General regression artificial neural networks for two-phase flow regime identification
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Fuzzy inference systems for efficient non-invasive on-line two-phase flow regime identification
ICANNGA'09 Proceedings of the 9th international conference on Adaptive and natural computing algorithms
Hi-index | 0.00 |
A fuzzy methodology for two-phase flow pattern identification based on local time-averaged two-phase parameters (void fraction and interfacial area) obtained from a multi-sensor probe is presented. The experimental data are obtained in a 5.08 cm I.D. vertical co-current air/water loop at an axial location L/D = 32.Raw data and trends from the fuzzy system are in good agreement with the experimental observations. Moreover, the method reveals the contribution of each flow regime to the two-phase flow system. As a conclusion, we suggest several ways for improving and using the proposed fuzzy methodology.