Noise evaluation of MF285 and U650 tractors by using Adaptive Neuro-Fuzzy Inference Systems (ANFIS) method

ABSTRACT: In this research ANFIS method has been used to predict sound pressure levels of MF285 and U650 tractors for following machines: moldboard plow, chisel plow, cultivator, rotary tiller, boom-type sprayer, disk harrow and ditcher. Combination of fuzzy logic with architectural design of neural network leads to creation of neuro-fuzzy systems, which benefit from feed forward calculation of output and back-propagation learning capability of neural networks, while keeping interpret- ability of a fuzzy system. An adaptive neuro-fuzzy inference system architecture based on the Takagi– Sugeno model created to modeling of sound pressure level of MF285 and U650 tractors during agricultural operations. The testing performance of the proposed ANFIS model revealed a good predictive capacity to yield acceptable error measures with, R2=0.917 and also RMSE=1.06, SSE= 76.11 and MAE= 0.7495. The study recommends that the ANFIS technique can be successfully used in estimation of sound pressure level of MF285 and U650 tractors.