Neural Tree for Estimating the Uniaxial Compressive Strength of Rock MaterialsVarun Ojha
The document presents a neural tree model for estimating the uniaxial compressive strength (UCS) of rock materials from index test parameters. It develops and compares models using fuzzy inference systems, adaptive neuro-fuzzy inference systems, multi-layer perceptrons, and heterogeneous flexible neural trees. The best performing and lightest weight model was a multiobjective heterogeneous flexible neural tree, which estimated UCS with the lowest error and highest correlation. Among the different index test parameters, the point load strength test was found to be the most significant in estimating UCS.
Neural Tree for Estimating the Uniaxial Compressive Strength of Rock MaterialsVarun Ojha
The document presents a neural tree model for estimating the uniaxial compressive strength (UCS) of rock materials from index test parameters. It develops and compares models using fuzzy inference systems, adaptive neuro-fuzzy inference systems, multi-layer perceptrons, and heterogeneous flexible neural trees. The best performing and lightest weight model was a multiobjective heterogeneous flexible neural tree, which estimated UCS with the lowest error and highest correlation. Among the different index test parameters, the point load strength test was found to be the most significant in estimating UCS.