This study investigates and challenges the capability of standard and hybrid soft computing models of fuzzy c-means clustering adaptive neuro-fuzzy inference system (ANFIS), wavenet and artificial neural networks (MLPNN and RBFNN) to estimate the spillway aerator air demand in dams. For the learning process, four different meta-heuristic optimization methods (particle swarm optimization (PSO), genetic algorithm (GA), firefly algorithm (FA) and biogeography-based optimization (BBO)) are considered as alternatives to the classical optimization algorithms of the data-driven models. In addition to the data-driven models, the multiple linear regressions and some empirical... (More)
This study investigates and challenges the capability of standard and hybrid soft computing models of fuzzy c-means clustering adaptive neuro-fuzzy inference system (ANFIS), wavenet and artificial neural networks (MLPNN and RBFNN) to estimate the spillway aerator air demand in dams. For the learning process, four different meta-heuristic optimization methods (particle swarm optimization (PSO), genetic algorithm (GA), firefly algorithm (FA) and biogeography-based optimization (BBO)) are considered as alternatives to the classical optimization algorithms of the data-driven models. In addition to the data-driven models, the multiple linear regressions and some empirical relations are used to evaluate the performance of the models. Evaluation of the models is assessed with five different statistical parameters as well as the diagnostic tool of the Taylor’s diagram. Analysis of the models’ outcome reveals that the ANFIS-GA has the best performance associated with a standard root mean square error of 0.309 and a coefficient of determination (R 2
) of 0.93.
@article{891c83a4-eb0c-44ba-b21e-f897ba9a9120,
abstract = {{<p><br>
This study investigates and challenges the capability of standard and hybrid soft computing models of fuzzy c-means clustering adaptive neuro-fuzzy inference system (ANFIS), wavenet and artificial neural networks (MLPNN and RBFNN) to estimate the spillway aerator air demand in dams. For the learning process, four different meta-heuristic optimization methods (particle swarm optimization (PSO), genetic algorithm (GA), firefly algorithm (FA) and biogeography-based optimization (BBO)) are considered as alternatives to the classical optimization algorithms of the data-driven models. In addition to the data-driven models, the multiple linear regressions and some empirical relations are used to evaluate the performance of the models. Evaluation of the models is assessed with five different statistical parameters as well as the diagnostic tool of the Taylor’s diagram. Analysis of the models’ outcome reveals that the ANFIS-GA has the best performance associated with a standard root mean square error of 0.309 and a coefficient of determination (R <br>
<sup>2</sup><br>
) of 0.93. <br>
</p>}},
author = {{Mahdavi-Meymand, Amin and Scholz, Miklas and Zounemat-Kermani, Mohammad}},
issn = {{2164-3040}},
keywords = {{Aerator air flow; fuzzy inference systems; meta-heuristic algorithms; spillway aerator}},
language = {{eng}},
number = {{sup1}},
pages = {{58--69}},
publisher = {{Taylor & Francis}},
series = {{ISH Journal of Hydraulic Engineering}},
title = {{Challenging soft computing optimization approaches in modeling complex hydraulic phenomenon of aeration process}},
url = {{http://dx.doi.org/10.1080/09715010.2019.1574619}},
doi = {{10.1080/09715010.2019.1574619}},
volume = {{27}},
year = {{2021}},
}