Research for Settlement Prediction on the Based of Neural Network and ADINA

2009 ◽  
Author(s):  
Meng Deguang ◽  
Zhu Tianzhi ◽  
Li Bingxin ◽  
Dong Yanying
Keyword(s):  
Neural Network ◽  
Settlement Prediction

Settlement Prediction of Buildings Based on BP Neural Network

2014 ◽  
Vol 602-605 ◽  
pp. 3232-3234
Author(s):  
Jian Cheng Li
Keyword(s):  
Neural Network ◽  
Seismic Performance ◽  
Network Model ◽  
Neural Network Model ◽  
Bp Neural Network ◽  
Existing Buildings ◽  
Large Area ◽  
Settlement Prediction ◽  
Prediction Result ◽  
Study Results

At present, the traditional neural network model have been used in settlement prediction of buildings area, but there are some limitations. In this paper, BP neural network is applied in the settlement prediction of buildings and the prediction result is compared with the measured values. The results show that: the use of BP neural network to predict the settlement of existing buildings is feasible. The study results can provide a reference for the anti-seismic performance census of existing large area buildings.

scholarly journals Application of the WNN-Based SCG Optimization Algorithm for Predicting Soft Soil Foundation Engineering Settlement

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Guihua Li ◽  
Chenyu Han ◽  
Hong Mei ◽  
Shuai Chen
Keyword(s):  
Neural Network ◽  
Soft Soil ◽  
Wavelet Neural Network ◽  
Foundation Engineering ◽  
Settlement Prediction ◽  
Training Techniques ◽  
Soft Foundation ◽  
Soil Foundation ◽  
Soft Soil Foundation ◽  
Hidden Layer

Settlement prediction in soft soil foundation engineering is a newer technique. Predicting soft soil settling has long been one of the most challenging techniques due to difficulties in soft soil engineering. To overcome these challenges, the wavelet neural network (WNN) is mostly used. So, after assessing its estimate performance, two elements, early parameter selection and system training techniques, are chosen to optimize the traditional WNN difficulties of readily convergence to the local infinitesimal point, low speed, and poor approximation performance. The number of hidden layer nodes is determined using a self-adaptive adjustment technique. The wavelet neural network (WNN) is coupled with the scaled conjugate gradient (SCG) to increase the feasibility and accuracy of the soft fundamental engineering settlement prediction model, and a better wavelet network for the soft ground engineering settlement prediction is suggested in this paper. Furthermore, we have proposed the technique of locating the early parameters based on autocorrelation. The settlement of three types of traditional soft foundation engineering, including metro tunnels, highways, and high-rise building foundations, has been predicted using our proposed model. The findings revealed that the model is superior to the backpropagation neural network and the standard WNN for solving problems of approximation performance. As a result, the model is acceptable for soft foundation engineering settlement prediction and has substantial project referential value.

scholarly journals Forecast of Highway Subgrade Settlement Based on Improved BP Neural Network

2020 ◽  
pp. 118
Author(s):  
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Bp Neural Network ◽  
Average Error ◽  
Good Prediction ◽  
Settlement Prediction ◽  
Training Samples ◽  
Good Prediction Accuracy ◽  
Neural Network Prediction ◽  
Network Prediction

In order to improve the feasibility and accuracy of the roadbed settlement prediction model, the factor analysis method is combined with the BP neural network method, and an improved BP neural network roadbed settlement prediction model is proposed. Select example data to test the improved BP neural network roadbed settlement prediction model. The test results: The relative average error of the 10 sets of training samples’ predicted and actual roadbed settlements was 4.287%, and the roads of five predicted samples The relative error of subgrade settlement is 1.79%, 1.93%, 6.62%, 7.19%, 4.05%, all less than 10%, which proves that the improved BP neural network prediction model has good prediction accuracy.

The Application of BP Neural Network in Settlement Prediction of Highway Soft Foundation

2011 ◽  
Vol 250-253 ◽  
pp. 3440-3443
Author(s):  
Yi Xue ◽  
Zheng Zheng Cao ◽  
Shan Liu
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Bp Neural Network ◽  
Linear Mapping ◽  
Point Method ◽  
Learning Ability ◽  
Settlement Prediction ◽  
Soft Foundation ◽  
Bp Neural Network Model

In view of the settlement of highway soft foundation, the paper proposes a method to predict soft foundation settlement based on BP neural network model, taking advantage of the strong non-linear mapping and learning ability of BP neural network. Then it is compared with the three-point method, obtaining some useful conclusions. Since the BP neural network model is directly based on real samples, it could avoid the mistakes due to factitiousness in the three-point method. It is proved that the BP neural network model is accurate and the settlement has least error.

Sign in / Sign up

Export Citation Format

Share Document