Search

Adaptive neuro- Fuzzy Inference System (ANFIS) was used to predict the efficiency of a small modified centrifugal compressor. Data were generated from earlier studies which were obtained from a three dimensional, steady state and turbulent flow by using a CFD analyse on aerodynamic flow field characteristics. Equations were analysed using finite volume method. The results obtained from numerical solutions were used for training and testing the (ANFIS). In this paper, is the use adaptive neuro-fuzzy inference systems (ANFIS) approach is developed a performance prediction method of centrifugal compressor, to use it as performance predictor. A comparison was performed among the ANFIS method and Computational Fluid Dynamic (CFD) code. It is observed that the ANFIS method can be used to predict the performance and gives more significant value to actual value, moreover; the computation time, memory space and effort were reduced. [ABSTRACT FROM AUTHOR]

In order to model the design parameters of centrifugal impeller it is necessary to find new method for design parameters prediction. Adaptive neuro- Fuzzy Inference System (ANFIS) was used to predict the design parameters. The geometry parameter definition system of radial impellers based on Bezier curves, a typical centrifugal impeller with an inlet and a radial outlet used in this paper comprises a series of three Bezier patches or segments. The hub and shroud blade sections are defined as distributions of camber line; Data were generated from Bezier curves equations. In this paper, is the use adaptive neuro-fuzzy inference systems (ANFIS) approach is developed a design prediction method for radial impellers, to use it as design parameters predictor of radial impeller angles. The results were compared by statistical criterion (RMSE). Considering the results, it is obvious that our proposed modeling by (ANFIS) is efficient and valid and it can be expanded for more general states. [ABSTRACT FROM AUTHOR]