<<
[an error occurred while processing this directive] | [an error occurred while processing this directive] >>
Prediction Model of TBM Advance Rate Based on Relevance Vector Machine
(1 Guangxi Key Laboratory of Geomechanics and Geotechnical Engineering, Guilin 541004; 2 School of Civil andArchitecture Engineering, Guilin University of Technology,Guilin 541004)
Abstract TBM has been widely used in tunnel construction, especially the long distance tunnel attributed to the advantages of strong safety, high construction efficiency and so on. The advance rate of TBM is affected by various factors which have complex correlation besides high uncertainty, and so it is difficult to establish a precise model for predicting the advance rate.A relevance vector machine based TBM advance rate prediction model is proposed by which it can build a nonlinear mapping relationship between various factors and advance rate through learning the samples, precisely predict the samples with only known influential factors. The results obtained from the TBM advance rate prediction show that this model has the advantages of high precision, easy operation and small discreteness.
Abstract：
TBM has been widely used in tunnel construction, especially the long distance tunnel attributed to the advantages of strong safety, high construction efficiency and so on. The advance rate of TBM is affected by various factors which have complex correlation besides high uncertainty, and so it is difficult to establish a precise model for predicting the advance rate.A relevance vector machine based TBM advance rate prediction model is proposed by which it can build a nonlinear mapping relationship between various factors and advance rate through learning the samples, precisely predict the samples with only known influential factors. The results obtained from the TBM advance rate prediction show that this model has the advantages of high precision, easy operation and small discreteness.
ZHANG Yan1,
2 WANG Wei2 DENG Xueqin2
.Prediction Model of TBM Advance Rate Based on Relevance Vector Machine[J] MODERN TUNNELLING TECHNOLOGY, 2020,V57(3): 108-114
2020, Vol. 57 