Prediction of Compaction and Strength Properties of Amended Soil Using Machine Learning

In the current work, a systematic approach is exercised to monitor amended soil reliability for a housing development program to holistically understand the targeted material mixture and the building input derived, focusing on the three governing parameters: (i) optimum moisture content (OMC), (ii) maximum dry density (MDD), and (iii) unconfined compressive strength (UCS). It is in essence the selection of machine learning algorithms that could optimally show the true relation of these factors in the best possible way. Thus, among the machine learning approaches, the optimizable ensemble and artificial neural networks were focused on. The data sources were those compiled from wide-ranging literature sources distributed over the five continents and twelve countries of origin. After a rigorous manipulation, synthesis, and results analyses, it was found that the selected algorithms performed well to better approximate OMC and UCS, whereas that of the MDD result falls short of the established threshold of the set limits referring to the MSE statistical performance evaluation metrics.

[1]  D. Feng,et al.  A probabilistic bond strength model for corroded reinforced concrete based on weighted averaging of non-fine-tuned machine learning models , 2022, Construction and Building Materials.

[2]  Kassahun Admassu Abegaz,et al.  Artificial Intelligence for Prediction of Physical and Mechanical Properties of Stabilized Soil for Affordable Housing , 2021, Applied Sciences.

[3]  De-Cheng Feng,et al.  A machine learning-based time-dependent shear strength model for corroded reinforced concrete beams , 2021 .

[4]  S. Shen,et al.  Improved prediction of slope stability using a hybrid stacking ensemble method based on finite element analysis and field data , 2020 .

[5]  Indra Prakash,et al.  Prediction of soil unconfined compressive strength using Artificial Neural Network Model , 2020 .

[6]  Mohsen Saadat,et al.  Prediction of the unconfined compressive strength of stabilised soil by Adaptive Neuro Fuzzy Inference System (ANFIS) and Non-Linear Regression (NLR) , 2019, Geomechanics and Geoengineering.

[7]  Kassahun Admassu.  Method of amended soils for compressed block and mortar in earthen construction , 2019 .

[8]  Hamid Gadouri,et al.  Prediction of geotechnical properties of clayey soils stabilised with lime using artificial neural networks (ANNs) , 2019 .

[9]  Ethiopia Nigussie,et al.  Internet of Things based Durability Monitoring and Assessment of Reinforced Concrete Structures , 2019, Procedia Computer Science.

[10]  Kassahun Admassu.  ENGINEERED SOIL AND THE NEED FOR LIME-NATURAL POZZOLAN MIXTURE PERCENTAGE APPROXIMATION , 2018 .

[11]  Esko Sistonen,et al.  Significance of chloride penetration controlling parameters in concrete: Ensemble methods , 2017 .

[12]  Sarat Kumar Das,et al.  Prediction of Maximum Dry Density and Unconfined Compressive Strength of Cement Stabilised Soil Using Artificial Intelligence Techniques , 2016 .

[13]  Pijush Samui,et al.  Application of Artificial Intelligence to Maximum Dry Density and Unconfined Compressive Strength of Cement Stabilized Soil , 2011 .

[14]  A. Gandomi,et al.  Modeling of maximum dry density and optimum moisture content of stabilized soil using artificial neural networks , 2010 .

[15]  Mahil Carr,et al.  Software Cost Estimation using Soft Computing Approaches , 2010 .

[16]  Ahmet Tortum,et al.  Prediction of the unconfined compressive strength of compacted granular soils by using inference systems , 2009 .

[17]  M. Gandomi,et al.  Prediction of maximum dry density and optimum moisture content of stabilised soil using RBF neural networks , 2009 .