August 9, 2022
Gholam Hossein Roshani

Gholam Hossein Roshani

Academic rank: Associate professor
Education: Ph.D in Nuclear Engineering
Faculty: Faculty of energy


A novel method for flow pattern identification in unstable operational conditions using gamma ray and radial basis function
Type Article
Radial basis function Neural network Flow pattern recognition Density independent Multi beam gamma ray
Researchers Gholam Hossein Roshani، Ehsan Nazemi، M. M. Roshani


Changes of fluid properties (especially density) strongly affect the performance of radiation-based multiphas eflow meter and could cause error in recognizing the flow pattern and determining void fraction. In this work, we proposed a methodology based on combination of multi-beam gamma ray attenuation and dual modality densitometry techniques using RBF neural network in order to recognize the flow regime and determine the void fraction in gas-liquid two phase flows independent of the liquid phase changes. The proposed system is consisted of one 137Cs source, two transmission detectors and one scattering detector. The registered counts in two transmission detectors were used as the inputs of one primary Radial Basis Function (RBF) neural network for recognizing the flow regime independent of liquid phase density. Then, after flow regime identification, three RBF neural networks were utilized for determining the void fraction independent of liquid phase density. Registered count in scattering detector and first transmission detector were used as the inputs of these three RBF neural networks. Using this simple methodology, all the flow patterns were correctly recognized and the void fraction was predicted independent of liquid phase density with mean relative error (MRE) of less than 3.28%.