Prediction of landslide deep displacement using improved genetic algorithm based on time series analysis

The change of landslide deep displacement due to excavation, reinforcement or rainfall is regarded as a time series. Predicting landslide deformation is a typical nonlinear optimization problem. This paper presents an improved genetic evolutionary algorithm with two step search to determine the mode...

Full description

Saved in:
Bibliographic Details
Main Authors: Shaojun Li, Fanzhen Meng, Chengxiang Yang
Format: Conference Proceeding
Language:English
Subjects:
displacement
Displacement measurement
improved genetic algorithm
landslide
Measurement uncertainty
Monitoring
Optimization
Prediction
Prediction algorithms
Predictive models
time series
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The change of landslide deep displacement due to excavation, reinforcement or rainfall is regarded as a time series. Predicting landslide deformation is a typical nonlinear optimization problem. This paper presents an improved genetic evolutionary algorithm with two step search to determine the model structure and parameters, it is applied to recognize the coefficients and orders of nonlinear polynomials model given by displacement time series analysis. On the basis of a practical engineering, results indicates that the predicted displacement is in good accordance with the monitoring data, the improved intelligent method is found to be reasonable and prospective.
DOI:10.1109/ICSSEM.2011.6081187