Application of LS-SVM to Prediction of Bearing Capacity of Cement-Flyash-Gravel Pile Composite Foundation

2013 ◽  
Vol 438-439 ◽  
pp. 1399-1403
Author(s):  
Wei Ding ◽  
Qing Liu ◽  
Kang Kang Sun ◽  
Feng Tao Sui
Keyword(s):  
Bearing Capacity ◽  
Great Influence ◽  
Composite Foundation ◽  
Learning Ability ◽  
Support Vector ◽  
Data Prediction ◽  
Svm Model ◽  
Cfg Pile Composite Foundation ◽  
Gravel Pile ◽  
Cfg Pile

There are a lot of factors that influence the bearing capacity of composite foundation, and the relationship between them is complex and nonlinear. Based on study of main factors that have great influence on bearing capacity of cement-flyash-gravel (CFG) pile composite foundation, the least squares support vector machine (LS-SVM) model of bearing capacity of composite foundation was established. The results show that the model has excellent learning ability and generalization and can provide accurate data prediction only with fewer observed sample. It is proved that the new method is a promising method for the determination of bearing capacity of CFG pile and other rigid piles composite foundation.

A Prediction Method of Bearing Capacity of CFG Pile Composite Foundation Based on Support Vector Machine

2013 ◽  
Vol 438-439 ◽  
pp. 1419-1422
Author(s):  
Qing Liu ◽  
Wei Ding ◽  
Kai Kang ◽  
Xiao Han ◽  
Bing Yu Wang
Keyword(s):  
Support Vector Machine ◽  
Theoretical Analysis ◽  
Bearing Capacity ◽  
Test Data ◽  
Prediction Method ◽  
Composite Foundation ◽  
Support Vector ◽  
Cfg Pile Composite Foundation ◽  
Set Up ◽  
Cfg Pile

A prediction method of bearing capacity of CFG pile composite foundation was presented based on that support vector machine and corresponding prediction model was set up. To obtain the model coefficients, 18 groups of test data of CFG pile composite foundation were trained, the training value conforms well to the test value. Then the model was used to predict another 4 groups of test data. The result showed that the prediction value was close to the test value. The theoretical analysis and practical example indicated that the prediction method of bearing capacity of CFG pile composite foundation based on support vector machine is accurate and reliable.

The Settlement Analysis of the Cement Fly-Ash Gravel Pile Composite Foundation of Baotou

2014 ◽  
Vol 580-583 ◽  
pp. 518-523
Author(s):  
Juan Li ◽  
Yao Xu ◽  
Jun Yin
Keyword(s):  
Fly Ash ◽  
Composite Foundation ◽  
Settlement Calculation ◽  
Practical Engineering ◽  
Cfg Pile Composite Foundation ◽  
Modified Formula ◽  
Gravel Pile ◽  
Final Settlement ◽  
Settlement Analysis ◽  
Cfg Pile

This paper analyzes the causes of larger differences of final settlement calculated value of cement fly-ash gravel pile (CFG pile) composite foundation of Baotou with actual observed result of it. On the basis of analysis on a number of practical engineering data of Baotou, we modify the settlement formula of the CFG pile composite foundation and gain the modified coefficient applied to the settlement calculation of the CFG pile composite foundation of Baotou. The modified formula and coefficient proposed in this paper have a positive effect on the accurate settlement calculation of puting forward a more accurate correction formula and coefficient of the calculation of the CFG pile composite foundation of Baotou.

Analysis on Bearing Capacity of CFG Pile Composite Foundation in Baotou

2013 ◽  
Vol 353-356 ◽  
pp. 337-340
Author(s):  
Ying Hao Wang ◽  
Yu Qin Feng ◽  
Shuo Li
Keyword(s):  
Bearing Capacity ◽  
Sandy Soil ◽  
Inner Mongolia ◽  
Composite Foundation ◽  
Engineering Project ◽  
Silty Soil ◽  
Practical Engineering ◽  
Soil Foundation ◽  
Cfg Pile Composite Foundation ◽  
Cfg Pile

By uniting composite foundation with CFG pile composite foundation for a practical engineering project in Baotou, the bearing capacity of CFG pile in sandy soil and silty soil foundation were analyzed. The conclusion can be applied to the similar projects in the region of Inner Mongolia.

Studies on the Residual Settlement of CFG Pile Composite Foundation of the Wuhan-Guangzhou High Speed Railway

2012 ◽  
Vol 178-181 ◽  
pp. 1590-1595
Author(s):  
Feng Zhang ◽  
Zhao Yi Xu ◽  
Zhi Yi Li
Keyword(s):  
High Speed ◽  
Soil Layer ◽  
Composite Foundation ◽  
High Speed Railway ◽  
Actual Observation ◽  
Permanent Load ◽  
Cfg Pile Composite Foundation ◽  
Gravel Pile ◽  
Pile Length ◽  
Cfg Pile

Wuhan-Guangzhou passenger special line is the most important backbone of China high speed railway net. The line span is 968 km, among of them; roadbed is 388 km, occupied 40.1% of the total line. Due to the rigorous residual settlement of the roadbed, the CFG (Cement Flayash Gravel) pile is used as the composite foundation to enforce the intensity of roadbed and reduce the post-settlement. The paper studies on CFG pile composite foundation at the Wuhan experimental section, using the finite element numerical simulate the interaction of the pile and pile surrounding soil under the permanent load conditions. The results show that the stimulation model has the more accordance with the actual observation results. The residual settlement comes from the soil layer is bigger than the pile length.

CPI Big Data Prediction Based on Wavelet Twin Support Vector Machine

2020 ◽  
pp. 2159013
Author(s):  
Yiqing Fan ◽  
Zhihui Sun
Keyword(s):  
Support Vector Machine ◽  
Big Data ◽  
Consumer Price Index ◽  
Low Frequency ◽  
Prediction Method ◽  
Twin Support Vector Machine ◽  
Support Vector ◽  
Reconstruction Method ◽  
Data Prediction ◽  
Svm Model

In order to effectively improve the accuracy of Consumer Price Index (CPI) prediction so as to more truly reflect the overall level of the country’s macroeconomic situation, a CPI big data prediction method based on wavelet twin support vector machine (SVM) is proposed. First, the historical CPI data are decomposed into high-frequency part and low-frequency part by wavelet transform. Then a more advanced twin SVM is used to build a prediction model to obtain two kinds of prediction results. Finally, the wavelet reconstruction method is used to fuse the two kinds of prediction results to obtain the final CPI prediction results. The wavelet twin SVM model is used to fit and predict CPI index. Experimental results show that compared with the similar prediction methods, the proposed prediction method has higher fitting accuracy and smaller root mean square error.

Sign in / Sign up

Export Citation Format

Share Document