Debris flow is one of the major secondary mountain hazards following the earthquake. This study explores the dynamic initiation mechanism of debris flows based on the strength reduction of soils through static and dyn...Debris flow is one of the major secondary mountain hazards following the earthquake. This study explores the dynamic initiation mechanism of debris flows based on the strength reduction of soils through static and dynamic triaxial tests. A series of static and dynamic triaxial tests were conducted on samples in the lab. The samples were prepared according to different grain size distribution, degree of saturation and earthquake magnitudes. The relations of dynamic shear strength, degree of saturation, and number of cycles are summarized through analyzing experimental results. The findings show that the gravelly soil with a wide and continuous gradation has a critical degree of saturation of approximately 87%, above which debris flows will be triggered by rainfall, while the debris flow will be triggered at a critical degree of saturation of about 73% under the effect of rainfall and earthquake(M>6.5). Debris flow initiation is developed in the humidification process, and the earthquake provides energy for triggering debris flows. Debris flows are more likely to be triggered at the relatively low saturation under dynamic loading than under static loading. The resistance of debris flow triggering relies more on internal frication angle than soil cohesion under the effect of rainfall and earthquake. The conclusions provide an experimental analysis method for dynamic initiation mechanism of debris flows.展开更多
Machine learning is frequently used in various geotechnical applications nowadays.This study presents a statistics and machine learning model for settlement prediction of helical piles that relates compressive service...Machine learning is frequently used in various geotechnical applications nowadays.This study presents a statistics and machine learning model for settlement prediction of helical piles that relates compressive service load and soil parameters as a group with the pile parameters.Machine learning algorithms such as Decision Trees,Random Forests,AdaBoost,and Artificial Neural Networks(ANN)were used to develop the predictive models.The models were validated using cross-validation techniques and tested on an independent dataset to assess their accuracy and generalizability.Numerical investigation is used here to supplement the field data by simulating various soil conditions and pile geometries that have not been tested in the field.This study compiled numerical results of 3600 models.As the models are well-calibrated and validated,the data from these models can be reasonably assumed to simulate the ground situation.At the end of this study,a comparative analysis of statistic learning and machine learning(ML)was done using the field axial load tests database and numerical investigation on helical piles.It is observed that ML models like Decision Trees and Random Forests provided the better model with R-squared values of 0.92 and 0.96,respectively,for large diameters.The authors believe this study will permit engineers and state agencies to understand this prediction model’s efficacy better,resulting in a more resilient approach to designing large-diameter helical piles for the compressive load.展开更多
基金sponsored by Natural Science Foundation of China (Grant No. 51269012)Major Projects of Natural Science Foundation of Inner Mongolia Autonomous Region (Grant No. ZD0602)+2 种基金part of National Project 973 "Wenchuan Earthquake Mountain Hazards Formation Mechanism and Risk Control" (Grant No. 2008CB425800)funded by "New Century Excellent Talents" of University of Ministry of Education of China (Grant No. NCET-11-1016)China Scholarship Council
文摘Debris flow is one of the major secondary mountain hazards following the earthquake. This study explores the dynamic initiation mechanism of debris flows based on the strength reduction of soils through static and dynamic triaxial tests. A series of static and dynamic triaxial tests were conducted on samples in the lab. The samples were prepared according to different grain size distribution, degree of saturation and earthquake magnitudes. The relations of dynamic shear strength, degree of saturation, and number of cycles are summarized through analyzing experimental results. The findings show that the gravelly soil with a wide and continuous gradation has a critical degree of saturation of approximately 87%, above which debris flows will be triggered by rainfall, while the debris flow will be triggered at a critical degree of saturation of about 73% under the effect of rainfall and earthquake(M>6.5). Debris flow initiation is developed in the humidification process, and the earthquake provides energy for triggering debris flows. Debris flows are more likely to be triggered at the relatively low saturation under dynamic loading than under static loading. The resistance of debris flow triggering relies more on internal frication angle than soil cohesion under the effect of rainfall and earthquake. The conclusions provide an experimental analysis method for dynamic initiation mechanism of debris flows.
文摘Machine learning is frequently used in various geotechnical applications nowadays.This study presents a statistics and machine learning model for settlement prediction of helical piles that relates compressive service load and soil parameters as a group with the pile parameters.Machine learning algorithms such as Decision Trees,Random Forests,AdaBoost,and Artificial Neural Networks(ANN)were used to develop the predictive models.The models were validated using cross-validation techniques and tested on an independent dataset to assess their accuracy and generalizability.Numerical investigation is used here to supplement the field data by simulating various soil conditions and pile geometries that have not been tested in the field.This study compiled numerical results of 3600 models.As the models are well-calibrated and validated,the data from these models can be reasonably assumed to simulate the ground situation.At the end of this study,a comparative analysis of statistic learning and machine learning(ML)was done using the field axial load tests database and numerical investigation on helical piles.It is observed that ML models like Decision Trees and Random Forests provided the better model with R-squared values of 0.92 and 0.96,respectively,for large diameters.The authors believe this study will permit engineers and state agencies to understand this prediction model’s efficacy better,resulting in a more resilient approach to designing large-diameter helical piles for the compressive load.
