A neuro-fuzzy approach for prediction of longitudinal wave velocity

Adaptive neuro-fuzzy inference system (ANFIS) is rapidly gaining popularity in the area of geophysics and geomechanics. This paper discusses the importance of ANFIS to prediction of p-wave velocity and its advantages over other conventional methods of computing. This paper deals with the application of a ANFIS to predict longitudinal wave velocity. P-wave measurement, which is also an indicator of peak particle velocity during blasting in a mine, is an important parameter to be determined to minimize the damage caused by ground vibrations. A number of previous researchers have tried to use different empirical methods to predict p-wave. But these empirical methods have their limitations due to its less versatile application. The fracture propagation is not only influenced by the physico-mechanical parameters of rock but also on the dynamic wave velocity of rock (e.g., compressional wave velocity). It has wide application in the different field of geophysics. An ANFIS model is designed to predict the compressional wave velocity of different rocks. The fracture roughness coefficient and physico-mechanical properties are taken as input parameters and compressional wave velocity as output parameters. The error for the predicted values is found to be negligible (0.5%) and generalization capability of the neuro-fuzzy model is found to be very useful for such type of geophysical problems.