APPLICATION OF ARTIFICIAL NEURAL NETWORKS TO SKIDDER TRACTION PERFORMANCE

An artificial neural network simulating the tractive performance of a rubber-tired skidder operating on soft organic soil in the Coastal Pla in region of North Carolina, U.S.A. was modeled for three tire sizes i nflated al each of three inflation pressures (69, 103, and 172 kPa). T he neural network (4-5-3-1) demonstrated good generalization of the pu ll-load relationship when presented with data not used in network trai ning. The output of the network was in close agreement with the equati ons fitted using least squares methods for the actual pull-load data w here the line pull increased linearly with the applied tree load.