The multivariable inverse artificial neural network combined with GA and PSO to improve the performance of solar parabolic trough collector

Abstract This work focused on presenting a multivariate inverse artificial neural network (ANNim) by developing two functions coupled to metaheuristic algorithms to increase a parabolic trough collector (PTC). This work aims to provide a new method capable of improving the thermal efficiency of a PTC by determining multiple optimal input variables. At first, two ANN models carried out to predict the PTC thermal efficiency ( η t ), validated, and compared in detail. For that, six input parameters rim-angle ( φ r ), inlet-temperature ( T in ), ambient-temperature ( T amb ), water volumetric flow rate ( F w ), direct-solar-radiation ( G b ) and wind-speed ( V v ) considered as variables in the input layer. Two non-linear transfer functions (TANSIG and LOGSIG) in the hidden layer, a linear function (PURELIN) in the output layer, and the Levenberg-Marquardt training algorithm were applied. The results showed that both ANN models achieved satisfactory results with a coefficient of determination of 0.9511 and a root mean square error of 0.0193. Then, to get the variable's optimal values: rim-angle, inlet-temperature, and water volumetric flow rate, both ANN models inverted to acquire the multivariable objective function that could be resolved with genetic-algorithms (GA) and particle-swarm-optimization (PSO). The TANSIG function demonstrated better adaptation to the ANNim model by finding all the input variables in a random test with an error of 3.96% with a computational time of 14.39 s applying PSO. The results showed that by using the ANNim methodology, it is feasible to improve the performance of the PTC by optimizing from one, two, and three variables at the same time. In optimizing one variable at a time, it was possible to increase a random test's performance up to 54.78%, 27.62%, and 51.92% by finding the rim-angle inlet-temperature and water volumetric flow rate, respectively. In optimizing two variables simultaneously, it was possible to increase a random test's performance up to 36.73% by finding the appropriate inlet-temperature and water volumetric flow rate. In optimizing three variables simultaneously, it was possible to increase a random experimental test of up to 67.12%. Finally, the new ANNim method proposed may increase the thermal efficiency of a PTC in real-time because of the coupling of metaheuristic algorithms that allow obtaining optimal variables in the shortest possible time. Therefore, it can be a promising and widely used method for optimizing and controlling thermal processes.

[1]  H. Benli.  Determination of thermal performance calculation of two different types solar air collectors with the use of artificial neural networks , 2013 .

[2]  Klaus-Jürgen Riffelmann,et al.  The Influence of Solar Field Inlet and Outlet Temperature on the Cost of Electricity in a Molten Salt Parabolic Trough Power Plant , 2015 .

[3]  M. Abd Elaziz,et al.  Modeling of solar energy systems using artificial neural network: A comprehensive review , 2019, Solar Energy.

[4]  R. P. Saini,et al.  Identification of unknown parameters of a single diode photovoltaic model using particle swarm optimization with binary constraints , 2017 .

[5]  Aránzazu Fernández-García,et al.  A parabolic-trough collector for cleaner industrial process heat , 2015 .

[6]  Jure Zupan,et al.  The use of artificial neural network (ANN) for modeling of the H2O2/UV decoloration process: part I , 1999 .

[7]  Weidong Huang,et al.  Performance simulation of a parabolic trough solar collector , 2012 .

[8]  D. Colorado,et al.  Inverse neural network for optimal performance in polygeneration systems , 2013 .

[9]  Eliene Oliveira Lucas,et al.  Heat Transfer Analysis and Modeling of a Parabolic Trough Solar Collector: An Analysis , 2014 .

[10]  Darrell Whitley,et al.  A genetic algorithm tutorial , 1994, Statistics and Computing.

[11]  O. A. Jaramillo,et al.  Parabolic trough solar collector for low enthalpy processes: An analysis of the efficiency enhancement by using twisted tape inserts , 2016 .

[12]  Ya-Ling He,et al.  A MCRT and FVM coupled simulation method for energy conversion process in parabolic trough solar collector , 2011 .

[13]  Richard Bannerot,et al.  Determination of error tolerances for the optical design of parabolic troughs for developing countries , 1986 .

[14]  G. David Garson,et al.  Interpreting neural-network connection weights , 1991 .

[15]  Jack Brouwer,et al.  Neural-network-based optimization for economic dispatch of combined heat and power systems , 2020, Applied Energy.

[16]  Kun Wang,et al.  A detailed parameter study on the comprehensive characteristics and performance of a parabolic trough solar collector system , 2014 .

[17]  F Despagne,et al.  Neural networks in multivariate calibration. , 1998, The Analyst.

[18]  Li Xu,et al.  Analysis of the influence of heat loss factors on the overall performance of utility-scale parabolic trough solar collectors , 2018, Energy.

[19]  Irving Eleazar Perez Montes,et al.  Design and Construction of a Parabolic Trough Solar Collector for Process Heat Production , 2014 .

[20]  Qi Liang,et al.  Geometric optimization on optical performance of parabolic trough solar collector systems using particle swarm optimization algorithm , 2015 .

[21]  Soteris A. Kalogirou,et al.  Use of solar Parabolic Trough Collectors for hot water production in Cyprus. A feasibility study , 1992 .

[22]  Imdat Taymaz,et al.  Generating hot water by solar energy and application of neural network , 2005 .

[23]  Kaihua Lu,et al.  The accuracy and efficiency of GA and PSO optimization schemes on estimating reaction kinetic parameters of biomass pyrolysis , 2019, Energy.

[24]  O. A. Jaramillo,et al.  Design, construction, and testing of a parabolic trough solar concentrator for hot water and low enthalpy steam generation , 2012 .

[25]  Eduardo Zarza,et al.  Parabolic-trough solar collectors and their applications , 2010 .

[26]  O. A. Jaramillo,et al.  Modeling and optimization of a solar parabolic trough concentrator system using inverse artificial neural network , 2017 .

[27]  Elimar Frank,et al.  Characterization of a Parabolic trough Collector for Process Heat Applications , 2014 .

[28]  Mohamad Rasekh,et al.  Using PSO-GA algorithm for training artificial neural network to forecast solar space heating system parameters , 2019, Applied Thermal Engineering.

[29]  Shijun You,et al.  A Monte Carlo method and finite volume method coupled optical simulation method for parabolic trough solar collectors , 2017 .

[30]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[31]  Jose Hernández,et al.  Optimum operating conditions for heat and mass transfer in foodstuffs drying by means of neural network inverse , 2009 .

[32]  Soteris A. Kalogirou,et al.  Artificial neural networks used for the performance prediction of a thermosiphon solar water heater , 1999 .

[33]  Fu Wang,et al.  Performance Assessment of Solar Assisted Absorption Heat Pump System with Parabolic Trough Collectors , 2015 .

[34]  Juan M. Belman-Flores,et al.  Using ANNs to approach to the energy performance for a small refrigeration system working with R134a and two alternative lower GWP mixtures , 2017 .

[35]  R. A. Conde-Gutiérrez,et al.  Direct neural network modeling for separation of linear and branched paraffins by adsorption process for gasoline octane number improvement , 2014 .

[36]  Matthew Orosz,et al.  Chapter 16 - Solar thermal powered Organic Rankine Cycles , 2016 .

[37]  Thomas Egli,et al.  Solar water disinfection by a Parabolic Trough Concentrator (PTC): flow-cytometric analysis of bacterial inactivation , 2014 .

[38]  L. Oliveira,et al.  Green photochemistry: solar-chemical synthesis of Juglone with medium concentrated sunlight , 2006 .

[39]  Dimitrios M. Korres,et al.  Thermal and optical efficiency investigation of a parabolic trough collector , 2015 .

[40]  Soteris A. Kalogirou,et al.  The potential of solar industrial process heat applications , 2003 .

[41]  Lingzhi Zhu,et al.  Influences of installation and tracking errors on the optical performance of a solar parabolic trough collector , 2016 .

[42]  S. Jahangiri Mamouri,et al.  A new desalination system using a combination of heat pipe, evacuated tube and parabolic trough collector. , 2015 .

[43]  M. Orosz,et al.  Solar thermal powered Organic Rankine Cycles 16 , 2016 .

[44]  Soteris A. Kalogirou,et al.  Artificial neural networks for modelling the starting-up of a solar steam-generator , 1998 .

[45]  A. Huicochea,et al.  Optimal multivariable conditions in the operation of an absorption heat transformer with energy recycling solved by the genetic algorithm in artificial neural network inverse , 2018, Appl. Soft Comput..

[46]  Soteris A. Kalogirou,et al.  MODELING OF SOLAR DOMESTIC WATER HEATING SYSTEMS USING ARTIFICIAL NEURAL NETWORKS , 1999 .

[47]  G. C. Bakos,et al.  Design and construction of a two-axis Sun tracking system for parabolic trough collector (PTC) efficiency improvement , 2006 .

[48]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[49]  Sunil Pranit Lal,et al.  Design and optimization of airfoils and a 20 kW wind turbine using multi-objective genetic algorithm and HARP_Opt code , 2019 .

[50]  Pablo D. Tagle,et al.  Study of Applications of Parabolic Trough Solar Collector Technology in Mexican Industry , 2016 .

[51]  W. Beckman,et al.  Solar Engineering of Thermal Processes: Duffie/Solar Engineering 4e , 2013 .

[52]  Ibrahim Dincer,et al.  Development and performance assessment of a parabolic trough solar collector-based integrated system for an ice-cream factory , 2016 .

[53]  T. E. Boukelia,et al.  ANN-based optimization of a parabolic trough solar thermal power plant , 2016 .

[54]  A. Rabl,et al.  Optimization of parabolic trough solar collectors , 1982 .

[55]  Ali M. Abdelsalam,et al.  Optimization of wind turbines siting in a wind farm using genetic algorithm based local search , 2018, Renewable Energy.

[56]  Soteris A. Kalogirou,et al.  Parabolic trough collectors for industrial process heat in Cyprus , 2002 .

[57]  Shahram Delfani,et al.  Application of artificial neural network for performance prediction of a nanofluid-based direct absorption solar collector , 2019 .

[58]  W. Beckman,et al.  Solar Engineering of Thermal Processes , 1985 .

[59]  Radha Krishna Prasad,et al.  Application of ANN technique to predict the performance of solar collector systems - A review , 2018 .

[60]  Hafiz Muhmmad khurram Ali,et al.  An investigation of a solar cooker with parabolic trough concentrator , 2019, Case Studies in Thermal Engineering.

[61]  Soteris A. Kalogirou.  Performance of Solar Collectors , 2009 .

[62]  Hongwen He,et al.  An intelligent braking system composed single-pedal and multi-objective optimization neural network braking control strategies for electric vehicle , 2020 .

[63]  Ali Jaber Abdulhamed,et al.  Review of solar parabolic-trough collector geometrical and thermal analyses, performance, and applications , 2018, Renewable and Sustainable Energy Reviews.

[64]  Amenallah Guizani,et al.  Optical and thermal evaluations of a medium temperature parabolic trough solar collector used in a cooling installation , 2014 .

[65]  Farshid Keynia,et al.  Scrutiny of multifarious particle swarm optimization for finding the optimal size of a PV/wind/battery hybrid system , 2015 .

[66]  Q. Falcoz,et al.  Optical and Thermal Analysis of a Parabolic Trough Solar Collector through Coupling MCRT and FVM Techniques , 2017, 2017 International Renewable and Sustainable Energy Conference (IRSEC).