딥러닝을 이용한 중간말뚝이 있는 지하구조물의 슬래브 모멘트 예측
Prediction of Slab Moment in Underground Structures with Intermediate Piles Using Deep Learning
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study focused on analyzing the impact of residual intermediate piles on the bending moments of underground structures' slabs. Using DNN, the research developed a model to predict slab moments under various conditions. The presence of intermediate piles increased moment values, varying with soil strength. From 216 conditions, optimal hyperparameters were identified: dropout ratio 0.1, 2 hidden layers, 384 nodes, and RMSE 0.0482. The worst conditions had a dropout ratio of 0.2, 6 hidden layers, 384 nodes, and RMSE 0.325. The optimized model accurately matched actual slab moment values.
Abstract
This study focused on analyzing the impact of residual intermediate piles on the bending moments of underground structures' slabs. Using DNN, the research developed a model to predict slab moments under various conditions. The presence of intermediate piles increased moment values, varying with soil strength. From 216 conditions, optimal hyperparameters were identified: dropout ratio 0.1, 2 hidden layers, 384 nodes, and RMSE 0.0482. The worst conditions had a dropout ratio of 0.2, 6 hidden layers, 384 nodes, and RMSE 0.325. The optimized model accurately matched actual slab moment values.
참고문헌 (8)
- Nikkei Construction, "Learning from defective structure", pp.100~120 (2005), Nikkei Business Publications
- 변형석, "지중 구조물의 단면력에 미치는 지반반력계수의 영향", ~ (2013)
- 박재원, "대규모 단층파쇄대에서의 터널변형특성에 관한 연구", ~ (2016)
- Bowles, J. E., "Foundation analysis and design" (1996), McGraw Hill Book Co
- Kim, D. S., "A study on the effect of center piles of temporary structures on the slab base plate of underground structures", pp.2024
- Ha, J., "A development of road crack detection system using deep learning-based segmentation and object detection", The Journal of Society for e-Business Studies, 26(1), pp.93~106 (2021)
- Lee, S. Y., "Bolt-loosening detection using vision-based deep learning algorithm and image processing method", Journal of the Computational Structural Engineering Institute of Korea, 32(4), pp.265~272 (2019)
- Chae, J., "A study on the pipe position estimation in GPR images using deep learning based convolutional neural network", Journal of Internet Computing and Services, 20(4), pp.39~46 (2019)