Machine learning prediction of ORC performance based on properties of working fluid

Abstract In order to develop machine learning methods for performance prediction of basic ORC (BORC) and regenerative ORC (RORC), thermodynamic properties of working fluids are used to separately model thermodynamic processes including compression, expansion, evaporation and regeneration by artificial neural network (ANN), based on REFPROP calculation data of 106 working fluids. These properties include critical temperature, critical pressure, acentric factor and ideal gas heat capacity. Other cycle performances can be derived from the predictions of established ANNs. Furthermore, for RORC, considering that dry or isentropic working fluid is usually preferred, vapor slope of temperature-entropy saturation curve is modeled by ANN to determine the working fluid behavior. Meanwhile, for ensuring occurrence of heat exchange in regenerator, temperature difference between outlets of turbine and pump is modeled to judge whether temperature difference is larger than the assumed pinch point temperature difference. Based on the obtained predictions for BORC, average absolute deviations (AADs) of net work and thermal efficiency are 1.3928% and 1.5461%, respectively. As for RORC, AADs of vapor slope, temperature difference, net work and thermal efficiency are 2.3659%, 1.2020% 1.8277% and 2.1047%, respectively. Based on the above models, cycle performances of BORC and RORC can be accurately predicted from thermodynamic properties of any working fluid.

[1]  Heejin Cho,et al.  Performance Prediction and Optimization of an Organic Rankine Cycle Using Back Propagation Neural Network for Diesel Engine Waste Heat Recovery , 2019, Journal of Energy Resources Technology.

[2]  S. Deng,et al.  How to predict the vapor slope of temperature-entropy saturation boundary of working fluids from molecular groups? , 2017 .

[3]  John P. Eason,et al.  Process optimization and working fluid mixture design for organic Rankine cycles (ORCs) recovering compression heat in oxy-combustion power plants , 2018, Energy Conversion and Management.

[4]  F. Boyaghchi,et al.  Multi-generation system incorporated with PEM electrolyzer and dual ORC based on biomass gasification waste heat recovery: Exergetic, economic and environmental impact optimizations , 2018 .

[5]  Lourdes García-Rodríguez,et al.  Preliminary design of seawater and brackish water reverse osmosis desalination systems driven by low-temperature solar organic Rankine cycles (ORC). , 2010 .

[6]  K. Thu,et al.  A hybrid power cycle using an inverted Brayton cycle with an indirect evaporative device for waste-heat recovery , 2020 .

[7]  Heejin Cho,et al.  Artificial neural network (ANN) based prediction and optimization of an organic Rankine cycle (ORC) for diesel engine waste heat recovery , 2018 .

[8]  Wei Wang,et al.  Application of machine learning into organic Rankine cycle for prediction and optimization of thermal and exergy efficiency , 2020 .

[9]  Christos N. Markides,et al.  Industrial waste-heat recovery through integrated computer-aided working-fluid and ORC system optimisation using SAFT-Γ Mie , 2017 .

[10]  C. H. F. Silva,et al.  Assessment of a Kalina cycle for waste heat recovery in the cement industry , 2019, Applied Thermal Engineering.

[11]  Shuai Deng,et al.  A neural network for predicting normal boiling point of pure refrigerants using molecular groups and a topological index , 2016 .

[12]  Jian Zhang,et al.  Prediction and optimization of power output of single screw expander in organic Rankine cycle (ORC) for diesel engine waste heat recovery , 2021 .

[13]  Xiaowei Zhao,et al.  An artificial intelligence approach for thermodynamic modeling of geothermal based-organic Rankine cycle equipped with solar system , 2019, Geothermics.

[14]  T. Serova,et al.  Analysis of the Properties of Working Substances for the Organic Rankine Cycle based Database “REFPROP” , 2016 .

[15]  S. Deng,et al.  New knowledge on the temperature-entropy saturation boundary slope of working fluids , 2017 .

[16]  Qian Wang,et al.  Performance prediction and optimization of an organic Rankine cycle (ORC) for waste heat recovery using back propagation neural network , 2020, Energy Conversion and Management.

[17]  Xinxin Zhang,et al.  Evaluation and selection of dry and isentropic working fluids based on their pump performance in small-scale organic Rankine cycle , 2021 .

[18]  Ruzhu Wang,et al.  Simulation and experiments on an ORC system with different scroll expanders based on energy and exergy analysis , 2015 .

[19]  Shuai Deng,et al.  Developing a performance evaluation model of Organic Rankine Cycle for working fluids based on the group contribution method , 2017 .

[20]  Yufeng Zhang,et al.  Investigation of Support Vector Machine and Back Propagation Artificial Neural Network for performance prediction of the organic Rankine cycle system , 2018 .

[21]  Riccardo Brignoli,et al.  Methodology for estimating thermodynamic parameters and performance of working fluids for organic Rankine cycles , 2014 .

[22]  Li Zhao,et al.  How to evaluate the performance of sub-critical Organic Rankine Cycle from key properties of working fluids by group contribution methods? , 2020 .

[23]  L. Nord,et al.  Fluid selection and thermodynamic optimization of organic Rankine cycles for waste heat recovery applications , 2017 .

[24]  Chi-Chuan Wang,et al.  Effect of working fluids on organic Rankine cycle for waste heat recovery , 2004 .

[25]  A. Abusoglu,et al.  Thermoeconomic multi-objective optimization of an organic Rankine cycle (ORC) adapted to an existing solid waste power plant , 2018, Energy Conversion and Management.

[26]  R. Ranasinghe,et al.  Working fluid selection of Organic Rankine Cycles , 2020 .

[27]  Burak Atakan,et al.  Reverse engineering of fluid selection for thermodynamic cycles with cubic equations of state, using a compression heat pump as example , 2015 .

[28]  Kwang Ho Lee,et al.  Application of artificial neural networks for optimized AHU discharge air temperature set-point and minimized cooling energy in VAV system , 2019, Applied Thermal Engineering.

[29]  Shuai Deng,et al.  Towards novel low temperature thermodynamic cycle: A critical review originated from organic Rankine cycle , 2020 .

[30]  Apostolos Pesyridis,et al.  Machine Learning for the prediction of the dynamic behavior of a small scale ORC system , 2019, Energy.

[31]  Tzu-Chen Hung,et al.  A study of organic working fluids on system efficiency of an ORC using low-grade energy sources , 2010 .

[32]  Masoud Ebrahimi,et al.  Experimental investigation, modeling and prediction of transition from uniform discharge to filamentary discharge in DBD plasma actuators using artificial neural network , 2018 .

[33]  Zhi Yang,et al.  Improved correlations for working fluid properties prediction and their application in performance evaluation of sub-critical Organic Rankine Cycle , 2019, Energy.

[34]  Michele Pinelli,et al.  Development of a Model for the Simulation of Organic Rankine Cycles Based on Group Contribution Techniques , 2011 .

[35]  L. Chen,et al.  Performance analysis and optimization of engine waste heat recovery with an improved transcritical-subcritical parallel organic Rankine cycle based on zeotropic mixtures , 2020 .

[36]  Zhen Yang,et al.  Thermo-economic optimization of the hybrid geothermal-solar power system: A data-driven method based on lifetime off-design operation , 2021 .

[37]  S. Jayasekara,et al.  Working Fluid Selection and Performance Evaluation of ORC , 2019, Energy Procedia.

[38]  Xu Ping,et al.  Introducing machine learning and hybrid algorithm for prediction and optimization of multistage centrifugal pump in an ORC system , 2021 .

[39]  G. Najafi,et al.  A review of industrial waste heat recovery system for power generation with Organic Rankine Cycle: Recent challenges and future outlook , 2020 .