O Departamento de Matemática (DMA) e o Laboratório de Engenharia Matemática (LEMA) estarão representados na 12th Engineering Applications Neural Networks (EANN2011), que se realiza em Corfu, Grécia, entre 14-19 de Setembro.
A presença de Manuel Cruz na conferência dedicada a aplicações de redes neuronais na Engenharia serve para apresentar a comunicação “Maximum Shear Modulus Prediction by Marchetti Dilatometer Test Using Neural Networks”, desenvolvida em coautoria com Jorge Santos e Nuno Cruz.
“Maximum Shear Modulus Prediction by Marchetti Dilatometer Test Using Neural Networks”
«The use of Neural Networks for modelling systems is been widespread, in particular within areas where the great amount of available data and the complexity of the systems keeps the problem very unfriendly to treat following traditional data analysis methodologies. In the last two decades, small strain shear modulus became one of the most important geotechnical parameters to characterize soil stiffness. Finite element analysis have shown that in-situ stiffness of soils and rocks is much higher than was previously thought, and that stress-strain behaviour of these materials is non-linear in most cases with small strain levels, especially in the ground around retaining walls, foundations and tunnels typically in the order of 0.01 to 0.0001 of strain. Although the best approach seems to be based in measuring seismic wave velocities, deriving the parameter through correlations with in-situ tests is usually considered very useful for design practice. In this work, a new approach using Neural Networks is proposed for sedimentary soils and the results are discussed and compared with some of the most common available methodologies for this evaluation».
Palavras-chave: Maximum Shear Modulus, Non-Linear Regression, SVR
Instituto Superior de Engenharia do Porto