Machine learning-based efficient multi-layered precooler design approach for supercritical CO2 cycle

Abstract In the current study, a multi-layered approach, combining 3D Reynolds Averaged Navier–Stokes (RANS) model, Artificial Neural Network (ANN), and in-house precooler design and analysis code (PDAC), is developed to investigate the influence of various parameters on the design of the precooler used in sCO2 cycle. The validated 3D-RANS model is utilized to compute thermal and hydraulic characteristics of a zigzag channeled PCHEs operating under the precooler's conditions. The generated CFD data is used to develop empirical correlations and train a machine learning (ML) model based on Artificial Neural Network (ANN). Finally, both trained ML model and empirical correlation are utilized in the PDAC to design and analyze the precooler under different design conditions. Regression data for the precooler, operating in the pseudocritical zone, show that the prediction accuracy of the developed Nusselt number and pressure drop correlation is relatively poor. At the same time, the trained Artificial Neural Network (ANN) can estimate 99% of the data with 90% confidence in the same operating regime. Further, precooler design and analysis code (PDAC) based on the trained ML model can accurately mimic the CFD prediction at a significantly reduced computational time. It is found that pressure losses on the s C O 2 -side and water pumping power are exceptionally sensitive to desired exit temperature and channel flow rate. Exit temperature lower than the pseudo critical temperature and higher channel flow rate result in pinch point location well inside the precooler, resulting in a massive rise in the heat exchanger’s size and pressure losses. The pinch point can be avoided by choosing the channel mass flow rate ratio of the hot and cold-sides fluid comparable with their ratio of specific heat capacities corresponding to pseudocritical temperature.

[1]  Nikolaos V. Sahinidis,et al.  A Machine Learning Approach to Correlation Development Applied to Fin-Tube Bundle Heat Exchangers , 2018, Energies.

[2]  Non-linear stability analysis of supercritical carbon dioxide flow in inclined heated channel , 2019, Progress in Nuclear Energy.

[3]  A. Berrouk,et al.  Numerical investigation of thermal and hydraulic characteristics of sCO2-water printed circuit heat exchangers with zigzag channels , 2020 .

[4]  Wei Tian,et al.  Thermal performance of a novel ultrasonic evaporator based on machine learning algorithms , 2019, Applied Thermal Engineering.

[5]  M. Singh,et al.  Development of a novel nodalized reduced order model for stability analysis of supercritical fluid in a heated channel , 2019, International Journal of Thermal Sciences.

[6]  R. Kumar,et al.  Numerical heat transfer analysis & predicting thermal performance of fins for a novel heat exchanger using machine learning , 2020 .

[7]  Application of an Artificial Neural Network (ANN) for predicting low-GWP refrigerant boiling heat transfer inside Brazed Plate Heat Exchangers (BPHE) , 2020 .

[8]  Lei Sun,et al.  Off-Design Performance Prediction of a S-CO2 Turbine Based on Field Reconstruction Using Deep-Learning Approach , 2020 .

[9]  Jiangfeng Guo,et al.  Experimental investigation of thermal-hydraulic characteristics of a printed circuit heat exchanger used as a pre-cooler for the supercritical CO2 Brayton cycle , 2020 .

[10]  J. Moore,et al.  DEVELOPMENT OF HIGH EFFICIENCY HOT GAS TURBO-EXPANDER FOR OPTIMIZED CSP SUPERCRITICAL CO2 POWER BLOCK OPERATION , 2014 .

[11]  A. Berrouk,et al.  CFD aided design and analysis of a precooler with zigzag channels for supercritical CO2 power cycle , 2021 .

[12]  Non-linear analysis of the Density-Wave Oscillations and Ledinegg Instability in heated channel at supercritical condition , 2021 .

[13]  Guangya Zhu,et al.  Machine learning based approach for the prediction of flow boiling/condensation heat transfer performance in mini channels with serrated fins , 2021 .

[14]  Jeong-Ik Lee,et al.  Study of various Brayton cycle designs for small modular sodium-cooled fast reactor , 2014 .

[15]  Man-Hoe Kim,et al.  Design optimization and performance analysis of a supercritical carbon dioxide recompression Brayton cycle based on the detailed models of the cycle components , 2019, Energy Conversion and Management.

[16]  M. Saeed,et al.  Performance of Supercritical CO2 Power Cycle and Its Turbomachinery with the Printed Circuit Heat Exchanger with Straight and Zigzag Channels , 2020, Energies.

[17]  Robert K. Salko,et al.  On the prediction of critical heat flux using a physics-informed machine learning-aided framework , 2019, Applied Thermal Engineering.

[18]  Man-Hoe Kim,et al.  Performance Analysis of the Supercritical Carbon Dioxide Re-compression Brayton Cycle , 2020, Applied Sciences.

[19]  Man-Hoe Kim,et al.  Thermal and hydraulic performance of SCO2 PCHE with different fin configurations , 2017 .

[20]  M. Givoni,et al.  Piling up or Packaging Policies? An Ex-Post Analysis of Modal Shift in Four Cities , 2018, Energies.

[21]  Abdallah S. Berrouk,et al.  Experimental measurements and large eddy simulation of expiratory droplet dispersion in a mechanically ventilated enclosure with thermal effects , 2009, Building and Environment.

[22]  M. Anderson,et al.  Development of a new forced convection heat transfer correlation for CO2 in both heating and cooling modes at supercritical pressures , 2011 .

[23]  Man-Hoe Kim,et al.  Aerodynamic performance analysis of an airborne wind turbine system with NREL Phase IV rotor , 2017 .

[24]  Abdallah S. Berrouk,et al.  Numerical simulation of a commercial FCC regenerator using Multiphase Particle-in-Cell methodology (MP-PIC) , 2017 .

[25]  Chaohe Yang,et al.  Equivalent Reactor Network Model for Simulating the Air Gasification of Polyethylene in a Conical Spouted Bed Gasifier , 2014 .

[26]  Marco Astolfi,et al.  Preliminary assessment of sCO2 cycles for power generation in CSP solar tower plants , 2017 .

[27]  Srinivasa M. Salapaka,et al.  Fouling modeling and prediction approach for heat exchangers using deep learning , 2020 .

[28]  M. Shafii,et al.  A comparative study of various machine learning methods for performance prediction of an evaporative condenser , 2021, International Journal of Refrigeration.

[29]  Jeong Ik Lee,et al.  Prediction of inner pinch for supercritical CO 2 heat exchanger using Artificial Neural Network and evaluation of its impact on cycle design , 2018 .

[30]  Yasuyoshi Kato,et al.  Thermal-Hydraulic Characteristics of a Printed Circuit Heat Exchanger in a Supercritical CO2 loop , 2005 .

[31]  A. Berrouk,et al.  Numerical investigation of the thermohydraulic characteristics of microchannel heat sinks using supercritical CO2 as a coolant , 2021 .

[32]  A. Berrouk,et al.  Effect of printed circuit heat exchanger’s different designs on the performance of supercritical carbon dioxide Brayton cycle , 2020 .

[33]  Man-Hoe Kim,et al.  Thermal-hydraulic analysis of sinusoidal fin-based printed circuit heat exchangers for supercritical CO2 Brayton cycle , 2019, Energy Conversion and Management.

[34]  Jonghark Park,et al.  EXPERIMENTAL INVESTIGATION OF CONVECTIVE HEAT TRANSFER IN A NARROW RECTANGULAR CHANNEL FOR UPWARD AND DOWNWARD FLOWS , 2014 .

[35]  Marcus Liwicki,et al.  Machine Learning Computational Fluid Dynamics , 2021, 2021 Swedish Artificial Intelligence Society Workshop (SAIS).

[36]  Ammar H. Elsheikh,et al.  Machine learning algorithms for improving the prediction of air injection effect on the thermohydraulic performance of shell and tube heat exchanger , 2021 .

[37]  Tae Ho Kim,et al.  Experimental study of a straight channel printed circuit heat exchanger on supercritical CO2 near the critical point with water cooling , 2020 .

[38]  Yue Wang,et al.  Review on the characteristics of flow and heat transfer in printed circuit heat exchangers , 2019, Applied Thermal Engineering.

[39]  Yoon-Ho Kim,et al.  Heat Transfer and Pressure Drop Characteristics in Straight Microchannel of Printed Circuit Heat Exchangers , 2015, Entropy.

[40]  Abdallah S. Berrouk,et al.  Enforcing mass conservation in DPM-CFD models of dense particulate flows , 2011 .

[41]  Seungjoon Baik,et al.  Study on CO2 – water printed circuit heat exchanger performance operating under various CO₂ phases for S-CO₂ power cycle application , 2017 .

[42]  David Sánchez,et al.  Supercritical carbon dioxide cycles for power generation: A review , 2017 .

[43]  Man-Hoe Kim,et al.  Airborne wind turbine shell behavior prediction under various wind conditions using strongly coupled fluid structure interaction formulation , 2016 .

[44]  Jeong-Ik Lee,et al.  CFD aided approach to design printed circuit heat exchangers for supercritical CO2 Brayton cycle application , 2016 .

[45]  O. İpek,et al.  Prediction of the parameters affecting the performance of compact heat exchangers with an innovative design using machine learning techniques , 2021, Journal of Intelligent Manufacturing.

[46]  Chaohe Yang,et al.  Impact of the drag law formulation on the predicted binary-particle segregation patterns in a gas–solid fluidized bed , 2012 .

[47]  Ting Ma,et al.  Experimental investigation on SCO2-water heat transfer characteristics in a printed circuit heat exchanger with straight channels , 2017 .