Abstract
Data-driven methods have recently shown their potential in engineering problems. In this paper, a data-driven model is proposed and tested for 2D granular column collapse, a typical problem involving flow-like behavior of granular material. Although many theoretical and numerical models have been developed to investigate granular flows, data-driven methods have yet to be explored. This model can predict granular flows based on the sequential relations over time with data collected from numerical solutions. Two frameworks, a Lagrangian framework and an Eulerian framework, are proposed to give rules for collecting data, and radial basis function networks are used to infer the sequential relations. It is shown that the data-driven model gives reasonable predictions compared to results obtained through direct solution. When the size of data in both frameworks are close, the performance in the Eulerian framework is better, especially for predicting states of columns with different geometric parameters. A sensitivity analysis to explore the influence of time increment and grid spacing is also conducted.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 79-88 |
| Number of pages | 10 |
| Journal | Geotechnical Special Publication |
| Volume | 2021-November |
| Issue number | GSP 330 |
| DOIs | |
| State | Published - 2021 |
| Event | Geo-Extreme 2021: Infrastructure Resilience, Big Data, and Risk - Savannah, Georgia Duration: Nov 7 2021 → Nov 10 2021 |
Funding
acknowledge the support of National Science -Kvina Power Company for sharing information. This study is supported by an NSERC (file no. 505755 - 16) Engage Grant held by Jan Adamowski. The GCM -based AMPs were provided by Pablo Jaramillo. We also thank Mr. Alain Charron for his support of this project and provision of hourly precipitation data. The authors are grateful for the financial support provided by the Ministry of Science and Technology (MOST) Shackleton Program through Grant No. MOST108 -2638 -E-008 -001 -MY2 (Principal Investigator: Dr. Hsein Juang). The authors also wish to thank the Central Geological Survey of Taiwan for sponsoring the airborne LiDAR survey in the study area. Finally, but not least, we also want to thank Dr. Yu-Chen Lu for his assistance in reviewing the MCS results and the manuscript. This research was partly funded by Prince Sultan University with a grant number of PSU - CE-SEED-11, 2020. Also, it is supported by the Structures and Material (SM) Re& search Lab of Prince Sultan University. In response to Hurricane Katrina, a multi -year study was performed for the US Department of Homeland Security to improve disaster recovery from flooding by way of emergency paving materials. This work was followed by several years of field aging research funded by the Mississippi Department of Transportation and supported by private industry. Chemical warm mix technologies were incorporated in all o f this work, and this paper assesses data collected over several years to assess the resiliency of paving materials containing chemical additives when they are initially used in challenging conditions such as emergency paving requiring very long haul times. This paper showed asphalt is a resilient material that should be part of conversations on how to respond to extreme events such as hurricanes or other natural disasters. Chemical warm mix technologies can simultaneously facilitate longer haul distances a nd keep the residual material less crack prone for service over time. The authors acknolw edge the support from the Research Grants Council of the Hong Kong SAR (No. C6012 -15G and No. 16206217). The authors would like to acknowledge Dr. Binod Tiwari and Jesse Bennett for training and technical assistance with the laboratory equipment. The authors would also like to thank Boral Resources and Hejintao Huang for their assistance in characterizing the brushfire ashes. This work was performed in part at the Georgia Tech Institute for Electronics and Nanotechnology, a member of the National Nanotechnology Coordinated Infrastructure, which is supported by the National Science Foundation (Grant ECCS -154217 4).
ASJC Scopus subject areas
- Civil and Structural Engineering
- Architecture
- Building and Construction
- Geotechnical Engineering and Engineering Geology