Deformation prediction of tunnel surrounding rock mass using CPSO-SVM model

Abstract

A new method integrating support vector machine (SVM), particle swarm optimization (PSO) and chaotic mapping (CPSO-SVM) was proposed to predict the deformation of tunnel surrounding rock mass. Since chaotic mapping was featured by certainty, ergodicity and stochastic property, it was employed to improve the convergence rate and resulting precision of PSO. The chaotic PSO was adopted in the optimization of the appropriate SVM parameters, such as kernel function and training parameters, improving substantially the generalization ability of SVM. And finally, the integrating method was applied to predict the convergence deformation of the Xiakeng tunnel in China. The results indicate that the proposed method can describe the relationship of deformation time series well and is proved to be more efficient.

Keywords

deformation prediction / tunnel / chaotic mapping / particle swarm optimization / support vector machine

References

[1] KontogianniV. A., StirosS. C.. Predictions and observations of convergence in shallow tunnels: Case histories in Greece[J]. Engineering Geology. 2002, 63: 333-345

[2] FENG X T, HUDSON J A. Rock engineering design [M]. CRC Press, 2011.

[3] JiaoY. Y., FanS. C., ZhaoJ.. Numerical investigation of joint effect on shock wave propagation in jointed rock masses[J]. Journal of Testing and Evaluation. 2005, 33(3): 197-203

[4] BrownE. T., BrayJ. W., LadanyiB., HoekE.. Ground response curves for rock tunnels[J]. Journal of Geotechnical Engineering, ASCE. 1983, 109(1): 15-39

[5] LiW. X., LiH. N.. Fuzzy system models (FSMs) for analysis of rock mass displacement caused by underground mining in soft rock strata[J]. Expert Systems with Applications. 2009, 36(3): 4637-4645

[6] HuangL. C., XuZ. S., PengL. M.. Deformation prediction in soft wall rock tunnel based on the equal-dimension gray filling model[J]. Journal of Railway Science and Engineering. 2009, 6(6): 13-17

[7] SuwansawatS., EinsteinH. H.. Artificial neural networks for predicting the maximum surface settlement caused by EPB shield tunneling[J]. Tunnelling and Underground Space Technology. 2006, 21(2): 133-150

[8] ShiJ., OrtigaoJ. A. R., BaiJ. J.. Modular neural networks for predicting settlements during tunneling[J]. Journal of Geotechnical and Geoenviroment Engineering. 1998, 124(5): 389-395

[9] KimC. Y., BaeG. J., HongS. W., et al. . Neural network based prediction of ground surface settlements due to tunneling[J]. Computers and Geotechnics. 2001, 28: 517-547

[10] NeaupaneK. M., AdhikariN. R.. Prediction of tunneling-induced ground movement with the multi-layer perceptron[J]. Tunnelling and Underground Space Technology. 2006, 21: 151-159

[11] FengX. T., ZhangZ. Q., ShengQ.. Estimating mechanical rock mass parameters relating to the Three Gorges Project permanent shiplock using an intelligent displacement back analysis method[J]. International Journal of Rock Mechanics and Mining Sciences. 2000, 37(7): 1039-1054

[12] FengX. T., ZhaoH. B., LiS. J.. Modeling non-linear displacement time series of geo-materials using evolutionary support vector machines[J]. International Journal of Rock Mechanics and Mining Sciences. 2004, 41(7): 1087-1107

[13] ZhaoH. B., RuZ. L., YinS. D.. Updated support vector machine for seismic liquefaction evaluation based on the penetration tests[J]. Marine Georesources & Geotechnology. 2007, 25(3): 209-220

[14] AnthonyT. C. G., GohS. H.. Support vector machines: Their use in geotechnical engineering as illustrated using seismic liquefaction data[J]. Computers and Geotechnics. 2007, 34(5): 410-421

[15] LiS. J., FengX. T., ZhaoH. B., et al. . Forecast analysis of monitoring data for high slopes based on three-dimensional geological information and intelligent algorithm[J]. International Journal of Rock Mechanics and Mining Sciences. 2004, 41(3): 519-520

[16] KennedyJ., EberhartR. C.. Particle swarm optimization [C]. Proceedings of IEEE international conference on neural networks. 1995, Perth, Australia, IEEE Service Center: 1942-1948

[17] ShiY., EberhartR. C.. Empirical study of particle swarm optimization [C]. Proceedings of the Congress on Evolutionary Computation (CEC’ 99), Washington D C, USA. 1999, 3: 1945-1950

[18] VapnikV. N.. The nature of statistical learning theory [M]. 1995, Springer, New York

[19] ShenJ. D., SyauY. R., LeeE. S.. Support vector fuzzy adaptive network in regression analysis[J]. Computers and Mathematics with Applications. 2007, 54: 1353-1366

[20] JingS. T., ZhuY. Q., SongY. X.. Reliability analysis of tunnel structure [M]. 2002, Beijing, Chinese Rail Road Press