입도분석에 기반한 Deep Neural Network를 이용한최대 건조 단위중량 예측 모델 평가
Evaluation of Maximum Dry Unit Weight Prediction Model Using Deep Neural Network Based on Particle Size Analysis
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The compaction properties of the soil change depending on the physical properties, and are also affected by crushing of the particles. Since the particlesize distribution of soil affects the engineering properties of the soil, it is necessary to analyze the material properties to understand the compactioncharacteristics. In this study, the size of each sieve was classified into four in the particle size analysis as a material property, and the compactioncharacteristics were evaluated by multiple regression and maximum dry unit weight. As a result of maximum dry unit weight prediction, multipleregression analysis showed R2 of 0.70 or more, and DNN analysis showed R2 of 0.80 or more. The reliability of the prediction result analyzed byDNN was evaluated higher than that of multiple regression, and the analysis result of DNN-T showed improved prediction results by 1.87% than DNN. The prediction of maximum dry unit weight using particle size distribution seems to be applied to evaluate the compacting state by identifying thematerial characteristics of roads and embankments. In addition, the particle size distribution can be used as a parameter for predicting maximum dryunit weight, and it is expected to be of great help in terms of time and cost of applying it to the compaction state evaluation.
Abstract
The compaction properties of the soil change depending on the physical properties, and are also affected by crushing of the particles. Since the particlesize distribution of soil affects the engineering properties of the soil, it is necessary to analyze the material properties to understand the compactioncharacteristics. In this study, the size of each sieve was classified into four in the particle size analysis as a material property, and the compactioncharacteristics were evaluated by multiple regression and maximum dry unit weight. As a result of maximum dry unit weight prediction, multipleregression analysis showed R2 of 0.70 or more, and DNN analysis showed R2 of 0.80 or more. The reliability of the prediction result analyzed byDNN was evaluated higher than that of multiple regression, and the analysis result of DNN-T showed improved prediction results by 1.87% than DNN. The prediction of maximum dry unit weight using particle size distribution seems to be applied to evaluate the compacting state by identifying thematerial characteristics of roads and embankments. In addition, the particle size distribution can be used as a parameter for predicting maximum dryunit weight, and it is expected to be of great help in terms of time and cost of applying it to the compaction state evaluation.
참고문헌 (37)
- Alawi, M. H., "Prediction of California bearing ratio of subbase layer using multiple linear regression models", Road Materials and Pavement Design, 14(1), pp.211~219 (2013)[DOI]
- Baek, J. W., "Context deep neural network model for predicting depression risk using multiple regression", IEEE Access, 8, pp.18171~18181 (2020)[DOI]
- 백승환, "입도분포와 다짐에너지의 변화에 따른 흙의 다짐 및 투수특성", 농업생명과학연구, 41(2), pp.45~50 (2007), 농업생명과학연구원
- Bengio, Y., "Representation learning: a review and new perspectives", IEEE Transactions on Patter Analysis and Machine Intelligence, 35(8), pp.1798~1828 (2014)[DOI]
- Bera, A., "Regression model for prediction of optimum moisture content and maximum dry unit weight of fine grained soil", International Journal of Geotechnical Engineering, 5, pp.297~305 (2011)[DOI]
- Chen, M. L., "Physical and compaction properties of granular materials with artificial grading behind the particle size distributions", Advances in Materials Science and Engineering, 2018, pp.1~20 (2018)[DOI]
- Chinkulkijniwat, A., "Compaction characteristics of non-gravel and gravelly soils using a small compaction apparatus", Journal of ASTM International, 7(7), pp.1~15 (2010)
- 조상호, "단계적 회귀분석과 인공신경망 모형을 이용한 광양항 석탄·철광석 물동량 예측력 비교 분석", 한국항해항만학회지, 44(3), pp.187~194 (2020), 한국항해항만학회
- Ding, Y., "Prediction and evaluation of grain size-dependent maximum dry density for gravelly soil", International Journal of Geomechanics, 20(9), pp.04020153~ (2020)[DOI]
- Elgibaly, A. A., "A new correlation for predicting hydrate formation conditions for various gas mixtures and inhibitors", Fluid Phase Equilibria, 152, pp.23~42 (1998)[DOI]
- Groupe, D., "Principle of artificial neural networks" (2007), World Scientific Publishing Co
- Gurtug, Y., "Compaction behaviour and prediction of its characteristics of fine grained soils with particular reference to compaction energy", Soil and Foundation, 44(5), pp.27~36 (2004)
- Hertäg, L., "Learning prediction error neurons in a canonical interneuron circuit", Elife, 9, pp.e57541~ (2020)[DOI]
- Johnson, A. W., "Factors that influence field compaction of soils", Highway Research Board Bulletin, 272, pp.206~ (1960)[DOI]
- Keijser, J., "Optimizing interneuron circuits for compartment-specific feedback inhibition", PLoS Computational Biology, 18(4), pp.e1009933~ (2022)
- 김광수, "상관성 회귀모형에 대한 비교연구", Journal of The Korean Data Analysis Society, 11(6), pp.3319~3329 (2009), 한국자료분석학회
- Kim, M. H., "Evaluation of permeability coefficient of agriculture reservoirs using deep neural network", KSAE Annual Conference (2022)
- 김우용, "국내 저수지 축조 재료특성 분류를 위한 실험적 연구", 한국방재학회논문집, 17(2), pp.219~230 (2017), 한국방재학회[DOI]
- Kim Y. G., "Correlation analysis and optimization between parameters using with deep learning", Annual Conference of Korea Information Processing Society, 22(2), pp.1285~1288 (2015)
- Kim, Y. S., "The engineering characteristics of weathered sedimentary rock soils - In Taegu and Kyungpook areas -", Journal of the Korean Geotechnical Society, 11(4), pp.63~74 (1995)
- 이충원, "다짐시공이 불량한 증고 저수지 제체의 침투 및 동적거동 해석", 한국농공학회논문집, 57(4), pp.85~99 (2015), 한국농공학회
- 이정협, "영하에서의 다짐에너지에 따른 다짐 효과 평가", 한국지반환경공학회 논문집, 16(8), pp.13~20 (2015), 한국지반환경공학회[DOI]
- Lumay, G., "Compaction of anisotropic granular materials: experiments and simulations", Physical Review E, 70(1), pp.051315-1~051315-5 (2004)[DOI]
- Myers, R. H., "Classical and modern regression with applications" (1990), Duxbury Press
- 노수각, "분열프랙탈을 이용한 다짐에너지의 영향 분석 - 입도와 투수특성을 중심으로 -", 한국농공학회논문집, 48(6), pp.59~67 (2006), 한국농공학회
- Ma, Z. Y., "Numerical study of the dynamic compaction of gravel soil ground using the discrete element method", Granular Matter, 16(6), pp.881~889 (2014)
- Pandian, N. S., "Reexamination of compaction characteristics of fine grained soils", Geotechnique, 47(2), pp.363~366 (1997)
- Park, H. I., "Development of neural network model to estimate the permeability coefficient of soils", Marine Georesources and Geotechnology, 29, pp.267~278 (2011)[DOI]
- 박성완, "입도분포를 고려한 다짐된 지반재료의 역학적 거동 평가", 한국지반공학회논문집, 32(1), pp.45~53 (2016), 한국지반공학회[DOI]
- 박종화, "10% 간극곡선을 이용한 다짐도 평가에 관한 연구", 석사, 토목공학, pp.2010
- 박준모, "비선형 회귀분석을 이용한 쇄석다짐말뚝의 극한지지력 예측", 한국해안·해양공학회논문집, 25(2), pp.112~121 (2013), 한국해안,해양공학회[DOI]
- 박춘식, "다양한 지반의 물리적 특성과 다짐특성 상관성", 한국지반환경공학회 논문집, 18(1), pp.23~29 (2017), 한국지반환경공학회[DOI]
- Perfect, E., "Applications of fractals in soil and tillage research: A review", Soil and Tillage Research, 36(1-2), pp.1~20 (1995)
- Ring III, G. W., "Correlation of compaction and classification test data", Highway Research Board Bulletin, 325, pp.577~587 (1962)[DOI]
- Sezer, A., "Estimation of the permeability of granular soils using neuro-fuzzy system", AIAI-2009 Workshops Proceedings (2009)
- Yu, C., "A risk evaluation method of agricultural infrastructures with climate change using hybridized fuzzy logic and neural network theory", KSAE Annual Conference (2002)
- 윤태영, "다짐밀도 예측을 위한 구형입자를 활용한 DEM의 적용성 평가", 한국도로학회논문집, 20(6), pp.21~30 (2018), 한국도로학회