Settlement Prediction Under Linearly Loading Condition

Mei, Guoxiong; Zhao, Xin; Wang, Zhaoyu

doi:10.1080/1064119x.2013.797061

Cited by 2 publications

(2 citation statements)

References 16 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They carried out many experimental studies on Kaolin clay, Hong Kong marine deposit clay, and Fukakusa clay, and all experiments achieved good prediction results. Mei et al [15] started with the relationship between time and settlement, and mathematically proved that the settlement curve under the linear load applied to construction and embankment engineering is an "S" shape. On this basis, a new settlement prediction model called 'Poison model', provides an effective predictive study of building and surface settlement.…”

Section: Related Workmentioning

confidence: 99%

Tunnel Surface Settlement Forecasting with Ensemble Learning

Yan

Dai

et al. 2019

Sustainability

View full text Add to dashboard Cite

Ground surface settlement forecasting in the process of tunnel construction is one of the most important techniques towards sustainable city development and preventing serious damages, such as landscape collapse. It is evident that modern artificial intelligence (AI) models, such as artificial neural network, extreme learning machine, and support vector regression, are capable of providing reliable forecasting results for tunnel surface settlement. However, two limitations exist for the current forecasting techniques. First, the data provided by the construction company are usually univariate (i.e., containing only the settlement data). Second, the demand of tunnel surface settlement is immediate after the construction process begins. The number of training data samples is limited. Targeting at the above two limitations, in this study, a novel ensemble machine learning model is proposed to forecast tunnel surface settlement using univariate short period of real-world tunnel settlement data. The proposed Adaboost.RT framework fully utilizes existing data points with three base machine learning models and iteratively updates hyperparameters using current surface point locations. Experimental results show that compared with existing machine learning techniques and algorithms, the proposed ensemble learning method provides a higher prediction accuracy with acceptable computational efficiency.

show abstract

Section: Related Workmentioning

confidence: 99%

Tunnel Surface Settlement Forecasting with Ensemble Learning

Yan

Dai

et al. 2019

Sustainability

View full text Add to dashboard Cite

show abstract

“…The methods used to predict the settlement include theoretical estimations based on the soil consolidation theory [7] and curve-fitting or prediction models based on deformation measurements [8]. The application of the former is limited by the few samples used and…”

Section: Introductionmentioning

confidence: 99%

Settlement Prediction of Reclaimed Coastal Airports with InSAR Observation: A Case Study of the Xiamen Xiang’an International Airport, China

Xiong

Deng²,

Feng

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Many coastal cities reclaim land from the sea to meet the rapidly growing demand for land caused by population growth and economic development. Settlement in reclaimed land may delay construction and even damage infrastructures, so accurately predicting the settlement over reclaimed areas is important. However, the limited settlement observation and ambiguous final settlement estimation affect accurate settlement prediction in traditional methods. This study proposes a new strategy to solve these problems by using the Multitemporal Interferometric Synthetic Aperture Radar (MT-InSAR) method and takes the Xiamen Xiang’an International Airport, built on reclaimed land, as an example. The MT-InSAR is adopted to process the Sentinel-1 images to obtain the settlement history of the study area. The results show that settlement mainly occurs in the reclaimed areas, with the maximum average settlement rate exceeding 40 mm/y. We use the statistical properties of curve fitting to choose the best curve model from several candidate curve models to predict the settlement time series. The Asaoka method is used to identify the critical state between settlement and stability. We predict the consolidation time of the whole study area and reveal that the deformation rate is positively correlated with the consolidation time. The maximum remaining settlement time is over ten years since 24 December 2019. Therefore, manual compaction operations can be carried out to speed up settlement in the areas that need a long time to consolidate. The proposed method can be used to predict the settlement of similar reclaimed areas, and the predicted results can provide a reference for engineering construction.

show abstract

Settlement Prediction Under Linearly Loading Condition

Cited by 2 publications

References 16 publications

Tunnel Surface Settlement Forecasting with Ensemble Learning

Tunnel Surface Settlement Forecasting with Ensemble Learning

Settlement Prediction of Reclaimed Coastal Airports with InSAR Observation: A Case Study of the Xiamen Xiang’an International Airport, China

Contact Info

Product

Resources

About