Application of soft computing techniques for shallow foundation reliability in geotechnical engineering

This research focuses on the application of three soft computing techniques including Minimax Probability Machine Regression(MPMR),Particle Swarm Optimization based Artificial Neural Network(ANN-PSO)and Particle Swarm Optimization based Adaptive Network Fuzzy Inference System(ANFIS-PSO)to study the shallow foundation reliability based on settlement criteria.Soil is a heterogeneous medium and the involvement of its attributes for geotechnical behaviour in soil-foundation system makes the prediction of settlement of shallow a complex engineering problem.This study explores the feasibility of soft computing techniques against the deterministic approach.The settlement of shallow foundation depends on the parametersγ(unit weight),e0(void ratio)and CC(compression index).These soil parameters are taken as input variables while the settlement of shallow foundation as output.To assess the performance of models,different performance indices i.e.RMSE,VAF,R^2,Bias Factor,MAPE,LMI,U(95),RSR,NS,RPD,etc.were used.From the analysis of results,it was found that MPMR model outperformed PSO-ANFIS and PSO-ANN.Therefore,MPMR can be used as a reliable soft computing technique for non-linear problems for settlement of shallow foundations on soils.     

Nonlinear regression model for peak-failure strength of rockfill materials in general stress space

A nonlinear regression model for peak-failure strength prediction of rockfill materials is proposed. It is based on the relationship between the peak-failure stress ratio and the normalized confining pressure as well as the relationship between the normalized peak-failure stress ratio and the exponent function of the intermediate principal stress ratio. This model can well predict the variations of the peak-failure stress ratio with the initial confining pressure and the intermediate principal stress ratio for different rockfill materials under different general stress paths. Comparisons of the measured and predicted results show that the peak-failure strength under the constant-p' and constant-b path is larger than that under the constant-σ'_3 and constant-b path. The predictive capacity of the proposed model for the peakfailure stress ratio is better than that for the peak-failure friction angle.     

Genesis of the supergiant Huayangchuan carbonatite-hosted uranium-polymetallic deposit in the Qinling Orogen,Central China

The newly-discovered supergiant Huayangchuan uranium (U)-polymetallic deposit is situated in the Qinling Orogen, Central China. The deposit contains economic endowments of U, Nb, Pb, Se, Sr, Ba and REEs, some of which (e.g., U, Se, and Sr) reaching super-large scale. Pyrochlore, allanite, monazite, barite-celestite and galena are the major ore minerals at Huayangchuan. Uranium is mainly hosted in the primary mineral of pyrochlore, and the mineralization is mainly hosted in or associated with carbonatite dikes.According to the mineral assemblages and crosscutting relationships, the alteration/mineralization at Huayangchuan comprises four stages, i.e., pegmatite REE mineralization (I), main mineralization (II), skarn mineralization (III) and post-ore alteration (IV). Coarse-grained euhedral allanite is the main Stage I REE mineral, and the pegmatite-hosted REE mineralization (ca. 1.8 Ga) occurs mostly in the shallow-level of northwestern Huayangchuan, corresponding to the Paleoproterozoic Xiong'er Group volcanic rocks (1.80–1.75 Ga) in the southern margin of North China Block. Carbonatite-hosted Stage II mineralization contributes to the majority of U-Nb-REE-Ba-Sr resources, and is controlled by the Huayangchuan Fault. Stage II mineralization can be further divided into the sulfate mineralization (barite-celestite) (II-A), alkali-rich U mineralization (aegirine-augite + pyrochlore + uraninite + uranothorite) (II-B) and REE (allanite + monazite + chevkinite)-U (pyrochlore + uraninite) mineralization (II-C) substages. Stage II mineralization may have occurred during the Late Triassic Mianlue Ocean closure. Skarn mineralization contributed to the majority of Pb and minor U-REE (uraninite-allanite) resources at Huayangchuan, and is spatially associated with the Late Cretaceous-Early Jurassic (Yanshanian) Huashan and Laoniushan granites. We suggested that hydrothermal fluids derived from the Laoniushan and Huashan granites may have reacted with the Triassic carbonatites, and formed the Huayangchuan Pb skarn mineralization.The mantle-derived Triassic carbonatites may have been fertilized by the U-rich subducting oceanic sediments, and were further enriched through reacting with the Proterozoic U-REE-rich pegmatite wallrocks at Huayangchuan. Ore-forming elements were likely transported in metal complexes (F⁻, ${\mathrm{PO}}_4^{3–}$, ${\mathrm{CO}}_3^{2–}$ and ${\mathrm{SO}}_4^{2–}$), and deposited with the dilution of the complex concentration. This may have formed the distinct vertical mineralization zoning, i.e., sodic fenite-related alkali-U mineralization at depths and potassic fenite-related REE-U mineralization at shallow level.