Performance Prediction of a Pump as Turbine: Sensitivity Analysis Based on Artificial Neural Networks and Evolutionary Polynomial Regression

The research of a general methodology to predict the pump performance in a reverse mode, knowing those of a pump in a direct mode, is a question that is still open. The scientific research is making many efforts toward answering this question, but at present, there is still not much clarity. This consideration has been the starting point of this research that thanks to artificial neural networks and evolutionary polynomial regression methods have tried to investigate and define the real weight of every input parameter, representing the efficiency of a pump in a direct way, on the output parameters, and representing efficiency of a pump used like a turbine.

[1]  Orazio Giustolisi.  Input–output dynamic neural networks simulating inflow–outflow phenomena in an urban hydrological basin , 2000 .

[2]  Alireza Riasi,et al.  Numerical and experimental study of using axial pump as turbine in Pico hydropower plants , 2013 .

[3]  Massimiliano Renzi,et al.  Analytical Prediction Models for Evaluating Pumps-As-Turbines (PaTs) Performance , 2017 .

[4]  Orazio Giustolisi,et al.  Optimal design of artificial neural networks by a multi-objective strategy: groundwater level predictions , 2006 .

[5]  Francesco Pugliese,et al.  Experimental characterization of two Pumps As Turbines for hydropower generation , 2016 .

[6]  Helena M. Ramos,et al.  Energy Recovery Using Micro-Hydropower Technology in Water Supply Systems: The Case Study of the City of Fribourg , 2016 .

[7]  Orazio Giustolisi,et al.  Multi-objective Evolutionary Polynomial Regression , 2006 .

[8]  Armando Carravetta,et al.  Energy Recovery in Water Systems by PATs: A Comparisons among the Different Installation Schemes , 2014 .

[9]  Sanjay V. Jain,et al.  Effects of impeller diameter and rotational speed on performance of pump running in turbine mode , 2015 .

[10]  Orazio Giustolisi,et al.  Improving generalization of artificial neural networks in rainfall–runoff modelling / Amélioration de la généralisation de réseaux de neurones artificiels pour la modélisation pluie-débit , 2005 .

[11]  Claudio Alatorre-Frenk.  Cost minimisation in micro-hydro systems using pumps-as-turbines , 1994 .

[12]  Massimiliano Renzi,et al.  Pump-as-turbine for Energy Recovery Applications: The Case Study of An Aqueduct☆ , 2016 .

[13]  Shahram Derakhshan,et al.  Experimental study of characteristic curves of centrifugal pumps working as turbines in different specific speeds , 2008 .

[14]  Claudia Biermann.  Centrifugal And Axial Flow Pumps Theory Design And Application , 2016 .

[15]  Gerhard Fischer,et al.  Manual on pumps used as turbines , 1992 .

[16]  Mauro Venturini,et al.  Comparison of Different Approaches to Predict the Performance of Pumps As Turbines (PATs) , 2018 .

[17]  Rajesh N. Patel,et al.  Investigations on pump running in turbine mode: A review of the state-of-the-art , 2014 .

[18]  S. Gopalakrishnan,et al.  Power Recovery Turbines For The Process Industry , 1986 .

[19]  Özgür Kişi,et al.  Multi-layer perceptrons with Levenberg-Marquardt training algorithm for suspended sediment concentration prediction and estimation / Prévision et estimation de la concentration en matières en suspension avec des perceptrons multi-couches et l’algorithme d’apprentissage de Levenberg-Marquardt , 2004 .

[20]  Bernardo Fortunato,et al.  Experimental investigation and performance prediction modeling of a single stage centrifugal pump operating as turbine , 2017 .

[21]  Mario Binetti,et al.  Innovative mini-hydro device for the recharge of electric vehicles in urban areas , 2018, International Journal of Energy and Environmental Engineering.

[22]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

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

[24]  Bruno Melo Brentan,et al.  Selection and location of Pumps as Turbines substituting pressure reducing valves , 2017 .

[25]  I. E. Karadirek,et al.  Full-Scale PAT Application for Energy Production and Pressure Reduction in a Water Distribution Network , 2017 .

[26]  H Kahlen.  Electric vehicles in Europe - the aims of AVERE, CITELEC and WEVA , 1992 .

[27]  D. Savić,et al.  Advances in data-driven analyses and modelling using EPR-MOGA. , 2009 .

[28]  Punit Singh.  Optimization of internal hydraulics and of system design for PUMPS AS Turbines with field implementation and evaluation , 2005 .

[29]  Anoop Kumar,et al.  Experimental Investigation of Centrifugal Pump Working as Turbine for Small Hydropower Systems , 2011 .

[30]  Gabriele Freni,et al.  Pumps as turbines (PATs) in water distribution networks affected by intermittent service , 2014 .

[31]  Massimiliano Renzi,et al.  A general methodology for performance prediction of pumps-as-turbines using Artificial Neural Networks , 2018, Renewable Energy.

[32]  Abraham Engeda,et al.  Performance of centrifugal pumps running in reverse as turbine: Part II- systematic specific speed and specific diameter based performance prediction , 2016 .

[33]  Kong Fanyu,et al.  Theoretical, numerical and experimental prediction of pump as turbine performance , 2012 .

[34]  Luigi Glielmo,et al.  Hydraulic and Electric Regulation of a Prototype for Real-Time Control of Pressure and Hydropower Generation in a Water Distribution Network , 2018, Journal of Water Resources Planning and Management.

[35]  Feng-Chen Li,et al.  Investigation on pump as turbine (PAT) technical aspects for micro hydropower schemes: A state-of-the-art review , 2017 .

[36]  S. Barbarelli,et al.  Experimental activity at test rig validating correlations to select pumps running as turbines in microhydro plants , 2017 .

[37]  Jane E. Sargison,et al.  Design and performance evaluation of a pump-as-turbine micro-hydro test facility with incorporated inlet flow control , 2015 .