Author(s): Habtamu Tolossa; Matthias Schneider; Silke Wieprecht
Linked Author(s): Silke Wieprecht, Matthias Schneider
Keywords: Fuzzy logic; Sediment transport; Adaptive neuro-fuzzy inference system (ANFIS)
Abstract: Correct estimation of sediment transport rates in alluvial rivers is important in the context of erosion, sedimentation, flood control, etc. Extensive research during the last decades has produced a plethora of sediment transport equations. Calculation of sediment transport is complex and often subject to semi-empirical or empirical treatment. In many practical situations prediction errors of these equations are observed to be high. Recently, the use of data driven modelling, which is especially attractive for modelling processes about which adequate knowledge of the physics is limited, like in the case for sediment transport, has gained attention. This research focuses on the applicability of a data driven fuzzy rule based modelling approach for estimating total sediment transport rates. A general fuzzy system has the components of fuzzification, fuzzy rule base, fuzzy output engine, and defuzzification. Four dominant parameters affecting sediment transport capacity are used for constructing the data driven fuzzy model, using 1023 laboratory datasets collected by different researchers. The optimisation of the fuzzy model is performed by data-driven tuning of the fuzzy model parameters using the Adaptive Neuro Fuzzy Inference Systems (ANFIS) so that the system output matches the observed data. The comparison of the results of the fuzzy rule based model with the results of other commonly utilized sediment transport functions is also performed. The fuzzy logic toolbox in MATLAB is used for performing the fuzzy modelling. The results show that the data driven fuzzy logic modelling approach could be used for correctly estimating total sediment transport rates.
Year: 2010