in the electrified transportation field in recent years to replace positive temperature coefficient (PTC) heaters, reduce energy consumption, and respect the international ban on Hydrofluorocarbons (HFCs) refrigerants. Thermostatic transport vehicles (TTVs) are well suited to exploit the benefits of CO2 due to their working conditions with a broad range of ambient temperatures, extensive transit distances, and substantial heating capacity requirements in cold climates. In this paper, a transcritical CO2 heat pump air-conditioning system used in TTV was constructed initially with proper control logic. Then following the assessment of the system’s steady-state performance, the dynamic operation process under high thermal inertia was thoroughly examined and analyzed in detail. Ultimately, the optimization of the dynamic response process was realized under varying heat flow boundary conditions. The primary results demonstrated that the rationally designed CO2 thermal management system performed admirably in various operating conditions, particularly in the heating mode where the coefficient of performance (COP) exceeded 3.2. Addressing the high-frequency fluctuation caused by the cargo thermal inertia, the temperature could be maintained with only two starts and stops within 3×105 seconds when the system control logic was refined. The optimized thermal management system of TTV efficiently allowed cargo to achieve the proper temperature as quickly as possible and sustain stability. This study provides an effective theoretical basis for the promotion of the transcritical CO2 thermal management system in the field of TTVs.

Numerical simulations and local entropy generation in a two-phase transcritical carbon dioxide Ranque-Hilsch vortex tube

The Ranque-Hilsch vortex tube arouses a renewed interest as a robust expansion device able to produce thermal energy separation. However, its two-phase transcritical CO2 operation remains unclear. In this work, 3D computational fluid dynamics simulations are performed using the open-source SU2 solver which key features are the implicit time integration and the real gas density-based formulation. The homogeneous equilibrium two-phase model is coupled with both the k−ω shear stress transport and the standard k−ϵ turbulence closures while a fast tabulated version of the Span and Wagner equation of state enables to compute the CO2 properties. First, the validation is performed on pressure measurements, condensation onset positions and visualizations in a transcritical CO2 nozzle available in the literature. Then, the vortex tube transcritical CO2 temperature, energy and phase separations are thoroughly investigated as well as the integral and local entropy generations due to viscous and heat dissipations. The results reveal that the temperature separation is produced below the inlet temperature at both outlets due to real gas effects. It is also shown that the energy separation is reversed as well as the available vortex tube outlet powers for heating and cooling purposes. Furthermore, higher irreversibility due to fluctuating components is unveiled near the vortex tube sharp angles at high cold mass fraction and high inlet operating pressure. Throughout this analysis, compelling arguments in favor of the friction theory for the energy separation phenomenon are also disclosed. Overall, the present work gives useful operation guidelines and sheds light on the complex phenomena at play in a Ranque-Hilsch vortex tube for transcritical CO2 heat pumps.

Comparison of different strategies for operating a solar-assisted ground-source CO2 heat pump system for space and water heating

This study quantifies and compares operational strategies as applied on a solar-assisted ground-source trans-critical CO2 heat pump (CO2 SAGSHP) system for simultaneous space and water heating, optimized on an hourly basis over the course of a week. Four (4) boundary conditions, representing spring, summer, autumn, and winter, were considered. To enable the use of a dynamic model for optimization simulations, the use of a previously developed surrogate Artificial Neural Network (ANN) model of a Modelica CO2 heat pump model was evaluated for use in this study. The simulation results from the system model that applies the surrogate ANN model demonstrated strong alignment with those generated by the full Modelica model, yielding low root mean square errors and mean absolute percentage errors. Furthermore, it accelerated the speed of results generation for a single forward run by 6–15 times, depending on the boundary conditions. It can be inferred from the results of the optimization runs that when warm climate conditions dominate, implementation of the on/off operation with thermal energy storage (TES) should be prioritized, given that it could potentially yield greater operational cost benefits (12% to 58 % cost reduction) compared to hourly discharge pressure optimization (0.5 to 1.5 % cost reduction). Conversely, when colder seasons are longer, optimizing the CO2 heat pump's discharge pressure becomes more practical (6.5 % to 6.9 % cost reduction) than on/off operation, particularly when only a small TES is installed (1.2 % to 2.6 % cost reduction). The optimization of the mass flow rate of the supply side working fluid of a CO2 SAGSHP system exhibited minimal benefit, except notably in the summer where it generated an even better cost reduction than controlling the discharge pressure. This shows the practicality of this strategy for conditions where relatively high solar irradiation and relatively low heat demand are concurrently expected. In general, weekly reductions in operational costs were more substantial when both the discharge pressure and the on/off operation of the CO2 heat pump were concurrently optimized, especially when using a larger TES tank. Hence, both should be applied if there are no practical or cost limitations that restrict their implementation. While previous studies on CO2 heat pumps primarily emphasized efficiency optimization via discharge pressure control, this study shows that comparable or greater operational cost reductions can also be achieved from other strategies, depending on the boundary conditions.

Optimal discharge pressure and performance characteristics of a transcritical CO2 heat pump system with a tri-partite gas cooler for combined space and water heating

The transcritical CO2 heat pump holds promise for achieving carbon neutrality in buildings, primarily due to its high energy efficiency in hot water heating. However, using it for space heating often leads to efficiency losses. A heat pump equipped with a tri-partite gas cooler can address this issue by providing both space heating and hot water while maintaining lower refrigerant temperatures at the gas cooler exit. Nonetheless, there is limited research on the characteristics of a CO2 heat pump system designed for simultaneous space and hot water production. This work fills this gap by analyzing the impacts of operational and system configuration, considering the variation of space heating to hot water production loads. A theoretical model is presented and verified with the experiments. Results show that under the specified conditions, the heat load ratio has minimal influence on the optimal discharge pressure. Increasing the water outlet temperature from 60 °C to 80 °C leads to a nearly 14% decrease in maximum COP, with a corresponding 12.2% increase in the optimal pressure. A 10 K rise in water inlet temperature results in approximately a 21% decline in maximum COP. Evaporation temperature has little impact on the optimal discharge pressure, while maximum COP increases by roughly 63% with a rise in evaporation temperature from -10 °C to 10 °C. Space heating water temperature notably affects the optimal discharge pressure. Integration of an IHX enhances system COP but has marginal impact on the optimal discharge pressure. These findings offer insights for designing and optimizing transcritical CO2 heat pumps for simultaneous space and water heating applications.

Application of transcritical CO2 heat pumps to boiler replacement in low impact refurbishment projects

80% of current UK housing stock is expected to still be in use in 2050. Difficult, intrusive and expensive, refurbishment measures are required to achieve the level of insulation required for current low temperature heat pumps. Transcritical CO2 heat pumps can achieve higher efficiencies, with higher output temperatures, than current, Carnot limited, synthetic gas heat pumps, with less environmental impact. Widely deployed in water heating and supermarket chilling systems, CO2 heat pumps need heating return temperatures of 30 °C or less to function effectively. This has impeded their adoption with hydronic heating systems which have high return temperatures.This study identified system modifications external to the refrigeration cycle that address return temperatures. It modelled a transcritical CO2 air source heat pump with a hydronic heating system in a solid wall semi-detached house. Full year system coefficients of performance over 3 were achieved in four UK locations by using space heating return fluids to defrost the air source heat exchanger and to pre-heat inlet water, recovering any remaining excess return fluid heat as a source for the heat pump. Solar panels boosted this to 5.1. The levelized cost of energy for the system was calculated (with heat pump grant) at 22p/kWh, lower than a gas boiler, with 9.45 tonnes CO2 emission savings over a fifteen-year life.

Energy, exergy, and exergoeconomic analyses of an air source transcritical CO2 heat pump for simultaneous domestic hot water and space heating

The transcritical CO2 heat pump system experiences significant throttling losses in space heating operation due to the higher temperature of returning water. This paper presents an energy, exergy, and exergoeconomic analyses of an air source transcritical CO2 heat pump integrating a tri-partite gas cooler, which is an effective method to match CO2 temperature glide with water for simultaneous domestic hot water and space heating (DHW+SH) production. A pinch point-based numerical model is developed to find the optimal discharge pressure. This validated model is then utilized to investigate the impacts of water inlet temperature and ambient temperature. Two configurations are examined: one with only DHW supply and the other with DHW+SH supply. The results indicate that combining SH with DHW enhances COP by 7.5% with a 7.9% reduction in discharge pressure at 10 °C ambient temperature and 10 °C water inlet temperature. At a water temperature of 10 °C, exergy efficiency improves by 4%. The compressor accounts for 54%–60% of the total exergy loss. The DHW+SH system exhibits an average exergy destruction reduction of 7.6%. With each 5 °C rise in ambient temperature, the DHW+SH system’s total exergy destruction cost rate decreases on average 7.7% compared to the DHW system. Furthermore, the combined exergy destruction cost rate of GC2 and GC3 in DHW+SH is significantly lower (by 48.2%) than only GC3 in DHW. The exergoeconomic factors of the compressor, gas cooler 2, and gas cooler 3 emphasize the need to decrease their costs to enhance cost-effectiveness.

Experimental verification of the novel transcritical CO2 heat pump system and model evaluation method

This work proposes a novel method for verifying the accuracy of the numerical simulation model of the compression/ejector transcritical CO2 heat pump system using convolutional neural networks. The method focuses on converting the original unequal input conditions into equal input conditions and comparing the simulation results with the experimental prediction results of each component. The validation results reveal the following findings: 1) The root mean square errors of the gas cooler and the water source evaporator are 9.16 °C and 11.47 °C respectively, indicating that future work should focus on correcting of the CO2 heat transfer coefficient calculation method; 2) The verification results of the evaporator indicate that suggesting the need to incorporate an air dynamic change module in the air source input; 3) The root mean square error of the CO2 outlet pressure in the ejector is 462.45 kPa. It can be inferred from the pressure variation trend that the limit pressure ratio of the compressor is the main factor affecting the accuracy of the ejector model. Overall, this article presents a novel and effective method for verifying the accuracy of numerical models.

Research progress and applications of transcritical carbon dioxide heat pumps: A review

Heat pump technology is an energy-saving technology that can efficiently utilize low-grade energy. It has broad application prospects in building heating, industrial waste heat utilization, new energy and other fields. However, the refrigerants used in traditional heat pump systems have serious negative impacts on the environment, and there is an urgent need to find a safe, environmentally friendly, and efficient alternative refrigerant. As a natural refrigerant, CO2 has good physical and chemical properties and is very suitable as a working fluid in transcritical cycles, showing great advantages in the field of heat pump technology. At present, research on CO2 heat pumps has made certain progress, but there are few reviews of the research status and development trends of CO2 heat pumps in different applications. Therefore, this article systematically summarizes the latest research results of transcritical CO2 heat pumps in different application fields, pointing out the difficulties such as high pressure and low operating efficiency in system design and operation. It also summarizes the latest optimization research on system components, cycle structure, mixed refrigerants and control strategies. The results show that each optimization method can significantly improve system performance, among which mixed refrigerant is the simplest optimization method. Finally, the outlook for CO2 heat pump technology is put forward. With policy support and technological advancement, more comprehensive, energy-saving, and intelligent CO2 heat pump technology will continue to develop and innovate.

Energy and economic analysis of a sub-cooler based vapor injection transcritical CO2 heat pump for space heating

The Chinese government has considered the transcritical CO2 heat pump (TCHP) as a promising solution for space heating with the goal of “carbon peaking” and “carbon neutrality.” Considering the convenient implementation and the performance improvement, the vapor injection technique should be taken into consideration. This paper presents the experimental and simulation investigation of the SCVI TCHP prototype with energetic and economic analysis. Under the design condition, the SCVI technique could improve the peak COP by 5.02 % with a 10.11 % improvement in heating capacity. Compared to the direct electric heater solution, the annual operation cost was reduced by 11966CNY, 29.03 % higher than the Base TCHP. The payback period was decreased from 8 to 6.9 years due to the application of vapor injection. The effect of ambient temperature on the system performances was evaluated based on the experimental data. As the simulation progressed, a control strategy optimizing both the discharge and the medium pressure was developed, and the influence of inlet and outlet water temperature was studied.

Real-time multi-variable optimization of the interstage subcooling vapor-injection based transcritical CO2 HPWH: An integrated model predictive control approach

The interstage subcooling vapor-injection technique has been introduced to transcritical CO2 heat pumps to alleviate performance degradation under conditions of low ambient temperature and high water-outlet temperature. This type of solution holds considerable appeal and finds utility across a wide range of applications. However, the efficacy and efficiency of such systems are contingent upon their management, which frequently requires the implementation of suitable control systems. The primary objective is to enhance the overall system operational performance, resulting in tangible advantages in terms of economic viability, energy conservation, and environmental sustainability. To achieve these objectives, one can utilize both explicit and implicit optimization methods ranging from Model Predictive Control (MPC) to Extremum Seeking Control (ESC), each with its strengths and weaknesses. This paper compares the performance of an ad hoc integrated MPC strategy and a multi-variable ESC one. Based on the results of the system operation employing the latter strategy, a significant linear correlation was discovered between the optimal medium pressure and the optimal discharge and suction pressure. Consequently, an intrinsic self-optimization strategy for the medium pressure was developed. Subsequently, a dynamic system identification was performed on the new system, incorporating this proposed strategy. To optimize the system Coefficient of Performance (COP) while maintaining the water outlet temperature, ensuring the thermal load constraint, the MPC strategy was employed. The main focus of the MPC was to determine the optimal Electronic Expansion Valve (EEV) opening degree and water pump settings. The integrated MPC strategy was evaluated and compared to the multi-variable ESC strategy under various conditions, including fixed design conditions, changing ambient conditions, and step-change water outlet temperature. The results clearly demonstrated the effectiveness and superiority of the integrated MPC.

Performance evaluation of transcritical CO2 desiccant heat pumps for electric vehicles

Transcritical CO2 heat pump systems are eco-friendly and have excellent heating performance, which makes them suitable for electric vehicles. The recirculation mode can save energy but requires a dehumidification function to ensure driving safety. Therefore, this paper proposes a transcritical CO2 desiccant heat pump, which differs from the typical transcritical CO2 heat pump system by incorporating an indoor evaporator and a full-pass throttle valve. The flow area of the full-pass throttle valve can be adjusted to obtain the appropriate dehumidification rate. In addition, this study suggested using the desiccant heat pump coefficient of performance (DHCOP) to evaluate the overall energy efficiency of the heat pump system. We have investigated the dehumidification rate and optimal discharge pressure under different operating conditions. The results show that even under the harsh operating conditions at -10 °C, the HDCOP of the transcritical CO2 desiccant heat pump can still exceed 2.1, and reach 3.12 at a moderate condition of Ta=5 °C. The transcritical CO2 heat pump desiccant system demonstrates significant energy-saving potential.

Development of a surrogate model of a trans-critical CO2 heat pump for use in operations optimization using an artificial neural network

Conventional physics-based models can demand substantial computational resources when employed for operational optimization. To allow faster system simulations that can be employed for operational optimization, a surrogate model of the CO2 heat pump has been developed using an artificial neural network (ANN). The ANN model takes in six (6) inputs: evaporator water-side mass flow, its temperature, gas cooler water-side mass flow, its temperature, set-point output temperature, and high-side heat pump pressure. The model’s outputs comprise the electrical energy needed to run the heat pump, the heat from the gas coolers, the temperature of the heat pump-heated fluid, and the outlet temperature of the heat pump’s evaporator. Data used for training, validating, and testing the ANN model were generated by running a calibrated Modelica model of the CO2 heat pump for various combinations of input parameters obtained from Latin hypercube sampling. The ANN model developed includes an input layer with 6 inputs, 2 hidden dense layers, each with 30 neurons, and an output layer for 4 outputs (6-30-30-3). The ReLU activation function was implemented on each hidden layer and no regularizations were imposed. The Adam optimizer was used with a learning rate of 0.001 specified. Early stopping (patience = 2000) was implemented to ensure that the training data was not overfitted. A maximum of 30000 epochs was specified. The resulting Mean Square Error (MSE) obtained for the training, validation, and testing data sets were 1.38x10−5, 2.05x10−5, and 3.65x10−5, respectively. When tested against one-week operational runs generated by Modelica, the Root Mean Square Errors (RMSEs) for coefficient of performance (COP)s for spring, summer, autumn, and winter operations obtained were 0.232, 0.346, 0.089 and 0.076, respectively. The resulting surrogate ANN model can be integrated into the system model as a functional mock-up unit within Modelica to facilitate faster simulations for operational optimization.