ANFIS approach to the scour depth prediction at a bridge abutment

摘要

An accurate estimation of the maximum possible scour depth at bridge abutments isnof paramount importance in decision-making for the safe abutment foundation depth andnalso for the degree of scour counter-measure to be implemented against excessive scouring.nDespite analysis of innumerable prototype and hydraulic model studies in the past, the scourndepth prediction at the bridge abutments has remained inconclusive. This paper presents annalternative to the conventional regression model (RM) in the form of an adaptive network-basednfuzzy inference system (ANFIS) modelling. The performance of ANFIS over RM and artificial neuralnnetworks (ANNs) is assessed here. It was found that the ANFIS model performed best amongnof these methods. The causative variables in raw form result in a more accurate predictionnof the scour depth than that of their grouped form.