Application of Adaptive Neuro-Fuzzy Inference Systems (ANFIS) in Modeling the Effects of Selected Input Variables on the Period of Oscillation in an Unsteady Flow Through Surge Chamber

摘要: In this research paper, an attempt was made to model the significant effects and interactions of some selected input variables on period oscillation in unsteady flow through surge chambers using adaptive neuro-fuzzy techniques. The choice technique is based fact that, it a hybrid modeling algorithm that combines both neural network fuzzy logic obtain better result. inlet valve reservoir opened adjusted give steady level discharge from overflow weir for predetermined time. rate water thereafter computed volume against time relationship. A then initiated following sudden closure dynamics behaviour studied oscillation. Statistical studies such as tower diameter, flow, velocity operational done design experiment (DOE) employing 2-level factorial with 3 central points’ one replication. Results obtained were modeled Adaptive Neuro-Fuzzy Inference Technique (ANFIS) incorporated into MATLAB toolbox determine variable (s) possess highest response (period oscillation) also develop Fuzzy Systems (FIS) structure which can be employed study adequacy results similar experiment. shows diameter root mean square error 0.7360 appears single amplitude displacement. More also, combine effects, (tower flow) having 0.4410 seen