Resumen

ROSAS, David Antonio; BURGOS, Daniel; BRANCH, John Willian  y  CORBI, Alberto. Automatic determination of the Atterberg limits with machine learning. Dyna rev.fac.nac.minas [online]. 2022, vol.89, n.224, pp.34-42.  Epub 10-Feb-2023. ISSN 0012-7353.  https://doi.org/10.15446/dyna.v89n224.102619.

In this study, we determine the liquid limit (W1), plasticity index (PI), and plastic limit (Wp) of several natural fine-grained soil samples with the help of machine-learning and statistical methods. This enables us to locate each soil type analysed in the Casagrande plasticity chart with a single measure in pressure-membrane extractors. These machine-learning models showed adjustments in the determination of the liquid limit for design purposes when compared with standardised methods. Similar adjustments were achieved in the determination of the plasticity index, whereas the plastic limit determinations were applicable for control works. Because the best techniques were based in Multiple Linear Regression and Support Vector Machines Regression, they provide explainable plasticity models. In this sense, Wl = (9.94 ± 4.2) + (2.25 ± 0.3) ∙pF4.2, PI = (-20.47 ± 5.6) + (1.48 ± 0.3) ∙pF4.2 + (0.21 ± 0.1) ∙F, and Wp = (23.32 ± 3.5) + (0.60 ± 0.2) ∙pF4.2 - (0.13 ± 0.04) ∙F. So that, we propose an alternative, automatic, multi-sample, and static method to address current issues on Atterberg limits determination with standardised tests.

Palabras clave : machine learning; Atterberg limits; pressure-membrane extractor; determination; soils.

        · resumen en Español     · texto en Inglés     · Inglés ( pdf )