The present study focused on developing the multi-layer perceptron neural network prediction model for the modified compaction parameters of coarse-grained and fine-grained soil. A total of 248 in situ collected soil ...
详细信息
The present study focused on developing the multi-layer perceptron neural network prediction model for the modified compaction parameters of coarse-grained and fine-grained soil. A total of 248 in situ collected soil samples were taken from the ongoing highways construction project work site for their quality control purposes. The collected soil samples were tested in the laboratory using Bureau of Indian Standard specification. Among 248 datasets, 179 datasets belong to coarse-grained soil, and the remaining 69 datasets are fit for fine-grained soil. The artificial neural network (ANN) algorithm, written in Python V3.7.9 platform, was adopted for the model development. The developed model exhibits the correlation coefficient (R) value more than 0.80 and 0.90 for coarse-grained and fine-grained soil, respectively. Additionally, the selected ANN models can predict MDD within +/- 4% and +/- 2% variations for coarse-grained and fine-grained soil, respectively. In contrast, OMC for both the soil can be predicted within +/- 8% variations.
Maximum dry density (MDD) and optimum moisture content (OMC) are two significant compaction criteria, especially for quality control and design engineers. Estimating laboratory proctor compaction test is rigorous, tim...
详细信息
Maximum dry density (MDD) and optimum moisture content (OMC) are two significant compaction criteria, especially for quality control and design engineers. Estimating laboratory proctor compaction test is rigorous, time-consuming, and expensive, hindering projects with limited budgets and tight schedules. This study proposed the novel application of hybrid particle swarm optimization (PSO) optimized Gaussian process regression (GPR), K-nearest neighbor (KNN), random forest (RF), and extreme gradient boosting (XGB) algorithms for predicting the soil compactionparameters. Analyzing 2148 in situ soil samples from various geological locations established the maximum proficiency of the XGB algorithm followed by KNN, GPR, and RF in MDD, whereas XGB, KNN, RF, and GPR in OMC. Furthermore, the level 1 and level 2 validation results ascertain the robustness of models in predicting MDD and OMC on different geological location datasets. Eventually, the AI-based computer software developed through this study offers reliable and efficient predictions for civil engineers.
暂无评论