Beyond p-y method:A review of artificial intelligence approaches for predicting lateral capacity of drilled shafts in clayey soils

In 2023,pivotal advancements in artificial intelligence(AI)have significantly experienced.With that in mind,traditional methodologies,notably the p-y approach,have struggled to accurately model the complex,nonlinear soil-structure interactions of laterally loaded large-diameter drilled shafts.This study undertakes a rigorous evaluation of machine learning(ML)and deep learning(DL)techniques,offering a comprehensive review of their application in addressing this geotechnical challenge.A thorough review and comparative analysis have been carried out to investigate various AI models such as artificial neural networks(ANNs),relevance vector machines(RVMs),and least squares support vector machines(LSSVMs).It was found that despite ML approaches outperforming classic methods in predicting the lateral behavior of piles,their‘black box'nature and reliance only on a data-driven approach made their results showcase statistical robustness rather than clear geotechnical insights,a fact underscored by the mathematical equations derived from these studies.Furthermore,the research identified a gap in the availability of drilled shaft datasets,limiting the extendibility of current findings to large-diameter piles.An extensive dataset,compiled from a series of lateral loading tests on free-head drilled shaft with varying properties and geometries,was introduced to bridge this gap.The paper concluded with a direction for future research,proposes the integration of physics-informed neural networks(PINNs),combining data-driven models with fundamental geotechnical principles to improve both the interpretability and predictive accuracy of AI applications in geotechnical engineering,marking a novel contribution to the field.

Drilling load modeling and validation based on the filling rate of auger flute in planetary sampling

Some type of penetration into a subsurface is required in planetary sampling. Drilling and coring, due to its efficient penetrating and cuttings removal characteristics, has been widely applied in previous sampling missions. Given the complicated mechanical properties of a planetary regolith, suitable drilling parameters should be matched with different drilling formations properly.Otherwise, drilling faults caused by overloads could easily happen. Hence, it is necessary to establish a drilling load model, which is able to reveal the relationships among drilling loads, an auger＇s structural parameters, soil＇s mechanical properties, and relevant drilling parameters. A concept for the filling rate of auger flute（FRAF） is proposed to describe drilling conditions. If the FRAF index under one group of drilling parameters is less than 1, this means that the auger flute currently removes cuttings smoothly. Otherwise, the auger will be choked with compressed cuttings. In drilling operations, the drilling loads on the auger mainly come from the conveyance action, while the drilling loads on the drill bit primarily come from the cutting action. Experiments in one typical lunar regolith simulant indicate that the estimated drilling loads based on the FRAF coincide with the test results quite well. Based on this drilling load model, drilling parameters have been optimized.