A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Modeling non-linear displacement time series of geo-materials using evolutionary support vector machines
Evaluation of the non-linear deformation behaviour of geo-materials is an important aspect of the safety assessment for geotechnical engineering in complex conditions. In line with the implementation of the general development strategy in Western China, there are many large-scale rock engineering projects being built and to be built in complex conditions, such as the Three Gorges Project, the Qinghai-Tibet Rail Road, the South-North water transfer project and the West-East gas transfer project. The deformation behaviour of large-scale rock masses is aggravated by complex rock structures, excavation blasting, reinforcements, seismic forces, tectonic activities, high stresses, high water pressure, temperature gradient, strong geo-chemical reaction and their coupled effects. A novel machine learning method, termed support vector machine (SVM) is presented, to obtain a global optimisation model in conditions of large project dimensions, small sample sizes and non-linearity. A new idea is put forward to combine the SVM with a genetic algorithm, The method has been used in the analysis of the high rock slope of the permanent shiplock of the Three Gorges Project and the horizontal deformation at depth in the Bachimen landslide in Fujian Province. The 92 non-linear SVMs in total were constructed with their kernel functions and the parameters were recognised using a genetic algorithm. The results indicate that the established SVMs can appropriately describe the evolutionary law of deformation of geo-materials at depth and provide predictions for the future 6-10 time steps with acceptable accuracy and confidence.
Modeling non-linear displacement time series of geo-materials using evolutionary support vector machines
Evaluation of the non-linear deformation behaviour of geo-materials is an important aspect of the safety assessment for geotechnical engineering in complex conditions. In line with the implementation of the general development strategy in Western China, there are many large-scale rock engineering projects being built and to be built in complex conditions, such as the Three Gorges Project, the Qinghai-Tibet Rail Road, the South-North water transfer project and the West-East gas transfer project. The deformation behaviour of large-scale rock masses is aggravated by complex rock structures, excavation blasting, reinforcements, seismic forces, tectonic activities, high stresses, high water pressure, temperature gradient, strong geo-chemical reaction and their coupled effects. A novel machine learning method, termed support vector machine (SVM) is presented, to obtain a global optimisation model in conditions of large project dimensions, small sample sizes and non-linearity. A new idea is put forward to combine the SVM with a genetic algorithm, The method has been used in the analysis of the high rock slope of the permanent shiplock of the Three Gorges Project and the horizontal deformation at depth in the Bachimen landslide in Fujian Province. The 92 non-linear SVMs in total were constructed with their kernel functions and the parameters were recognised using a genetic algorithm. The results indicate that the established SVMs can appropriately describe the evolutionary law of deformation of geo-materials at depth and provide predictions for the future 6-10 time steps with acceptable accuracy and confidence.
Modeling non-linear displacement time series of geo-materials using evolutionary support vector machines
Modellierung nichlinearer Verschiebungs-Zeit-Serien von Geomaterialien unter Verwendung evolutionärer Vektormaschinen
Feng, Xia-Ting (author) / Zhao, Hongbo (author) / Li, Shaojun (author)
International Journal of Rock Mechanics and Mining Sciences ; 41 ; 1087-1107
2004
21 Seiten, 26 Bilder, 4 Tabellen, 19 Quellen
Article (Journal)
English
Tunnel , Tunnelbau , Felsbau , Felsmechanik , Verlagerung , Böschung , Gestein , Boden (Erde) , Verformung , China , genetischer Algorithmus
Prediction of Displacement Time Series Based on Support Vector Machines-Markov Chain
| British Library Conference Proceedings | 2014
Evolutionary Support Vector Machines for Transient Stability Monitoring
| Springer Verlag | 2012
Bus Arrival Time Prediction Using Support Vector Machines
| British Library Online Contents | 2006
| British Library Online Contents | 2012