Transactions of the Canadian Society for Mechanical Engineering · 2011 · 23 citations · 12 references
ArchitectureComputational EngineeringMechanical EngineeringComputational Fluid DynamicsDesign OptimizationOptimizationEvolutionary ComputationEvolutionary OptimizationGenetic AlgorithmsMetaheuristic OptimizationMulti-objective Design OptimizationMulti-objective OptimizationBlade Geometry OptimizationBlade OptimizationCentrifugal Fan PerformanceHead LossHead Loss AnalysisMulti-objective Evolutionary AlgorithmsMulti-objective Evolutionary ComputationMulti-objective Evolutionary Optimization
In the present study, multi-objective optimization of Forward-Curved (FC) blade centrifugal fans is performed in three steps. In the first step, Head rise (H R ) and the Head loss (H L ) in a set of FC centrifugal fan is numerically investigated using commercial software NUMECA. Two meta-models based on the evolved group method of data handling (GMDH) type neural networks are obtained, in the second step, for modeling of H R and H L with respect to geometrical design variables. Finally, using the obtained polynomial neural networks, multi-objective genetic algorithms are used for Pareto based optimization of FC centrifugal fans considering two conflicting objectives, H R and H L .
12
Polynomial Theory of Complex Systems
A. G. Ivakhnenko · IEEE Transactions on Systems Man and Cybernetics · 1971 · 1.7K citations
System identification—A survey
Karl Johan Åström, P. Eykhoff · Automatica · 1971 · 1.5K citations · Full text
Kazem Atashkari, N. Nariman-zadeh, M. Gölcü et al. · Energy Conversion and Management · 2006 · 162 citations